diff options
| author | Len Brown <len.brown@intel.com> | 2010-08-15 09:06:31 +0400 |
|---|---|---|
| committer | Len Brown <len.brown@intel.com> | 2010-08-15 09:06:31 +0400 |
| commit | 95ee46aa8698f2000647dfb362400fadbb5807cf (patch) | |
| tree | e5a05c7297f997e191c73091934e42e3195c0e40 /arch/x86 | |
| parent | cfa806f059801dbe7e435745eb2e187c8bfe1e7f (diff) | |
| parent | 92fa5bd9a946b6e7aab6764e7312e4e3d9bed295 (diff) | |
| download | linux-95ee46aa8698f2000647dfb362400fadbb5807cf.tar.xz | |
Merge branch 'linus' into release
Conflicts:
drivers/acpi/debug.c
Signed-off-by: Len Brown <len.brown@intel.com>
Diffstat (limited to 'arch/x86')
202 files changed, 6510 insertions, 3148 deletions
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index dcb0593b4a66..a84fc34c8f77 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -55,6 +55,7 @@ config X86 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 @@ -72,9 +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 @@ -2046,7 +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 @@ -2062,6 +2060,15 @@ config OLPC 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/boot/Makefile b/arch/x86/boot/Makefile index ec749c2bfdd7..f7cb086b4add 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 98239d2658f2..c7093bd9f2d3 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 a1d35634bce0..6b3b6f708c04 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 fbb47daf2459..0c229551eead 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 000000000000..cb62f786990d --- /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 000000000000..261e81fb9582 --- /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 f543b70ffae2..67a655a39ce4 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 faff0dc9c06a..52f85a196fa0 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 51e240779a44..8f7bef8e9fff 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 000000000000..3f19c81a6203 --- /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/string.c b/arch/x86/boot/compressed/string.c new file mode 100644 index 000000000000..19b3e693cd72 --- /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 5ddabceee124..34d047c98284 100644 --- a/arch/x86/boot/compressed/vmlinux.lds.S +++ b/arch/x86/boot/compressed/vmlinux.lds.S @@ -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 000000000000..25e13403193c --- /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 000000000000..030f4b93e255 --- /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 140172b895bd..40358c8905be 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 50e47cdbdddd..cdac91ca55d3 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 f94b7a0c2abf..3cbc4058dd26 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 01ec69c901c7..def2451f46ae 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/configs/i386_defconfig b/arch/x86/configs/i386_defconfig index d28fad19654a..e3a32431ca1e 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 6c86acd847a4..4251f8372050 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/ia32/ia32entry.S b/arch/x86/ia32/ia32entry.S index e790bc1fbfa3..b86feabed69b 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 626be156d88d..849813f398e7 100644 --- a/arch/x86/ia32/sys_ia32.c +++ b/arch/x86/ia32/sys_ia32.c @@ -51,7 +51,7 @@ #define AA(__x) ((unsigned long)(__x)) -asmlinkage long sys32_truncate64(char __user *filename, +asmlinkage long sys32_truncate64(const char __user *filename, unsigned long offset_low, unsigned long offset_high) { @@ -96,7 +96,7 @@ static int cp_stat64(struct stat64 __user *ubuf, struct kstat *stat) return 0; } -asmlinkage long sys32_stat64(char __user *filename, +asmlinkage long sys32_stat64(const char __user *filename, struct stat64 __user *statbuf) { struct kstat stat; @@ -107,7 +107,7 @@ asmlinkage long sys32_stat64(char __user *filename, return ret; } -asmlinkage long sys32_lstat64(char __user *filename, +asmlinkage long sys32_lstat64(const char __user *filename, struct stat64 __user *statbuf) { struct kstat stat; @@ -126,7 +126,7 @@ asmlinkage long sys32_fstat64(unsigned int fd, struct stat64 __user *statbuf) return ret; } -asmlinkage long sys32_fstatat(unsigned int dfd, char __user *filename, +asmlinkage long sys32_fstatat(unsigned int dfd, const char __user *filename, struct stat64 __user *statbuf, int flag) { struct kstat stat; @@ -408,8 +408,8 @@ asmlinkage long sys32_pread(unsigned int fd, char __user *ubuf, u32 count, ((loff_t)AA(poshi) << 32) | AA(poslo)); } -asmlinkage long sys32_pwrite(unsigned int fd, char __user *ubuf, u32 count, - u32 poslo, u32 poshi) +asmlinkage long sys32_pwrite(unsigned int fd, const char __user *ubuf, + u32 count, u32 poslo, u32 poshi) { return sys_pwrite64(fd, ubuf, count, ((loff_t)AA(poshi) << 32) | AA(poslo)); @@ -449,7 +449,7 @@ asmlinkage long sys32_sendfile(int out_fd, int in_fd, return ret; } -asmlinkage long sys32_execve(char __user *name, compat_uptr_t __user *argv, +asmlinkage long sys32_execve(const char __user *name, compat_uptr_t __user *argv, compat_uptr_t __user *envp, struct pt_regs *regs) { long error; @@ -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 aa2c39d968fc..92091de11113 100644 --- a/arch/x86/include/asm/acpi.h +++ b/arch/x86/include/asm/acpi.h @@ -134,7 +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.h b/arch/x86/include/asm/alternative.h index 03b6bb5394a0..bc6abb7bc7ee 100644 --- a/arch/x86/include/asm/alternative.h +++ b/arch/x86/include/asm/alternative.h @@ -45,10 +45,9 @@ 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" \ diff --git a/arch/x86/include/asm/apb_timer.h b/arch/x86/include/asm/apb_timer.h index c74a2eebe570..a69b1ac9eaf8 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/bootparam.h b/arch/x86/include/asm/bootparam.h index 6be33d83c716..8e6218550e77 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/cmpxchg_32.h b/arch/x86/include/asm/cmpxchg_32.h index 8859e12dd3cf..284a6e8f7ce1 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. * - * 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. + * 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. 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; } @@ -264,8 +246,6 @@ 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; \ @@ -283,20 +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 485ae415faec..423ae58aa020 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 468145914389..781a50b29a49 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 */ @@ -157,22 +159,29 @@ /* * 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__) @@ -194,7 +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)) @@ -291,7 +302,7 @@ extern const char * const x86_power_flags[32]; * patch the target code for additional performance. * */ -static __always_inline __pure bool __static_cpu_has(u8 bit) +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" @@ -300,11 +311,11 @@ static __always_inline __pure bool __static_cpu_has(u8 bit) _ASM_ALIGN "\n" _ASM_PTR "1b\n" _ASM_PTR "0\n" /* no replacement */ - " .byte %P0\n" /* feature bit */ + " .word %P0\n" /* feature bit */ " .byte 2b - 1b\n" /* source len */ " .byte 0\n" /* replacement len */ - " .byte 0xff + 0 - (2b-1b)\n" /* padding */ ".previous\n" + /* skipping size check since replacement size = 0 */ : : "i" (bit) : : t_no); return true; t_no: @@ -318,10 +329,12 @@ static __always_inline __pure bool __static_cpu_has(u8 bit) _ASM_ALIGN "\n" _ASM_PTR "1b\n" _ASM_PTR "3f\n" - " .byte %P1\n" /* feature bit */ + " .word %P1\n" /* feature bit */ " .byte 2b - 1b\n" /* source len */ " .byte 4f - 3f\n" /* replacement len */ - " .byte 0xff + (4f-3f) - (2b-1b)\n" /* padding */ + ".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" @@ -337,7 +350,7 @@ static __always_inline __pure bool __static_cpu_has(u8 bit) ( \ __builtin_constant_p(boot_cpu_has(bit)) ? \ boot_cpu_has(bit) : \ - (__builtin_constant_p(bit) && !((bit) & ~0xff)) ? \ + __builtin_constant_p(bit) ? \ __static_cpu_has(bit) : \ boot_cpu_has(bit) \ ) diff --git a/arch/x86/include/asm/dma-mapping.h b/arch/x86/include/asm/dma-mapping.h index ac91eed21061..d4c419f883a0 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/highmem.h b/arch/x86/include/asm/highmem.h index a726650fc80f..8caac76ac324 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/hw_breakpoint.h b/arch/x86/include/asm/hw_breakpoint.h index 942255310e6a..528a11e8d3e3 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 diff --git a/arch/x86/include/asm/hypervisor.h b/arch/x86/include/asm/hypervisor.h index 70abda7058c8..ff2546ce7178 100644 --- a/arch/x86/include/asm/hypervisor.h +++ b/arch/x86/include/asm/hypervisor.h @@ -45,5 +45,6 @@ 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 c991b3a7b904..a73a8d5a5e69 100644 --- a/arch/x86/include/asm/i387.h +++ b/arch/x86/include/asm/i387.h @@ -31,7 +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; @@ -58,11 +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 */ @@ -127,6 +140,15 @@ 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" @@ -482,6 +504,8 @@ 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/intel_scu_ipc.h b/arch/x86/include/asm/intel_scu_ipc.h index 4470c9ad4a3e..29f66793cc55 100644 --- a/arch/x86/include/asm/intel_scu_ipc.h +++ b/arch/x86/include/asm/intel_scu_ipc.h @@ -1,6 +1,12 @@ #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); @@ -28,20 +34,6 @@ 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); -/* - * Indirect register read - * Can be used when SCCB(System Controller Configuration Block) register - * HRIM(Honor Restricted IPC Messages) is set (bit 23) - */ -int intel_scu_ipc_register_read(u32 addr, u32 *data); - -/* - * Indirect register write - * Can be used when SCCB(System Controller Configuration Block) register - * HRIM(Honor Restricted IPC Messages) is set (bit 23) - */ -int intel_scu_ipc_register_write(u32 addr, u32 data); - /* 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, diff --git a/arch/x86/include/asm/irq_vectors.h b/arch/x86/include/asm/irq_vectors.h index 8767d99c4f64..e2ca30092557 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/kdebug.h b/arch/x86/include/asm/kdebug.h index fa7c0b974761..5bdfca86581b 100644 --- a/arch/x86/include/asm/kdebug.h +++ b/arch/x86/include/asm/kdebug.h @@ -33,5 +33,11 @@ extern void __show_regs(struct pt_regs *regs, int all); extern void show_regs(struct pt_regs *regs); extern unsigned long oops_begin(void); extern void oops_end(unsigned long, struct pt_regs *, int signr); +#ifdef CONFIG_KEXEC +extern int in_crash_kexec; +#else +/* no crash dump is ever in progress if no crash kernel can be kexec'd */ +#define in_crash_kexec 0 +#endif #endif /* _ASM_X86_KDEBUG_H */ diff --git a/arch/x86/include/asm/kgdb.h b/arch/x86/include/asm/kgdb.h index 006da3687cdc..396f5b5fc4d7 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) { diff --git a/arch/x86/include/asm/kvm.h b/arch/x86/include/asm/kvm.h index ff90055c7f0b..4d8dcbdfc120 100644 --- a/arch/x86/include/asm/kvm.h +++ b/arch/x86/include/asm/kvm.h @@ -22,6 +22,8 @@ #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 @@ -299,4 +301,24 @@ struct kvm_debugregs { __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 0b2729bf2070..51cfd730ac5d 100644 --- a/arch/x86/include/asm/kvm_emulate.h +++ b/arch/x86/include/asm/kvm_emulate.h @@ -51,8 +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. @@ -92,6 +94,7 @@ struct x86_emulate_ops { int (*read_emulated)(unsigned long addr, void *val, unsigned int bytes, + unsigned int *error, struct kvm_vcpu *vcpu); /* @@ -104,6 +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); /* @@ -118,6 +122,7 @@ 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, @@ -132,18 +137,26 @@ struct x86_emulate_ops { 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); - void (*set_cr)(int cr, ulong val, struct kvm_vcpu *vcpu); + int (*set_cr)(int cr, ulong val, struct kvm_vcpu *vcpu); int (*cpl)(struct kvm_vcpu *vcpu); - void (*set_rflags)(struct kvm_vcpu *vcpu, unsigned long rflags); + 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 { @@ -186,6 +199,7 @@ struct decode_cache { unsigned long modrm_val; struct fetch_cache fetch; struct read_cache io_read; + struct read_cache mem_read; }; struct x86_emulate_ctxt { @@ -202,6 +216,12 @@ struct x86_emulate_ctxt { 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; }; diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index 76f5483cffec..502e53f999cf 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 @@ -241,7 +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; @@ -301,8 +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; @@ -360,26 +362,11 @@ struct kvm_vcpu_arch { /* 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; @@ -533,6 +520,8 @@ struct kvm_x86_ops { void (*set_supported_cpuid)(u32 func, struct kvm_cpuid_entry2 *entry); + bool (*has_wbinvd_exit)(void); + const struct trace_print_flags *exit_reasons_str; }; @@ -576,7 +565,6 @@ 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); @@ -591,10 +579,7 @@ 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); @@ -602,15 +587,16 @@ 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, 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); @@ -630,12 +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); +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, @@ -664,8 +645,6 @@ void kvm_disable_tdp(void); 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); @@ -719,21 +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 */ diff --git a/arch/x86/include/asm/local64.h b/arch/x86/include/asm/local64.h new file mode 100644 index 000000000000..36c93b5cc239 --- /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 f32a4301c4d4..c62c13cb9788 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 */ diff --git a/arch/x86/include/asm/mrst.h b/arch/x86/include/asm/mrst.h index 451d30e7f62d..16350740edf6 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/msr-index.h b/arch/x86/include/asm/msr-index.h index 8c7ae4318629..986f7790fdb2 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 */ @@ -94,9 +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 @@ -159,8 +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 @@ -224,12 +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 @@ -239,6 +238,19 @@ #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) diff --git a/arch/x86/include/asm/msr.h b/arch/x86/include/asm/msr.h index c5bc4c2d33f5..084ef95274cd 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 93da9c3f3341..932f0f86b4b7 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 000000000000..08fde475cb3b --- /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/page.h b/arch/x86/include/asm/page.h index 625c3f0e741a..8ca82839288a 100644 --- a/arch/x86/include/asm/page.h +++ b/arch/x86/include/asm/page.h @@ -37,6 +37,13 @@ static inline void copy_user_page(void *to, void *from, unsigned long vaddr, #define __pa_nodebug(x) __phys_addr_nodebug((unsigned long)(x)) /* __pa_symbol should be used for C visible symbols. This seems to be the official gcc blessed way to do such arithmetic. */ +/* + * We need __phys_reloc_hide() here because gcc may assume that there is no + * overflow during __pa() calculation and can optimize it unexpectedly. + * Newer versions of gcc provide -fno-strict-overflow switch to handle this + * case properly. Once all supported versions of gcc understand it, we can + * remove this Voodoo magic stuff. (i.e. once gcc3.x is deprecated) + */ #define __pa_symbol(x) __pa(__phys_reloc_hide((unsigned long)(x))) #define __va(x) ((void *)((unsigned long)(x)+PAGE_OFFSET)) diff --git a/arch/x86/include/asm/pci_x86.h b/arch/x86/include/asm/pci_x86.h index cd2a31dc5fb8..49c7219826f9 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; diff --git a/arch/x86/include/asm/perf_event.h b/arch/x86/include/asm/perf_event.h index 254883d0c7e0..6e742cc4251b 100644 --- a/arch/x86/include/asm/perf_event.h +++ b/arch/x86/include/asm/perf_event.h @@ -68,8 +68,9 @@ union cpuid10_eax { union cpuid10_edx { struct { - unsigned int num_counters_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; }; @@ -140,6 +141,19 @@ 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 index 64a8ebff06fc..def500776b16 100644 --- a/arch/x86/include/asm/perf_event_p4.h +++ b/arch/x86/include/asm/perf_event_p4.h @@ -19,7 +19,6 @@ #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 ARCH_P4_MAX_COUNTER (ARCH_P4_MAX_CCCR / 2) #define P4_ESCR_EVENT_MASK 0x7e000000U #define P4_ESCR_EVENT_SHIFT 25 @@ -71,10 +70,6 @@ #define P4_CCCR_THRESHOLD(v) ((v) << P4_CCCR_THRESHOLD_SHIFT) #define P4_CCCR_ESEL(v) ((v) << P4_CCCR_ESCR_SELECT_SHIFT) -/* Custom bits in reerved CCCR area */ -#define P4_CCCR_CACHE_OPS_MASK 0x0000003fU - - /* Non HT mask */ #define P4_CCCR_MASK \ (P4_CCCR_OVF | \ @@ -106,8 +101,7 @@ * 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 + * 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) @@ -130,8 +124,6 @@ t; \ }) -#define p4_config_unpack_cache_event(v) (((u64)(v)) & P4_CCCR_CACHE_OPS_MASK) - #define P4_CONFIG_HT_SHIFT 63 #define P4_CONFIG_HT (1ULL << P4_CONFIG_HT_SHIFT) @@ -214,6 +206,12 @@ static inline u32 p4_default_escr_conf(int cpu, int exclude_os, int exclude_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, @@ -561,7 +559,7 @@ enum P4_EVENT_OPCODES { * a caller should use P4_ESCR_EMASK_NAME helper to * pick the EventMask needed, for example * - * P4_ESCR_EMASK_NAME(P4_EVENT_TC_DELIVER_MODE, DD) + * 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), @@ -753,43 +751,50 @@ enum P4_ESCR_EMASKS { P4_GEN_ESCR_EMASK(P4_EVENT_INSTR_COMPLETED, BOGUS, 1), }; -/* P4 PEBS: stale for a while */ -#define P4_PEBS_METRIC_MASK 0x00001fffU -#define P4_PEBS_UOB_TAG 0x01000000U -#define P4_PEBS_ENABLE 0x02000000U - -/* Replay metrics for MSR_IA32_PEBS_ENABLE and MSR_P4_PEBS_MATRIX_VERT */ -#define P4_PEBS__1stl_cache_load_miss_retired 0x3000001 -#define P4_PEBS__2ndl_cache_load_miss_retired 0x3000002 -#define P4_PEBS__dtlb_load_miss_retired 0x3000004 -#define P4_PEBS__dtlb_store_miss_retired 0x3000004 -#define P4_PEBS__dtlb_all_miss_retired 0x3000004 -#define P4_PEBS__tagged_mispred_branch 0x3018000 -#define P4_PEBS__mob_load_replay_retired 0x3000200 -#define P4_PEBS__split_load_retired 0x3000400 -#define P4_PEBS__split_store_retired 0x3000400 - -#define P4_VERT__1stl_cache_load_miss_retired 0x0000001 -#define P4_VERT__2ndl_cache_load_miss_retired 0x0000001 -#define P4_VERT__dtlb_load_miss_retired 0x0000001 -#define P4_VERT__dtlb_store_miss_retired 0x0000002 -#define P4_VERT__dtlb_all_miss_retired 0x0000003 -#define P4_VERT__tagged_mispred_branch 0x0000010 -#define P4_VERT__mob_load_replay_retired 0x0000001 -#define P4_VERT__split_load_retired 0x0000001 -#define P4_VERT__split_store_retired 0x0000002 - -enum P4_CACHE_EVENTS { - P4_CACHE__NONE, - - P4_CACHE__1stl_cache_load_miss_retired, - P4_CACHE__2ndl_cache_load_miss_retired, - P4_CACHE__dtlb_load_miss_retired, - P4_CACHE__dtlb_store_miss_retired, - P4_CACHE__itlb_reference_hit, - P4_CACHE__itlb_reference_miss, - - P4_CACHE__MAX +/* + * 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_64.h b/arch/x86/include/asm/pgtable_64.h index 181be528c612..076052cd62be 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 7e5c6a60b8ee..325b7bdbebaa 100644 --- a/arch/x86/include/asm/processor.h +++ b/arch/x86/include/asm/processor.h @@ -762,6 +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 @@ -1025,4 +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/required-features.h b/arch/x86/include/asm/required-features.h index 64cf2d24fad1..6c7fc25f2c34 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 606ede126972..d1e41b0f9b60 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 fb0b1874396f..4240878b9d76 100644 --- a/arch/x86/include/asm/scatterlist.h +++ b/arch/x86/include/asm/scatterlist.h @@ -3,7 +3,6 @@ #include <asm-generic/scatterlist.h> -#define ISA_DMA_THRESHOLD (0x00ffffff) #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 86b1506f4179..ef292c792d74 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 4dab78edbad9..2b16a2ad23dc 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/sys_ia32.h b/arch/x86/include/asm/sys_ia32.h index 3ad421784ae7..cb238526a9f1 100644 --- a/arch/x86/include/asm/sys_ia32.h +++ b/arch/x86/include/asm/sys_ia32.h @@ -18,13 +18,13 @@ #include <asm/ia32.h> /* ia32/sys_ia32.c */ -asmlinkage long sys32_truncate64(char __user *, unsigned long, unsigned long); +asmlinkage long sys32_truncate64(const char __user *, unsigned long, unsigned long); asmlinkage long sys32_ftruncate64(unsigned int, unsigned long, unsigned long); -asmlinkage long sys32_stat64(char __user *, struct stat64 __user *); -asmlinkage long sys32_lstat64(char __user *, struct stat64 __user *); +asmlinkage long sys32_stat64(const char __user *, struct stat64 __user *); +asmlinkage long sys32_lstat64(const char __user *, struct stat64 __user *); asmlinkage long sys32_fstat64(unsigned int, struct stat64 __user *); -asmlinkage long sys32_fstatat(unsigned int, char __user *, +asmlinkage long sys32_fstatat(unsigned int, const char __user *, struct stat64 __user *, int); struct mmap_arg_struct32; asmlinkage long sys32_mmap(struct mmap_arg_struct32 __user *); @@ -49,12 +49,12 @@ asmlinkage long sys32_rt_sigpending(compat_sigset_t __user *, compat_size_t); asmlinkage long sys32_rt_sigqueueinfo(int, int, compat_siginfo_t __user *); asmlinkage long sys32_pread(unsigned int, char __user *, u32, u32, u32); -asmlinkage long sys32_pwrite(unsigned int, char __user *, u32, u32, u32); +asmlinkage long sys32_pwrite(unsigned int, const char __user *, u32, u32, u32); asmlinkage long sys32_personality(unsigned long); asmlinkage long sys32_sendfile(int, int, compat_off_t __user *, s32); -asmlinkage long sys32_execve(char __user *, compat_uptr_t __user *, +asmlinkage long sys32_execve(const char __user *, compat_uptr_t __user *, compat_uptr_t __user *, struct pt_regs *); asmlinkage long sys32_clone(unsigned int, unsigned int, struct pt_regs *); @@ -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/syscalls.h b/arch/x86/include/asm/syscalls.h index 5c044b43e9a7..feb2ff9bfc2d 100644 --- a/arch/x86/include/asm/syscalls.h +++ b/arch/x86/include/asm/syscalls.h @@ -23,7 +23,7 @@ long sys_iopl(unsigned int, struct pt_regs *); /* kernel/process.c */ int sys_fork(struct pt_regs *); int sys_vfork(struct pt_regs *); -long sys_execve(char __user *, char __user * __user *, +long sys_execve(const char __user *, char __user * __user *, char __user * __user *, struct pt_regs *); long sys_clone(unsigned long, unsigned long, void __user *, void __user *, struct pt_regs *); diff --git a/arch/x86/include/asm/system.h b/arch/x86/include/asm/system.h index e7f4d33c55ed..33ecc3ea8782 100644 --- a/arch/x86/include/asm/system.h +++ b/arch/x86/include/asm/system.h @@ -457,4 +457,11 @@ static __always_inline void rdtsc_barrier(void) 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/unistd_32.h b/arch/x86/include/asm/unistd_32.h index beb9b5f8f8a4..b766a5e8ba0e 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 ff4307b0e81e..363e9b8a715b 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 aa558ac0306e..42d412fd8b02 100644 --- a/arch/x86/include/asm/uv/uv_bau.h +++ b/arch/x86/include/asm/uv/uv_bau.h @@ -34,6 +34,7 @@ */ #define UV_ITEMS_PER_DESCRIPTOR 8 +/* the 'throttle' to prevent the hardware stay-busy bug */ #define MAX_BAU_CONCURRENT 3 #define UV_CPUS_PER_ACT_STATUS 32 #define UV_ACT_STATUS_MASK 0x3 @@ -45,10 +46,26 @@ #define UV_DESC_BASE_PNODE_SHIFT 49 #define UV_PAYLOADQ_PNODE_SHIFT 49 #define UV_PTC_BASENAME "sgi_uv/ptc_statistics" +#define UV_BAU_BASENAME "sgi_uv/bau_tunables" +#define UV_BAU_TUNABLES_DIR "sgi_uv" +#define UV_BAU_TUNABLES_FILE "bau_tunables" +#define WHITESPACE " \t\n" #define uv_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 +#define UV_INTD_SOFT_ACK_TIMEOUT_PERIOD 0x0000000009UL +/* [19:16] SOFT_ACK timeout period 19: 1 is urgency 7 17:16 1 is multiplier */ +#define BAU_MISC_CONTROL_MULT_MASK 3 + +#define UVH_AGING_PRESCALE_SEL 0x000000b000UL +/* [30:28] URGENCY_7 an index into a table of times */ +#define BAU_URGENCY_7_SHIFT 28 +#define BAU_URGENCY_7_MASK 7 + +#define UVH_TRANSACTION_TIMEOUT 0x000000b200UL +/* [45:40] BAU - BAU transaction timeout select - a multiplier */ +#define BAU_TRANS_SHIFT 40 +#define BAU_TRANS_MASK 0x3f /* * bits in UVH_LB_BAU_SB_ACTIVATION_STATUS_0/1 @@ -59,24 +76,21 @@ #define DESC_STATUS_SOURCE_TIMEOUT 3 /* - * source side threshholds at which message retries print a warning - */ -#define SOURCE_TIMEOUT_LIMIT 20 -#define DESTINATION_TIMEOUT_LIMIT 20 - -/* - * misc. delays, in microseconds + * delay for 'plugged' timeout retries, 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 */ +#define PLUGGED_DELAY 10 /* * threshholds at which to use IPI to free resources */ +/* after this # consecutive 'plugged' timeouts, use IPI to release resources */ #define PLUGSB4RESET 100 -#define TIMEOUTSB4RESET 100 +/* after this many consecutive timeouts, use IPI to release resources */ +#define TIMEOUTSB4RESET 1 +/* at this number uses of IPI to release resources, giveup the request */ +#define IPI_RESET_LIMIT 1 +/* after this # consecutive successes, bump up the throttle if it was lowered */ +#define COMPLETE_THRESHOLD 5 /* * number of entries in the destination side payload queue @@ -96,6 +110,13 @@ #define FLUSH_COMPLETE 4 /* + * tuning the action when the numalink network is extremely delayed + */ +#define CONGESTED_RESPONSE_US 1000 /* 'long' response time, in microseconds */ +#define CONGESTED_REPS 10 /* long delays averaged over this many broadcasts */ +#define CONGESTED_PERIOD 30 /* time for the bau to be disabled, in seconds */ + +/* * Distribution: 32 bytes (256 bits) (bytes 0-0x1f of descriptor) * If the 'multilevel' flag in the header portion of the descriptor * has been set to 0, then endpoint multi-unicast mode is selected. @@ -300,37 +321,16 @@ struct bau_payload_queue_entry { /* bytes 24-31 */ }; -/* - * one per-cpu; to locate the software tables - */ -struct bau_control { - struct bau_desc *descriptor_base; +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; - 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; +}; + +struct reset_args { + int sender; }; /* @@ -344,18 +344,25 @@ struct ptc_stats { 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_ntargcpu; /* total number of cpu's targeted */ + unsigned long s_ntargself; /* times the sending cpu was targeted */ + unsigned long s_ntarglocals; /* targets of cpus on the local blade */ + unsigned long s_ntargremotes; /* targets of cpus on remote blades */ + unsigned long s_ntarglocaluvhub; /* targets of the local hub */ + unsigned long s_ntargremoteuvhub; /* remotes hubs targeted */ + unsigned long s_ntarguvhub; /* total number of uvhubs targeted */ + unsigned long s_ntarguvhub16; /* number of times target hubs >= 16*/ + unsigned long s_ntarguvhub8; /* number of times target hubs >= 8 */ + unsigned long s_ntarguvhub4; /* number of times target hubs >= 4 */ + unsigned long s_ntarguvhub2; /* number of times target hubs >= 2 */ + unsigned long s_ntarguvhub1; /* number of times target hubs == 1 */ 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 */ + unsigned long s_bau_reenabled; /* for bau enable/disable */ + unsigned long s_bau_disabled; /* for bau enable/disable */ /* 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 */ @@ -370,6 +377,52 @@ struct ptc_stats { unsigned long d_rcanceled; /* number of messages canceled by resets */ }; +/* + * one per-cpu; to locate the software tables + */ +struct bau_control { + struct bau_desc *descriptor_base; + struct bau_payload_queue_entry *va_queue_first; + struct bau_payload_queue_entry *va_queue_last; + struct bau_payload_queue_entry *bau_msg_head; + struct bau_control *uvhub_master; + struct bau_control *socket_master; + struct ptc_stats *statp; + unsigned long timeout_interval; + unsigned long set_bau_on_time; + atomic_t active_descriptor_count; + int plugged_tries; + int timeout_tries; + int ipi_attempts; + int conseccompletes; + int baudisabled; + int set_bau_off; + 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 uvhub_lock; + spinlock_t queue_lock; + /* tunables */ + int max_bau_concurrent; + int max_bau_concurrent_constant; + int plugged_delay; + int plugsb4reset; + int timeoutsb4reset; + int ipi_reset_limit; + int complete_threshold; + int congested_response_us; + int congested_reps; + int congested_period; + cycles_t period_time; + long period_requests; +}; + static inline int bau_uvhub_isset(int uvhub, struct bau_target_uvhubmask *dstp) { return constant_test_bit(uvhub, &dstp->bits[0]); diff --git a/arch/x86/include/asm/vmx.h b/arch/x86/include/asm/vmx.h index 9e6779f7cf2d..9f0cbd987d50 100644 --- a/arch/x86/include/asm/vmx.h +++ b/arch/x86/include/asm/vmx.h @@ -257,6 +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 @@ -266,6 +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 @@ -375,6 +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 diff --git a/arch/x86/include/asm/xen/hypercall.h b/arch/x86/include/asm/xen/hypercall.h index 9c371e4a9fa6..7fda040a76cd 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/xen/page.h b/arch/x86/include/asm/xen/page.h index 018a0a400799..bf5f7d32bd08 100644 --- a/arch/x86/include/asm/xen/page.h +++ b/arch/x86/include/asm/xen/page.h @@ -112,13 +112,9 @@ static inline xpaddr_t machine_to_phys(xmaddr_t machine) */ static inline unsigned long mfn_to_local_pfn(unsigned long mfn) { - extern unsigned long max_mapnr; unsigned long pfn = mfn_to_pfn(mfn); - if ((pfn < max_mapnr) - && !xen_feature(XENFEAT_auto_translated_physmap) - && (get_phys_to_machine(pfn) != mfn)) - return max_mapnr; /* force !pfn_valid() */ - /* XXX fixme; not true with sparsemem */ + if (get_phys_to_machine(pfn) != mfn) + return -1; /* force !pfn_valid() */ return pfn; } diff --git a/arch/x86/include/asm/xen/swiotlb-xen.h b/arch/x86/include/asm/xen/swiotlb-xen.h new file mode 100644 index 000000000000..1be1ab7d6a41 --- /dev/null +++ b/arch/x86/include/asm/xen/swiotlb-xen.h @@ -0,0 +1,14 @@ +#ifndef _ASM_X86_SWIOTLB_XEN_H +#define _ASM_X86_SWIOTLB_XEN_H + +#ifdef CONFIG_SWIOTLB_XEN +extern int xen_swiotlb; +extern int __init pci_xen_swiotlb_detect(void); +extern void __init pci_xen_swiotlb_init(void); +#else +#define xen_swiotlb (0) +static inline int __init pci_xen_swiotlb_detect(void) { return 0; } +static inline void __init pci_xen_swiotlb_init(void) { } +#endif + +#endif /* _ASM_X86_SWIOTLB_XEN_H */ diff --git a/arch/x86/include/asm/xsave.h b/arch/x86/include/asm/xsave.h index 2c4390cae228..c6ce2452f10c 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); @@ -59,6 +64,16 @@ static inline int fpu_xrstor_checking(struct fpu *fpu) 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" @@ -111,12 +126,25 @@ static inline void xrstor_state(struct xsave_struct *fx, u64 mask) : "memory"); } +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" (&(fpu->state->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 e77b22083721..0925676266bd 100644 --- a/arch/x86/kernel/Makefile +++ b/arch/x86/kernel/Makefile @@ -104,6 +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/realmode/wakeup.S b/arch/x86/kernel/acpi/realmode/wakeup.S index 580b4e296010..28595d6df47c 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 fcc3c61fdecc..33cec152070d 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> diff --git a/arch/x86/kernel/alternative.c b/arch/x86/kernel/alternative.c index 70237732a6c7..f65ab8b014c4 100644 --- a/arch/x86/kernel/alternative.c +++ b/arch/x86/kernel/alternative.c @@ -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 diff --git a/arch/x86/kernel/amd_iommu.c b/arch/x86/kernel/amd_iommu.c index 0d20286d78c6..fa044e1e30a2 100644 --- a/arch/x86/kernel/amd_iommu.c +++ b/arch/x86/kernel/amd_iommu.c @@ -2572,6 +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; } @@ -2609,8 +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/apb_timer.c b/arch/x86/kernel/apb_timer.c index a35347501d36..8dd77800ff5d 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 b5d8b0bcf235..a2e0caf26e17 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 565c1bfc507d..910f20b457c4 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 a96489ee6cab..e3b534cda49a 100644 --- a/arch/x86/kernel/apic/apic.c +++ b/arch/x86/kernel/apic/apic.c @@ -460,7 +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) @@ -1606,7 +1606,7 @@ void __init init_apic_mappings(void) * acpi lapic path already maps that address in * acpi_register_lapic_address() */ - if (!acpi_lapic) + if (!acpi_lapic && !smp_found_config) set_fixmap_nocache(FIX_APIC_BASE, apic_phys); apic_printk(APIC_VERBOSE, "mapped APIC to %08lx (%08lx)\n", diff --git a/arch/x86/kernel/apic/es7000_32.c b/arch/x86/kernel/apic/es7000_32.c index 425e53a87feb..8593582d8022 100644 --- a/arch/x86/kernel/apic/es7000_32.c +++ b/arch/x86/kernel/apic/es7000_32.c @@ -129,7 +129,6 @@ int es7000_plat; * GSI override for ES7000 platforms. */ -static unsigned int base; static int __cpuinit wakeup_secondary_cpu_via_mip(int cpu, unsigned long eip) { diff --git a/arch/x86/kernel/apic/hw_nmi.c b/arch/x86/kernel/apic/hw_nmi.c new file mode 100644 index 000000000000..cefd6942f0e9 --- /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 e41ed24ab26d..4dc0084ec1b1 100644 --- a/arch/x86/kernel/apic/io_apic.c +++ b/arch/x86/kernel/apic/io_apic.c @@ -3397,7 +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); diff --git a/arch/x86/kernel/apic/nmi.c b/arch/x86/kernel/apic/nmi.c index 1edaf15c0b8e..a43f71cb30f8 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 e46f98f36e31..7b598b84c902 100644 --- a/arch/x86/kernel/apic/x2apic_uv_x.c +++ b/arch/x86/kernel/apic/x2apic_uv_x.c @@ -604,6 +604,10 @@ int uv_handle_nmi(struct notifier_block *self, unsigned long reason, void *data) { if (reason != DIE_NMI_IPI) return NOTIFY_OK; + + if (in_crash_kexec) + /* do nothing if entering the crash kernel */ + return NOTIFY_OK; /* * Use a lock so only one cpu prints at a time * to prevent intermixed output. diff --git a/arch/x86/kernel/apm_32.c b/arch/x86/kernel/apm_32.c index c4f9182ca3ac..4c9c67bf09b7 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). diff --git a/arch/x86/kernel/cpu/Makefile b/arch/x86/kernel/cpu/Makefile index 3a785da34b6f..3f0ebe429a01 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 := $(nostackp) -obj-y := intel_cacheinfo.o addon_cpuid_features.o +obj-y := intel_cacheinfo.o scattered.o topology.o obj-y += proc.o capflags.o powerflags.o common.o obj-y += vmware.o hypervisor.o sched.o mshyperv.o -obj-$(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 e485825130d2..60a57b13082d 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/common.c b/arch/x86/kernel/cpu/common.c index 68e4a6f2211e..490dac63c2d2 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); } @@ -1192,6 +1210,7 @@ void __cpuinit cpu_init(void) dbg_restore_debug_regs(); fpu_init(); + xsave_init(); raw_local_save_flags(kernel_eflags); @@ -1252,12 +1271,7 @@ void __cpuinit cpu_init(void) 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/acpi-cpufreq.c b/arch/x86/kernel/cpu/cpufreq/acpi-cpufreq.c index 1d3cddaa40ee..cd8da247dda1 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> @@ -73,7 +72,7 @@ struct acpi_cpufreq_data { static DEFINE_PER_CPU(struct acpi_cpufreq_data *, acfreq_data); /* acpi_perf_data is a pointer to percpu data. */ -static struct acpi_processor_performance *acpi_perf_data; +static struct acpi_processor_performance __percpu *acpi_perf_data; static struct cpufreq_driver acpi_cpufreq_driver; @@ -324,8 +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; @@ -351,7 +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); } @@ -367,7 +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); } diff --git a/arch/x86/kernel/cpu/cpufreq/gx-suspmod.c b/arch/x86/kernel/cpu/cpufreq/gx-suspmod.c index 16e3483be9e3..32974cf84232 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 7e7eea4f8261..03162dac6271 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 e2360a469f79..cbf48fbca881 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 e7b559d74c52..fc09f142d94d 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/p4-clockmod.c b/arch/x86/kernel/cpu/cpufreq/p4-clockmod.c index 7b8a8ba67b07..bd1cac747f67 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 a36de5bbb622..994230d4dc4e 100644 --- a/arch/x86/kernel/cpu/cpufreq/pcc-cpufreq.c +++ b/arch/x86/kernel/cpu/cpufreq/pcc-cpufreq.c @@ -110,7 +110,7 @@ struct pcc_cpu { u32 output_offset; }; -static struct pcc_cpu *pcc_cpu_info; +static struct pcc_cpu __percpu *pcc_cpu_info; static int pcc_cpufreq_verify(struct cpufreq_policy *policy) { diff --git a/arch/x86/kernel/cpu/cpufreq/powernow-k7.c b/arch/x86/kernel/cpu/cpufreq/powernow-k7.c index 9a97116f89e5..4a45fd6e41ba 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 3e90cce3dc8b..491977baf6c0 100644 --- a/arch/x86/kernel/cpu/cpufreq/powernow-k8.c +++ b/arch/x86/kernel/cpu/cpufreq/powernow-k8.c @@ -9,7 +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. * @@ -806,6 +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; } @@ -910,8 +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; diff --git a/arch/x86/kernel/cpu/hypervisor.c b/arch/x86/kernel/cpu/hypervisor.c index dd531cc56a8f..8095f8611f8a 100644 --- a/arch/x86/kernel/cpu/hypervisor.c +++ b/arch/x86/kernel/cpu/hypervisor.c @@ -34,6 +34,9 @@ static const __initconst struct hypervisor_x86 * const hypervisors[] = { &x86_hyper_vmware, &x86_hyper_ms_hyperv, +#ifdef CONFIG_XEN_PVHVM + &x86_hyper_xen_hvm, +#endif }; const struct hypervisor_x86 *x86_hyper; diff --git a/arch/x86/kernel/cpu/intel_cacheinfo.c b/arch/x86/kernel/cpu/intel_cacheinfo.c index 33eae2062cf5..898c2f4eab88 100644 --- a/arch/x86/kernel/cpu/intel_cacheinfo.c +++ b/arch/x86/kernel/cpu/intel_cacheinfo.c @@ -347,8 +347,8 @@ static struct amd_l3_cache * __cpuinit amd_init_l3_cache(int node) return l3; } -static void __cpuinit -amd_check_l3_disable(int index, struct _cpuid4_info_regs *this_leaf) +static void __cpuinit amd_check_l3_disable(struct _cpuid4_info_regs *this_leaf, + int index) { int node; @@ -396,20 +396,39 @@ amd_check_l3_disable(int index, struct _cpuid4_info_regs *this_leaf) this_leaf->l3 = l3_caches[node]; } +/* + * 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) +{ + unsigned int reg = 0; + + pci_read_config_dword(l3->dev, 0x1BC + slot * 4, ®); + + /* check whether this slot is activated already */ + if (reg & (3UL << 30)) + return reg & 0xfff; + + return -1; +} + static ssize_t show_cache_disable(struct _cpuid4_info *this_leaf, char *buf, unsigned int slot) { - struct pci_dev *dev = this_leaf->l3->dev; - unsigned int reg = 0; + int index; if (!this_leaf->l3 || !this_leaf->l3->can_disable) return -EINVAL; - if (!dev) - return -EINVAL; + index = amd_get_l3_disable_slot(this_leaf->l3, slot); + if (index >= 0) + return sprintf(buf, "%d\n", index); - pci_read_config_dword(dev, 0x1BC + slot * 4, ®); - return sprintf(buf, "0x%08x\n", reg); + return sprintf(buf, "FREE\n"); } #define SHOW_CACHE_DISABLE(slot) \ @@ -451,37 +470,74 @@ static void amd_l3_disable_index(struct amd_l3_cache *l3, int cpu, } } - -static ssize_t store_cache_disable(struct _cpuid4_info *this_leaf, - const char *buf, size_t count, - unsigned int slot) +/* + * 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) { - struct pci_dev *dev = this_leaf->l3->dev; - int cpu = cpumask_first(to_cpumask(this_leaf->shared_cpu_map)); - unsigned long val = 0; + int ret = 0; #define SUBCACHE_MASK (3UL << 20) #define SUBCACHE_INDEX 0xfff - if (!this_leaf->l3 || !this_leaf->l3->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; - amd_l3_disable_index(this_leaf->l3, cpu, slot, val); - + 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; } @@ -502,7 +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 */ @@ -518,7 +574,7 @@ __cpuinit cpuid4_cache_lookup_regs(int index, if (boot_cpu_data.x86_vendor == X86_VENDOR_AMD) { amd_cpuid4(index, &eax, &ebx, &ecx); - 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); } diff --git a/arch/x86/kernel/cpu/mcheck/mce.c b/arch/x86/kernel/cpu/mcheck/mce.c index 18cc42562250..ed41562909fe 100644 --- a/arch/x86/kernel/cpu/mcheck/mce.c +++ b/arch/x86/kernel/cpu/mcheck/mce.c @@ -51,7 +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)) @@ -107,8 +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; } @@ -211,11 +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); @@ -224,14 +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); /* @@ -241,16 +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; @@ -291,7 +281,6 @@ 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]; @@ -322,16 +311,15 @@ static void mce_panic(char *msg, struct mce *final, char *exp) 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 */ @@ -600,6 +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); } @@ -1220,7 +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; } diff --git a/arch/x86/kernel/cpu/mcheck/mce_intel.c b/arch/x86/kernel/cpu/mcheck/mce_intel.c index 62b48e40920a..6fcd0936194f 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 e1a0a3bf9716..c2a8b26d4fea 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: */ @@ -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 index 16f41bbe46b6..d944bf6c50e9 100644 --- a/arch/x86/kernel/cpu/mshyperv.c +++ b/arch/x86/kernel/cpu/mshyperv.c @@ -18,6 +18,7 @@ #include <asm/mshyperv.h> struct ms_hyperv_info ms_hyperv; +EXPORT_SYMBOL_GPL(ms_hyperv); static bool __init ms_hyperv_platform(void) { diff --git a/arch/x86/kernel/cpu/mtrr/cleanup.c b/arch/x86/kernel/cpu/mtrr/cleanup.c index 06130b52f012..c5f59d071425 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 fd31a441c61c..7d28d7d03885 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 79556bd9b602..01c0f3ee6cc3 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 5db5b7d65a18..f2da20fda02d 100644 --- a/arch/x86/kernel/cpu/perf_event.c +++ b/arch/x86/kernel/cpu/perf_event.c @@ -220,6 +220,7 @@ struct x86_pmu { 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); @@ -295,10 +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; @@ -313,8 +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; } @@ -438,7 +439,7 @@ static int x86_setup_perfctr(struct perf_event *event) 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 @@ -885,7 +886,7 @@ 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 ret = 0, idx = hwc->idx; @@ -897,14 +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; } @@ -923,10 +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, + wrmsrl(hwc->event_base + idx, (u64)(-left) & x86_pmu.cntval_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); @@ -969,7 +979,7 @@ static int x86_pmu_enable(struct perf_event *event) * skip the schedulability test here, it will be peformed * at commit time(->commit_txn) as a whole */ - if (cpuc->group_flag & PERF_EVENT_TXN_STARTED) + if (cpuc->group_flag & PERF_EVENT_TXN) goto out; ret = x86_pmu.schedule_events(cpuc, n, assign); @@ -1096,7 +1106,7 @@ static void x86_pmu_disable(struct perf_event *event) * The events never got scheduled and ->cancel_txn will truncate * the event_list. */ - if (cpuc->group_flag & PERF_EVENT_TXN_STARTED) + if (cpuc->group_flag & PERF_EVENT_TXN) return; x86_pmu_stop(event); @@ -1388,7 +1398,7 @@ 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_STARTED; + cpuc->group_flag |= PERF_EVENT_TXN; cpuc->n_txn = 0; } @@ -1401,7 +1411,7 @@ 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_STARTED; + cpuc->group_flag &= ~PERF_EVENT_TXN; /* * Truncate the collected events. */ @@ -1435,11 +1445,7 @@ static int x86_pmu_commit_txn(const struct pmu *pmu) */ memcpy(cpuc->assign, assign, n*sizeof(int)); - /* - * Clear out the txn count so that ->cancel_txn() which gets - * run after ->commit_txn() doesn't undo things. - */ - cpuc->n_txn = 0; + cpuc->group_flag &= ~PERF_EVENT_TXN; return 0; } @@ -1607,8 +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) { @@ -1730,22 +1734,6 @@ 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) -{ - 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; - /* - * We abuse bit 3 to pass exact information, see perf_misc_flags - * and the comment with PERF_EFLAGS_EXACT. - */ - regs->flags = 0; -} - unsigned long perf_instruction_pointer(struct pt_regs *regs) { unsigned long ip; diff --git a/arch/x86/kernel/cpu/perf_event_p4.c b/arch/x86/kernel/cpu/perf_event_p4.c index ae85d69644d1..febb12cea795 100644 --- a/arch/x86/kernel/cpu/perf_event_p4.c +++ b/arch/x86/kernel/cpu/perf_event_p4.c @@ -21,22 +21,36 @@ struct p4_event_bind { char cntr[2][P4_CNTR_LIMIT]; /* counter index (offset), -1 on abscence */ }; -struct p4_cache_event_bind { +struct p4_pebs_bind { unsigned int metric_pebs; unsigned int metric_vert; }; -#define P4_GEN_CACHE_EVENT_BIND(name) \ - [P4_CACHE__##name] = { \ - .metric_pebs = P4_PEBS__##name, \ - .metric_vert = P4_VERT__##name, \ +/* 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, \ } -static struct p4_cache_event_bind p4_cache_event_bind_map[] = { - P4_GEN_CACHE_EVENT_BIND(1stl_cache_load_miss_retired), - P4_GEN_CACHE_EVENT_BIND(2ndl_cache_load_miss_retired), - P4_GEN_CACHE_EVENT_BIND(dtlb_load_miss_retired), - P4_GEN_CACHE_EVENT_BIND(dtlb_store_miss_retired), +/* + * 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), }; /* @@ -281,10 +295,10 @@ static struct p4_event_bind p4_event_bind_map[] = { }, }; -#define P4_GEN_CACHE_EVENT(event, bit, cache_event) \ +#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(cache_event | \ + p4_config_pack_cccr(metric | \ P4_CCCR_ESEL(P4_OPCODE_ESEL(P4_OPCODE(event)))) static __initconst const u64 p4_hw_cache_event_ids @@ -296,34 +310,34 @@ static __initconst const u64 p4_hw_cache_event_ids [ C(OP_READ) ] = { [ C(RESULT_ACCESS) ] = 0x0, [ C(RESULT_MISS) ] = P4_GEN_CACHE_EVENT(P4_EVENT_REPLAY_EVENT, NBOGUS, - P4_CACHE__1stl_cache_load_miss_retired), + 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_CACHE__2ndl_cache_load_miss_retired), + 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_CACHE__dtlb_load_miss_retired), + 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_CACHE__dtlb_store_miss_retired), + 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_CACHE__itlb_reference_hit), + P4_PEBS_METRIC__none), [ C(RESULT_MISS) ] = P4_GEN_CACHE_EVENT(P4_EVENT_ITLB_REFERENCE, MISS, - P4_CACHE__itlb_reference_miss), + P4_PEBS_METRIC__none), }, [ C(OP_WRITE) ] = { [ C(RESULT_ACCESS) ] = -1, @@ -414,11 +428,37 @@ static u64 p4_pmu_event_map(int hw_event) 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; - unsigned int evnt; u32 escr, cccr; /* @@ -438,12 +478,9 @@ static int p4_hw_config(struct perf_event *event) if (event->attr.type == PERF_TYPE_RAW) { - /* user data may have out-of-bound event index */ - evnt = p4_config_unpack_event(event->attr.config); - if (evnt >= ARRAY_SIZE(p4_event_bind_map)) { - rc = -EINVAL; + rc = p4_validate_raw_event(event); + if (rc) goto out; - } /* * We don't control raw events so it's up to the caller @@ -451,12 +488,15 @@ static int p4_hw_config(struct perf_event *event) * 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_config_pack_cccr(P4_CCCR_MASK_HT | P4_CCCR_RESERVED)); } rc = x86_setup_perfctr(event); @@ -482,6 +522,29 @@ static inline int p4_pmu_clear_cccr_ovf(struct hw_perf_event *hwc) 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; @@ -507,6 +570,26 @@ static void p4_pmu_disable_all(void) 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) @@ -515,9 +598,7 @@ static void p4_pmu_enable_event(struct perf_event *event) 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); - unsigned int idx_cache = p4_config_unpack_cache_event(hwc->config); struct p4_event_bind *bind; - struct p4_cache_event_bind *bind_cache; u64 escr_addr, cccr; bind = &p4_event_bind_map[idx]; @@ -537,16 +618,10 @@ static void p4_pmu_enable_event(struct perf_event *event) cccr = p4_config_unpack_cccr(hwc->config); /* - * it could be Cache event so that we need to - * set metrics into additional MSRs + * it could be Cache event so we need to write metrics + * into additional MSRs */ - BUILD_BUG_ON(P4_CACHE__MAX > P4_CCCR_CACHE_OPS_MASK); - if (idx_cache > P4_CACHE__NONE && - idx_cache < ARRAY_SIZE(p4_cache_event_bind_map)) { - bind_cache = &p4_cache_event_bind_map[idx_cache]; - (void)checking_wrmsrl(MSR_IA32_PEBS_ENABLE, (u64)bind_cache->metric_pebs); - (void)checking_wrmsrl(MSR_P4_PEBS_MATRIX_VERT, (u64)bind_cache->metric_vert); - } + p4_pmu_enable_pebs(hwc->config); (void)checking_wrmsrl(escr_addr, escr_conf); (void)checking_wrmsrl(hwc->config_base + hwc->idx, @@ -581,6 +656,7 @@ static int p4_pmu_handle_irq(struct pt_regs *regs) cpuc = &__get_cpu_var(cpu_hw_events); for (idx = 0; idx < x86_pmu.num_counters; idx++) { + int overflow; if (!test_bit(idx, cpuc->active_mask)) continue; @@ -591,12 +667,14 @@ static int p4_pmu_handle_irq(struct pt_regs *regs) WARN_ON_ONCE(hwc->idx != idx); /* it might be unflagged overflow */ - handled = p4_pmu_clear_cccr_ovf(hwc); + overflow = p4_pmu_clear_cccr_ovf(hwc); val = x86_perf_event_update(event); - if (!handled && (val & (1ULL << (x86_pmu.cntval_bits - 1)))) + if (!overflow && (val & (1ULL << (x86_pmu.cntval_bits - 1)))) continue; + handled += overflow; + /* event overflow for sure */ data.period = event->hw.last_period; @@ -612,7 +690,7 @@ static int p4_pmu_handle_irq(struct pt_regs *regs) inc_irq_stat(apic_perf_irqs); } - return handled; + return handled > 0; } /* @@ -829,6 +907,15 @@ static __initconst const struct x86_pmu p4_pmu = { .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) diff --git a/arch/x86/kernel/cpu/scattered.c b/arch/x86/kernel/cpu/scattered.c new file mode 100644 index 000000000000..34b4dad6f0b8 --- /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 10fa5684a662..4397e987a1cf 100644 --- a/arch/x86/kernel/cpu/addon_cpuid_features.c +++ b/arch/x86/kernel/cpu/topology.c @@ -1,62 +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_APERFMPERF, CR_ECX, 0, 0x00000006 }, - { X86_FEATURE_CPB, CR_EDX, 9, 0x80000007 }, - { 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 b9d1ff588445..227b0448960d 100644 --- a/arch/x86/kernel/cpu/vmware.c +++ b/arch/x86/kernel/cpu/vmware.c @@ -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); @@ -62,6 +62,13 @@ 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; } diff --git a/arch/x86/kernel/crash.c b/arch/x86/kernel/crash.c index ebd4c51d096a..764c7c2b1811 100644 --- a/arch/x86/kernel/crash.c +++ b/arch/x86/kernel/crash.c @@ -28,6 +28,8 @@ #include <asm/reboot.h> #include <asm/virtext.h> +int in_crash_kexec; + #if defined(CONFIG_SMP) && defined(CONFIG_X86_LOCAL_APIC) static void kdump_nmi_callback(int cpu, struct die_args *args) @@ -61,6 +63,7 @@ static void kdump_nmi_callback(int cpu, struct die_args *args) static void kdump_nmi_shootdown_cpus(void) { + in_crash_kexec = 1; nmi_shootdown_cpus(kdump_nmi_callback); disable_local_APIC(); diff --git a/arch/x86/kernel/dumpstack.c b/arch/x86/kernel/dumpstack.c index c89a386930b7..6e8752c1bd52 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; diff --git a/arch/x86/kernel/dumpstack.h b/arch/x86/kernel/dumpstack.h deleted file mode 100644 index e1a93be4fd44..000000000000 --- 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 11540a189d93..0f6376ffa2d9 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 272c9f1f05f3..57a21f11c791 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/entry_32.S b/arch/x86/kernel/entry_32.S index cd49141cf153..227d00920d2f 100644 --- a/arch/x86/kernel/entry_32.S +++ b/arch/x86/kernel/entry_32.S @@ -611,14 +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 */ @@ -791,9 +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 @@ -914,7 +913,7 @@ ENTRY(simd_coprocessor_error) .balign 4 .long 661b .long 663f - .byte X86_FEATURE_XMM + .word X86_FEATURE_XMM .byte 662b-661b .byte 664f-663f .previous @@ -1166,6 +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 4db7c4d12ffa..17be5ec7cbba 100644 --- a/arch/x86/kernel/entry_64.S +++ b/arch/x86/kernel/entry_64.S @@ -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) @@ -1185,13 +1185,13 @@ END(kernel_thread_helper) * execve(). This function needs to use IRET, not SYSRET, to set up all state properly. * * C extern interface: - * extern long execve(char *name, char **argv, char **envp) + * extern long execve(const char *name, char **argv, char **envp) * * asm input arguments: * rdi: name, rsi: argv, rdx: envp * * We want to fallback into: - * extern long sys_execve(char *name, char **argv,char **envp, struct pt_regs *regs) + * extern long sys_execve(const char *name, char **argv,char **envp, struct pt_regs *regs) * * do_sys_execve asm fallback arguments: * rdi: name, rsi: argv, rdx: envp, rcx: fake frame on the stack @@ -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 b2e246037392..784360c0625c 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 37c3d4b17d85..ff4c453e13f3 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 3d1e6f16b7a6..239046bd447f 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 ba390d731175..351f9c0fea1f 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 */ @@ -583,7 +582,7 @@ static void init_one_hpet_msi_clockevent(struct hpet_dev *hdev, int cpu) * scaled math multiplication factor for nanosecond to hpet tick * conversion. */ - hpet_freq = 1000000000000000ULL; + hpet_freq = FSEC_PER_SEC; do_div(hpet_freq, hpet_period); evt->mult = div_sc((unsigned long) hpet_freq, NSEC_PER_SEC, evt->shift); @@ -787,7 +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 @@ -798,6 +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 */ @@ -832,9 +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_SEC; + do_div(hpet_freq, hpet_period); + clocksource_register_hz(&clocksource_hpet, (u32)hpet_freq); return 0; } diff --git a/arch/x86/kernel/hw_breakpoint.c b/arch/x86/kernel/hw_breakpoint.c index a8f1b803d2fd..a474ec37c32f 100644 --- a/arch/x86/kernel/hw_breakpoint.c +++ b/arch/x86/kernel/hw_breakpoint.c @@ -208,6 +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; @@ -251,6 +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: @@ -271,21 +297,6 @@ 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; } /* @@ -305,6 +316,9 @@ int arch_validate_hwbkpt_settings(struct perf_event *bp) ret = -EINVAL; switch (info->len) { + case X86_BREAKPOINT_LEN_X: + align = sizeof(long) -1; + break; case X86_BREAKPOINT_LEN_1: align = 0; break; @@ -466,6 +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 86cef6b32253..1f11f5ce668f 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(); @@ -93,21 +94,26 @@ 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 */ current_thread_info()->status = 0; clear_used_math(); } -#endif /* CONFIG_X86_64 */ -static void fpu_finit(struct fpu *fpu) +#else /* CONFIG_X86_64 */ + +void __cpuinit fpu_init(void) +{ + if (!smp_processor_id()) + init_thread_xstate(); +} + +#endif /* CONFIG_X86_32 */ + +void fpu_finit(struct fpu *fpu) { #ifdef CONFIG_X86_32 if (!HAVE_HWFP) { @@ -132,6 +138,7 @@ static void fpu_finit(struct fpu *fpu) fp->fos = 0xffff0000u; } } +EXPORT_SYMBOL_GPL(fpu_finit); /* * The _current_ task is using the FPU for the first time @@ -190,6 +197,8 @@ 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.fpu.state->fxsave, 0, -1); } @@ -207,6 +216,8 @@ 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.fpu.state->fxsave, 0, -1); @@ -446,6 +457,8 @@ int fpregs_get(struct task_struct *target, const struct user_regset *regset, -1); } + sanitize_i387_state(target); + if (kbuf && pos == 0 && count == sizeof(env)) { convert_from_fxsr(kbuf, target); return 0; @@ -467,6 +480,8 @@ 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); @@ -533,6 +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. diff --git a/arch/x86/kernel/kgdb.c b/arch/x86/kernel/kgdb.c index 01ab17ae2ae7..ef10940e1af0 100644 --- a/arch/x86/kernel/kgdb.c +++ b/arch/x86/kernel/kgdb.c @@ -49,55 +49,94 @@ #include <asm/system.h> #include <asm/apic.h> -/** - * 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; } /** @@ -150,54 +189,13 @@ 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; @@ -205,7 +203,7 @@ 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; @@ -292,10 +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)) { @@ -313,7 +311,7 @@ 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); @@ -333,10 +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) { @@ -397,7 +395,7 @@ 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) { @@ -458,7 +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': @@ -469,8 +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); @@ -645,7 +640,7 @@ void kgdb_arch_late(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); diff --git a/arch/x86/kernel/kprobes.c b/arch/x86/kernel/kprobes.c index 675879b65ce6..1bfb6cf4dd55 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; } @@ -803,9 +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/mpparse.c b/arch/x86/kernel/mpparse.c index d86dbf7e54be..d7b6f7fb4fec 100644 --- a/arch/x86/kernel/mpparse.c +++ b/arch/x86/kernel/mpparse.c @@ -274,6 +274,18 @@ static void __init smp_dump_mptable(struct mpc_table *mpc, unsigned char *mpt) void __init default_smp_read_mpc_oem(struct mpc_table *mpc) { } +static void __init smp_register_lapic_address(unsigned long address) +{ + mp_lapic_addr = address; + + set_fixmap_nocache(FIX_APIC_BASE, address); + if (boot_cpu_physical_apicid == -1U) { + boot_cpu_physical_apicid = read_apic_id(); + apic_version[boot_cpu_physical_apicid] = + GET_APIC_VERSION(apic_read(APIC_LVR)); + } +} + static int __init smp_read_mpc(struct mpc_table *mpc, unsigned early) { char str[16]; @@ -295,6 +307,10 @@ static int __init smp_read_mpc(struct mpc_table *mpc, unsigned early) if (early) return 1; + /* Initialize the lapic mapping */ + if (!acpi_lapic) + smp_register_lapic_address(mpc->lapic); + if (mpc->oemptr) x86_init.mpparse.smp_read_mpc_oem(mpc); diff --git a/arch/x86/kernel/mrst.c b/arch/x86/kernel/mrst.c index 5915e0b33303..79ae68154e87 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 +234,21 @@ 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) @@ -232,11 +266,13 @@ 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; @@ -250,3 +286,26 @@ void __init x86_mrst_early_setup(void) 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/olpc.c b/arch/x86/kernel/olpc.c index 8297160c41b3..0e0cdde519be 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 000000000000..3218aa71ab5e --- /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-dma.c b/arch/x86/kernel/pci-dma.c index 4b7e3d8b01dd..9f07cfcbd3a5 100644 --- a/arch/x86/kernel/pci-dma.c +++ b/arch/x86/kernel/pci-dma.c @@ -13,6 +13,7 @@ #include <asm/calgary.h> #include <asm/amd_iommu.h> #include <asm/x86_init.h> +#include <asm/xen/swiotlb-xen.h> static int forbid_dac __read_mostly; @@ -132,7 +133,7 @@ void __init pci_iommu_alloc(void) /* free the range so iommu could get some range less than 4G */ dma32_free_bootmem(); - if (pci_swiotlb_detect()) + if (pci_xen_swiotlb_detect() || pci_swiotlb_detect()) goto out; gart_iommu_hole_init(); @@ -144,6 +145,8 @@ void __init pci_iommu_alloc(void) /* needs to be called after gart_iommu_hole_init */ amd_iommu_detect(); out: + pci_xen_swiotlb_init(); + pci_swiotlb_init(); } @@ -296,7 +299,7 @@ static int __init pci_iommu_init(void) #endif x86_init.iommu.iommu_init(); - if (swiotlb) { + if (swiotlb || xen_swiotlb) { printk(KERN_INFO "PCI-DMA: " "Using software bounce buffering for IO (SWIOTLB)\n"); swiotlb_print_info(); diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c index e7e35219b32f..64ecaf0af9af 100644 --- a/arch/x86/kernel/process.c +++ b/arch/x86/kernel/process.c @@ -28,6 +28,7 @@ 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) { @@ -300,7 +301,7 @@ EXPORT_SYMBOL(kernel_thread); /* * sys_execve() executes a new program. */ -long sys_execve(char __user *name, char __user * __user *argv, +long sys_execve(const char __user *name, char __user * __user *argv, char __user * __user *envp, struct pt_regs *regs) { long error; @@ -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 8d128783af47..96586c3cbbbf 100644 --- a/arch/x86/kernel/process_32.c +++ b/arch/x86/kernel/process_32.c @@ -57,6 +57,8 @@ #include <asm/syscalls.h> #include <asm/debugreg.h> +#include <trace/events/power.h> + asmlinkage void ret_from_fork(void) __asm__("ret_from_fork"); /* @@ -111,6 +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(); diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c index 3c2422a99f1f..3d9ea531ddd1 100644 --- a/arch/x86/kernel/process_64.c +++ b/arch/x86/kernel/process_64.c @@ -51,6 +51,8 @@ #include <asm/syscalls.h> #include <asm/debugreg.h> +#include <trace/events/power.h> + asmlinkage extern void ret_from_fork(void); DEFINE_PER_CPU(unsigned long, old_rsp); @@ -138,6 +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. */ diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c index b4ae4acbd031..b008e7883207 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> @@ -736,10 +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/smpboot.c b/arch/x86/kernel/smpboot.c index c4f33b2e77d6..a5e928b0cb5f 100644 --- a/arch/x86/kernel/smpboot.c +++ b/arch/x86/kernel/smpboot.c @@ -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)) diff --git a/arch/x86/kernel/stacktrace.c b/arch/x86/kernel/stacktrace.c index 922eefbb3f6c..b53c525368a7 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/syscall_table_32.S b/arch/x86/kernel/syscall_table_32.S index 8b3729341216..b35786dc9b8f 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/tlb_uv.c b/arch/x86/kernel/tlb_uv.c index 7fea555929e2..312ef0292815 100644 --- a/arch/x86/kernel/tlb_uv.c +++ b/arch/x86/kernel/tlb_uv.c @@ -8,6 +8,7 @@ */ #include <linux/seq_file.h> #include <linux/proc_fs.h> +#include <linux/debugfs.h> #include <linux/kernel.h> #include <linux/slab.h> @@ -22,19 +23,37 @@ #include <asm/irq_vectors.h> #include <asm/timer.h> -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; +/* timeouts in nanoseconds (indexed by UVH_AGING_PRESCALE_SEL urgency7 30:28) */ +static int timeout_base_ns[] = { + 20, + 160, + 1280, + 10240, + 81920, + 655360, + 5242880, + 167772160 }; - -#define UV_INTD_SOFT_ACK_TIMEOUT_PERIOD 0x000000000bUL - -static int uv_bau_max_concurrent __read_mostly; - +static int timeout_us; static int nobau; +static int baudisabled; +static spinlock_t disable_lock; +static cycles_t congested_cycles; + +/* tunables: */ +static int max_bau_concurrent = MAX_BAU_CONCURRENT; +static int max_bau_concurrent_constant = MAX_BAU_CONCURRENT; +static int plugged_delay = PLUGGED_DELAY; +static int plugsb4reset = PLUGSB4RESET; +static int timeoutsb4reset = TIMEOUTSB4RESET; +static int ipi_reset_limit = IPI_RESET_LIMIT; +static int complete_threshold = COMPLETE_THRESHOLD; +static int congested_response_us = CONGESTED_RESPONSE_US; +static int congested_reps = CONGESTED_REPS; +static int congested_period = CONGESTED_PERIOD; +static struct dentry *tunables_dir; +static struct dentry *tunables_file; + static int __init setup_nobau(char *arg) { nobau = 1; @@ -52,10 +71,6 @@ 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 uvhub. 'Nodes' are used for kernel * memory allocation. @@ -126,7 +141,7 @@ static inline void uv_bau_process_retry_msg(struct msg_desc *mdp, struct ptc_stats *stat; msg = mdp->msg; - stat = &per_cpu(ptcstats, bcp->cpu); + stat = bcp->statp; stat->d_retries++; /* * cancel any message from msg+1 to the retry itself @@ -146,15 +161,14 @@ static inline void uv_bau_process_retry_msg(struct msg_desc *mdp, 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); + msg_res = 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)) { + if (mmr & (msg_res << UV_SW_ACK_NPENDING)) { /* * is the resource timed out? * make everyone ignore the cancelled message. @@ -164,9 +178,9 @@ static inline void uv_bau_process_retry_msg(struct msg_desc *mdp, 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"); + (msg_res << UV_SW_ACK_NPENDING) | + msg_res); + } } } if (!cancel_count) @@ -190,7 +204,7 @@ static void uv_bau_process_message(struct msg_desc *mdp, * This must be a normal message, or retry of a normal message */ msg = mdp->msg; - stat = &per_cpu(ptcstats, bcp->cpu); + stat = bcp->statp; if (msg->address == TLB_FLUSH_ALL) { local_flush_tlb(); stat->d_alltlb++; @@ -274,7 +288,7 @@ uv_do_reset(void *ptr) bcp = &per_cpu(bau_control, smp_processor_id()); rap = (struct reset_args *)ptr; - stat = &per_cpu(ptcstats, bcp->cpu); + stat = bcp->statp; stat->d_resets++; /* @@ -302,13 +316,13 @@ uv_do_reset(void *ptr) */ mmr = uv_read_local_mmr (UVH_LB_BAU_INTD_SOFTWARE_ACKNOWLEDGE); - msg_res = ((msg->sw_ack_vector << 8) | - msg->sw_ack_vector); + msg_res = msg->sw_ack_vector; if (mmr & msg_res) { stat->d_rcanceled++; uv_write_local_mmr( UVH_LB_BAU_INTD_SOFTWARE_ACKNOWLEDGE_ALIAS, - msg_res); + (msg_res << UV_SW_ACK_NPENDING) | + msg_res); } } } @@ -386,17 +400,12 @@ static int uv_wait_completion(struct bau_desc *bau_desc, unsigned long mmr_offset, int right_shift, int this_cpu, struct bau_control *bcp, struct bau_control *smaster, long try) { - 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 ptc_stats *stat = bcp->statp; 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) @@ -423,7 +432,8 @@ static int uv_wait_completion(struct bau_desc *bau_desc, * pending. In that case hardware returns the * ERROR that looks like a destination timeout. */ - if (cycles_2_us(ttime - bcp->send_message) < BIOS_TO) { + if (cycles_2_us(ttime - bcp->send_message) < + timeout_us) { bcp->conseccompletes = 0; return FLUSH_RETRY_PLUGGED; } @@ -435,26 +445,6 @@ static int uv_wait_completion(struct bau_desc *bau_desc, * 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; - } - } } } bcp->conseccompletes++; @@ -494,56 +484,116 @@ static inline int atomic_inc_unless_ge(spinlock_t *lock, atomic_t *v, int u) return 1; } +/* + * Our retries are blocked by all destination swack resources being + * in use, and a timeout is pending. In that case hardware immediately + * returns the ERROR that looks like a destination timeout. + */ +static void +destination_plugged(struct bau_desc *bau_desc, struct bau_control *bcp, + struct bau_control *hmaster, struct ptc_stats *stat) +{ + udelay(bcp->plugged_delay); + bcp->plugged_tries++; + if (bcp->plugged_tries >= bcp->plugsb4reset) { + bcp->plugged_tries = 0; + quiesce_local_uvhub(hmaster); + spin_lock(&hmaster->queue_lock); + uv_reset_with_ipi(&bau_desc->distribution, bcp->cpu); + spin_unlock(&hmaster->queue_lock); + end_uvhub_quiesce(hmaster); + bcp->ipi_attempts++; + stat->s_resets_plug++; + } +} + +static void +destination_timeout(struct bau_desc *bau_desc, struct bau_control *bcp, + struct bau_control *hmaster, struct ptc_stats *stat) +{ + hmaster->max_bau_concurrent = 1; + bcp->timeout_tries++; + if (bcp->timeout_tries >= bcp->timeoutsb4reset) { + bcp->timeout_tries = 0; + quiesce_local_uvhub(hmaster); + spin_lock(&hmaster->queue_lock); + uv_reset_with_ipi(&bau_desc->distribution, bcp->cpu); + spin_unlock(&hmaster->queue_lock); + end_uvhub_quiesce(hmaster); + bcp->ipi_attempts++; + stat->s_resets_timeout++; + } +} + +/* + * Completions are taking a very long time due to a congested numalink + * network. + */ +static void +disable_for_congestion(struct bau_control *bcp, struct ptc_stats *stat) +{ + int tcpu; + struct bau_control *tbcp; + + /* let only one cpu do this disabling */ + spin_lock(&disable_lock); + if (!baudisabled && bcp->period_requests && + ((bcp->period_time / bcp->period_requests) > congested_cycles)) { + /* it becomes this cpu's job to turn on the use of the + BAU again */ + baudisabled = 1; + bcp->set_bau_off = 1; + bcp->set_bau_on_time = get_cycles() + + sec_2_cycles(bcp->congested_period); + stat->s_bau_disabled++; + for_each_present_cpu(tcpu) { + tbcp = &per_cpu(bau_control, tcpu); + tbcp->baudisabled = 1; + } + } + spin_unlock(&disable_lock); +} + /** * uv_flush_send_and_wait * * Send a broadcast and wait for it to complete. * - * The flush_mask contains the cpus the broadcast is to be sent to, plus + * The flush_mask contains the cpus the broadcast is to be sent to including * cpus that are on the local uvhub. * - * 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, representing any cpus on the local - * uvhub (not current cpu) and any on remote uvhubs if the broadcast failed. + * Returns 0 if all flushing represented in the mask was done. + * Returns 1 if it gives up entirely and the original cpu mask is to be + * returned to the kernel. */ -const struct cpumask *uv_flush_send_and_wait(struct bau_desc *bau_desc, - struct cpumask *flush_mask, - struct bau_control *bcp) +int uv_flush_send_and_wait(struct bau_desc *bau_desc, + struct cpumask *flush_mask, struct bau_control *bcp) { int right_shift; - 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); + cycles_t elapsed; + struct ptc_stats *stat = bcp->statp; 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)) { + hmaster->max_bau_concurrent)) { stat->s_throttles++; do { cpu_relax(); } while (!atomic_inc_unless_ge(&hmaster->uvhub_lock, &hmaster->active_descriptor_count, - hmaster->max_concurrent)); + hmaster->max_bau_concurrent)); } - while (hmaster->uvhub_quiesce) cpu_relax(); @@ -557,23 +607,10 @@ const struct cpumask *uv_flush_send_and_wait(struct bau_desc *bau_desc, } time1 = get_cycles(); do { - /* - * 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 */ + bau_desc->header.msg_type = MSG_REGULAR; 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++; } @@ -581,50 +618,17 @@ const struct cpumask *uv_flush_send_and_wait(struct bau_desc *bau_desc, index = (1UL << UVH_LB_BAU_SB_ACTIVATION_CONTROL_PUSH_SHFT) | 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, 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++; - } + destination_plugged(bau_desc, bcp, hmaster, stat); } 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++; - } + destination_timeout(bau_desc, bcp, hmaster, stat); } - if (bcp->ipi_attempts >= 3) { + if (bcp->ipi_attempts >= bcp->ipi_reset_limit) { bcp->ipi_attempts = 0; completion_status = FLUSH_GIVEUP; break; @@ -633,49 +637,36 @@ const struct cpumask *uv_flush_send_and_wait(struct bau_desc *bau_desc, } while ((completion_status == FLUSH_RETRY_PLUGGED) || (completion_status == FLUSH_RETRY_TIMEOUT)); time2 = get_cycles(); - - 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 - */ + bcp->plugged_tries = 0; + bcp->timeout_tries = 0; + if ((completion_status == FLUSH_COMPLETE) && + (bcp->conseccompletes > bcp->complete_threshold) && + (hmaster->max_bau_concurrent < + hmaster->max_bau_concurrent_constant)) + hmaster->max_bau_concurrent++; 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 (time2 > time1) { + elapsed = time2 - time1; + stat->s_time += elapsed; + if ((completion_status == FLUSH_COMPLETE) && (try == 1)) { + bcp->period_requests++; + bcp->period_time += elapsed; + if ((elapsed > congested_cycles) && + (bcp->period_requests > bcp->congested_reps)) { + disable_for_congestion(bcp, stat); + } + } + } else + stat->s_requestor--; 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 target cpu's, all of which are still in the mask. - */ stat->s_giveup++; - return flush_mask; - } - - /* - * Success, so clear the remote cpu's from the mask so we don't - * use the IPI method of shootdown on them. - */ - for_each_cpu(bit, flush_mask) { - uvhub = uv_cpu_to_blade_id(bit); - if (uvhub == this_uvhub) - continue; - cpumask_clear_cpu(bit, flush_mask); + return 1; } - if (!cpumask_empty(flush_mask)) - return flush_mask; - - return NULL; + return 0; } /** @@ -707,70 +698,89 @@ const struct cpumask *uv_flush_tlb_others(const struct cpumask *cpumask, struct mm_struct *mm, unsigned long va, unsigned int cpu) { - int remotes; int tcpu; int uvhub; int locals = 0; + int remotes = 0; + int hubs = 0; struct bau_desc *bau_desc; struct cpumask *flush_mask; struct ptc_stats *stat; struct bau_control *bcp; + struct bau_control *tbcp; + /* kernel was booted 'nobau' */ if (nobau) return cpumask; bcp = &per_cpu(bau_control, cpu); + stat = bcp->statp; + + /* bau was disabled due to slow response */ + if (bcp->baudisabled) { + /* the cpu that disabled it must re-enable it */ + if (bcp->set_bau_off) { + if (get_cycles() >= bcp->set_bau_on_time) { + stat->s_bau_reenabled++; + baudisabled = 0; + for_each_present_cpu(tcpu) { + tbcp = &per_cpu(bau_control, tcpu); + tbcp->baudisabled = 0; + tbcp->period_requests = 0; + tbcp->period_time = 0; + } + } + } + return cpumask; + } + /* * 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. + * cpu mask. All cpus are converted to uvhubs and copied to the + * activation descriptor. */ 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) - */ + /* don't actually do a shootdown of the local cpu */ cpumask_andnot(flush_mask, cpumask, cpumask_of(cpu)); if (cpu_isset(cpu, *cpumask)) - locals++; /* current cpu was targeted */ + stat->s_ntargself++; bau_desc = bcp->descriptor_base; bau_desc += UV_ITEMS_PER_DESCRIPTOR * bcp->uvhub_cpu; - bau_uvhubs_clear(&bau_desc->distribution, UV_DISTRIBUTION_SIZE); - remotes = 0; + + /* cpu statistics */ for_each_cpu(tcpu, flush_mask) { uvhub = uv_cpu_to_blade_id(tcpu); - if (uvhub == bcp->uvhub) { - locals++; - continue; - } bau_uvhub_set(uvhub, &bau_desc->distribution); - remotes++; - } - if (remotes == 0) { - /* - * 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 cpumask; + if (uvhub == bcp->uvhub) + locals++; else - return NULL; + remotes++; } - stat = &per_cpu(ptcstats, cpu); + if ((locals + remotes) == 0) + return NULL; stat->s_requestor++; - stat->s_ntargcpu += remotes; + stat->s_ntargcpu += remotes + locals; + stat->s_ntargremotes += remotes; + stat->s_ntarglocals += locals; remotes = bau_uvhub_weight(&bau_desc->distribution); - stat->s_ntarguvhub += remotes; - if (remotes >= 16) + + /* uvhub statistics */ + hubs = bau_uvhub_weight(&bau_desc->distribution); + if (locals) { + stat->s_ntarglocaluvhub++; + stat->s_ntargremoteuvhub += (hubs - 1); + } else + stat->s_ntargremoteuvhub += hubs; + stat->s_ntarguvhub += hubs; + if (hubs >= 16) stat->s_ntarguvhub16++; - else if (remotes >= 8) + else if (hubs >= 8) stat->s_ntarguvhub8++; - else if (remotes >= 4) + else if (hubs >= 4) stat->s_ntarguvhub4++; - else if (remotes >= 2) + else if (hubs >= 2) stat->s_ntarguvhub2++; else stat->s_ntarguvhub1++; @@ -779,10 +789,13 @@ const struct cpumask *uv_flush_tlb_others(const struct cpumask *cpumask, bau_desc->payload.sending_cpu = cpu; /* - * 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. + * uv_flush_send_and_wait returns 0 if all cpu's were messaged, + * or 1 if it gave up and the original cpumask should be returned. */ - return uv_flush_send_and_wait(bau_desc, flush_mask, bcp); + if (!uv_flush_send_and_wait(bau_desc, flush_mask, bcp)) + return NULL; + else + return cpumask; } /* @@ -810,7 +823,7 @@ void uv_bau_message_interrupt(struct pt_regs *regs) time_start = get_cycles(); bcp = &per_cpu(bau_control, smp_processor_id()); - stat = &per_cpu(ptcstats, smp_processor_id()); + stat = bcp->statp; msgdesc.va_queue_first = bcp->va_queue_first; msgdesc.va_queue_last = bcp->va_queue_last; msg = bcp->bau_msg_head; @@ -908,12 +921,12 @@ static void uv_ptc_seq_stop(struct seq_file *file, void *data) } static inline unsigned long long -millisec_2_cycles(unsigned long millisec) +microsec_2_cycles(unsigned long microsec) { unsigned long ns; unsigned long long cyc; - ns = millisec * 1000; + ns = microsec * 1000; cyc = (ns << CYC2NS_SCALE_FACTOR)/(per_cpu(cyc2ns, smp_processor_id())); return cyc; } @@ -931,15 +944,19 @@ static int uv_ptc_seq_show(struct seq_file *file, void *data) if (!cpu) { seq_printf(file, - "# cpu sent stime numuvhubs numuvhubs16 numuvhubs8 "); + "# cpu sent stime self locals remotes ncpus localhub "); + seq_printf(file, + "remotehub numuvhubs numuvhubs16 numuvhubs8 "); seq_printf(file, - "numuvhubs4 numuvhubs2 numuvhubs1 numcpus dto "); + "numuvhubs4 numuvhubs2 numuvhubs1 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"); + "one mult none retry canc nocan reset rcan "); + seq_printf(file, + "disable enable\n"); } if (cpu < num_possible_cpus() && cpu_online(cpu)) { stat = &per_cpu(ptcstats, cpu); @@ -947,18 +964,23 @@ static int uv_ptc_seq_show(struct seq_file *file, void *data) 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_ntargself, stat->s_ntarglocals, + stat->s_ntargremotes, stat->s_ntargcpu, + stat->s_ntarglocaluvhub, stat->s_ntargremoteuvhub, + stat->s_ntarguvhub, stat->s_ntarguvhub16); + seq_printf(file, "%ld %ld %ld %ld %ld ", stat->s_ntarguvhub8, stat->s_ntarguvhub4, stat->s_ntarguvhub2, stat->s_ntarguvhub1, - stat->s_ntargcpu, stat->s_dtimeout); + 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", + "%lx %ld %ld %ld %ld %ld %ld %ld %ld %ld %ld %ld ", uv_read_global_mmr64(uv_cpu_to_pnode(cpu), UVH_LB_BAU_INTD_SOFTWARE_ACKNOWLEDGE), stat->d_requestee, cycles_2_us(stat->d_time), @@ -966,15 +988,36 @@ static int uv_ptc_seq_show(struct seq_file *file, void *data) stat->d_nomsg, stat->d_retries, stat->d_canceled, stat->d_nocanceled, stat->d_resets, stat->d_rcanceled); + seq_printf(file, "%ld %ld\n", + stat->s_bau_disabled, stat->s_bau_reenabled); } return 0; } /* + * Display the tunables thru debugfs + */ +static ssize_t tunables_read(struct file *file, char __user *userbuf, + size_t count, loff_t *ppos) +{ + char buf[300]; + int ret; + + ret = snprintf(buf, 300, "%s %s %s\n%d %d %d %d %d %d %d %d %d\n", + "max_bau_concurrent plugged_delay plugsb4reset", + "timeoutsb4reset ipi_reset_limit complete_threshold", + "congested_response_us congested_reps congested_period", + max_bau_concurrent, plugged_delay, plugsb4reset, + timeoutsb4reset, ipi_reset_limit, complete_threshold, + congested_response_us, congested_reps, congested_period); + + return simple_read_from_buffer(userbuf, count, ppos, buf, ret); +} + +/* * -1: resetf the statistics * 0: display meaning of the statistics - * >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) @@ -983,7 +1026,6 @@ static ssize_t uv_ptc_proc_write(struct file *file, const char __user *user, long input_arg; char optstr[64]; struct ptc_stats *stat; - struct bau_control *bcp; if (count == 0 || count > sizeof(optstr)) return -EINVAL; @@ -1059,29 +1101,158 @@ static ssize_t uv_ptc_proc_write(struct file *file, const char __user *user, "reset: number of ipi-style reset requests processed\n"); printk(KERN_DEBUG "rcan: number messages canceled by reset requests\n"); + printk(KERN_DEBUG + "disable: number times use of the BAU was disabled\n"); + printk(KERN_DEBUG + "enable: number times use of the BAU was re-enabled\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_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; +} + +static int local_atoi(const char *name) +{ + int val = 0; + + for (;; name++) { + switch (*name) { + case '0' ... '9': + val = 10*val+(*name-'0'); + break; + default: + return val; } } +} + +/* + * set the tunables + * 0 values reset them to defaults + */ +static ssize_t tunables_write(struct file *file, const char __user *user, + size_t count, loff_t *data) +{ + int cpu; + int cnt = 0; + int val; + char *p; + char *q; + char instr[64]; + struct bau_control *bcp; + + if (count == 0 || count > sizeof(instr)-1) + return -EINVAL; + if (copy_from_user(instr, user, count)) + return -EFAULT; + instr[count] = '\0'; + /* count the fields */ + p = instr + strspn(instr, WHITESPACE); + q = p; + for (; *p; p = q + strspn(q, WHITESPACE)) { + q = p + strcspn(p, WHITESPACE); + cnt++; + if (q == p) + break; + } + if (cnt != 9) { + printk(KERN_INFO "bau tunable error: should be 9 numbers\n"); + return -EINVAL; + } + + p = instr + strspn(instr, WHITESPACE); + q = p; + for (cnt = 0; *p; p = q + strspn(q, WHITESPACE), cnt++) { + q = p + strcspn(p, WHITESPACE); + val = local_atoi(p); + switch (cnt) { + case 0: + if (val == 0) { + max_bau_concurrent = MAX_BAU_CONCURRENT; + max_bau_concurrent_constant = + MAX_BAU_CONCURRENT; + continue; + } + bcp = &per_cpu(bau_control, smp_processor_id()); + if (val < 1 || val > bcp->cpus_in_uvhub) { + printk(KERN_DEBUG + "Error: BAU max concurrent %d is invalid\n", + val); + return -EINVAL; + } + max_bau_concurrent = val; + max_bau_concurrent_constant = val; + continue; + case 1: + if (val == 0) + plugged_delay = PLUGGED_DELAY; + else + plugged_delay = val; + continue; + case 2: + if (val == 0) + plugsb4reset = PLUGSB4RESET; + else + plugsb4reset = val; + continue; + case 3: + if (val == 0) + timeoutsb4reset = TIMEOUTSB4RESET; + else + timeoutsb4reset = val; + continue; + case 4: + if (val == 0) + ipi_reset_limit = IPI_RESET_LIMIT; + else + ipi_reset_limit = val; + continue; + case 5: + if (val == 0) + complete_threshold = COMPLETE_THRESHOLD; + else + complete_threshold = val; + continue; + case 6: + if (val == 0) + congested_response_us = CONGESTED_RESPONSE_US; + else + congested_response_us = val; + continue; + case 7: + if (val == 0) + congested_reps = CONGESTED_REPS; + else + congested_reps = val; + continue; + case 8: + if (val == 0) + congested_period = CONGESTED_PERIOD; + else + congested_period = val; + continue; + } + if (q == p) + break; + } + for_each_present_cpu(cpu) { + bcp = &per_cpu(bau_control, cpu); + bcp->max_bau_concurrent = max_bau_concurrent; + bcp->max_bau_concurrent_constant = max_bau_concurrent; + bcp->plugged_delay = plugged_delay; + bcp->plugsb4reset = plugsb4reset; + bcp->timeoutsb4reset = timeoutsb4reset; + bcp->ipi_reset_limit = ipi_reset_limit; + bcp->complete_threshold = complete_threshold; + bcp->congested_response_us = congested_response_us; + bcp->congested_reps = congested_reps; + bcp->congested_period = congested_period; + } return count; } @@ -1097,6 +1268,11 @@ static int uv_ptc_proc_open(struct inode *inode, struct file *file) return seq_open(file, &uv_ptc_seq_ops); } +static int tunables_open(struct inode *inode, struct file *file) +{ + return 0; +} + static const struct file_operations proc_uv_ptc_operations = { .open = uv_ptc_proc_open, .read = seq_read, @@ -1105,6 +1281,12 @@ static const struct file_operations proc_uv_ptc_operations = { .release = seq_release, }; +static const struct file_operations tunables_fops = { + .open = tunables_open, + .read = tunables_read, + .write = tunables_write, +}; + static int __init uv_ptc_init(void) { struct proc_dir_entry *proc_uv_ptc; @@ -1119,6 +1301,20 @@ static int __init uv_ptc_init(void) UV_PTC_BASENAME); return -EINVAL; } + + tunables_dir = debugfs_create_dir(UV_BAU_TUNABLES_DIR, NULL); + if (!tunables_dir) { + printk(KERN_ERR "unable to create debugfs directory %s\n", + UV_BAU_TUNABLES_DIR); + return -EINVAL; + } + tunables_file = debugfs_create_file(UV_BAU_TUNABLES_FILE, 0600, + tunables_dir, NULL, &tunables_fops); + if (!tunables_file) { + printk(KERN_ERR "unable to create debugfs file %s\n", + UV_BAU_TUNABLES_FILE); + return -EINVAL; + } return 0; } @@ -1259,15 +1455,45 @@ static void __init uv_init_uvhub(int uvhub, int vector) } /* + * We will set BAU_MISC_CONTROL with a timeout period. + * But the BIOS has set UVH_AGING_PRESCALE_SEL and UVH_TRANSACTION_TIMEOUT. + * So the destination timeout period has be be calculated from them. + */ +static int +calculate_destination_timeout(void) +{ + unsigned long mmr_image; + int mult1; + int mult2; + int index; + int base; + int ret; + unsigned long ts_ns; + + mult1 = UV_INTD_SOFT_ACK_TIMEOUT_PERIOD & BAU_MISC_CONTROL_MULT_MASK; + mmr_image = uv_read_local_mmr(UVH_AGING_PRESCALE_SEL); + index = (mmr_image >> BAU_URGENCY_7_SHIFT) & BAU_URGENCY_7_MASK; + mmr_image = uv_read_local_mmr(UVH_TRANSACTION_TIMEOUT); + mult2 = (mmr_image >> BAU_TRANS_SHIFT) & BAU_TRANS_MASK; + base = timeout_base_ns[index]; + ts_ns = base * mult1 * mult2; + ret = ts_ns / 1000; + return ret; +} + +/* * initialize the bau_control structure for each cpu */ -static void uv_init_per_cpu(int nuvhubs) +static void __init uv_init_per_cpu(int nuvhubs) { - int i, j, k; + int i; int cpu; int pnode; int uvhub; + int have_hmaster; short socket = 0; + unsigned short socket_mask; + unsigned char *uvhub_mask; struct bau_control *bcp; struct uvhub_desc *bdp; struct socket_desc *sdp; @@ -1278,7 +1504,7 @@ static void uv_init_per_cpu(int nuvhubs) short cpu_number[16]; }; struct uvhub_desc { - short num_sockets; + unsigned short socket_mask; short num_cpus; short uvhub; short pnode; @@ -1286,57 +1512,84 @@ static void uv_init_per_cpu(int nuvhubs) }; struct uvhub_desc *uvhub_descs; + timeout_us = calculate_destination_timeout(); + uvhub_descs = (struct uvhub_desc *) kmalloc(nuvhubs * sizeof(struct uvhub_desc), GFP_KERNEL); memset(uvhub_descs, 0, nuvhubs * sizeof(struct uvhub_desc)); + uvhub_mask = kzalloc((nuvhubs+7)/8, GFP_KERNEL); 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; + *(uvhub_mask + (uvhub/8)) |= (1 << (uvhub%8)); 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; + /* kludge: 'assuming' one node per socket, and assuming that + disabling a socket just leaves a gap in node numbers */ + socket = (cpu_to_node(cpu) & 1); + bdp->socket_mask |= (1 << socket); sdp = &bdp->socket[socket]; sdp->cpu_number[sdp->num_cpus] = cpu; sdp->num_cpus++; } - socket = 0; - for_each_possible_blade(uvhub) { + for (uvhub = 0; uvhub < nuvhubs; uvhub++) { + if (!(*(uvhub_mask + (uvhub/8)) & (1 << (uvhub%8)))) + continue; + have_hmaster = 0; 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]; + socket_mask = bdp->socket_mask; + socket = 0; + while (socket_mask) { + if (!(socket_mask & 1)) + goto nextsocket; + sdp = &bdp->socket[socket]; + for (i = 0; i < sdp->num_cpus; i++) { + cpu = sdp->cpu_number[i]; bcp = &per_cpu(bau_control, cpu); bcp->cpu = cpu; - if (j == 0) { + if (i == 0) { smaster = bcp; - if (i == 0) + if (!have_hmaster) { + have_hmaster++; hmaster = bcp; + } } bcp->cpus_in_uvhub = bdp->num_cpus; bcp->cpus_in_socket = sdp->num_cpus; bcp->socket_master = smaster; + bcp->uvhub = bdp->uvhub; 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; + bcp->uvhub_cpu = uv_cpu_hub_info(cpu)-> + blade_processor_id; } +nextsocket: socket++; + socket_mask = (socket_mask >> 1); } } kfree(uvhub_descs); + kfree(uvhub_mask); + for_each_present_cpu(cpu) { + bcp = &per_cpu(bau_control, cpu); + bcp->baudisabled = 0; + bcp->statp = &per_cpu(ptcstats, cpu); + /* time interval to catch a hardware stay-busy bug */ + bcp->timeout_interval = microsec_2_cycles(2*timeout_us); + bcp->max_bau_concurrent = max_bau_concurrent; + bcp->max_bau_concurrent_constant = max_bau_concurrent; + bcp->plugged_delay = plugged_delay; + bcp->plugsb4reset = plugsb4reset; + bcp->timeoutsb4reset = timeoutsb4reset; + bcp->ipi_reset_limit = ipi_reset_limit; + bcp->complete_threshold = complete_threshold; + bcp->congested_response_us = congested_response_us; + bcp->congested_reps = congested_reps; + bcp->congested_period = congested_period; + } } /* @@ -1361,10 +1614,11 @@ static int __init uv_bau_init(void) zalloc_cpumask_var_node(&per_cpu(uv_flush_tlb_mask, cur_cpu), GFP_KERNEL, cpu_to_node(cur_cpu)); - uv_bau_max_concurrent = MAX_BAU_CONCURRENT; uv_nshift = uv_hub_info->m_val; uv_mmask = (1UL << uv_hub_info->m_val) - 1; nuvhubs = uv_num_possible_blades(); + spin_lock_init(&disable_lock); + congested_cycles = microsec_2_cycles(congested_response_us); uv_init_per_cpu(nuvhubs); @@ -1383,15 +1637,19 @@ static int __init uv_bau_init(void) 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); + if (uv_blade_nr_possible_cpus(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; } core_initcall(uv_bau_init); -core_initcall(uv_ptc_init); +fs_initcall(uv_ptc_init); diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c index 725ef4d17cd5..60788dee0f8a 100644 --- a/arch/x86/kernel/traps.c +++ b/arch/x86/kernel/traps.c @@ -392,7 +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. @@ -400,6 +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); diff --git a/arch/x86/kernel/tsc.c b/arch/x86/kernel/tsc.c index 9faf91ae1841..ce8e50239332 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/verify_cpu_64.S b/arch/x86/kernel/verify_cpu_64.S index 45b6f8a975a1..56a8c2a867d9 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/vsyscall_64.c b/arch/x86/kernel/vsyscall_64.c index 1c0c6ab9c60f..dcbb28c4b694 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/xsave.c b/arch/x86/kernel/xsave.c index 37e68fc5e24a..9c253bd65e24 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; } @@ -91,14 +169,6 @@ 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 (use_xsave()) err = xsave_user(buf); else @@ -109,6 +179,7 @@ int save_i387_xstate(void __user *buf) task_thread_info(tsk)->status &= ~TS_USEDFPU; stts(); } else { + sanitize_i387_state(tsk); if (__copy_to_user(buf, &tsk->thread.fpu.state->fxsave, xstate_size)) return -1; @@ -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; @@ -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 5ac0bb465ed6..b38bd8b92aa6 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> @@ -67,6 +68,9 @@ #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) @@ -88,10 +92,6 @@ #define Src2CL (1<<29) #define Src2ImmByte (2<<29) #define Src2One (3<<29) -#define Src2Imm16 (4<<29) -#define Src2Mem16 (5<<29) /* Used for Ep encoding. First argument has to be - in memory and second argument is located - immediately after the first one in memory. */ #define Src2Mask (7<<29) enum { @@ -124,15 +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, @@ -170,20 +170,20 @@ 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 | 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 | DstDI | Mov | String, DstDI | Mov | 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 */ @@ -215,7 +215,7 @@ static u32 opcode_table[256] = { ByteOp | SrcImmUByte | DstAcc, SrcImmUByte | DstAcc, /* 0xE8 - 0xEF */ SrcImm | Stack, SrcImm | ImplicitOps, - SrcImmU | Src2Imm16 | No64, SrcImmByte | ImplicitOps, + SrcImmFAddr | No64, SrcImmByte | ImplicitOps, SrcNone | ByteOp | DstAcc, SrcNone | DstAcc, SrcNone | ByteOp | DstAcc, SrcNone | DstAcc, /* 0xF0 - 0xF7 */ @@ -337,20 +337,20 @@ 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, SrcMem | ModRM | Src2Mem16 | ImplicitOps, + SrcMem | ModRM | Stack, SrcMemFAddr | ModRM | ImplicitOps, SrcMem | ModRM | Stack, 0, [Group7*8] = 0, 0, ModRM | SrcMem | Priv, ModRM | SrcMem | Priv, @@ -576,6 +576,13 @@ static u32 group2_table[] = { (_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; @@ -617,31 +624,66 @@ 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 void emulate_gp(struct x86_emulate_ctxt *ctxt, int err) +{ + emulate_exception(ctxt, GP_VECTOR, err, true); } -static unsigned long es_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_ES); + ctxt->cr2 = addr; + emulate_exception(ctxt, PF_VECTOR, err, true); } -static unsigned long ss_base(struct x86_emulate_ctxt *ctxt) +static void emulate_ud(struct x86_emulate_ctxt *ctxt) { - return seg_base(ctxt, VCPU_SREG_SS); + 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, @@ -932,12 +974,9 @@ x86_decode_insn(struct x86_emulate_ctxt *ctxt, struct x86_emulate_ops *ops) /* we cannot decode insn before we complete previous rep insn */ WARN_ON(ctxt->restart); - /* Shadow copy of register state. Committed on successful emulation. */ - memset(c, 0, sizeof(struct decode_cache)); c->eip = ctxt->eip; c->fetch.start = c->fetch.end = c->eip; - ctxt->cs_base = seg_base(ctxt, VCPU_SREG_CS); - memcpy(c->regs, ctxt->vcpu->arch.regs, sizeof c->regs); + ctxt->cs_base = seg_base(ctxt, ops, VCPU_SREG_CS); switch (mode) { case X86EMUL_MODE_REAL: @@ -1060,7 +1099,7 @@ done_prefixes: 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; @@ -1148,6 +1187,25 @@ 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; @@ -1156,10 +1214,21 @@ done_prefixes: 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, c), + 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; } /* @@ -1179,22 +1248,10 @@ 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; break; - case Src2Mem16: - c->src2.type = OP_MEM; - c->src2.bytes = 2; - c->src2.ptr = (unsigned long *)(c->modrm_ea + c->src.bytes); - c->src2.val = 0; - break; } /* Decode and fetch the destination operand: register or memory. */ @@ -1253,7 +1310,7 @@ done_prefixes: 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), + register_address(c, es_base(ctxt, ops), c->regs[VCPU_REGS_RDI]); c->dst.val = 0; break; @@ -1263,6 +1320,37 @@ done: return (rc == X86EMUL_UNHANDLEABLE) ? -1 : 0; } +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, @@ -1330,13 +1418,13 @@ static int read_segment_descriptor(struct x86_emulate_ctxt *ctxt, get_descriptor_table_ptr(ctxt, ops, selector, &dt); if (dt.size < index * 8 + 7) { - kvm_inject_gp(ctxt->vcpu, selector & 0xfffc); + 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) - kvm_inject_page_fault(ctxt->vcpu, addr, err); + emulate_pf(ctxt, addr, err); return ret; } @@ -1355,14 +1443,14 @@ static int write_segment_descriptor(struct x86_emulate_ctxt *ctxt, get_descriptor_table_ptr(ctxt, ops, selector, &dt); if (dt.size < index * 8 + 7) { - kvm_inject_gp(ctxt->vcpu, selector & 0xfffc); + 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) - kvm_inject_page_fault(ctxt->vcpu, addr, err); + emulate_pf(ctxt, addr, err); return ret; } @@ -1481,11 +1569,70 @@ load: ops->set_cached_descriptor(&seg_desc, seg, ctxt->vcpu); return X86EMUL_CONTINUE; exception: - kvm_queue_exception_e(ctxt->vcpu, err_vec, err_code); + emulate_exception(ctxt, err_vec, err_code, true); return X86EMUL_PROPAGATE_FAULT; } -static inline void emulate_push(struct x86_emulate_ctxt *ctxt) +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; @@ -1493,7 +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]); } @@ -1504,9 +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; @@ -1541,7 +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; @@ -1557,15 +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, @@ -1583,19 +1729,31 @@ static int emulate_pop_sreg(struct x86_emulate_ctxt *ctxt, 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, @@ -1695,14 +1853,14 @@ 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 X86EMUL_CONTINUE; @@ -1748,145 +1906,82 @@ static int emulate_ret_far(struct x86_emulate_ctxt *ctxt, 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 X86EMUL_CONTINUE; -} - -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) { - kvm_queue_exception(ctxt->vcpu, UD_VECTOR); + 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); @@ -1896,15 +1991,16 @@ 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); + emulate_gp(ctxt, 0); return X86EMUL_PROPAGATE_FAULT; } @@ -1912,67 +2008,70 @@ emulate_sysenter(struct x86_emulate_ctxt *ctxt) * Therefore, we inject an #UD. */ if (ctxt->mode == X86EMUL_MODE_PROT64) { - kvm_queue_exception(ctxt->vcpu, UD_VECTOR); + 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); + 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; @@ -1981,35 +2080,37 @@ 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; } @@ -2030,25 +2131,25 @@ 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) @@ -2066,17 +2167,6 @@ static bool emulator_io_permited(struct x86_emulate_ctxt *ctxt, return true; } -static u32 get_cached_descriptor_base(struct x86_emulate_ctxt *ctxt, - struct x86_emulate_ops *ops, - int seg) -{ - struct desc_struct desc; - if (ops->get_cached_descriptor(&desc, seg, ctxt->vcpu)) - return get_desc_base(&desc); - else - return ~0; -} - static void save_state_to_tss16(struct x86_emulate_ctxt *ctxt, struct x86_emulate_ops *ops, struct tss_segment_16 *tss) @@ -2165,7 +2255,7 @@ static int task_switch_16(struct x86_emulate_ctxt *ctxt, &err); if (ret == X86EMUL_PROPAGATE_FAULT) { /* FIXME: need to provide precise fault address */ - kvm_inject_page_fault(ctxt->vcpu, old_tss_base, err); + emulate_pf(ctxt, old_tss_base, err); return ret; } @@ -2175,7 +2265,7 @@ static int task_switch_16(struct x86_emulate_ctxt *ctxt, &err); if (ret == X86EMUL_PROPAGATE_FAULT) { /* FIXME: need to provide precise fault address */ - kvm_inject_page_fault(ctxt->vcpu, old_tss_base, err); + emulate_pf(ctxt, old_tss_base, err); return ret; } @@ -2183,7 +2273,7 @@ static int task_switch_16(struct x86_emulate_ctxt *ctxt, &err); if (ret == X86EMUL_PROPAGATE_FAULT) { /* FIXME: need to provide precise fault address */ - kvm_inject_page_fault(ctxt->vcpu, new_tss_base, err); + emulate_pf(ctxt, new_tss_base, err); return ret; } @@ -2196,7 +2286,7 @@ static int task_switch_16(struct x86_emulate_ctxt *ctxt, ctxt->vcpu, &err); if (ret == X86EMUL_PROPAGATE_FAULT) { /* FIXME: need to provide precise fault address */ - kvm_inject_page_fault(ctxt->vcpu, new_tss_base, err); + emulate_pf(ctxt, new_tss_base, err); return ret; } } @@ -2238,7 +2328,10 @@ static int load_state_from_tss32(struct x86_emulate_ctxt *ctxt, struct decode_cache *c = &ctxt->decode; int ret; - ops->set_cr(3, tss->cr3, ctxt->vcpu); + 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; @@ -2304,7 +2397,7 @@ static int task_switch_32(struct x86_emulate_ctxt *ctxt, &err); if (ret == X86EMUL_PROPAGATE_FAULT) { /* FIXME: need to provide precise fault address */ - kvm_inject_page_fault(ctxt->vcpu, old_tss_base, err); + emulate_pf(ctxt, old_tss_base, err); return ret; } @@ -2314,7 +2407,7 @@ static int task_switch_32(struct x86_emulate_ctxt *ctxt, &err); if (ret == X86EMUL_PROPAGATE_FAULT) { /* FIXME: need to provide precise fault address */ - kvm_inject_page_fault(ctxt->vcpu, old_tss_base, err); + emulate_pf(ctxt, old_tss_base, err); return ret; } @@ -2322,7 +2415,7 @@ static int task_switch_32(struct x86_emulate_ctxt *ctxt, &err); if (ret == X86EMUL_PROPAGATE_FAULT) { /* FIXME: need to provide precise fault address */ - kvm_inject_page_fault(ctxt->vcpu, new_tss_base, err); + emulate_pf(ctxt, new_tss_base, err); return ret; } @@ -2335,7 +2428,7 @@ static int task_switch_32(struct x86_emulate_ctxt *ctxt, ctxt->vcpu, &err); if (ret == X86EMUL_PROPAGATE_FAULT) { /* FIXME: need to provide precise fault address */ - kvm_inject_page_fault(ctxt->vcpu, new_tss_base, err); + emulate_pf(ctxt, new_tss_base, err); return ret; } } @@ -2352,7 +2445,7 @@ static int emulator_do_task_switch(struct x86_emulate_ctxt *ctxt, int ret; u16 old_tss_sel = ops->get_segment_selector(VCPU_SREG_TR, ctxt->vcpu); ulong old_tss_base = - get_cached_descriptor_base(ctxt, ops, VCPU_SREG_TR); + ops->get_cached_segment_base(VCPU_SREG_TR, ctxt->vcpu); u32 desc_limit; /* FIXME: old_tss_base == ~0 ? */ @@ -2369,7 +2462,7 @@ static int emulator_do_task_switch(struct x86_emulate_ctxt *ctxt, if (reason != TASK_SWITCH_IRET) { if ((tss_selector & 3) > next_tss_desc.dpl || ops->cpl(ctxt->vcpu) > next_tss_desc.dpl) { - kvm_inject_gp(ctxt->vcpu, 0); + emulate_gp(ctxt, 0); return X86EMUL_PROPAGATE_FAULT; } } @@ -2378,8 +2471,7 @@ static int emulator_do_task_switch(struct x86_emulate_ctxt *ctxt, if (!next_tss_desc.p || ((desc_limit < 0x67 && (next_tss_desc.type & 8)) || desc_limit < 0x2b)) { - kvm_queue_exception_e(ctxt->vcpu, TS_VECTOR, - tss_selector & 0xfffc); + emulate_ts(ctxt, tss_selector & 0xfffc); return X86EMUL_PROPAGATE_FAULT; } @@ -2425,7 +2517,7 @@ static int emulator_do_task_switch(struct x86_emulate_ctxt *ctxt, 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); + emulate_push(ctxt, ops); } return ret; @@ -2439,18 +2531,16 @@ int emulator_task_switch(struct x86_emulate_ctxt *ctxt, struct decode_cache *c = &ctxt->decode; int rc; - memset(c, 0, sizeof(struct decode_cache)); c->eip = ctxt->eip; - memcpy(c->regs, ctxt->vcpu->arch.regs, sizeof c->regs); c->dst.type = OP_NONE; rc = emulator_do_task_switch(ctxt, ops, tss_selector, reason, has_error_code, error_code); if (rc == X86EMUL_CONTINUE) { - memcpy(ctxt->vcpu->arch.regs, c->regs, sizeof c->regs); - kvm_rip_write(ctxt->vcpu, c->eip); rc = writeback(ctxt, ops); + if (rc == X86EMUL_CONTINUE) + ctxt->eip = c->eip; } return (rc == X86EMUL_UNHANDLEABLE) ? -1 : 0; @@ -2474,29 +2564,22 @@ x86_emulate_insn(struct x86_emulate_ctxt *ctxt, struct x86_emulate_ops *ops) int rc = X86EMUL_CONTINUE; int saved_dst_type = c->dst.type; - ctxt->interruptibility = 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); + ctxt->decode.mem_read.pos = 0; if (ctxt->mode == X86EMUL_MODE_PROT64 && (c->d & No64)) { - kvm_queue_exception(ctxt->vcpu, UD_VECTOR); + emulate_ud(ctxt); goto done; } /* LOCK prefix is allowed only with some instructions */ if (c->lock_prefix && (!(c->d & Lock) || c->dst.type != OP_MEM)) { - kvm_queue_exception(ctxt->vcpu, UD_VECTOR); + emulate_ud(ctxt); goto done; } /* Privileged instruction can be executed only in CPL=0 */ if ((c->d & Priv) && ops->cpl(ctxt->vcpu)) { - kvm_inject_gp(ctxt->vcpu, 0); + emulate_gp(ctxt, 0); goto done; } @@ -2506,7 +2589,7 @@ x86_emulate_insn(struct x86_emulate_ctxt *ctxt, struct x86_emulate_ops *ops) if (address_mask(c, c->regs[VCPU_REGS_RCX]) == 0) { string_done: ctxt->restart = false; - kvm_rip_write(ctxt->vcpu, c->eip); + ctxt->eip = c->eip; goto done; } /* The second termination condition only applies for REPE @@ -2529,20 +2612,16 @@ x86_emulate_insn(struct x86_emulate_ctxt *ctxt, struct x86_emulate_ops *ops) } if (c->src.type == OP_MEM) { - 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 = ops->read_emulated((unsigned long)c->src2.ptr, - &c->src2.val, - c->src2.bytes, - ctxt->vcpu); + rc = read_emulated(ctxt, ops, (unsigned long)c->src2.ptr, + &c->src2.val, c->src2.bytes); if (rc != X86EMUL_CONTINUE) goto done; } @@ -2553,8 +2632,8 @@ x86_emulate_insn(struct x86_emulate_ctxt *ctxt, struct x86_emulate_ops *ops) if ((c->dst.type == OP_MEM) && !(c->d & Mov)) { /* optimisation - avoid slow emulated read if Mov */ - rc = ops->read_emulated((unsigned long)c->dst.ptr, &c->dst.val, - c->dst.bytes, ctxt->vcpu); + rc = read_emulated(ctxt, ops, (unsigned long)c->dst.ptr, + &c->dst.val, c->dst.bytes); if (rc != X86EMUL_CONTINUE) goto done; } @@ -2571,7 +2650,7 @@ 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); @@ -2583,14 +2662,14 @@ 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); @@ -2602,7 +2681,7 @@ 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); @@ -2632,7 +2711,7 @@ 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: @@ -2641,7 +2720,9 @@ special_insn: 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); @@ -2655,14 +2736,14 @@ 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->dst.bytes)) { - kvm_inject_gp(ctxt->vcpu, 0); + emulate_gp(ctxt, 0); goto done; } if (!pio_in_emulated(ctxt, ops, c->dst.bytes, @@ -2674,7 +2755,7 @@ special_insn: c->src.bytes = min(c->src.bytes, 4u); if (!emulator_io_permited(ctxt, ops, c->regs[VCPU_REGS_RDX], c->src.bytes)) { - kvm_inject_gp(ctxt->vcpu, 0); + emulate_gp(ctxt, 0); goto done; } ops->pio_out_emulated(c->src.bytes, c->regs[VCPU_REGS_RDX], @@ -2707,6 +2788,7 @@ special_insn: } break; case 0x84 ... 0x85: + test: emulate_2op_SrcV("test", c->src, c->dst, ctxt->eflags); break; case 0x86 ... 0x87: /* xchg */ @@ -2735,18 +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 <= VCPU_SREG_GS) - kvm_get_segment(ctxt->vcpu, &segreg, c->modrm_reg); - else { - kvm_queue_exception(ctxt->vcpu, UD_VECTOR); + 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; @@ -2757,12 +2834,12 @@ 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, KVM_X86_SHADOW_INT_MOV_SS); + ctxt->interruptibility = KVM_X86_SHADOW_INT_MOV_SS; rc = load_segment_descriptor(ctxt, ops, sel, c->modrm_reg); @@ -2775,19 +2852,19 @@ special_insn: 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; @@ -2797,19 +2874,15 @@ 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 */ goto mov; case 0xa6 ... 0xa7: /* cmps */ c->dst.type = OP_NONE; /* Disable writeback. */ DPRINTF("cmps: mem1=0x%p mem2=0x%p\n", c->src.ptr, c->dst.ptr); goto cmp; + case 0xa8 ... 0xa9: /* test ax, imm */ + goto test; case 0xaa ... 0xab: /* stos */ c->dst.val = c->regs[VCPU_REGS_RAX]; break; @@ -2855,19 +2928,23 @@ special_insn: 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 */ + case 0xea: { /* jmp far */ + unsigned short sel; jump_far: - if (load_segment_descriptor(ctxt, ops, c->src2.val, - VCPU_SREG_CS)) + 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); @@ -2879,20 +2956,20 @@ special_insn: do_io_in: c->dst.bytes = min(c->dst.bytes, 4u); if (!emulator_io_permited(ctxt, ops, c->src.val, c->dst.bytes)) { - kvm_inject_gp(ctxt->vcpu, 0); + emulate_gp(ctxt, 0); goto done; } if (!pio_in_emulated(ctxt, ops, c->dst.bytes, c->src.val, &c->dst.val)) goto done; /* IO is needed */ break; - case 0xee: /* out al,dx */ - case 0xef: /* out (e/r)ax,dx */ + 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)) { - kvm_inject_gp(ctxt->vcpu, 0); + emulate_gp(ctxt, 0); goto done; } ops->pio_out_emulated(c->dst.bytes, c->src.val, &c->dst.val, 1, @@ -2916,18 +2993,20 @@ special_insn: c->dst.type = OP_NONE; /* Disable writeback. */ break; case 0xfa: /* cli */ - if (emulator_bad_iopl(ctxt, ops)) - 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, ops)) - kvm_inject_gp(ctxt->vcpu, 0); - else { - toggle_interruptibility(ctxt, KVM_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. */ } @@ -2964,11 +3043,12 @@ writeback: c->dst.type = saved_dst_type; if ((c->d & SrcMask) == SrcSI) - string_addr_inc(ctxt, seg_override_base(ctxt, c), VCPU_REGS_RSI, - &c->src); + 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), VCPU_REGS_RDI, &c->dst); + 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; @@ -2981,11 +3061,12 @@ writeback: (rc->end != 0 && rc->end == rc->pos)) ctxt->restart = false; } - - /* Commit shadow register state. */ - memcpy(ctxt->vcpu->arch.regs, c->regs, sizeof c->regs); - kvm_rip_write(ctxt->vcpu, c->eip); - ops->set_rflags(ctxt->vcpu, ctxt->eflags); + /* + * 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; @@ -3051,7 +3132,7 @@ twobyte_insn: c->dst.type = OP_NONE; break; case 5: /* not defined */ - kvm_queue_exception(ctxt->vcpu, UD_VECTOR); + emulate_ud(ctxt); goto done; case 7: /* invlpg*/ emulate_invlpg(ctxt->vcpu, c->modrm_ea); @@ -3063,7 +3144,7 @@ twobyte_insn: } break; case 0x05: /* syscall */ - rc = emulate_syscall(ctxt); + rc = emulate_syscall(ctxt, ops); if (rc != X86EMUL_CONTINUE) goto done; else @@ -3073,8 +3154,11 @@ 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; @@ -3084,7 +3168,7 @@ twobyte_insn: case 1: case 5 ... 7: case 9 ... 15: - kvm_queue_exception(ctxt->vcpu, UD_VECTOR); + emulate_ud(ctxt); goto done; } c->regs[c->modrm_rm] = ops->get_cr(c->modrm_reg, ctxt->vcpu); @@ -3093,31 +3177,42 @@ twobyte_insn: case 0x21: /* mov from dr to reg */ if ((ops->get_cr(4, ctxt->vcpu) & X86_CR4_DE) && (c->modrm_reg == 4 || c->modrm_reg == 5)) { - kvm_queue_exception(ctxt->vcpu, UD_VECTOR); + emulate_ud(ctxt); goto done; } - emulator_get_dr(ctxt, c->modrm_reg, &c->regs[c->modrm_rm]); + 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 */ - ops->set_cr(c->modrm_reg, c->modrm_val, ctxt->vcpu); + 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 ((ops->get_cr(4, ctxt->vcpu) & X86_CR4_DE) && (c->modrm_reg == 4 || c->modrm_reg == 5)) { - kvm_queue_exception(ctxt->vcpu, UD_VECTOR); + 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; } - emulator_set_dr(ctxt, c->modrm_reg, c->regs[c->modrm_rm]); + 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); - if (kvm_set_msr(ctxt->vcpu, c->regs[VCPU_REGS_RCX], msr_data)) { - kvm_inject_gp(ctxt->vcpu, 0); + if (ops->set_msr(ctxt->vcpu, c->regs[VCPU_REGS_RCX], msr_data)) { + emulate_gp(ctxt, 0); goto done; } rc = X86EMUL_CONTINUE; @@ -3125,8 +3220,8 @@ twobyte_insn: break; case 0x32: /* rdmsr */ - if (kvm_get_msr(ctxt->vcpu, c->regs[VCPU_REGS_RCX], &msr_data)) { - kvm_inject_gp(ctxt->vcpu, 0); + 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; @@ -3136,14 +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 @@ -3160,7 +3255,7 @@ 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); @@ -3179,7 +3274,7 @@ 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); diff --git a/arch/x86/kvm/i8254.c b/arch/x86/kvm/i8254.c index 0150affad25d..0fd6378981f4 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 900d6b0ba7c2..46d08ca0b48f 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 93825ff3338f..8d10c063d7f2 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 +34,8 @@ #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) { @@ -43,16 +46,25 @@ static void pic_unlock(struct kvm_pic *s) __releases(&s->lock) { bool wakeup = s->wakeup_needed; - struct kvm_vcpu *vcpu; + struct kvm_vcpu *vcpu, *found = NULL; + int i; s->wakeup_needed = false; raw_spin_unlock(&s->lock); if (wakeup) { - vcpu = s->kvm->bsp_vcpu; - if (vcpu) - kvm_vcpu_kick(vcpu); + 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); } } @@ -173,10 +185,7 @@ 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) @@ -261,8 +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; @@ -301,8 +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) @@ -356,10 +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; @@ -518,9 +535,8 @@ static int picdev_read(struct kvm_io_device *this, /* * 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]); @@ -549,8 +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 96dfbb6ad2a9..2095a049835e 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 cd1f362f413d..ffed06871c5c 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 */ @@ -67,8 +65,6 @@ struct kvm_pic { 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 cff851cf5322..6491ac8e755b 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/lapic.c b/arch/x86/kvm/lapic.c index 1eb7a4ae0c9c..77d8c0f4817d 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 b1ed0a1a5913..311f6dad8951 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) \ @@ -173,7 +173,7 @@ struct kvm_shadow_walk_iterator { shadow_walk_okay(&(_walker)); \ shadow_walk_next(&(_walker))) -typedef int (*mmu_parent_walk_fn) (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; @@ -281,13 +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) { @@ -304,10 +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, @@ -355,10 +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, @@ -379,7 +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) @@ -390,7 +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; } /* @@ -403,8 +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; } @@ -414,9 +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); @@ -430,8 +471,7 @@ static void unaccount_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); @@ -447,8 +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; @@ -501,7 +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) @@ -513,8 +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; } @@ -541,9 +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); @@ -600,19 +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(); @@ -644,6 +675,32 @@ 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; @@ -676,7 +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); @@ -685,7 +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); @@ -709,9 +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; } @@ -731,8 +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; @@ -754,8 +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); @@ -763,9 +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); } } @@ -799,8 +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); @@ -863,7 +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); @@ -894,10 +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; } @@ -907,13 +965,15 @@ 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); bitmap_zero(sp->slot_bitmap, KVM_MEMORY_SLOTS + KVM_PRIVATE_MEM_SLOTS); @@ -998,7 +1058,6 @@ static void mmu_page_remove_parent_pte(struct kvm_mmu_page *sp, BUG(); } - static void mmu_parent_walk(struct kvm_mmu_page *sp, mmu_parent_walk_fn fn) { struct kvm_pte_chain *pte_chain; @@ -1008,63 +1067,37 @@ static void mmu_parent_walk(struct kvm_mmu_page *sp, mmu_parent_walk_fn fn) if (!sp->multimapped && sp->parent_pte) { parent_sp = page_header(__pa(sp->parent_pte)); - fn(parent_sp); - mmu_parent_walk(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(parent_sp); - mmu_parent_walk(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_mmu_page *sp) -{ - kvm_mmu_update_parents_unsync(sp); - return 1; -} - -static void kvm_mmu_mark_parents_unsync(struct kvm_mmu_page *sp) -{ - mmu_parent_walk(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, @@ -1077,7 +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; } @@ -1123,35 +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; } @@ -1166,26 +1204,6 @@ 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); @@ -1194,20 +1212,36 @@ static void kvm_unlink_unsync_page(struct kvm *kvm, struct kvm_mmu_page *sp) --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); -static int kvm_sync_page(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp) +#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 + +/* @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.cr4_pae != !!is_pae(vcpu)) { - kvm_mmu_zap_page(vcpu->kvm, sp); + kvm_mmu_prepare_zap_page(vcpu->kvm, sp, invalid_list); return 1; } - 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; } @@ -1215,6 +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]; @@ -1281,6 +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)) { @@ -1293,9 +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); } @@ -1310,11 +1392,10 @@ 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; @@ -1322,40 +1403,45 @@ static struct kvm_mmu_page *kvm_mmu_get_page(struct kvm_vcpu *vcpu, 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(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) @@ -1402,6 +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) { @@ -1422,7 +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; @@ -1464,7 +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; @@ -1478,7 +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++; } @@ -1488,32 +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 @@ -1521,6 +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); @@ -1538,9 +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; } @@ -1553,47 +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]; -restart: - 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)) - goto restart; - } + + 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; + struct hlist_node *node; + LIST_HEAD(invalid_list); - index = kvm_page_table_hashfn(gfn); - bucket = &kvm->arch.mmu_page_hash[index]; -restart: - 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)) - goto restart; - } + 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) @@ -1723,47 +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; - - 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; - } trace_kvm_mmu_unsync_page(sp); ++vcpu->kvm->stat.mmu_unsync; sp->unsync = 1; 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; } @@ -1804,13 +1948,14 @@ 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; @@ -1841,7 +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; } @@ -1853,7 +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" @@ -1878,8 +2025,7 @@ static void mmu_set_spte(struct kvm_vcpu *vcpu, u64 *sptep, } else if (pfn != spte_to_pfn(*sptep)) { pgprintk("hfn old %lx new %lx\n", spte_to_pfn(*sptep), pfn); - rmap_remove(vcpu->kvm, sptep); - __set_spte(sptep, shadow_trap_nonpresent_pte); + drop_spte(vcpu->kvm, sptep, shadow_trap_nonpresent_pte); kvm_flush_remote_tlbs(vcpu->kvm); } else was_rmapped = 1; @@ -1890,7 +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); @@ -1904,15 +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; @@ -1941,7 +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); @@ -1960,6 +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; @@ -1983,10 +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)) @@ -2009,6 +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; @@ -2018,8 +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; @@ -2032,10 +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; } @@ -2045,7 +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; } @@ -2073,6 +2243,7 @@ static int mmu_alloc_roots(struct kvm_vcpu *vcpu) 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); @@ -2103,6 +2274,7 @@ static int mmu_alloc_roots(struct kvm_vcpu *vcpu) 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); @@ -2198,10 +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; @@ -2243,7 +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) @@ -2457,10 +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) @@ -2477,9 +2646,6 @@ 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); - spin_unlock(&vcpu->kvm->mmu_lock); r = mmu_alloc_roots(vcpu); spin_lock(&vcpu->kvm->mmu_lock); mmu_sync_roots(vcpu); @@ -2508,7 +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); @@ -2529,6 +2695,9 @@ 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.cr4_pae) paging32_update_pte(vcpu, sp, spte, new); @@ -2549,11 +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); } @@ -2603,10 +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); @@ -2619,6 +2792,9 @@ void kvm_mmu_pte_write(struct kvm_vcpu *vcpu, gpa_t gpa, 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); @@ -2674,13 +2850,9 @@ 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]; -restart: - hlist_for_each_entry_safe(sp, node, n, bucket, hash_link) { - if (sp->gfn != gfn || sp->role.direct || sp->role.invalid) - continue; + 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; @@ -2697,8 +2869,8 @@ restart: */ pgprintk("misaligned: gpa %llx bytes %d role %x\n", gpa, bytes, sp->role.word); - if (kvm_mmu_zap_page(vcpu->kvm, sp)) - goto restart; + zap_page |= !!kvm_mmu_prepare_zap_page(vcpu->kvm, sp, + &invalid_list); ++vcpu->kvm->stat.mmu_flooded; continue; } @@ -2722,16 +2894,22 @@ restart: if (quadrant != sp->role.quadrant) continue; } + local_flush = true; spte = &sp->spt[page_offset / sizeof(*spte)]; while (npte--) { entry = *spte; mmu_pte_write_zap_pte(vcpu, sp, spte); - if (gentry) + if (gentry && + !((sp->role.word ^ vcpu->arch.mmu.base_role.word) + & mask.word)) mmu_pte_write_new_pte(vcpu, sp, spte, &gentry); - mmu_pte_write_flush_tlb(vcpu, entry, *spte); + 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)) { @@ -2759,15 +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) @@ -2795,11 +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(); @@ -2896,7 +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); @@ -2905,25 +3086,26 @@ 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)) + if (kvm_mmu_prepare_zap_page(kvm, sp, &invalid_list)) goto restart; + kvm_mmu_commit_zap_page(kvm, &invalid_list); spin_unlock(&kvm->mmu_lock); - - kvm_flush_remote_tlbs(kvm); } -static int kvm_mmu_remove_some_alloc_mmu_pages(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); - return kvm_mmu_zap_page(kvm, page) + 1; + return kvm_mmu_prepare_zap_page(kvm, page, invalid_list); } static int mmu_shrink(struct shrinker *shrink, int nr_to_scan, gfp_t gfp_mask) @@ -2936,6 +3118,7 @@ static int mmu_shrink(struct shrinker *shrink, int nr_to_scan, gfp_t gfp_mask) list_for_each_entry(kvm, &vm_list, vm_list) { int npages, idx, freed_pages; + LIST_HEAD(invalid_list); idx = srcu_read_lock(&kvm->srcu); spin_lock(&kvm->mmu_lock); @@ -2943,12 +3126,14 @@ static int mmu_shrink(struct shrinker *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) { - freed_pages = kvm_mmu_remove_some_alloc_mmu_pages(kvm); + 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); } @@ -3074,7 +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; } @@ -3331,9 +3516,9 @@ void inspect_spte_has_rmap(struct kvm *kvm, u64 *sptep) 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()) @@ -3347,8 +3532,7 @@ void inspect_spte_has_rmap(struct kvm *kvm, u64 *sptep) return; } - rmapp = gfn_to_rmap(kvm, rev_sp->gfns[sptep - rev_sp->spt], - rev_sp->role.level); + rmapp = gfn_to_rmap(kvm, gfn, rev_sp->role.level); if (!*rmapp) { if (!printk_ratelimit()) return; @@ -3381,7 +3565,7 @@ 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, &pt[i]); } @@ -3409,13 +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 42f07b1bfbc9..3aab0f0930ef 100644 --- a/arch/x86/kvm/mmutrace.h +++ b/arch/x86/kvm/mmutrace.h @@ -190,7 +190,7 @@ DEFINE_EVENT(kvm_mmu_page_class, kvm_mmu_unsync_page, TP_ARGS(sp) ); -DEFINE_EVENT(kvm_mmu_page_class, kvm_mmu_zap_page, +DEFINE_EVENT(kvm_mmu_page_class, kvm_mmu_prepare_zap_page, TP_PROTO(struct kvm_mmu_page *sp), TP_ARGS(sp) diff --git a/arch/x86/kvm/paging_tmpl.h b/arch/x86/kvm/paging_tmpl.h index 2331bdc2b549..51ef9097960d 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 && (pte & PT64_NX_MASK)) - goto access_error; + 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; } @@ -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; @@ -252,7 +261,7 @@ 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; @@ -263,7 +272,7 @@ static void FNAME(update_pte)(struct kvm_vcpu *vcpu, struct kvm_mmu_page *page, gpte = *(const pt_element_t *)pte; if (~gpte & (PT_PRESENT_MASK | PT_ACCESSED_MASK)) { if (!is_present_gpte(gpte)) { - if (page->unsync) + if (sp->unsync) new_spte = shadow_trap_nonpresent_pte; else new_spte = shadow_notrap_nonpresent_pte; @@ -272,7 +281,7 @@ static void FNAME(update_pte)(struct kvm_vcpu *vcpu, struct kvm_mmu_page *page, 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; @@ -285,11 +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. */ @@ -299,75 +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); - access &= gw->pte_access; - } 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); } - return sptep; + 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); + } + + 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; } /* @@ -431,11 +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)) @@ -443,6 +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); @@ -464,6 +493,7 @@ 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; @@ -475,10 +505,13 @@ static void FNAME(invlpg)(struct kvm_vcpu *vcpu, gva_t gva) level = iterator.level; sptep = iterator.sptep; + sp = page_header(__pa(sptep)); if (is_last_spte(*sptep, level)) { - struct kvm_mmu_page *sp = page_header(__pa(sptep)); int offset, shift; + if (!sp->unsync) + break; + shift = PAGE_SHIFT - (PT_LEVEL_BITS - PT64_LEVEL_BITS) * level; offset = sp->role.quadrant << shift; @@ -487,16 +520,17 @@ static void FNAME(invlpg)(struct kvm_vcpu *vcpu, gva_t gva) 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; } @@ -570,9 +604,9 @@ 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; @@ -580,6 +614,9 @@ static int FNAME(sync_page)(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp) 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; @@ -589,7 +626,7 @@ static int FNAME(sync_page)(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp) 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; @@ -600,16 +637,17 @@ static int FNAME(sync_page)(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp) 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 ce438e0fdd26..bc5b9b8d4a33 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> @@ -130,7 +131,7 @@ 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_K6_STAR, .always = true }, + { .index = MSR_STAR, .always = true }, { .index = MSR_IA32_SYSENTER_CS, .always = true }, #ifdef CONFIG_X86_64 { .index = MSR_GS_BASE, .always = true }, @@ -285,11 +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 int is_external_interrupt(u32 info) @@ -383,8 +384,7 @@ static void svm_init_erratum_383(void) int err; u64 val; - /* Only Fam10h is affected */ - if (boot_cpu_data.x86 != 0x10) + if (!cpu_has_amd_erratum(amd_erratum_383)) return; /* Use _safe variants to not break nested virtualization */ @@ -640,7 +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) { @@ -806,7 +806,7 @@ static void init_vmcb(struct vcpu_svm *svm) * 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 = ?? */ @@ -903,13 +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: @@ -1488,7 +1493,7 @@ static void svm_handle_mce(struct vcpu_svm *svm) */ pr_err("KVM: Guest triggered AMD Erratum 383\n"); - set_bit(KVM_REQ_TRIPLE_FAULT, &svm->vcpu.requests); + kvm_make_request(KVM_REQ_TRIPLE_FAULT, &svm->vcpu); return; } @@ -1535,7 +1540,7 @@ static int io_interception(struct vcpu_svm *svm) string = (io_info & SVM_IOIO_STR_MASK) != 0; in = (io_info & SVM_IOIO_TYPE_MASK) != 0; if (string || in) - return !(emulate_instruction(vcpu, 0, 0, 0) == EMULATE_DO_MMIO); + return emulate_instruction(vcpu, 0, 0, 0) == EMULATE_DONE; port = io_info >> 16; size = (io_info & SVM_IOIO_SIZE_MASK) >> SVM_IOIO_SIZE_SHIFT; @@ -1957,7 +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); @@ -2080,7 +2085,7 @@ static bool nested_svm_vmrun(struct vcpu_svm *svm) 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); + (void)kvm_set_cr3(&svm->vcpu, nested_vmcb->save.cr3); /* Guest paging mode is active - reset mmu */ kvm_mmu_reset_context(&svm->vcpu); @@ -2386,16 +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) @@ -2431,7 +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 @@ -2555,7 +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 @@ -2726,6 +2727,99 @@ 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); @@ -2770,6 +2864,8 @@ static int handle_exit(struct kvm_vcpu *vcpu) 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; } @@ -2826,9 +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; @@ -2842,6 +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; } @@ -3327,6 +3423,11 @@ 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); @@ -3411,6 +3512,8 @@ static struct kvm_x86_ops svm_x86_ops = { .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) diff --git a/arch/x86/kvm/timer.c b/arch/x86/kvm/timer.c index 4ddadb1a5ffe..e16a0dbe74d8 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> @@ -18,7 +32,7 @@ static int __kvm_timer_fn(struct kvm_vcpu *vcpu, struct kvm_timer *ktimer) 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/vmx.c b/arch/x86/kvm/vmx.c index ee03679efe78..49b25eee25ac 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> @@ -36,6 +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" @@ -63,6 +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 \ @@ -173,10 +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; @@ -231,14 +240,14 @@ 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) @@ -334,6 +343,11 @@ static inline bool cpu_has_vmx_ept_1g_page(void) 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; @@ -349,6 +363,16 @@ static inline bool cpu_has_vmx_invept_global(void) return vmx_capability.ept & VMX_EPT_EXTENT_GLOBAL_BIT; } +static inline bool cpu_has_vmx_invvpid_single(void) +{ + return vmx_capability.vpid & VMX_VPID_EXTENT_SINGLE_CONTEXT_BIT; +} + +static inline bool cpu_has_vmx_invvpid_global(void) +{ + return vmx_capability.vpid & VMX_VPID_EXTENT_GLOBAL_CONTEXT_BIT; +} + static inline bool cpu_has_vmx_ept(void) { return vmcs_config.cpu_based_2nd_exec_ctrl & @@ -389,6 +413,12 @@ 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; @@ -453,6 +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; @@ -475,12 +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) @@ -812,6 +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) @@ -828,35 +889,30 @@ 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 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 @@ -884,6 +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) @@ -1057,10 +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++); } @@ -1286,6 +1346,13 @@ static __init int vmx_disabled_by_bios(void) /* 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(); @@ -1308,11 +1375,13 @@ static int hardware_enable(void *garbage) 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; } @@ -1334,13 +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, @@ -1539,7 +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; } @@ -1628,7 +1700,7 @@ static gva_t rmode_tss_base(struct kvm *kvm) gfn_t base_gfn; slots = kvm_memslots(kvm); - base_gfn = kvm->memslots->memslots[0].base_gfn + + base_gfn = slots->memslots[0].base_gfn + kvm->memslots->memslots[0].npages - 3; return base_gfn << PAGE_SHIFT; } @@ -1759,9 +1831,12 @@ static void exit_lmode(struct kvm_vcpu *vcpu) 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) @@ -2507,7 +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 */ @@ -2599,21 +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; @@ -2630,7 +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); /* @@ -2713,7 +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; @@ -2721,7 +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; } @@ -2826,9 +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) @@ -3070,7 +3150,7 @@ static int handle_io(struct kvm_vcpu *vcpu) ++vcpu->stat.io_exits; if (string || in) - return !(emulate_instruction(vcpu, 0, 0, 0) == EMULATE_DO_MMIO); + return emulate_instruction(vcpu, 0, 0, 0) == EMULATE_DONE; port = exit_qualification >> 16; size = (exit_qualification & 7) + 1; @@ -3090,11 +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; @@ -3105,16 +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); @@ -3321,30 +3410,25 @@ 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); @@ -3554,13 +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; @@ -3623,6 +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, @@ -3656,6 +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 @@ -3861,11 +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;" @@ -4001,6 +4083,19 @@ static void vmx_free_vcpu(struct kvm_vcpu *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; @@ -4026,7 +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); @@ -4265,6 +4360,8 @@ static struct kvm_x86_ops vmx_x86_ops = { .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) diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 7fa89c39c64f..25f19078b321 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> @@ -41,17 +42,19 @@ #include <linux/srcu.h> #include <linux/slab.h> #include <linux/perf_event.h> +#include <linux/uaccess.h> #include <trace/events/kvm.h> #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 \ @@ -62,6 +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) @@ -147,6 +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; @@ -285,7 +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); @@ -414,121 +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); - 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, ~0x0eul) | (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; - 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 @@ -546,24 +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); @@ -576,7 +633,7 @@ unsigned long kvm_get_cr8(struct kvm_vcpu *vcpu) } EXPORT_SYMBOL_GPL(kvm_get_cr8); -int kvm_set_dr(struct kvm_vcpu *vcpu, int dr, unsigned long val) +static int __kvm_set_dr(struct kvm_vcpu *vcpu, int dr, unsigned long val) { switch (dr) { case 0 ... 3: @@ -585,29 +642,21 @@ int kvm_set_dr(struct kvm_vcpu *vcpu, int dr, unsigned long val) vcpu->arch.eff_db[dr] = val; break; case 4: - if (kvm_read_cr4_bits(vcpu, X86_CR4_DE)) { - kvm_queue_exception(vcpu, UD_VECTOR); - return 1; - } + if (kvm_read_cr4_bits(vcpu, X86_CR4_DE)) + return 1; /* #UD */ /* fall through */ case 6: - if (val & 0xffffffff00000000ULL) { - kvm_inject_gp(vcpu, 0); - return 1; - } + 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)) { - kvm_queue_exception(vcpu, UD_VECTOR); - return 1; - } + if (kvm_read_cr4_bits(vcpu, X86_CR4_DE)) + return 1; /* #UD */ /* fall through */ default: /* 7 */ - if (val & 0xffffffff00000000ULL) { - kvm_inject_gp(vcpu, 0); - return 1; - } + 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); @@ -618,28 +667,37 @@ int kvm_set_dr(struct kvm_vcpu *vcpu, int dr, unsigned long val) 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); -int kvm_get_dr(struct kvm_vcpu *vcpu, int dr, unsigned long *val) +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)) { - kvm_queue_exception(vcpu, UD_VECTOR); + 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)) { - kvm_queue_exception(vcpu, UD_VECTOR); + if (kvm_read_cr4_bits(vcpu, X86_CR4_DE)) return 1; - } /* fall through */ default: /* 7 */ *val = vcpu->arch.dr7; @@ -648,12 +706,16 @@ int kvm_get_dr(struct kvm_vcpu *vcpu, int dr, unsigned long *val) return 0; } -EXPORT_SYMBOL_GPL(kvm_get_dr); -static inline u32 bit(int bitno) +int kvm_get_dr(struct kvm_vcpu *vcpu, int dr, unsigned long *val) { - return 1 << (bitno & 31); + 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 @@ -671,7 +733,7 @@ static u32 msrs_to_save[] = { 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 @@ -682,10 +744,14 @@ static unsigned num_msrs_to_save; static u32 emulated_msrs[] = { MSR_IA32_MISC_ENABLE, + MSR_IA32_MCG_STATUS, + MSR_IA32_MCG_CTL, }; static int set_efer(struct kvm_vcpu *vcpu, u64 efer) { + u64 old_efer = vcpu->arch.efer; + if (efer & efer_reserved_bits) return 1; @@ -714,11 +780,13 @@ static int set_efer(struct kvm_vcpu *vcpu, u64 efer) kvm_x86_ops->set_efer(vcpu, efer); - vcpu->arch.efer = 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; } @@ -882,7 +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; } @@ -1524,16 +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; } @@ -1618,6 +1682,7 @@ int kvm_dev_ioctl_check_extension(long ext) 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: @@ -1641,6 +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; @@ -1717,8 +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); @@ -1731,8 +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) @@ -1781,7 +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; @@ -1799,7 +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); @@ -1820,11 +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: @@ -1837,7 +1923,6 @@ static int kvm_vcpu_ioctl_get_cpuid2(struct kvm_vcpu *vcpu, { int r; - vcpu_load(vcpu); r = -E2BIG; if (cpuid->nent < vcpu->arch.cpuid_nent) goto out; @@ -1849,7 +1934,6 @@ static int kvm_vcpu_ioctl_get_cpuid2(struct kvm_vcpu *vcpu, out: cpuid->nent = vcpu->arch.cpuid_nent; - vcpu_put(vcpu); return r; } @@ -1901,13 +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 */ | @@ -1922,7 +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; @@ -1980,6 +2064,20 @@ 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; @@ -2081,9 +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; } @@ -2091,11 +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; } @@ -2107,20 +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; } @@ -2140,7 +2229,6 @@ static int kvm_vcpu_ioctl_x86_setup_mce(struct kvm_vcpu *vcpu, int r; unsigned bank_num = mcg_cap & 0xff, bank; - vcpu_load(vcpu); r = -EINVAL; if (!bank_num || bank_num >= KVM_MAX_MCE_BANKS) goto out; @@ -2155,7 +2243,6 @@ static int kvm_vcpu_ioctl_x86_setup_mce(struct kvm_vcpu *vcpu, for (bank = 0; bank < bank_num; bank++) vcpu->arch.mce_banks[bank*4] = ~(u64)0; out: - vcpu_put(vcpu); return r; } @@ -2188,7 +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) @@ -2213,8 +2300,6 @@ 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 && !kvm_exception_is_soft(vcpu->arch.exception.nr); @@ -2239,8 +2324,6 @@ static void kvm_vcpu_ioctl_x86_get_vcpu_events(struct kvm_vcpu *vcpu, events->flags = (KVM_VCPUEVENT_VALID_NMI_PENDING | KVM_VCPUEVENT_VALID_SIPI_VECTOR | KVM_VCPUEVENT_VALID_SHADOW); - - vcpu_put(vcpu); } static int kvm_vcpu_ioctl_x86_set_vcpu_events(struct kvm_vcpu *vcpu, @@ -2251,8 +2334,6 @@ static int kvm_vcpu_ioctl_x86_set_vcpu_events(struct kvm_vcpu *vcpu, | 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; @@ -2275,22 +2356,16 @@ 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) { - vcpu_load(vcpu); - memcpy(dbgregs->db, vcpu->arch.db, sizeof(vcpu->arch.db)); dbgregs->dr6 = vcpu->arch.dr6; dbgregs->dr7 = vcpu->arch.dr7; dbgregs->flags = 0; - - vcpu_put(vcpu); } static int kvm_vcpu_ioctl_x86_set_debugregs(struct kvm_vcpu *vcpu, @@ -2299,40 +2374,113 @@ static int kvm_vcpu_ioctl_x86_set_debugregs(struct kvm_vcpu *vcpu, if (dbgregs->flags) return -EINVAL; - vcpu_load(vcpu); - memcpy(vcpu->arch.db, dbgregs->db, sizeof(vcpu->arch.db)); vcpu->arch.dr6 = dbgregs->dr6; vcpu->arch.dr7 = dbgregs->dr7; - vcpu_put(vcpu); + 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; @@ -2341,14 +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; @@ -2464,9 +2612,7 @@ long kvm_arch_vcpu_ioctl(struct file *filp, r = -EFAULT; if (copy_from_user(&mce, argp, sizeof mce)) goto out; - vcpu_load(vcpu); r = kvm_vcpu_ioctl_x86_set_mce(vcpu, &mce); - vcpu_put(vcpu); break; } case KVM_GET_VCPU_EVENTS: { @@ -2513,11 +2659,67 @@ long kvm_arch_vcpu_ioctl(struct file *filp, 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; } @@ -2560,115 +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 = kvm_aliases(kvm); - - 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 = kvm_aliases(kvm); - - 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; @@ -2797,7 +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); @@ -2812,27 +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; @@ -2841,13 +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; @@ -2867,7 +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; @@ -2888,22 +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) @@ -2912,14 +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; @@ -3259,7 +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; } @@ -3315,7 +3392,7 @@ static int kvm_write_guest_virt_system(gva_t addr, void *val, } ret = kvm_write_guest(vcpu->kvm, gpa, data, towrite); if (ret < 0) { - r = X86EMUL_UNHANDLEABLE; + r = X86EMUL_IO_NEEDED; goto out; } @@ -3330,10 +3407,10 @@ out: 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); @@ -3343,12 +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) @@ -3370,11 +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, @@ -3392,17 +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) @@ -3420,10 +3494,11 @@ 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; } @@ -3431,6 +3506,7 @@ mmio: int emulator_write_emulated(unsigned long addr, const void *val, unsigned int bytes, + unsigned int *error_code, struct kvm_vcpu *vcpu) { /* Crossing a page boundary? */ @@ -3438,16 +3514,17 @@ int emulator_write_emulated(unsigned long addr, 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)) @@ -3463,6 +3540,7 @@ 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) { gpa_t gpa; @@ -3484,6 +3562,10 @@ static int emulator_cmpxchg_emulated(unsigned long addr, goto emul_write; 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); kaddr += offset_in_page(gpa); @@ -3516,7 +3598,7 @@ static int emulator_cmpxchg_emulated(unsigned long addr, emul_write: printk_once(KERN_WARNING "kvm: emulating exchange as write\n"); - return emulator_write_emulated(addr, new, bytes, vcpu); + return emulator_write_emulated(addr, new, bytes, error_code, vcpu); } static int kernel_pio(struct kvm_vcpu *vcpu, void *pd) @@ -3604,42 +3686,38 @@ int emulate_invlpg(struct kvm_vcpu *vcpu, gva_t address) return X86EMUL_CONTINUE; } -int emulate_clts(struct kvm_vcpu *vcpu) +int kvm_emulate_wbinvd(struct kvm_vcpu *vcpu) { - kvm_x86_ops->set_cr0(vcpu, kvm_read_cr0_bits(vcpu, ~X86_CR0_TS)); - kvm_x86_ops->fpu_activate(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 emulator_get_dr(struct x86_emulate_ctxt *ctxt, int dr, unsigned long *dest) +int emulate_clts(struct kvm_vcpu *vcpu) { - return kvm_get_dr(ctxt->vcpu, dr, dest); + kvm_x86_ops->set_cr0(vcpu, kvm_read_cr0_bits(vcpu, ~X86_CR0_TS)); + kvm_x86_ops->fpu_activate(vcpu); + return X86EMUL_CONTINUE; } -int emulator_set_dr(struct x86_emulate_ctxt *ctxt, int dr, unsigned long value) +int emulator_get_dr(int dr, unsigned long *dest, struct kvm_vcpu *vcpu) { - unsigned long mask = (ctxt->mode == X86EMUL_MODE_PROT64) ? ~0ULL : ~0U; - - return kvm_set_dr(ctxt->vcpu, dr, value & mask); + return _kvm_get_dr(vcpu, dr, dest); } -void kvm_report_emulation_failure(struct kvm_vcpu *vcpu, const char *context) +int emulator_set_dr(int dr, unsigned long value, struct kvm_vcpu *vcpu) { - u8 opcodes[4]; - unsigned long rip = kvm_rip_read(vcpu); - unsigned long rip_linear; - - if (!printk_ratelimit()) - return; - rip_linear = rip + get_segment_base(vcpu, VCPU_SREG_CS); - - kvm_read_guest_virt(rip_linear, (void *)opcodes, 4, vcpu, NULL); - - printk(KERN_ERR "emulation failed (%s) rip %lx %02x %02x %02x %02x\n", - context, rip, opcodes[0], opcodes[1], opcodes[2], opcodes[3]); + return __kvm_set_dr(vcpu, dr, value); } -EXPORT_SYMBOL_GPL(kvm_report_emulation_failure); static u64 mk_cr_64(u64 curr_cr, u32 new_val) { @@ -3674,27 +3752,32 @@ static unsigned long emulator_get_cr(int cr, struct kvm_vcpu *vcpu) return value; } -static void emulator_set_cr(int cr, unsigned long val, struct kvm_vcpu *vcpu) +static int emulator_set_cr(int cr, unsigned long val, struct kvm_vcpu *vcpu) { + int res = 0; + switch (cr) { case 0: - kvm_set_cr0(vcpu, mk_cr_64(kvm_read_cr0(vcpu), val)); + res = kvm_set_cr0(vcpu, mk_cr_64(kvm_read_cr0(vcpu), val)); break; case 2: vcpu->arch.cr2 = val; break; case 3: - kvm_set_cr3(vcpu, val); + res = kvm_set_cr3(vcpu, val); break; case 4: - kvm_set_cr4(vcpu, mk_cr_64(kvm_read_cr4(vcpu), val)); + res = kvm_set_cr4(vcpu, mk_cr_64(kvm_read_cr4(vcpu), val)); break; case 8: - kvm_set_cr8(vcpu, val & 0xfUL); + res = __kvm_set_cr8(vcpu, val & 0xfUL); break; default: vcpu_printf(vcpu, "%s: unexpected cr %u\n", __func__, cr); + res = -1; } + + return res; } static int emulator_get_cpl(struct kvm_vcpu *vcpu) @@ -3707,6 +3790,12 @@ 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) { @@ -3779,11 +3868,6 @@ static void emulator_set_segment_selector(u16 sel, int seg, kvm_set_segment(vcpu, &kvm_seg, seg); } -static void emulator_set_rflags(struct kvm_vcpu *vcpu, unsigned long rflags) -{ - kvm_x86_ops->set_rflags(vcpu, rflags); -} - static struct x86_emulate_ops emulate_ops = { .read_std = kvm_read_guest_virt_system, .write_std = kvm_write_guest_virt_system, @@ -3797,11 +3881,15 @@ static struct x86_emulate_ops emulate_ops = { .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, - .set_rflags = emulator_set_rflags, + .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) @@ -3812,14 +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; @@ -3831,8 +3980,6 @@ int emulate_instruction(struct kvm_vcpu *vcpu, */ cache_all_regs(vcpu); - vcpu->mmio_is_write = 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); @@ -3846,13 +3993,16 @@ int emulate_instruction(struct kvm_vcpu *vcpu, ? 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; @@ -3880,11 +4030,11 @@ int emulate_instruction(struct kvm_vcpu *vcpu, ++vcpu->stat.insn_emulation; if (r) { - ++vcpu->stat.insn_emulation_fail; - trace_kvm_emulate_insn_failed(vcpu); - 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); } } @@ -3893,48 +4043,42 @@ 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.count) { - if (!vcpu->arch.pio.in) - vcpu->arch.pio.count = 0; - return EMULATE_DO_MMIO; + return handle_emulation_failure(vcpu); } - if (r || vcpu->mmio_is_write) { - 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)) - goto done; - if (!vcpu->mmio_needed) { - ++vcpu->stat.insn_emulation_fail; - trace_kvm_emulate_insn_failed(vcpu); - 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; } - 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; } -done: - if (vcpu->arch.exception.pending) - vcpu->arch.emulate_ctxt.restart = false; - if (vcpu->arch.emulate_ctxt.restart) goto restart; @@ -4108,6 +4252,9 @@ int kvm_arch_init(void *opaque) perf_register_guest_info_callbacks(&kvm_guest_cbs); + if (cpu_has_xsave) + host_xcr0 = xgetbv(XCR_XFEATURE_ENABLED_MASK); + return 0; out: @@ -4270,7 +4417,7 @@ int kvm_fix_hypercall(struct kvm_vcpu *vcpu) kvm_x86_ops->patch_hypercall(vcpu, instruction); - return emulator_write_emulated(rip, instruction, 3, vcpu); + return emulator_write_emulated(rip, instruction, 3, NULL, vcpu); } void realmode_lgdt(struct kvm_vcpu *vcpu, u16 limit, unsigned long base) @@ -4506,59 +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; @@ -4603,7 +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; @@ -4665,7 +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: @@ -4717,8 +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); @@ -4743,7 +4908,7 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) vcpu->srcu_idx = srcu_read_lock(&vcpu->kvm->srcu); r = emulate_instruction(vcpu, 0, 0, EMULTYPE_NO_DECODE); srcu_read_unlock(&vcpu->kvm->srcu, vcpu->srcu_idx); - if (r == EMULATE_DO_MMIO) { + if (r != EMULATE_DONE) { r = 0; goto out; } @@ -4759,14 +4924,11 @@ out: 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); @@ -4789,15 +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); @@ -4822,8 +4980,6 @@ 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; } @@ -4842,8 +4998,6 @@ int kvm_arch_vcpu_ioctl_get_sregs(struct kvm_vcpu *vcpu, { struct desc_ptr dt; - vcpu_load(vcpu); - kvm_get_segment(vcpu, &sregs->cs, VCPU_SREG_CS); kvm_get_segment(vcpu, &sregs->ds, VCPU_SREG_DS); kvm_get_segment(vcpu, &sregs->es, VCPU_SREG_ES); @@ -4875,32 +5029,27 @@ 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; } int kvm_task_switch(struct kvm_vcpu *vcpu, u16 tss_selector, int reason, bool has_error_code, u32 error_code) { + struct decode_cache *c = &vcpu->arch.emulate_ctxt.decode; int cs_db, cs_l, ret; cache_all_regs(vcpu); @@ -4915,6 +5064,8 @@ int kvm_task_switch(struct kvm_vcpu *vcpu, u16 tss_selector, int reason, ? 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, @@ -4923,6 +5074,8 @@ int kvm_task_switch(struct kvm_vcpu *vcpu, u16 tss_selector, int reason, if (ret) return EMULATE_FAIL; + 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; } @@ -4935,8 +5088,6 @@ int kvm_arch_vcpu_ioctl_set_sregs(struct kvm_vcpu *vcpu, int pending_vec, max_bits; struct desc_ptr dt; - vcpu_load(vcpu); - dt.size = sregs->idt.limit; dt.address = sregs->idt.base; kvm_x86_ops->set_idt(vcpu, &dt); @@ -4996,8 +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; } @@ -5007,12 +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 @@ -5054,34 +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, @@ -5091,7 +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); @@ -5099,16 +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; @@ -5119,16 +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; @@ -5139,61 +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); } @@ -5204,6 +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); } @@ -5217,9 +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); @@ -5241,6 +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); } @@ -5334,7 +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: @@ -5364,12 +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); @@ -5412,12 +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); @@ -5427,7 +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); } @@ -5438,6 +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. @@ -5450,7 +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); @@ -5523,7 +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(); } diff --git a/arch/x86/kvm/x86.h b/arch/x86/kvm/x86.h index f4b54458285b..b7a404722d2b 100644 --- a/arch/x86/kvm/x86.h +++ b/arch/x86/kvm/x86.h @@ -65,13 +65,6 @@ static inline int is_paging(struct kvm_vcpu *vcpu) return kvm_read_cr0_bits(vcpu, X86_CR0_PG); } -static inline struct kvm_mem_aliases *kvm_aliases(struct kvm *kvm) -{ - return rcu_dereference_check(kvm->arch.aliases, - srcu_read_lock_held(&kvm->srcu) - || lockdep_is_held(&kvm->slots_lock)); -} - void kvm_before_handle_nmi(struct kvm_vcpu *vcpu); void kvm_after_handle_nmi(struct kvm_vcpu *vcpu); diff --git a/arch/x86/lib/Makefile b/arch/x86/lib/Makefile index f871e04b6965..e10cf070ede0 100644 --- a/arch/x86/lib/Makefile +++ b/arch/x86/lib/Makefile @@ -30,6 +30,7 @@ ifeq ($(CONFIG_X86_32),y) lib-y += checksum_32.o lib-y += strstr_32.o lib-y += semaphore_32.o string_32.o + lib-y += cmpxchg.o ifneq ($(CONFIG_X86_CMPXCHG64),y) lib-y += cmpxchg8b_emu.o atomic64_386_32.o endif diff --git a/arch/x86/lib/atomic64_386_32.S b/arch/x86/lib/atomic64_386_32.S index 4a5979aa6883..2cda60a06e65 100644 --- a/arch/x86/lib/atomic64_386_32.S +++ b/arch/x86/lib/atomic64_386_32.S @@ -25,150 +25,172 @@ CFI_ADJUST_CFA_OFFSET -4 .endm -.macro BEGIN func reg -$v = \reg - -ENTRY(atomic64_\func\()_386) - CFI_STARTPROC - LOCK $v - -.macro RETURN - UNLOCK $v +#define BEGIN(op) \ +.macro endp; \ + CFI_ENDPROC; \ +ENDPROC(atomic64_##op##_386); \ +.purgem endp; \ +.endm; \ +ENTRY(atomic64_##op##_386); \ + CFI_STARTPROC; \ + LOCK v; + +#define ENDP endp + +#define RET \ + 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 +#define RET_ENDP \ + RET; \ + ENDP + +#define v %ecx +BEGIN(read) + movl (v), %eax + movl 4(v), %edx +RET_ENDP +#undef v + +#define v %esi +BEGIN(set) + movl %ebx, (v) + movl %ecx, 4(v) +RET_ENDP +#undef v + +#define v %esi +BEGIN(xchg) + movl (v), %eax + movl 4(v), %edx + movl %ebx, (v) + movl %ecx, 4(v) +RET_ENDP +#undef v + +#define v %ecx +BEGIN(add) + addl %eax, (v) + adcl %edx, 4(v) +RET_ENDP +#undef v + +#define v %ecx +BEGIN(add_return) + addl (v), %eax + adcl 4(v), %edx + movl %eax, (v) + movl %edx, 4(v) +RET_ENDP +#undef v + +#define v %ecx +BEGIN(sub) + subl %eax, (v) + sbbl %edx, 4(v) +RET_ENDP +#undef v + +#define v %ecx +BEGIN(sub_return) 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 (v), %eax + adcl 4(v), %edx + movl %eax, (v) + movl %edx, 4(v) +RET_ENDP +#undef v + +#define v %esi +BEGIN(inc) + addl $1, (v) + adcl $0, 4(v) +RET_ENDP +#undef v + +#define v %esi +BEGIN(inc_return) + 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 + movl %eax, (v) + movl %edx, 4(v) +RET_ENDP +#undef v + +#define v %esi +BEGIN(dec) + subl $1, (v) + sbbl $0, 4(v) +RET_ENDP +#undef v + +#define v %esi +BEGIN(dec_return) + movl (v), %eax + movl 4(v), %edx subl $1, %eax sbbl $0, %edx - movl %eax, ($v) - movl %edx, 4($v) -END + movl %eax, (v) + movl %edx, 4(v) +RET_ENDP +#undef v -BEGIN add_unless %ecx +#define v %ecx +BEGIN(add_unless) addl %eax, %esi adcl %edx, %edi - addl ($v), %eax - adcl 4($v), %edx + addl (v), %eax + adcl 4(v), %edx cmpl %eax, %esi je 3f 1: - movl %eax, ($v) - movl %edx, 4($v) + movl %eax, (v) + movl %edx, 4(v) movl $1, %eax 2: -RETURN + RET 3: cmpl %edx, %edi jne 1b xorl %eax, %eax jmp 2b -END_ +ENDP +#undef v -BEGIN inc_not_zero %esi - movl ($v), %eax - movl 4($v), %edx +#define v %esi +BEGIN(inc_not_zero) + 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 %eax, (v) + movl %edx, 4(v) movl $1, %eax 2: -RETURN + RET 3: testl %edx, %edx jne 1b jmp 2b -END_ +ENDP +#undef v -BEGIN dec_if_positive %esi - movl ($v), %eax - movl 4($v), %edx +#define v %esi +BEGIN(dec_if_positive) + movl (v), %eax + movl 4(v), %edx subl $1, %eax sbbl $0, %edx js 1f - movl %eax, ($v) - movl %edx, 4($v) + movl %eax, (v) + movl %edx, 4(v) 1: -END +RET_ENDP +#undef v diff --git a/arch/x86/lib/clear_page_64.S b/arch/x86/lib/clear_page_64.S index ebeafcce04a9..aa4326bfb24a 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 2056ccf572cc..5d619f6df3ee 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 727a5d46d2fc..6fec2d1cebe1 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 71100c98e337..a460158b5ac5 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 f82e884928af..bcbcd1e0f7d5 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 e88d3b81644a..09d344269652 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/mm/dump_pagetables.c b/arch/x86/mm/dump_pagetables.c index a725b7f760ae..0002a3a33081 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/fault.c b/arch/x86/mm/fault.c index f62777940dfb..4c4508e8a204 100644 --- a/arch/x86/mm/fault.c +++ b/arch/x86/mm/fault.c @@ -802,8 +802,10 @@ do_sigbus(struct pt_regs *regs, unsigned long error_code, unsigned long address, up_read(&mm->mmap_sem); /* Kernel mode? Handle exceptions or die: */ - if (!(error_code & PF_USER)) + if (!(error_code & PF_USER)) { no_context(regs, error_code, address); + return; + } /* User-space => ok to do another page fault: */ if (is_prefetch(regs, error_code, address)) diff --git a/arch/x86/mm/highmem_32.c b/arch/x86/mm/highmem_32.c index 63a6ba66cbe0..5e8fa12ef861 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 ee41bba315d1..9a6674689a20 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 12e4d2d3c110..3ba6e0608c55 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 5d0e67fff1a6..e5d5e2ce9f77 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/pat.c b/arch/x86/mm/pat.c index 64121a18b8cb..f6ff57b7efa5 100644 --- a/arch/x86/mm/pat.c +++ b/arch/x86/mm/pat.c @@ -158,7 +158,7 @@ static unsigned long pat_x_mtrr_type(u64 start, u64 end, unsigned long req_type) return req_type; } -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; diff --git a/arch/x86/mm/pf_in.c b/arch/x86/mm/pf_in.c index 308e32570d84..38e6d174c497 100644 --- a/arch/x86/mm/pf_in.c +++ b/arch/x86/mm/pf_in.c @@ -40,16 +40,16 @@ 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 }; /* 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/testmmiotrace.c b/arch/x86/mm/testmmiotrace.c index 8565d944f7cf..38868adf07ea 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 426f3a1a64d3..c03f14ab6667 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 b28d2f1253bb..f6b48f6c5951 100644 --- a/arch/x86/oprofile/nmi_int.c +++ b/arch/x86/oprofile/nmi_int.c @@ -634,6 +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"; @@ -655,12 +667,13 @@ static int __init ppro_init(char **cpu_type) case 15: case 23: *cpu_type = "i386/core_2"; break; + case 0x1a: + case 0x1e: 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: diff --git a/arch/x86/pci/acpi.c b/arch/x86/pci/acpi.c index 2ec04c424a62..15466c096ba5 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"), + }, + }, {} }; diff --git a/arch/x86/pci/common.c b/arch/x86/pci/common.c index 215a27ae050d..a0772af64efb 100644 --- a/arch/x86/pci/common.c +++ b/arch/x86/pci/common.c @@ -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/irq.c b/arch/x86/pci/irq.c index 9810a0f76c91..f547ee05f715 100644 --- a/arch/x86/pci/irq.c +++ b/arch/x86/pci/irq.c @@ -989,7 +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; @@ -1028,7 +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 @@ -1052,7 +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 8d460eaf524f..c89266be6048 100644 --- a/arch/x86/pci/legacy.c +++ b/arch/x86/pci/legacy.c @@ -36,7 +36,7 @@ int __init pci_legacy_init(void) return 0; } -void pcibios_scan_specific_bus(int busn) +void __devinit pcibios_scan_specific_bus(int busn) { int devfn; long node; diff --git a/arch/x86/power/cpu.c b/arch/x86/power/cpu.c index 1290ba54b350..e7e8c5f54956 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> */ diff --git a/arch/x86/power/hibernate_64.c b/arch/x86/power/hibernate_64.c index d24f983ba1e5..460f314d13e5 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 6b4ffedb93c9..4a2afa1bac51 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 000000000000..7ee90a9b549d --- /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 02b442e92007..36df991985b2 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 ac74869b8140..4b5d26f108bb 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 b83e119fbeb0..68128a1b401a 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 3bb4fc21f4f2..779385158915 100644 --- a/arch/x86/xen/Makefile +++ b/arch/x86/xen/Makefile @@ -12,9 +12,10 @@ 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 obj-$(CONFIG_XEN_DEBUG_FS) += debugfs.o +obj-$(CONFIG_SWIOTLB_XEN) += pci-swiotlb-xen.o diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c index 65d8d79b46a8..7d46c8441418 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. @@ -1145,6 +1172,10 @@ asmlinkage void __init xen_start_kernel(void) pgd = (pgd_t *)xen_start_info->pt_base; + if (!xen_initial_domain()) + __supported_pte_mask &= ~(_PAGE_PWT | _PAGE_PCD); + + __supported_pte_mask |= _PAGE_IOMAP; /* Don't do the full vcpu_info placement stuff until we have a possible map and a non-dummy shared_info. */ per_cpu(xen_vcpu, 0) = &HYPERVISOR_shared_info->vcpu_info[0]; @@ -1206,3 +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 914f04695ce5..42086ac406af 100644 --- a/arch/x86/xen/mmu.c +++ b/arch/x86/xen/mmu.c @@ -42,6 +42,7 @@ #include <linux/highmem.h> #include <linux/debugfs.h> #include <linux/bug.h> +#include <linux/vmalloc.h> #include <linux/module.h> #include <linux/gfp.h> @@ -51,14 +52,19 @@ #include <asm/mmu_context.h> #include <asm/setup.h> #include <asm/paravirt.h> +#include <asm/e820.h> #include <asm/linkage.h> +#include <asm/page.h> #include <asm/xen/hypercall.h> #include <asm/xen/hypervisor.h> +#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> #include "multicalls.h" @@ -67,6 +73,13 @@ #define MMU_UPDATE_HISTO 30 +/* + * Protects atomic reservation decrease/increase against concurrent increases. + * Also protects non-atomic updates of current_pages and driver_pages, and + * balloon lists. + */ +DEFINE_SPINLOCK(xen_reservation_lock); + #ifdef CONFIG_XEN_DEBUG_FS static struct { @@ -377,6 +390,28 @@ static bool xen_page_pinned(void *ptr) return PagePinned(page); } +static bool xen_iomap_pte(pte_t pte) +{ + return pte_flags(pte) & _PAGE_IOMAP; +} + +static void xen_set_iomap_pte(pte_t *ptep, pte_t pteval) +{ + struct multicall_space mcs; + struct mmu_update *u; + + mcs = xen_mc_entry(sizeof(*u)); + u = mcs.args; + + /* ptep might be kmapped when using 32-bit HIGHPTE */ + u->ptr = arbitrary_virt_to_machine(ptep).maddr; + u->val = pte_val_ma(pteval); + + MULTI_mmu_update(mcs.mc, mcs.args, 1, NULL, DOMID_IO); + + xen_mc_issue(PARAVIRT_LAZY_MMU); +} + static void xen_extend_mmu_update(const struct mmu_update *update) { struct multicall_space mcs; @@ -453,6 +488,11 @@ void set_pte_mfn(unsigned long vaddr, unsigned long mfn, pgprot_t flags) void xen_set_pte_at(struct mm_struct *mm, unsigned long addr, pte_t *ptep, pte_t pteval) { + if (xen_iomap_pte(pteval)) { + xen_set_iomap_pte(ptep, pteval); + goto out; + } + ADD_STATS(set_pte_at, 1); // ADD_STATS(set_pte_at_pinned, xen_page_pinned(ptep)); ADD_STATS(set_pte_at_current, mm == current->mm); @@ -523,8 +563,25 @@ static pteval_t pte_pfn_to_mfn(pteval_t val) return val; } +static pteval_t iomap_pte(pteval_t val) +{ + if (val & _PAGE_PRESENT) { + unsigned long pfn = (val & PTE_PFN_MASK) >> PAGE_SHIFT; + pteval_t flags = val & PTE_FLAGS_MASK; + + /* We assume the pte frame number is a MFN, so + just use it as-is. */ + val = ((pteval_t)pfn << PAGE_SHIFT) | flags; + } + + return val; +} + pteval_t xen_pte_val(pte_t pte) { + if (xen_initial_domain() && (pte.pte & _PAGE_IOMAP)) + return pte.pte; + return pte_mfn_to_pfn(pte.pte); } PV_CALLEE_SAVE_REGS_THUNK(xen_pte_val); @@ -537,7 +594,22 @@ PV_CALLEE_SAVE_REGS_THUNK(xen_pgd_val); pte_t xen_make_pte(pteval_t pte) { - pte = pte_pfn_to_mfn(pte); + phys_addr_t addr = (pte & PTE_PFN_MASK); + + /* + * Unprivileged domains are allowed to do IOMAPpings for + * PCI passthrough, but not map ISA space. The ISA + * mappings are just dummy local mappings to keep other + * parts of the kernel happy. + */ + if (unlikely(pte & _PAGE_IOMAP) && + (xen_initial_domain() || addr >= ISA_END_ADDRESS)) { + pte = iomap_pte(pte); + } else { + pte &= ~_PAGE_IOMAP; + pte = pte_pfn_to_mfn(pte); + } + return native_make_pte(pte); } PV_CALLEE_SAVE_REGS_THUNK(xen_make_pte); @@ -593,6 +665,11 @@ void xen_set_pud(pud_t *ptr, pud_t val) void xen_set_pte(pte_t *ptep, pte_t pte) { + if (xen_iomap_pte(pte)) { + xen_set_iomap_pte(ptep, pte); + return; + } + ADD_STATS(pte_update, 1); // ADD_STATS(pte_update_pinned, xen_page_pinned(ptep)); ADD_STATS(pte_update_batched, paravirt_get_lazy_mode() == PARAVIRT_LAZY_MMU); @@ -609,6 +686,11 @@ void xen_set_pte(pte_t *ptep, pte_t pte) #ifdef CONFIG_X86_PAE void xen_set_pte_atomic(pte_t *ptep, pte_t pte) { + if (xen_iomap_pte(pte)) { + xen_set_iomap_pte(ptep, pte); + return; + } + set_64bit((u64 *)ptep, native_pte_val(pte)); } @@ -935,8 +1017,6 @@ static int xen_pin_page(struct mm_struct *mm, struct page *page, read-only, and can be pinned. */ static void __xen_pgd_pin(struct mm_struct *mm, pgd_t *pgd) { - vm_unmap_aliases(); - xen_mc_batch(); if (__xen_pgd_walk(mm, pgd, xen_pin_page, USER_LIMIT)) { @@ -1500,7 +1580,6 @@ static void xen_alloc_ptpage(struct mm_struct *mm, unsigned long pfn, unsigned l if (PagePinned(virt_to_page(mm->pgd))) { SetPagePinned(page); - vm_unmap_aliases(); if (!PageHighMem(page)) { make_lowmem_page_readonly(__va(PFN_PHYS((unsigned long)pfn))); if (level == PT_PTE && USE_SPLIT_PTLOCKS) @@ -1811,9 +1890,16 @@ static void xen_set_fixmap(unsigned idx, phys_addr_t phys, pgprot_t prot) pte = pfn_pte(phys, prot); break; - default: + case FIX_PARAVIRT_BOOTMAP: + /* This is an MFN, but it isn't an IO mapping from the + IO domain */ pte = mfn_pte(phys, prot); break; + + default: + /* By default, set_fixmap is used for hardware mappings */ + pte = mfn_pte(phys, __pgprot(pgprot_val(prot) | _PAGE_IOMAP)); + break; } __native_set_fixmap(idx, pte); @@ -1939,8 +2025,240 @@ void __init xen_init_mmu_ops(void) x86_init.paging.pagetable_setup_start = xen_pagetable_setup_start; x86_init.paging.pagetable_setup_done = xen_pagetable_setup_done; pv_mmu_ops = xen_mmu_ops; + + vmap_lazy_unmap = false; +} + +/* Protected by xen_reservation_lock. */ +#define MAX_CONTIG_ORDER 9 /* 2MB */ +static unsigned long discontig_frames[1<<MAX_CONTIG_ORDER]; + +#define VOID_PTE (mfn_pte(0, __pgprot(0))) +static void xen_zap_pfn_range(unsigned long vaddr, unsigned int order, + unsigned long *in_frames, + unsigned long *out_frames) +{ + int i; + struct multicall_space mcs; + + xen_mc_batch(); + for (i = 0; i < (1UL<<order); i++, vaddr += PAGE_SIZE) { + mcs = __xen_mc_entry(0); + + if (in_frames) + in_frames[i] = virt_to_mfn(vaddr); + + MULTI_update_va_mapping(mcs.mc, vaddr, VOID_PTE, 0); + set_phys_to_machine(virt_to_pfn(vaddr), INVALID_P2M_ENTRY); + + if (out_frames) + out_frames[i] = virt_to_pfn(vaddr); + } + xen_mc_issue(0); +} + +/* + * Update the pfn-to-mfn mappings for a virtual address range, either to + * point to an array of mfns, or contiguously from a single starting + * mfn. + */ +static void xen_remap_exchanged_ptes(unsigned long vaddr, int order, + unsigned long *mfns, + unsigned long first_mfn) +{ + unsigned i, limit; + unsigned long mfn; + + xen_mc_batch(); + + limit = 1u << order; + for (i = 0; i < limit; i++, vaddr += PAGE_SIZE) { + struct multicall_space mcs; + unsigned flags; + + mcs = __xen_mc_entry(0); + if (mfns) + mfn = mfns[i]; + else + mfn = first_mfn + i; + + if (i < (limit - 1)) + flags = 0; + else { + if (order == 0) + flags = UVMF_INVLPG | UVMF_ALL; + else + flags = UVMF_TLB_FLUSH | UVMF_ALL; + } + + MULTI_update_va_mapping(mcs.mc, vaddr, + mfn_pte(mfn, PAGE_KERNEL), flags); + + set_phys_to_machine(virt_to_pfn(vaddr), mfn); + } + + xen_mc_issue(0); +} + +/* + * Perform the hypercall to exchange a region of our pfns to point to + * memory with the required contiguous alignment. Takes the pfns as + * input, and populates mfns as output. + * + * Returns a success code indicating whether the hypervisor was able to + * satisfy the request or not. + */ +static int xen_exchange_memory(unsigned long extents_in, unsigned int order_in, + unsigned long *pfns_in, + unsigned long extents_out, + unsigned int order_out, + unsigned long *mfns_out, + unsigned int address_bits) +{ + long rc; + int success; + + struct xen_memory_exchange exchange = { + .in = { + .nr_extents = extents_in, + .extent_order = order_in, + .extent_start = pfns_in, + .domid = DOMID_SELF + }, + .out = { + .nr_extents = extents_out, + .extent_order = order_out, + .extent_start = mfns_out, + .address_bits = address_bits, + .domid = DOMID_SELF + } + }; + + BUG_ON(extents_in << order_in != extents_out << order_out); + + rc = HYPERVISOR_memory_op(XENMEM_exchange, &exchange); + success = (exchange.nr_exchanged == extents_in); + + BUG_ON(!success && ((exchange.nr_exchanged != 0) || (rc == 0))); + BUG_ON(success && (rc != 0)); + + return success; } +int xen_create_contiguous_region(unsigned long vstart, unsigned int order, + unsigned int address_bits) +{ + unsigned long *in_frames = discontig_frames, out_frame; + unsigned long flags; + int success; + + /* + * Currently an auto-translated guest will not perform I/O, nor will + * it require PAE page directories below 4GB. Therefore any calls to + * this function are redundant and can be ignored. + */ + + if (xen_feature(XENFEAT_auto_translated_physmap)) + return 0; + + if (unlikely(order > MAX_CONTIG_ORDER)) + return -ENOMEM; + + memset((void *) vstart, 0, PAGE_SIZE << order); + + spin_lock_irqsave(&xen_reservation_lock, flags); + + /* 1. Zap current PTEs, remembering MFNs. */ + xen_zap_pfn_range(vstart, order, in_frames, NULL); + + /* 2. Get a new contiguous memory extent. */ + out_frame = virt_to_pfn(vstart); + success = xen_exchange_memory(1UL << order, 0, in_frames, + 1, order, &out_frame, + address_bits); + + /* 3. Map the new extent in place of old pages. */ + if (success) + xen_remap_exchanged_ptes(vstart, order, NULL, out_frame); + else + xen_remap_exchanged_ptes(vstart, order, in_frames, 0); + + spin_unlock_irqrestore(&xen_reservation_lock, flags); + + return success ? 0 : -ENOMEM; +} +EXPORT_SYMBOL_GPL(xen_create_contiguous_region); + +void xen_destroy_contiguous_region(unsigned long vstart, unsigned int order) +{ + unsigned long *out_frames = discontig_frames, in_frame; + unsigned long flags; + int success; + + if (xen_feature(XENFEAT_auto_translated_physmap)) + return; + + if (unlikely(order > MAX_CONTIG_ORDER)) + return; + + memset((void *) vstart, 0, PAGE_SIZE << order); + + spin_lock_irqsave(&xen_reservation_lock, flags); + + /* 1. Find start MFN of contiguous extent. */ + in_frame = virt_to_mfn(vstart); + + /* 2. Zap current PTEs. */ + xen_zap_pfn_range(vstart, order, NULL, out_frames); + + /* 3. Do the exchange for non-contiguous MFNs. */ + success = xen_exchange_memory(1, order, &in_frame, 1UL << order, + 0, out_frames, 0); + + /* 4. Map new pages in place of old pages. */ + if (success) + xen_remap_exchanged_ptes(vstart, order, out_frames, 0); + else + xen_remap_exchanged_ptes(vstart, order, NULL, in_frame); + + spin_unlock_irqrestore(&xen_reservation_lock, flags); +} +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 5fe6bc7f5ecf..fa938c4aa2f7 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/pci-swiotlb-xen.c b/arch/x86/xen/pci-swiotlb-xen.c new file mode 100644 index 000000000000..a013ec9d0c54 --- /dev/null +++ b/arch/x86/xen/pci-swiotlb-xen.c @@ -0,0 +1,58 @@ +/* Glue code to lib/swiotlb-xen.c */ + +#include <linux/dma-mapping.h> +#include <xen/swiotlb-xen.h> + +#include <asm/xen/hypervisor.h> +#include <xen/xen.h> + +int xen_swiotlb __read_mostly; + +static struct dma_map_ops xen_swiotlb_dma_ops = { + .mapping_error = xen_swiotlb_dma_mapping_error, + .alloc_coherent = xen_swiotlb_alloc_coherent, + .free_coherent = xen_swiotlb_free_coherent, + .sync_single_for_cpu = xen_swiotlb_sync_single_for_cpu, + .sync_single_for_device = xen_swiotlb_sync_single_for_device, + .sync_sg_for_cpu = xen_swiotlb_sync_sg_for_cpu, + .sync_sg_for_device = xen_swiotlb_sync_sg_for_device, + .map_sg = xen_swiotlb_map_sg_attrs, + .unmap_sg = xen_swiotlb_unmap_sg_attrs, + .map_page = xen_swiotlb_map_page, + .unmap_page = xen_swiotlb_unmap_page, + .dma_supported = xen_swiotlb_dma_supported, +}; + +/* + * pci_xen_swiotlb_detect - set xen_swiotlb to 1 if necessary + * + * This returns non-zero if we are forced to use xen_swiotlb (by the boot + * option). + */ +int __init pci_xen_swiotlb_detect(void) +{ + + /* If running as PV guest, either iommu=soft, or swiotlb=force will + * activate this IOMMU. If running as PV privileged, activate it + * irregardlesss. + */ + if ((xen_initial_domain() || swiotlb || swiotlb_force) && + (xen_pv_domain())) + xen_swiotlb = 1; + + /* If we are running under Xen, we MUST disable the native SWIOTLB. + * Don't worry about swiotlb_force flag activating the native, as + * the 'swiotlb' flag is the only one turning it on. */ + if (xen_pv_domain()) + swiotlb = 0; + + return xen_swiotlb; +} + +void __init pci_xen_swiotlb_init(void) +{ + if (xen_swiotlb) { + xen_swiotlb_init(1); + dma_ops = &xen_swiotlb_dma_ops; + } +} diff --git a/arch/x86/xen/platform-pci-unplug.c b/arch/x86/xen/platform-pci-unplug.c new file mode 100644 index 000000000000..554c002a1e1a --- /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 ad0047f47cd4..328b00305426 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 a29693fd3138..25f232b18a82 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 a9c661108034..1d789d56877c 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(); diff --git a/arch/x86/xen/time.c b/arch/x86/xen/time.c index b3c6c59ed302..1a5353a753fc 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; @@ -473,7 +435,11 @@ 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; @@ -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 f9153a300bce..7c8ab86163e9 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 */ |