diff options
| author | Ingo Molnar <mingo@kernel.org> | 2012-03-30 08:47:19 +0200 |
|---|---|---|
| committer | Ingo Molnar <mingo@kernel.org> | 2012-03-30 08:50:06 +0200 |
| commit | 186e54cbe1145f4d11e32fe10e7e20a11f1b27dd (patch) | |
| tree | 9b6cf3667a3ea90e0cec0ea7119688ba76c55a71 /arch/x86 | |
| parent | 99dd5497e5be4fe4194cad181d45fd6569a930db (diff) | |
| parent | 4bde23f8751f388867766b0a62ed1ef8b7e01561 (diff) | |
| download | linux-186e54cbe1145f4d11e32fe10e7e20a11f1b27dd.tar.bz2 | |
Merge branch 'linus' into x86/urgent
Merge reason: Needed for include file dependencies.
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Diffstat (limited to 'arch/x86')
152 files changed, 3090 insertions, 1751 deletions
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index 901952355969..1d14cc6b79ad 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -69,7 +69,6 @@ config X86 select HAVE_ARCH_JUMP_LABEL select HAVE_TEXT_POKE_SMP select HAVE_GENERIC_HARDIRQS - select HAVE_SPARSE_IRQ select SPARSE_IRQ select GENERIC_FIND_FIRST_BIT select GENERIC_IRQ_PROBE @@ -2125,6 +2124,13 @@ config NET5501 ---help--- This option enables system support for the Soekris Engineering net5501. +config GEOS + bool "Traverse Technologies GEOS System Support (LEDS, GPIO, etc)" + select GPIOLIB + depends on DMI + ---help--- + This option enables system support for the Traverse Technologies GEOS. + endif # X86_32 config AMD_NB @@ -2157,9 +2163,9 @@ config IA32_EMULATION depends on X86_64 select COMPAT_BINFMT_ELF ---help--- - Include code to run 32-bit programs under a 64-bit kernel. You should - likely turn this on, unless you're 100% sure that you don't have any - 32-bit programs left. + Include code to run legacy 32-bit programs under a + 64-bit kernel. You should likely turn this on, unless you're + 100% sure that you don't have any 32-bit programs left. config IA32_AOUT tristate "IA32 a.out support" @@ -2167,9 +2173,23 @@ config IA32_AOUT ---help--- Support old a.out binaries in the 32bit emulation. +config X86_X32 + bool "x32 ABI for 64-bit mode (EXPERIMENTAL)" + depends on X86_64 && IA32_EMULATION && EXPERIMENTAL + ---help--- + Include code to run binaries for the x32 native 32-bit ABI + for 64-bit processors. An x32 process gets access to the + full 64-bit register file and wide data path while leaving + pointers at 32 bits for smaller memory footprint. + + You will need a recent binutils (2.22 or later) with + elf32_x86_64 support enabled to compile a kernel with this + option set. + config COMPAT def_bool y - depends on IA32_EMULATION + depends on IA32_EMULATION || X86_X32 + select ARCH_WANT_OLD_COMPAT_IPC config COMPAT_FOR_U64_ALIGNMENT def_bool COMPAT diff --git a/arch/x86/Makefile b/arch/x86/Makefile index 209ba1294592..968dbe24a255 100644 --- a/arch/x86/Makefile +++ b/arch/x86/Makefile @@ -82,6 +82,22 @@ ifdef CONFIG_CC_STACKPROTECTOR endif endif +ifdef CONFIG_X86_X32 + x32_ld_ok := $(call try-run,\ + /bin/echo -e '1: .quad 1b' | \ + $(CC) $(KBUILD_AFLAGS) -c -xassembler -o "$$TMP" - && \ + $(OBJCOPY) -O elf32-x86-64 "$$TMP" "$$TMPO" && \ + $(LD) -m elf32_x86_64 "$$TMPO" -o "$$TMP",y,n) + ifeq ($(x32_ld_ok),y) + CONFIG_X86_X32_ABI := y + KBUILD_AFLAGS += -DCONFIG_X86_X32_ABI + KBUILD_CFLAGS += -DCONFIG_X86_X32_ABI + else + $(warning CONFIG_X86_X32 enabled but no binutils support) + endif +endif +export CONFIG_X86_X32_ABI + # Don't unroll struct assignments with kmemcheck enabled ifeq ($(CONFIG_KMEMCHECK),y) KBUILD_CFLAGS += $(call cc-option,-fno-builtin-memcpy) diff --git a/arch/x86/Makefile.um b/arch/x86/Makefile.um index 36ddec6a41c9..4be406abeefd 100644 --- a/arch/x86/Makefile.um +++ b/arch/x86/Makefile.um @@ -8,15 +8,11 @@ ELF_ARCH := i386 ELF_FORMAT := elf32-i386 CHECKFLAGS += -D__i386__ -ifeq ("$(origin SUBARCH)", "command line") -ifneq ("$(shell uname -m | sed -e s/i.86/i386/)", "$(SUBARCH)") KBUILD_CFLAGS += $(call cc-option,-m32) KBUILD_AFLAGS += $(call cc-option,-m32) LINK-y += $(call cc-option,-m32) export LDFLAGS -endif -endif # First of all, tune CFLAGS for the specific CPU. This actually sets cflags-y. include $(srctree)/arch/x86/Makefile_32.cpu diff --git a/arch/x86/crypto/camellia_glue.c b/arch/x86/crypto/camellia_glue.c index 1ca36a93fd2f..3306dc0b139e 100644 --- a/arch/x86/crypto/camellia_glue.c +++ b/arch/x86/crypto/camellia_glue.c @@ -1925,7 +1925,7 @@ static int force; module_param(force, int, 0); MODULE_PARM_DESC(force, "Force module load, ignore CPU blacklist"); -int __init init(void) +static int __init init(void) { if (!force && is_blacklisted_cpu()) { printk(KERN_INFO @@ -1938,7 +1938,7 @@ int __init init(void) return crypto_register_algs(camellia_algs, ARRAY_SIZE(camellia_algs)); } -void __exit fini(void) +static void __exit fini(void) { crypto_unregister_algs(camellia_algs, ARRAY_SIZE(camellia_algs)); } diff --git a/arch/x86/crypto/twofish_glue_3way.c b/arch/x86/crypto/twofish_glue_3way.c index 408fc0c5814e..922ab24cce31 100644 --- a/arch/x86/crypto/twofish_glue_3way.c +++ b/arch/x86/crypto/twofish_glue_3way.c @@ -668,7 +668,7 @@ static int force; module_param(force, int, 0); MODULE_PARM_DESC(force, "Force module load, ignore CPU blacklist"); -int __init init(void) +static int __init init(void) { if (!force && is_blacklisted_cpu()) { printk(KERN_INFO @@ -681,7 +681,7 @@ int __init init(void) return crypto_register_algs(tf_algs, ARRAY_SIZE(tf_algs)); } -void __exit fini(void) +static void __exit fini(void) { crypto_unregister_algs(tf_algs, ARRAY_SIZE(tf_algs)); } diff --git a/arch/x86/ia32/ia32_aout.c b/arch/x86/ia32/ia32_aout.c index 4c2e59a420b9..d511d951a052 100644 --- a/arch/x86/ia32/ia32_aout.c +++ b/arch/x86/ia32/ia32_aout.c @@ -26,7 +26,6 @@ #include <linux/init.h> #include <linux/jiffies.h> -#include <asm/system.h> #include <asm/uaccess.h> #include <asm/pgalloc.h> #include <asm/cacheflush.h> diff --git a/arch/x86/ia32/ia32_signal.c b/arch/x86/ia32/ia32_signal.c index 5563ba1cf513..a69245ba27e3 100644 --- a/arch/x86/ia32/ia32_signal.c +++ b/arch/x86/ia32/ia32_signal.c @@ -12,10 +12,8 @@ #include <linux/mm.h> #include <linux/smp.h> #include <linux/kernel.h> -#include <linux/signal.h> #include <linux/errno.h> #include <linux/wait.h> -#include <linux/ptrace.h> #include <linux/unistd.h> #include <linux/stddef.h> #include <linux/personality.h> @@ -32,20 +30,15 @@ #include <asm/proto.h> #include <asm/vdso.h> #include <asm/sigframe.h> +#include <asm/sighandling.h> #include <asm/sys_ia32.h> -#define _BLOCKABLE (~(sigmask(SIGKILL) | sigmask(SIGSTOP))) - -#define FIX_EFLAGS (X86_EFLAGS_AC | X86_EFLAGS_OF | \ - X86_EFLAGS_DF | X86_EFLAGS_TF | X86_EFLAGS_SF | \ - X86_EFLAGS_ZF | X86_EFLAGS_AF | X86_EFLAGS_PF | \ - X86_EFLAGS_CF) - -void signal_fault(struct pt_regs *regs, void __user *frame, char *where); +#define FIX_EFLAGS __FIX_EFLAGS int copy_siginfo_to_user32(compat_siginfo_t __user *to, siginfo_t *from) { int err = 0; + bool ia32 = is_ia32_task(); if (!access_ok(VERIFY_WRITE, to, sizeof(compat_siginfo_t))) return -EFAULT; @@ -75,8 +68,13 @@ int copy_siginfo_to_user32(compat_siginfo_t __user *to, siginfo_t *from) case __SI_FAULT >> 16: break; case __SI_CHLD >> 16: - put_user_ex(from->si_utime, &to->si_utime); - put_user_ex(from->si_stime, &to->si_stime); + if (ia32) { + put_user_ex(from->si_utime, &to->si_utime); + put_user_ex(from->si_stime, &to->si_stime); + } else { + put_user_ex(from->si_utime, &to->_sifields._sigchld_x32._utime); + put_user_ex(from->si_stime, &to->_sifields._sigchld_x32._stime); + } put_user_ex(from->si_status, &to->si_status); /* FALL THROUGH */ default: @@ -348,7 +346,7 @@ static int ia32_setup_sigcontext(struct sigcontext_ia32 __user *sc, put_user_ex(regs->dx, &sc->dx); put_user_ex(regs->cx, &sc->cx); put_user_ex(regs->ax, &sc->ax); - put_user_ex(current->thread.trap_no, &sc->trapno); + put_user_ex(current->thread.trap_nr, &sc->trapno); put_user_ex(current->thread.error_code, &sc->err); put_user_ex(regs->ip, &sc->ip); put_user_ex(regs->cs, (unsigned int __user *)&sc->cs); diff --git a/arch/x86/ia32/sys_ia32.c b/arch/x86/ia32/sys_ia32.c index f6f5c53dc903..aec2202a596c 100644 --- a/arch/x86/ia32/sys_ia32.c +++ b/arch/x86/ia32/sys_ia32.c @@ -287,46 +287,6 @@ asmlinkage long sys32_sigaction(int sig, struct old_sigaction32 __user *act, return ret; } -asmlinkage long sys32_rt_sigprocmask(int how, compat_sigset_t __user *set, - compat_sigset_t __user *oset, - unsigned int sigsetsize) -{ - sigset_t s; - compat_sigset_t s32; - int ret; - mm_segment_t old_fs = get_fs(); - - if (set) { - if (copy_from_user(&s32, set, sizeof(compat_sigset_t))) - return -EFAULT; - switch (_NSIG_WORDS) { - case 4: s.sig[3] = s32.sig[6] | (((long)s32.sig[7]) << 32); - case 3: s.sig[2] = s32.sig[4] | (((long)s32.sig[5]) << 32); - case 2: s.sig[1] = s32.sig[2] | (((long)s32.sig[3]) << 32); - case 1: s.sig[0] = s32.sig[0] | (((long)s32.sig[1]) << 32); - } - } - set_fs(KERNEL_DS); - ret = sys_rt_sigprocmask(how, - set ? (sigset_t __user *)&s : NULL, - oset ? (sigset_t __user *)&s : NULL, - sigsetsize); - set_fs(old_fs); - if (ret) - return ret; - if (oset) { - switch (_NSIG_WORDS) { - case 4: s32.sig[7] = (s.sig[3] >> 32); s32.sig[6] = s.sig[3]; - case 3: s32.sig[5] = (s.sig[2] >> 32); s32.sig[4] = s.sig[2]; - case 2: s32.sig[3] = (s.sig[1] >> 32); s32.sig[2] = s.sig[1]; - case 1: s32.sig[1] = (s.sig[0] >> 32); s32.sig[0] = s.sig[0]; - } - if (copy_to_user(oset, &s32, sizeof(compat_sigset_t))) - return -EFAULT; - } - return 0; -} - asmlinkage long sys32_alarm(unsigned int seconds) { return alarm_setitimer(seconds); diff --git a/arch/x86/include/asm/Kbuild b/arch/x86/include/asm/Kbuild index b57e6a43a37a..f9c0d3ba9e84 100644 --- a/arch/x86/include/asm/Kbuild +++ b/arch/x86/include/asm/Kbuild @@ -14,6 +14,7 @@ header-y += msr.h header-y += mtrr.h header-y += posix_types_32.h header-y += posix_types_64.h +header-y += posix_types_x32.h header-y += prctl.h header-y += processor-flags.h header-y += ptrace-abi.h @@ -24,3 +25,4 @@ header-y += vsyscall.h genhdr-y += unistd_32.h genhdr-y += unistd_64.h +genhdr-y += unistd_x32.h diff --git a/arch/x86/include/asm/apic.h b/arch/x86/include/asm/apic.h index d3eaac44860a..d85410171260 100644 --- a/arch/x86/include/asm/apic.h +++ b/arch/x86/include/asm/apic.h @@ -11,7 +11,6 @@ #include <linux/atomic.h> #include <asm/fixmap.h> #include <asm/mpspec.h> -#include <asm/system.h> #include <asm/msr.h> #define ARCH_APICTIMER_STOPS_ON_C3 1 diff --git a/arch/x86/include/asm/auxvec.h b/arch/x86/include/asm/auxvec.h index 1316b4c35425..77203ac352de 100644 --- a/arch/x86/include/asm/auxvec.h +++ b/arch/x86/include/asm/auxvec.h @@ -9,4 +9,11 @@ #endif #define AT_SYSINFO_EHDR 33 +/* entries in ARCH_DLINFO: */ +#if defined(CONFIG_IA32_EMULATION) || !defined(CONFIG_X86_64) +# define AT_VECTOR_SIZE_ARCH 2 +#else /* else it's non-compat x86-64 */ +# define AT_VECTOR_SIZE_ARCH 1 +#endif + #endif /* _ASM_X86_AUXVEC_H */ diff --git a/arch/x86/include/asm/barrier.h b/arch/x86/include/asm/barrier.h new file mode 100644 index 000000000000..c6cd358a1eec --- /dev/null +++ b/arch/x86/include/asm/barrier.h @@ -0,0 +1,116 @@ +#ifndef _ASM_X86_BARRIER_H +#define _ASM_X86_BARRIER_H + +#include <asm/alternative.h> +#include <asm/nops.h> + +/* + * Force strict CPU ordering. + * And yes, this is required on UP too when we're talking + * to devices. + */ + +#ifdef CONFIG_X86_32 +/* + * Some non-Intel clones support out of order store. wmb() ceases to be a + * nop for these. + */ +#define mb() alternative("lock; addl $0,0(%%esp)", "mfence", X86_FEATURE_XMM2) +#define rmb() alternative("lock; addl $0,0(%%esp)", "lfence", X86_FEATURE_XMM2) +#define wmb() alternative("lock; addl $0,0(%%esp)", "sfence", X86_FEATURE_XMM) +#else +#define mb() asm volatile("mfence":::"memory") +#define rmb() asm volatile("lfence":::"memory") +#define wmb() asm volatile("sfence" ::: "memory") +#endif + +/** + * read_barrier_depends - Flush all pending reads that subsequents reads + * depend on. + * + * No data-dependent reads from memory-like regions are ever reordered + * over this barrier. All reads preceding this primitive are guaranteed + * to access memory (but not necessarily other CPUs' caches) before any + * reads following this primitive that depend on the data return by + * any of the preceding reads. This primitive is much lighter weight than + * rmb() on most CPUs, and is never heavier weight than is + * rmb(). + * + * These ordering constraints are respected by both the local CPU + * and the compiler. + * + * Ordering is not guaranteed by anything other than these primitives, + * not even by data dependencies. See the documentation for + * memory_barrier() for examples and URLs to more information. + * + * For example, the following code would force ordering (the initial + * value of "a" is zero, "b" is one, and "p" is "&a"): + * + * <programlisting> + * CPU 0 CPU 1 + * + * b = 2; + * memory_barrier(); + * p = &b; q = p; + * read_barrier_depends(); + * d = *q; + * </programlisting> + * + * because the read of "*q" depends on the read of "p" and these + * two reads are separated by a read_barrier_depends(). However, + * the following code, with the same initial values for "a" and "b": + * + * <programlisting> + * CPU 0 CPU 1 + * + * a = 2; + * memory_barrier(); + * b = 3; y = b; + * read_barrier_depends(); + * x = a; + * </programlisting> + * + * does not enforce ordering, since there is no data dependency between + * the read of "a" and the read of "b". Therefore, on some CPUs, such + * as Alpha, "y" could be set to 3 and "x" to 0. Use rmb() + * in cases like this where there are no data dependencies. + **/ + +#define read_barrier_depends() do { } while (0) + +#ifdef CONFIG_SMP +#define smp_mb() mb() +#ifdef CONFIG_X86_PPRO_FENCE +# define smp_rmb() rmb() +#else +# define smp_rmb() barrier() +#endif +#ifdef CONFIG_X86_OOSTORE +# define smp_wmb() wmb() +#else +# define smp_wmb() barrier() +#endif +#define smp_read_barrier_depends() read_barrier_depends() +#define set_mb(var, value) do { (void)xchg(&var, value); } while (0) +#else +#define smp_mb() barrier() +#define smp_rmb() barrier() +#define smp_wmb() barrier() +#define smp_read_barrier_depends() do { } while (0) +#define set_mb(var, value) do { var = value; barrier(); } while (0) +#endif + +/* + * Stop RDTSC speculation. This is needed when you need to use RDTSC + * (or get_cycles or vread that possibly accesses the TSC) in a defined + * code region. + * + * (Could use an alternative three way for this if there was one.) + */ +static __always_inline void rdtsc_barrier(void) +{ + alternative(ASM_NOP3, "mfence", X86_FEATURE_MFENCE_RDTSC); + alternative(ASM_NOP3, "lfence", X86_FEATURE_LFENCE_RDTSC); +} + +#endif /* _ASM_X86_BARRIER_H */ diff --git a/arch/x86/include/asm/bug.h b/arch/x86/include/asm/bug.h index f654d1bb17fb..11e1152222d0 100644 --- a/arch/x86/include/asm/bug.h +++ b/arch/x86/include/asm/bug.h @@ -36,4 +36,8 @@ do { \ #endif /* !CONFIG_BUG */ #include <asm-generic/bug.h> + + +extern void show_regs_common(void); + #endif /* _ASM_X86_BUG_H */ diff --git a/arch/x86/include/asm/cacheflush.h b/arch/x86/include/asm/cacheflush.h index 4e12668711e5..9863ee3747da 100644 --- a/arch/x86/include/asm/cacheflush.h +++ b/arch/x86/include/asm/cacheflush.h @@ -3,6 +3,7 @@ /* Caches aren't brain-dead on the intel. */ #include <asm-generic/cacheflush.h> +#include <asm/special_insns.h> #ifdef CONFIG_X86_PAT /* diff --git a/arch/x86/include/asm/compat.h b/arch/x86/include/asm/compat.h index 30d737ef2a42..d6805798d6fc 100644 --- a/arch/x86/include/asm/compat.h +++ b/arch/x86/include/asm/compat.h @@ -6,7 +6,9 @@ */ #include <linux/types.h> #include <linux/sched.h> +#include <asm/processor.h> #include <asm/user32.h> +#include <asm/unistd.h> #define COMPAT_USER_HZ 100 #define COMPAT_UTS_MACHINE "i686\0\0" @@ -186,7 +188,20 @@ struct compat_shmid64_ds { /* * The type of struct elf_prstatus.pr_reg in compatible core dumps. */ +#ifdef CONFIG_X86_X32_ABI +typedef struct user_regs_struct compat_elf_gregset_t; + +#define PR_REG_SIZE(S) (test_thread_flag(TIF_IA32) ? 68 : 216) +#define PRSTATUS_SIZE(S) (test_thread_flag(TIF_IA32) ? 144 : 296) +#define SET_PR_FPVALID(S,V) \ + do { *(int *) (((void *) &((S)->pr_reg)) + PR_REG_SIZE(0)) = (V); } \ + while (0) + +#define COMPAT_USE_64BIT_TIME \ + (!!(task_pt_regs(current)->orig_ax & __X32_SYSCALL_BIT)) +#else typedef struct user_regs_struct32 compat_elf_gregset_t; +#endif /* * A pointer passed in from user mode. This should not @@ -208,13 +223,30 @@ static inline compat_uptr_t ptr_to_compat(void __user *uptr) static inline void __user *arch_compat_alloc_user_space(long len) { - struct pt_regs *regs = task_pt_regs(current); - return (void __user *)regs->sp - len; + compat_uptr_t sp; + + if (test_thread_flag(TIF_IA32)) { + sp = task_pt_regs(current)->sp; + } else { + /* -128 for the x32 ABI redzone */ + sp = percpu_read(old_rsp) - 128; + } + + return (void __user *)round_down(sp - len, 16); +} + +static inline bool is_x32_task(void) +{ +#ifdef CONFIG_X86_X32_ABI + if (task_pt_regs(current)->orig_ax & __X32_SYSCALL_BIT) + return true; +#endif + return false; } -static inline int is_compat_task(void) +static inline bool is_compat_task(void) { - return current_thread_info()->status & TS_COMPAT; + return is_ia32_task() || is_x32_task(); } #endif /* _ASM_X86_COMPAT_H */ diff --git a/arch/x86/include/asm/debugreg.h b/arch/x86/include/asm/debugreg.h index b903d5ea3941..2d91580bf228 100644 --- a/arch/x86/include/asm/debugreg.h +++ b/arch/x86/include/asm/debugreg.h @@ -78,8 +78,75 @@ */ #ifdef __KERNEL__ +#include <linux/bug.h> + DECLARE_PER_CPU(unsigned long, cpu_dr7); +#ifndef CONFIG_PARAVIRT +/* + * These special macros can be used to get or set a debugging register + */ +#define get_debugreg(var, register) \ + (var) = native_get_debugreg(register) +#define set_debugreg(value, register) \ + native_set_debugreg(register, value) +#endif + +static inline unsigned long native_get_debugreg(int regno) +{ + unsigned long val = 0; /* Damn you, gcc! */ + + switch (regno) { + case 0: + asm("mov %%db0, %0" :"=r" (val)); + break; + case 1: + asm("mov %%db1, %0" :"=r" (val)); + break; + case 2: + asm("mov %%db2, %0" :"=r" (val)); + break; + case 3: + asm("mov %%db3, %0" :"=r" (val)); + break; + case 6: + asm("mov %%db6, %0" :"=r" (val)); + break; + case 7: + asm("mov %%db7, %0" :"=r" (val)); + break; + default: + BUG(); + } + return val; +} + +static inline void native_set_debugreg(int regno, unsigned long value) +{ + switch (regno) { + case 0: + asm("mov %0, %%db0" ::"r" (value)); + break; + case 1: + asm("mov %0, %%db1" ::"r" (value)); + break; + case 2: + asm("mov %0, %%db2" ::"r" (value)); + break; + case 3: + asm("mov %0, %%db3" ::"r" (value)); + break; + case 6: + asm("mov %0, %%db6" ::"r" (value)); + break; + case 7: + asm("mov %0, %%db7" ::"r" (value)); + break; + default: + BUG(); + } +} + static inline void hw_breakpoint_disable(void) { /* Zero the control register for HW Breakpoint */ diff --git a/arch/x86/include/asm/elf.h b/arch/x86/include/asm/elf.h index 5f962df30d0f..5939f44fe0c0 100644 --- a/arch/x86/include/asm/elf.h +++ b/arch/x86/include/asm/elf.h @@ -84,7 +84,6 @@ extern unsigned int vdso_enabled; (((x)->e_machine == EM_386) || ((x)->e_machine == EM_486)) #include <asm/processor.h> -#include <asm/system.h> #ifdef CONFIG_X86_32 #include <asm/desc.h> @@ -156,7 +155,12 @@ do { \ #define elf_check_arch(x) \ ((x)->e_machine == EM_X86_64) -#define compat_elf_check_arch(x) elf_check_arch_ia32(x) +#define compat_elf_check_arch(x) \ + (elf_check_arch_ia32(x) || (x)->e_machine == EM_X86_64) + +#if __USER32_DS != __USER_DS +# error "The following code assumes __USER32_DS == __USER_DS" +#endif static inline void elf_common_init(struct thread_struct *t, struct pt_regs *regs, const u16 ds) @@ -179,8 +183,9 @@ static inline void elf_common_init(struct thread_struct *t, void start_thread_ia32(struct pt_regs *regs, u32 new_ip, u32 new_sp); #define compat_start_thread start_thread_ia32 -void set_personality_ia32(void); -#define COMPAT_SET_PERSONALITY(ex) set_personality_ia32() +void set_personality_ia32(bool); +#define COMPAT_SET_PERSONALITY(ex) \ + set_personality_ia32((ex).e_machine == EM_X86_64) #define COMPAT_ELF_PLATFORM ("i686") @@ -287,7 +292,7 @@ do { \ #define VDSO_HIGH_BASE 0xffffe000U /* CONFIG_COMPAT_VDSO address */ /* 1GB for 64bit, 8MB for 32bit */ -#define STACK_RND_MASK (test_thread_flag(TIF_IA32) ? 0x7ff : 0x3fffff) +#define STACK_RND_MASK (test_thread_flag(TIF_ADDR32) ? 0x7ff : 0x3fffff) #define ARCH_DLINFO \ do { \ @@ -296,9 +301,20 @@ do { \ (unsigned long)current->mm->context.vdso); \ } while (0) +#define ARCH_DLINFO_X32 \ +do { \ + if (vdso_enabled) \ + NEW_AUX_ENT(AT_SYSINFO_EHDR, \ + (unsigned long)current->mm->context.vdso); \ +} while (0) + #define AT_SYSINFO 32 -#define COMPAT_ARCH_DLINFO ARCH_DLINFO_IA32(sysctl_vsyscall32) +#define COMPAT_ARCH_DLINFO \ +if (test_thread_flag(TIF_X32)) \ + ARCH_DLINFO_X32; \ +else \ + ARCH_DLINFO_IA32(sysctl_vsyscall32) #define COMPAT_ELF_ET_DYN_BASE (TASK_UNMAPPED_BASE + 0x1000000) @@ -314,6 +330,8 @@ struct linux_binprm; #define ARCH_HAS_SETUP_ADDITIONAL_PAGES 1 extern int arch_setup_additional_pages(struct linux_binprm *bprm, int uses_interp); +extern int x32_setup_additional_pages(struct linux_binprm *bprm, + int uses_interp); extern int syscall32_setup_pages(struct linux_binprm *, int exstack); #define compat_arch_setup_additional_pages syscall32_setup_pages @@ -330,7 +348,7 @@ static inline int mmap_is_ia32(void) return 1; #endif #ifdef CONFIG_IA32_EMULATION - if (test_thread_flag(TIF_IA32)) + if (test_thread_flag(TIF_ADDR32)) return 1; #endif return 0; diff --git a/arch/x86/include/asm/exec.h b/arch/x86/include/asm/exec.h new file mode 100644 index 000000000000..54c2e1db274a --- /dev/null +++ b/arch/x86/include/asm/exec.h @@ -0,0 +1 @@ +/* define arch_align_stack() here */ diff --git a/arch/x86/include/asm/futex.h b/arch/x86/include/asm/futex.h index d09bb03653f0..71ecbcba1a4e 100644 --- a/arch/x86/include/asm/futex.h +++ b/arch/x86/include/asm/futex.h @@ -9,7 +9,6 @@ #include <asm/asm.h> #include <asm/errno.h> #include <asm/processor.h> -#include <asm/system.h> #define __futex_atomic_op1(insn, ret, oldval, uaddr, oparg) \ asm volatile("1:\t" insn "\n" \ diff --git a/arch/x86/include/asm/i387.h b/arch/x86/include/asm/i387.h index 7ce0798b1b26..257d9cca214f 100644 --- a/arch/x86/include/asm/i387.h +++ b/arch/x86/include/asm/i387.h @@ -14,7 +14,6 @@ #include <linux/sched.h> #include <linux/hardirq.h> -#include <asm/system.h> struct pt_regs; struct user_i387_struct; diff --git a/arch/x86/include/asm/ia32.h b/arch/x86/include/asm/ia32.h index 1f7e62517284..ee52760549f0 100644 --- a/arch/x86/include/asm/ia32.h +++ b/arch/x86/include/asm/ia32.h @@ -43,6 +43,15 @@ struct ucontext_ia32 { compat_sigset_t uc_sigmask; /* mask last for extensibility */ }; +struct ucontext_x32 { + unsigned int uc_flags; + unsigned int uc_link; + stack_ia32_t uc_stack; + unsigned int uc__pad0; /* needed for alignment */ + struct sigcontext uc_mcontext; /* the 64-bit sigcontext type */ + compat_sigset_t uc_sigmask; /* mask last for extensibility */ +}; + /* This matches struct stat64 in glibc2.2, hence the absolutely * insane amounts of padding around dev_t's. */ @@ -116,6 +125,15 @@ typedef struct compat_siginfo { compat_clock_t _stime; } _sigchld; + /* SIGCHLD (x32 version) */ + struct { + unsigned int _pid; /* which child */ + unsigned int _uid; /* sender's uid */ + int _status; /* exit code */ + compat_s64 _utime; + compat_s64 _stime; + } _sigchld_x32; + /* SIGILL, SIGFPE, SIGSEGV, SIGBUS */ struct { unsigned int _addr; /* faulting insn/memory ref. */ diff --git a/arch/x86/include/asm/kgdb.h b/arch/x86/include/asm/kgdb.h index 77e95f54570a..332f98c9111f 100644 --- a/arch/x86/include/asm/kgdb.h +++ b/arch/x86/include/asm/kgdb.h @@ -64,11 +64,15 @@ enum regnames { GDB_PS, /* 17 */ GDB_CS, /* 18 */ GDB_SS, /* 19 */ + GDB_DS, /* 20 */ + GDB_ES, /* 21 */ + GDB_FS, /* 22 */ + GDB_GS, /* 23 */ }; #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)) +#define DBG_MAX_REG_NUM 24 +/* 17 64 bit regs and 5 32 bit regs */ +#define NUMREGBYTES ((17 * 8) + (5 * 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 4d8dcbdfc120..e7d1c194d272 100644 --- a/arch/x86/include/asm/kvm.h +++ b/arch/x86/include/asm/kvm.h @@ -321,4 +321,8 @@ struct kvm_xcrs { __u64 padding[16]; }; +/* definition of registers in kvm_run */ +struct kvm_sync_regs { +}; + #endif /* _ASM_X86_KVM_H */ diff --git a/arch/x86/include/asm/kvm_emulate.h b/arch/x86/include/asm/kvm_emulate.h index 7b9cfc4878af..c222e1a1b12a 100644 --- a/arch/x86/include/asm/kvm_emulate.h +++ b/arch/x86/include/asm/kvm_emulate.h @@ -176,6 +176,7 @@ struct x86_emulate_ops { void (*set_idt)(struct x86_emulate_ctxt *ctxt, struct desc_ptr *dt); ulong (*get_cr)(struct x86_emulate_ctxt *ctxt, int cr); int (*set_cr)(struct x86_emulate_ctxt *ctxt, int cr, ulong val); + void (*set_rflags)(struct x86_emulate_ctxt *ctxt, ulong val); int (*cpl)(struct x86_emulate_ctxt *ctxt); int (*get_dr)(struct x86_emulate_ctxt *ctxt, int dr, ulong *dest); int (*set_dr)(struct x86_emulate_ctxt *ctxt, int dr, ulong value); @@ -388,7 +389,7 @@ bool x86_page_table_writing_insn(struct x86_emulate_ctxt *ctxt); #define EMULATION_INTERCEPTED 2 int x86_emulate_insn(struct x86_emulate_ctxt *ctxt); int emulator_task_switch(struct x86_emulate_ctxt *ctxt, - u16 tss_selector, int reason, + u16 tss_selector, int idt_index, int reason, bool has_error_code, u32 error_code); int emulate_int_real(struct x86_emulate_ctxt *ctxt, int irq); #endif /* _ASM_X86_KVM_X86_EMULATE_H */ diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index 52d6640a5ca1..e216ba066e79 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -29,7 +29,7 @@ #include <asm/msr-index.h> #define KVM_MAX_VCPUS 254 -#define KVM_SOFT_MAX_VCPUS 64 +#define KVM_SOFT_MAX_VCPUS 160 #define KVM_MEMORY_SLOTS 32 /* memory slots that does not exposed to userspace */ #define KVM_PRIVATE_MEM_SLOTS 4 @@ -181,13 +181,6 @@ struct kvm_mmu_memory_cache { void *objects[KVM_NR_MEM_OBJS]; }; -#define NR_PTE_CHAIN_ENTRIES 5 - -struct kvm_pte_chain { - u64 *parent_ptes[NR_PTE_CHAIN_ENTRIES]; - struct hlist_node link; -}; - /* * kvm_mmu_page_role, below, is defined as: * @@ -427,12 +420,16 @@ struct kvm_vcpu_arch { u64 last_guest_tsc; u64 last_kernel_ns; - u64 last_tsc_nsec; - u64 last_tsc_write; - u32 virtual_tsc_khz; + u64 last_host_tsc; + u64 tsc_offset_adjustment; + u64 this_tsc_nsec; + u64 this_tsc_write; + u8 this_tsc_generation; bool tsc_catchup; - u32 tsc_catchup_mult; - s8 tsc_catchup_shift; + bool tsc_always_catchup; + s8 virtual_tsc_shift; + u32 virtual_tsc_mult; + u32 virtual_tsc_khz; atomic_t nmi_queued; /* unprocessed asynchronous NMIs */ unsigned nmi_pending; /* NMI queued after currently running handler */ @@ -478,6 +475,21 @@ struct kvm_vcpu_arch { u32 id; bool send_user_only; } apf; + + /* OSVW MSRs (AMD only) */ + struct { + u64 length; + u64 status; + } osvw; +}; + +struct kvm_lpage_info { + unsigned long rmap_pde; + int write_count; +}; + +struct kvm_arch_memory_slot { + struct kvm_lpage_info *lpage_info[KVM_NR_PAGE_SIZES - 1]; }; struct kvm_arch { @@ -511,8 +523,12 @@ struct kvm_arch { s64 kvmclock_offset; raw_spinlock_t tsc_write_lock; u64 last_tsc_nsec; - u64 last_tsc_offset; u64 last_tsc_write; + u32 last_tsc_khz; + u64 cur_tsc_nsec; + u64 cur_tsc_write; + u64 cur_tsc_offset; + u8 cur_tsc_generation; struct kvm_xen_hvm_config xen_hvm_config; @@ -644,7 +660,7 @@ struct kvm_x86_ops { u64 (*get_mt_mask)(struct kvm_vcpu *vcpu, gfn_t gfn, bool is_mmio); int (*get_lpage_level)(void); bool (*rdtscp_supported)(void); - void (*adjust_tsc_offset)(struct kvm_vcpu *vcpu, s64 adjustment); + void (*adjust_tsc_offset)(struct kvm_vcpu *vcpu, s64 adjustment, bool host); void (*set_tdp_cr3)(struct kvm_vcpu *vcpu, unsigned long cr3); @@ -652,7 +668,7 @@ struct kvm_x86_ops { bool (*has_wbinvd_exit)(void); - void (*set_tsc_khz)(struct kvm_vcpu *vcpu, u32 user_tsc_khz); + void (*set_tsc_khz)(struct kvm_vcpu *vcpu, u32 user_tsc_khz, bool scale); void (*write_tsc_offset)(struct kvm_vcpu *vcpu, u64 offset); u64 (*compute_tsc_offset)(struct kvm_vcpu *vcpu, u64 target_tsc); @@ -674,6 +690,17 @@ struct kvm_arch_async_pf { extern struct kvm_x86_ops *kvm_x86_ops; +static inline void adjust_tsc_offset_guest(struct kvm_vcpu *vcpu, + s64 adjustment) +{ + kvm_x86_ops->adjust_tsc_offset(vcpu, adjustment, false); +} + +static inline void adjust_tsc_offset_host(struct kvm_vcpu *vcpu, s64 adjustment) +{ + kvm_x86_ops->adjust_tsc_offset(vcpu, adjustment, true); +} + int kvm_mmu_module_init(void); void kvm_mmu_module_exit(void); @@ -741,8 +768,8 @@ int kvm_emulate_wbinvd(struct kvm_vcpu *vcpu); void kvm_get_segment(struct kvm_vcpu *vcpu, struct kvm_segment *var, int seg); int kvm_load_segment_descriptor(struct kvm_vcpu *vcpu, u16 selector, int seg); -int kvm_task_switch(struct kvm_vcpu *vcpu, u16 tss_selector, int reason, - bool has_error_code, u32 error_code); +int kvm_task_switch(struct kvm_vcpu *vcpu, u16 tss_selector, int idt_index, + int reason, bool has_error_code, u32 error_code); int kvm_set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0); int kvm_set_cr3(struct kvm_vcpu *vcpu, unsigned long cr3); diff --git a/arch/x86/include/asm/local.h b/arch/x86/include/asm/local.h index 9cdae5d47e8f..c8bed0da434a 100644 --- a/arch/x86/include/asm/local.h +++ b/arch/x86/include/asm/local.h @@ -3,7 +3,6 @@ #include <linux/percpu.h> -#include <asm/system.h> #include <linux/atomic.h> #include <asm/asm.h> diff --git a/arch/x86/include/asm/mc146818rtc.h b/arch/x86/include/asm/mc146818rtc.h index 0e8e85bb7c51..d354fb781c57 100644 --- a/arch/x86/include/asm/mc146818rtc.h +++ b/arch/x86/include/asm/mc146818rtc.h @@ -5,7 +5,6 @@ #define _ASM_X86_MC146818RTC_H #include <asm/io.h> -#include <asm/system.h> #include <asm/processor.h> #include <linux/mc146818rtc.h> diff --git a/arch/x86/include/asm/mtrr.h b/arch/x86/include/asm/mtrr.h index 4365ffdb461f..7e3f17f92c66 100644 --- a/arch/x86/include/asm/mtrr.h +++ b/arch/x86/include/asm/mtrr.h @@ -29,18 +29,18 @@ #define MTRR_IOCTL_BASE 'M' -struct mtrr_sentry { - unsigned long base; /* Base address */ - unsigned int size; /* Size of region */ - unsigned int type; /* Type of region */ -}; - /* Warning: this structure has a different order from i386 on x86-64. The 32bit emulation code takes care of that. But you need to use this for 64bit, otherwise your X server will break. */ #ifdef __i386__ +struct mtrr_sentry { + unsigned long base; /* Base address */ + unsigned int size; /* Size of region */ + unsigned int type; /* Type of region */ +}; + struct mtrr_gentry { unsigned int regnum; /* Register number */ unsigned long base; /* Base address */ @@ -50,12 +50,20 @@ struct mtrr_gentry { #else /* __i386__ */ +struct mtrr_sentry { + __u64 base; /* Base address */ + __u32 size; /* Size of region */ + __u32 type; /* Type of region */ +}; + struct mtrr_gentry { - unsigned long base; /* Base address */ - unsigned int size; /* Size of region */ - unsigned int regnum; /* Register number */ - unsigned int type; /* Type of region */ + __u64 base; /* Base address */ + __u32 size; /* Size of region */ + __u32 regnum; /* Register number */ + __u32 type; /* Type of region */ + __u32 _pad; /* Unused */ }; + #endif /* !__i386__ */ struct mtrr_var_range { diff --git a/arch/x86/include/asm/page_types.h b/arch/x86/include/asm/page_types.h index bce688d54c12..e21fdd10479f 100644 --- a/arch/x86/include/asm/page_types.h +++ b/arch/x86/include/asm/page_types.h @@ -55,7 +55,6 @@ extern unsigned long init_memory_mapping(unsigned long start, unsigned long end); extern void initmem_init(void); -extern void free_initmem(void); #endif /* !__ASSEMBLY__ */ diff --git a/arch/x86/include/asm/paravirt.h b/arch/x86/include/asm/paravirt.h index c0180fd372d2..aa0f91308367 100644 --- a/arch/x86/include/asm/paravirt.h +++ b/arch/x86/include/asm/paravirt.h @@ -10,6 +10,7 @@ #include <asm/paravirt_types.h> #ifndef __ASSEMBLY__ +#include <linux/bug.h> #include <linux/types.h> #include <linux/cpumask.h> diff --git a/arch/x86/include/asm/perf_event.h b/arch/x86/include/asm/perf_event.h index e8fb2c7a5f4f..2291895b1836 100644 --- a/arch/x86/include/asm/perf_event.h +++ b/arch/x86/include/asm/perf_event.h @@ -23,6 +23,7 @@ #define ARCH_PERFMON_EVENTSEL_USR (1ULL << 16) #define ARCH_PERFMON_EVENTSEL_OS (1ULL << 17) #define ARCH_PERFMON_EVENTSEL_EDGE (1ULL << 18) +#define ARCH_PERFMON_EVENTSEL_PIN_CONTROL (1ULL << 19) #define ARCH_PERFMON_EVENTSEL_INT (1ULL << 20) #define ARCH_PERFMON_EVENTSEL_ANY (1ULL << 21) #define ARCH_PERFMON_EVENTSEL_ENABLE (1ULL << 22) diff --git a/arch/x86/include/asm/posix_types.h b/arch/x86/include/asm/posix_types.h index bb7133dc155d..3427b7798dbc 100644 --- a/arch/x86/include/asm/posix_types.h +++ b/arch/x86/include/asm/posix_types.h @@ -7,7 +7,9 @@ #else # ifdef __i386__ # include "posix_types_32.h" -# else +# elif defined(__LP64__) # include "posix_types_64.h" +# else +# include "posix_types_x32.h" # endif #endif diff --git a/arch/x86/include/asm/posix_types_32.h b/arch/x86/include/asm/posix_types_32.h index f7d9adf82e53..99f262e04b91 100644 --- a/arch/x86/include/asm/posix_types_32.h +++ b/arch/x86/include/asm/posix_types_32.h @@ -7,79 +7,22 @@ * assume GCC is being used. */ -typedef unsigned long __kernel_ino_t; typedef unsigned short __kernel_mode_t; +#define __kernel_mode_t __kernel_mode_t + typedef unsigned short __kernel_nlink_t; -typedef long __kernel_off_t; -typedef int __kernel_pid_t; +#define __kernel_nlink_t __kernel_nlink_t + typedef unsigned short __kernel_ipc_pid_t; +#define __kernel_ipc_pid_t __kernel_ipc_pid_t + typedef unsigned short __kernel_uid_t; typedef unsigned short __kernel_gid_t; -typedef unsigned int __kernel_size_t; -typedef int __kernel_ssize_t; -typedef int __kernel_ptrdiff_t; -typedef long __kernel_time_t; -typedef long __kernel_suseconds_t; -typedef long __kernel_clock_t; -typedef int __kernel_timer_t; -typedef int __kernel_clockid_t; -typedef int __kernel_daddr_t; -typedef char * __kernel_caddr_t; -typedef unsigned short __kernel_uid16_t; -typedef unsigned short __kernel_gid16_t; -typedef unsigned int __kernel_uid32_t; -typedef unsigned int __kernel_gid32_t; +#define __kernel_uid_t __kernel_uid_t -typedef unsigned short __kernel_old_uid_t; -typedef unsigned short __kernel_old_gid_t; typedef unsigned short __kernel_old_dev_t; +#define __kernel_old_dev_t __kernel_old_dev_t -#ifdef __GNUC__ -typedef long long __kernel_loff_t; -#endif - -typedef struct { - int val[2]; -} __kernel_fsid_t; - -#if defined(__KERNEL__) - -#undef __FD_SET -#define __FD_SET(fd,fdsetp) \ - asm volatile("btsl %1,%0": \ - "+m" (*(__kernel_fd_set *)(fdsetp)) \ - : "r" ((int)(fd))) - -#undef __FD_CLR -#define __FD_CLR(fd,fdsetp) \ - asm volatile("btrl %1,%0": \ - "+m" (*(__kernel_fd_set *)(fdsetp)) \ - : "r" ((int) (fd))) - -#undef __FD_ISSET -#define __FD_ISSET(fd,fdsetp) \ - (__extension__ \ - ({ \ - unsigned char __result; \ - asm volatile("btl %1,%2 ; setb %0" \ - : "=q" (__result) \ - : "r" ((int)(fd)), \ - "m" (*(__kernel_fd_set *)(fdsetp))); \ - __result; \ -})) - -#undef __FD_ZERO -#define __FD_ZERO(fdsetp) \ -do { \ - int __d0, __d1; \ - asm volatile("cld ; rep ; stosl" \ - : "=m" (*(__kernel_fd_set *)(fdsetp)), \ - "=&c" (__d0), "=&D" (__d1) \ - : "a" (0), "1" (__FDSET_LONGS), \ - "2" ((__kernel_fd_set *)(fdsetp)) \ - : "memory"); \ -} while (0) - -#endif /* defined(__KERNEL__) */ +#include <asm-generic/posix_types.h> #endif /* _ASM_X86_POSIX_TYPES_32_H */ diff --git a/arch/x86/include/asm/posix_types_64.h b/arch/x86/include/asm/posix_types_64.h index eb8d2d92b63e..cba0c1ead162 100644 --- a/arch/x86/include/asm/posix_types_64.h +++ b/arch/x86/include/asm/posix_types_64.h @@ -7,113 +7,13 @@ * assume GCC is being used. */ -typedef unsigned long __kernel_ino_t; -typedef unsigned int __kernel_mode_t; -typedef unsigned long __kernel_nlink_t; -typedef long __kernel_off_t; -typedef int __kernel_pid_t; -typedef int __kernel_ipc_pid_t; -typedef unsigned int __kernel_uid_t; -typedef unsigned int __kernel_gid_t; -typedef unsigned long __kernel_size_t; -typedef long __kernel_ssize_t; -typedef long __kernel_ptrdiff_t; -typedef long __kernel_time_t; -typedef long __kernel_suseconds_t; -typedef long __kernel_clock_t; -typedef int __kernel_timer_t; -typedef int __kernel_clockid_t; -typedef int __kernel_daddr_t; -typedef char * __kernel_caddr_t; -typedef unsigned short __kernel_uid16_t; -typedef unsigned short __kernel_gid16_t; - -#ifdef __GNUC__ -typedef long long __kernel_loff_t; -#endif - -typedef struct { - int val[2]; -} __kernel_fsid_t; - typedef unsigned short __kernel_old_uid_t; typedef unsigned short __kernel_old_gid_t; -typedef __kernel_uid_t __kernel_uid32_t; -typedef __kernel_gid_t __kernel_gid32_t; +#define __kernel_old_uid_t __kernel_old_uid_t typedef unsigned long __kernel_old_dev_t; +#define __kernel_old_dev_t __kernel_old_dev_t -#ifdef __KERNEL__ - -#undef __FD_SET -static inline void __FD_SET(unsigned long fd, __kernel_fd_set *fdsetp) -{ - unsigned long _tmp = fd / __NFDBITS; - unsigned long _rem = fd % __NFDBITS; - fdsetp->fds_bits[_tmp] |= (1UL<<_rem); -} - -#undef __FD_CLR -static inline void __FD_CLR(unsigned long fd, __kernel_fd_set *fdsetp) -{ - unsigned long _tmp = fd / __NFDBITS; - unsigned long _rem = fd % __NFDBITS; - fdsetp->fds_bits[_tmp] &= ~(1UL<<_rem); -} - -#undef __FD_ISSET -static inline int __FD_ISSET(unsigned long fd, __const__ __kernel_fd_set *p) -{ - unsigned long _tmp = fd / __NFDBITS; - unsigned long _rem = fd % __NFDBITS; - return (p->fds_bits[_tmp] & (1UL<<_rem)) != 0; -} - -/* - * This will unroll the loop for the normal constant cases (8 or 32 longs, - * for 256 and 1024-bit fd_sets respectively) - */ -#undef __FD_ZERO -static inline void __FD_ZERO(__kernel_fd_set *p) -{ - unsigned long *tmp = p->fds_bits; - int i; - - if (__builtin_constant_p(__FDSET_LONGS)) { - switch (__FDSET_LONGS) { - case 32: - tmp[ 0] = 0; tmp[ 1] = 0; tmp[ 2] = 0; tmp[ 3] = 0; - tmp[ 4] = 0; tmp[ 5] = 0; tmp[ 6] = 0; tmp[ 7] = 0; - tmp[ 8] = 0; tmp[ 9] = 0; tmp[10] = 0; tmp[11] = 0; - tmp[12] = 0; tmp[13] = 0; tmp[14] = 0; tmp[15] = 0; - tmp[16] = 0; tmp[17] = 0; tmp[18] = 0; tmp[19] = 0; - tmp[20] = 0; tmp[21] = 0; tmp[22] = 0; tmp[23] = 0; - tmp[24] = 0; tmp[25] = 0; tmp[26] = 0; tmp[27] = 0; - tmp[28] = 0; tmp[29] = 0; tmp[30] = 0; tmp[31] = 0; - return; - case 16: - tmp[ 0] = 0; tmp[ 1] = 0; tmp[ 2] = 0; tmp[ 3] = 0; - tmp[ 4] = 0; tmp[ 5] = 0; tmp[ 6] = 0; tmp[ 7] = 0; - tmp[ 8] = 0; tmp[ 9] = 0; tmp[10] = 0; tmp[11] = 0; - tmp[12] = 0; tmp[13] = 0; tmp[14] = 0; tmp[15] = 0; - return; - case 8: - tmp[ 0] = 0; tmp[ 1] = 0; tmp[ 2] = 0; tmp[ 3] = 0; - tmp[ 4] = 0; tmp[ 5] = 0; tmp[ 6] = 0; tmp[ 7] = 0; - return; - case 4: - tmp[ 0] = 0; tmp[ 1] = 0; tmp[ 2] = 0; tmp[ 3] = 0; - return; - } - } - i = __FDSET_LONGS; - while (i) { - i--; - *tmp = 0; - tmp++; - } -} - -#endif /* defined(__KERNEL__) */ +#include <asm-generic/posix_types.h> #endif /* _ASM_X86_POSIX_TYPES_64_H */ diff --git a/arch/x86/include/asm/posix_types_x32.h b/arch/x86/include/asm/posix_types_x32.h new file mode 100644 index 000000000000..85f9bdafa93c --- /dev/null +++ b/arch/x86/include/asm/posix_types_x32.h @@ -0,0 +1,19 @@ +#ifndef _ASM_X86_POSIX_TYPES_X32_H +#define _ASM_X86_POSIX_TYPES_X32_H + +/* + * This file is only used by user-level software, so you need to + * be a little careful about namespace pollution etc. Also, we cannot + * assume GCC is being used. + * + * These types should generally match the ones used by the 64-bit kernel, + * + */ + +typedef long long __kernel_long_t; +typedef unsigned long long __kernel_ulong_t; +#define __kernel_long_t __kernel_long_t + +#include <asm/posix_types_64.h> + +#endif /* _ASM_X86_POSIX_TYPES_X32_H */ diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h index 95da14f7ee85..7284c9a6a0b5 100644 --- a/arch/x86/include/asm/processor.h +++ b/arch/x86/include/asm/processor.h @@ -14,13 +14,13 @@ struct mm_struct; #include <asm/sigcontext.h> #include <asm/current.h> #include <asm/cpufeature.h> -#include <asm/system.h> #include <asm/page.h> #include <asm/pgtable_types.h> #include <asm/percpu.h> #include <asm/msr.h> #include <asm/desc_defs.h> #include <asm/nops.h> +#include <asm/special_insns.h> #include <linux/personality.h> #include <linux/cpumask.h> @@ -29,6 +29,15 @@ struct mm_struct; #include <linux/math64.h> #include <linux/init.h> #include <linux/err.h> +#include <linux/irqflags.h> + +/* + * 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 #define HBP_NUM 4 /* @@ -454,7 +463,7 @@ struct thread_struct { unsigned long ptrace_dr7; /* Fault info: */ unsigned long cr2; - unsigned long trap_no; + unsigned long trap_nr; unsigned long error_code; /* floating point and extended processor state */ struct fpu fpu; @@ -475,61 +484,6 @@ struct thread_struct { unsigned io_bitmap_max; }; -static inline unsigned long native_get_debugreg(int regno) -{ - unsigned long val = 0; /* Damn you, gcc! */ - - switch (regno) { - case 0: - asm("mov %%db0, %0" :"=r" (val)); - break; - case 1: - asm("mov %%db1, %0" :"=r" (val)); - break; - case 2: - asm("mov %%db2, %0" :"=r" (val)); - break; - case 3: - asm("mov %%db3, %0" :"=r" (val)); - break; - case 6: - asm("mov %%db6, %0" :"=r" (val)); - break; - case 7: - asm("mov %%db7, %0" :"=r" (val)); - break; - default: - BUG(); - } - return val; -} - -static inline void native_set_debugreg(int regno, unsigned long value) -{ - switch (regno) { - case 0: - asm("mov %0, %%db0" ::"r" (value)); - break; - case 1: - asm("mov %0, %%db1" ::"r" (value)); - break; - case 2: - asm("mov %0, %%db2" ::"r" (value)); - break; - case 3: - asm("mov %0, %%db3" ::"r" (value)); - break; - case 6: - asm("mov %0, %%db6" ::"r" (value)); - break; - case 7: - asm("mov %0, %%db7" ::"r" (value)); - break; - default: - BUG(); - } -} - /* * Set IOPL bits in EFLAGS from given mask */ @@ -575,14 +529,6 @@ static inline void native_swapgs(void) #define __cpuid native_cpuid #define paravirt_enabled() 0 -/* - * These special macros can be used to get or set a debugging register - */ -#define get_debugreg(var, register) \ - (var) = native_get_debugreg(register) -#define set_debugreg(value, register) \ - native_set_debugreg(register, value) - static inline void load_sp0(struct tss_struct *tss, struct thread_struct *thread) { @@ -927,9 +873,9 @@ extern unsigned long thread_saved_pc(struct task_struct *tsk); #define IA32_PAGE_OFFSET ((current->personality & ADDR_LIMIT_3GB) ? \ 0xc0000000 : 0xFFFFe000) -#define TASK_SIZE (test_thread_flag(TIF_IA32) ? \ +#define TASK_SIZE (test_thread_flag(TIF_ADDR32) ? \ IA32_PAGE_OFFSET : TASK_SIZE_MAX) -#define TASK_SIZE_OF(child) ((test_tsk_thread_flag(child, TIF_IA32)) ? \ +#define TASK_SIZE_OF(child) ((test_tsk_thread_flag(child, TIF_ADDR32)) ? \ IA32_PAGE_OFFSET : TASK_SIZE_MAX) #define STACK_TOP TASK_SIZE @@ -951,6 +897,12 @@ extern unsigned long thread_saved_pc(struct task_struct *tsk); #define task_pt_regs(tsk) ((struct pt_regs *)(tsk)->thread.sp0 - 1) extern unsigned long KSTK_ESP(struct task_struct *task); + +/* + * User space RSP while inside the SYSCALL fast path + */ +DECLARE_PER_CPU(unsigned long, old_rsp); + #endif /* CONFIG_X86_64 */ extern void start_thread(struct pt_regs *regs, unsigned long new_ip, @@ -1022,4 +974,24 @@ extern bool cpu_has_amd_erratum(const int *); #define cpu_has_amd_erratum(x) (false) #endif /* CONFIG_CPU_SUP_AMD */ +#ifdef CONFIG_X86_32 +/* + * disable hlt during certain critical i/o operations + */ +#define HAVE_DISABLE_HLT +#endif + +void disable_hlt(void); +void enable_hlt(void); + +void cpu_idle_wait(void); + +extern unsigned long arch_align_stack(unsigned long sp); +extern void free_init_pages(char *what, unsigned long begin, unsigned long end); + +void default_idle(void); +bool set_pm_idle_to_default(void); + +void stop_this_cpu(void *dummy); + #endif /* _ASM_X86_PROCESSOR_H */ diff --git a/arch/x86/include/asm/ptrace.h b/arch/x86/include/asm/ptrace.h index 35664547125b..dcfde52979c3 100644 --- a/arch/x86/include/asm/ptrace.h +++ b/arch/x86/include/asm/ptrace.h @@ -145,7 +145,6 @@ extern unsigned long convert_ip_to_linear(struct task_struct *child, struct pt_regs *regs); extern void send_sigtrap(struct task_struct *tsk, struct pt_regs *regs, int error_code, int si_code); -void signal_fault(struct pt_regs *regs, void __user *frame, char *where); extern long syscall_trace_enter(struct pt_regs *); extern void syscall_trace_leave(struct pt_regs *); diff --git a/arch/x86/include/asm/segment.h b/arch/x86/include/asm/segment.h index 5e641715c3fe..165466233ab0 100644 --- a/arch/x86/include/asm/segment.h +++ b/arch/x86/include/asm/segment.h @@ -212,7 +212,61 @@ #ifdef __KERNEL__ #ifndef __ASSEMBLY__ extern const char early_idt_handlers[NUM_EXCEPTION_VECTORS][10]; -#endif -#endif + +/* + * Load a segment. Fall back on loading the zero + * segment if something goes wrong.. + */ +#define loadsegment(seg, value) \ +do { \ + unsigned short __val = (value); \ + \ + asm volatile(" \n" \ + "1: movl %k0,%%" #seg " \n" \ + \ + ".section .fixup,\"ax\" \n" \ + "2: xorl %k0,%k0 \n" \ + " jmp 1b \n" \ + ".previous \n" \ + \ + _ASM_EXTABLE(1b, 2b) \ + \ + : "+r" (__val) : : "memory"); \ +} while (0) + +/* + * Save a segment register away + */ +#define savesegment(seg, value) \ + asm("mov %%" #seg ",%0":"=r" (value) : : "memory") + +/* + * x86_32 user gs accessors. + */ +#ifdef CONFIG_X86_32 +#ifdef CONFIG_X86_32_LAZY_GS +#define get_user_gs(regs) (u16)({unsigned long v; savesegment(gs, v); v;}) +#define set_user_gs(regs, v) loadsegment(gs, (unsigned long)(v)) +#define task_user_gs(tsk) ((tsk)->thread.gs) +#define lazy_save_gs(v) savesegment(gs, (v)) +#define lazy_load_gs(v) loadsegment(gs, (v)) +#else /* X86_32_LAZY_GS */ +#define get_user_gs(regs) (u16)((regs)->gs) +#define set_user_gs(regs, v) do { (regs)->gs = (v); } while (0) +#define task_user_gs(tsk) (task_pt_regs(tsk)->gs) +#define lazy_save_gs(v) do { } while (0) +#define lazy_load_gs(v) do { } while (0) +#endif /* X86_32_LAZY_GS */ +#endif /* X86_32 */ + +static inline unsigned long get_limit(unsigned long segment) +{ + unsigned long __limit; + asm("lsll %1,%0" : "=r" (__limit) : "r" (segment)); + return __limit + 1; +} + +#endif /* !__ASSEMBLY__ */ +#endif /* __KERNEL__ */ #endif /* _ASM_X86_SEGMENT_H */ diff --git a/arch/x86/include/asm/sigcontext.h b/arch/x86/include/asm/sigcontext.h index 04459d25e66e..4a085383af27 100644 --- a/arch/x86/include/asm/sigcontext.h +++ b/arch/x86/include/asm/sigcontext.h @@ -230,34 +230,37 @@ struct sigcontext { * User-space might still rely on the old definition: */ struct sigcontext { - unsigned long r8; - unsigned long r9; - unsigned long r10; - unsigned long r11; - unsigned long r12; - unsigned long r13; - unsigned long r14; - unsigned long r15; - unsigned long rdi; - unsigned long rsi; - unsigned long rbp; - unsigned long rbx; - unsigned long rdx; - unsigned long rax; - unsigned long rcx; - unsigned long rsp; - unsigned long rip; - unsigned long eflags; /* RFLAGS */ - unsigned short cs; - unsigned short gs; - unsigned short fs; - unsigned short __pad0; - unsigned long err; - unsigned long trapno; - unsigned long oldmask; - unsigned long cr2; + __u64 r8; + __u64 r9; + __u64 r10; + __u64 r11; + __u64 r12; + __u64 r13; + __u64 r14; + __u64 r15; + __u64 rdi; + __u64 rsi; + __u64 rbp; + __u64 rbx; + __u64 rdx; + __u64 rax; + __u64 rcx; + __u64 rsp; + __u64 rip; + __u64 eflags; /* RFLAGS */ + __u16 cs; + __u16 gs; + __u16 fs; + __u16 __pad0; + __u64 err; + __u64 trapno; + __u64 oldmask; + __u64 cr2; struct _fpstate __user *fpstate; /* zero when no FPU context */ - unsigned long reserved1[8]; +#ifndef __LP64__ + __u32 __fpstate_pad; +#endif + __u64 reserved1[8]; }; #endif /* !__KERNEL__ */ diff --git a/arch/x86/include/asm/sigframe.h b/arch/x86/include/asm/sigframe.h index 4e0fe26d27d3..7c7c27c97daa 100644 --- a/arch/x86/include/asm/sigframe.h +++ b/arch/x86/include/asm/sigframe.h @@ -59,12 +59,25 @@ struct rt_sigframe_ia32 { #endif /* defined(CONFIG_X86_32) || defined(CONFIG_IA32_EMULATION) */ #ifdef CONFIG_X86_64 + struct rt_sigframe { char __user *pretcode; struct ucontext uc; struct siginfo info; /* fp state follows here */ }; + +#ifdef CONFIG_X86_X32_ABI + +struct rt_sigframe_x32 { + u64 pretcode; + struct ucontext_x32 uc; + compat_siginfo_t info; + /* fp state follows here */ +}; + +#endif /* CONFIG_X86_X32_ABI */ + #endif /* CONFIG_X86_64 */ #endif /* _ASM_X86_SIGFRAME_H */ diff --git a/arch/x86/include/asm/sighandling.h b/arch/x86/include/asm/sighandling.h new file mode 100644 index 000000000000..ada93b3b8c66 --- /dev/null +++ b/arch/x86/include/asm/sighandling.h @@ -0,0 +1,24 @@ +#ifndef _ASM_X86_SIGHANDLING_H +#define _ASM_X86_SIGHANDLING_H + +#include <linux/compiler.h> +#include <linux/ptrace.h> +#include <linux/signal.h> + +#include <asm/processor-flags.h> + +#define _BLOCKABLE (~(sigmask(SIGKILL) | sigmask(SIGSTOP))) + +#define __FIX_EFLAGS (X86_EFLAGS_AC | X86_EFLAGS_OF | \ + X86_EFLAGS_DF | X86_EFLAGS_TF | X86_EFLAGS_SF | \ + X86_EFLAGS_ZF | X86_EFLAGS_AF | X86_EFLAGS_PF | \ + X86_EFLAGS_CF) + +void signal_fault(struct pt_regs *regs, void __user *frame, char *where); + +int restore_sigcontext(struct pt_regs *regs, struct sigcontext __user *sc, + unsigned long *pax); +int setup_sigcontext(struct sigcontext __user *sc, void __user *fpstate, + struct pt_regs *regs, unsigned long mask); + +#endif /* _ASM_X86_SIGHANDLING_H */ diff --git a/arch/x86/include/asm/special_insns.h b/arch/x86/include/asm/special_insns.h new file mode 100644 index 000000000000..41fc93a2e225 --- /dev/null +++ b/arch/x86/include/asm/special_insns.h @@ -0,0 +1,199 @@ +#ifndef _ASM_X86_SPECIAL_INSNS_H +#define _ASM_X86_SPECIAL_INSNS_H + + +#ifdef __KERNEL__ + +static inline void native_clts(void) +{ + asm volatile("clts"); +} + +/* + * Volatile isn't enough to prevent the compiler from reordering the + * read/write functions for the control registers and messing everything up. + * A memory clobber would solve the problem, but would prevent reordering of + * all loads stores around it, which can hurt performance. Solution is to + * use a variable and mimic reads and writes to it to enforce serialization + */ +static unsigned long __force_order; + +static inline unsigned long native_read_cr0(void) +{ + unsigned long val; + asm volatile("mov %%cr0,%0\n\t" : "=r" (val), "=m" (__force_order)); + return val; +} + +static inline void native_write_cr0(unsigned long val) +{ + asm volatile("mov %0,%%cr0": : "r" (val), "m" (__force_order)); +} + +static inline unsigned long native_read_cr2(void) +{ + unsigned long val; + asm volatile("mov %%cr2,%0\n\t" : "=r" (val), "=m" (__force_order)); + return val; +} + +static inline void native_write_cr2(unsigned long val) +{ + asm volatile("mov %0,%%cr2": : "r" (val), "m" (__force_order)); +} + +static inline unsigned long native_read_cr3(void) +{ + unsigned long val; + asm volatile("mov %%cr3,%0\n\t" : "=r" (val), "=m" (__force_order)); + return val; +} + +static inline void native_write_cr3(unsigned long val) +{ + asm volatile("mov %0,%%cr3": : "r" (val), "m" (__force_order)); +} + +static inline unsigned long native_read_cr4(void) +{ + unsigned long val; + asm volatile("mov %%cr4,%0\n\t" : "=r" (val), "=m" (__force_order)); + return val; +} + +static inline unsigned long native_read_cr4_safe(void) +{ + unsigned long val; + /* This could fault if %cr4 does not exist. In x86_64, a cr4 always + * exists, so it will never fail. */ +#ifdef CONFIG_X86_32 + asm volatile("1: mov %%cr4, %0\n" + "2:\n" + _ASM_EXTABLE(1b, 2b) + : "=r" (val), "=m" (__force_order) : "0" (0)); +#else + val = native_read_cr4(); +#endif + return val; +} + +static inline void native_write_cr4(unsigned long val) +{ + asm volatile("mov %0,%%cr4": : "r" (val), "m" (__force_order)); +} + +#ifdef CONFIG_X86_64 +static inline unsigned long native_read_cr8(void) +{ + unsigned long cr8; + asm volatile("movq %%cr8,%0" : "=r" (cr8)); + return cr8; +} + +static inline void native_write_cr8(unsigned long val) +{ + asm volatile("movq %0,%%cr8" :: "r" (val) : "memory"); +} +#endif + +static inline void native_wbinvd(void) +{ + asm volatile("wbinvd": : :"memory"); +} + +extern void native_load_gs_index(unsigned); + +#ifdef CONFIG_PARAVIRT +#include <asm/paravirt.h> +#else + +static inline unsigned long read_cr0(void) +{ + return native_read_cr0(); +} + +static inline void write_cr0(unsigned long x) +{ + native_write_cr0(x); +} + +static inline unsigned long read_cr2(void) +{ + return native_read_cr2(); +} + +static inline void write_cr2(unsigned long x) +{ + native_write_cr2(x); +} + +static inline unsigned long read_cr3(void) +{ + return native_read_cr3(); +} + +static inline void write_cr3(unsigned long x) +{ + native_write_cr3(x); +} + +static inline unsigned long read_cr4(void) +{ + return native_read_cr4(); +} + +static inline unsigned long read_cr4_safe(void) +{ + return native_read_cr4_safe(); +} + +static inline void write_cr4(unsigned long x) +{ + native_write_cr4(x); +} + +static inline void wbinvd(void) +{ + native_wbinvd(); +} + +#ifdef CONFIG_X86_64 + +static inline unsigned long read_cr8(void) +{ + return native_read_cr8(); +} + +static inline void write_cr8(unsigned long x) +{ + native_write_cr8(x); +} + +static inline void load_gs_index(unsigned selector) +{ + native_load_gs_index(selector); +} + +#endif + +/* Clear the 'TS' bit */ +static inline void clts(void) +{ + native_clts(); +} + +#endif/* CONFIG_PARAVIRT */ + +#define stts() write_cr0(read_cr0() | X86_CR0_TS) + +static inline void clflush(volatile void *__p) +{ + asm volatile("clflush %0" : "+m" (*(volatile char __force *)__p)); +} + +#define nop() asm volatile ("nop") + + +#endif /* __KERNEL__ */ + +#endif /* _ASM_X86_SPECIAL_INSNS_H */ diff --git a/arch/x86/include/asm/stackprotector.h b/arch/x86/include/asm/stackprotector.h index 157517763565..b5d9533d2c38 100644 --- a/arch/x86/include/asm/stackprotector.h +++ b/arch/x86/include/asm/stackprotector.h @@ -38,7 +38,6 @@ #include <asm/tsc.h> #include <asm/processor.h> #include <asm/percpu.h> -#include <asm/system.h> #include <asm/desc.h> #include <linux/random.h> diff --git a/arch/x86/include/asm/switch_to.h b/arch/x86/include/asm/switch_to.h new file mode 100644 index 000000000000..4ec45b3abba1 --- /dev/null +++ b/arch/x86/include/asm/switch_to.h @@ -0,0 +1,129 @@ +#ifndef _ASM_X86_SWITCH_TO_H +#define _ASM_X86_SWITCH_TO_H + +struct task_struct; /* one of the stranger aspects of C forward declarations */ +struct task_struct *__switch_to(struct task_struct *prev, + struct task_struct *next); +struct tss_struct; +void __switch_to_xtra(struct task_struct *prev_p, struct task_struct *next_p, + struct tss_struct *tss); + +#ifdef CONFIG_X86_32 + +#ifdef CONFIG_CC_STACKPROTECTOR +#define __switch_canary \ + "movl %P[task_canary](%[next]), %%ebx\n\t" \ + "movl %%ebx, "__percpu_arg([stack_canary])"\n\t" +#define __switch_canary_oparam \ + , [stack_canary] "=m" (stack_canary.canary) +#define __switch_canary_iparam \ + , [task_canary] "i" (offsetof(struct task_struct, stack_canary)) +#else /* CC_STACKPROTECTOR */ +#define __switch_canary +#define __switch_canary_oparam +#define __switch_canary_iparam +#endif /* CC_STACKPROTECTOR */ + +/* + * Saving eflags is important. It switches not only IOPL between tasks, + * it also protects other tasks from NT leaking through sysenter etc. + */ +#define switch_to(prev, next, last) \ +do { \ + /* \ + * Context-switching clobbers all registers, so we clobber \ + * them explicitly, via unused output variables. \ + * (EAX and EBP is not listed because EBP is saved/restored \ + * explicitly for wchan access and EAX is the return value of \ + * __switch_to()) \ + */ \ + unsigned long ebx, ecx, edx, esi, edi; \ + \ + asm volatile("pushfl\n\t" /* save flags */ \ + "pushl %%ebp\n\t" /* save EBP */ \ + "movl %%esp,%[prev_sp]\n\t" /* save ESP */ \ + "movl %[next_sp],%%esp\n\t" /* restore ESP */ \ + "movl $1f,%[prev_ip]\n\t" /* save EIP */ \ + "pushl %[next_ip]\n\t" /* restore EIP */ \ + __switch_canary \ + "jmp __switch_to\n" /* regparm call */ \ + "1:\t" \ + "popl %%ebp\n\t" /* restore EBP */ \ + "popfl\n" /* restore flags */ \ + \ + /* output parameters */ \ + : [prev_sp] "=m" (prev->thread.sp), \ + [prev_ip] "=m" (prev->thread.ip), \ + "=a" (last), \ + \ + /* clobbered output registers: */ \ + "=b" (ebx), "=c" (ecx), "=d" (edx), \ + "=S" (esi), "=D" (edi) \ + \ + __switch_canary_oparam \ + \ + /* input parameters: */ \ + : [next_sp] "m" (next->thread.sp), \ + [next_ip] "m" (next->thread.ip), \ + \ + /* regparm parameters for __switch_to(): */ \ + [prev] "a" (prev), \ + [next] "d" (next) \ + \ + __switch_canary_iparam \ + \ + : /* reloaded segment registers */ \ + "memory"); \ +} while (0) + +#else /* CONFIG_X86_32 */ + +/* frame pointer must be last for get_wchan */ +#define SAVE_CONTEXT "pushf ; pushq %%rbp ; movq %%rsi,%%rbp\n\t" +#define RESTORE_CONTEXT "movq %%rbp,%%rsi ; popq %%rbp ; popf\t" + +#define __EXTRA_CLOBBER \ + , "rcx", "rbx", "rdx", "r8", "r9", "r10", "r11", \ + "r12", "r13", "r14", "r15" + +#ifdef CONFIG_CC_STACKPROTECTOR +#define __switch_canary \ + "movq %P[task_canary](%%rsi),%%r8\n\t" \ + "movq %%r8,"__percpu_arg([gs_canary])"\n\t" +#define __switch_canary_oparam \ + , [gs_canary] "=m" (irq_stack_union.stack_canary) +#define __switch_canary_iparam \ + , [task_canary] "i" (offsetof(struct task_struct, stack_canary)) +#else /* CC_STACKPROTECTOR */ +#define __switch_canary +#define __switch_canary_oparam +#define __switch_canary_iparam +#endif /* CC_STACKPROTECTOR */ + +/* Save restore flags to clear handle leaking NT */ +#define switch_to(prev, next, last) \ + asm volatile(SAVE_CONTEXT \ + "movq %%rsp,%P[threadrsp](%[prev])\n\t" /* save RSP */ \ + "movq %P[threadrsp](%[next]),%%rsp\n\t" /* restore RSP */ \ + "call __switch_to\n\t" \ + "movq "__percpu_arg([current_task])",%%rsi\n\t" \ + __switch_canary \ + "movq %P[thread_info](%%rsi),%%r8\n\t" \ + "movq %%rax,%%rdi\n\t" \ + "testl %[_tif_fork],%P[ti_flags](%%r8)\n\t" \ + "jnz ret_from_fork\n\t" \ + RESTORE_CONTEXT \ + : "=a" (last) \ + __switch_canary_oparam \ + : [next] "S" (next), [prev] "D" (prev), \ + [threadrsp] "i" (offsetof(struct task_struct, thread.sp)), \ + [ti_flags] "i" (offsetof(struct thread_info, flags)), \ + [_tif_fork] "i" (_TIF_FORK), \ + [thread_info] "i" (offsetof(struct task_struct, stack)), \ + [current_task] "m" (current_task) \ + __switch_canary_iparam \ + : "memory", "cc" __EXTRA_CLOBBER) + +#endif /* CONFIG_X86_32 */ + +#endif /* _ASM_X86_SWITCH_TO_H */ diff --git a/arch/x86/include/asm/sys_ia32.h b/arch/x86/include/asm/sys_ia32.h index cb238526a9f1..3fda9db48819 100644 --- a/arch/x86/include/asm/sys_ia32.h +++ b/arch/x86/include/asm/sys_ia32.h @@ -10,6 +10,8 @@ #ifndef _ASM_X86_SYS_IA32_H #define _ASM_X86_SYS_IA32_H +#ifdef CONFIG_COMPAT + #include <linux/compiler.h> #include <linux/linkage.h> #include <linux/types.h> @@ -36,8 +38,6 @@ asmlinkage long sys32_rt_sigaction(int, struct sigaction32 __user *, struct sigaction32 __user *, unsigned int); asmlinkage long sys32_sigaction(int, struct old_sigaction32 __user *, struct old_sigaction32 __user *); -asmlinkage long sys32_rt_sigprocmask(int, compat_sigset_t __user *, - compat_sigset_t __user *, unsigned int); asmlinkage long sys32_alarm(unsigned int); asmlinkage long sys32_waitpid(compat_pid_t, unsigned int *, int); @@ -83,4 +83,7 @@ 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 /* CONFIG_COMPAT */ + #endif /* _ASM_X86_SYS_IA32_H */ diff --git a/arch/x86/include/asm/syscall.h b/arch/x86/include/asm/syscall.h index d962e5652a73..386b78686c4d 100644 --- a/arch/x86/include/asm/syscall.h +++ b/arch/x86/include/asm/syscall.h @@ -16,6 +16,7 @@ #include <linux/sched.h> #include <linux/err.h> #include <asm/asm-offsets.h> /* For NR_syscalls */ +#include <asm/unistd.h> extern const unsigned long sys_call_table[]; @@ -26,13 +27,13 @@ extern const unsigned long sys_call_table[]; */ static inline int syscall_get_nr(struct task_struct *task, struct pt_regs *regs) { - return regs->orig_ax; + return regs->orig_ax & __SYSCALL_MASK; } static inline void syscall_rollback(struct task_struct *task, struct pt_regs *regs) { - regs->ax = regs->orig_ax; + regs->ax = regs->orig_ax & __SYSCALL_MASK; } static inline long syscall_get_error(struct task_struct *task, diff --git a/arch/x86/include/asm/system.h b/arch/x86/include/asm/system.h deleted file mode 100644 index 2d2f01ce6dcb..000000000000 --- a/arch/x86/include/asm/system.h +++ /dev/null @@ -1,523 +0,0 @@ -#ifndef _ASM_X86_SYSTEM_H -#define _ASM_X86_SYSTEM_H - -#include <asm/asm.h> -#include <asm/segment.h> -#include <asm/cpufeature.h> -#include <asm/cmpxchg.h> -#include <asm/nops.h> - -#include <linux/kernel.h> -#include <linux/irqflags.h> - -/* entries in ARCH_DLINFO: */ -#if defined(CONFIG_IA32_EMULATION) || !defined(CONFIG_X86_64) -# define AT_VECTOR_SIZE_ARCH 2 -#else /* else it's non-compat x86-64 */ -# define AT_VECTOR_SIZE_ARCH 1 -#endif - -struct task_struct; /* one of the stranger aspects of C forward declarations */ -struct task_struct *__switch_to(struct task_struct *prev, - struct task_struct *next); -struct tss_struct; -void __switch_to_xtra(struct task_struct *prev_p, struct task_struct *next_p, - struct tss_struct *tss); -extern void show_regs_common(void); - -#ifdef CONFIG_X86_32 - -#ifdef CONFIG_CC_STACKPROTECTOR -#define __switch_canary \ - "movl %P[task_canary](%[next]), %%ebx\n\t" \ - "movl %%ebx, "__percpu_arg([stack_canary])"\n\t" -#define __switch_canary_oparam \ - , [stack_canary] "=m" (stack_canary.canary) -#define __switch_canary_iparam \ - , [task_canary] "i" (offsetof(struct task_struct, stack_canary)) -#else /* CC_STACKPROTECTOR */ -#define __switch_canary -#define __switch_canary_oparam -#define __switch_canary_iparam -#endif /* CC_STACKPROTECTOR */ - -/* - * Saving eflags is important. It switches not only IOPL between tasks, - * it also protects other tasks from NT leaking through sysenter etc. - */ -#define switch_to(prev, next, last) \ -do { \ - /* \ - * Context-switching clobbers all registers, so we clobber \ - * them explicitly, via unused output variables. \ - * (EAX and EBP is not listed because EBP is saved/restored \ - * explicitly for wchan access and EAX is the return value of \ - * __switch_to()) \ - */ \ - unsigned long ebx, ecx, edx, esi, edi; \ - \ - asm volatile("pushfl\n\t" /* save flags */ \ - "pushl %%ebp\n\t" /* save EBP */ \ - "movl %%esp,%[prev_sp]\n\t" /* save ESP */ \ - "movl %[next_sp],%%esp\n\t" /* restore ESP */ \ - "movl $1f,%[prev_ip]\n\t" /* save EIP */ \ - "pushl %[next_ip]\n\t" /* restore EIP */ \ - __switch_canary \ - "jmp __switch_to\n" /* regparm call */ \ - "1:\t" \ - "popl %%ebp\n\t" /* restore EBP */ \ - "popfl\n" /* restore flags */ \ - \ - /* output parameters */ \ - : [prev_sp] "=m" (prev->thread.sp), \ - [prev_ip] "=m" (prev->thread.ip), \ - "=a" (last), \ - \ - /* clobbered output registers: */ \ - "=b" (ebx), "=c" (ecx), "=d" (edx), \ - "=S" (esi), "=D" (edi) \ - \ - __switch_canary_oparam \ - \ - /* input parameters: */ \ - : [next_sp] "m" (next->thread.sp), \ - [next_ip] "m" (next->thread.ip), \ - \ - /* regparm parameters for __switch_to(): */ \ - [prev] "a" (prev), \ - [next] "d" (next) \ - \ - __switch_canary_iparam \ - \ - : /* reloaded segment registers */ \ - "memory"); \ -} while (0) - -/* - * disable hlt during certain critical i/o operations - */ -#define HAVE_DISABLE_HLT -#else - -/* frame pointer must be last for get_wchan */ -#define SAVE_CONTEXT "pushf ; pushq %%rbp ; movq %%rsi,%%rbp\n\t" -#define RESTORE_CONTEXT "movq %%rbp,%%rsi ; popq %%rbp ; popf\t" - -#define __EXTRA_CLOBBER \ - , "rcx", "rbx", "rdx", "r8", "r9", "r10", "r11", \ - "r12", "r13", "r14", "r15" - -#ifdef CONFIG_CC_STACKPROTECTOR -#define __switch_canary \ - "movq %P[task_canary](%%rsi),%%r8\n\t" \ - "movq %%r8,"__percpu_arg([gs_canary])"\n\t" -#define __switch_canary_oparam \ - , [gs_canary] "=m" (irq_stack_union.stack_canary) -#define __switch_canary_iparam \ - , [task_canary] "i" (offsetof(struct task_struct, stack_canary)) -#else /* CC_STACKPROTECTOR */ -#define __switch_canary -#define __switch_canary_oparam -#define __switch_canary_iparam -#endif /* CC_STACKPROTECTOR */ - -/* Save restore flags to clear handle leaking NT */ -#define switch_to(prev, next, last) \ - asm volatile(SAVE_CONTEXT \ - "movq %%rsp,%P[threadrsp](%[prev])\n\t" /* save RSP */ \ - "movq %P[threadrsp](%[next]),%%rsp\n\t" /* restore RSP */ \ - "call __switch_to\n\t" \ - "movq "__percpu_arg([current_task])",%%rsi\n\t" \ - __switch_canary \ - "movq %P[thread_info](%%rsi),%%r8\n\t" \ - "movq %%rax,%%rdi\n\t" \ - "testl %[_tif_fork],%P[ti_flags](%%r8)\n\t" \ - "jnz ret_from_fork\n\t" \ - RESTORE_CONTEXT \ - : "=a" (last) \ - __switch_canary_oparam \ - : [next] "S" (next), [prev] "D" (prev), \ - [threadrsp] "i" (offsetof(struct task_struct, thread.sp)), \ - [ti_flags] "i" (offsetof(struct thread_info, flags)), \ - [_tif_fork] "i" (_TIF_FORK), \ - [thread_info] "i" (offsetof(struct task_struct, stack)), \ - [current_task] "m" (current_task) \ - __switch_canary_iparam \ - : "memory", "cc" __EXTRA_CLOBBER) -#endif - -#ifdef __KERNEL__ - -extern void native_load_gs_index(unsigned); - -/* - * Load a segment. Fall back on loading the zero - * segment if something goes wrong.. - */ -#define loadsegment(seg, value) \ -do { \ - unsigned short __val = (value); \ - \ - asm volatile(" \n" \ - "1: movl %k0,%%" #seg " \n" \ - \ - ".section .fixup,\"ax\" \n" \ - "2: xorl %k0,%k0 \n" \ - " jmp 1b \n" \ - ".previous \n" \ - \ - _ASM_EXTABLE(1b, 2b) \ - \ - : "+r" (__val) : : "memory"); \ -} while (0) - -/* - * Save a segment register away - */ -#define savesegment(seg, value) \ - asm("mov %%" #seg ",%0":"=r" (value) : : "memory") - -/* - * x86_32 user gs accessors. - */ -#ifdef CONFIG_X86_32 -#ifdef CONFIG_X86_32_LAZY_GS -#define get_user_gs(regs) (u16)({unsigned long v; savesegment(gs, v); v;}) -#define set_user_gs(regs, v) loadsegment(gs, (unsigned long)(v)) -#define task_user_gs(tsk) ((tsk)->thread.gs) -#define lazy_save_gs(v) savesegment(gs, (v)) -#define lazy_load_gs(v) loadsegment(gs, (v)) -#else /* X86_32_LAZY_GS */ -#define get_user_gs(regs) (u16)((regs)->gs) -#define set_user_gs(regs, v) do { (regs)->gs = (v); } while (0) -#define task_user_gs(tsk) (task_pt_regs(tsk)->gs) -#define lazy_save_gs(v) do { } while (0) -#define lazy_load_gs(v) do { } while (0) -#endif /* X86_32_LAZY_GS */ -#endif /* X86_32 */ - -static inline unsigned long get_limit(unsigned long segment) -{ - unsigned long __limit; - asm("lsll %1,%0" : "=r" (__limit) : "r" (segment)); - return __limit + 1; -} - -static inline void native_clts(void) -{ - asm volatile("clts"); -} - -/* - * Volatile isn't enough to prevent the compiler from reordering the - * read/write functions for the control registers and messing everything up. - * A memory clobber would solve the problem, but would prevent reordering of - * all loads stores around it, which can hurt performance. Solution is to - * use a variable and mimic reads and writes to it to enforce serialization - */ -static unsigned long __force_order; - -static inline unsigned long native_read_cr0(void) -{ - unsigned long val; - asm volatile("mov %%cr0,%0\n\t" : "=r" (val), "=m" (__force_order)); - return val; -} - -static inline void native_write_cr0(unsigned long val) -{ - asm volatile("mov %0,%%cr0": : "r" (val), "m" (__force_order)); -} - -static inline unsigned long native_read_cr2(void) -{ - unsigned long val; - asm volatile("mov %%cr2,%0\n\t" : "=r" (val), "=m" (__force_order)); - return val; -} - -static inline void native_write_cr2(unsigned long val) -{ - asm volatile("mov %0,%%cr2": : "r" (val), "m" (__force_order)); -} - -static inline unsigned long native_read_cr3(void) -{ - unsigned long val; - asm volatile("mov %%cr3,%0\n\t" : "=r" (val), "=m" (__force_order)); - return val; -} - -static inline void native_write_cr3(unsigned long val) -{ - asm volatile("mov %0,%%cr3": : "r" (val), "m" (__force_order)); -} - -static inline unsigned long native_read_cr4(void) -{ - unsigned long val; - asm volatile("mov %%cr4,%0\n\t" : "=r" (val), "=m" (__force_order)); - return val; -} - -static inline unsigned long native_read_cr4_safe(void) -{ - unsigned long val; - /* This could fault if %cr4 does not exist. In x86_64, a cr4 always - * exists, so it will never fail. */ -#ifdef CONFIG_X86_32 - asm volatile("1: mov %%cr4, %0\n" - "2:\n" - _ASM_EXTABLE(1b, 2b) - : "=r" (val), "=m" (__force_order) : "0" (0)); -#else - val = native_read_cr4(); -#endif - return val; -} - -static inline void native_write_cr4(unsigned long val) -{ - asm volatile("mov %0,%%cr4": : "r" (val), "m" (__force_order)); -} - -#ifdef CONFIG_X86_64 -static inline unsigned long native_read_cr8(void) -{ - unsigned long cr8; - asm volatile("movq %%cr8,%0" : "=r" (cr8)); - return cr8; -} - -static inline void native_write_cr8(unsigned long val) -{ - asm volatile("movq %0,%%cr8" :: "r" (val) : "memory"); -} -#endif - -static inline void native_wbinvd(void) -{ - asm volatile("wbinvd": : :"memory"); -} - -#ifdef CONFIG_PARAVIRT -#include <asm/paravirt.h> -#else - -static inline unsigned long read_cr0(void) -{ - return native_read_cr0(); -} - -static inline void write_cr0(unsigned long x) -{ - native_write_cr0(x); -} - -static inline unsigned long read_cr2(void) -{ - return native_read_cr2(); -} - -static inline void write_cr2(unsigned long x) -{ - native_write_cr2(x); -} - -static inline unsigned long read_cr3(void) -{ - return native_read_cr3(); -} - -static inline void write_cr3(unsigned long x) -{ - native_write_cr3(x); -} - -static inline unsigned long read_cr4(void) -{ - return native_read_cr4(); -} - -static inline unsigned long read_cr4_safe(void) -{ - return native_read_cr4_safe(); -} - -static inline void write_cr4(unsigned long x) -{ - native_write_cr4(x); -} - -static inline void wbinvd(void) -{ - native_wbinvd(); -} - -#ifdef CONFIG_X86_64 - -static inline unsigned long read_cr8(void) -{ - return native_read_cr8(); -} - -static inline void write_cr8(unsigned long x) -{ - native_write_cr8(x); -} - -static inline void load_gs_index(unsigned selector) -{ - native_load_gs_index(selector); -} - -#endif - -/* Clear the 'TS' bit */ -static inline void clts(void) -{ - native_clts(); -} - -#endif/* CONFIG_PARAVIRT */ - -#define stts() write_cr0(read_cr0() | X86_CR0_TS) - -#endif /* __KERNEL__ */ - -static inline void clflush(volatile void *__p) -{ - asm volatile("clflush %0" : "+m" (*(volatile char __force *)__p)); -} - -#define nop() asm volatile ("nop") - -void disable_hlt(void); -void enable_hlt(void); - -void cpu_idle_wait(void); - -extern unsigned long arch_align_stack(unsigned long sp); -extern void free_init_pages(char *what, unsigned long begin, unsigned long end); - -void default_idle(void); -bool set_pm_idle_to_default(void); - -void stop_this_cpu(void *dummy); - -/* - * Force strict CPU ordering. - * And yes, this is required on UP too when we're talking - * to devices. - */ -#ifdef CONFIG_X86_32 -/* - * Some non-Intel clones support out of order store. wmb() ceases to be a - * nop for these. - */ -#define mb() alternative("lock; addl $0,0(%%esp)", "mfence", X86_FEATURE_XMM2) -#define rmb() alternative("lock; addl $0,0(%%esp)", "lfence", X86_FEATURE_XMM2) -#define wmb() alternative("lock; addl $0,0(%%esp)", "sfence", X86_FEATURE_XMM) -#else -#define mb() asm volatile("mfence":::"memory") -#define rmb() asm volatile("lfence":::"memory") -#define wmb() asm volatile("sfence" ::: "memory") -#endif - -/** - * read_barrier_depends - Flush all pending reads that subsequents reads - * depend on. - * - * No data-dependent reads from memory-like regions are ever reordered - * over this barrier. All reads preceding this primitive are guaranteed - * to access memory (but not necessarily other CPUs' caches) before any - * reads following this primitive that depend on the data return by - * any of the preceding reads. This primitive is much lighter weight than - * rmb() on most CPUs, and is never heavier weight than is - * rmb(). - * - * These ordering constraints are respected by both the local CPU - * and the compiler. - * - * Ordering is not guaranteed by anything other than these primitives, - * not even by data dependencies. See the documentation for - * memory_barrier() for examples and URLs to more information. - * - * For example, the following code would force ordering (the initial - * value of "a" is zero, "b" is one, and "p" is "&a"): - * - * <programlisting> - * CPU 0 CPU 1 - * - * b = 2; - * memory_barrier(); - * p = &b; q = p; - * read_barrier_depends(); - * d = *q; - * </programlisting> - * - * because the read of "*q" depends on the read of "p" and these - * two reads are separated by a read_barrier_depends(). However, - * the following code, with the same initial values for "a" and "b": - * - * <programlisting> - * CPU 0 CPU 1 - * - * a = 2; - * memory_barrier(); - * b = 3; y = b; - * read_barrier_depends(); - * x = a; - * </programlisting> - * - * does not enforce ordering, since there is no data dependency between - * the read of "a" and the read of "b". Therefore, on some CPUs, such - * as Alpha, "y" could be set to 3 and "x" to 0. Use rmb() - * in cases like this where there are no data dependencies. - **/ - -#define read_barrier_depends() do { } while (0) - -#ifdef CONFIG_SMP -#define smp_mb() mb() -#ifdef CONFIG_X86_PPRO_FENCE -# define smp_rmb() rmb() -#else -# define smp_rmb() barrier() -#endif -#ifdef CONFIG_X86_OOSTORE -# define smp_wmb() wmb() -#else -# define smp_wmb() barrier() -#endif -#define smp_read_barrier_depends() read_barrier_depends() -#define set_mb(var, value) do { (void)xchg(&var, value); } while (0) -#else -#define smp_mb() barrier() -#define smp_rmb() barrier() -#define smp_wmb() barrier() -#define smp_read_barrier_depends() do { } while (0) -#define set_mb(var, value) do { var = value; barrier(); } while (0) -#endif - -/* - * Stop RDTSC speculation. This is needed when you need to use RDTSC - * (or get_cycles or vread that possibly accesses the TSC) in a defined - * code region. - * - * (Could use an alternative three way for this if there was one.) - */ -static __always_inline void rdtsc_barrier(void) -{ - alternative(ASM_NOP3, "mfence", X86_FEATURE_MFENCE_RDTSC); - alternative(ASM_NOP3, "lfence", X86_FEATURE_LFENCE_RDTSC); -} - -/* - * We handle most unaligned accesses in hardware. On the other hand - * unaligned DMA can be quite expensive on some Nehalem processors. - * - * Based on this we disable the IP header alignment in network drivers. - */ -#define NET_IP_ALIGN 0 -#endif /* _ASM_X86_SYSTEM_H */ diff --git a/arch/x86/include/asm/thread_info.h b/arch/x86/include/asm/thread_info.h index cfd8144d5527..ad6df8ccd715 100644 --- a/arch/x86/include/asm/thread_info.h +++ b/arch/x86/include/asm/thread_info.h @@ -86,7 +86,7 @@ struct thread_info { #define TIF_MCE_NOTIFY 10 /* notify userspace of an MCE */ #define TIF_USER_RETURN_NOTIFY 11 /* notify kernel of userspace return */ #define TIF_NOTSC 16 /* TSC is not accessible in userland */ -#define TIF_IA32 17 /* 32bit process */ +#define TIF_IA32 17 /* IA32 compatibility process */ #define TIF_FORK 18 /* ret_from_fork */ #define TIF_MEMDIE 20 /* is terminating due to OOM killer */ #define TIF_DEBUG 21 /* uses debug registers */ @@ -95,6 +95,8 @@ struct thread_info { #define TIF_BLOCKSTEP 25 /* set when we want DEBUGCTLMSR_BTF */ #define TIF_LAZY_MMU_UPDATES 27 /* task is updating the mmu lazily */ #define TIF_SYSCALL_TRACEPOINT 28 /* syscall tracepoint instrumentation */ +#define TIF_ADDR32 29 /* 32-bit address space on 64 bits */ +#define TIF_X32 30 /* 32-bit native x86-64 binary */ #define _TIF_SYSCALL_TRACE (1 << TIF_SYSCALL_TRACE) #define _TIF_NOTIFY_RESUME (1 << TIF_NOTIFY_RESUME) @@ -116,6 +118,8 @@ struct thread_info { #define _TIF_BLOCKSTEP (1 << TIF_BLOCKSTEP) #define _TIF_LAZY_MMU_UPDATES (1 << TIF_LAZY_MMU_UPDATES) #define _TIF_SYSCALL_TRACEPOINT (1 << TIF_SYSCALL_TRACEPOINT) +#define _TIF_ADDR32 (1 << TIF_ADDR32) +#define _TIF_X32 (1 << TIF_X32) /* work to do in syscall_trace_enter() */ #define _TIF_WORK_SYSCALL_ENTRY \ @@ -262,6 +266,18 @@ static inline void set_restore_sigmask(void) ti->status |= TS_RESTORE_SIGMASK; set_bit(TIF_SIGPENDING, (unsigned long *)&ti->flags); } + +static inline bool is_ia32_task(void) +{ +#ifdef CONFIG_X86_32 + return true; +#endif +#ifdef CONFIG_IA32_EMULATION + if (current_thread_info()->status & TS_COMPAT) + return true; +#endif + return false; +} #endif /* !__ASSEMBLY__ */ #ifndef __ASSEMBLY__ diff --git a/arch/x86/include/asm/tlbflush.h b/arch/x86/include/asm/tlbflush.h index 169be8938b96..c0e108e08079 100644 --- a/arch/x86/include/asm/tlbflush.h +++ b/arch/x86/include/asm/tlbflush.h @@ -5,7 +5,7 @@ #include <linux/sched.h> #include <asm/processor.h> -#include <asm/system.h> +#include <asm/special_insns.h> #ifdef CONFIG_PARAVIRT #include <asm/paravirt.h> diff --git a/arch/x86/include/asm/traps.h b/arch/x86/include/asm/traps.h index 0012d0902c5f..88eae2aec619 100644 --- a/arch/x86/include/asm/traps.h +++ b/arch/x86/include/asm/traps.h @@ -89,4 +89,29 @@ asmlinkage void smp_thermal_interrupt(void); asmlinkage void mce_threshold_interrupt(void); #endif +/* Interrupts/Exceptions */ +enum { + X86_TRAP_DE = 0, /* 0, Divide-by-zero */ + X86_TRAP_DB, /* 1, Debug */ + X86_TRAP_NMI, /* 2, Non-maskable Interrupt */ + X86_TRAP_BP, /* 3, Breakpoint */ + X86_TRAP_OF, /* 4, Overflow */ + X86_TRAP_BR, /* 5, Bound Range Exceeded */ + X86_TRAP_UD, /* 6, Invalid Opcode */ + X86_TRAP_NM, /* 7, Device Not Available */ + X86_TRAP_DF, /* 8, Double Fault */ + X86_TRAP_OLD_MF, /* 9, Coprocessor Segment Overrun */ + X86_TRAP_TS, /* 10, Invalid TSS */ + X86_TRAP_NP, /* 11, Segment Not Present */ + X86_TRAP_SS, /* 12, Stack Segment Fault */ + X86_TRAP_GP, /* 13, General Protection Fault */ + X86_TRAP_PF, /* 14, Page Fault */ + X86_TRAP_SPURIOUS, /* 15, Spurious Interrupt */ + X86_TRAP_MF, /* 16, x87 Floating-Point Exception */ + X86_TRAP_AC, /* 17, Alignment Check */ + X86_TRAP_MC, /* 18, Machine Check */ + X86_TRAP_XF, /* 19, SIMD Floating-Point Exception */ + X86_TRAP_IRET = 32, /* 32, IRET Exception */ +}; + #endif /* _ASM_X86_TRAPS_H */ diff --git a/arch/x86/include/asm/tsc.h b/arch/x86/include/asm/tsc.h index 15d99153a96d..c91e8b9d588b 100644 --- a/arch/x86/include/asm/tsc.h +++ b/arch/x86/include/asm/tsc.h @@ -61,7 +61,7 @@ extern void check_tsc_sync_source(int cpu); extern void check_tsc_sync_target(void); extern int notsc_setup(char *); -extern void save_sched_clock_state(void); -extern void restore_sched_clock_state(void); +extern void tsc_save_sched_clock_state(void); +extern void tsc_restore_sched_clock_state(void); #endif /* _ASM_X86_TSC_H */ diff --git a/arch/x86/include/asm/unistd.h b/arch/x86/include/asm/unistd.h index 21f77b89e47a..37cdc9d99bb1 100644 --- a/arch/x86/include/asm/unistd.h +++ b/arch/x86/include/asm/unistd.h @@ -1,7 +1,17 @@ #ifndef _ASM_X86_UNISTD_H #define _ASM_X86_UNISTD_H 1 +/* x32 syscall flag bit */ +#define __X32_SYSCALL_BIT 0x40000000 + #ifdef __KERNEL__ + +# ifdef CONFIG_X86_X32_ABI +# define __SYSCALL_MASK (~(__X32_SYSCALL_BIT)) +# else +# define __SYSCALL_MASK (~0) +# endif + # ifdef CONFIG_X86_32 # include <asm/unistd_32.h> @@ -14,6 +24,7 @@ # else # include <asm/unistd_64.h> +# include <asm/unistd_64_x32.h> # define __ARCH_WANT_COMPAT_SYS_TIME # endif @@ -52,8 +63,10 @@ #else # ifdef __i386__ # include <asm/unistd_32.h> -# else +# elif defined(__LP64__) # include <asm/unistd_64.h> +# else +# include <asm/unistd_x32.h> # endif #endif diff --git a/arch/x86/include/asm/vgtod.h b/arch/x86/include/asm/vgtod.h index 815285bcaceb..8b38be2de9e1 100644 --- a/arch/x86/include/asm/vgtod.h +++ b/arch/x86/include/asm/vgtod.h @@ -5,13 +5,8 @@ #include <linux/clocksource.h> struct vsyscall_gtod_data { - seqlock_t lock; + seqcount_t seq; - /* open coded 'struct timespec' */ - time_t wall_time_sec; - u32 wall_time_nsec; - - struct timezone sys_tz; struct { /* extract of a clocksource struct */ int vclock_mode; cycle_t cycle_last; @@ -19,8 +14,16 @@ struct vsyscall_gtod_data { u32 mult; u32 shift; } clock; - struct timespec wall_to_monotonic; + + /* open coded 'struct timespec' */ + time_t wall_time_sec; + u32 wall_time_nsec; + u32 monotonic_time_nsec; + time_t monotonic_time_sec; + + struct timezone sys_tz; struct timespec wall_time_coarse; + struct timespec monotonic_time_coarse; }; extern struct vsyscall_gtod_data vsyscall_gtod_data; diff --git a/arch/x86/include/asm/virtext.h b/arch/x86/include/asm/virtext.h index e0f9aa16358b..5da71c27cc59 100644 --- a/arch/x86/include/asm/virtext.h +++ b/arch/x86/include/asm/virtext.h @@ -16,7 +16,6 @@ #define _ASM_X86_VIRTEX_H #include <asm/processor.h> -#include <asm/system.h> #include <asm/vmx.h> #include <asm/svm.h> diff --git a/arch/x86/include/asm/x86_init.h b/arch/x86/include/asm/x86_init.h index 517d4767ffdd..baaca8defec8 100644 --- a/arch/x86/include/asm/x86_init.h +++ b/arch/x86/include/asm/x86_init.h @@ -145,9 +145,11 @@ struct x86_init_ops { /** * struct x86_cpuinit_ops - platform specific cpu hotplug setups * @setup_percpu_clockev: set up the per cpu clock event device + * @early_percpu_clock_init: early init of the per cpu clock event device */ struct x86_cpuinit_ops { void (*setup_percpu_clockev)(void); + void (*early_percpu_clock_init)(void); void (*fixup_cpu_id)(struct cpuinfo_x86 *c, int node); }; @@ -160,6 +162,8 @@ struct x86_cpuinit_ops { * @is_untracked_pat_range exclude from PAT logic * @nmi_init enable NMI on cpus * @i8042_detect pre-detect if i8042 controller exists + * @save_sched_clock_state: save state for sched_clock() on suspend + * @restore_sched_clock_state: restore state for sched_clock() on resume */ struct x86_platform_ops { unsigned long (*calibrate_tsc)(void); @@ -171,6 +175,8 @@ struct x86_platform_ops { void (*nmi_init)(void); unsigned char (*get_nmi_reason)(void); int (*i8042_detect)(void); + void (*save_sched_clock_state)(void); + void (*restore_sched_clock_state)(void); }; struct pci_dev; diff --git a/arch/x86/include/asm/xen/interface.h b/arch/x86/include/asm/xen/interface.h index a1f2db5f1170..cbf0c9d50b92 100644 --- a/arch/x86/include/asm/xen/interface.h +++ b/arch/x86/include/asm/xen/interface.h @@ -56,6 +56,7 @@ DEFINE_GUEST_HANDLE(int); DEFINE_GUEST_HANDLE(long); DEFINE_GUEST_HANDLE(void); DEFINE_GUEST_HANDLE(uint64_t); +DEFINE_GUEST_HANDLE(uint32_t); #endif #ifndef HYPERVISOR_VIRT_START diff --git a/arch/x86/kernel/acpi/cstate.c b/arch/x86/kernel/acpi/cstate.c index f50e7fb2a201..d2b7f27781bc 100644 --- a/arch/x86/kernel/acpi/cstate.c +++ b/arch/x86/kernel/acpi/cstate.c @@ -14,6 +14,7 @@ #include <acpi/processor.h> #include <asm/acpi.h> #include <asm/mwait.h> +#include <asm/special_insns.h> /* * Initialize bm_flags based on the CPU cache properties diff --git a/arch/x86/kernel/apm_32.c b/arch/x86/kernel/apm_32.c index 5d56931a15b3..459e78cbf61e 100644 --- a/arch/x86/kernel/apm_32.c +++ b/arch/x86/kernel/apm_32.c @@ -231,7 +231,6 @@ #include <linux/syscore_ops.h> #include <linux/i8253.h> -#include <asm/system.h> #include <asm/uaccess.h> #include <asm/desc.h> #include <asm/olpc.h> diff --git a/arch/x86/kernel/asm-offsets_64.c b/arch/x86/kernel/asm-offsets_64.c index 834e897b1e25..1b4754f82ba7 100644 --- a/arch/x86/kernel/asm-offsets_64.c +++ b/arch/x86/kernel/asm-offsets_64.c @@ -1,6 +1,12 @@ #include <asm/ia32.h> #define __SYSCALL_64(nr, sym, compat) [nr] = 1, +#define __SYSCALL_COMMON(nr, sym, compat) [nr] = 1, +#ifdef CONFIG_X86_X32_ABI +# define __SYSCALL_X32(nr, sym, compat) [nr] = 1, +#else +# define __SYSCALL_X32(nr, sym, compat) /* nothing */ +#endif static char syscalls_64[] = { #include <asm/syscalls_64.h> }; diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c index b24032355a76..67e258362a3d 100644 --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -18,6 +18,7 @@ #include <asm/archrandom.h> #include <asm/hypervisor.h> #include <asm/processor.h> +#include <asm/debugreg.h> #include <asm/sections.h> #include <linux/topology.h> #include <linux/cpumask.h> diff --git a/arch/x86/kernel/cpu/mcheck/p5.c b/arch/x86/kernel/cpu/mcheck/p5.c index 5c0e6533d9bc..2d5454cd2c4f 100644 --- a/arch/x86/kernel/cpu/mcheck/p5.c +++ b/arch/x86/kernel/cpu/mcheck/p5.c @@ -9,7 +9,6 @@ #include <linux/smp.h> #include <asm/processor.h> -#include <asm/system.h> #include <asm/mce.h> #include <asm/msr.h> diff --git a/arch/x86/kernel/cpu/mcheck/therm_throt.c b/arch/x86/kernel/cpu/mcheck/therm_throt.c index 67bb17a37a0a..47a1870279aa 100644 --- a/arch/x86/kernel/cpu/mcheck/therm_throt.c +++ b/arch/x86/kernel/cpu/mcheck/therm_throt.c @@ -25,7 +25,6 @@ #include <linux/cpu.h> #include <asm/processor.h> -#include <asm/system.h> #include <asm/apic.h> #include <asm/idle.h> #include <asm/mce.h> diff --git a/arch/x86/kernel/cpu/mcheck/winchip.c b/arch/x86/kernel/cpu/mcheck/winchip.c index 54060f565974..2d7998fb628c 100644 --- a/arch/x86/kernel/cpu/mcheck/winchip.c +++ b/arch/x86/kernel/cpu/mcheck/winchip.c @@ -8,7 +8,6 @@ #include <linux/init.h> #include <asm/processor.h> -#include <asm/system.h> #include <asm/mce.h> #include <asm/msr.h> diff --git a/arch/x86/kernel/cpu/mtrr/generic.c b/arch/x86/kernel/cpu/mtrr/generic.c index 97b26356e9ee..75772ae6c65f 100644 --- a/arch/x86/kernel/cpu/mtrr/generic.c +++ b/arch/x86/kernel/cpu/mtrr/generic.c @@ -12,7 +12,6 @@ #include <asm/processor-flags.h> #include <asm/cpufeature.h> #include <asm/tlbflush.h> -#include <asm/system.h> #include <asm/mtrr.h> #include <asm/msr.h> #include <asm/pat.h> diff --git a/arch/x86/kernel/cpu/mtrr/if.c b/arch/x86/kernel/cpu/mtrr/if.c index 79289632cb27..a041e094b8b9 100644 --- a/arch/x86/kernel/cpu/mtrr/if.c +++ b/arch/x86/kernel/cpu/mtrr/if.c @@ -167,6 +167,7 @@ mtrr_ioctl(struct file *file, unsigned int cmd, unsigned long __arg) { int err = 0; mtrr_type type; + unsigned long base; unsigned long size; struct mtrr_sentry sentry; struct mtrr_gentry gentry; @@ -267,14 +268,14 @@ mtrr_ioctl(struct file *file, unsigned int cmd, unsigned long __arg) #endif if (gentry.regnum >= num_var_ranges) return -EINVAL; - mtrr_if->get(gentry.regnum, &gentry.base, &size, &type); + mtrr_if->get(gentry.regnum, &base, &size, &type); /* Hide entries that go above 4GB */ - if (gentry.base + size - 1 >= (1UL << (8 * sizeof(gentry.size) - PAGE_SHIFT)) + if (base + size - 1 >= (1UL << (8 * sizeof(gentry.size) - PAGE_SHIFT)) || size >= (1UL << (8 * sizeof(gentry.size) - PAGE_SHIFT))) gentry.base = gentry.size = gentry.type = 0; else { - gentry.base <<= PAGE_SHIFT; + gentry.base = base << PAGE_SHIFT; gentry.size = size << PAGE_SHIFT; gentry.type = type; } @@ -321,11 +322,12 @@ mtrr_ioctl(struct file *file, unsigned int cmd, unsigned long __arg) #endif if (gentry.regnum >= num_var_ranges) return -EINVAL; - mtrr_if->get(gentry.regnum, &gentry.base, &size, &type); + mtrr_if->get(gentry.regnum, &base, &size, &type); /* Hide entries that would overflow */ if (size != (__typeof__(gentry.size))size) gentry.base = gentry.size = gentry.type = 0; else { + gentry.base = base; gentry.size = size; gentry.type = type; } diff --git a/arch/x86/kernel/cpu/perf_event.c b/arch/x86/kernel/cpu/perf_event.c index 0a18d16cb58d..40883ffe2da9 100644 --- a/arch/x86/kernel/cpu/perf_event.c +++ b/arch/x86/kernel/cpu/perf_event.c @@ -29,7 +29,6 @@ #include <asm/apic.h> #include <asm/stacktrace.h> #include <asm/nmi.h> -#include <asm/compat.h> #include <asm/smp.h> #include <asm/alternative.h> #include <asm/timer.h> @@ -643,14 +642,14 @@ static bool __perf_sched_find_counter(struct perf_sched *sched) /* Prefer fixed purpose counters */ if (x86_pmu.num_counters_fixed) { idx = X86_PMC_IDX_FIXED; - for_each_set_bit_cont(idx, c->idxmsk, X86_PMC_IDX_MAX) { + for_each_set_bit_from(idx, c->idxmsk, X86_PMC_IDX_MAX) { if (!__test_and_set_bit(idx, sched->state.used)) goto done; } } /* Grab the first unused counter starting with idx */ idx = sched->state.counter; - for_each_set_bit_cont(idx, c->idxmsk, X86_PMC_IDX_FIXED) { + for_each_set_bit_from(idx, c->idxmsk, X86_PMC_IDX_FIXED) { if (!__test_and_set_bit(idx, sched->state.used)) goto done; } @@ -1748,6 +1747,9 @@ perf_callchain_kernel(struct perf_callchain_entry *entry, struct pt_regs *regs) } #ifdef CONFIG_COMPAT + +#include <asm/compat.h> + static inline int perf_callchain_user32(struct pt_regs *regs, struct perf_callchain_entry *entry) { diff --git a/arch/x86/kernel/cpuid.c b/arch/x86/kernel/cpuid.c index a524353d93f2..39472dd2323f 100644 --- a/arch/x86/kernel/cpuid.c +++ b/arch/x86/kernel/cpuid.c @@ -43,7 +43,6 @@ #include <asm/processor.h> #include <asm/msr.h> -#include <asm/system.h> static struct class *cpuid_class; diff --git a/arch/x86/kernel/dumpstack.c b/arch/x86/kernel/dumpstack.c index 90bf130f09bc..1b81839b6c88 100644 --- a/arch/x86/kernel/dumpstack.c +++ b/arch/x86/kernel/dumpstack.c @@ -268,7 +268,7 @@ int __kprobes __die(const char *str, struct pt_regs *regs, long err) #endif printk("\n"); if (notify_die(DIE_OOPS, str, regs, err, - current->thread.trap_no, SIGSEGV) == NOTIFY_STOP) + current->thread.trap_nr, SIGSEGV) == NOTIFY_STOP) return 1; show_registers(regs); diff --git a/arch/x86/kernel/entry_64.S b/arch/x86/kernel/entry_64.S index 734ebd1d3caa..cdc79b5cfcd9 100644 --- a/arch/x86/kernel/entry_64.S +++ b/arch/x86/kernel/entry_64.S @@ -481,7 +481,12 @@ GLOBAL(system_call_after_swapgs) testl $_TIF_WORK_SYSCALL_ENTRY,TI_flags+THREAD_INFO(%rsp,RIP-ARGOFFSET) jnz tracesys system_call_fastpath: +#if __SYSCALL_MASK == ~0 cmpq $__NR_syscall_max,%rax +#else + andl $__SYSCALL_MASK,%eax + cmpl $__NR_syscall_max,%eax +#endif ja badsys movq %r10,%rcx call *sys_call_table(,%rax,8) # XXX: rip relative @@ -595,7 +600,12 @@ tracesys: */ LOAD_ARGS ARGOFFSET, 1 RESTORE_REST +#if __SYSCALL_MASK == ~0 cmpq $__NR_syscall_max,%rax +#else + andl $__SYSCALL_MASK,%eax + cmpl $__NR_syscall_max,%eax +#endif ja int_ret_from_sys_call /* RAX(%rsp) set to -ENOSYS above */ movq %r10,%rcx /* fixup for C */ call *sys_call_table(,%rax,8) @@ -735,6 +745,40 @@ ENTRY(stub_rt_sigreturn) CFI_ENDPROC END(stub_rt_sigreturn) +#ifdef CONFIG_X86_X32_ABI + PTREGSCALL stub_x32_sigaltstack, sys32_sigaltstack, %rdx + +ENTRY(stub_x32_rt_sigreturn) + CFI_STARTPROC + addq $8, %rsp + PARTIAL_FRAME 0 + SAVE_REST + movq %rsp,%rdi + FIXUP_TOP_OF_STACK %r11 + call sys32_x32_rt_sigreturn + movq %rax,RAX(%rsp) # fixme, this could be done at the higher layer + RESTORE_REST + jmp int_ret_from_sys_call + CFI_ENDPROC +END(stub_x32_rt_sigreturn) + +ENTRY(stub_x32_execve) + CFI_STARTPROC + addq $8, %rsp + PARTIAL_FRAME 0 + SAVE_REST + FIXUP_TOP_OF_STACK %r11 + movq %rsp, %rcx + call sys32_execve + RESTORE_TOP_OF_STACK %r11 + movq %rax,RAX(%rsp) + RESTORE_REST + jmp int_ret_from_sys_call + CFI_ENDPROC +END(stub_x32_execve) + +#endif + /* * Build the entry stubs and pointer table with some assembler magic. * We pack 7 stubs into a single 32-byte chunk, which will fit in a diff --git a/arch/x86/kernel/i8259.c b/arch/x86/kernel/i8259.c index 610485223bdb..36d1853e91af 100644 --- a/arch/x86/kernel/i8259.c +++ b/arch/x86/kernel/i8259.c @@ -15,7 +15,6 @@ #include <linux/delay.h> #include <linux/atomic.h> -#include <asm/system.h> #include <asm/timer.h> #include <asm/hw_irq.h> #include <asm/pgtable.h> diff --git a/arch/x86/kernel/irqinit.c b/arch/x86/kernel/irqinit.c index 313fb5cddbce..252981afd6c4 100644 --- a/arch/x86/kernel/irqinit.c +++ b/arch/x86/kernel/irqinit.c @@ -16,7 +16,6 @@ #include <linux/delay.h> #include <linux/atomic.h> -#include <asm/system.h> #include <asm/timer.h> #include <asm/hw_irq.h> #include <asm/pgtable.h> @@ -61,7 +60,7 @@ static irqreturn_t math_error_irq(int cpl, void *dev_id) outb(0, 0xF0); if (ignore_fpu_irq || !boot_cpu_data.hard_math) return IRQ_NONE; - math_error(get_irq_regs(), 0, 16); + math_error(get_irq_regs(), 0, X86_TRAP_MF); return IRQ_HANDLED; } @@ -306,10 +305,10 @@ void __init native_init_IRQ(void) * us. (some of these will be overridden and become * 'special' SMP interrupts) */ - for (i = FIRST_EXTERNAL_VECTOR; i < NR_VECTORS; i++) { + i = FIRST_EXTERNAL_VECTOR; + for_each_clear_bit_from(i, used_vectors, NR_VECTORS) { /* IA32_SYSCALL_VECTOR could be used in trap_init already. */ - if (!test_bit(i, used_vectors)) - set_intr_gate(i, interrupt[i-FIRST_EXTERNAL_VECTOR]); + set_intr_gate(i, interrupt[i - FIRST_EXTERNAL_VECTOR]); } if (!acpi_ioapic && !of_ioapic) diff --git a/arch/x86/kernel/kgdb.c b/arch/x86/kernel/kgdb.c index faba5771acad..db6720edfdd0 100644 --- a/arch/x86/kernel/kgdb.c +++ b/arch/x86/kernel/kgdb.c @@ -46,7 +46,6 @@ #include <asm/debugreg.h> #include <asm/apicdef.h> -#include <asm/system.h> #include <asm/apic.h> #include <asm/nmi.h> @@ -67,8 +66,6 @@ struct dbg_reg_def_t dbg_reg_def[DBG_MAX_REG_NUM] = { "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) }, @@ -90,7 +87,11 @@ struct dbg_reg_def_t dbg_reg_def[DBG_MAX_REG_NUM] = { "flags", 4, offsetof(struct pt_regs, flags) }, { "cs", 4, offsetof(struct pt_regs, cs) }, { "ss", 4, offsetof(struct pt_regs, ss) }, + { "ds", 4, -1 }, + { "es", 4, -1 }, #endif + { "fs", 4, -1 }, + { "gs", 4, -1 }, }; int dbg_set_reg(int regno, void *mem, struct pt_regs *regs) diff --git a/arch/x86/kernel/kvmclock.c b/arch/x86/kernel/kvmclock.c index 44842d756b29..f8492da65bfc 100644 --- a/arch/x86/kernel/kvmclock.c +++ b/arch/x86/kernel/kvmclock.c @@ -136,6 +136,15 @@ int kvm_register_clock(char *txt) return ret; } +static void kvm_save_sched_clock_state(void) +{ +} + +static void kvm_restore_sched_clock_state(void) +{ + kvm_register_clock("primary cpu clock, resume"); +} + #ifdef CONFIG_X86_LOCAL_APIC static void __cpuinit kvm_setup_secondary_clock(void) { @@ -144,8 +153,6 @@ static void __cpuinit kvm_setup_secondary_clock(void) * we shouldn't fail. */ WARN_ON(kvm_register_clock("secondary cpu clock")); - /* ok, done with our trickery, call native */ - setup_secondary_APIC_clock(); } #endif @@ -194,9 +201,11 @@ void __init kvmclock_init(void) x86_platform.get_wallclock = kvm_get_wallclock; x86_platform.set_wallclock = kvm_set_wallclock; #ifdef CONFIG_X86_LOCAL_APIC - x86_cpuinit.setup_percpu_clockev = + x86_cpuinit.early_percpu_clock_init = kvm_setup_secondary_clock; #endif + x86_platform.save_sched_clock_state = kvm_save_sched_clock_state; + x86_platform.restore_sched_clock_state = kvm_restore_sched_clock_state; machine_ops.shutdown = kvm_shutdown; #ifdef CONFIG_KEXEC machine_ops.crash_shutdown = kvm_crash_shutdown; diff --git a/arch/x86/kernel/ldt.c b/arch/x86/kernel/ldt.c index ea697263b373..ebc987398923 100644 --- a/arch/x86/kernel/ldt.c +++ b/arch/x86/kernel/ldt.c @@ -15,7 +15,6 @@ #include <linux/vmalloc.h> #include <linux/uaccess.h> -#include <asm/system.h> #include <asm/ldt.h> #include <asm/desc.h> #include <asm/mmu_context.h> diff --git a/arch/x86/kernel/machine_kexec_32.c b/arch/x86/kernel/machine_kexec_32.c index a3fa43ba5d3b..5b19e4d78b00 100644 --- a/arch/x86/kernel/machine_kexec_32.c +++ b/arch/x86/kernel/machine_kexec_32.c @@ -23,7 +23,6 @@ #include <asm/apic.h> #include <asm/cpufeature.h> #include <asm/desc.h> -#include <asm/system.h> #include <asm/cacheflush.h> #include <asm/debugreg.h> diff --git a/arch/x86/kernel/mca_32.c b/arch/x86/kernel/mca_32.c index 177183cbb6ae..7eb1e2b97827 100644 --- a/arch/x86/kernel/mca_32.c +++ b/arch/x86/kernel/mca_32.c @@ -43,7 +43,6 @@ #include <linux/mca.h> #include <linux/kprobes.h> #include <linux/slab.h> -#include <asm/system.h> #include <asm/io.h> #include <linux/proc_fs.h> #include <linux/mman.h> diff --git a/arch/x86/kernel/module.c b/arch/x86/kernel/module.c index 925179f871de..f21fd94ac897 100644 --- a/arch/x86/kernel/module.c +++ b/arch/x86/kernel/module.c @@ -26,7 +26,6 @@ #include <linux/gfp.h> #include <linux/jump_label.h> -#include <asm/system.h> #include <asm/page.h> #include <asm/pgtable.h> diff --git a/arch/x86/kernel/msr.c b/arch/x86/kernel/msr.c index 96356762a51d..eb113693f043 100644 --- a/arch/x86/kernel/msr.c +++ b/arch/x86/kernel/msr.c @@ -40,7 +40,6 @@ #include <asm/processor.h> #include <asm/msr.h> -#include <asm/system.h> static struct class *msr_class; diff --git a/arch/x86/kernel/paravirt.c b/arch/x86/kernel/paravirt.c index ada2f99388dd..ab137605e694 100644 --- a/arch/x86/kernel/paravirt.c +++ b/arch/x86/kernel/paravirt.c @@ -26,6 +26,7 @@ #include <asm/bug.h> #include <asm/paravirt.h> +#include <asm/debugreg.h> #include <asm/desc.h> #include <asm/setup.h> #include <asm/pgtable.h> @@ -37,6 +38,7 @@ #include <asm/apic.h> #include <asm/tlbflush.h> #include <asm/timer.h> +#include <asm/special_insns.h> /* nop stub */ void _paravirt_nop(void) diff --git a/arch/x86/kernel/pci-calgary_64.c b/arch/x86/kernel/pci-calgary_64.c index 726494b58345..6ac5782f4d6b 100644 --- a/arch/x86/kernel/pci-calgary_64.c +++ b/arch/x86/kernel/pci-calgary_64.c @@ -42,7 +42,6 @@ #include <asm/calgary.h> #include <asm/tce.h> #include <asm/pci-direct.h> -#include <asm/system.h> #include <asm/dma.h> #include <asm/rio.h> #include <asm/bios_ebda.h> diff --git a/arch/x86/kernel/pci-dma.c b/arch/x86/kernel/pci-dma.c index 1c4d769e21ea..28e5e06fcba4 100644 --- a/arch/x86/kernel/pci-dma.c +++ b/arch/x86/kernel/pci-dma.c @@ -262,10 +262,11 @@ rootfs_initcall(pci_iommu_init); static __devinit void via_no_dac(struct pci_dev *dev) { - if ((dev->class >> 8) == PCI_CLASS_BRIDGE_PCI && forbid_dac == 0) { + if (forbid_dac == 0) { dev_info(&dev->dev, "disabling DAC on VIA PCI bridge\n"); forbid_dac = 1; } } -DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_VIA, PCI_ANY_ID, via_no_dac); +DECLARE_PCI_FIXUP_CLASS_FINAL(PCI_VENDOR_ID_VIA, PCI_ANY_ID, + PCI_CLASS_BRIDGE_PCI, 8, via_no_dac); #endif diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c index 29309c42b9e5..a33afaa5ddb7 100644 --- a/arch/x86/kernel/process.c +++ b/arch/x86/kernel/process.c @@ -18,7 +18,6 @@ #include <trace/events/power.h> #include <linux/hw_breakpoint.h> #include <asm/cpu.h> -#include <asm/system.h> #include <asm/apic.h> #include <asm/syscalls.h> #include <asm/idle.h> diff --git a/arch/x86/kernel/process_32.c b/arch/x86/kernel/process_32.c index ea207c245aa4..ae6847303e26 100644 --- a/arch/x86/kernel/process_32.c +++ b/arch/x86/kernel/process_32.c @@ -38,7 +38,6 @@ #include <linux/kdebug.h> #include <asm/pgtable.h> -#include <asm/system.h> #include <asm/ldt.h> #include <asm/processor.h> #include <asm/i387.h> @@ -55,6 +54,7 @@ #include <asm/idle.h> #include <asm/syscalls.h> #include <asm/debugreg.h> +#include <asm/switch_to.h> asmlinkage void ret_from_fork(void) __asm__("ret_from_fork"); diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c index ce5e34f2beca..733ca39f367e 100644 --- a/arch/x86/kernel/process_64.c +++ b/arch/x86/kernel/process_64.c @@ -37,7 +37,6 @@ #include <linux/ftrace.h> #include <asm/pgtable.h> -#include <asm/system.h> #include <asm/processor.h> #include <asm/i387.h> #include <asm/fpu-internal.h> @@ -49,6 +48,7 @@ #include <asm/idle.h> #include <asm/syscalls.h> #include <asm/debugreg.h> +#include <asm/switch_to.h> asmlinkage extern void ret_from_fork(void); @@ -258,7 +258,9 @@ start_thread(struct pt_regs *regs, unsigned long new_ip, unsigned long new_sp) void start_thread_ia32(struct pt_regs *regs, u32 new_ip, u32 new_sp) { start_thread_common(regs, new_ip, new_sp, - __USER32_CS, __USER32_DS, __USER32_DS); + test_thread_flag(TIF_X32) + ? __USER_CS : __USER32_CS, + __USER_DS, __USER_DS); } #endif @@ -381,6 +383,8 @@ void set_personality_64bit(void) /* Make sure to be in 64bit mode */ clear_thread_flag(TIF_IA32); + clear_thread_flag(TIF_ADDR32); + clear_thread_flag(TIF_X32); /* Ensure the corresponding mm is not marked. */ if (current->mm) @@ -393,20 +397,31 @@ void set_personality_64bit(void) current->personality &= ~READ_IMPLIES_EXEC; } -void set_personality_ia32(void) +void set_personality_ia32(bool x32) { /* inherit personality from parent */ /* Make sure to be in 32bit mode */ - set_thread_flag(TIF_IA32); - current->personality |= force_personality32; + set_thread_flag(TIF_ADDR32); /* Mark the associated mm as containing 32-bit tasks. */ if (current->mm) current->mm->context.ia32_compat = 1; - /* Prepare the first "return" to user space */ - current_thread_info()->status |= TS_COMPAT; + if (x32) { + clear_thread_flag(TIF_IA32); + set_thread_flag(TIF_X32); + current->personality &= ~READ_IMPLIES_EXEC; + /* is_compat_task() uses the presence of the x32 + syscall bit flag to determine compat status */ + current_thread_info()->status &= ~TS_COMPAT; + } else { + set_thread_flag(TIF_IA32); + clear_thread_flag(TIF_X32); + current->personality |= force_personality32; + /* Prepare the first "return" to user space */ + current_thread_info()->status |= TS_COMPAT; + } } unsigned long get_wchan(struct task_struct *p) diff --git a/arch/x86/kernel/ptrace.c b/arch/x86/kernel/ptrace.c index 78f05e438be5..685845cf16e0 100644 --- a/arch/x86/kernel/ptrace.c +++ b/arch/x86/kernel/ptrace.c @@ -24,7 +24,6 @@ #include <asm/uaccess.h> #include <asm/pgtable.h> -#include <asm/system.h> #include <asm/processor.h> #include <asm/i387.h> #include <asm/fpu-internal.h> @@ -34,6 +33,7 @@ #include <asm/prctl.h> #include <asm/proto.h> #include <asm/hw_breakpoint.h> +#include <asm/traps.h> #include "tls.h" @@ -1131,6 +1131,100 @@ static int genregs32_set(struct task_struct *target, return ret; } +#ifdef CONFIG_X86_X32_ABI +static long x32_arch_ptrace(struct task_struct *child, + compat_long_t request, compat_ulong_t caddr, + compat_ulong_t cdata) +{ + unsigned long addr = caddr; + unsigned long data = cdata; + void __user *datap = compat_ptr(data); + int ret; + + switch (request) { + /* Read 32bits at location addr in the USER area. Only allow + to return the lower 32bits of segment and debug registers. */ + case PTRACE_PEEKUSR: { + u32 tmp; + + ret = -EIO; + if ((addr & (sizeof(data) - 1)) || addr >= sizeof(struct user) || + addr < offsetof(struct user_regs_struct, cs)) + break; + + tmp = 0; /* Default return condition */ + if (addr < sizeof(struct user_regs_struct)) + tmp = getreg(child, addr); + else if (addr >= offsetof(struct user, u_debugreg[0]) && + addr <= offsetof(struct user, u_debugreg[7])) { + addr -= offsetof(struct user, u_debugreg[0]); + tmp = ptrace_get_debugreg(child, addr / sizeof(data)); + } + ret = put_user(tmp, (__u32 __user *)datap); + break; + } + + /* Write the word at location addr in the USER area. Only allow + to update segment and debug registers with the upper 32bits + zero-extended. */ + case PTRACE_POKEUSR: + ret = -EIO; + if ((addr & (sizeof(data) - 1)) || addr >= sizeof(struct user) || + addr < offsetof(struct user_regs_struct, cs)) + break; + + if (addr < sizeof(struct user_regs_struct)) + ret = putreg(child, addr, data); + else if (addr >= offsetof(struct user, u_debugreg[0]) && + addr <= offsetof(struct user, u_debugreg[7])) { + addr -= offsetof(struct user, u_debugreg[0]); + ret = ptrace_set_debugreg(child, + addr / sizeof(data), data); + } + break; + + case PTRACE_GETREGS: /* Get all gp regs from the child. */ + return copy_regset_to_user(child, + task_user_regset_view(current), + REGSET_GENERAL, + 0, sizeof(struct user_regs_struct), + datap); + + case PTRACE_SETREGS: /* Set all gp regs in the child. */ + return copy_regset_from_user(child, + task_user_regset_view(current), + REGSET_GENERAL, + 0, sizeof(struct user_regs_struct), + datap); + + case PTRACE_GETFPREGS: /* Get the child FPU state. */ + return copy_regset_to_user(child, + task_user_regset_view(current), + REGSET_FP, + 0, sizeof(struct user_i387_struct), + datap); + + case PTRACE_SETFPREGS: /* Set the child FPU state. */ + return copy_regset_from_user(child, + task_user_regset_view(current), + REGSET_FP, + 0, sizeof(struct user_i387_struct), + datap); + + /* normal 64bit interface to access TLS data. + Works just like arch_prctl, except that the arguments + are reversed. */ + case PTRACE_ARCH_PRCTL: + return do_arch_prctl(child, data, addr); + + default: + return compat_ptrace_request(child, request, addr, data); + } + + return ret; +} +#endif + long compat_arch_ptrace(struct task_struct *child, compat_long_t request, compat_ulong_t caddr, compat_ulong_t cdata) { @@ -1140,6 +1234,11 @@ long compat_arch_ptrace(struct task_struct *child, compat_long_t request, int ret; __u32 val; +#ifdef CONFIG_X86_X32_ABI + if (!is_ia32_task()) + return x32_arch_ptrace(child, request, caddr, cdata); +#endif + switch (request) { case PTRACE_PEEKUSR: ret = getreg32(child, addr, &val); @@ -1327,7 +1426,7 @@ static void fill_sigtrap_info(struct task_struct *tsk, int error_code, int si_code, struct siginfo *info) { - tsk->thread.trap_no = 1; + tsk->thread.trap_nr = X86_TRAP_DB; tsk->thread.error_code = error_code; memset(info, 0, sizeof(*info)); diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c index 88638883176a..1a2901562059 100644 --- a/arch/x86/kernel/setup.c +++ b/arch/x86/kernel/setup.c @@ -90,7 +90,6 @@ #include <asm/processor.h> #include <asm/bugs.h> -#include <asm/system.h> #include <asm/vsyscall.h> #include <asm/cpu.h> #include <asm/desc.h> @@ -509,15 +508,6 @@ static void __init memblock_x86_reserve_range_setup_data(void) #ifdef CONFIG_KEXEC -static inline unsigned long long get_total_mem(void) -{ - unsigned long long total; - - total = max_pfn - min_low_pfn; - - return total << PAGE_SHIFT; -} - /* * Keep the crash kernel below this limit. On 32 bits earlier kernels * would limit the kernel to the low 512 MiB due to mapping restrictions. @@ -536,7 +526,7 @@ static void __init reserve_crashkernel(void) unsigned long long crash_size, crash_base; int ret; - total_mem = get_total_mem(); + total_mem = memblock_phys_mem_size(); ret = parse_crashkernel(boot_command_line, total_mem, &crash_size, &crash_base); diff --git a/arch/x86/kernel/signal.c b/arch/x86/kernel/signal.c index 25edcfc9ba5b..115eac431483 100644 --- a/arch/x86/kernel/signal.c +++ b/arch/x86/kernel/signal.c @@ -10,10 +10,8 @@ #include <linux/mm.h> #include <linux/smp.h> #include <linux/kernel.h> -#include <linux/signal.h> #include <linux/errno.h> #include <linux/wait.h> -#include <linux/ptrace.h> #include <linux/tracehook.h> #include <linux/unistd.h> #include <linux/stddef.h> @@ -27,10 +25,12 @@ #include <asm/fpu-internal.h> #include <asm/vdso.h> #include <asm/mce.h> +#include <asm/sighandling.h> #ifdef CONFIG_X86_64 #include <asm/proto.h> #include <asm/ia32_unistd.h> +#include <asm/sys_ia32.h> #endif /* CONFIG_X86_64 */ #include <asm/syscall.h> @@ -38,13 +38,6 @@ #include <asm/sigframe.h> -#define _BLOCKABLE (~(sigmask(SIGKILL) | sigmask(SIGSTOP))) - -#define __FIX_EFLAGS (X86_EFLAGS_AC | X86_EFLAGS_OF | \ - X86_EFLAGS_DF | X86_EFLAGS_TF | X86_EFLAGS_SF | \ - X86_EFLAGS_ZF | X86_EFLAGS_AF | X86_EFLAGS_PF | \ - X86_EFLAGS_CF) - #ifdef CONFIG_X86_32 # define FIX_EFLAGS (__FIX_EFLAGS | X86_EFLAGS_RF) #else @@ -69,9 +62,8 @@ regs->seg = GET_SEG(seg) | 3; \ } while (0) -static int -restore_sigcontext(struct pt_regs *regs, struct sigcontext __user *sc, - unsigned long *pax) +int restore_sigcontext(struct pt_regs *regs, struct sigcontext __user *sc, + unsigned long *pax) { void __user *buf; unsigned int tmpflags; @@ -126,9 +118,8 @@ restore_sigcontext(struct pt_regs *regs, struct sigcontext __user *sc, return err; } -static int -setup_sigcontext(struct sigcontext __user *sc, void __user *fpstate, - struct pt_regs *regs, unsigned long mask) +int setup_sigcontext(struct sigcontext __user *sc, void __user *fpstate, + struct pt_regs *regs, unsigned long mask) { int err = 0; @@ -160,7 +151,7 @@ setup_sigcontext(struct sigcontext __user *sc, void __user *fpstate, put_user_ex(regs->r15, &sc->r15); #endif /* CONFIG_X86_64 */ - put_user_ex(current->thread.trap_no, &sc->trapno); + put_user_ex(current->thread.trap_nr, &sc->trapno); put_user_ex(current->thread.error_code, &sc->err); put_user_ex(regs->ip, &sc->ip); #ifdef CONFIG_X86_32 @@ -643,6 +634,16 @@ static int signr_convert(int sig) #define is_ia32 0 #endif /* CONFIG_IA32_EMULATION */ +#ifdef CONFIG_X86_X32_ABI +#define is_x32 test_thread_flag(TIF_X32) + +static int x32_setup_rt_frame(int sig, struct k_sigaction *ka, + siginfo_t *info, compat_sigset_t *set, + struct pt_regs *regs); +#else /* !CONFIG_X86_X32_ABI */ +#define is_x32 0 +#endif /* CONFIG_X86_X32_ABI */ + int ia32_setup_rt_frame(int sig, struct k_sigaction *ka, siginfo_t *info, sigset_t *set, struct pt_regs *regs); int ia32_setup_frame(int sig, struct k_sigaction *ka, @@ -667,8 +668,14 @@ setup_rt_frame(int sig, struct k_sigaction *ka, siginfo_t *info, ret = ia32_setup_rt_frame(usig, ka, info, set, regs); else ret = ia32_setup_frame(usig, ka, set, regs); - } else +#ifdef CONFIG_X86_X32_ABI + } else if (is_x32) { + ret = x32_setup_rt_frame(usig, ka, info, + (compat_sigset_t *)set, regs); +#endif + } else { ret = __setup_rt_frame(sig, ka, info, set, regs); + } if (ret) { force_sigsegv(sig, current); @@ -851,3 +858,102 @@ void signal_fault(struct pt_regs *regs, void __user *frame, char *where) force_sig(SIGSEGV, me); } + +#ifdef CONFIG_X86_X32_ABI +static int x32_setup_rt_frame(int sig, struct k_sigaction *ka, + siginfo_t *info, compat_sigset_t *set, + struct pt_regs *regs) +{ + struct rt_sigframe_x32 __user *frame; + void __user *restorer; + int err = 0; + void __user *fpstate = NULL; + + frame = get_sigframe(ka, regs, sizeof(*frame), &fpstate); + + if (!access_ok(VERIFY_WRITE, frame, sizeof(*frame))) + return -EFAULT; + + if (ka->sa.sa_flags & SA_SIGINFO) { + if (copy_siginfo_to_user32(&frame->info, info)) + return -EFAULT; + } + + put_user_try { + /* Create the ucontext. */ + if (cpu_has_xsave) + put_user_ex(UC_FP_XSTATE, &frame->uc.uc_flags); + else + put_user_ex(0, &frame->uc.uc_flags); + put_user_ex(0, &frame->uc.uc_link); + put_user_ex(current->sas_ss_sp, &frame->uc.uc_stack.ss_sp); + put_user_ex(sas_ss_flags(regs->sp), + &frame->uc.uc_stack.ss_flags); + put_user_ex(current->sas_ss_size, &frame->uc.uc_stack.ss_size); + put_user_ex(0, &frame->uc.uc__pad0); + err |= setup_sigcontext(&frame->uc.uc_mcontext, fpstate, + regs, set->sig[0]); + err |= __copy_to_user(&frame->uc.uc_sigmask, set, sizeof(*set)); + + if (ka->sa.sa_flags & SA_RESTORER) { + restorer = ka->sa.sa_restorer; + } else { + /* could use a vstub here */ + restorer = NULL; + err |= -EFAULT; + } + put_user_ex(restorer, &frame->pretcode); + } put_user_catch(err); + + if (err) + return -EFAULT; + + /* Set up registers for signal handler */ + regs->sp = (unsigned long) frame; + regs->ip = (unsigned long) ka->sa.sa_handler; + + /* We use the x32 calling convention here... */ + regs->di = sig; + regs->si = (unsigned long) &frame->info; + regs->dx = (unsigned long) &frame->uc; + + loadsegment(ds, __USER_DS); + loadsegment(es, __USER_DS); + + regs->cs = __USER_CS; + regs->ss = __USER_DS; + + return 0; +} + +asmlinkage long sys32_x32_rt_sigreturn(struct pt_regs *regs) +{ + struct rt_sigframe_x32 __user *frame; + sigset_t set; + unsigned long ax; + struct pt_regs tregs; + + frame = (struct rt_sigframe_x32 __user *)(regs->sp - 8); + + if (!access_ok(VERIFY_READ, frame, sizeof(*frame))) + goto badframe; + if (__copy_from_user(&set, &frame->uc.uc_sigmask, sizeof(set))) + goto badframe; + + sigdelsetmask(&set, ~_BLOCKABLE); + set_current_blocked(&set); + + if (restore_sigcontext(regs, &frame->uc.uc_mcontext, &ax)) + goto badframe; + + tregs = *regs; + if (sys32_sigaltstack(&frame->uc.uc_stack, NULL, &tregs) == -EFAULT) + goto badframe; + + return ax; + +badframe: + signal_fault(regs, frame, "x32 rt_sigreturn"); + return 0; +} +#endif diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c index e578a79a3093..ce13315d48fb 100644 --- a/arch/x86/kernel/smpboot.c +++ b/arch/x86/kernel/smpboot.c @@ -219,14 +219,9 @@ static void __cpuinit smp_callin(void) * Update loops_per_jiffy in cpu_data. Previous call to * smp_store_cpu_info() stored a value that is close but not as * accurate as the value just calculated. - * - * Need to enable IRQs because it can take longer and then - * the NMI watchdog might kill us. */ - local_irq_enable(); calibrate_delay(); cpu_data(cpuid).loops_per_jiffy = loops_per_jiffy; - local_irq_disable(); pr_debug("Stack at about %p\n", &cpuid); /* @@ -255,6 +250,7 @@ notrace static void __cpuinit start_secondary(void *unused) * most necessary things. */ cpu_init(); + x86_cpuinit.early_percpu_clock_init(); preempt_disable(); smp_callin(); diff --git a/arch/x86/kernel/sys_x86_64.c b/arch/x86/kernel/sys_x86_64.c index ef59642ff1bf..b4d3c3927dd8 100644 --- a/arch/x86/kernel/sys_x86_64.c +++ b/arch/x86/kernel/sys_x86_64.c @@ -98,7 +98,7 @@ out: static void find_start_end(unsigned long flags, unsigned long *begin, unsigned long *end) { - if (!test_thread_flag(TIF_IA32) && (flags & MAP_32BIT)) { + if (!test_thread_flag(TIF_ADDR32) && (flags & MAP_32BIT)) { unsigned long new_begin; /* This is usually used needed to map code in small model, so it needs to be in the first 31bit. Limit @@ -144,7 +144,7 @@ arch_get_unmapped_area(struct file *filp, unsigned long addr, (!vma || addr + len <= vma->vm_start)) return addr; } - if (((flags & MAP_32BIT) || test_thread_flag(TIF_IA32)) + if (((flags & MAP_32BIT) || test_thread_flag(TIF_ADDR32)) && len <= mm->cached_hole_size) { mm->cached_hole_size = 0; mm->free_area_cache = begin; @@ -205,7 +205,7 @@ arch_get_unmapped_area_topdown(struct file *filp, const unsigned long addr0, return addr; /* for MAP_32BIT mappings we force the legact mmap base */ - if (!test_thread_flag(TIF_IA32) && (flags & MAP_32BIT)) + if (!test_thread_flag(TIF_ADDR32) && (flags & MAP_32BIT)) goto bottomup; /* requesting a specific address */ diff --git a/arch/x86/kernel/syscall_64.c b/arch/x86/kernel/syscall_64.c index 7ac7943be02c..5c7f8c20da74 100644 --- a/arch/x86/kernel/syscall_64.c +++ b/arch/x86/kernel/syscall_64.c @@ -5,6 +5,14 @@ #include <linux/cache.h> #include <asm/asm-offsets.h> +#define __SYSCALL_COMMON(nr, sym, compat) __SYSCALL_64(nr, sym, compat) + +#ifdef CONFIG_X86_X32_ABI +# define __SYSCALL_X32(nr, sym, compat) __SYSCALL_64(nr, sym, compat) +#else +# define __SYSCALL_X32(nr, sym, compat) /* nothing */ +#endif + #define __SYSCALL_64(nr, sym, compat) extern asmlinkage void sym(void) ; #include <asm/syscalls_64.h> #undef __SYSCALL_64 diff --git a/arch/x86/kernel/tce_64.c b/arch/x86/kernel/tce_64.c index 9e540fee7009..ab40954e113e 100644 --- a/arch/x86/kernel/tce_64.c +++ b/arch/x86/kernel/tce_64.c @@ -34,6 +34,7 @@ #include <asm/tce.h> #include <asm/calgary.h> #include <asm/proto.h> +#include <asm/cacheflush.h> /* flush a tce at 'tceaddr' to main memory */ static inline void flush_tce(void* tceaddr) diff --git a/arch/x86/kernel/tls.c b/arch/x86/kernel/tls.c index bcfec2d23769..9d9d2f9e77a5 100644 --- a/arch/x86/kernel/tls.c +++ b/arch/x86/kernel/tls.c @@ -6,7 +6,6 @@ #include <asm/uaccess.h> #include <asm/desc.h> -#include <asm/system.h> #include <asm/ldt.h> #include <asm/processor.h> #include <asm/proto.h> diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c index ec61d4c1b93b..ff9281f16029 100644 --- a/arch/x86/kernel/traps.c +++ b/arch/x86/kernel/traps.c @@ -50,7 +50,6 @@ #include <asm/processor.h> #include <asm/debugreg.h> #include <linux/atomic.h> -#include <asm/system.h> #include <asm/traps.h> #include <asm/desc.h> #include <asm/i387.h> @@ -120,7 +119,7 @@ do_trap(int trapnr, int signr, char *str, struct pt_regs *regs, * traps 0, 1, 3, 4, and 5 should be forwarded to vm86. * On nmi (interrupt 2), do_trap should not be called. */ - if (trapnr < 6) + if (trapnr < X86_TRAP_UD) goto vm86_trap; goto trap_signal; } @@ -133,7 +132,7 @@ do_trap(int trapnr, int signr, char *str, struct pt_regs *regs, trap_signal: #endif /* - * We want error_code and trap_no set for userspace faults and + * We want error_code and trap_nr set for userspace faults and * kernelspace faults which result in die(), but not * kernelspace faults which are fixed up. die() gives the * process no chance to handle the signal and notice the @@ -142,7 +141,7 @@ trap_signal: * delivered, faults. See also do_general_protection below. */ tsk->thread.error_code = error_code; - tsk->thread.trap_no = trapnr; + tsk->thread.trap_nr = trapnr; #ifdef CONFIG_X86_64 if (show_unhandled_signals && unhandled_signal(tsk, signr) && @@ -165,7 +164,7 @@ trap_signal: kernel_trap: if (!fixup_exception(regs)) { tsk->thread.error_code = error_code; - tsk->thread.trap_no = trapnr; + tsk->thread.trap_nr = trapnr; die(str, regs, error_code); } return; @@ -204,27 +203,31 @@ dotraplinkage void do_##name(struct pt_regs *regs, long error_code) \ do_trap(trapnr, signr, str, regs, error_code, &info); \ } -DO_ERROR_INFO(0, SIGFPE, "divide error", divide_error, FPE_INTDIV, regs->ip) -DO_ERROR(4, SIGSEGV, "overflow", overflow) -DO_ERROR(5, SIGSEGV, "bounds", bounds) -DO_ERROR_INFO(6, SIGILL, "invalid opcode", invalid_op, ILL_ILLOPN, regs->ip) -DO_ERROR(9, SIGFPE, "coprocessor segment overrun", coprocessor_segment_overrun) -DO_ERROR(10, SIGSEGV, "invalid TSS", invalid_TSS) -DO_ERROR(11, SIGBUS, "segment not present", segment_not_present) +DO_ERROR_INFO(X86_TRAP_DE, SIGFPE, "divide error", divide_error, FPE_INTDIV, + regs->ip) +DO_ERROR(X86_TRAP_OF, SIGSEGV, "overflow", overflow) +DO_ERROR(X86_TRAP_BR, SIGSEGV, "bounds", bounds) +DO_ERROR_INFO(X86_TRAP_UD, SIGILL, "invalid opcode", invalid_op, ILL_ILLOPN, + regs->ip) +DO_ERROR(X86_TRAP_OLD_MF, SIGFPE, "coprocessor segment overrun", + coprocessor_segment_overrun) +DO_ERROR(X86_TRAP_TS, SIGSEGV, "invalid TSS", invalid_TSS) +DO_ERROR(X86_TRAP_NP, SIGBUS, "segment not present", segment_not_present) #ifdef CONFIG_X86_32 -DO_ERROR(12, SIGBUS, "stack segment", stack_segment) +DO_ERROR(X86_TRAP_SS, SIGBUS, "stack segment", stack_segment) #endif -DO_ERROR_INFO(17, SIGBUS, "alignment check", alignment_check, BUS_ADRALN, 0) +DO_ERROR_INFO(X86_TRAP_AC, SIGBUS, "alignment check", alignment_check, + BUS_ADRALN, 0) #ifdef CONFIG_X86_64 /* Runs on IST stack */ dotraplinkage void do_stack_segment(struct pt_regs *regs, long error_code) { if (notify_die(DIE_TRAP, "stack segment", regs, error_code, - 12, SIGBUS) == NOTIFY_STOP) + X86_TRAP_SS, SIGBUS) == NOTIFY_STOP) return; preempt_conditional_sti(regs); - do_trap(12, SIGBUS, "stack segment", regs, error_code, NULL); + do_trap(X86_TRAP_SS, SIGBUS, "stack segment", regs, error_code, NULL); preempt_conditional_cli(regs); } @@ -234,10 +237,10 @@ dotraplinkage void do_double_fault(struct pt_regs *regs, long error_code) struct task_struct *tsk = current; /* Return not checked because double check cannot be ignored */ - notify_die(DIE_TRAP, str, regs, error_code, 8, SIGSEGV); + notify_die(DIE_TRAP, str, regs, error_code, X86_TRAP_DF, SIGSEGV); tsk->thread.error_code = error_code; - tsk->thread.trap_no = 8; + tsk->thread.trap_nr = X86_TRAP_DF; /* * This is always a kernel trap and never fixable (and thus must @@ -265,7 +268,7 @@ do_general_protection(struct pt_regs *regs, long error_code) goto gp_in_kernel; tsk->thread.error_code = error_code; - tsk->thread.trap_no = 13; + tsk->thread.trap_nr = X86_TRAP_GP; if (show_unhandled_signals && unhandled_signal(tsk, SIGSEGV) && printk_ratelimit()) { @@ -292,9 +295,9 @@ gp_in_kernel: return; tsk->thread.error_code = error_code; - tsk->thread.trap_no = 13; - if (notify_die(DIE_GPF, "general protection fault", regs, - error_code, 13, SIGSEGV) == NOTIFY_STOP) + tsk->thread.trap_nr = X86_TRAP_GP; + if (notify_die(DIE_GPF, "general protection fault", regs, error_code, + X86_TRAP_GP, SIGSEGV) == NOTIFY_STOP) return; die("general protection fault", regs, error_code); } @@ -303,13 +306,13 @@ gp_in_kernel: dotraplinkage void __kprobes do_int3(struct pt_regs *regs, long error_code) { #ifdef CONFIG_KGDB_LOW_LEVEL_TRAP - if (kgdb_ll_trap(DIE_INT3, "int3", regs, error_code, 3, SIGTRAP) - == NOTIFY_STOP) + if (kgdb_ll_trap(DIE_INT3, "int3", regs, error_code, X86_TRAP_BP, + SIGTRAP) == NOTIFY_STOP) return; #endif /* CONFIG_KGDB_LOW_LEVEL_TRAP */ - if (notify_die(DIE_INT3, "int3", regs, error_code, 3, SIGTRAP) - == NOTIFY_STOP) + if (notify_die(DIE_INT3, "int3", regs, error_code, X86_TRAP_BP, + SIGTRAP) == NOTIFY_STOP) return; /* @@ -318,7 +321,7 @@ dotraplinkage void __kprobes do_int3(struct pt_regs *regs, long error_code) */ debug_stack_usage_inc(); preempt_conditional_sti(regs); - do_trap(3, SIGTRAP, "int3", regs, error_code, NULL); + do_trap(X86_TRAP_BP, SIGTRAP, "int3", regs, error_code, NULL); preempt_conditional_cli(regs); debug_stack_usage_dec(); } @@ -423,8 +426,8 @@ dotraplinkage void __kprobes do_debug(struct pt_regs *regs, long error_code) preempt_conditional_sti(regs); if (regs->flags & X86_VM_MASK) { - handle_vm86_trap((struct kernel_vm86_regs *) regs, - error_code, 1); + handle_vm86_trap((struct kernel_vm86_regs *) regs, error_code, + X86_TRAP_DB); preempt_conditional_cli(regs); debug_stack_usage_dec(); return; @@ -461,7 +464,8 @@ void math_error(struct pt_regs *regs, int error_code, int trapnr) struct task_struct *task = current; siginfo_t info; unsigned short err; - char *str = (trapnr == 16) ? "fpu exception" : "simd exception"; + char *str = (trapnr == X86_TRAP_MF) ? "fpu exception" : + "simd exception"; if (notify_die(DIE_TRAP, str, regs, error_code, trapnr, SIGFPE) == NOTIFY_STOP) return; @@ -471,7 +475,7 @@ void math_error(struct pt_regs *regs, int error_code, int trapnr) { if (!fixup_exception(regs)) { task->thread.error_code = error_code; - task->thread.trap_no = trapnr; + task->thread.trap_nr = trapnr; die(str, regs, error_code); } return; @@ -481,12 +485,12 @@ void math_error(struct pt_regs *regs, int error_code, int trapnr) * Save the info for the exception handler and clear the error. */ save_init_fpu(task); - task->thread.trap_no = trapnr; + task->thread.trap_nr = trapnr; task->thread.error_code = error_code; info.si_signo = SIGFPE; info.si_errno = 0; info.si_addr = (void __user *)regs->ip; - if (trapnr == 16) { + if (trapnr == X86_TRAP_MF) { unsigned short cwd, swd; /* * (~cwd & swd) will mask out exceptions that are not set to unmasked @@ -530,10 +534,11 @@ void math_error(struct pt_regs *regs, int error_code, int trapnr) info.si_code = FPE_FLTRES; } else { /* - * If we're using IRQ 13, or supposedly even some trap 16 - * implementations, it's possible we get a spurious trap... + * If we're using IRQ 13, or supposedly even some trap + * X86_TRAP_MF implementations, it's possible + * we get a spurious trap, which is not an error. */ - return; /* Spurious trap, no error */ + return; } force_sig_info(SIGFPE, &info, task); } @@ -544,13 +549,13 @@ dotraplinkage void do_coprocessor_error(struct pt_regs *regs, long error_code) ignore_fpu_irq = 1; #endif - math_error(regs, error_code, 16); + math_error(regs, error_code, X86_TRAP_MF); } dotraplinkage void do_simd_coprocessor_error(struct pt_regs *regs, long error_code) { - math_error(regs, error_code, 19); + math_error(regs, error_code, X86_TRAP_XF); } dotraplinkage void @@ -644,20 +649,21 @@ dotraplinkage void do_iret_error(struct pt_regs *regs, long error_code) info.si_errno = 0; info.si_code = ILL_BADSTK; info.si_addr = NULL; - if (notify_die(DIE_TRAP, "iret exception", - regs, error_code, 32, SIGILL) == NOTIFY_STOP) + if (notify_die(DIE_TRAP, "iret exception", regs, error_code, + X86_TRAP_IRET, SIGILL) == NOTIFY_STOP) return; - do_trap(32, SIGILL, "iret exception", regs, error_code, &info); + do_trap(X86_TRAP_IRET, SIGILL, "iret exception", regs, error_code, + &info); } #endif /* Set of traps needed for early debugging. */ void __init early_trap_init(void) { - set_intr_gate_ist(1, &debug, DEBUG_STACK); + set_intr_gate_ist(X86_TRAP_DB, &debug, DEBUG_STACK); /* int3 can be called from all */ - set_system_intr_gate_ist(3, &int3, DEBUG_STACK); - set_intr_gate(14, &page_fault); + set_system_intr_gate_ist(X86_TRAP_BP, &int3, DEBUG_STACK); + set_intr_gate(X86_TRAP_PF, &page_fault); load_idt(&idt_descr); } @@ -673,30 +679,30 @@ void __init trap_init(void) early_iounmap(p, 4); #endif - set_intr_gate(0, ÷_error); - set_intr_gate_ist(2, &nmi, NMI_STACK); + set_intr_gate(X86_TRAP_DE, ÷_error); + set_intr_gate_ist(X86_TRAP_NMI, &nmi, NMI_STACK); /* int4 can be called from all */ - set_system_intr_gate(4, &overflow); - set_intr_gate(5, &bounds); - set_intr_gate(6, &invalid_op); - set_intr_gate(7, &device_not_available); + set_system_intr_gate(X86_TRAP_OF, &overflow); + set_intr_gate(X86_TRAP_BR, &bounds); + set_intr_gate(X86_TRAP_UD, &invalid_op); + set_intr_gate(X86_TRAP_NM, &device_not_available); #ifdef CONFIG_X86_32 - set_task_gate(8, GDT_ENTRY_DOUBLEFAULT_TSS); + set_task_gate(X86_TRAP_DF, GDT_ENTRY_DOUBLEFAULT_TSS); #else - set_intr_gate_ist(8, &double_fault, DOUBLEFAULT_STACK); + set_intr_gate_ist(X86_TRAP_DF, &double_fault, DOUBLEFAULT_STACK); #endif - set_intr_gate(9, &coprocessor_segment_overrun); - set_intr_gate(10, &invalid_TSS); - set_intr_gate(11, &segment_not_present); - set_intr_gate_ist(12, &stack_segment, STACKFAULT_STACK); - set_intr_gate(13, &general_protection); - set_intr_gate(15, &spurious_interrupt_bug); - set_intr_gate(16, &coprocessor_error); - set_intr_gate(17, &alignment_check); + set_intr_gate(X86_TRAP_OLD_MF, &coprocessor_segment_overrun); + set_intr_gate(X86_TRAP_TS, &invalid_TSS); + set_intr_gate(X86_TRAP_NP, &segment_not_present); + set_intr_gate_ist(X86_TRAP_SS, &stack_segment, STACKFAULT_STACK); + set_intr_gate(X86_TRAP_GP, &general_protection); + set_intr_gate(X86_TRAP_SPURIOUS, &spurious_interrupt_bug); + set_intr_gate(X86_TRAP_MF, &coprocessor_error); + set_intr_gate(X86_TRAP_AC, &alignment_check); #ifdef CONFIG_X86_MCE - set_intr_gate_ist(18, &machine_check, MCE_STACK); + set_intr_gate_ist(X86_TRAP_MC, &machine_check, MCE_STACK); #endif - set_intr_gate(19, &simd_coprocessor_error); + set_intr_gate(X86_TRAP_XF, &simd_coprocessor_error); /* Reserve all the builtin and the syscall vector: */ for (i = 0; i < FIRST_EXTERNAL_VECTOR; i++) @@ -721,7 +727,7 @@ void __init trap_init(void) #ifdef CONFIG_X86_64 memcpy(&nmi_idt_table, &idt_table, IDT_ENTRIES * 16); - set_nmi_gate(1, &debug); - set_nmi_gate(3, &int3); + set_nmi_gate(X86_TRAP_DB, &debug); + set_nmi_gate(X86_TRAP_BP, &int3); #endif } diff --git a/arch/x86/kernel/tsc.c b/arch/x86/kernel/tsc.c index 183c5925a9fe..fc0a147e3727 100644 --- a/arch/x86/kernel/tsc.c +++ b/arch/x86/kernel/tsc.c @@ -630,7 +630,7 @@ static void set_cyc2ns_scale(unsigned long cpu_khz, int cpu) static unsigned long long cyc2ns_suspend; -void save_sched_clock_state(void) +void tsc_save_sched_clock_state(void) { if (!sched_clock_stable) return; @@ -646,7 +646,7 @@ void save_sched_clock_state(void) * that sched_clock() continues from the point where it was left off during * suspend. */ -void restore_sched_clock_state(void) +void tsc_restore_sched_clock_state(void) { unsigned long long offset; unsigned long flags; @@ -933,6 +933,16 @@ static int __init init_tsc_clocksource(void) clocksource_tsc.rating = 0; clocksource_tsc.flags &= ~CLOCK_SOURCE_IS_CONTINUOUS; } + + /* + * Trust the results of the earlier calibration on systems + * exporting a reliable TSC. + */ + if (boot_cpu_has(X86_FEATURE_TSC_RELIABLE)) { + clocksource_register_khz(&clocksource_tsc, tsc_khz); + return 0; + } + schedule_delayed_work(&tsc_irqwork, 0); return 0; } diff --git a/arch/x86/kernel/vm86_32.c b/arch/x86/kernel/vm86_32.c index 328cb37bb827..255f58ae71e8 100644 --- a/arch/x86/kernel/vm86_32.c +++ b/arch/x86/kernel/vm86_32.c @@ -569,7 +569,7 @@ int handle_vm86_trap(struct kernel_vm86_regs *regs, long error_code, int trapno) } if (trapno != 1) return 1; /* we let this handle by the calling routine */ - current->thread.trap_no = trapno; + current->thread.trap_nr = trapno; current->thread.error_code = error_code; force_sig(SIGTRAP, current); return 0; diff --git a/arch/x86/kernel/vsyscall_64.c b/arch/x86/kernel/vsyscall_64.c index b07ba9393564..f386dc49f988 100644 --- a/arch/x86/kernel/vsyscall_64.c +++ b/arch/x86/kernel/vsyscall_64.c @@ -52,10 +52,7 @@ #include "vsyscall_trace.h" DEFINE_VVAR(int, vgetcpu_mode); -DEFINE_VVAR(struct vsyscall_gtod_data, vsyscall_gtod_data) = -{ - .lock = __SEQLOCK_UNLOCKED(__vsyscall_gtod_data.lock), -}; +DEFINE_VVAR(struct vsyscall_gtod_data, vsyscall_gtod_data); static enum { EMULATE, NATIVE, NONE } vsyscall_mode = EMULATE; @@ -80,20 +77,15 @@ early_param("vsyscall", vsyscall_setup); void update_vsyscall_tz(void) { - unsigned long flags; - - write_seqlock_irqsave(&vsyscall_gtod_data.lock, flags); - /* sys_tz has changed */ vsyscall_gtod_data.sys_tz = sys_tz; - write_sequnlock_irqrestore(&vsyscall_gtod_data.lock, flags); } void update_vsyscall(struct timespec *wall_time, struct timespec *wtm, struct clocksource *clock, u32 mult) { - unsigned long flags; + struct timespec monotonic; - write_seqlock_irqsave(&vsyscall_gtod_data.lock, flags); + write_seqcount_begin(&vsyscall_gtod_data.seq); /* copy vsyscall data */ vsyscall_gtod_data.clock.vclock_mode = clock->archdata.vclock_mode; @@ -101,12 +93,19 @@ void update_vsyscall(struct timespec *wall_time, struct timespec *wtm, vsyscall_gtod_data.clock.mask = clock->mask; vsyscall_gtod_data.clock.mult = mult; 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 = *wtm; + + monotonic = timespec_add(*wall_time, *wtm); + vsyscall_gtod_data.monotonic_time_sec = monotonic.tv_sec; + vsyscall_gtod_data.monotonic_time_nsec = monotonic.tv_nsec; + vsyscall_gtod_data.wall_time_coarse = __current_kernel_time(); + vsyscall_gtod_data.monotonic_time_coarse = + timespec_add(vsyscall_gtod_data.wall_time_coarse, *wtm); - write_sequnlock_irqrestore(&vsyscall_gtod_data.lock, flags); + write_seqcount_end(&vsyscall_gtod_data.seq); } static void warn_bad_vsyscall(const char *level, struct pt_regs *regs, @@ -153,7 +152,7 @@ static bool write_ok_or_segv(unsigned long ptr, size_t size) thread->error_code = 6; /* user fault, no page, write */ thread->cr2 = ptr; - thread->trap_no = 14; + thread->trap_nr = X86_TRAP_PF; memset(&info, 0, sizeof(info)); info.si_signo = SIGSEGV; diff --git a/arch/x86/kernel/x86_init.c b/arch/x86/kernel/x86_init.c index 947a06ccc673..e9f265fd79ae 100644 --- a/arch/x86/kernel/x86_init.c +++ b/arch/x86/kernel/x86_init.c @@ -91,6 +91,7 @@ struct x86_init_ops x86_init __initdata = { }; struct x86_cpuinit_ops x86_cpuinit __cpuinitdata = { + .early_percpu_clock_init = x86_init_noop, .setup_percpu_clockev = setup_secondary_APIC_clock, .fixup_cpu_id = x86_default_fixup_cpu_id, }; @@ -107,7 +108,9 @@ struct x86_platform_ops x86_platform = { .is_untracked_pat_range = is_ISA_range, .nmi_init = default_nmi_init, .get_nmi_reason = default_get_nmi_reason, - .i8042_detect = default_i8042_detect + .i8042_detect = default_i8042_detect, + .save_sched_clock_state = tsc_save_sched_clock_state, + .restore_sched_clock_state = tsc_restore_sched_clock_state, }; EXPORT_SYMBOL_GPL(x86_platform); diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c index 89b02bfaaca5..9fed5bedaad6 100644 --- a/arch/x86/kvm/cpuid.c +++ b/arch/x86/kvm/cpuid.c @@ -236,7 +236,7 @@ static int do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function, const u32 kvm_supported_word6_x86_features = F(LAHF_LM) | F(CMP_LEGACY) | 0 /*SVM*/ | 0 /* ExtApicSpace */ | F(CR8_LEGACY) | F(ABM) | F(SSE4A) | F(MISALIGNSSE) | - F(3DNOWPREFETCH) | 0 /* OSVW */ | 0 /* IBS */ | F(XOP) | + F(3DNOWPREFETCH) | F(OSVW) | 0 /* IBS */ | F(XOP) | 0 /* SKINIT, WDT, LWP */ | F(FMA4) | F(TBM); /* cpuid 0xC0000001.edx */ diff --git a/arch/x86/kvm/cpuid.h b/arch/x86/kvm/cpuid.h index 5b97e1797a6d..26d1fb437eb5 100644 --- a/arch/x86/kvm/cpuid.h +++ b/arch/x86/kvm/cpuid.h @@ -43,4 +43,12 @@ static inline bool guest_cpuid_has_fsgsbase(struct kvm_vcpu *vcpu) return best && (best->ebx & bit(X86_FEATURE_FSGSBASE)); } +static inline bool guest_cpuid_has_osvw(struct kvm_vcpu *vcpu) +{ + struct kvm_cpuid_entry2 *best; + + best = kvm_find_cpuid_entry(vcpu, 0x80000001, 0); + return best && (best->ecx & bit(X86_FEATURE_OSVW)); +} + #endif diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c index 0982507b962a..83756223f8aa 100644 --- a/arch/x86/kvm/emulate.c +++ b/arch/x86/kvm/emulate.c @@ -57,6 +57,7 @@ #define OpDS 23ull /* DS */ #define OpFS 24ull /* FS */ #define OpGS 25ull /* GS */ +#define OpMem8 26ull /* 8-bit zero extended memory operand */ #define OpBits 5 /* Width of operand field */ #define OpMask ((1ull << OpBits) - 1) @@ -101,6 +102,7 @@ #define SrcAcc (OpAcc << SrcShift) #define SrcImmU16 (OpImmU16 << SrcShift) #define SrcDX (OpDX << SrcShift) +#define SrcMem8 (OpMem8 << SrcShift) #define SrcMask (OpMask << SrcShift) #define BitOp (1<<11) #define MemAbs (1<<12) /* Memory operand is absolute displacement */ @@ -858,8 +860,7 @@ static void write_sse_reg(struct x86_emulate_ctxt *ctxt, sse128_t *data, } static void decode_register_operand(struct x86_emulate_ctxt *ctxt, - struct operand *op, - int inhibit_bytereg) + struct operand *op) { unsigned reg = ctxt->modrm_reg; int highbyte_regs = ctxt->rex_prefix == 0; @@ -876,7 +877,7 @@ static void decode_register_operand(struct x86_emulate_ctxt *ctxt, } op->type = OP_REG; - if ((ctxt->d & ByteOp) && !inhibit_bytereg) { + if (ctxt->d & ByteOp) { op->addr.reg = decode_register(reg, ctxt->regs, highbyte_regs); op->bytes = 1; } else { @@ -1151,6 +1152,22 @@ static int pio_in_emulated(struct x86_emulate_ctxt *ctxt, return 1; } +static int read_interrupt_descriptor(struct x86_emulate_ctxt *ctxt, + u16 index, struct desc_struct *desc) +{ + struct desc_ptr dt; + ulong addr; + + ctxt->ops->get_idt(ctxt, &dt); + + if (dt.size < index * 8 + 7) + return emulate_gp(ctxt, index << 3 | 0x2); + + addr = dt.address + index * 8; + return ctxt->ops->read_std(ctxt, addr, desc, sizeof *desc, + &ctxt->exception); +} + static void get_descriptor_table_ptr(struct x86_emulate_ctxt *ctxt, u16 selector, struct desc_ptr *dt) { @@ -1227,6 +1244,8 @@ static int load_segment_descriptor(struct x86_emulate_ctxt *ctxt, seg_desc.type = 3; seg_desc.p = 1; seg_desc.s = 1; + if (ctxt->mode == X86EMUL_MODE_VM86) + seg_desc.dpl = 3; goto load; } @@ -1891,6 +1910,17 @@ setup_syscalls_segments(struct x86_emulate_ctxt *ctxt, ss->p = 1; } +static bool vendor_intel(struct x86_emulate_ctxt *ctxt) +{ + u32 eax, ebx, ecx, edx; + + eax = ecx = 0; + return ctxt->ops->get_cpuid(ctxt, &eax, &ebx, &ecx, &edx) + && ebx == X86EMUL_CPUID_VENDOR_GenuineIntel_ebx + && ecx == X86EMUL_CPUID_VENDOR_GenuineIntel_ecx + && edx == X86EMUL_CPUID_VENDOR_GenuineIntel_edx; +} + static bool em_syscall_is_enabled(struct x86_emulate_ctxt *ctxt) { struct x86_emulate_ops *ops = ctxt->ops; @@ -2007,6 +2037,14 @@ static int em_sysenter(struct x86_emulate_ctxt *ctxt) if (ctxt->mode == X86EMUL_MODE_REAL) return emulate_gp(ctxt, 0); + /* + * Not recognized on AMD in compat mode (but is recognized in legacy + * mode). + */ + if ((ctxt->mode == X86EMUL_MODE_PROT32) && (efer & EFER_LMA) + && !vendor_intel(ctxt)) + return emulate_ud(ctxt); + /* XXX sysenter/sysexit have not been tested in 64bit mode. * Therefore, we inject an #UD. */ @@ -2306,6 +2344,8 @@ static int load_state_from_tss32(struct x86_emulate_ctxt *ctxt, return emulate_gp(ctxt, 0); ctxt->_eip = tss->eip; ctxt->eflags = tss->eflags | 2; + + /* General purpose registers */ ctxt->regs[VCPU_REGS_RAX] = tss->eax; ctxt->regs[VCPU_REGS_RCX] = tss->ecx; ctxt->regs[VCPU_REGS_RDX] = tss->edx; @@ -2328,6 +2368,24 @@ static int load_state_from_tss32(struct x86_emulate_ctxt *ctxt, set_segment_selector(ctxt, tss->gs, VCPU_SREG_GS); /* + * If we're switching between Protected Mode and VM86, we need to make + * sure to update the mode before loading the segment descriptors so + * that the selectors are interpreted correctly. + * + * Need to get rflags to the vcpu struct immediately because it + * influences the CPL which is checked at least when loading the segment + * descriptors and when pushing an error code to the new kernel stack. + * + * TODO Introduce a separate ctxt->ops->set_cpl callback + */ + if (ctxt->eflags & X86_EFLAGS_VM) + ctxt->mode = X86EMUL_MODE_VM86; + else + ctxt->mode = X86EMUL_MODE_PROT32; + + ctxt->ops->set_rflags(ctxt, ctxt->eflags); + + /* * Now load segment descriptors. If fault happenes at this stage * it is handled in a context of new task */ @@ -2401,7 +2459,7 @@ static int task_switch_32(struct x86_emulate_ctxt *ctxt, } static int emulator_do_task_switch(struct x86_emulate_ctxt *ctxt, - u16 tss_selector, int reason, + u16 tss_selector, int idt_index, int reason, bool has_error_code, u32 error_code) { struct x86_emulate_ops *ops = ctxt->ops; @@ -2423,12 +2481,35 @@ static int emulator_do_task_switch(struct x86_emulate_ctxt *ctxt, /* FIXME: check that next_tss_desc is tss */ - if (reason != TASK_SWITCH_IRET) { - if ((tss_selector & 3) > next_tss_desc.dpl || - ops->cpl(ctxt) > next_tss_desc.dpl) - return emulate_gp(ctxt, 0); + /* + * Check privileges. The three cases are task switch caused by... + * + * 1. jmp/call/int to task gate: Check against DPL of the task gate + * 2. Exception/IRQ/iret: No check is performed + * 3. jmp/call to TSS: Check agains DPL of the TSS + */ + if (reason == TASK_SWITCH_GATE) { + if (idt_index != -1) { + /* Software interrupts */ + struct desc_struct task_gate_desc; + int dpl; + + ret = read_interrupt_descriptor(ctxt, idt_index, + &task_gate_desc); + if (ret != X86EMUL_CONTINUE) + return ret; + + dpl = task_gate_desc.dpl; + if ((tss_selector & 3) > dpl || ops->cpl(ctxt) > dpl) + return emulate_gp(ctxt, (idt_index << 3) | 0x2); + } + } else if (reason != TASK_SWITCH_IRET) { + int dpl = next_tss_desc.dpl; + if ((tss_selector & 3) > dpl || ops->cpl(ctxt) > dpl) + return emulate_gp(ctxt, tss_selector); } + desc_limit = desc_limit_scaled(&next_tss_desc); if (!next_tss_desc.p || ((desc_limit < 0x67 && (next_tss_desc.type & 8)) || @@ -2481,7 +2562,7 @@ static int emulator_do_task_switch(struct x86_emulate_ctxt *ctxt, } int emulator_task_switch(struct x86_emulate_ctxt *ctxt, - u16 tss_selector, int reason, + u16 tss_selector, int idt_index, int reason, bool has_error_code, u32 error_code) { int rc; @@ -2489,7 +2570,7 @@ int emulator_task_switch(struct x86_emulate_ctxt *ctxt, ctxt->_eip = ctxt->eip; ctxt->dst.type = OP_NONE; - rc = emulator_do_task_switch(ctxt, tss_selector, reason, + rc = emulator_do_task_switch(ctxt, tss_selector, idt_index, reason, has_error_code, error_code); if (rc == X86EMUL_CONTINUE) @@ -3514,13 +3595,13 @@ static struct opcode twobyte_table[256] = { I(DstMem | SrcReg | ModRM | BitOp | Lock, em_btr), I(DstReg | SrcMemFAddr | ModRM | Src2FS, em_lseg), I(DstReg | SrcMemFAddr | ModRM | Src2GS, em_lseg), - D(ByteOp | DstReg | SrcMem | ModRM | Mov), D(DstReg | SrcMem16 | ModRM | Mov), + D(DstReg | SrcMem8 | ModRM | Mov), D(DstReg | SrcMem16 | ModRM | Mov), /* 0xB8 - 0xBF */ N, N, G(BitOp, group8), I(DstMem | SrcReg | ModRM | BitOp | Lock | PageTable, em_btc), I(DstReg | SrcMem | ModRM, em_bsf), I(DstReg | SrcMem | ModRM, em_bsr), - D(ByteOp | DstReg | SrcMem | ModRM | Mov), D(DstReg | SrcMem16 | ModRM | Mov), + D(DstReg | SrcMem8 | ModRM | Mov), D(DstReg | SrcMem16 | ModRM | Mov), /* 0xC0 - 0xCF */ D2bv(DstMem | SrcReg | ModRM | Lock), N, D(DstMem | SrcReg | ModRM | Mov), @@ -3602,9 +3683,7 @@ static int decode_operand(struct x86_emulate_ctxt *ctxt, struct operand *op, switch (d) { case OpReg: - decode_register_operand(ctxt, op, - op == &ctxt->dst && - ctxt->twobyte && (ctxt->b == 0xb6 || ctxt->b == 0xb7)); + decode_register_operand(ctxt, op); break; case OpImmUByte: rc = decode_imm(ctxt, op, 1, false); @@ -3656,6 +3735,9 @@ static int decode_operand(struct x86_emulate_ctxt *ctxt, struct operand *op, case OpImm: rc = decode_imm(ctxt, op, imm_size(ctxt), true); break; + case OpMem8: + ctxt->memop.bytes = 1; + goto mem_common; case OpMem16: ctxt->memop.bytes = 2; goto mem_common; diff --git a/arch/x86/kvm/i8259.c b/arch/x86/kvm/i8259.c index b6a73537e1ef..81cf4fa4a2be 100644 --- a/arch/x86/kvm/i8259.c +++ b/arch/x86/kvm/i8259.c @@ -307,6 +307,7 @@ static void pic_ioport_write(void *opaque, u32 addr, u32 val) if (val & 0x10) { s->init4 = val & 1; s->last_irr = 0; + s->irr &= s->elcr; s->imr = 0; s->priority_add = 0; s->special_mask = 0; diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c index 31bfc6927bc0..858432287ab6 100644 --- a/arch/x86/kvm/lapic.c +++ b/arch/x86/kvm/lapic.c @@ -433,7 +433,7 @@ static int __apic_accept_irq(struct kvm_lapic *apic, int delivery_mode, break; case APIC_DM_INIT: - if (level) { + if (!trig_mode || level) { result = 1; vcpu->arch.mp_state = KVM_MP_STATE_INIT_RECEIVED; kvm_make_request(KVM_REQ_EVENT, vcpu); @@ -731,7 +731,7 @@ static void start_apic_timer(struct kvm_lapic *apic) u64 guest_tsc, tscdeadline = apic->lapic_timer.tscdeadline; u64 ns = 0; struct kvm_vcpu *vcpu = apic->vcpu; - unsigned long this_tsc_khz = vcpu_tsc_khz(vcpu); + unsigned long this_tsc_khz = vcpu->arch.virtual_tsc_khz; unsigned long flags; if (unlikely(!tscdeadline || !this_tsc_khz)) diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c index 224b02c3cda9..4cb164268846 100644 --- a/arch/x86/kvm/mmu.c +++ b/arch/x86/kvm/mmu.c @@ -688,9 +688,8 @@ static struct kvm_lpage_info *lpage_info_slot(gfn_t gfn, { unsigned long idx; - idx = (gfn >> KVM_HPAGE_GFN_SHIFT(level)) - - (slot->base_gfn >> KVM_HPAGE_GFN_SHIFT(level)); - return &slot->lpage_info[level - 2][idx]; + idx = gfn_to_index(gfn, slot->base_gfn, level); + return &slot->arch.lpage_info[level - 2][idx]; } static void account_shadowed(struct kvm *kvm, gfn_t gfn) @@ -946,7 +945,7 @@ static void pte_list_walk(unsigned long *pte_list, pte_list_walk_fn fn) } } -static unsigned long *__gfn_to_rmap(struct kvm *kvm, gfn_t gfn, int level, +static unsigned long *__gfn_to_rmap(gfn_t gfn, int level, struct kvm_memory_slot *slot) { struct kvm_lpage_info *linfo; @@ -966,7 +965,7 @@ static unsigned long *gfn_to_rmap(struct kvm *kvm, gfn_t gfn, int level) struct kvm_memory_slot *slot; slot = gfn_to_memslot(kvm, gfn); - return __gfn_to_rmap(kvm, gfn, level, slot); + return __gfn_to_rmap(gfn, level, slot); } static bool rmap_can_add(struct kvm_vcpu *vcpu) @@ -988,7 +987,7 @@ static int rmap_add(struct kvm_vcpu *vcpu, u64 *spte, gfn_t gfn) return pte_list_add(vcpu, spte, rmapp); } -static u64 *rmap_next(struct kvm *kvm, unsigned long *rmapp, u64 *spte) +static u64 *rmap_next(unsigned long *rmapp, u64 *spte) { return pte_list_next(rmapp, spte); } @@ -1018,8 +1017,8 @@ int kvm_mmu_rmap_write_protect(struct kvm *kvm, u64 gfn, u64 *spte; int i, write_protected = 0; - rmapp = __gfn_to_rmap(kvm, gfn, PT_PAGE_TABLE_LEVEL, slot); - spte = rmap_next(kvm, rmapp, NULL); + rmapp = __gfn_to_rmap(gfn, PT_PAGE_TABLE_LEVEL, slot); + spte = rmap_next(rmapp, NULL); while (spte) { BUG_ON(!(*spte & PT_PRESENT_MASK)); rmap_printk("rmap_write_protect: spte %p %llx\n", spte, *spte); @@ -1027,14 +1026,14 @@ int kvm_mmu_rmap_write_protect(struct kvm *kvm, u64 gfn, mmu_spte_update(spte, *spte & ~PT_WRITABLE_MASK); write_protected = 1; } - spte = rmap_next(kvm, rmapp, spte); + spte = rmap_next(rmapp, spte); } /* check for huge page mappings */ for (i = PT_DIRECTORY_LEVEL; i < PT_PAGE_TABLE_LEVEL + KVM_NR_PAGE_SIZES; ++i) { - rmapp = __gfn_to_rmap(kvm, gfn, i, slot); - spte = rmap_next(kvm, rmapp, NULL); + rmapp = __gfn_to_rmap(gfn, i, slot); + spte = rmap_next(rmapp, NULL); while (spte) { BUG_ON(!(*spte & PT_PRESENT_MASK)); BUG_ON(!is_large_pte(*spte)); @@ -1045,7 +1044,7 @@ int kvm_mmu_rmap_write_protect(struct kvm *kvm, u64 gfn, spte = NULL; write_protected = 1; } - spte = rmap_next(kvm, rmapp, spte); + spte = rmap_next(rmapp, spte); } } @@ -1066,7 +1065,7 @@ static int kvm_unmap_rmapp(struct kvm *kvm, unsigned long *rmapp, u64 *spte; int need_tlb_flush = 0; - while ((spte = rmap_next(kvm, rmapp, NULL))) { + while ((spte = rmap_next(rmapp, NULL))) { BUG_ON(!(*spte & PT_PRESENT_MASK)); rmap_printk("kvm_rmap_unmap_hva: spte %p %llx\n", spte, *spte); drop_spte(kvm, spte); @@ -1085,14 +1084,14 @@ static int kvm_set_pte_rmapp(struct kvm *kvm, unsigned long *rmapp, WARN_ON(pte_huge(*ptep)); new_pfn = pte_pfn(*ptep); - spte = rmap_next(kvm, rmapp, NULL); + spte = rmap_next(rmapp, NULL); while (spte) { BUG_ON(!is_shadow_present_pte(*spte)); rmap_printk("kvm_set_pte_rmapp: spte %p %llx\n", spte, *spte); need_flush = 1; if (pte_write(*ptep)) { drop_spte(kvm, spte); - spte = rmap_next(kvm, rmapp, NULL); + spte = rmap_next(rmapp, NULL); } else { new_spte = *spte &~ (PT64_BASE_ADDR_MASK); new_spte |= (u64)new_pfn << PAGE_SHIFT; @@ -1102,7 +1101,7 @@ static int kvm_set_pte_rmapp(struct kvm *kvm, unsigned long *rmapp, new_spte &= ~shadow_accessed_mask; mmu_spte_clear_track_bits(spte); mmu_spte_set(spte, new_spte); - spte = rmap_next(kvm, rmapp, spte); + spte = rmap_next(rmapp, spte); } } if (need_flush) @@ -1176,7 +1175,7 @@ static int kvm_age_rmapp(struct kvm *kvm, unsigned long *rmapp, if (!shadow_accessed_mask) return kvm_unmap_rmapp(kvm, rmapp, data); - spte = rmap_next(kvm, rmapp, NULL); + spte = rmap_next(rmapp, NULL); while (spte) { int _young; u64 _spte = *spte; @@ -1186,7 +1185,7 @@ static int kvm_age_rmapp(struct kvm *kvm, unsigned long *rmapp, young = 1; clear_bit(PT_ACCESSED_SHIFT, (unsigned long *)spte); } - spte = rmap_next(kvm, rmapp, spte); + spte = rmap_next(rmapp, spte); } return young; } @@ -1205,7 +1204,7 @@ static int kvm_test_age_rmapp(struct kvm *kvm, unsigned long *rmapp, if (!shadow_accessed_mask) goto out; - spte = rmap_next(kvm, rmapp, NULL); + spte = rmap_next(rmapp, NULL); while (spte) { u64 _spte = *spte; BUG_ON(!(_spte & PT_PRESENT_MASK)); @@ -1214,7 +1213,7 @@ static int kvm_test_age_rmapp(struct kvm *kvm, unsigned long *rmapp, young = 1; break; } - spte = rmap_next(kvm, rmapp, spte); + spte = rmap_next(rmapp, spte); } out: return young; @@ -1391,11 +1390,6 @@ struct kvm_mmu_pages { unsigned int nr; }; -#define for_each_unsync_children(bitmap, idx) \ - for (idx = find_first_bit(bitmap, 512); \ - idx < 512; \ - idx = find_next_bit(bitmap, 512, idx+1)) - static int mmu_pages_add(struct kvm_mmu_pages *pvec, struct kvm_mmu_page *sp, int idx) { @@ -1417,7 +1411,7 @@ 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) { + for_each_set_bit(i, sp->unsync_child_bitmap, 512) { struct kvm_mmu_page *child; u64 ent = sp->spt[i]; @@ -1803,6 +1797,7 @@ static void drop_large_spte(struct kvm_vcpu *vcpu, u64 *sptep) { if (is_large_pte(*sptep)) { drop_spte(vcpu->kvm, sptep); + --vcpu->kvm->stat.lpages; kvm_flush_remote_tlbs(vcpu->kvm); } } @@ -3190,15 +3185,14 @@ static bool sync_mmio_spte(u64 *sptep, gfn_t gfn, unsigned access, #undef PTTYPE static void reset_rsvds_bits_mask(struct kvm_vcpu *vcpu, - struct kvm_mmu *context, - int level) + struct kvm_mmu *context) { int maxphyaddr = cpuid_maxphyaddr(vcpu); u64 exb_bit_rsvd = 0; if (!context->nx) exb_bit_rsvd = rsvd_bits(63, 63); - switch (level) { + switch (context->root_level) { case PT32_ROOT_LEVEL: /* no rsvd bits for 2 level 4K page table entries */ context->rsvd_bits_mask[0][1] = 0; @@ -3256,8 +3250,9 @@ static int paging64_init_context_common(struct kvm_vcpu *vcpu, int level) { context->nx = is_nx(vcpu); + context->root_level = level; - reset_rsvds_bits_mask(vcpu, context, level); + reset_rsvds_bits_mask(vcpu, context); ASSERT(is_pae(vcpu)); context->new_cr3 = paging_new_cr3; @@ -3267,7 +3262,6 @@ static int paging64_init_context_common(struct kvm_vcpu *vcpu, context->invlpg = paging64_invlpg; context->update_pte = paging64_update_pte; context->free = paging_free; - context->root_level = level; context->shadow_root_level = level; context->root_hpa = INVALID_PAGE; context->direct_map = false; @@ -3284,8 +3278,9 @@ static int paging32_init_context(struct kvm_vcpu *vcpu, struct kvm_mmu *context) { context->nx = false; + context->root_level = PT32_ROOT_LEVEL; - reset_rsvds_bits_mask(vcpu, context, PT32_ROOT_LEVEL); + reset_rsvds_bits_mask(vcpu, context); context->new_cr3 = paging_new_cr3; context->page_fault = paging32_page_fault; @@ -3294,7 +3289,6 @@ static int paging32_init_context(struct kvm_vcpu *vcpu, context->sync_page = paging32_sync_page; context->invlpg = paging32_invlpg; context->update_pte = paging32_update_pte; - context->root_level = PT32_ROOT_LEVEL; context->shadow_root_level = PT32E_ROOT_LEVEL; context->root_hpa = INVALID_PAGE; context->direct_map = false; @@ -3325,7 +3319,6 @@ static int init_kvm_tdp_mmu(struct kvm_vcpu *vcpu) context->get_cr3 = get_cr3; context->get_pdptr = kvm_pdptr_read; context->inject_page_fault = kvm_inject_page_fault; - context->nx = is_nx(vcpu); if (!is_paging(vcpu)) { context->nx = false; @@ -3333,19 +3326,19 @@ static int init_kvm_tdp_mmu(struct kvm_vcpu *vcpu) context->root_level = 0; } else if (is_long_mode(vcpu)) { context->nx = is_nx(vcpu); - reset_rsvds_bits_mask(vcpu, context, PT64_ROOT_LEVEL); - context->gva_to_gpa = paging64_gva_to_gpa; context->root_level = PT64_ROOT_LEVEL; + reset_rsvds_bits_mask(vcpu, context); + context->gva_to_gpa = paging64_gva_to_gpa; } else if (is_pae(vcpu)) { context->nx = is_nx(vcpu); - reset_rsvds_bits_mask(vcpu, context, PT32E_ROOT_LEVEL); - context->gva_to_gpa = paging64_gva_to_gpa; context->root_level = PT32E_ROOT_LEVEL; + reset_rsvds_bits_mask(vcpu, context); + context->gva_to_gpa = paging64_gva_to_gpa; } else { context->nx = false; - reset_rsvds_bits_mask(vcpu, context, PT32_ROOT_LEVEL); - context->gva_to_gpa = paging32_gva_to_gpa; context->root_level = PT32_ROOT_LEVEL; + reset_rsvds_bits_mask(vcpu, context); + context->gva_to_gpa = paging32_gva_to_gpa; } return 0; @@ -3408,18 +3401,18 @@ static int init_kvm_nested_mmu(struct kvm_vcpu *vcpu) g_context->gva_to_gpa = nonpaging_gva_to_gpa_nested; } else if (is_long_mode(vcpu)) { g_context->nx = is_nx(vcpu); - reset_rsvds_bits_mask(vcpu, g_context, PT64_ROOT_LEVEL); g_context->root_level = PT64_ROOT_LEVEL; + reset_rsvds_bits_mask(vcpu, g_context); g_context->gva_to_gpa = paging64_gva_to_gpa_nested; } else if (is_pae(vcpu)) { g_context->nx = is_nx(vcpu); - reset_rsvds_bits_mask(vcpu, g_context, PT32E_ROOT_LEVEL); g_context->root_level = PT32E_ROOT_LEVEL; + reset_rsvds_bits_mask(vcpu, g_context); g_context->gva_to_gpa = paging64_gva_to_gpa_nested; } else { g_context->nx = false; - reset_rsvds_bits_mask(vcpu, g_context, PT32_ROOT_LEVEL); g_context->root_level = PT32_ROOT_LEVEL; + reset_rsvds_bits_mask(vcpu, g_context); g_context->gva_to_gpa = paging32_gva_to_gpa_nested; } @@ -3555,7 +3548,7 @@ static u64 mmu_pte_write_fetch_gpte(struct kvm_vcpu *vcpu, gpa_t *gpa, * If we're seeing too many writes to a page, it may no longer be a page table, * or we may be forking, in which case it is better to unmap the page. */ -static bool detect_write_flooding(struct kvm_mmu_page *sp, u64 *spte) +static bool detect_write_flooding(struct kvm_mmu_page *sp) { /* * Skip write-flooding detected for the sp whose level is 1, because @@ -3664,10 +3657,8 @@ void kvm_mmu_pte_write(struct kvm_vcpu *vcpu, gpa_t gpa, mask.cr0_wp = mask.cr4_pae = mask.nxe = 1; for_each_gfn_indirect_valid_sp(vcpu->kvm, sp, gfn, node) { - spte = get_written_sptes(sp, gpa, &npte); - if (detect_write_misaligned(sp, gpa, bytes) || - detect_write_flooding(sp, spte)) { + detect_write_flooding(sp)) { zap_page |= !!kvm_mmu_prepare_zap_page(vcpu->kvm, sp, &invalid_list); ++vcpu->kvm->stat.mmu_flooded; diff --git a/arch/x86/kvm/mmu_audit.c b/arch/x86/kvm/mmu_audit.c index ea7b4fd34676..715da5a19a5b 100644 --- a/arch/x86/kvm/mmu_audit.c +++ b/arch/x86/kvm/mmu_audit.c @@ -200,13 +200,13 @@ static void audit_write_protection(struct kvm *kvm, struct kvm_mmu_page *sp) slot = gfn_to_memslot(kvm, sp->gfn); rmapp = &slot->rmap[sp->gfn - slot->base_gfn]; - spte = rmap_next(kvm, rmapp, NULL); + spte = rmap_next(rmapp, NULL); while (spte) { if (is_writable_pte(*spte)) audit_printk(kvm, "shadow page has writable " "mappings: gfn %llx role %x\n", sp->gfn, sp->role.word); - spte = rmap_next(kvm, rmapp, spte); + spte = rmap_next(rmapp, spte); } } diff --git a/arch/x86/kvm/pmu.c b/arch/x86/kvm/pmu.c index 7aad5446f393..a73f0c104813 100644 --- a/arch/x86/kvm/pmu.c +++ b/arch/x86/kvm/pmu.c @@ -33,10 +33,11 @@ static struct kvm_arch_event_perf_mapping { [4] = { 0x2e, 0x41, PERF_COUNT_HW_CACHE_MISSES }, [5] = { 0xc4, 0x00, PERF_COUNT_HW_BRANCH_INSTRUCTIONS }, [6] = { 0xc5, 0x00, PERF_COUNT_HW_BRANCH_MISSES }, + [7] = { 0x00, 0x30, PERF_COUNT_HW_REF_CPU_CYCLES }, }; /* mapping between fixed pmc index and arch_events array */ -int fixed_pmc_events[] = {1, 0, 2}; +int fixed_pmc_events[] = {1, 0, 7}; static bool pmc_is_gp(struct kvm_pmc *pmc) { @@ -210,6 +211,9 @@ static void reprogram_gp_counter(struct kvm_pmc *pmc, u64 eventsel) unsigned config, type = PERF_TYPE_RAW; u8 event_select, unit_mask; + if (eventsel & ARCH_PERFMON_EVENTSEL_PIN_CONTROL) + printk_once("kvm pmu: pin control bit is ignored\n"); + pmc->eventsel = eventsel; stop_counter(pmc); @@ -220,7 +224,7 @@ static void reprogram_gp_counter(struct kvm_pmc *pmc, u64 eventsel) event_select = eventsel & ARCH_PERFMON_EVENTSEL_EVENT; unit_mask = (eventsel & ARCH_PERFMON_EVENTSEL_UMASK) >> 8; - if (!(event_select & (ARCH_PERFMON_EVENTSEL_EDGE | + if (!(eventsel & (ARCH_PERFMON_EVENTSEL_EDGE | ARCH_PERFMON_EVENTSEL_INV | ARCH_PERFMON_EVENTSEL_CMASK))) { config = find_arch_event(&pmc->vcpu->arch.pmu, event_select, @@ -413,7 +417,7 @@ int kvm_pmu_read_pmc(struct kvm_vcpu *vcpu, unsigned pmc, u64 *data) struct kvm_pmc *counters; u64 ctr; - pmc &= (3u << 30) - 1; + pmc &= ~(3u << 30); if (!fixed && pmc >= pmu->nr_arch_gp_counters) return 1; if (fixed && pmc >= pmu->nr_arch_fixed_counters) diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c index e385214711cb..e334389e1c75 100644 --- a/arch/x86/kvm/svm.c +++ b/arch/x86/kvm/svm.c @@ -111,6 +111,12 @@ struct nested_state { #define MSRPM_OFFSETS 16 static u32 msrpm_offsets[MSRPM_OFFSETS] __read_mostly; +/* + * Set osvw_len to higher value when updated Revision Guides + * are published and we know what the new status bits are + */ +static uint64_t osvw_len = 4, osvw_status; + struct vcpu_svm { struct kvm_vcpu vcpu; struct vmcb *vmcb; @@ -177,11 +183,13 @@ static bool npt_enabled = true; #else static bool npt_enabled; #endif -static int npt = 1; +/* allow nested paging (virtualized MMU) for all guests */ +static int npt = true; module_param(npt, int, S_IRUGO); -static int nested = 1; +/* allow nested virtualization in KVM/SVM */ +static int nested = true; module_param(nested, int, S_IRUGO); static void svm_flush_tlb(struct kvm_vcpu *vcpu); @@ -557,6 +565,27 @@ static void svm_init_erratum_383(void) erratum_383_found = true; } +static void svm_init_osvw(struct kvm_vcpu *vcpu) +{ + /* + * Guests should see errata 400 and 415 as fixed (assuming that + * HLT and IO instructions are intercepted). + */ + vcpu->arch.osvw.length = (osvw_len >= 3) ? (osvw_len) : 3; + vcpu->arch.osvw.status = osvw_status & ~(6ULL); + + /* + * By increasing VCPU's osvw.length to 3 we are telling the guest that + * all osvw.status bits inside that length, including bit 0 (which is + * reserved for erratum 298), are valid. However, if host processor's + * osvw_len is 0 then osvw_status[0] carries no information. We need to + * be conservative here and therefore we tell the guest that erratum 298 + * is present (because we really don't know). + */ + if (osvw_len == 0 && boot_cpu_data.x86 == 0x10) + vcpu->arch.osvw.status |= 1; +} + static int has_svm(void) { const char *msg; @@ -623,6 +652,36 @@ static int svm_hardware_enable(void *garbage) __get_cpu_var(current_tsc_ratio) = TSC_RATIO_DEFAULT; } + + /* + * Get OSVW bits. + * + * Note that it is possible to have a system with mixed processor + * revisions and therefore different OSVW bits. If bits are not the same + * on different processors then choose the worst case (i.e. if erratum + * is present on one processor and not on another then assume that the + * erratum is present everywhere). + */ + if (cpu_has(&boot_cpu_data, X86_FEATURE_OSVW)) { + uint64_t len, status = 0; + int err; + + len = native_read_msr_safe(MSR_AMD64_OSVW_ID_LENGTH, &err); + if (!err) + status = native_read_msr_safe(MSR_AMD64_OSVW_STATUS, + &err); + + if (err) + osvw_status = osvw_len = 0; + else { + if (len < osvw_len) + osvw_len = len; + osvw_status |= status; + osvw_status &= (1ULL << osvw_len) - 1; + } + } else + osvw_status = osvw_len = 0; + svm_init_erratum_383(); amd_pmu_enable_virt(); @@ -910,20 +969,25 @@ static u64 svm_scale_tsc(struct kvm_vcpu *vcpu, u64 tsc) return _tsc; } -static void svm_set_tsc_khz(struct kvm_vcpu *vcpu, u32 user_tsc_khz) +static void svm_set_tsc_khz(struct kvm_vcpu *vcpu, u32 user_tsc_khz, bool scale) { struct vcpu_svm *svm = to_svm(vcpu); u64 ratio; u64 khz; - /* TSC scaling supported? */ - if (!boot_cpu_has(X86_FEATURE_TSCRATEMSR)) + /* Guest TSC same frequency as host TSC? */ + if (!scale) { + svm->tsc_ratio = TSC_RATIO_DEFAULT; return; + } - /* TSC-Scaling disabled or guest TSC same frequency as host TSC? */ - if (user_tsc_khz == 0) { - vcpu->arch.virtual_tsc_khz = 0; - svm->tsc_ratio = TSC_RATIO_DEFAULT; + /* TSC scaling supported? */ + if (!boot_cpu_has(X86_FEATURE_TSCRATEMSR)) { + if (user_tsc_khz > tsc_khz) { + vcpu->arch.tsc_catchup = 1; + vcpu->arch.tsc_always_catchup = 1; + } else + WARN(1, "user requested TSC rate below hardware speed\n"); return; } @@ -938,7 +1002,6 @@ static void svm_set_tsc_khz(struct kvm_vcpu *vcpu, u32 user_tsc_khz) user_tsc_khz); return; } - vcpu->arch.virtual_tsc_khz = user_tsc_khz; svm->tsc_ratio = ratio; } @@ -958,10 +1021,14 @@ static void svm_write_tsc_offset(struct kvm_vcpu *vcpu, u64 offset) mark_dirty(svm->vmcb, VMCB_INTERCEPTS); } -static void svm_adjust_tsc_offset(struct kvm_vcpu *vcpu, s64 adjustment) +static void svm_adjust_tsc_offset(struct kvm_vcpu *vcpu, s64 adjustment, bool host) { struct vcpu_svm *svm = to_svm(vcpu); + WARN_ON(adjustment < 0); + if (host) + adjustment = svm_scale_tsc(vcpu, adjustment); + svm->vmcb->control.tsc_offset += adjustment; if (is_guest_mode(vcpu)) svm->nested.hsave->control.tsc_offset += adjustment; @@ -1191,6 +1258,8 @@ static struct kvm_vcpu *svm_create_vcpu(struct kvm *kvm, unsigned int id) if (kvm_vcpu_is_bsp(&svm->vcpu)) svm->vcpu.arch.apic_base |= MSR_IA32_APICBASE_BSP; + svm_init_osvw(&svm->vcpu); + return &svm->vcpu; free_page4: @@ -1268,6 +1337,21 @@ static void svm_vcpu_put(struct kvm_vcpu *vcpu) wrmsrl(host_save_user_msrs[i], svm->host_user_msrs[i]); } +static void svm_update_cpl(struct kvm_vcpu *vcpu) +{ + struct vcpu_svm *svm = to_svm(vcpu); + int cpl; + + if (!is_protmode(vcpu)) + cpl = 0; + else if (svm->vmcb->save.rflags & X86_EFLAGS_VM) + cpl = 3; + else + cpl = svm->vmcb->save.cs.selector & 0x3; + + svm->vmcb->save.cpl = cpl; +} + static unsigned long svm_get_rflags(struct kvm_vcpu *vcpu) { return to_svm(vcpu)->vmcb->save.rflags; @@ -1275,7 +1359,11 @@ static unsigned long svm_get_rflags(struct kvm_vcpu *vcpu) static void svm_set_rflags(struct kvm_vcpu *vcpu, unsigned long rflags) { + unsigned long old_rflags = to_svm(vcpu)->vmcb->save.rflags; + to_svm(vcpu)->vmcb->save.rflags = rflags; + if ((old_rflags ^ rflags) & X86_EFLAGS_VM) + svm_update_cpl(vcpu); } static void svm_cache_reg(struct kvm_vcpu *vcpu, enum kvm_reg reg) @@ -1543,9 +1631,7 @@ static void svm_set_segment(struct kvm_vcpu *vcpu, s->attrib |= (var->g & 1) << SVM_SELECTOR_G_SHIFT; } if (seg == VCPU_SREG_CS) - svm->vmcb->save.cpl - = (svm->vmcb->save.cs.attrib - >> SVM_SELECTOR_DPL_SHIFT) & 3; + svm_update_cpl(vcpu); mark_dirty(svm->vmcb, VMCB_SEG); } @@ -2735,7 +2821,10 @@ static int task_switch_interception(struct vcpu_svm *svm) (int_vec == OF_VECTOR || int_vec == BP_VECTOR))) skip_emulated_instruction(&svm->vcpu); - if (kvm_task_switch(&svm->vcpu, tss_selector, reason, + if (int_type != SVM_EXITINTINFO_TYPE_SOFT) + int_vec = -1; + + if (kvm_task_switch(&svm->vcpu, tss_selector, int_vec, reason, has_error_code, error_code) == EMULATE_FAIL) { svm->vcpu.run->exit_reason = KVM_EXIT_INTERNAL_ERROR; svm->vcpu.run->internal.suberror = KVM_INTERNAL_ERROR_EMULATION; diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c index 246490f643b6..280751c84724 100644 --- a/arch/x86/kvm/vmx.c +++ b/arch/x86/kvm/vmx.c @@ -70,9 +70,6 @@ module_param(emulate_invalid_guest_state, bool, S_IRUGO); static bool __read_mostly vmm_exclusive = 1; module_param(vmm_exclusive, bool, S_IRUGO); -static bool __read_mostly yield_on_hlt = 1; -module_param(yield_on_hlt, bool, S_IRUGO); - static bool __read_mostly fasteoi = 1; module_param(fasteoi, bool, S_IRUGO); @@ -1655,17 +1652,6 @@ static void skip_emulated_instruction(struct kvm_vcpu *vcpu) vmx_set_interrupt_shadow(vcpu, 0); } -static void vmx_clear_hlt(struct kvm_vcpu *vcpu) -{ - /* Ensure that we clear the HLT state in the VMCS. We don't need to - * explicitly skip the instruction because if the HLT state is set, then - * the instruction is already executing and RIP has already been - * advanced. */ - if (!yield_on_hlt && - vmcs_read32(GUEST_ACTIVITY_STATE) == GUEST_ACTIVITY_HLT) - vmcs_write32(GUEST_ACTIVITY_STATE, GUEST_ACTIVITY_ACTIVE); -} - /* * KVM wants to inject page-faults which it got to the guest. This function * checks whether in a nested guest, we need to inject them to L1 or L2. @@ -1678,7 +1664,7 @@ static int nested_pf_handled(struct kvm_vcpu *vcpu) struct vmcs12 *vmcs12 = get_vmcs12(vcpu); /* TODO: also check PFEC_MATCH/MASK, not just EB.PF. */ - if (!(vmcs12->exception_bitmap & PF_VECTOR)) + if (!(vmcs12->exception_bitmap & (1u << PF_VECTOR))) return 0; nested_vmx_vmexit(vcpu); @@ -1718,7 +1704,6 @@ static void vmx_queue_exception(struct kvm_vcpu *vcpu, unsigned nr, intr_info |= INTR_TYPE_HARD_EXCEPTION; vmcs_write32(VM_ENTRY_INTR_INFO_FIELD, intr_info); - vmx_clear_hlt(vcpu); } static bool vmx_rdtscp_supported(void) @@ -1817,13 +1802,19 @@ u64 vmx_read_l1_tsc(struct kvm_vcpu *vcpu) } /* - * Empty call-back. Needs to be implemented when VMX enables the SET_TSC_KHZ - * ioctl. In this case the call-back should update internal vmx state to make - * the changes effective. + * Engage any workarounds for mis-matched TSC rates. Currently limited to + * software catchup for faster rates on slower CPUs. */ -static void vmx_set_tsc_khz(struct kvm_vcpu *vcpu, u32 user_tsc_khz) +static void vmx_set_tsc_khz(struct kvm_vcpu *vcpu, u32 user_tsc_khz, bool scale) { - /* Nothing to do here */ + if (!scale) + return; + + if (user_tsc_khz > tsc_khz) { + vcpu->arch.tsc_catchup = 1; + vcpu->arch.tsc_always_catchup = 1; + } else + WARN(1, "user requested TSC rate below hardware speed\n"); } /* @@ -1850,7 +1841,7 @@ static void vmx_write_tsc_offset(struct kvm_vcpu *vcpu, u64 offset) } } -static void vmx_adjust_tsc_offset(struct kvm_vcpu *vcpu, s64 adjustment) +static void vmx_adjust_tsc_offset(struct kvm_vcpu *vcpu, s64 adjustment, bool host) { u64 offset = vmcs_read64(TSC_OFFSET); vmcs_write64(TSC_OFFSET, offset + adjustment); @@ -2219,6 +2210,9 @@ static int vmx_set_msr(struct kvm_vcpu *vcpu, u32 msr_index, u64 data) msr = find_msr_entry(vmx, msr_index); if (msr) { msr->data = data; + if (msr - vmx->guest_msrs < vmx->save_nmsrs) + kvm_set_shared_msr(msr->index, msr->data, + msr->mask); break; } ret = kvm_set_msr_common(vcpu, msr_index, data); @@ -2399,7 +2393,7 @@ static __init int setup_vmcs_config(struct vmcs_config *vmcs_conf) &_pin_based_exec_control) < 0) return -EIO; - min = + min = CPU_BASED_HLT_EXITING | #ifdef CONFIG_X86_64 CPU_BASED_CR8_LOAD_EXITING | CPU_BASED_CR8_STORE_EXITING | @@ -2414,9 +2408,6 @@ static __init int setup_vmcs_config(struct vmcs_config *vmcs_conf) CPU_BASED_INVLPG_EXITING | CPU_BASED_RDPMC_EXITING; - if (yield_on_hlt) - min |= CPU_BASED_HLT_EXITING; - opt = CPU_BASED_TPR_SHADOW | CPU_BASED_USE_MSR_BITMAPS | CPU_BASED_ACTIVATE_SECONDARY_CONTROLS; @@ -4003,7 +3994,6 @@ static void vmx_inject_irq(struct kvm_vcpu *vcpu) } else intr |= INTR_TYPE_EXT_INTR; vmcs_write32(VM_ENTRY_INTR_INFO_FIELD, intr); - vmx_clear_hlt(vcpu); } static void vmx_inject_nmi(struct kvm_vcpu *vcpu) @@ -4035,7 +4025,6 @@ static void vmx_inject_nmi(struct kvm_vcpu *vcpu) } vmcs_write32(VM_ENTRY_INTR_INFO_FIELD, INTR_TYPE_NMI_INTR | INTR_INFO_VALID_MASK | NMI_VECTOR); - vmx_clear_hlt(vcpu); } static int vmx_nmi_allowed(struct kvm_vcpu *vcpu) @@ -4672,9 +4661,10 @@ static int handle_task_switch(struct kvm_vcpu *vcpu) bool has_error_code = false; u32 error_code = 0; u16 tss_selector; - int reason, type, idt_v; + int reason, type, idt_v, idt_index; idt_v = (vmx->idt_vectoring_info & VECTORING_INFO_VALID_MASK); + idt_index = (vmx->idt_vectoring_info & VECTORING_INFO_VECTOR_MASK); type = (vmx->idt_vectoring_info & VECTORING_INFO_TYPE_MASK); exit_qualification = vmcs_readl(EXIT_QUALIFICATION); @@ -4712,8 +4702,9 @@ static int handle_task_switch(struct kvm_vcpu *vcpu) type != INTR_TYPE_NMI_INTR)) skip_emulated_instruction(vcpu); - if (kvm_task_switch(vcpu, tss_selector, reason, - has_error_code, error_code) == EMULATE_FAIL) { + if (kvm_task_switch(vcpu, tss_selector, + type == INTR_TYPE_SOFT_INTR ? idt_index : -1, reason, + has_error_code, error_code) == EMULATE_FAIL) { vcpu->run->exit_reason = KVM_EXIT_INTERNAL_ERROR; vcpu->run->internal.suberror = KVM_INTERNAL_ERROR_EMULATION; vcpu->run->internal.ndata = 0; diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 54696b5f8443..4044ce0bf7c1 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -97,6 +97,10 @@ EXPORT_SYMBOL_GPL(kvm_has_tsc_control); u32 kvm_max_guest_tsc_khz; EXPORT_SYMBOL_GPL(kvm_max_guest_tsc_khz); +/* tsc tolerance in parts per million - default to 1/2 of the NTP threshold */ +static u32 tsc_tolerance_ppm = 250; +module_param(tsc_tolerance_ppm, uint, S_IRUGO | S_IWUSR); + #define KVM_NR_SHARED_MSRS 16 struct kvm_shared_msrs_global { @@ -969,50 +973,51 @@ static inline u64 get_kernel_ns(void) static DEFINE_PER_CPU(unsigned long, cpu_tsc_khz); unsigned long max_tsc_khz; -static inline int kvm_tsc_changes_freq(void) +static inline u64 nsec_to_cycles(struct kvm_vcpu *vcpu, u64 nsec) { - int cpu = get_cpu(); - int ret = !boot_cpu_has(X86_FEATURE_CONSTANT_TSC) && - cpufreq_quick_get(cpu) != 0; - put_cpu(); - return ret; + return pvclock_scale_delta(nsec, vcpu->arch.virtual_tsc_mult, + vcpu->arch.virtual_tsc_shift); } -u64 vcpu_tsc_khz(struct kvm_vcpu *vcpu) +static u32 adjust_tsc_khz(u32 khz, s32 ppm) { - if (vcpu->arch.virtual_tsc_khz) - return vcpu->arch.virtual_tsc_khz; - else - return __this_cpu_read(cpu_tsc_khz); + u64 v = (u64)khz * (1000000 + ppm); + do_div(v, 1000000); + return v; } -static inline u64 nsec_to_cycles(struct kvm_vcpu *vcpu, u64 nsec) +static void kvm_set_tsc_khz(struct kvm_vcpu *vcpu, u32 this_tsc_khz) { - u64 ret; - - WARN_ON(preemptible()); - if (kvm_tsc_changes_freq()) - printk_once(KERN_WARNING - "kvm: unreliable cycle conversion on adjustable rate TSC\n"); - ret = nsec * vcpu_tsc_khz(vcpu); - do_div(ret, USEC_PER_SEC); - return ret; -} + u32 thresh_lo, thresh_hi; + int use_scaling = 0; -static void kvm_init_tsc_catchup(struct kvm_vcpu *vcpu, u32 this_tsc_khz) -{ /* Compute a scale to convert nanoseconds in TSC cycles */ kvm_get_time_scale(this_tsc_khz, NSEC_PER_SEC / 1000, - &vcpu->arch.tsc_catchup_shift, - &vcpu->arch.tsc_catchup_mult); + &vcpu->arch.virtual_tsc_shift, + &vcpu->arch.virtual_tsc_mult); + vcpu->arch.virtual_tsc_khz = this_tsc_khz; + + /* + * Compute the variation in TSC rate which is acceptable + * within the range of tolerance and decide if the + * rate being applied is within that bounds of the hardware + * rate. If so, no scaling or compensation need be done. + */ + thresh_lo = adjust_tsc_khz(tsc_khz, -tsc_tolerance_ppm); + thresh_hi = adjust_tsc_khz(tsc_khz, tsc_tolerance_ppm); + if (this_tsc_khz < thresh_lo || this_tsc_khz > thresh_hi) { + pr_debug("kvm: requested TSC rate %u falls outside tolerance [%u,%u]\n", this_tsc_khz, thresh_lo, thresh_hi); + use_scaling = 1; + } + kvm_x86_ops->set_tsc_khz(vcpu, this_tsc_khz, use_scaling); } static u64 compute_guest_tsc(struct kvm_vcpu *vcpu, s64 kernel_ns) { - u64 tsc = pvclock_scale_delta(kernel_ns-vcpu->arch.last_tsc_nsec, - vcpu->arch.tsc_catchup_mult, - vcpu->arch.tsc_catchup_shift); - tsc += vcpu->arch.last_tsc_write; + u64 tsc = pvclock_scale_delta(kernel_ns-vcpu->arch.this_tsc_nsec, + vcpu->arch.virtual_tsc_mult, + vcpu->arch.virtual_tsc_shift); + tsc += vcpu->arch.this_tsc_write; return tsc; } @@ -1021,48 +1026,88 @@ void kvm_write_tsc(struct kvm_vcpu *vcpu, u64 data) struct kvm *kvm = vcpu->kvm; u64 offset, ns, elapsed; unsigned long flags; - s64 sdiff; + s64 usdiff; raw_spin_lock_irqsave(&kvm->arch.tsc_write_lock, flags); offset = kvm_x86_ops->compute_tsc_offset(vcpu, data); ns = get_kernel_ns(); elapsed = ns - kvm->arch.last_tsc_nsec; - sdiff = data - kvm->arch.last_tsc_write; - if (sdiff < 0) - sdiff = -sdiff; + + /* n.b - signed multiplication and division required */ + usdiff = data - kvm->arch.last_tsc_write; +#ifdef CONFIG_X86_64 + usdiff = (usdiff * 1000) / vcpu->arch.virtual_tsc_khz; +#else + /* do_div() only does unsigned */ + asm("idivl %2; xor %%edx, %%edx" + : "=A"(usdiff) + : "A"(usdiff * 1000), "rm"(vcpu->arch.virtual_tsc_khz)); +#endif + do_div(elapsed, 1000); + usdiff -= elapsed; + if (usdiff < 0) + usdiff = -usdiff; /* - * Special case: close write to TSC within 5 seconds of - * another CPU is interpreted as an attempt to synchronize - * The 5 seconds is to accommodate host load / swapping as - * well as any reset of TSC during the boot process. - * - * In that case, for a reliable TSC, we can match TSC offsets, - * or make a best guest using elapsed value. - */ - if (sdiff < nsec_to_cycles(vcpu, 5ULL * NSEC_PER_SEC) && - elapsed < 5ULL * NSEC_PER_SEC) { + * Special case: TSC write with a small delta (1 second) of virtual + * cycle time against real time is interpreted as an attempt to + * synchronize the CPU. + * + * For a reliable TSC, we can match TSC offsets, and for an unstable + * TSC, we add elapsed time in this computation. We could let the + * compensation code attempt to catch up if we fall behind, but + * it's better to try to match offsets from the beginning. + */ + if (usdiff < USEC_PER_SEC && + vcpu->arch.virtual_tsc_khz == kvm->arch.last_tsc_khz) { if (!check_tsc_unstable()) { - offset = kvm->arch.last_tsc_offset; + offset = kvm->arch.cur_tsc_offset; pr_debug("kvm: matched tsc offset for %llu\n", data); } else { u64 delta = nsec_to_cycles(vcpu, elapsed); - offset += delta; + data += delta; + offset = kvm_x86_ops->compute_tsc_offset(vcpu, data); pr_debug("kvm: adjusted tsc offset by %llu\n", delta); } - ns = kvm->arch.last_tsc_nsec; + } else { + /* + * We split periods of matched TSC writes into generations. + * For each generation, we track the original measured + * nanosecond time, offset, and write, so if TSCs are in + * sync, we can match exact offset, and if not, we can match + * exact software computaion in compute_guest_tsc() + * + * These values are tracked in kvm->arch.cur_xxx variables. + */ + kvm->arch.cur_tsc_generation++; + kvm->arch.cur_tsc_nsec = ns; + kvm->arch.cur_tsc_write = data; + kvm->arch.cur_tsc_offset = offset; + pr_debug("kvm: new tsc generation %u, clock %llu\n", + kvm->arch.cur_tsc_generation, data); } + + /* + * We also track th most recent recorded KHZ, write and time to + * allow the matching interval to be extended at each write. + */ kvm->arch.last_tsc_nsec = ns; kvm->arch.last_tsc_write = data; - kvm->arch.last_tsc_offset = offset; - kvm_x86_ops->write_tsc_offset(vcpu, offset); - raw_spin_unlock_irqrestore(&kvm->arch.tsc_write_lock, flags); + kvm->arch.last_tsc_khz = vcpu->arch.virtual_tsc_khz; /* Reset of TSC must disable overshoot protection below */ vcpu->arch.hv_clock.tsc_timestamp = 0; - vcpu->arch.last_tsc_write = data; - vcpu->arch.last_tsc_nsec = ns; + vcpu->arch.last_guest_tsc = data; + + /* Keep track of which generation this VCPU has synchronized to */ + vcpu->arch.this_tsc_generation = kvm->arch.cur_tsc_generation; + vcpu->arch.this_tsc_nsec = kvm->arch.cur_tsc_nsec; + vcpu->arch.this_tsc_write = kvm->arch.cur_tsc_write; + + kvm_x86_ops->write_tsc_offset(vcpu, offset); + raw_spin_unlock_irqrestore(&kvm->arch.tsc_write_lock, flags); } + EXPORT_SYMBOL_GPL(kvm_write_tsc); static int kvm_guest_time_update(struct kvm_vcpu *v) @@ -1078,7 +1123,7 @@ static int kvm_guest_time_update(struct kvm_vcpu *v) local_irq_save(flags); tsc_timestamp = kvm_x86_ops->read_l1_tsc(v); kernel_ns = get_kernel_ns(); - this_tsc_khz = vcpu_tsc_khz(v); + this_tsc_khz = __get_cpu_var(cpu_tsc_khz); if (unlikely(this_tsc_khz == 0)) { local_irq_restore(flags); kvm_make_request(KVM_REQ_CLOCK_UPDATE, v); @@ -1098,7 +1143,7 @@ static int kvm_guest_time_update(struct kvm_vcpu *v) if (vcpu->tsc_catchup) { u64 tsc = compute_guest_tsc(v, kernel_ns); if (tsc > tsc_timestamp) { - kvm_x86_ops->adjust_tsc_offset(v, tsc - tsc_timestamp); + adjust_tsc_offset_guest(v, tsc - tsc_timestamp); tsc_timestamp = tsc; } } @@ -1130,7 +1175,7 @@ static int kvm_guest_time_update(struct kvm_vcpu *v) * observed by the guest and ensure the new system time is greater. */ max_kernel_ns = 0; - if (vcpu->hv_clock.tsc_timestamp && vcpu->last_guest_tsc) { + if (vcpu->hv_clock.tsc_timestamp) { max_kernel_ns = vcpu->last_guest_tsc - vcpu->hv_clock.tsc_timestamp; max_kernel_ns = pvclock_scale_delta(max_kernel_ns, @@ -1504,6 +1549,7 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 data) case MSR_K7_HWCR: data &= ~(u64)0x40; /* ignore flush filter disable */ data &= ~(u64)0x100; /* ignore ignne emulation enable */ + data &= ~(u64)0x8; /* ignore TLB cache disable */ if (data != 0) { pr_unimpl(vcpu, "unimplemented HWCR wrmsr: 0x%llx\n", data); @@ -1676,6 +1722,16 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 data) */ pr_unimpl(vcpu, "ignored wrmsr: 0x%x data %llx\n", msr, data); break; + case MSR_AMD64_OSVW_ID_LENGTH: + if (!guest_cpuid_has_osvw(vcpu)) + return 1; + vcpu->arch.osvw.length = data; + break; + case MSR_AMD64_OSVW_STATUS: + if (!guest_cpuid_has_osvw(vcpu)) + return 1; + vcpu->arch.osvw.status = data; + break; default: if (msr && (msr == vcpu->kvm->arch.xen_hvm_config.msr)) return xen_hvm_config(vcpu, data); @@ -1960,6 +2016,16 @@ int kvm_get_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata) */ data = 0xbe702111; break; + case MSR_AMD64_OSVW_ID_LENGTH: + if (!guest_cpuid_has_osvw(vcpu)) + return 1; + data = vcpu->arch.osvw.length; + break; + case MSR_AMD64_OSVW_STATUS: + if (!guest_cpuid_has_osvw(vcpu)) + return 1; + data = vcpu->arch.osvw.status; + break; default: if (kvm_pmu_msr(vcpu, msr)) return kvm_pmu_get_msr(vcpu, msr, pdata); @@ -2080,6 +2146,7 @@ int kvm_dev_ioctl_check_extension(long ext) case KVM_CAP_XSAVE: case KVM_CAP_ASYNC_PF: case KVM_CAP_GET_TSC_KHZ: + case KVM_CAP_PCI_2_3: r = 1; break; case KVM_CAP_COALESCED_MMIO: @@ -2214,19 +2281,23 @@ void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu) } kvm_x86_ops->vcpu_load(vcpu, cpu); - if (unlikely(vcpu->cpu != cpu) || check_tsc_unstable()) { - /* Make sure TSC doesn't go backwards */ - s64 tsc_delta; - u64 tsc; - tsc = kvm_x86_ops->read_l1_tsc(vcpu); - tsc_delta = !vcpu->arch.last_guest_tsc ? 0 : - tsc - vcpu->arch.last_guest_tsc; + /* Apply any externally detected TSC adjustments (due to suspend) */ + if (unlikely(vcpu->arch.tsc_offset_adjustment)) { + adjust_tsc_offset_host(vcpu, vcpu->arch.tsc_offset_adjustment); + vcpu->arch.tsc_offset_adjustment = 0; + set_bit(KVM_REQ_CLOCK_UPDATE, &vcpu->requests); + } + if (unlikely(vcpu->cpu != cpu) || check_tsc_unstable()) { + s64 tsc_delta = !vcpu->arch.last_host_tsc ? 0 : + native_read_tsc() - vcpu->arch.last_host_tsc; if (tsc_delta < 0) mark_tsc_unstable("KVM discovered backwards TSC"); if (check_tsc_unstable()) { - kvm_x86_ops->adjust_tsc_offset(vcpu, -tsc_delta); + u64 offset = kvm_x86_ops->compute_tsc_offset(vcpu, + vcpu->arch.last_guest_tsc); + kvm_x86_ops->write_tsc_offset(vcpu, offset); vcpu->arch.tsc_catchup = 1; } kvm_make_request(KVM_REQ_CLOCK_UPDATE, vcpu); @@ -2243,7 +2314,7 @@ void kvm_arch_vcpu_put(struct kvm_vcpu *vcpu) { kvm_x86_ops->vcpu_put(vcpu); kvm_put_guest_fpu(vcpu); - vcpu->arch.last_guest_tsc = kvm_x86_ops->read_l1_tsc(vcpu); + vcpu->arch.last_host_tsc = native_read_tsc(); } static int kvm_vcpu_ioctl_get_lapic(struct kvm_vcpu *vcpu, @@ -2785,26 +2856,21 @@ long kvm_arch_vcpu_ioctl(struct file *filp, u32 user_tsc_khz; r = -EINVAL; - if (!kvm_has_tsc_control) - break; - user_tsc_khz = (u32)arg; if (user_tsc_khz >= kvm_max_guest_tsc_khz) goto out; - kvm_x86_ops->set_tsc_khz(vcpu, user_tsc_khz); + if (user_tsc_khz == 0) + user_tsc_khz = tsc_khz; + + kvm_set_tsc_khz(vcpu, user_tsc_khz); r = 0; goto out; } case KVM_GET_TSC_KHZ: { - r = -EIO; - if (check_tsc_unstable()) - goto out; - - r = vcpu_tsc_khz(vcpu); - + r = vcpu->arch.virtual_tsc_khz; goto out; } default: @@ -2815,6 +2881,11 @@ out: return r; } +int kvm_arch_vcpu_fault(struct kvm_vcpu *vcpu, struct vm_fault *vmf) +{ + return VM_FAULT_SIGBUS; +} + static int kvm_vm_ioctl_set_tss_addr(struct kvm *kvm, unsigned long addr) { int ret; @@ -2998,6 +3069,8 @@ static void write_protect_slot(struct kvm *kvm, unsigned long *dirty_bitmap, unsigned long nr_dirty_pages) { + spin_lock(&kvm->mmu_lock); + /* Not many dirty pages compared to # of shadow pages. */ if (nr_dirty_pages < kvm->arch.n_used_mmu_pages) { unsigned long gfn_offset; @@ -3005,16 +3078,13 @@ static void write_protect_slot(struct kvm *kvm, for_each_set_bit(gfn_offset, dirty_bitmap, memslot->npages) { unsigned long gfn = memslot->base_gfn + gfn_offset; - spin_lock(&kvm->mmu_lock); kvm_mmu_rmap_write_protect(kvm, gfn, memslot); - spin_unlock(&kvm->mmu_lock); } kvm_flush_remote_tlbs(kvm); - } else { - spin_lock(&kvm->mmu_lock); + } else kvm_mmu_slot_remove_write_access(kvm, memslot->id); - spin_unlock(&kvm->mmu_lock); - } + + spin_unlock(&kvm->mmu_lock); } /* @@ -3133,6 +3203,9 @@ long kvm_arch_vm_ioctl(struct file *filp, r = -EEXIST; if (kvm->arch.vpic) goto create_irqchip_unlock; + r = -EINVAL; + if (atomic_read(&kvm->online_vcpus)) + goto create_irqchip_unlock; r = -ENOMEM; vpic = kvm_create_pic(kvm); if (vpic) { @@ -4063,6 +4136,11 @@ static int emulator_set_cr(struct x86_emulate_ctxt *ctxt, int cr, ulong val) return res; } +static void emulator_set_rflags(struct x86_emulate_ctxt *ctxt, ulong val) +{ + kvm_set_rflags(emul_to_vcpu(ctxt), val); +} + static int emulator_get_cpl(struct x86_emulate_ctxt *ctxt) { return kvm_x86_ops->get_cpl(emul_to_vcpu(ctxt)); @@ -4244,6 +4322,7 @@ static struct x86_emulate_ops emulate_ops = { .set_idt = emulator_set_idt, .get_cr = emulator_get_cr, .set_cr = emulator_set_cr, + .set_rflags = emulator_set_rflags, .cpl = emulator_get_cpl, .get_dr = emulator_get_dr, .set_dr = emulator_set_dr, @@ -5288,6 +5367,8 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) profile_hit(KVM_PROFILING, (void *)rip); } + if (unlikely(vcpu->arch.tsc_always_catchup)) + kvm_make_request(KVM_REQ_CLOCK_UPDATE, vcpu); kvm_lapic_sync_from_vapic(vcpu); @@ -5587,15 +5668,15 @@ int kvm_arch_vcpu_ioctl_set_mpstate(struct kvm_vcpu *vcpu, return 0; } -int kvm_task_switch(struct kvm_vcpu *vcpu, u16 tss_selector, int reason, - bool has_error_code, u32 error_code) +int kvm_task_switch(struct kvm_vcpu *vcpu, u16 tss_selector, int idt_index, + int reason, bool has_error_code, u32 error_code) { struct x86_emulate_ctxt *ctxt = &vcpu->arch.emulate_ctxt; int ret; init_emulate_ctxt(vcpu); - ret = emulator_task_switch(ctxt, tss_selector, reason, + ret = emulator_task_switch(ctxt, tss_selector, idt_index, reason, has_error_code, error_code); if (ret) @@ -5928,13 +6009,88 @@ int kvm_arch_hardware_enable(void *garbage) struct kvm *kvm; struct kvm_vcpu *vcpu; int i; + int ret; + u64 local_tsc; + u64 max_tsc = 0; + bool stable, backwards_tsc = false; kvm_shared_msr_cpu_online(); - list_for_each_entry(kvm, &vm_list, vm_list) - kvm_for_each_vcpu(i, vcpu, kvm) - if (vcpu->cpu == smp_processor_id()) - kvm_make_request(KVM_REQ_CLOCK_UPDATE, vcpu); - return kvm_x86_ops->hardware_enable(garbage); + ret = kvm_x86_ops->hardware_enable(garbage); + if (ret != 0) + return ret; + + local_tsc = native_read_tsc(); + stable = !check_tsc_unstable(); + list_for_each_entry(kvm, &vm_list, vm_list) { + kvm_for_each_vcpu(i, vcpu, kvm) { + if (!stable && vcpu->cpu == smp_processor_id()) + set_bit(KVM_REQ_CLOCK_UPDATE, &vcpu->requests); + if (stable && vcpu->arch.last_host_tsc > local_tsc) { + backwards_tsc = true; + if (vcpu->arch.last_host_tsc > max_tsc) + max_tsc = vcpu->arch.last_host_tsc; + } + } + } + + /* + * Sometimes, even reliable TSCs go backwards. This happens on + * platforms that reset TSC during suspend or hibernate actions, but + * maintain synchronization. We must compensate. Fortunately, we can + * detect that condition here, which happens early in CPU bringup, + * before any KVM threads can be running. Unfortunately, we can't + * bring the TSCs fully up to date with real time, as we aren't yet far + * enough into CPU bringup that we know how much real time has actually + * elapsed; our helper function, get_kernel_ns() will be using boot + * variables that haven't been updated yet. + * + * So we simply find the maximum observed TSC above, then record the + * adjustment to TSC in each VCPU. When the VCPU later gets loaded, + * the adjustment will be applied. Note that we accumulate + * adjustments, in case multiple suspend cycles happen before some VCPU + * gets a chance to run again. In the event that no KVM threads get a + * chance to run, we will miss the entire elapsed period, as we'll have + * reset last_host_tsc, so VCPUs will not have the TSC adjusted and may + * loose cycle time. This isn't too big a deal, since the loss will be + * uniform across all VCPUs (not to mention the scenario is extremely + * unlikely). It is possible that a second hibernate recovery happens + * much faster than a first, causing the observed TSC here to be + * smaller; this would require additional padding adjustment, which is + * why we set last_host_tsc to the local tsc observed here. + * + * N.B. - this code below runs only on platforms with reliable TSC, + * as that is the only way backwards_tsc is set above. Also note + * that this runs for ALL vcpus, which is not a bug; all VCPUs should + * have the same delta_cyc adjustment applied if backwards_tsc + * is detected. Note further, this adjustment is only done once, + * as we reset last_host_tsc on all VCPUs to stop this from being + * called multiple times (one for each physical CPU bringup). + * + * Platforms with unnreliable TSCs don't have to deal with this, they + * will be compensated by the logic in vcpu_load, which sets the TSC to + * catchup mode. This will catchup all VCPUs to real time, but cannot + * guarantee that they stay in perfect synchronization. + */ + if (backwards_tsc) { + u64 delta_cyc = max_tsc - local_tsc; + list_for_each_entry(kvm, &vm_list, vm_list) { + kvm_for_each_vcpu(i, vcpu, kvm) { + vcpu->arch.tsc_offset_adjustment += delta_cyc; + vcpu->arch.last_host_tsc = local_tsc; + } + + /* + * We have to disable TSC offset matching.. if you were + * booting a VM while issuing an S4 host suspend.... + * you may have some problem. Solving this issue is + * left as an exercise to the reader. + */ + kvm->arch.last_tsc_nsec = 0; + kvm->arch.last_tsc_write = 0; + } + + } + return 0; } void kvm_arch_hardware_disable(void *garbage) @@ -5958,6 +6114,11 @@ void kvm_arch_check_processor_compat(void *rtn) kvm_x86_ops->check_processor_compatibility(rtn); } +bool kvm_vcpu_compatible(struct kvm_vcpu *vcpu) +{ + return irqchip_in_kernel(vcpu->kvm) == (vcpu->arch.apic != NULL); +} + int kvm_arch_vcpu_init(struct kvm_vcpu *vcpu) { struct page *page; @@ -5980,7 +6141,7 @@ int kvm_arch_vcpu_init(struct kvm_vcpu *vcpu) } vcpu->arch.pio_data = page_address(page); - kvm_init_tsc_catchup(vcpu, max_tsc_khz); + kvm_set_tsc_khz(vcpu, max_tsc_khz); r = kvm_mmu_create(vcpu); if (r < 0) @@ -6032,8 +6193,11 @@ void kvm_arch_vcpu_uninit(struct kvm_vcpu *vcpu) free_page((unsigned long)vcpu->arch.pio_data); } -int kvm_arch_init_vm(struct kvm *kvm) +int kvm_arch_init_vm(struct kvm *kvm, unsigned long type) { + if (type) + return -EINVAL; + INIT_LIST_HEAD(&kvm->arch.active_mmu_pages); INIT_LIST_HEAD(&kvm->arch.assigned_dev_head); @@ -6093,6 +6257,65 @@ void kvm_arch_destroy_vm(struct kvm *kvm) put_page(kvm->arch.ept_identity_pagetable); } +void kvm_arch_free_memslot(struct kvm_memory_slot *free, + struct kvm_memory_slot *dont) +{ + int i; + + for (i = 0; i < KVM_NR_PAGE_SIZES - 1; ++i) { + if (!dont || free->arch.lpage_info[i] != dont->arch.lpage_info[i]) { + vfree(free->arch.lpage_info[i]); + free->arch.lpage_info[i] = NULL; + } + } +} + +int kvm_arch_create_memslot(struct kvm_memory_slot *slot, unsigned long npages) +{ + int i; + + for (i = 0; i < KVM_NR_PAGE_SIZES - 1; ++i) { + unsigned long ugfn; + int lpages; + int level = i + 2; + + lpages = gfn_to_index(slot->base_gfn + npages - 1, + slot->base_gfn, level) + 1; + + slot->arch.lpage_info[i] = + vzalloc(lpages * sizeof(*slot->arch.lpage_info[i])); + if (!slot->arch.lpage_info[i]) + goto out_free; + + if (slot->base_gfn & (KVM_PAGES_PER_HPAGE(level) - 1)) + slot->arch.lpage_info[i][0].write_count = 1; + if ((slot->base_gfn + npages) & (KVM_PAGES_PER_HPAGE(level) - 1)) + slot->arch.lpage_info[i][lpages - 1].write_count = 1; + ugfn = slot->userspace_addr >> PAGE_SHIFT; + /* + * If the gfn and userspace address are not aligned wrt each + * other, or if explicitly asked to, disable large page + * support for this slot + */ + if ((slot->base_gfn ^ ugfn) & (KVM_PAGES_PER_HPAGE(level) - 1) || + !kvm_largepages_enabled()) { + unsigned long j; + + for (j = 0; j < lpages; ++j) + slot->arch.lpage_info[i][j].write_count = 1; + } + } + + return 0; + +out_free: + for (i = 0; i < KVM_NR_PAGE_SIZES - 1; ++i) { + vfree(slot->arch.lpage_info[i]); + slot->arch.lpage_info[i] = NULL; + } + return -ENOMEM; +} + int kvm_arch_prepare_memory_region(struct kvm *kvm, struct kvm_memory_slot *memslot, struct kvm_memory_slot old, diff --git a/arch/x86/math-emu/fpu_entry.c b/arch/x86/math-emu/fpu_entry.c index 7718541541d4..9b868124128d 100644 --- a/arch/x86/math-emu/fpu_entry.c +++ b/arch/x86/math-emu/fpu_entry.c @@ -28,6 +28,7 @@ #include <linux/regset.h> #include <asm/uaccess.h> +#include <asm/traps.h> #include <asm/desc.h> #include <asm/user.h> #include <asm/i387.h> @@ -269,7 +270,7 @@ void math_emulate(struct math_emu_info *info) FPU_EIP = FPU_ORIG_EIP; /* Point to current FPU instruction. */ RE_ENTRANT_CHECK_OFF; - current->thread.trap_no = 16; + current->thread.trap_nr = X86_TRAP_MF; current->thread.error_code = 0; send_sig(SIGFPE, current, 1); return; @@ -662,7 +663,7 @@ static int valid_prefix(u_char *Byte, u_char __user **fpu_eip, void math_abort(struct math_emu_info *info, unsigned int signal) { FPU_EIP = FPU_ORIG_EIP; - current->thread.trap_no = 16; + current->thread.trap_nr = X86_TRAP_MF; current->thread.error_code = 0; send_sig(signal, current, 1); RE_ENTRANT_CHECK_OFF; diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c index f0b4caf85c1a..3ecfd1aaf214 100644 --- a/arch/x86/mm/fault.c +++ b/arch/x86/mm/fault.c @@ -615,7 +615,7 @@ pgtable_bad(struct pt_regs *regs, unsigned long error_code, dump_pagetable(address); tsk->thread.cr2 = address; - tsk->thread.trap_no = 14; + tsk->thread.trap_nr = X86_TRAP_PF; tsk->thread.error_code = error_code; if (__die("Bad pagetable", regs, error_code)) @@ -636,7 +636,7 @@ no_context(struct pt_regs *regs, unsigned long error_code, /* Are we prepared to handle this kernel fault? */ if (fixup_exception(regs)) { if (current_thread_info()->sig_on_uaccess_error && signal) { - tsk->thread.trap_no = 14; + tsk->thread.trap_nr = X86_TRAP_PF; tsk->thread.error_code = error_code | PF_USER; tsk->thread.cr2 = address; @@ -676,7 +676,7 @@ no_context(struct pt_regs *regs, unsigned long error_code, printk(KERN_EMERG "Thread overran stack, or stack corrupted\n"); tsk->thread.cr2 = address; - tsk->thread.trap_no = 14; + tsk->thread.trap_nr = X86_TRAP_PF; tsk->thread.error_code = error_code; sig = SIGKILL; @@ -754,7 +754,7 @@ __bad_area_nosemaphore(struct pt_regs *regs, unsigned long error_code, /* Kernel addresses are always protection faults: */ tsk->thread.cr2 = address; tsk->thread.error_code = error_code | (address >= TASK_SIZE); - tsk->thread.trap_no = 14; + tsk->thread.trap_nr = X86_TRAP_PF; force_sig_info_fault(SIGSEGV, si_code, address, tsk, 0); @@ -838,7 +838,7 @@ do_sigbus(struct pt_regs *regs, unsigned long error_code, unsigned long address, tsk->thread.cr2 = address; tsk->thread.error_code = error_code; - tsk->thread.trap_no = 14; + tsk->thread.trap_nr = X86_TRAP_PF; #ifdef CONFIG_MEMORY_FAILURE if (fault & (VM_FAULT_HWPOISON|VM_FAULT_HWPOISON_LARGE)) { diff --git a/arch/x86/mm/init.c b/arch/x86/mm/init.c index 6cabf6570d64..4f0cec7e4ffb 100644 --- a/arch/x86/mm/init.c +++ b/arch/x86/mm/init.c @@ -12,7 +12,6 @@ #include <asm/page_types.h> #include <asm/sections.h> #include <asm/setup.h> -#include <asm/system.h> #include <asm/tlbflush.h> #include <asm/tlb.h> #include <asm/proto.h> diff --git a/arch/x86/mm/init_32.c b/arch/x86/mm/init_32.c index 8663f6c47ccb..575d86f85ce4 100644 --- a/arch/x86/mm/init_32.c +++ b/arch/x86/mm/init_32.c @@ -35,7 +35,6 @@ #include <asm/asm.h> #include <asm/bios_ebda.h> #include <asm/processor.h> -#include <asm/system.h> #include <asm/uaccess.h> #include <asm/pgtable.h> #include <asm/dma.h> diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c index 436a0309db33..fc18be0f6f29 100644 --- a/arch/x86/mm/init_64.c +++ b/arch/x86/mm/init_64.c @@ -35,7 +35,6 @@ #include <asm/processor.h> #include <asm/bios_ebda.h> -#include <asm/system.h> #include <asm/uaccess.h> #include <asm/pgtable.h> #include <asm/pgalloc.h> diff --git a/arch/x86/mm/kmemcheck/selftest.c b/arch/x86/mm/kmemcheck/selftest.c index 036efbea8b28..aef7140c0063 100644 --- a/arch/x86/mm/kmemcheck/selftest.c +++ b/arch/x86/mm/kmemcheck/selftest.c @@ -1,3 +1,4 @@ +#include <linux/bug.h> #include <linux/kernel.h> #include "opcode.h" diff --git a/arch/x86/mm/pgtable_32.c b/arch/x86/mm/pgtable_32.c index cac718499256..a69bcb8c7621 100644 --- a/arch/x86/mm/pgtable_32.c +++ b/arch/x86/mm/pgtable_32.c @@ -10,7 +10,6 @@ #include <linux/spinlock.h> #include <linux/module.h> -#include <asm/system.h> #include <asm/pgtable.h> #include <asm/pgalloc.h> #include <asm/fixmap.h> diff --git a/arch/x86/oprofile/backtrace.c b/arch/x86/oprofile/backtrace.c index bff89dfe3619..d6aa6e8315d1 100644 --- a/arch/x86/oprofile/backtrace.c +++ b/arch/x86/oprofile/backtrace.c @@ -67,7 +67,7 @@ x86_backtrace_32(struct pt_regs * const regs, unsigned int depth) { struct stack_frame_ia32 *head; - /* User process is 32-bit */ + /* User process is IA32 */ if (!current || !test_thread_flag(TIF_IA32)) return 0; diff --git a/arch/x86/pci/acpi.c b/arch/x86/pci/acpi.c index 49a5cb55429b..ed2835e148b5 100644 --- a/arch/x86/pci/acpi.c +++ b/arch/x86/pci/acpi.c @@ -416,7 +416,12 @@ struct pci_bus * __devinit pci_acpi_scan_root(struct acpi_pci_root *root) kfree(sd); } else { get_current_resources(device, busnum, domain, &resources); - if (list_empty(&resources)) + + /* + * _CRS with no apertures is normal, so only fall back to + * defaults or native bridge info if we're ignoring _CRS. + */ + if (!pci_use_crs) x86_pci_root_bus_resources(busnum, &resources); bus = pci_create_root_bus(NULL, busnum, &pci_root_ops, sd, &resources); diff --git a/arch/x86/pci/fixup.c b/arch/x86/pci/fixup.c index 6dd89555fbfa..d0e6e403b4f6 100644 --- a/arch/x86/pci/fixup.c +++ b/arch/x86/pci/fixup.c @@ -164,11 +164,11 @@ DECLARE_PCI_FIXUP_RESUME(PCI_VENDOR_ID_VIA, PCI_DEVICE_ID_VIA_8367_0, pci_fixup_ */ static void __devinit pci_fixup_transparent_bridge(struct pci_dev *dev) { - if ((dev->class >> 8) == PCI_CLASS_BRIDGE_PCI && - (dev->device & 0xff00) == 0x2400) + if ((dev->device & 0xff00) == 0x2400) dev->transparent = 1; } -DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, PCI_ANY_ID, pci_fixup_transparent_bridge); +DECLARE_PCI_FIXUP_CLASS_HEADER(PCI_VENDOR_ID_INTEL, PCI_ANY_ID, + PCI_CLASS_BRIDGE_PCI, 8, pci_fixup_transparent_bridge); /* * Fixup for C1 Halt Disconnect problem on nForce2 systems. @@ -322,9 +322,6 @@ static void __devinit pci_fixup_video(struct pci_dev *pdev) struct pci_bus *bus; u16 config; - if ((pdev->class >> 8) != PCI_CLASS_DISPLAY_VGA) - return; - /* Is VGA routed to us? */ bus = pdev->bus; while (bus) { @@ -353,7 +350,8 @@ static void __devinit pci_fixup_video(struct pci_dev *pdev) dev_printk(KERN_DEBUG, &pdev->dev, "Boot video device\n"); } } -DECLARE_PCI_FIXUP_FINAL(PCI_ANY_ID, PCI_ANY_ID, pci_fixup_video); +DECLARE_PCI_FIXUP_CLASS_FINAL(PCI_ANY_ID, PCI_ANY_ID, + PCI_CLASS_DISPLAY_VGA, 8, pci_fixup_video); static const struct dmi_system_id __devinitconst msi_k8t_dmi_table[] = { diff --git a/arch/x86/pci/i386.c b/arch/x86/pci/i386.c index 91821a1a0c3a..831971e731f7 100644 --- a/arch/x86/pci/i386.c +++ b/arch/x86/pci/i386.c @@ -39,6 +39,87 @@ #include <asm/io_apic.h> +/* + * This list of dynamic mappings is for temporarily maintaining + * original BIOS BAR addresses for possible reinstatement. + */ +struct pcibios_fwaddrmap { + struct list_head list; + struct pci_dev *dev; + resource_size_t fw_addr[DEVICE_COUNT_RESOURCE]; +}; + +static LIST_HEAD(pcibios_fwaddrmappings); +static DEFINE_SPINLOCK(pcibios_fwaddrmap_lock); + +/* Must be called with 'pcibios_fwaddrmap_lock' lock held. */ +static struct pcibios_fwaddrmap *pcibios_fwaddrmap_lookup(struct pci_dev *dev) +{ + struct pcibios_fwaddrmap *map; + + WARN_ON(!spin_is_locked(&pcibios_fwaddrmap_lock)); + + list_for_each_entry(map, &pcibios_fwaddrmappings, list) + if (map->dev == dev) + return map; + + return NULL; +} + +static void +pcibios_save_fw_addr(struct pci_dev *dev, int idx, resource_size_t fw_addr) +{ + unsigned long flags; + struct pcibios_fwaddrmap *map; + + spin_lock_irqsave(&pcibios_fwaddrmap_lock, flags); + map = pcibios_fwaddrmap_lookup(dev); + if (!map) { + spin_unlock_irqrestore(&pcibios_fwaddrmap_lock, flags); + map = kzalloc(sizeof(*map), GFP_KERNEL); + if (!map) + return; + + map->dev = pci_dev_get(dev); + map->fw_addr[idx] = fw_addr; + INIT_LIST_HEAD(&map->list); + + spin_lock_irqsave(&pcibios_fwaddrmap_lock, flags); + list_add_tail(&map->list, &pcibios_fwaddrmappings); + } else + map->fw_addr[idx] = fw_addr; + spin_unlock_irqrestore(&pcibios_fwaddrmap_lock, flags); +} + +resource_size_t pcibios_retrieve_fw_addr(struct pci_dev *dev, int idx) +{ + unsigned long flags; + struct pcibios_fwaddrmap *map; + resource_size_t fw_addr = 0; + + spin_lock_irqsave(&pcibios_fwaddrmap_lock, flags); + map = pcibios_fwaddrmap_lookup(dev); + if (map) + fw_addr = map->fw_addr[idx]; + spin_unlock_irqrestore(&pcibios_fwaddrmap_lock, flags); + + return fw_addr; +} + +static void pcibios_fw_addr_list_del(void) +{ + unsigned long flags; + struct pcibios_fwaddrmap *entry, *next; + + spin_lock_irqsave(&pcibios_fwaddrmap_lock, flags); + list_for_each_entry_safe(entry, next, &pcibios_fwaddrmappings, list) { + list_del(&entry->list); + pci_dev_put(entry->dev); + kfree(entry); + } + spin_unlock_irqrestore(&pcibios_fwaddrmap_lock, flags); +} + static int skip_isa_ioresource_align(struct pci_dev *dev) { @@ -182,7 +263,8 @@ static void __init pcibios_allocate_resources(int pass) idx, r, disabled, pass); if (pci_claim_resource(dev, idx) < 0) { /* We'll assign a new address later */ - dev->fw_addr[idx] = r->start; + pcibios_save_fw_addr(dev, + idx, r->start); r->end -= r->start; r->start = 0; } @@ -228,6 +310,7 @@ static int __init pcibios_assign_resources(void) } pci_assign_unassigned_resources(); + pcibios_fw_addr_list_del(); return 0; } diff --git a/arch/x86/pci/mrst.c b/arch/x86/pci/mrst.c index cb29191cee58..140942f66b31 100644 --- a/arch/x86/pci/mrst.c +++ b/arch/x86/pci/mrst.c @@ -43,6 +43,8 @@ #define PCI_FIXED_BAR_4_SIZE 0x14 #define PCI_FIXED_BAR_5_SIZE 0x1c +static int pci_soc_mode = 0; + /** * fixed_bar_cap - return the offset of the fixed BAR cap if found * @bus: PCI bus @@ -148,7 +150,9 @@ static bool type1_access_ok(unsigned int bus, unsigned int devfn, int reg) */ if (reg >= 0x100 || reg == PCI_STATUS || reg == PCI_HEADER_TYPE) return 0; - if (bus == 0 && (devfn == PCI_DEVFN(2, 0) || devfn == PCI_DEVFN(0, 0))) + if (bus == 0 && (devfn == PCI_DEVFN(2, 0) + || devfn == PCI_DEVFN(0, 0) + || devfn == PCI_DEVFN(3, 0))) return 1; return 0; /* langwell on others */ } @@ -231,14 +235,43 @@ struct pci_ops pci_mrst_ops = { */ int __init pci_mrst_init(void) { - printk(KERN_INFO "Moorestown platform detected, using MRST PCI ops\n"); + printk(KERN_INFO "Intel MID platform detected, using MID PCI ops\n"); pci_mmcfg_late_init(); pcibios_enable_irq = mrst_pci_irq_enable; pci_root_ops = pci_mrst_ops; + pci_soc_mode = 1; /* Continue with standard init */ return 1; } +/* Langwell devices are not true pci devices, they are not subject to 10 ms + * d3 to d0 delay required by pci spec. + */ +static void __devinit pci_d3delay_fixup(struct pci_dev *dev) +{ + /* PCI fixups are effectively decided compile time. If we have a dual + SoC/non-SoC kernel we don't want to mangle d3 on non SoC devices */ + if (!pci_soc_mode) + return; + /* true pci devices in lincroft should allow type 1 access, the rest + * are langwell fake pci devices. + */ + if (type1_access_ok(dev->bus->number, dev->devfn, PCI_DEVICE_ID)) + return; + dev->d3_delay = 0; +} +DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL, PCI_ANY_ID, pci_d3delay_fixup); + +static void __devinit mrst_power_off_unused_dev(struct pci_dev *dev) +{ + pci_set_power_state(dev, PCI_D3cold); +} +DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL, 0x0801, mrst_power_off_unused_dev); +DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL, 0x0809, mrst_power_off_unused_dev); +DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL, 0x080C, mrst_power_off_unused_dev); +DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL, 0x0812, mrst_power_off_unused_dev); +DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL, 0x0815, mrst_power_off_unused_dev); + /* * Langwell devices reside at fixed offsets, don't try to move them. */ @@ -248,6 +281,9 @@ static void __devinit pci_fixed_bar_fixup(struct pci_dev *dev) u32 size; int i; + if (!pci_soc_mode) + return; + /* Must have extended configuration space */ if (dev->cfg_size < PCIE_CAP_OFFSET + 4) return; diff --git a/arch/x86/pci/xen.c b/arch/x86/pci/xen.c index d99346ea8fdb..7415aa927913 100644 --- a/arch/x86/pci/xen.c +++ b/arch/x86/pci/xen.c @@ -324,6 +324,32 @@ static int xen_initdom_setup_msi_irqs(struct pci_dev *dev, int nvec, int type) out: return ret; } + +static void xen_initdom_restore_msi_irqs(struct pci_dev *dev, int irq) +{ + int ret = 0; + + if (pci_seg_supported) { + struct physdev_pci_device restore_ext; + + restore_ext.seg = pci_domain_nr(dev->bus); + restore_ext.bus = dev->bus->number; + restore_ext.devfn = dev->devfn; + ret = HYPERVISOR_physdev_op(PHYSDEVOP_restore_msi_ext, + &restore_ext); + if (ret == -ENOSYS) + pci_seg_supported = false; + WARN(ret && ret != -ENOSYS, "restore_msi_ext -> %d\n", ret); + } + if (!pci_seg_supported) { + struct physdev_restore_msi restore; + + restore.bus = dev->bus->number; + restore.devfn = dev->devfn; + ret = HYPERVISOR_physdev_op(PHYSDEVOP_restore_msi, &restore); + WARN(ret && ret != -ENOSYS, "restore_msi -> %d\n", ret); + } +} #endif static void xen_teardown_msi_irqs(struct pci_dev *dev) @@ -446,6 +472,7 @@ int __init pci_xen_initial_domain(void) #ifdef CONFIG_PCI_MSI x86_msi.setup_msi_irqs = xen_initdom_setup_msi_irqs; x86_msi.teardown_msi_irq = xen_teardown_msi_irq; + x86_msi.restore_msi_irqs = xen_initdom_restore_msi_irqs; #endif xen_setup_acpi_sci(); __acpi_register_gsi = acpi_register_gsi_xen; diff --git a/arch/x86/platform/ce4100/falconfalls.dts b/arch/x86/platform/ce4100/falconfalls.dts index e70be38ce039..ce874f872cc6 100644 --- a/arch/x86/platform/ce4100/falconfalls.dts +++ b/arch/x86/platform/ce4100/falconfalls.dts @@ -208,16 +208,19 @@ interrupts = <14 1>; }; - gpio@b,1 { + pcigpio: gpio@b,1 { + #gpio-cells = <2>; + #interrupt-cells = <2>; compatible = "pci8086,2e67.2", "pci8086,2e67", "pciclassff0000", "pciclassff00"; - #gpio-cells = <2>; reg = <0x15900 0x0 0x0 0x0 0x0>; interrupts = <15 1>; + interrupt-controller; gpio-controller; + intel,muxctl = <0>; }; i2c-controller@b,2 { diff --git a/arch/x86/platform/geode/Makefile b/arch/x86/platform/geode/Makefile index 246b788847ff..5b51194f4c8d 100644 --- a/arch/x86/platform/geode/Makefile +++ b/arch/x86/platform/geode/Makefile @@ -1,2 +1,3 @@ obj-$(CONFIG_ALIX) += alix.o obj-$(CONFIG_NET5501) += net5501.o +obj-$(CONFIG_GEOS) += geos.o diff --git a/arch/x86/platform/geode/geos.c b/arch/x86/platform/geode/geos.c new file mode 100644 index 000000000000..c2e6d53558be --- /dev/null +++ b/arch/x86/platform/geode/geos.c @@ -0,0 +1,128 @@ +/* + * System Specific setup for Traverse Technologies GEOS. + * At the moment this means setup of GPIO control of LEDs. + * + * Copyright (C) 2008 Constantin Baranov <const@mimas.ru> + * Copyright (C) 2011 Ed Wildgoose <kernel@wildgooses.com> + * and Philip Prindeville <philipp@redfish-solutions.com> + * + * TODO: There are large similarities with leds-net5501.c + * by Alessandro Zummo <a.zummo@towertech.it> + * In the future leds-net5501.c should be migrated over to platform + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 + * as published by the Free Software Foundation. + */ + +#include <linux/kernel.h> +#include <linux/init.h> +#include <linux/io.h> +#include <linux/string.h> +#include <linux/module.h> +#include <linux/leds.h> +#include <linux/platform_device.h> +#include <linux/gpio.h> +#include <linux/input.h> +#include <linux/gpio_keys.h> +#include <linux/dmi.h> + +#include <asm/geode.h> + +static struct gpio_keys_button geos_gpio_buttons[] = { + { + .code = KEY_RESTART, + .gpio = 3, + .active_low = 1, + .desc = "Reset button", + .type = EV_KEY, + .wakeup = 0, + .debounce_interval = 100, + .can_disable = 0, + } +}; +static struct gpio_keys_platform_data geos_buttons_data = { + .buttons = geos_gpio_buttons, + .nbuttons = ARRAY_SIZE(geos_gpio_buttons), + .poll_interval = 20, +}; + +static struct platform_device geos_buttons_dev = { + .name = "gpio-keys-polled", + .id = 1, + .dev = { + .platform_data = &geos_buttons_data, + } +}; + +static struct gpio_led geos_leds[] = { + { + .name = "geos:1", + .gpio = 6, + .default_trigger = "default-on", + .active_low = 1, + }, + { + .name = "geos:2", + .gpio = 25, + .default_trigger = "default-off", + .active_low = 1, + }, + { + .name = "geos:3", + .gpio = 27, + .default_trigger = "default-off", + .active_low = 1, + }, +}; + +static struct gpio_led_platform_data geos_leds_data = { + .num_leds = ARRAY_SIZE(geos_leds), + .leds = geos_leds, +}; + +static struct platform_device geos_leds_dev = { + .name = "leds-gpio", + .id = -1, + .dev.platform_data = &geos_leds_data, +}; + +static struct __initdata platform_device *geos_devs[] = { + &geos_buttons_dev, + &geos_leds_dev, +}; + +static void __init register_geos(void) +{ + /* Setup LED control through leds-gpio driver */ + platform_add_devices(geos_devs, ARRAY_SIZE(geos_devs)); +} + +static int __init geos_init(void) +{ + const char *vendor, *product; + + if (!is_geode()) + return 0; + + vendor = dmi_get_system_info(DMI_SYS_VENDOR); + if (!vendor || strcmp(vendor, "Traverse Technologies")) + return 0; + + product = dmi_get_system_info(DMI_PRODUCT_NAME); + if (!product || strcmp(product, "Geos")) + return 0; + + printk(KERN_INFO "%s: system is recognized as \"%s %s\"\n", + KBUILD_MODNAME, vendor, product); + + register_geos(); + + return 0; +} + +module_init(geos_init); + +MODULE_AUTHOR("Philip Prindeville <philipp@redfish-solutions.com>"); +MODULE_DESCRIPTION("Traverse Technologies Geos System Setup"); +MODULE_LICENSE("GPL"); diff --git a/arch/x86/platform/mrst/mrst.c b/arch/x86/platform/mrst/mrst.c index 721e65285dce..e0a37233c0af 100644 --- a/arch/x86/platform/mrst/mrst.c +++ b/arch/x86/platform/mrst/mrst.c @@ -28,6 +28,8 @@ #include <linux/module.h> #include <linux/notifier.h> #include <linux/mfd/intel_msic.h> +#include <linux/gpio.h> +#include <linux/i2c/tc35876x.h> #include <asm/setup.h> #include <asm/mpspec_def.h> @@ -675,6 +677,19 @@ static void *msic_thermal_platform_data(void *info) return msic_generic_platform_data(info, INTEL_MSIC_BLOCK_THERMAL); } +/* tc35876x DSI-LVDS bridge chip and panel platform data */ +static void *tc35876x_platform_data(void *data) +{ + static struct tc35876x_platform_data pdata; + + /* gpio pins set to -1 will not be used by the driver */ + pdata.gpio_bridge_reset = get_gpio_by_name("LCMB_RXEN"); + pdata.gpio_panel_bl_en = get_gpio_by_name("6S6P_BL_EN"); + pdata.gpio_panel_vadd = get_gpio_by_name("EN_VREG_LCD_V3P3"); + + return &pdata; +} + static const struct devs_id __initconst device_ids[] = { {"bma023", SFI_DEV_TYPE_I2C, 1, &no_platform_data}, {"pmic_gpio", SFI_DEV_TYPE_SPI, 1, &pmic_gpio_platform_data}, @@ -687,6 +702,7 @@ static const struct devs_id __initconst device_ids[] = { {"i2c_accel", SFI_DEV_TYPE_I2C, 0, &lis331dl_platform_data}, {"pmic_audio", SFI_DEV_TYPE_IPC, 1, &no_platform_data}, {"mpu3050", SFI_DEV_TYPE_I2C, 1, &mpu3050_platform_data}, + {"i2c_disp_brig", SFI_DEV_TYPE_I2C, 0, &tc35876x_platform_data}, /* MSIC subdevices */ {"msic_battery", SFI_DEV_TYPE_IPC, 1, &msic_battery_platform_data}, diff --git a/arch/x86/power/cpu.c b/arch/x86/power/cpu.c index 4889655ba784..47936830968c 100644 --- a/arch/x86/power/cpu.c +++ b/arch/x86/power/cpu.c @@ -115,7 +115,7 @@ static void __save_processor_state(struct saved_context *ctxt) void save_processor_state(void) { __save_processor_state(&saved_context); - save_sched_clock_state(); + x86_platform.save_sched_clock_state(); } #ifdef CONFIG_X86_32 EXPORT_SYMBOL(save_processor_state); @@ -231,8 +231,8 @@ static void __restore_processor_state(struct saved_context *ctxt) /* Needed by apm.c */ void restore_processor_state(void) { + x86_platform.restore_sched_clock_state(); __restore_processor_state(&saved_context); - restore_sched_clock_state(); } #ifdef CONFIG_X86_32 EXPORT_SYMBOL(restore_processor_state); diff --git a/arch/x86/power/hibernate_32.c b/arch/x86/power/hibernate_32.c index 3769079874d8..74202c1910cd 100644 --- a/arch/x86/power/hibernate_32.c +++ b/arch/x86/power/hibernate_32.c @@ -10,7 +10,6 @@ #include <linux/suspend.h> #include <linux/bootmem.h> -#include <asm/system.h> #include <asm/page.h> #include <asm/pgtable.h> #include <asm/mmzone.h> diff --git a/arch/x86/syscalls/Makefile b/arch/x86/syscalls/Makefile index 564b2476fede..3236aebc828d 100644 --- a/arch/x86/syscalls/Makefile +++ b/arch/x86/syscalls/Makefile @@ -10,8 +10,10 @@ syshdr := $(srctree)/$(src)/syscallhdr.sh systbl := $(srctree)/$(src)/syscalltbl.sh quiet_cmd_syshdr = SYSHDR $@ - cmd_syshdr = $(CONFIG_SHELL) '$(syshdr)' $< $@ \ - $(syshdr_abi_$(basetarget)) $(syshdr_pfx_$(basetarget)) + cmd_syshdr = $(CONFIG_SHELL) '$(syshdr)' '$<' '$@' \ + '$(syshdr_abi_$(basetarget))' \ + '$(syshdr_pfx_$(basetarget))' \ + '$(syshdr_offset_$(basetarget))' quiet_cmd_systbl = SYSTBL $@ cmd_systbl = $(CONFIG_SHELL) '$(systbl)' $< $@ @@ -24,18 +26,28 @@ syshdr_pfx_unistd_32_ia32 := ia32_ $(out)/unistd_32_ia32.h: $(syscall32) $(syshdr) $(call if_changed,syshdr) -syshdr_abi_unistd_64 := 64 +syshdr_abi_unistd_x32 := common,x32 +syshdr_offset_unistd_x32 := __X32_SYSCALL_BIT +$(out)/unistd_x32.h: $(syscall64) $(syshdr) + $(call if_changed,syshdr) + +syshdr_abi_unistd_64 := common,64 $(out)/unistd_64.h: $(syscall64) $(syshdr) $(call if_changed,syshdr) +syshdr_abi_unistd_64_x32 := x32 +syshdr_pfx_unistd_64_x32 := x32_ +$(out)/unistd_64_x32.h: $(syscall64) $(syshdr) + $(call if_changed,syshdr) + $(out)/syscalls_32.h: $(syscall32) $(systbl) $(call if_changed,systbl) $(out)/syscalls_64.h: $(syscall64) $(systbl) $(call if_changed,systbl) -syshdr-y += unistd_32.h unistd_64.h +syshdr-y += unistd_32.h unistd_64.h unistd_x32.h syshdr-y += syscalls_32.h -syshdr-$(CONFIG_X86_64) += unistd_32_ia32.h +syshdr-$(CONFIG_X86_64) += unistd_32_ia32.h unistd_64_x32.h syshdr-$(CONFIG_X86_64) += syscalls_64.h targets += $(syshdr-y) diff --git a/arch/x86/syscalls/syscall_32.tbl b/arch/x86/syscalls/syscall_32.tbl index e7e67cc3c14b..29f9f0554f7d 100644 --- a/arch/x86/syscalls/syscall_32.tbl +++ b/arch/x86/syscalls/syscall_32.tbl @@ -181,7 +181,7 @@ 172 i386 prctl sys_prctl 173 i386 rt_sigreturn ptregs_rt_sigreturn stub32_rt_sigreturn 174 i386 rt_sigaction sys_rt_sigaction sys32_rt_sigaction -175 i386 rt_sigprocmask sys_rt_sigprocmask sys32_rt_sigprocmask +175 i386 rt_sigprocmask sys_rt_sigprocmask 176 i386 rt_sigpending sys_rt_sigpending sys32_rt_sigpending 177 i386 rt_sigtimedwait sys_rt_sigtimedwait compat_sys_rt_sigtimedwait 178 i386 rt_sigqueueinfo sys_rt_sigqueueinfo sys32_rt_sigqueueinfo diff --git a/arch/x86/syscalls/syscall_64.tbl b/arch/x86/syscalls/syscall_64.tbl index b440a8f7eefa..dd29a9ea27c5 100644 --- a/arch/x86/syscalls/syscall_64.tbl +++ b/arch/x86/syscalls/syscall_64.tbl @@ -4,317 +4,350 @@ # The format is: # <number> <abi> <name> <entry point> # -# The abi is always "64" for this file (for now.) +# The abi is "common", "64" or "x32" for this file. # -0 64 read sys_read -1 64 write sys_write -2 64 open sys_open -3 64 close sys_close -4 64 stat sys_newstat -5 64 fstat sys_newfstat -6 64 lstat sys_newlstat -7 64 poll sys_poll -8 64 lseek sys_lseek -9 64 mmap sys_mmap -10 64 mprotect sys_mprotect -11 64 munmap sys_munmap -12 64 brk sys_brk +0 common read sys_read +1 common write sys_write +2 common open sys_open +3 common close sys_close +4 common stat sys_newstat +5 common fstat sys_newfstat +6 common lstat sys_newlstat +7 common poll sys_poll +8 common lseek sys_lseek +9 common mmap sys_mmap +10 common mprotect sys_mprotect +11 common munmap sys_munmap +12 common brk sys_brk 13 64 rt_sigaction sys_rt_sigaction -14 64 rt_sigprocmask sys_rt_sigprocmask +14 common rt_sigprocmask sys_rt_sigprocmask 15 64 rt_sigreturn stub_rt_sigreturn 16 64 ioctl sys_ioctl -17 64 pread64 sys_pread64 -18 64 pwrite64 sys_pwrite64 +17 common pread64 sys_pread64 +18 common pwrite64 sys_pwrite64 19 64 readv sys_readv 20 64 writev sys_writev -21 64 access sys_access -22 64 pipe sys_pipe -23 64 select sys_select -24 64 sched_yield sys_sched_yield -25 64 mremap sys_mremap -26 64 msync sys_msync -27 64 mincore sys_mincore -28 64 madvise sys_madvise -29 64 shmget sys_shmget -30 64 shmat sys_shmat -31 64 shmctl sys_shmctl -32 64 dup sys_dup -33 64 dup2 sys_dup2 -34 64 pause sys_pause -35 64 nanosleep sys_nanosleep -36 64 getitimer sys_getitimer -37 64 alarm sys_alarm -38 64 setitimer sys_setitimer -39 64 getpid sys_getpid -40 64 sendfile sys_sendfile64 -41 64 socket sys_socket -42 64 connect sys_connect -43 64 accept sys_accept -44 64 sendto sys_sendto +21 common access sys_access +22 common pipe sys_pipe +23 common select sys_select +24 common sched_yield sys_sched_yield +25 common mremap sys_mremap +26 common msync sys_msync +27 common mincore sys_mincore +28 common madvise sys_madvise +29 common shmget sys_shmget +30 common shmat sys_shmat +31 common shmctl sys_shmctl +32 common dup sys_dup +33 common dup2 sys_dup2 +34 common pause sys_pause +35 common nanosleep sys_nanosleep +36 common getitimer sys_getitimer +37 common alarm sys_alarm +38 common setitimer sys_setitimer +39 common getpid sys_getpid +40 common sendfile sys_sendfile64 +41 common socket sys_socket +42 common connect sys_connect +43 common accept sys_accept +44 common sendto sys_sendto 45 64 recvfrom sys_recvfrom 46 64 sendmsg sys_sendmsg 47 64 recvmsg sys_recvmsg -48 64 shutdown sys_shutdown -49 64 bind sys_bind -50 64 listen sys_listen -51 64 getsockname sys_getsockname -52 64 getpeername sys_getpeername -53 64 socketpair sys_socketpair -54 64 setsockopt sys_setsockopt -55 64 getsockopt sys_getsockopt -56 64 clone stub_clone -57 64 fork stub_fork -58 64 vfork stub_vfork +48 common shutdown sys_shutdown +49 common bind sys_bind +50 common listen sys_listen +51 common getsockname sys_getsockname +52 common getpeername sys_getpeername +53 common socketpair sys_socketpair +54 common setsockopt sys_setsockopt +55 common getsockopt sys_getsockopt +56 common clone stub_clone +57 common fork stub_fork +58 common vfork stub_vfork 59 64 execve stub_execve -60 64 exit sys_exit -61 64 wait4 sys_wait4 -62 64 kill sys_kill -63 64 uname sys_newuname -64 64 semget sys_semget -65 64 semop sys_semop -66 64 semctl sys_semctl -67 64 shmdt sys_shmdt -68 64 msgget sys_msgget -69 64 msgsnd sys_msgsnd -70 64 msgrcv sys_msgrcv -71 64 msgctl sys_msgctl -72 64 fcntl sys_fcntl -73 64 flock sys_flock -74 64 fsync sys_fsync -75 64 fdatasync sys_fdatasync -76 64 truncate sys_truncate -77 64 ftruncate sys_ftruncate -78 64 getdents sys_getdents -79 64 getcwd sys_getcwd -80 64 chdir sys_chdir -81 64 fchdir sys_fchdir -82 64 rename sys_rename -83 64 mkdir sys_mkdir -84 64 rmdir sys_rmdir -85 64 creat sys_creat -86 64 link sys_link -87 64 unlink sys_unlink -88 64 symlink sys_symlink -89 64 readlink sys_readlink -90 64 chmod sys_chmod -91 64 fchmod sys_fchmod -92 64 chown sys_chown -93 64 fchown sys_fchown -94 64 lchown sys_lchown -95 64 umask sys_umask -96 64 gettimeofday sys_gettimeofday -97 64 getrlimit sys_getrlimit -98 64 getrusage sys_getrusage -99 64 sysinfo sys_sysinfo -100 64 times sys_times +60 common exit sys_exit +61 common wait4 sys_wait4 +62 common kill sys_kill +63 common uname sys_newuname +64 common semget sys_semget +65 common semop sys_semop +66 common semctl sys_semctl +67 common shmdt sys_shmdt +68 common msgget sys_msgget +69 common msgsnd sys_msgsnd +70 common msgrcv sys_msgrcv +71 common msgctl sys_msgctl +72 common fcntl sys_fcntl +73 common flock sys_flock +74 common fsync sys_fsync +75 common fdatasync sys_fdatasync +76 common truncate sys_truncate +77 common ftruncate sys_ftruncate +78 common getdents sys_getdents +79 common getcwd sys_getcwd +80 common chdir sys_chdir +81 common fchdir sys_fchdir +82 common rename sys_rename +83 common mkdir sys_mkdir +84 common rmdir sys_rmdir +85 common creat sys_creat +86 common link sys_link +87 common unlink sys_unlink +88 common symlink sys_symlink +89 common readlink sys_readlink +90 common chmod sys_chmod +91 common fchmod sys_fchmod +92 common chown sys_chown +93 common fchown sys_fchown +94 common lchown sys_lchown +95 common umask sys_umask +96 common gettimeofday sys_gettimeofday +97 common getrlimit sys_getrlimit +98 common getrusage sys_getrusage +99 common sysinfo sys_sysinfo +100 common times sys_times 101 64 ptrace sys_ptrace -102 64 getuid sys_getuid -103 64 syslog sys_syslog -104 64 getgid sys_getgid -105 64 setuid sys_setuid -106 64 setgid sys_setgid -107 64 geteuid sys_geteuid -108 64 getegid sys_getegid -109 64 setpgid sys_setpgid -110 64 getppid sys_getppid -111 64 getpgrp sys_getpgrp -112 64 setsid sys_setsid -113 64 setreuid sys_setreuid -114 64 setregid sys_setregid -115 64 getgroups sys_getgroups -116 64 setgroups sys_setgroups -117 64 setresuid sys_setresuid -118 64 getresuid sys_getresuid -119 64 setresgid sys_setresgid -120 64 getresgid sys_getresgid -121 64 getpgid sys_getpgid -122 64 setfsuid sys_setfsuid -123 64 setfsgid sys_setfsgid -124 64 getsid sys_getsid -125 64 capget sys_capget -126 64 capset sys_capset +102 common getuid sys_getuid +103 common syslog sys_syslog +104 common getgid sys_getgid +105 common setuid sys_setuid +106 common setgid sys_setgid +107 common geteuid sys_geteuid +108 common getegid sys_getegid +109 common setpgid sys_setpgid +110 common getppid sys_getppid +111 common getpgrp sys_getpgrp +112 common setsid sys_setsid +113 common setreuid sys_setreuid +114 common setregid sys_setregid +115 common getgroups sys_getgroups +116 common setgroups sys_setgroups +117 common setresuid sys_setresuid +118 common getresuid sys_getresuid +119 common setresgid sys_setresgid +120 common getresgid sys_getresgid +121 common getpgid sys_getpgid +122 common setfsuid sys_setfsuid +123 common setfsgid sys_setfsgid +124 common getsid sys_getsid +125 common capget sys_capget +126 common capset sys_capset 127 64 rt_sigpending sys_rt_sigpending 128 64 rt_sigtimedwait sys_rt_sigtimedwait 129 64 rt_sigqueueinfo sys_rt_sigqueueinfo -130 64 rt_sigsuspend sys_rt_sigsuspend +130 common rt_sigsuspend sys_rt_sigsuspend 131 64 sigaltstack stub_sigaltstack -132 64 utime sys_utime -133 64 mknod sys_mknod +132 common utime sys_utime +133 common mknod sys_mknod 134 64 uselib -135 64 personality sys_personality -136 64 ustat sys_ustat -137 64 statfs sys_statfs -138 64 fstatfs sys_fstatfs -139 64 sysfs sys_sysfs -140 64 getpriority sys_getpriority -141 64 setpriority sys_setpriority -142 64 sched_setparam sys_sched_setparam -143 64 sched_getparam sys_sched_getparam -144 64 sched_setscheduler sys_sched_setscheduler -145 64 sched_getscheduler sys_sched_getscheduler -146 64 sched_get_priority_max sys_sched_get_priority_max -147 64 sched_get_priority_min sys_sched_get_priority_min -148 64 sched_rr_get_interval sys_sched_rr_get_interval -149 64 mlock sys_mlock -150 64 munlock sys_munlock -151 64 mlockall sys_mlockall -152 64 munlockall sys_munlockall -153 64 vhangup sys_vhangup -154 64 modify_ldt sys_modify_ldt -155 64 pivot_root sys_pivot_root +135 common personality sys_personality +136 common ustat sys_ustat +137 common statfs sys_statfs +138 common fstatfs sys_fstatfs +139 common sysfs sys_sysfs +140 common getpriority sys_getpriority +141 common setpriority sys_setpriority +142 common sched_setparam sys_sched_setparam +143 common sched_getparam sys_sched_getparam +144 common sched_setscheduler sys_sched_setscheduler +145 common sched_getscheduler sys_sched_getscheduler +146 common sched_get_priority_max sys_sched_get_priority_max +147 common sched_get_priority_min sys_sched_get_priority_min +148 common sched_rr_get_interval sys_sched_rr_get_interval +149 common mlock sys_mlock +150 common munlock sys_munlock +151 common mlockall sys_mlockall +152 common munlockall sys_munlockall +153 common vhangup sys_vhangup +154 common modify_ldt sys_modify_ldt +155 common pivot_root sys_pivot_root 156 64 _sysctl sys_sysctl -157 64 prctl sys_prctl -158 64 arch_prctl sys_arch_prctl -159 64 adjtimex sys_adjtimex -160 64 setrlimit sys_setrlimit -161 64 chroot sys_chroot -162 64 sync sys_sync -163 64 acct sys_acct -164 64 settimeofday sys_settimeofday -165 64 mount sys_mount -166 64 umount2 sys_umount -167 64 swapon sys_swapon -168 64 swapoff sys_swapoff -169 64 reboot sys_reboot -170 64 sethostname sys_sethostname -171 64 setdomainname sys_setdomainname -172 64 iopl stub_iopl -173 64 ioperm sys_ioperm +157 common prctl sys_prctl +158 common arch_prctl sys_arch_prctl +159 common adjtimex sys_adjtimex +160 common setrlimit sys_setrlimit +161 common chroot sys_chroot +162 common sync sys_sync +163 common acct sys_acct +164 common settimeofday sys_settimeofday +165 common mount sys_mount +166 common umount2 sys_umount +167 common swapon sys_swapon +168 common swapoff sys_swapoff +169 common reboot sys_reboot +170 common sethostname sys_sethostname +171 common setdomainname sys_setdomainname +172 common iopl stub_iopl +173 common ioperm sys_ioperm 174 64 create_module -175 64 init_module sys_init_module -176 64 delete_module sys_delete_module +175 common init_module sys_init_module +176 common delete_module sys_delete_module 177 64 get_kernel_syms 178 64 query_module -179 64 quotactl sys_quotactl +179 common quotactl sys_quotactl 180 64 nfsservctl -181 64 getpmsg -182 64 putpmsg -183 64 afs_syscall -184 64 tuxcall -185 64 security -186 64 gettid sys_gettid -187 64 readahead sys_readahead -188 64 setxattr sys_setxattr -189 64 lsetxattr sys_lsetxattr -190 64 fsetxattr sys_fsetxattr -191 64 getxattr sys_getxattr -192 64 lgetxattr sys_lgetxattr -193 64 fgetxattr sys_fgetxattr -194 64 listxattr sys_listxattr -195 64 llistxattr sys_llistxattr -196 64 flistxattr sys_flistxattr -197 64 removexattr sys_removexattr -198 64 lremovexattr sys_lremovexattr -199 64 fremovexattr sys_fremovexattr -200 64 tkill sys_tkill -201 64 time sys_time -202 64 futex sys_futex -203 64 sched_setaffinity sys_sched_setaffinity -204 64 sched_getaffinity sys_sched_getaffinity +181 common getpmsg +182 common putpmsg +183 common afs_syscall +184 common tuxcall +185 common security +186 common gettid sys_gettid +187 common readahead sys_readahead +188 common setxattr sys_setxattr +189 common lsetxattr sys_lsetxattr +190 common fsetxattr sys_fsetxattr +191 common getxattr sys_getxattr +192 common lgetxattr sys_lgetxattr +193 common fgetxattr sys_fgetxattr +194 common listxattr sys_listxattr +195 common llistxattr sys_llistxattr +196 common flistxattr sys_flistxattr +197 common removexattr sys_removexattr +198 common lremovexattr sys_lremovexattr +199 common fremovexattr sys_fremovexattr +200 common tkill sys_tkill +201 common time sys_time +202 common futex sys_futex +203 common sched_setaffinity sys_sched_setaffinity +204 common sched_getaffinity sys_sched_getaffinity 205 64 set_thread_area -206 64 io_setup sys_io_setup -207 64 io_destroy sys_io_destroy -208 64 io_getevents sys_io_getevents -209 64 io_submit sys_io_submit -210 64 io_cancel sys_io_cancel +206 common io_setup sys_io_setup +207 common io_destroy sys_io_destroy +208 common io_getevents sys_io_getevents +209 common io_submit sys_io_submit +210 common io_cancel sys_io_cancel 211 64 get_thread_area -212 64 lookup_dcookie sys_lookup_dcookie -213 64 epoll_create sys_epoll_create +212 common lookup_dcookie sys_lookup_dcookie +213 common epoll_create sys_epoll_create 214 64 epoll_ctl_old 215 64 epoll_wait_old -216 64 remap_file_pages sys_remap_file_pages -217 64 getdents64 sys_getdents64 -218 64 set_tid_address sys_set_tid_address -219 64 restart_syscall sys_restart_syscall -220 64 semtimedop sys_semtimedop -221 64 fadvise64 sys_fadvise64 +216 common remap_file_pages sys_remap_file_pages +217 common getdents64 sys_getdents64 +218 common set_tid_address sys_set_tid_address +219 common restart_syscall sys_restart_syscall +220 common semtimedop sys_semtimedop +221 common fadvise64 sys_fadvise64 222 64 timer_create sys_timer_create -223 64 timer_settime sys_timer_settime -224 64 timer_gettime sys_timer_gettime -225 64 timer_getoverrun sys_timer_getoverrun -226 64 timer_delete sys_timer_delete -227 64 clock_settime sys_clock_settime -228 64 clock_gettime sys_clock_gettime -229 64 clock_getres sys_clock_getres -230 64 clock_nanosleep sys_clock_nanosleep -231 64 exit_group sys_exit_group -232 64 epoll_wait sys_epoll_wait -233 64 epoll_ctl sys_epoll_ctl -234 64 tgkill sys_tgkill -235 64 utimes sys_utimes +223 common timer_settime sys_timer_settime +224 common timer_gettime sys_timer_gettime +225 common timer_getoverrun sys_timer_getoverrun +226 common timer_delete sys_timer_delete +227 common clock_settime sys_clock_settime +228 common clock_gettime sys_clock_gettime +229 common clock_getres sys_clock_getres +230 common clock_nanosleep sys_clock_nanosleep +231 common exit_group sys_exit_group +232 common epoll_wait sys_epoll_wait +233 common epoll_ctl sys_epoll_ctl +234 common tgkill sys_tgkill +235 common utimes sys_utimes 236 64 vserver -237 64 mbind sys_mbind -238 64 set_mempolicy sys_set_mempolicy -239 64 get_mempolicy sys_get_mempolicy -240 64 mq_open sys_mq_open -241 64 mq_unlink sys_mq_unlink -242 64 mq_timedsend sys_mq_timedsend -243 64 mq_timedreceive sys_mq_timedreceive +237 common mbind sys_mbind +238 common set_mempolicy sys_set_mempolicy +239 common get_mempolicy sys_get_mempolicy +240 common mq_open sys_mq_open +241 common mq_unlink sys_mq_unlink +242 common mq_timedsend sys_mq_timedsend +243 common mq_timedreceive sys_mq_timedreceive 244 64 mq_notify sys_mq_notify -245 64 mq_getsetattr sys_mq_getsetattr +245 common mq_getsetattr sys_mq_getsetattr 246 64 kexec_load sys_kexec_load 247 64 waitid sys_waitid -248 64 add_key sys_add_key -249 64 request_key sys_request_key -250 64 keyctl sys_keyctl -251 64 ioprio_set sys_ioprio_set -252 64 ioprio_get sys_ioprio_get -253 64 inotify_init sys_inotify_init -254 64 inotify_add_watch sys_inotify_add_watch -255 64 inotify_rm_watch sys_inotify_rm_watch -256 64 migrate_pages sys_migrate_pages -257 64 openat sys_openat -258 64 mkdirat sys_mkdirat -259 64 mknodat sys_mknodat -260 64 fchownat sys_fchownat -261 64 futimesat sys_futimesat -262 64 newfstatat sys_newfstatat -263 64 unlinkat sys_unlinkat -264 64 renameat sys_renameat -265 64 linkat sys_linkat -266 64 symlinkat sys_symlinkat -267 64 readlinkat sys_readlinkat -268 64 fchmodat sys_fchmodat -269 64 faccessat sys_faccessat -270 64 pselect6 sys_pselect6 -271 64 ppoll sys_ppoll -272 64 unshare sys_unshare +248 common add_key sys_add_key +249 common request_key sys_request_key +250 common keyctl sys_keyctl +251 common ioprio_set sys_ioprio_set +252 common ioprio_get sys_ioprio_get +253 common inotify_init sys_inotify_init +254 common inotify_add_watch sys_inotify_add_watch +255 common inotify_rm_watch sys_inotify_rm_watch +256 common migrate_pages sys_migrate_pages +257 common openat sys_openat +258 common mkdirat sys_mkdirat +259 common mknodat sys_mknodat +260 common fchownat sys_fchownat +261 common futimesat sys_futimesat +262 common newfstatat sys_newfstatat +263 common unlinkat sys_unlinkat +264 common renameat sys_renameat +265 common linkat sys_linkat +266 common symlinkat sys_symlinkat +267 common readlinkat sys_readlinkat +268 common fchmodat sys_fchmodat +269 common faccessat sys_faccessat +270 common pselect6 sys_pselect6 +271 common ppoll sys_ppoll +272 common unshare sys_unshare 273 64 set_robust_list sys_set_robust_list 274 64 get_robust_list sys_get_robust_list -275 64 splice sys_splice -276 64 tee sys_tee -277 64 sync_file_range sys_sync_file_range +275 common splice sys_splice +276 common tee sys_tee +277 common sync_file_range sys_sync_file_range 278 64 vmsplice sys_vmsplice 279 64 move_pages sys_move_pages -280 64 utimensat sys_utimensat -281 64 epoll_pwait sys_epoll_pwait -282 64 signalfd sys_signalfd -283 64 timerfd_create sys_timerfd_create -284 64 eventfd sys_eventfd -285 64 fallocate sys_fallocate -286 64 timerfd_settime sys_timerfd_settime -287 64 timerfd_gettime sys_timerfd_gettime -288 64 accept4 sys_accept4 -289 64 signalfd4 sys_signalfd4 -290 64 eventfd2 sys_eventfd2 -291 64 epoll_create1 sys_epoll_create1 -292 64 dup3 sys_dup3 -293 64 pipe2 sys_pipe2 -294 64 inotify_init1 sys_inotify_init1 +280 common utimensat sys_utimensat +281 common epoll_pwait sys_epoll_pwait +282 common signalfd sys_signalfd +283 common timerfd_create sys_timerfd_create +284 common eventfd sys_eventfd +285 common fallocate sys_fallocate +286 common timerfd_settime sys_timerfd_settime +287 common timerfd_gettime sys_timerfd_gettime +288 common accept4 sys_accept4 +289 common signalfd4 sys_signalfd4 +290 common eventfd2 sys_eventfd2 +291 common epoll_create1 sys_epoll_create1 +292 common dup3 sys_dup3 +293 common pipe2 sys_pipe2 +294 common inotify_init1 sys_inotify_init1 295 64 preadv sys_preadv 296 64 pwritev sys_pwritev 297 64 rt_tgsigqueueinfo sys_rt_tgsigqueueinfo -298 64 perf_event_open sys_perf_event_open +298 common perf_event_open sys_perf_event_open 299 64 recvmmsg sys_recvmmsg -300 64 fanotify_init sys_fanotify_init -301 64 fanotify_mark sys_fanotify_mark -302 64 prlimit64 sys_prlimit64 -303 64 name_to_handle_at sys_name_to_handle_at -304 64 open_by_handle_at sys_open_by_handle_at -305 64 clock_adjtime sys_clock_adjtime -306 64 syncfs sys_syncfs +300 common fanotify_init sys_fanotify_init +301 common fanotify_mark sys_fanotify_mark +302 common prlimit64 sys_prlimit64 +303 common name_to_handle_at sys_name_to_handle_at +304 common open_by_handle_at sys_open_by_handle_at +305 common clock_adjtime sys_clock_adjtime +306 common syncfs sys_syncfs 307 64 sendmmsg sys_sendmmsg -308 64 setns sys_setns -309 64 getcpu sys_getcpu +308 common setns sys_setns +309 common getcpu sys_getcpu 310 64 process_vm_readv sys_process_vm_readv 311 64 process_vm_writev sys_process_vm_writev +# +# x32-specific system call numbers start at 512 to avoid cache impact +# for native 64-bit operation. +# +512 x32 rt_sigaction sys32_rt_sigaction +513 x32 rt_sigreturn stub_x32_rt_sigreturn +514 x32 ioctl compat_sys_ioctl +515 x32 readv compat_sys_readv +516 x32 writev compat_sys_writev +517 x32 recvfrom compat_sys_recvfrom +518 x32 sendmsg compat_sys_sendmsg +519 x32 recvmsg compat_sys_recvmsg +520 x32 execve stub_x32_execve +521 x32 ptrace compat_sys_ptrace +522 x32 rt_sigpending sys32_rt_sigpending +523 x32 rt_sigtimedwait compat_sys_rt_sigtimedwait +524 x32 rt_sigqueueinfo sys32_rt_sigqueueinfo +525 x32 sigaltstack stub_x32_sigaltstack +526 x32 timer_create compat_sys_timer_create +527 x32 mq_notify compat_sys_mq_notify +528 x32 kexec_load compat_sys_kexec_load +529 x32 waitid compat_sys_waitid +530 x32 set_robust_list compat_sys_set_robust_list +531 x32 get_robust_list compat_sys_get_robust_list +532 x32 vmsplice compat_sys_vmsplice +533 x32 move_pages compat_sys_move_pages +534 x32 preadv compat_sys_preadv64 +535 x32 pwritev compat_sys_pwritev64 +536 x32 rt_tgsigqueueinfo compat_sys_rt_tgsigqueueinfo +537 x32 recvmmsg compat_sys_recvmmsg +538 x32 sendmmsg compat_sys_sendmmsg +539 x32 process_vm_readv compat_sys_process_vm_readv +540 x32 process_vm_writev compat_sys_process_vm_writev diff --git a/arch/x86/um/Kconfig b/arch/x86/um/Kconfig index b2b54d2edf53..9926e11a772d 100644 --- a/arch/x86/um/Kconfig +++ b/arch/x86/um/Kconfig @@ -15,8 +15,8 @@ config UML_X86 select GENERIC_FIND_FIRST_BIT config 64BIT - bool - default SUBARCH = "x86_64" + bool "64-bit kernel" if SUBARCH = "x86" + default SUBARCH != "i386" config X86_32 def_bool !64BIT diff --git a/arch/x86/um/asm/processor.h b/arch/x86/um/asm/processor.h index 2c32df6fe231..04f82e020f2b 100644 --- a/arch/x86/um/asm/processor.h +++ b/arch/x86/um/asm/processor.h @@ -17,6 +17,16 @@ #define ARCH_IS_STACKGROW(address) \ (address + 65536 + 32 * sizeof(unsigned long) >= UPT_SP(¤t->thread.regs.regs)) +#include <asm/user.h> + +/* REP NOP (PAUSE) is a good thing to insert into busy-wait loops. */ +static inline void rep_nop(void) +{ + __asm__ __volatile__("rep;nop": : :"memory"); +} + +#define cpu_relax() rep_nop() + #include <asm/processor-generic.h> #endif diff --git a/arch/x86/um/asm/processor_32.h b/arch/x86/um/asm/processor_32.h index 018f732704dd..6c6689e574ce 100644 --- a/arch/x86/um/asm/processor_32.h +++ b/arch/x86/um/asm/processor_32.h @@ -45,16 +45,6 @@ static inline void arch_copy_thread(struct arch_thread *from, memcpy(&to->tls_array, &from->tls_array, sizeof(from->tls_array)); } -#include <asm/user.h> - -/* REP NOP (PAUSE) is a good thing to insert into busy-wait loops. */ -static inline void rep_nop(void) -{ - __asm__ __volatile__("rep;nop": : :"memory"); -} - -#define cpu_relax() rep_nop() - /* * Default implementation of macro that returns current * instruction pointer ("program counter"). Stolen diff --git a/arch/x86/um/asm/processor_64.h b/arch/x86/um/asm/processor_64.h index 61de92d916c3..4b02a8455bd1 100644 --- a/arch/x86/um/asm/processor_64.h +++ b/arch/x86/um/asm/processor_64.h @@ -14,14 +14,6 @@ struct arch_thread { struct faultinfo faultinfo; }; -/* REP NOP (PAUSE) is a good thing to insert into busy-wait loops. */ -static inline void rep_nop(void) -{ - __asm__ __volatile__("rep;nop": : :"memory"); -} - -#define cpu_relax() rep_nop() - #define INIT_ARCH_THREAD { .debugregs = { [ 0 ... 7 ] = 0 }, \ .debugregs_seq = 0, \ .fs = 0, \ @@ -37,8 +29,6 @@ static inline void arch_copy_thread(struct arch_thread *from, to->fs = from->fs; } -#include <asm/user.h> - #define current_text_addr() \ ({ void *pc; __asm__("movq $1f,%0\n1:":"=g" (pc)); pc; }) diff --git a/arch/x86/um/bugs_32.c b/arch/x86/um/bugs_32.c index a1fba5fb9dbe..17d88cf2c6c4 100644 --- a/arch/x86/um/bugs_32.c +++ b/arch/x86/um/bugs_32.c @@ -13,8 +13,6 @@ static int host_has_cmov = 1; static jmp_buf cmov_test_return; -#define TASK_PID(task) *((int *) &(((char *) (task))[HOST_TASK_PID])) - static void cmov_sigill_test_handler(int sig) { host_has_cmov = 0; @@ -51,7 +49,7 @@ void arch_examine_signal(int sig, struct uml_pt_regs *regs) * This is testing for a cmov (0x0f 0x4x) instruction causing a * SIGILL in init. */ - if ((sig != SIGILL) || (TASK_PID(get_current()) != 1)) + if ((sig != SIGILL) || (get_current_pid() != 1)) return; if (copy_from_user_proc(tmp, (void *) UPT_IP(regs), 2)) { diff --git a/arch/x86/um/mem_32.c b/arch/x86/um/mem_32.c index 639900a6fde9..f40281e5d6a2 100644 --- a/arch/x86/um/mem_32.c +++ b/arch/x86/um/mem_32.c @@ -23,14 +23,6 @@ static int __init gate_vma_init(void) gate_vma.vm_flags = VM_READ | VM_MAYREAD | VM_EXEC | VM_MAYEXEC; gate_vma.vm_page_prot = __P101; - /* - * Make sure the vDSO gets into every core dump. - * Dumping its contents makes post-mortem fully interpretable later - * without matching up the same kernel and hardware config to see - * what PC values meant. - */ - gate_vma.vm_flags |= VM_ALWAYSDUMP; - return 0; } __initcall(gate_vma_init); diff --git a/arch/x86/um/sys_call_table_64.c b/arch/x86/um/sys_call_table_64.c index fe626c3ba01b..9924776f4265 100644 --- a/arch/x86/um/sys_call_table_64.c +++ b/arch/x86/um/sys_call_table_64.c @@ -35,6 +35,9 @@ #define stub_sigaltstack sys_sigaltstack #define stub_rt_sigreturn sys_rt_sigreturn +#define __SYSCALL_COMMON(nr, sym, compat) __SYSCALL_64(nr, sym, compat) +#define __SYSCALL_X32(nr, sym, compat) /* Not supported */ + #define __SYSCALL_64(nr, sym, compat) extern asmlinkage void sym(void) ; #include <asm/syscalls_64.h> diff --git a/arch/x86/um/user-offsets.c b/arch/x86/um/user-offsets.c index 5edf4f4bbf53..ce7e3607a870 100644 --- a/arch/x86/um/user-offsets.c +++ b/arch/x86/um/user-offsets.c @@ -15,6 +15,8 @@ static char syscalls[] = { }; #else #define __SYSCALL_64(nr, sym, compat) [nr] = 1, +#define __SYSCALL_COMMON(nr, sym, compat) [nr] = 1, +#define __SYSCALL_X32(nr, sym, compat) /* Not supported */ static char syscalls[] = { #include <asm/syscalls_64.h> }; diff --git a/arch/x86/um/vdso/vma.c b/arch/x86/um/vdso/vma.c index 91f4ec9a0a56..af91901babb8 100644 --- a/arch/x86/um/vdso/vma.c +++ b/arch/x86/um/vdso/vma.c @@ -64,8 +64,7 @@ int arch_setup_additional_pages(struct linux_binprm *bprm, int uses_interp) err = install_special_mapping(mm, um_vdso_addr, PAGE_SIZE, VM_READ|VM_EXEC| - VM_MAYREAD|VM_MAYWRITE|VM_MAYEXEC| - VM_ALWAYSDUMP, + VM_MAYREAD|VM_MAYWRITE|VM_MAYEXEC, vdsop); up_write(&mm->mmap_sem); diff --git a/arch/x86/vdso/.gitignore b/arch/x86/vdso/.gitignore index 60274d5746e1..3282874bc61d 100644 --- a/arch/x86/vdso/.gitignore +++ b/arch/x86/vdso/.gitignore @@ -1,5 +1,7 @@ vdso.lds vdso-syms.lds +vdsox32.lds +vdsox32-syms.lds vdso32-syms.lds vdso32-syscall-syms.lds vdso32-sysenter-syms.lds diff --git a/arch/x86/vdso/Makefile b/arch/x86/vdso/Makefile index 5d179502a52c..fd14be1d1472 100644 --- a/arch/x86/vdso/Makefile +++ b/arch/x86/vdso/Makefile @@ -3,21 +3,29 @@ # VDSO64-$(CONFIG_X86_64) := y +VDSOX32-$(CONFIG_X86_X32_ABI) := y VDSO32-$(CONFIG_X86_32) := y VDSO32-$(CONFIG_COMPAT) := y vdso-install-$(VDSO64-y) += vdso.so +vdso-install-$(VDSOX32-y) += vdsox32.so vdso-install-$(VDSO32-y) += $(vdso32-images) # files to link into the vdso vobjs-y := vdso-note.o vclock_gettime.o vgetcpu.o +vobjs-$(VDSOX32-y) += $(vobjx32s-compat) + +# Filter out x32 objects. +vobj64s := $(filter-out $(vobjx32s-compat),$(vobjs-y)) + # files to link into kernel obj-$(VDSO64-y) += vma.o vdso.o +obj-$(VDSOX32-y) += vdsox32.o obj-$(VDSO32-y) += vdso32.o vdso32-setup.o -vobjs := $(foreach F,$(vobjs-y),$(obj)/$F) +vobjs := $(foreach F,$(vobj64s),$(obj)/$F) $(obj)/vdso.o: $(obj)/vdso.so @@ -73,6 +81,42 @@ $(obj)/%-syms.lds: $(obj)/%.so.dbg FORCE $(call if_changed,vdsosym) # +# X32 processes use x32 vDSO to access 64bit kernel data. +# +# Build x32 vDSO image: +# 1. Compile x32 vDSO as 64bit. +# 2. Convert object files to x32. +# 3. Build x32 VDSO image with x32 objects, which contains 64bit codes +# so that it can reach 64bit address space with 64bit pointers. +# + +targets += vdsox32-syms.lds +obj-$(VDSOX32-y) += vdsox32-syms.lds + +CPPFLAGS_vdsox32.lds = $(CPPFLAGS_vdso.lds) +VDSO_LDFLAGS_vdsox32.lds = -Wl,-m,elf32_x86_64 \ + -Wl,-soname=linux-vdso.so.1 \ + -Wl,-z,max-page-size=4096 \ + -Wl,-z,common-page-size=4096 + +vobjx32s-y := $(vobj64s:.o=-x32.o) +vobjx32s := $(foreach F,$(vobjx32s-y),$(obj)/$F) + +# Convert 64bit object file to x32 for x32 vDSO. +quiet_cmd_x32 = X32 $@ + cmd_x32 = $(OBJCOPY) -O elf32-x86-64 $< $@ + +$(obj)/%-x32.o: $(obj)/%.o FORCE + $(call if_changed,x32) + +targets += vdsox32.so vdsox32.so.dbg vdsox32.lds $(vobjx32s-y) + +$(obj)/vdsox32.o: $(src)/vdsox32.S $(obj)/vdsox32.so + +$(obj)/vdsox32.so.dbg: $(src)/vdsox32.lds $(vobjx32s) FORCE + $(call if_changed,vdso) + +# # Build multiple 32-bit vDSO images to choose from at boot time. # obj-$(VDSO32-y) += vdso32-syms.lds diff --git a/arch/x86/vdso/vclock_gettime.c b/arch/x86/vdso/vclock_gettime.c index 6bc0e723b6e8..885eff49d6ab 100644 --- a/arch/x86/vdso/vclock_gettime.c +++ b/arch/x86/vdso/vclock_gettime.c @@ -70,100 +70,98 @@ notrace static long vdso_fallback_gettime(long clock, struct timespec *ts) return ret; } +notrace static long vdso_fallback_gtod(struct timeval *tv, struct timezone *tz) +{ + long ret; + + asm("syscall" : "=a" (ret) : + "0" (__NR_gettimeofday), "D" (tv), "S" (tz) : "memory"); + return ret; +} + + notrace static inline long vgetns(void) { long v; cycles_t cycles; if (gtod->clock.vclock_mode == VCLOCK_TSC) cycles = vread_tsc(); - else + else if (gtod->clock.vclock_mode == VCLOCK_HPET) cycles = vread_hpet(); + else + return 0; v = (cycles - gtod->clock.cycle_last) & gtod->clock.mask; return (v * gtod->clock.mult) >> gtod->clock.shift; } -notrace static noinline int do_realtime(struct timespec *ts) +/* Code size doesn't matter (vdso is 4k anyway) and this is faster. */ +notrace static int __always_inline do_realtime(struct timespec *ts) { unsigned long seq, ns; + int mode; + do { - seq = read_seqbegin(>od->lock); + seq = read_seqcount_begin(>od->seq); + mode = gtod->clock.vclock_mode; ts->tv_sec = gtod->wall_time_sec; ts->tv_nsec = gtod->wall_time_nsec; ns = vgetns(); - } while (unlikely(read_seqretry(>od->lock, seq))); + } while (unlikely(read_seqcount_retry(>od->seq, seq))); + timespec_add_ns(ts, ns); - return 0; + return mode; } -notrace static noinline int do_monotonic(struct timespec *ts) +notrace static int do_monotonic(struct timespec *ts) { - unsigned long seq, ns, secs; + unsigned long seq, ns; + int mode; + do { - seq = read_seqbegin(>od->lock); - secs = gtod->wall_time_sec; - ns = gtod->wall_time_nsec + vgetns(); - secs += gtod->wall_to_monotonic.tv_sec; - ns += gtod->wall_to_monotonic.tv_nsec; - } while (unlikely(read_seqretry(>od->lock, seq))); - - /* wall_time_nsec, vgetns(), and wall_to_monotonic.tv_nsec - * are all guaranteed to be nonnegative. - */ - while (ns >= NSEC_PER_SEC) { - ns -= NSEC_PER_SEC; - ++secs; - } - ts->tv_sec = secs; - ts->tv_nsec = ns; + seq = read_seqcount_begin(>od->seq); + mode = gtod->clock.vclock_mode; + ts->tv_sec = gtod->monotonic_time_sec; + ts->tv_nsec = gtod->monotonic_time_nsec; + ns = vgetns(); + } while (unlikely(read_seqcount_retry(>od->seq, seq))); + timespec_add_ns(ts, ns); - return 0; + return mode; } -notrace static noinline int do_realtime_coarse(struct timespec *ts) +notrace static int do_realtime_coarse(struct timespec *ts) { unsigned long seq; do { - seq = read_seqbegin(>od->lock); + seq = read_seqcount_begin(>od->seq); ts->tv_sec = gtod->wall_time_coarse.tv_sec; ts->tv_nsec = gtod->wall_time_coarse.tv_nsec; - } while (unlikely(read_seqretry(>od->lock, seq))); + } while (unlikely(read_seqcount_retry(>od->seq, seq))); return 0; } -notrace static noinline int do_monotonic_coarse(struct timespec *ts) +notrace static int do_monotonic_coarse(struct timespec *ts) { - unsigned long seq, ns, secs; + unsigned long seq; do { - seq = read_seqbegin(>od->lock); - secs = gtod->wall_time_coarse.tv_sec; - ns = gtod->wall_time_coarse.tv_nsec; - secs += gtod->wall_to_monotonic.tv_sec; - ns += gtod->wall_to_monotonic.tv_nsec; - } while (unlikely(read_seqretry(>od->lock, seq))); - - /* wall_time_nsec and wall_to_monotonic.tv_nsec are - * guaranteed to be between 0 and NSEC_PER_SEC. - */ - if (ns >= NSEC_PER_SEC) { - ns -= NSEC_PER_SEC; - ++secs; - } - ts->tv_sec = secs; - ts->tv_nsec = ns; + seq = read_seqcount_begin(>od->seq); + ts->tv_sec = gtod->monotonic_time_coarse.tv_sec; + ts->tv_nsec = gtod->monotonic_time_coarse.tv_nsec; + } while (unlikely(read_seqcount_retry(>od->seq, seq))); return 0; } notrace int __vdso_clock_gettime(clockid_t clock, struct timespec *ts) { + int ret = VCLOCK_NONE; + switch (clock) { case CLOCK_REALTIME: - if (likely(gtod->clock.vclock_mode != VCLOCK_NONE)) - return do_realtime(ts); + ret = do_realtime(ts); break; case CLOCK_MONOTONIC: - if (likely(gtod->clock.vclock_mode != VCLOCK_NONE)) - return do_monotonic(ts); + ret = do_monotonic(ts); break; case CLOCK_REALTIME_COARSE: return do_realtime_coarse(ts); @@ -171,32 +169,33 @@ notrace int __vdso_clock_gettime(clockid_t clock, struct timespec *ts) return do_monotonic_coarse(ts); } - return vdso_fallback_gettime(clock, ts); + if (ret == VCLOCK_NONE) + return vdso_fallback_gettime(clock, ts); + return 0; } int clock_gettime(clockid_t, struct timespec *) __attribute__((weak, alias("__vdso_clock_gettime"))); notrace int __vdso_gettimeofday(struct timeval *tv, struct timezone *tz) { - long ret; - if (likely(gtod->clock.vclock_mode != VCLOCK_NONE)) { - if (likely(tv != NULL)) { - BUILD_BUG_ON(offsetof(struct timeval, tv_usec) != - offsetof(struct timespec, tv_nsec) || - sizeof(*tv) != sizeof(struct timespec)); - do_realtime((struct timespec *)tv); - tv->tv_usec /= 1000; - } - if (unlikely(tz != NULL)) { - /* Avoid memcpy. Some old compilers fail to inline it */ - tz->tz_minuteswest = gtod->sys_tz.tz_minuteswest; - tz->tz_dsttime = gtod->sys_tz.tz_dsttime; - } - return 0; + long ret = VCLOCK_NONE; + + if (likely(tv != NULL)) { + BUILD_BUG_ON(offsetof(struct timeval, tv_usec) != + offsetof(struct timespec, tv_nsec) || + sizeof(*tv) != sizeof(struct timespec)); + ret = do_realtime((struct timespec *)tv); + tv->tv_usec /= 1000; } - asm("syscall" : "=a" (ret) : - "0" (__NR_gettimeofday), "D" (tv), "S" (tz) : "memory"); - return ret; + if (unlikely(tz != NULL)) { + /* Avoid memcpy. Some old compilers fail to inline it */ + tz->tz_minuteswest = gtod->sys_tz.tz_minuteswest; + tz->tz_dsttime = gtod->sys_tz.tz_dsttime; + } + + if (ret == VCLOCK_NONE) + return vdso_fallback_gtod(tv, tz); + return 0; } int gettimeofday(struct timeval *, struct timezone *) __attribute__((weak, alias("__vdso_gettimeofday"))); diff --git a/arch/x86/vdso/vdso32-setup.c b/arch/x86/vdso/vdso32-setup.c index 468d591dde31..66e6d9359826 100644 --- a/arch/x86/vdso/vdso32-setup.c +++ b/arch/x86/vdso/vdso32-setup.c @@ -250,13 +250,7 @@ static int __init gate_vma_init(void) gate_vma.vm_end = FIXADDR_USER_END; gate_vma.vm_flags = VM_READ | VM_MAYREAD | VM_EXEC | VM_MAYEXEC; gate_vma.vm_page_prot = __P101; - /* - * Make sure the vDSO gets into every core dump. - * Dumping its contents makes post-mortem fully interpretable later - * without matching up the same kernel and hardware config to see - * what PC values meant. - */ - gate_vma.vm_flags |= VM_ALWAYSDUMP; + return 0; } @@ -317,6 +311,11 @@ int arch_setup_additional_pages(struct linux_binprm *bprm, int uses_interp) int ret = 0; bool compat; +#ifdef CONFIG_X86_X32_ABI + if (test_thread_flag(TIF_X32)) + return x32_setup_additional_pages(bprm, uses_interp); +#endif + if (vdso_enabled == VDSO_DISABLED) return 0; @@ -343,17 +342,10 @@ int arch_setup_additional_pages(struct linux_binprm *bprm, int uses_interp) if (compat_uses_vma || !compat) { /* * MAYWRITE to allow gdb to COW and set breakpoints - * - * Make sure the vDSO gets into every core dump. - * Dumping its contents makes post-mortem fully - * interpretable later without matching up the same - * kernel and hardware config to see what PC values - * meant. */ ret = install_special_mapping(mm, addr, PAGE_SIZE, VM_READ|VM_EXEC| - VM_MAYREAD|VM_MAYWRITE|VM_MAYEXEC| - VM_ALWAYSDUMP, + VM_MAYREAD|VM_MAYWRITE|VM_MAYEXEC, vdso32_pages); if (ret) diff --git a/arch/x86/vdso/vdsox32.S b/arch/x86/vdso/vdsox32.S new file mode 100644 index 000000000000..d6b9a7f42a8a --- /dev/null +++ b/arch/x86/vdso/vdsox32.S @@ -0,0 +1,22 @@ +#include <asm/page_types.h> +#include <linux/linkage.h> +#include <linux/init.h> + +__PAGE_ALIGNED_DATA + + .globl vdsox32_start, vdsox32_end + .align PAGE_SIZE +vdsox32_start: + .incbin "arch/x86/vdso/vdsox32.so" +vdsox32_end: + .align PAGE_SIZE /* extra data here leaks to userspace. */ + +.previous + + .globl vdsox32_pages + .bss + .align 8 + .type vdsox32_pages, @object +vdsox32_pages: + .zero (vdsox32_end - vdsox32_start + PAGE_SIZE - 1) / PAGE_SIZE * 8 + .size vdsox32_pages, .-vdsox32_pages diff --git a/arch/x86/vdso/vdsox32.lds.S b/arch/x86/vdso/vdsox32.lds.S new file mode 100644 index 000000000000..62272aa2ae0a --- /dev/null +++ b/arch/x86/vdso/vdsox32.lds.S @@ -0,0 +1,28 @@ +/* + * Linker script for x32 vDSO. + * We #include the file to define the layout details. + * Here we only choose the prelinked virtual address. + * + * This file defines the version script giving the user-exported symbols in + * the DSO. We can define local symbols here called VDSO* to make their + * values visible using the asm-x86/vdso.h macros from the kernel proper. + */ + +#define VDSO_PRELINK 0 +#include "vdso-layout.lds.S" + +/* + * This controls what userland symbols we export from the vDSO. + */ +VERSION { + LINUX_2.6 { + global: + __vdso_clock_gettime; + __vdso_gettimeofday; + __vdso_getcpu; + __vdso_time; + local: *; + }; +} + +VDSOX32_PRELINK = VDSO_PRELINK; diff --git a/arch/x86/vdso/vma.c b/arch/x86/vdso/vma.c index 153407c35b75..00aaf047b39f 100644 --- a/arch/x86/vdso/vma.c +++ b/arch/x86/vdso/vma.c @@ -24,7 +24,44 @@ extern unsigned short vdso_sync_cpuid; extern struct page *vdso_pages[]; static unsigned vdso_size; -static void __init patch_vdso(void *vdso, size_t len) +#ifdef CONFIG_X86_X32_ABI +extern char vdsox32_start[], vdsox32_end[]; +extern struct page *vdsox32_pages[]; +static unsigned vdsox32_size; + +static void __init patch_vdsox32(void *vdso, size_t len) +{ + Elf32_Ehdr *hdr = vdso; + Elf32_Shdr *sechdrs, *alt_sec = 0; + char *secstrings; + void *alt_data; + int i; + + BUG_ON(len < sizeof(Elf32_Ehdr)); + BUG_ON(memcmp(hdr->e_ident, ELFMAG, SELFMAG) != 0); + + sechdrs = (void *)hdr + hdr->e_shoff; + secstrings = (void *)hdr + sechdrs[hdr->e_shstrndx].sh_offset; + + for (i = 1; i < hdr->e_shnum; i++) { + Elf32_Shdr *shdr = &sechdrs[i]; + if (!strcmp(secstrings + shdr->sh_name, ".altinstructions")) { + alt_sec = shdr; + goto found; + } + } + + /* If we get here, it's probably a bug. */ + pr_warning("patch_vdsox32: .altinstructions not found\n"); + return; /* nothing to patch */ + +found: + alt_data = (void *)hdr + alt_sec->sh_offset; + apply_alternatives(alt_data, alt_data + alt_sec->sh_size); +} +#endif + +static void __init patch_vdso64(void *vdso, size_t len) { Elf64_Ehdr *hdr = vdso; Elf64_Shdr *sechdrs, *alt_sec = 0; @@ -47,7 +84,7 @@ static void __init patch_vdso(void *vdso, size_t len) } /* If we get here, it's probably a bug. */ - pr_warning("patch_vdso: .altinstructions not found\n"); + pr_warning("patch_vdso64: .altinstructions not found\n"); return; /* nothing to patch */ found: @@ -60,12 +97,20 @@ static int __init init_vdso(void) int npages = (vdso_end - vdso_start + PAGE_SIZE - 1) / PAGE_SIZE; int i; - patch_vdso(vdso_start, vdso_end - vdso_start); + patch_vdso64(vdso_start, vdso_end - vdso_start); vdso_size = npages << PAGE_SHIFT; for (i = 0; i < npages; i++) vdso_pages[i] = virt_to_page(vdso_start + i*PAGE_SIZE); +#ifdef CONFIG_X86_X32_ABI + patch_vdsox32(vdsox32_start, vdsox32_end - vdsox32_start); + npages = (vdsox32_end - vdsox32_start + PAGE_SIZE - 1) / PAGE_SIZE; + vdsox32_size = npages << PAGE_SHIFT; + for (i = 0; i < npages; i++) + vdsox32_pages[i] = virt_to_page(vdsox32_start + i*PAGE_SIZE); +#endif + return 0; } subsys_initcall(init_vdso); @@ -103,7 +148,10 @@ static unsigned long vdso_addr(unsigned long start, unsigned len) /* Setup a VMA at program startup for the vsyscall page. Not called for compat tasks */ -int arch_setup_additional_pages(struct linux_binprm *bprm, int uses_interp) +static int setup_additional_pages(struct linux_binprm *bprm, + int uses_interp, + struct page **pages, + unsigned size) { struct mm_struct *mm = current->mm; unsigned long addr; @@ -113,8 +161,8 @@ int arch_setup_additional_pages(struct linux_binprm *bprm, int uses_interp) return 0; down_write(&mm->mmap_sem); - addr = vdso_addr(mm->start_stack, vdso_size); - addr = get_unmapped_area(NULL, addr, vdso_size, 0, 0); + addr = vdso_addr(mm->start_stack, size); + addr = get_unmapped_area(NULL, addr, size, 0, 0); if (IS_ERR_VALUE(addr)) { ret = addr; goto up_fail; @@ -122,11 +170,10 @@ int arch_setup_additional_pages(struct linux_binprm *bprm, int uses_interp) current->mm->context.vdso = (void *)addr; - ret = install_special_mapping(mm, addr, vdso_size, + ret = install_special_mapping(mm, addr, size, VM_READ|VM_EXEC| - VM_MAYREAD|VM_MAYWRITE|VM_MAYEXEC| - VM_ALWAYSDUMP, - vdso_pages); + VM_MAYREAD|VM_MAYWRITE|VM_MAYEXEC, + pages); if (ret) { current->mm->context.vdso = NULL; goto up_fail; @@ -137,6 +184,20 @@ up_fail: return ret; } +int arch_setup_additional_pages(struct linux_binprm *bprm, int uses_interp) +{ + return setup_additional_pages(bprm, uses_interp, vdso_pages, + vdso_size); +} + +#ifdef CONFIG_X86_X32_ABI +int x32_setup_additional_pages(struct linux_binprm *bprm, int uses_interp) +{ + return setup_additional_pages(bprm, uses_interp, vdsox32_pages, + vdsox32_size); +} +#endif + static __init int vdso_setup(char *s) { vdso_enabled = simple_strtoul(s, NULL, 0); diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c index 4172af8ceeb3..b132ade26f77 100644 --- a/arch/x86/xen/enlighten.c +++ b/arch/x86/xen/enlighten.c @@ -62,6 +62,15 @@ #include <asm/reboot.h> #include <asm/stackprotector.h> #include <asm/hypervisor.h> +#include <asm/mwait.h> + +#ifdef CONFIG_ACPI +#include <linux/acpi.h> +#include <asm/acpi.h> +#include <acpi/pdc_intel.h> +#include <acpi/processor.h> +#include <xen/interface/platform.h> +#endif #include "xen-ops.h" #include "mmu.h" @@ -200,13 +209,17 @@ static void __init xen_banner(void) static __read_mostly unsigned int cpuid_leaf1_edx_mask = ~0; static __read_mostly unsigned int cpuid_leaf1_ecx_mask = ~0; +static __read_mostly unsigned int cpuid_leaf1_ecx_set_mask; +static __read_mostly unsigned int cpuid_leaf5_ecx_val; +static __read_mostly unsigned int cpuid_leaf5_edx_val; + static void xen_cpuid(unsigned int *ax, unsigned int *bx, unsigned int *cx, unsigned int *dx) { unsigned maskebx = ~0; unsigned maskecx = ~0; unsigned maskedx = ~0; - + unsigned setecx = 0; /* * Mask out inconvenient features, to try and disable as many * unsupported kernel subsystems as possible. @@ -214,9 +227,18 @@ static void xen_cpuid(unsigned int *ax, unsigned int *bx, switch (*ax) { case 1: maskecx = cpuid_leaf1_ecx_mask; + setecx = cpuid_leaf1_ecx_set_mask; maskedx = cpuid_leaf1_edx_mask; break; + case CPUID_MWAIT_LEAF: + /* Synthesize the values.. */ + *ax = 0; + *bx = 0; + *cx = cpuid_leaf5_ecx_val; + *dx = cpuid_leaf5_edx_val; + return; + case 0xb: /* Suppress extended topology stuff */ maskebx = 0; @@ -232,9 +254,75 @@ static void xen_cpuid(unsigned int *ax, unsigned int *bx, *bx &= maskebx; *cx &= maskecx; + *cx |= setecx; *dx &= maskedx; + } +static bool __init xen_check_mwait(void) +{ +#ifdef CONFIG_ACPI + struct xen_platform_op op = { + .cmd = XENPF_set_processor_pminfo, + .u.set_pminfo.id = -1, + .u.set_pminfo.type = XEN_PM_PDC, + }; + uint32_t buf[3]; + unsigned int ax, bx, cx, dx; + unsigned int mwait_mask; + + /* We need to determine whether it is OK to expose the MWAIT + * capability to the kernel to harvest deeper than C3 states from ACPI + * _CST using the processor_harvest_xen.c module. For this to work, we + * need to gather the MWAIT_LEAF values (which the cstate.c code + * checks against). The hypervisor won't expose the MWAIT flag because + * it would break backwards compatibility; so we will find out directly + * from the hardware and hypercall. + */ + if (!xen_initial_domain()) + return false; + + ax = 1; + cx = 0; + + native_cpuid(&ax, &bx, &cx, &dx); + + mwait_mask = (1 << (X86_FEATURE_EST % 32)) | + (1 << (X86_FEATURE_MWAIT % 32)); + + if ((cx & mwait_mask) != mwait_mask) + return false; + + /* We need to emulate the MWAIT_LEAF and for that we need both + * ecx and edx. The hypercall provides only partial information. + */ + + ax = CPUID_MWAIT_LEAF; + bx = 0; + cx = 0; + dx = 0; + + native_cpuid(&ax, &bx, &cx, &dx); + + /* Ask the Hypervisor whether to clear ACPI_PDC_C_C2C3_FFH. If so, + * don't expose MWAIT_LEAF and let ACPI pick the IOPORT version of C3. + */ + buf[0] = ACPI_PDC_REVISION_ID; + buf[1] = 1; + buf[2] = (ACPI_PDC_C_CAPABILITY_SMP | ACPI_PDC_EST_CAPABILITY_SWSMP); + + set_xen_guest_handle(op.u.set_pminfo.pdc, buf); + + if ((HYPERVISOR_dom0_op(&op) == 0) && + (buf[2] & (ACPI_PDC_C_C1_FFH | ACPI_PDC_C_C2C3_FFH))) { + cpuid_leaf5_ecx_val = cx; + cpuid_leaf5_edx_val = dx; + } + return true; +#else + return false; +#endif +} static void __init xen_init_cpuid_mask(void) { unsigned int ax, bx, cx, dx; @@ -261,6 +349,9 @@ static void __init xen_init_cpuid_mask(void) /* Xen will set CR4.OSXSAVE if supported and not disabled by force */ if ((cx & xsave_mask) != xsave_mask) cpuid_leaf1_ecx_mask &= ~xsave_mask; /* disable XSAVE & OSXSAVE */ + + if (xen_check_mwait()) + cpuid_leaf1_ecx_set_mask = (1 << (X86_FEATURE_MWAIT % 32)); } static void xen_set_debugreg(int reg, unsigned long val) @@ -777,11 +868,11 @@ static DEFINE_PER_CPU(unsigned long, xen_cr0_value); static unsigned long xen_read_cr0(void) { - unsigned long cr0 = percpu_read(xen_cr0_value); + unsigned long cr0 = this_cpu_read(xen_cr0_value); if (unlikely(cr0 == 0)) { cr0 = native_read_cr0(); - percpu_write(xen_cr0_value, cr0); + this_cpu_write(xen_cr0_value, cr0); } return cr0; @@ -791,7 +882,7 @@ static void xen_write_cr0(unsigned long cr0) { struct multicall_space mcs; - percpu_write(xen_cr0_value, cr0); + this_cpu_write(xen_cr0_value, cr0); /* Only pay attention to cr0.TS; everything else is ignored. */ diff --git a/arch/x86/xen/irq.c b/arch/x86/xen/irq.c index 8bbb465b6f0a..157337657971 100644 --- a/arch/x86/xen/irq.c +++ b/arch/x86/xen/irq.c @@ -26,7 +26,7 @@ static unsigned long xen_save_fl(void) struct vcpu_info *vcpu; unsigned long flags; - vcpu = percpu_read(xen_vcpu); + vcpu = this_cpu_read(xen_vcpu); /* flag has opposite sense of mask */ flags = !vcpu->evtchn_upcall_mask; @@ -50,7 +50,7 @@ static void xen_restore_fl(unsigned long flags) make sure we're don't switch CPUs between getting the vcpu pointer and updating the mask. */ preempt_disable(); - vcpu = percpu_read(xen_vcpu); + vcpu = this_cpu_read(xen_vcpu); vcpu->evtchn_upcall_mask = flags; preempt_enable_no_resched(); @@ -72,7 +72,7 @@ static void xen_irq_disable(void) make sure we're don't switch CPUs between getting the vcpu pointer and updating the mask. */ preempt_disable(); - percpu_read(xen_vcpu)->evtchn_upcall_mask = 1; + this_cpu_read(xen_vcpu)->evtchn_upcall_mask = 1; preempt_enable_no_resched(); } PV_CALLEE_SAVE_REGS_THUNK(xen_irq_disable); @@ -86,7 +86,7 @@ static void xen_irq_enable(void) the caller is confused and is trying to re-enable interrupts on an indeterminate processor. */ - vcpu = percpu_read(xen_vcpu); + vcpu = this_cpu_read(xen_vcpu); vcpu->evtchn_upcall_mask = 0; /* Doesn't matter if we get preempted here, because any diff --git a/arch/x86/xen/mmu.c b/arch/x86/xen/mmu.c index 95c1cf60c669..988828b479ed 100644 --- a/arch/x86/xen/mmu.c +++ b/arch/x86/xen/mmu.c @@ -1071,14 +1071,14 @@ static void drop_other_mm_ref(void *info) struct mm_struct *mm = info; struct mm_struct *active_mm; - active_mm = percpu_read(cpu_tlbstate.active_mm); + active_mm = this_cpu_read(cpu_tlbstate.active_mm); - if (active_mm == mm && percpu_read(cpu_tlbstate.state) != TLBSTATE_OK) + if (active_mm == mm && this_cpu_read(cpu_tlbstate.state) != TLBSTATE_OK) leave_mm(smp_processor_id()); /* If this cpu still has a stale cr3 reference, then make sure it has been flushed. */ - if (percpu_read(xen_current_cr3) == __pa(mm->pgd)) + if (this_cpu_read(xen_current_cr3) == __pa(mm->pgd)) load_cr3(swapper_pg_dir); } @@ -1185,17 +1185,17 @@ static void __init xen_pagetable_setup_done(pgd_t *base) static void xen_write_cr2(unsigned long cr2) { - percpu_read(xen_vcpu)->arch.cr2 = cr2; + this_cpu_read(xen_vcpu)->arch.cr2 = cr2; } static unsigned long xen_read_cr2(void) { - return percpu_read(xen_vcpu)->arch.cr2; + return this_cpu_read(xen_vcpu)->arch.cr2; } unsigned long xen_read_cr2_direct(void) { - return percpu_read(xen_vcpu_info.arch.cr2); + return this_cpu_read(xen_vcpu_info.arch.cr2); } static void xen_flush_tlb(void) @@ -1278,12 +1278,12 @@ static void xen_flush_tlb_others(const struct cpumask *cpus, static unsigned long xen_read_cr3(void) { - return percpu_read(xen_cr3); + return this_cpu_read(xen_cr3); } static void set_current_cr3(void *v) { - percpu_write(xen_current_cr3, (unsigned long)v); + this_cpu_write(xen_current_cr3, (unsigned long)v); } static void __xen_write_cr3(bool kernel, unsigned long cr3) @@ -1306,7 +1306,7 @@ static void __xen_write_cr3(bool kernel, unsigned long cr3) xen_extend_mmuext_op(&op); if (kernel) { - percpu_write(xen_cr3, cr3); + this_cpu_write(xen_cr3, cr3); /* Update xen_current_cr3 once the batch has actually been submitted. */ @@ -1322,7 +1322,7 @@ static void xen_write_cr3(unsigned long cr3) /* Update while interrupts are disabled, so its atomic with respect to ipis */ - percpu_write(xen_cr3, cr3); + this_cpu_write(xen_cr3, cr3); __xen_write_cr3(true, cr3); diff --git a/arch/x86/xen/multicalls.h b/arch/x86/xen/multicalls.h index dee79b78a90f..9c2e74f9096c 100644 --- a/arch/x86/xen/multicalls.h +++ b/arch/x86/xen/multicalls.h @@ -47,7 +47,7 @@ static inline void xen_mc_issue(unsigned mode) xen_mc_flush(); /* restore flags saved in xen_mc_batch */ - local_irq_restore(percpu_read(xen_mc_irq_flags)); + local_irq_restore(this_cpu_read(xen_mc_irq_flags)); } /* Set up a callback to be called when the current batch is flushed */ diff --git a/arch/x86/xen/setup.c b/arch/x86/xen/setup.c index e03c63692176..1ba8dff26753 100644 --- a/arch/x86/xen/setup.c +++ b/arch/x86/xen/setup.c @@ -10,6 +10,7 @@ #include <linux/pm.h> #include <linux/memblock.h> #include <linux/cpuidle.h> +#include <linux/cpufreq.h> #include <asm/elf.h> #include <asm/vdso.h> @@ -420,7 +421,7 @@ void __init xen_arch_setup(void) boot_cpu_data.hlt_works_ok = 1; #endif disable_cpuidle(); - boot_option_idle_override = IDLE_HALT; + disable_cpufreq(); WARN_ON(set_pm_idle_to_default()); fiddle_vdso(); } diff --git a/arch/x86/xen/smp.c b/arch/x86/xen/smp.c index 501d4e0244ba..02900e8ce26c 100644 --- a/arch/x86/xen/smp.c +++ b/arch/x86/xen/smp.c @@ -75,8 +75,14 @@ static void __cpuinit cpu_bringup(void) xen_setup_cpu_clockevents(); + notify_cpu_starting(cpu); + + ipi_call_lock(); set_cpu_online(cpu, true); - percpu_write(cpu_state, CPU_ONLINE); + ipi_call_unlock(); + + this_cpu_write(cpu_state, CPU_ONLINE); + wmb(); /* We can take interrupts now: we're officially "up". */ |