diff options
30 files changed, 617 insertions, 507 deletions
diff --git a/Documentation/kernel-parameters.txt b/Documentation/kernel-parameters.txt index 121d5fcbd94a..2311dad7a57a 100644 --- a/Documentation/kernel-parameters.txt +++ b/Documentation/kernel-parameters.txt @@ -3424,14 +3424,24 @@ bytes respectively. Such letter suffixes can also be entirely omitted. of CONFIG_HIGHPTE. vdso= [X86,SH] - vdso=2: enable compat VDSO (default with COMPAT_VDSO) - vdso=1: enable VDSO (default) + On X86_32, this is an alias for vdso32=. Otherwise: + + vdso=1: enable VDSO (the default) vdso=0: disable VDSO mapping - vdso32= [X86] - vdso32=2: enable compat VDSO (default with COMPAT_VDSO) - vdso32=1: enable 32-bit VDSO (default) - vdso32=0: disable 32-bit VDSO mapping + vdso32= [X86] Control the 32-bit vDSO + vdso32=1: enable 32-bit VDSO + vdso32=0 or vdso32=2: disable 32-bit VDSO + + See the help text for CONFIG_COMPAT_VDSO for more + details. If CONFIG_COMPAT_VDSO is set, the default is + vdso32=0; otherwise, the default is vdso32=1. + + For compatibility with older kernels, vdso32=2 is an + alias for vdso32=0. + + Try vdso32=0 if you encounter an error that says: + dl_main: Assertion `(void *) ph->p_vaddr == _rtld_local._dl_sysinfo_dso' failed! vector= [IA-64,SMP] vector=percpu: enable percpu vector domain diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index 26237934ac87..ac04d9804391 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -107,9 +107,9 @@ config X86 select HAVE_ARCH_SOFT_DIRTY select CLOCKSOURCE_WATCHDOG select GENERIC_CLOCKEVENTS - select ARCH_CLOCKSOURCE_DATA if X86_64 + select ARCH_CLOCKSOURCE_DATA select GENERIC_CLOCKEVENTS_BROADCAST if X86_64 || (X86_32 && X86_LOCAL_APIC) - select GENERIC_TIME_VSYSCALL if X86_64 + select GENERIC_TIME_VSYSCALL select KTIME_SCALAR if X86_32 select GENERIC_STRNCPY_FROM_USER select GENERIC_STRNLEN_USER @@ -1848,17 +1848,29 @@ config DEBUG_HOTPLUG_CPU0 If unsure, say N. config COMPAT_VDSO - def_bool y - prompt "Compat VDSO support" + def_bool n + prompt "Disable the 32-bit vDSO (needed for glibc 2.3.3)" depends on X86_32 || IA32_EMULATION ---help--- - Map the 32-bit VDSO to the predictable old-style address too. + Certain buggy versions of glibc will crash if they are + presented with a 32-bit vDSO that is not mapped at the address + indicated in its segment table. - Say N here if you are running a sufficiently recent glibc - version (2.3.3 or later), to remove the high-mapped - VDSO mapping and to exclusively use the randomized VDSO. + The bug was introduced by f866314b89d56845f55e6f365e18b31ec978ec3a + and fixed by 3b3ddb4f7db98ec9e912ccdf54d35df4aa30e04a and + 49ad572a70b8aeb91e57483a11dd1b77e31c4468. Glibc 2.3.3 is + the only released version with the bug, but OpenSUSE 9 + contains a buggy "glibc 2.3.2". - If unsure, say Y. + The symptom of the bug is that everything crashes on startup, saying: + dl_main: Assertion `(void *) ph->p_vaddr == _rtld_local._dl_sysinfo_dso' failed! + + Saying Y here changes the default value of the vdso32 boot + option from 1 to 0, which turns off the 32-bit vDSO entirely. + This works around the glibc bug but hurts performance. + + If unsure, say N: if you are compiling your own kernel, you + are unlikely to be using a buggy version of glibc. config CMDLINE_BOOL bool "Built-in kernel command line" diff --git a/arch/x86/include/asm/clocksource.h b/arch/x86/include/asm/clocksource.h index 16a57f4ed64d..eda81dc0f4ae 100644 --- a/arch/x86/include/asm/clocksource.h +++ b/arch/x86/include/asm/clocksource.h @@ -3,8 +3,6 @@ #ifndef _ASM_X86_CLOCKSOURCE_H #define _ASM_X86_CLOCKSOURCE_H -#ifdef CONFIG_X86_64 - #define VCLOCK_NONE 0 /* No vDSO clock available. */ #define VCLOCK_TSC 1 /* vDSO should use vread_tsc. */ #define VCLOCK_HPET 2 /* vDSO should use vread_hpet. */ @@ -14,6 +12,4 @@ struct arch_clocksource_data { int vclock_mode; }; -#endif /* CONFIG_X86_64 */ - #endif /* _ASM_X86_CLOCKSOURCE_H */ diff --git a/arch/x86/include/asm/elf.h b/arch/x86/include/asm/elf.h index 9c999c1674fa..2c71182d30ef 100644 --- a/arch/x86/include/asm/elf.h +++ b/arch/x86/include/asm/elf.h @@ -281,16 +281,12 @@ do { \ #define STACK_RND_MASK (0x7ff) -#define VDSO_HIGH_BASE (__fix_to_virt(FIX_VDSO)) - #define ARCH_DLINFO ARCH_DLINFO_IA32(vdso_enabled) /* update AT_VECTOR_SIZE_ARCH if the number of NEW_AUX_ENT entries changes */ #else /* CONFIG_X86_32 */ -#define VDSO_HIGH_BASE 0xffffe000U /* CONFIG_COMPAT_VDSO address */ - /* 1GB for 64bit, 8MB for 32bit */ #define STACK_RND_MASK (test_thread_flag(TIF_ADDR32) ? 0x7ff : 0x3fffff) diff --git a/arch/x86/include/asm/fixmap.h b/arch/x86/include/asm/fixmap.h index 7252cd339175..2377f5618fb7 100644 --- a/arch/x86/include/asm/fixmap.h +++ b/arch/x86/include/asm/fixmap.h @@ -40,15 +40,8 @@ */ extern unsigned long __FIXADDR_TOP; #define FIXADDR_TOP ((unsigned long)__FIXADDR_TOP) - -#define FIXADDR_USER_START __fix_to_virt(FIX_VDSO) -#define FIXADDR_USER_END __fix_to_virt(FIX_VDSO - 1) #else #define FIXADDR_TOP (VSYSCALL_END-PAGE_SIZE) - -/* Only covers 32bit vsyscalls currently. Need another set for 64bit. */ -#define FIXADDR_USER_START ((unsigned long)VSYSCALL32_VSYSCALL) -#define FIXADDR_USER_END (FIXADDR_USER_START + PAGE_SIZE) #endif @@ -74,7 +67,6 @@ extern unsigned long __FIXADDR_TOP; enum fixed_addresses { #ifdef CONFIG_X86_32 FIX_HOLE, - FIX_VDSO, #else VSYSCALL_LAST_PAGE, VSYSCALL_FIRST_PAGE = VSYSCALL_LAST_PAGE diff --git a/arch/x86/include/asm/pgtable_types.h b/arch/x86/include/asm/pgtable_types.h index 708f19fb4fc7..eb3d44945133 100644 --- a/arch/x86/include/asm/pgtable_types.h +++ b/arch/x86/include/asm/pgtable_types.h @@ -214,13 +214,8 @@ #ifdef CONFIG_X86_64 #define __PAGE_KERNEL_IDENT_LARGE_EXEC __PAGE_KERNEL_LARGE_EXEC #else -/* - * For PDE_IDENT_ATTR include USER bit. As the PDE and PTE protection - * bits are combined, this will alow user to access the high address mapped - * VDSO in the presence of CONFIG_COMPAT_VDSO - */ #define PTE_IDENT_ATTR 0x003 /* PRESENT+RW */ -#define PDE_IDENT_ATTR 0x067 /* PRESENT+RW+USER+DIRTY+ACCESSED */ +#define PDE_IDENT_ATTR 0x063 /* PRESENT+RW+DIRTY+ACCESSED */ #define PGD_IDENT_ATTR 0x001 /* PRESENT (no other attributes) */ #endif diff --git a/arch/x86/include/asm/vdso.h b/arch/x86/include/asm/vdso.h index fddb53d63915..d1dc55404ff1 100644 --- a/arch/x86/include/asm/vdso.h +++ b/arch/x86/include/asm/vdso.h @@ -1,8 +1,45 @@ #ifndef _ASM_X86_VDSO_H #define _ASM_X86_VDSO_H +#include <asm/page_types.h> +#include <linux/linkage.h> + +#ifdef __ASSEMBLER__ + +#define DEFINE_VDSO_IMAGE(symname, filename) \ +__PAGE_ALIGNED_DATA ; \ + .globl symname##_start, symname##_end ; \ + .align PAGE_SIZE ; \ + symname##_start: ; \ + .incbin filename ; \ + symname##_end: ; \ + .align PAGE_SIZE /* extra data here leaks to userspace. */ ; \ + \ +.previous ; \ + \ + .globl symname##_pages ; \ + .bss ; \ + .align 8 ; \ + .type symname##_pages, @object ; \ + symname##_pages: ; \ + .zero (symname##_end - symname##_start + PAGE_SIZE - 1) / PAGE_SIZE * (BITS_PER_LONG / 8) ; \ + .size symname##_pages, .-symname##_pages + +#else + +#define DECLARE_VDSO_IMAGE(symname) \ + extern char symname##_start[], symname##_end[]; \ + extern struct page *symname##_pages[] + #if defined CONFIG_X86_32 || defined CONFIG_COMPAT -extern const char VDSO32_PRELINK[]; + +#include <asm/vdso32.h> + +DECLARE_VDSO_IMAGE(vdso32_int80); +#ifdef CONFIG_COMPAT +DECLARE_VDSO_IMAGE(vdso32_syscall); +#endif +DECLARE_VDSO_IMAGE(vdso32_sysenter); /* * Given a pointer to the vDSO image, find the pointer to VDSO32_name @@ -11,8 +48,7 @@ extern const char VDSO32_PRELINK[]; #define VDSO32_SYMBOL(base, name) \ ({ \ extern const char VDSO32_##name[]; \ - (void __user *)(VDSO32_##name - VDSO32_PRELINK + \ - (unsigned long)(base)); \ + (void __user *)(VDSO32_##name + (unsigned long)(base)); \ }) #endif @@ -23,12 +59,8 @@ extern const char VDSO32_PRELINK[]; extern void __user __kernel_sigreturn; extern void __user __kernel_rt_sigreturn; -/* - * These symbols are defined by vdso32.S to mark the bounds - * of the ELF DSO images included therein. - */ -extern const char vdso32_int80_start, vdso32_int80_end; -extern const char vdso32_syscall_start, vdso32_syscall_end; -extern const char vdso32_sysenter_start, vdso32_sysenter_end; +void __init patch_vdso32(void *vdso, size_t len); + +#endif /* __ASSEMBLER__ */ #endif /* _ASM_X86_VDSO_H */ diff --git a/arch/x86/include/asm/vdso32.h b/arch/x86/include/asm/vdso32.h new file mode 100644 index 000000000000..7efb7018406e --- /dev/null +++ b/arch/x86/include/asm/vdso32.h @@ -0,0 +1,11 @@ +#ifndef _ASM_X86_VDSO32_H +#define _ASM_X86_VDSO32_H + +#define VDSO_BASE_PAGE 0 +#define VDSO_VVAR_PAGE 1 +#define VDSO_HPET_PAGE 2 +#define VDSO_PAGES 3 +#define VDSO_PREV_PAGES 2 +#define VDSO_OFFSET(x) ((x) * PAGE_SIZE) + +#endif diff --git a/arch/x86/include/asm/vgtod.h b/arch/x86/include/asm/vgtod.h index 46e24d36b7da..3c3366c2e37f 100644 --- a/arch/x86/include/asm/vgtod.h +++ b/arch/x86/include/asm/vgtod.h @@ -1,30 +1,73 @@ #ifndef _ASM_X86_VGTOD_H #define _ASM_X86_VGTOD_H -#include <asm/vsyscall.h> +#include <linux/compiler.h> #include <linux/clocksource.h> +#ifdef BUILD_VDSO32_64 +typedef u64 gtod_long_t; +#else +typedef unsigned long gtod_long_t; +#endif +/* + * vsyscall_gtod_data will be accessed by 32 and 64 bit code at the same time + * so be carefull by modifying this structure. + */ struct vsyscall_gtod_data { - seqcount_t seq; + unsigned seq; - struct { /* extract of a clocksource struct */ - int vclock_mode; - cycle_t cycle_last; - cycle_t mask; - u32 mult; - u32 shift; - } clock; + int vclock_mode; + cycle_t cycle_last; + cycle_t mask; + u32 mult; + u32 shift; /* open coded 'struct timespec' */ - time_t wall_time_sec; u64 wall_time_snsec; + gtod_long_t wall_time_sec; + gtod_long_t monotonic_time_sec; u64 monotonic_time_snsec; - time_t monotonic_time_sec; + gtod_long_t wall_time_coarse_sec; + gtod_long_t wall_time_coarse_nsec; + gtod_long_t monotonic_time_coarse_sec; + gtod_long_t monotonic_time_coarse_nsec; - struct timezone sys_tz; - struct timespec wall_time_coarse; - struct timespec monotonic_time_coarse; + int tz_minuteswest; + int tz_dsttime; }; extern struct vsyscall_gtod_data vsyscall_gtod_data; +static inline unsigned gtod_read_begin(const struct vsyscall_gtod_data *s) +{ + unsigned ret; + +repeat: + ret = ACCESS_ONCE(s->seq); + if (unlikely(ret & 1)) { + cpu_relax(); + goto repeat; + } + smp_rmb(); + return ret; +} + +static inline int gtod_read_retry(const struct vsyscall_gtod_data *s, + unsigned start) +{ + smp_rmb(); + return unlikely(s->seq != start); +} + +static inline void gtod_write_begin(struct vsyscall_gtod_data *s) +{ + ++s->seq; + smp_wmb(); +} + +static inline void gtod_write_end(struct vsyscall_gtod_data *s) +{ + smp_wmb(); + ++s->seq; +} + #endif /* _ASM_X86_VGTOD_H */ diff --git a/arch/x86/include/asm/vvar.h b/arch/x86/include/asm/vvar.h index d76ac40da206..081d909bc495 100644 --- a/arch/x86/include/asm/vvar.h +++ b/arch/x86/include/asm/vvar.h @@ -16,8 +16,8 @@ * you mess up, the linker will catch it.) */ -/* Base address of vvars. This is not ABI. */ -#define VVAR_ADDRESS (-10*1024*1024 - 4096) +#ifndef _ASM_X86_VVAR_H +#define _ASM_X86_VVAR_H #if defined(__VVAR_KERNEL_LDS) @@ -29,16 +29,35 @@ #else +#ifdef BUILD_VDSO32 + +#define DECLARE_VVAR(offset, type, name) \ + extern type vvar_ ## name __attribute__((visibility("hidden"))); + +#define VVAR(name) (vvar_ ## name) + +#else + +extern char __vvar_page; + +/* Base address of vvars. This is not ABI. */ +#ifdef CONFIG_X86_64 +#define VVAR_ADDRESS (-10*1024*1024 - 4096) +#else +#define VVAR_ADDRESS (&__vvar_page) +#endif + #define DECLARE_VVAR(offset, type, name) \ static type const * const vvaraddr_ ## name = \ (void *)(VVAR_ADDRESS + (offset)); +#define VVAR(name) (*vvaraddr_ ## name) +#endif + #define DEFINE_VVAR(type, name) \ type name \ __attribute__((section(".vvar_" #name), aligned(16))) __visible -#define VVAR(name) (*vvaraddr_ ## name) - #endif /* DECLARE_VVAR(offset, type, name) */ @@ -48,3 +67,5 @@ DECLARE_VVAR(16, int, vgetcpu_mode) DECLARE_VVAR(128, struct vsyscall_gtod_data, vsyscall_gtod_data) #undef DECLARE_VVAR + +#endif diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile index cb648c84b327..f4d96000d33a 100644 --- a/arch/x86/kernel/Makefile +++ b/arch/x86/kernel/Makefile @@ -26,7 +26,7 @@ obj-$(CONFIG_IRQ_WORK) += irq_work.o obj-y += probe_roms.o obj-$(CONFIG_X86_32) += i386_ksyms_32.o obj-$(CONFIG_X86_64) += sys_x86_64.o x8664_ksyms_64.o -obj-y += syscall_$(BITS).o +obj-y += syscall_$(BITS).o vsyscall_gtod.o obj-$(CONFIG_X86_64) += vsyscall_64.o obj-$(CONFIG_X86_64) += vsyscall_emu_64.o obj-$(CONFIG_SYSFS) += ksysfs.o diff --git a/arch/x86/kernel/hpet.c b/arch/x86/kernel/hpet.c index 014618dbaa7b..93eed15a8fd4 100644 --- a/arch/x86/kernel/hpet.c +++ b/arch/x86/kernel/hpet.c @@ -752,9 +752,7 @@ static struct clocksource clocksource_hpet = { .mask = HPET_MASK, .flags = CLOCK_SOURCE_IS_CONTINUOUS, .resume = hpet_resume_counter, -#ifdef CONFIG_X86_64 .archdata = { .vclock_mode = VCLOCK_HPET }, -#endif }; static int hpet_clocksource_register(void) diff --git a/arch/x86/kernel/tsc.c b/arch/x86/kernel/tsc.c index 7a9296ab8834..57e5ce126d5a 100644 --- a/arch/x86/kernel/tsc.c +++ b/arch/x86/kernel/tsc.c @@ -984,9 +984,7 @@ static struct clocksource clocksource_tsc = { .mask = CLOCKSOURCE_MASK(64), .flags = CLOCK_SOURCE_IS_CONTINUOUS | CLOCK_SOURCE_MUST_VERIFY, -#ifdef CONFIG_X86_64 .archdata = { .vclock_mode = VCLOCK_TSC }, -#endif }; void mark_tsc_unstable(char *reason) diff --git a/arch/x86/kernel/vmlinux.lds.S b/arch/x86/kernel/vmlinux.lds.S index da6b35a98260..49edf2dd3613 100644 --- a/arch/x86/kernel/vmlinux.lds.S +++ b/arch/x86/kernel/vmlinux.lds.S @@ -147,7 +147,6 @@ SECTIONS _edata = .; } :data -#ifdef CONFIG_X86_64 . = ALIGN(PAGE_SIZE); __vvar_page = .; @@ -165,12 +164,15 @@ SECTIONS #undef __VVAR_KERNEL_LDS #undef EMIT_VVAR + /* + * Pad the rest of the page with zeros. Otherwise the loader + * can leave garbage here. + */ + . = __vvar_beginning_hack + PAGE_SIZE; } :data . = ALIGN(__vvar_page + PAGE_SIZE, PAGE_SIZE); -#endif /* CONFIG_X86_64 */ - /* Init code and data - will be freed after init */ . = ALIGN(PAGE_SIZE); .init.begin : AT(ADDR(.init.begin) - LOAD_OFFSET) { diff --git a/arch/x86/kernel/vsyscall_64.c b/arch/x86/kernel/vsyscall_64.c index 1f96f9347ed9..9ea287666c65 100644 --- a/arch/x86/kernel/vsyscall_64.c +++ b/arch/x86/kernel/vsyscall_64.c @@ -47,14 +47,12 @@ #include <asm/segment.h> #include <asm/desc.h> #include <asm/topology.h> -#include <asm/vgtod.h> #include <asm/traps.h> #define CREATE_TRACE_POINTS #include "vsyscall_trace.h" DEFINE_VVAR(int, vgetcpu_mode); -DEFINE_VVAR(struct vsyscall_gtod_data, vsyscall_gtod_data); static enum { EMULATE, NATIVE, NONE } vsyscall_mode = EMULATE; @@ -77,48 +75,6 @@ static int __init vsyscall_setup(char *str) } early_param("vsyscall", vsyscall_setup); -void update_vsyscall_tz(void) -{ - vsyscall_gtod_data.sys_tz = sys_tz; -} - -void update_vsyscall(struct timekeeper *tk) -{ - struct vsyscall_gtod_data *vdata = &vsyscall_gtod_data; - - write_seqcount_begin(&vdata->seq); - - /* copy vsyscall data */ - vdata->clock.vclock_mode = tk->clock->archdata.vclock_mode; - vdata->clock.cycle_last = tk->clock->cycle_last; - vdata->clock.mask = tk->clock->mask; - vdata->clock.mult = tk->mult; - vdata->clock.shift = tk->shift; - - vdata->wall_time_sec = tk->xtime_sec; - vdata->wall_time_snsec = tk->xtime_nsec; - - vdata->monotonic_time_sec = tk->xtime_sec - + tk->wall_to_monotonic.tv_sec; - vdata->monotonic_time_snsec = tk->xtime_nsec - + (tk->wall_to_monotonic.tv_nsec - << tk->shift); - while (vdata->monotonic_time_snsec >= - (((u64)NSEC_PER_SEC) << tk->shift)) { - vdata->monotonic_time_snsec -= - ((u64)NSEC_PER_SEC) << tk->shift; - vdata->monotonic_time_sec++; - } - - vdata->wall_time_coarse.tv_sec = tk->xtime_sec; - vdata->wall_time_coarse.tv_nsec = (long)(tk->xtime_nsec >> tk->shift); - - vdata->monotonic_time_coarse = timespec_add(vdata->wall_time_coarse, - tk->wall_to_monotonic); - - write_seqcount_end(&vdata->seq); -} - static void warn_bad_vsyscall(const char *level, struct pt_regs *regs, const char *message) { @@ -374,7 +330,6 @@ void __init map_vsyscall(void) { extern char __vsyscall_page; unsigned long physaddr_vsyscall = __pa_symbol(&__vsyscall_page); - extern char __vvar_page; unsigned long physaddr_vvar_page = __pa_symbol(&__vvar_page); __set_fixmap(VSYSCALL_FIRST_PAGE, physaddr_vsyscall, diff --git a/arch/x86/kernel/vsyscall_gtod.c b/arch/x86/kernel/vsyscall_gtod.c new file mode 100644 index 000000000000..f9c6e56e14b5 --- /dev/null +++ b/arch/x86/kernel/vsyscall_gtod.c @@ -0,0 +1,69 @@ +/* + * Copyright (C) 2001 Andrea Arcangeli <andrea@suse.de> SuSE + * Copyright 2003 Andi Kleen, SuSE Labs. + * + * Modified for x86 32 bit architecture by + * Stefani Seibold <stefani@seibold.net> + * sponsored by Rohde & Schwarz GmbH & Co. KG Munich/Germany + * + * Thanks to hpa@transmeta.com for some useful hint. + * Special thanks to Ingo Molnar for his early experience with + * a different vsyscall implementation for Linux/IA32 and for the name. + * + */ + +#include <linux/timekeeper_internal.h> +#include <asm/vgtod.h> +#include <asm/vvar.h> + +DEFINE_VVAR(struct vsyscall_gtod_data, vsyscall_gtod_data); + +void update_vsyscall_tz(void) +{ + vsyscall_gtod_data.tz_minuteswest = sys_tz.tz_minuteswest; + vsyscall_gtod_data.tz_dsttime = sys_tz.tz_dsttime; +} + +void update_vsyscall(struct timekeeper *tk) +{ + struct vsyscall_gtod_data *vdata = &vsyscall_gtod_data; + + gtod_write_begin(vdata); + + /* copy vsyscall data */ + vdata->vclock_mode = tk->clock->archdata.vclock_mode; + vdata->cycle_last = tk->clock->cycle_last; + vdata->mask = tk->clock->mask; + vdata->mult = tk->mult; + vdata->shift = tk->shift; + + vdata->wall_time_sec = tk->xtime_sec; + vdata->wall_time_snsec = tk->xtime_nsec; + + vdata->monotonic_time_sec = tk->xtime_sec + + tk->wall_to_monotonic.tv_sec; + vdata->monotonic_time_snsec = tk->xtime_nsec + + (tk->wall_to_monotonic.tv_nsec + << tk->shift); + while (vdata->monotonic_time_snsec >= + (((u64)NSEC_PER_SEC) << tk->shift)) { + vdata->monotonic_time_snsec -= + ((u64)NSEC_PER_SEC) << tk->shift; + vdata->monotonic_time_sec++; + } + + vdata->wall_time_coarse_sec = tk->xtime_sec; + vdata->wall_time_coarse_nsec = (long)(tk->xtime_nsec >> tk->shift); + + vdata->monotonic_time_coarse_sec = + vdata->wall_time_coarse_sec + tk->wall_to_monotonic.tv_sec; + vdata->monotonic_time_coarse_nsec = + vdata->wall_time_coarse_nsec + tk->wall_to_monotonic.tv_nsec; + + while (vdata->monotonic_time_coarse_nsec >= NSEC_PER_SEC) { + vdata->monotonic_time_coarse_nsec -= NSEC_PER_SEC; + vdata->monotonic_time_coarse_sec++; + } + + gtod_write_end(vdata); +} diff --git a/arch/x86/tools/relocs.c b/arch/x86/tools/relocs.c index cfbdbdb4e173..bbb1d2259ecf 100644 --- a/arch/x86/tools/relocs.c +++ b/arch/x86/tools/relocs.c @@ -69,8 +69,8 @@ static const char * const sym_regex_kernel[S_NSYMTYPES] = { "__per_cpu_load|" "init_per_cpu__.*|" "__end_rodata_hpage_align|" - "__vvar_page|" #endif + "__vvar_page|" "_end)$" }; diff --git a/arch/x86/vdso/Makefile b/arch/x86/vdso/Makefile index 9206ac7961a5..c580d1210ffe 100644 --- a/arch/x86/vdso/Makefile +++ b/arch/x86/vdso/Makefile @@ -23,7 +23,8 @@ vobjs-$(VDSOX32-y) += $(vobjx32s-compat) vobj64s := $(filter-out $(vobjx32s-compat),$(vobjs-y)) # files to link into kernel -obj-$(VDSO64-y) += vma.o vdso.o +obj-y += vma.o +obj-$(VDSO64-y) += vdso.o obj-$(VDSOX32-y) += vdsox32.o obj-$(VDSO32-y) += vdso32.o vdso32-setup.o @@ -138,7 +139,7 @@ override obj-dirs = $(dir $(obj)) $(obj)/vdso32/ targets += vdso32/vdso32.lds targets += $(vdso32-images) $(vdso32-images:=.dbg) -targets += vdso32/note.o $(vdso32.so-y:%=vdso32/%.o) +targets += vdso32/note.o vdso32/vclock_gettime.o $(vdso32.so-y:%=vdso32/%.o) extra-y += $(vdso32-images) @@ -148,8 +149,19 @@ KBUILD_AFLAGS_32 := $(filter-out -m64,$(KBUILD_AFLAGS)) $(vdso32-images:%=$(obj)/%.dbg): KBUILD_AFLAGS = $(KBUILD_AFLAGS_32) $(vdso32-images:%=$(obj)/%.dbg): asflags-$(CONFIG_X86_64) += -m32 +KBUILD_CFLAGS_32 := $(filter-out -m64,$(KBUILD_CFLAGS)) +KBUILD_CFLAGS_32 := $(filter-out -mcmodel=kernel,$(KBUILD_CFLAGS_32)) +KBUILD_CFLAGS_32 := $(filter-out -fno-pic,$(KBUILD_CFLAGS_32)) +KBUILD_CFLAGS_32 := $(filter-out -mfentry,$(KBUILD_CFLAGS_32)) +KBUILD_CFLAGS_32 += -m32 -msoft-float -mregparm=0 -fpic +KBUILD_CFLAGS_32 += $(call cc-option, -fno-stack-protector) +KBUILD_CFLAGS_32 += $(call cc-option, -foptimize-sibling-calls) +KBUILD_CFLAGS_32 += -fno-omit-frame-pointer +$(vdso32-images:%=$(obj)/%.dbg): KBUILD_CFLAGS = $(KBUILD_CFLAGS_32) + $(vdso32-images:%=$(obj)/%.dbg): $(obj)/vdso32-%.so.dbg: FORCE \ $(obj)/vdso32/vdso32.lds \ + $(obj)/vdso32/vclock_gettime.o \ $(obj)/vdso32/note.o \ $(obj)/vdso32/%.o $(call if_changed,vdso) diff --git a/arch/x86/vdso/vclock_gettime.c b/arch/x86/vdso/vclock_gettime.c index eb5d7a56f8d4..16d686171e9a 100644 --- a/arch/x86/vdso/vclock_gettime.c +++ b/arch/x86/vdso/vclock_gettime.c @@ -4,6 +4,9 @@ * * Fast user context implementation of clock_gettime, gettimeofday, and time. * + * 32 Bit compat layer by Stefani Seibold <stefani@seibold.net> + * sponsored by Rohde & Schwarz GmbH & Co. KG Munich/Germany + * * The code should have no internal unresolved relocations. * Check with readelf after changing. */ @@ -11,56 +14,55 @@ /* Disable profiling for userspace code: */ #define DISABLE_BRANCH_PROFILING -#include <linux/kernel.h> -#include <linux/posix-timers.h> -#include <linux/time.h> -#include <linux/string.h> -#include <asm/vsyscall.h> -#include <asm/fixmap.h> +#include <uapi/linux/time.h> #include <asm/vgtod.h> -#include <asm/timex.h> #include <asm/hpet.h> +#include <asm/vvar.h> #include <asm/unistd.h> -#include <asm/io.h> -#include <asm/pvclock.h> +#include <asm/msr.h> +#include <linux/math64.h> +#include <linux/time.h> #define gtod (&VVAR(vsyscall_gtod_data)) -notrace static cycle_t vread_tsc(void) +extern int __vdso_clock_gettime(clockid_t clock, struct timespec *ts); +extern int __vdso_gettimeofday(struct timeval *tv, struct timezone *tz); +extern time_t __vdso_time(time_t *t); + +#ifdef CONFIG_HPET_TIMER +static inline u32 read_hpet_counter(const volatile void *addr) { - cycle_t ret; - u64 last; + return *(const volatile u32 *) (addr + HPET_COUNTER); +} +#endif - /* - * Empirically, a fence (of type that depends on the CPU) - * before rdtsc is enough to ensure that rdtsc is ordered - * with respect to loads. The various CPU manuals are unclear - * as to whether rdtsc can be reordered with later loads, - * but no one has ever seen it happen. - */ - rdtsc_barrier(); - ret = (cycle_t)vget_cycles(); +#ifndef BUILD_VDSO32 - last = VVAR(vsyscall_gtod_data).clock.cycle_last; +#include <linux/kernel.h> +#include <asm/vsyscall.h> +#include <asm/fixmap.h> +#include <asm/pvclock.h> - if (likely(ret >= last)) - return ret; +static notrace cycle_t vread_hpet(void) +{ + return read_hpet_counter((const void *)fix_to_virt(VSYSCALL_HPET)); +} - /* - * GCC likes to generate cmov here, but this branch is extremely - * predictable (it's just a funciton of time and the likely is - * very likely) and there's a data dependence, so force GCC - * to generate a branch instead. I don't barrier() because - * we don't actually need a barrier, and if this function - * ever gets inlined it will generate worse code. - */ - asm volatile (""); - return last; +notrace static long vdso_fallback_gettime(long clock, struct timespec *ts) +{ + long ret; + asm("syscall" : "=a" (ret) : + "0" (__NR_clock_gettime), "D" (clock), "S" (ts) : "memory"); + return ret; } -static notrace cycle_t vread_hpet(void) +notrace static long vdso_fallback_gtod(struct timeval *tv, struct timezone *tz) { - return readl((const void __iomem *)fix_to_virt(VSYSCALL_HPET) + HPET_COUNTER); + long ret; + + asm("syscall" : "=a" (ret) : + "0" (__NR_gettimeofday), "D" (tv), "S" (tz) : "memory"); + return ret; } #ifdef CONFIG_PARAVIRT_CLOCK @@ -124,7 +126,7 @@ static notrace cycle_t vread_pvclock(int *mode) *mode = VCLOCK_NONE; /* refer to tsc.c read_tsc() comment for rationale */ - last = VVAR(vsyscall_gtod_data).clock.cycle_last; + last = gtod->cycle_last; if (likely(ret >= last)) return ret; @@ -133,11 +135,30 @@ static notrace cycle_t vread_pvclock(int *mode) } #endif +#else + +extern u8 hpet_page + __attribute__((visibility("hidden"))); + +#ifdef CONFIG_HPET_TIMER +static notrace cycle_t vread_hpet(void) +{ + return read_hpet_counter((const void *)(&hpet_page)); +} +#endif + notrace static long vdso_fallback_gettime(long clock, struct timespec *ts) { long ret; - asm("syscall" : "=a" (ret) : - "0" (__NR_clock_gettime),"D" (clock), "S" (ts) : "memory"); + + asm( + "mov %%ebx, %%edx \n" + "mov %2, %%ebx \n" + "call VDSO32_vsyscall \n" + "mov %%edx, %%ebx \n" + : "=a" (ret) + : "0" (__NR_clock_gettime), "g" (clock), "c" (ts) + : "memory", "edx"); return ret; } @@ -145,28 +166,79 @@ 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"); + asm( + "mov %%ebx, %%edx \n" + "mov %2, %%ebx \n" + "call VDSO32_vsyscall \n" + "mov %%edx, %%ebx \n" + : "=a" (ret) + : "0" (__NR_gettimeofday), "g" (tv), "c" (tz) + : "memory", "edx"); return ret; } +#ifdef CONFIG_PARAVIRT_CLOCK + +static notrace cycle_t vread_pvclock(int *mode) +{ + *mode = VCLOCK_NONE; + return 0; +} +#endif + +#endif + +notrace static cycle_t vread_tsc(void) +{ + cycle_t ret; + u64 last; + + /* + * Empirically, a fence (of type that depends on the CPU) |