From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1754757Ab1E3Dtb (ORCPT ); Sun, 29 May 2011 23:49:31 -0400 Received: from DMZ-MAILSEC-SCANNER-2.MIT.EDU ([18.9.25.13]:47892 "EHLO dmz-mailsec-scanner-2.mit.edu" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1753275Ab1E3Dt2 (ORCPT ); Sun, 29 May 2011 23:49:28 -0400 X-AuditID: 1209190d-b7bdeae0000004f8-a8-4de31388cad3 From: Andy Lutomirski To: Ingo Molnar , x86@kernel.org Cc: Thomas Gleixner , linux-kernel@vger.kernel.org, Jesper Juhl , Borislav Petkov , Linus Torvalds , Andrew Morton , Arjan van de Ven , Jan Beulich , richard -rw- weinberger , Mikael Pettersson , Andy Lutomirski Subject: [PATCH v2 03/10] x86-64: Remove kernel.vsyscall64 sysctl Date: Sun, 29 May 2011 23:48:40 -0400 Message-Id: <90d0671510f3dca4e2a08b1683354f276dafef8b.1306724657.git.luto@mit.edu> X-Mailer: git-send-email 1.7.5.1 In-Reply-To: References: In-Reply-To: References: X-Brightmail-Tracker: H4sIAAAAAAAAA+NgFtrCKsWRmVeSWpSXmKPExsUixG6nrtsh/NjXYO1TIYs569ewWfRdOcpu Mesar8XnDf/YLA78espm8f7qdjaLy7vmsFk8ab7OaLHlUjOrxYeJG9gsNm+aymzxqO8tu8WP DY9ZHXg9vrf2sXgcO3OY0eNW2x9mj52z7rJ7bF6h5fH/5RE2j02rOtk83p07x+5xYsZvFo/j Z5w9Pm+SC+CO4rJJSc3JLEst0rdL4MqYs3kNa8F+g4rOs9PZGxhfq3cxcnJICJhIbD3+nRHC FpO4cG89WxcjF4eQwD5Gicsn/rBAOBsYJX6cOMsE4Txjkth26QQbSAubgIpEx9IHQAkODhEB fYmrnxlBapgFnjNLPHi4ixWkRljAUWLahvUsIDaLgKrE7el9zCD1vAJBEqf+akBsVpC4cmUe WAmngIHEyTv3wGwhoJHzbr1lwyU+gVFgASPDKkbZlNwq3dzEzJzi1GTd4uTEvLzUIl0jvdzM Er3UlNJNjKAI4ZTk3cH47qDSIUYBDkYlHl7Xoke+QqyJZcWVuYcYJTmYlER5Hwk+9hXiS8pP qcxILM6ILyrNSS0+xCjBwawkwqv+C6icNyWxsiq1KB8mJc3BoiTOO1NS3VdIID2xJDU7NbUg tQgmK8PBoSTBGwZMBEKCRanpqRVpmTklCGkmDk6Q4TxAw/VBFvMWFyTmFmemQ+RPMepyNK7d cZBRiCUvPy9VSpzXBmSQAEhRRmke3BxYYnvFKA70ljDvFSGgKh5gUoSb9ApoCRPQkt53D0GW lCQipKQaGBevPrVjr0ci4zXOQIOfXh3PTjVkuPHxpvrutRPU1Wq8dDtuzen6ZdET25tmZPZv bCt3ie4wOu3kfveBJeMX3jkHWK+Uaees2he3Wzj82wKrNc+npKd+Tdf+nP1/654Pr2y++Tz1 977f7sjwe69z0809GWuNX33iYk+eemv55uYDkgmnuZsfhSixFGckGmoxFxUnAgCpiEfcRwMA AA== Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org It's unnecessary overhead in code that's supposed to be highly optimized. Removing it allows us to remove one of the two syscall instructions in the vsyscall page. The only sensible use for it is for UML users, and it doesn't fully address inconsistent vsyscall results on UML. The real fix for UML is to stop using vsyscalls entirely. Signed-off-by: Andy Lutomirski --- arch/x86/include/asm/vgtod.h | 1 - arch/x86/kernel/vsyscall_64.c | 34 +------------------------ arch/x86/vdso/vclock_gettime.c | 55 +++++++++++++++------------------------ 3 files changed, 22 insertions(+), 68 deletions(-) diff --git a/arch/x86/include/asm/vgtod.h b/arch/x86/include/asm/vgtod.h index 646b4c1..aa5add8 100644 --- a/arch/x86/include/asm/vgtod.h +++ b/arch/x86/include/asm/vgtod.h @@ -11,7 +11,6 @@ struct vsyscall_gtod_data { time_t wall_time_sec; u32 wall_time_nsec; - int sysctl_enabled; struct timezone sys_tz; struct { /* extract of a clocksource struct */ cycle_t (*vread)(void); diff --git a/arch/x86/kernel/vsyscall_64.c b/arch/x86/kernel/vsyscall_64.c index ee22180..3e8dac7 100644 --- a/arch/x86/kernel/vsyscall_64.c +++ b/arch/x86/kernel/vsyscall_64.c @@ -53,7 +53,6 @@ DEFINE_VVAR(int, vgetcpu_mode); DEFINE_VVAR(struct vsyscall_gtod_data, vsyscall_gtod_data) = { .lock = SEQLOCK_UNLOCKED, - .sysctl_enabled = 1, }; void update_vsyscall_tz(void) @@ -103,15 +102,6 @@ static __always_inline int gettimeofday(struct timeval *tv, struct timezone *tz) return ret; } -static __always_inline long time_syscall(long *t) -{ - long secs; - asm volatile("syscall" - : "=a" (secs) - : "0" (__NR_time),"D" (t) : __syscall_clobber); - return secs; -} - static __always_inline void do_vgettimeofday(struct timeval * tv) { cycle_t now, base, mask, cycle_delta; @@ -122,8 +112,7 @@ static __always_inline void do_vgettimeofday(struct timeval * tv) seq = read_seqbegin(&VVAR(vsyscall_gtod_data).lock); vread = VVAR(vsyscall_gtod_data).clock.vread; - if (unlikely(!VVAR(vsyscall_gtod_data).sysctl_enabled || - !vread)) { + if (unlikely(!vread)) { gettimeofday(tv,NULL); return; } @@ -165,8 +154,6 @@ time_t __vsyscall(1) vtime(time_t *t) { unsigned seq; time_t result; - if (unlikely(!VVAR(vsyscall_gtod_data).sysctl_enabled)) - return time_syscall(t); do { seq = read_seqbegin(&VVAR(vsyscall_gtod_data).lock); @@ -227,22 +214,6 @@ static long __vsyscall(3) venosys_1(void) return -ENOSYS; } -#ifdef CONFIG_SYSCTL -static ctl_table kernel_table2[] = { - { .procname = "vsyscall64", - .data = &vsyscall_gtod_data.sysctl_enabled, .maxlen = sizeof(int), - .mode = 0644, - .proc_handler = proc_dointvec }, - {} -}; - -static ctl_table kernel_root_table2[] = { - { .procname = "kernel", .mode = 0555, - .child = kernel_table2 }, - {} -}; -#endif - /* Assume __initcall executes before all user space. Hopefully kmod doesn't violate that. We'll find out if it does. */ static void __cpuinit vsyscall_set_cpu(int cpu) @@ -301,9 +272,6 @@ static int __init vsyscall_init(void) BUG_ON((unsigned long) &vtime != VSYSCALL_ADDR(__NR_vtime)); BUG_ON((VSYSCALL_ADDR(0) != __fix_to_virt(VSYSCALL_FIRST_PAGE))); BUG_ON((unsigned long) &vgetcpu != VSYSCALL_ADDR(__NR_vgetcpu)); -#ifdef CONFIG_SYSCTL - register_sysctl_table(kernel_root_table2); -#endif on_each_cpu(cpu_vsyscall_init, NULL, 1); /* notifier priority > KVM */ hotcpu_notifier(cpu_vsyscall_notifier, 30); diff --git a/arch/x86/vdso/vclock_gettime.c b/arch/x86/vdso/vclock_gettime.c index a724905..cf54813 100644 --- a/arch/x86/vdso/vclock_gettime.c +++ b/arch/x86/vdso/vclock_gettime.c @@ -116,21 +116,21 @@ notrace static noinline int do_monotonic_coarse(struct timespec *ts) notrace int __vdso_clock_gettime(clockid_t clock, struct timespec *ts) { - if (likely(gtod->sysctl_enabled)) - switch (clock) { - case CLOCK_REALTIME: - if (likely(gtod->clock.vread)) - return do_realtime(ts); - break; - case CLOCK_MONOTONIC: - if (likely(gtod->clock.vread)) - return do_monotonic(ts); - break; - case CLOCK_REALTIME_COARSE: - return do_realtime_coarse(ts); - case CLOCK_MONOTONIC_COARSE: - return do_monotonic_coarse(ts); - } + switch (clock) { + case CLOCK_REALTIME: + if (likely(gtod->clock.vread)) + return do_realtime(ts); + break; + case CLOCK_MONOTONIC: + if (likely(gtod->clock.vread)) + return do_monotonic(ts); + break; + case CLOCK_REALTIME_COARSE: + return do_realtime_coarse(ts); + case CLOCK_MONOTONIC_COARSE: + return do_monotonic_coarse(ts); + } + return vdso_fallback_gettime(clock, ts); } int clock_gettime(clockid_t, struct timespec *) @@ -139,7 +139,7 @@ int clock_gettime(clockid_t, struct timespec *) notrace int __vdso_gettimeofday(struct timeval *tv, struct timezone *tz) { long ret; - if (likely(gtod->sysctl_enabled && gtod->clock.vread)) { + if (likely(gtod->clock.vread)) { if (likely(tv != NULL)) { BUILD_BUG_ON(offsetof(struct timeval, tv_usec) != offsetof(struct timespec, tv_nsec) || @@ -161,27 +161,14 @@ notrace int __vdso_gettimeofday(struct timeval *tv, struct timezone *tz) int gettimeofday(struct timeval *, struct timezone *) __attribute__((weak, alias("__vdso_gettimeofday"))); -/* This will break when the xtime seconds get inaccurate, but that is - * unlikely */ - -static __always_inline long time_syscall(long *t) -{ - long secs; - asm volatile("syscall" - : "=a" (secs) - : "0" (__NR_time), "D" (t) : "cc", "r11", "cx", "memory"); - return secs; -} - +/* + * This will break when the xtime seconds get inaccurate, but that is + * unlikely + */ notrace time_t __vdso_time(time_t *t) { - time_t result; - - if (unlikely(!VVAR(vsyscall_gtod_data).sysctl_enabled)) - return time_syscall(t); - /* This is atomic on x86_64 so we don't need any locks. */ - result = ACCESS_ONCE(VVAR(vsyscall_gtod_data).wall_time_sec); + time_t result = ACCESS_ONCE(VVAR(vsyscall_gtod_data).wall_time_sec); if (t) *t = result; -- 1.7.5.1