x86-64: Remove kernel.vsyscall64 sysctl

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 <luto@mit.edu>
Cc: Jesper Juhl <jj@chaosbits.net>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Arjan van de Ven <arjan@infradead.org>
Cc: Jan Beulich <JBeulich@novell.com>
Cc: richard -rw- weinberger <richard.weinberger@gmail.com>
Cc: Mikael Pettersson <mikpe@it.uu.se>
Cc: Andi Kleen <andi@firstfloor.org>
Cc: Brian Gerst <brgerst@gmail.com>
Cc: Louis Rilling <Louis.Rilling@kerlabs.com>
Cc: Valdis.Kletnieks@vt.edu
Cc: pageexec@freemail.hu
Link: http://lkml.kernel.org/r/973ae803fe76f712da4b2740e66dccf452d3b1e4.1307292171.git.luto@mit.edu
Signed-off-by: Ingo Molnar <mingo@elte.hu>

diff --git a/arch/x86/include/asm/vgtod.h b/arch/x86/include/asm/vgtod.h
index 646b4c1..aa5add8 100644 (file)
--- 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 3cf1cef..9b2f3f5 100644 (file)
--- 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(__vsyscall_gtod_data.lock),
-       .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 (file)
--- 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;