vDSO time changes for 2.6.40

index 9064052..bb05228 100644
@@ -1,20 +1,6 @@
 #ifndef _ASM_X86_VDSO_H
 #define _ASM_X86_VDSO_H
 
-#ifdef CONFIG_X86_64
-extern const char VDSO64_PRELINK[];
-
-/*
- * Given a pointer to the vDSO image, find the pointer to VDSO64_name
- * as that symbol is defined in the vDSO sources or linker script.
- */
-#define VDSO64_SYMBOL(base, name)					\
-({									\
-	extern const char VDSO64_##name[];				\
-	(void *)(VDSO64_##name - VDSO64_PRELINK + (unsigned long)(base)); \
-})
-#endif
-
 #if defined CONFIG_X86_32 || defined CONFIG_COMPAT
 extern const char VDSO32_PRELINK[];
 

index 3d61e20..646b4c1 100644
@@ -23,8 +23,6 @@ struct vsyscall_gtod_data {
 	struct timespec wall_to_monotonic;
 	struct timespec wall_time_coarse;
 };
-extern struct vsyscall_gtod_data __vsyscall_gtod_data
-__section_vsyscall_gtod_data;
 extern struct vsyscall_gtod_data vsyscall_gtod_data;
 
 #endif /* _ASM_X86_VGTOD_H */

index d0983d2..d555973 100644
@@ -16,27 +16,19 @@ enum vsyscall_num {
 #ifdef __KERNEL__
 #include <linux/seqlock.h>
 
-#define __section_vgetcpu_mode __attribute__ ((unused, __section__ (".vgetcpu_mode"), aligned(16)))
-#define __section_jiffies __attribute__ ((unused, __section__ (".jiffies"), aligned(16)))
-
 /* Definitions for CONFIG_GENERIC_TIME definitions */
-#define __section_vsyscall_gtod_data __attribute__ \
-	((unused, __section__ (".vsyscall_gtod_data"),aligned(16)))
-#define __section_vsyscall_clock __attribute__ \
-	((unused, __section__ (".vsyscall_clock"),aligned(16)))
 #define __vsyscall_fn \
 	__attribute__ ((unused, __section__(".vsyscall_fn"))) notrace
 
 #define VGETCPU_RDTSCP	1
 #define VGETCPU_LSL	2
 
-extern int __vgetcpu_mode;
-extern volatile unsigned long __jiffies;
-
 /* kernel space (writeable) */
 extern int vgetcpu_mode;
 extern struct timezone sys_tz;
 
+#include <asm/vvar.h>
+
 extern void map_vsyscall(void);
 
 #endif /* __KERNEL__ */

52 lines not on this page · raw message

index 25a28a2..00cbb27 100644
@@ -23,7 +23,7 @@
 #include <asm/time.h>
 
 #ifdef CONFIG_X86_64
-volatile unsigned long __jiffies __section_jiffies = INITIAL_JIFFIES;
+DEFINE_VVAR(volatile unsigned long, jiffies) = INITIAL_JIFFIES;
 #endif
 
 unsigned long profile_pc(struct pt_regs *regs)

index 9335bf7..db697b8 100644
@@ -777,8 +777,8 @@ static cycle_t __vsyscall_fn vread_tsc(void)
 	ret = (cycle_t)vget_cycles();
 	rdtsc_barrier();
 
-	return ret >= __vsyscall_gtod_data.clock.cycle_last ?
-		ret : __vsyscall_gtod_data.clock.cycle_last;
+	return ret >= VVAR(vsyscall_gtod_data).clock.cycle_last ?
+		ret : VVAR(vsyscall_gtod_data).clock.cycle_last;
 }
 #endif
 

89 lines not on this page · raw message

index ee55754..0b873d4 100644
@@ -22,9 +22,8 @@
 #include <asm/hpet.h>
 #include <asm/unistd.h>
 #include <asm/io.h>
-#include "vextern.h"
 
-#define gtod vdso_vsyscall_gtod_data
+#define gtod (&VVAR(vsyscall_gtod_data))
 
 notrace static long vdso_fallback_gettime(long clock, struct timespec *ts)
 {

deleted file mode 100644
index 1683ba2..0000000
@@ -1,16 +0,0 @@
-#ifndef VEXTERN
-#include <asm/vsyscall.h>
-#define VEXTERN(x) \
-	extern typeof(x) *vdso_ ## x __attribute__((visibility("hidden")));
-#endif
-
-#define VMAGIC 0xfeedbabeabcdefabUL
-
-/* Any kernel variables used in the vDSO must be exported in the main
-   kernel's vmlinux.lds.S/vsyscall.h/proper __section and
-   put into vextern.h and be referenced as a pointer with vdso prefix.
-   The main kernel later fills in the values.   */
-
-VEXTERN(jiffies)
-VEXTERN(vgetcpu_mode)
-VEXTERN(vsyscall_gtod_data)

index 9fbc6b2..5463ad5 100644
@@ -11,14 +11,13 @@
 #include <linux/time.h>
 #include <asm/vsyscall.h>
 #include <asm/vgtod.h>
-#include "vextern.h"
 
 notrace long
 __vdso_getcpu(unsigned *cpu, unsigned *node, struct getcpu_cache *unused)
 {
 	unsigned int p;
 
-	if (*vdso_vgetcpu_mode == VGETCPU_RDTSCP) {
+	if (VVAR(vgetcpu_mode) == VGETCPU_RDTSCP) {
 		/* Load per CPU data from RDTSCP */
 		native_read_tscp(&p);
 	} else {

index 4b5d26f..7abd2be 100644
@@ -15,9 +15,6 @@
 #include <asm/proto.h>
 #include <asm/vdso.h>
 
-#include "vextern.h"		/* Just for VMAGIC.  */
-#undef VEXTERN
-
 unsigned int __read_mostly vdso_enabled = 1;
 
 extern char vdso_start[], vdso_end[];

@@ -26,20 +23,10 @@ extern unsigned short vdso_sync_cpuid;
 static struct page **vdso_pages;
 static unsigned vdso_size;
 
-static inline void *var_ref(void *p, char *name)
-{
-	if (*(void **)p != (void *)VMAGIC) {
-		printk("VDSO: variable %s broken\n", name);
-		vdso_enabled = 0;
-	}
-	return p;
-}
-
 static int __init init_vdso_vars(void)
 {
 	int npages = (vdso_end - vdso_start + PAGE_SIZE - 1) / PAGE_SIZE;
 	int i;
-	char *vbase;
 
 	vdso_size = npages << PAGE_SHIFT;
 	vdso_pages = kmalloc(sizeof(struct page *) * npages, GFP_KERNEL);

@@ -54,20 +41,6 @@ static int __init init_vdso_vars(void)
 		copy_page(page_address(p), vdso_start + i*PAGE_SIZE);
 	}
 
-	vbase = vmap(vdso_pages, npages, 0, PAGE_KERNEL);
-	if (!vbase)
-		goto oom;
-
-	if (memcmp(vbase, "\177ELF", 4)) {
-		printk("VDSO: I'm broken; not ELF\n");
-		vdso_enabled = 0;
-	}
-
-#define VEXTERN(x) \
-	*(typeof(__ ## x) **) var_ref(VDSO64_SYMBOL(vbase, x), #x) = &__ ## x;
-#include "vextern.h"
-#undef VEXTERN
-	vunmap(vbase);
 	return 0;
 
  oom:

deleted file mode 100644
index 1b7e703..0000000
@@ -1,12 +0,0 @@
-/* Define pointer to external vDSO variables.
-   These are part of the vDSO. The kernel fills in the real addresses
-   at boot time. This is done because when the vdso is linked the
-   kernel isn't yet and we don't know the final addresses. */
-#include <linux/kernel.h>
-#include <linux/time.h>
-#include <asm/vsyscall.h>
-#include <asm/timex.h>
-#include <asm/vgtod.h>
-
-#define VEXTERN(x) typeof (__ ## x) *const vdso_ ## x = (void *)VMAGIC;
-#include "vextern.h"

index db697b8..1e62442 100644
@@ -769,13 +769,14 @@ static cycle_t __vsyscall_fn vread_tsc(void)
 	cycle_t ret;
 
 	/*
-	 * Surround the RDTSC by barriers, to make sure it's not
-	 * speculated to outside the seqlock critical section and
-	 * does not cause time warps:
+	 * 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();
-	rdtsc_barrier();
 
 	return ret >= VVAR(vsyscall_gtod_data).clock.cycle_last ?
 		ret : VVAR(vsyscall_gtod_data).clock.cycle_last;

index 1e62442..24249a5 100644
@@ -767,6 +767,7 @@ static cycle_t read_tsc(struct clocksource *cs)
 static cycle_t __vsyscall_fn vread_tsc(void)
 {
 	cycle_t ret;
+	u64 last;
 
 	/*
 	 * Empirically, a fence (of type that depends on the CPU)

@@ -778,8 +779,21 @@ static cycle_t __vsyscall_fn vread_tsc(void)
 	rdtsc_barrier();
 	ret = (cycle_t)vget_cycles();
 
-	return ret >= VVAR(vsyscall_gtod_data).clock.cycle_last ?
-		ret : VVAR(vsyscall_gtod_data).clock.cycle_last;
+	last = VVAR(vsyscall_gtod_data).clock.cycle_last;
+
+	if (likely(ret >= last))
+		return ret;
+
+	/*
+	 * 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;
 }
 #endif
 

index 0b873d4..28b2c00 100644
@@ -55,22 +55,6 @@ notrace static noinline int do_realtime(struct timespec *ts)
 	return 0;
 }
 
-/* Copy of the version in kernel/time.c which we cannot directly access */
-notrace static void
-vset_normalized_timespec(struct timespec *ts, long sec, long nsec)
-{
-	while (nsec >= NSEC_PER_SEC) {
-		nsec -= NSEC_PER_SEC;
-		++sec;
-	}
-	while (nsec < 0) {
-		nsec += NSEC_PER_SEC;
-		--sec;
-	}
-	ts->tv_sec = sec;
-	ts->tv_nsec = nsec;
-}
-
 notrace static noinline int do_monotonic(struct timespec *ts)
 {
 	unsigned long seq, ns, secs;

@@ -81,7 +65,17 @@ notrace static noinline int do_monotonic(struct timespec *ts)
 		secs += gtod->wall_to_monotonic.tv_sec;
 		ns += gtod->wall_to_monotonic.tv_nsec;
 	} while (unlikely(read_seqretry(&gtod->lock, seq)));
-	vset_normalized_timespec(ts, secs, ns);
+
+	/* 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;
+
 	return 0;
 }
 

@@ -106,7 +100,17 @@ notrace static noinline int do_monotonic_coarse(struct timespec *ts)
 		secs += gtod->wall_to_monotonic.tv_sec;
 		ns += gtod->wall_to_monotonic.tv_nsec;
 	} while (unlikely(read_seqretry(&gtod->lock, seq)));
-	vset_normalized_timespec(ts, secs, ns);
+
+	/* 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;
+
 	return 0;
 }
 

index 83e2efd..9db5583 100644
@@ -51,6 +51,10 @@ extern int unsynchronized_tsc(void);
 extern int check_tsc_unstable(void);
 extern unsigned long native_calibrate_tsc(void);
 
+#ifdef CONFIG_X86_64
+extern cycles_t vread_tsc(void);
+#endif
+
 /*
  * Boot-time check whether the TSCs are synchronized across
  * all CPUs/cores:

index 24249a5..6cc6922 100644
@@ -763,40 +763,6 @@ static cycle_t read_tsc(struct clocksource *cs)
 		ret : clocksource_tsc.cycle_last;
 }
 
-#ifdef CONFIG_X86_64
-static cycle_t __vsyscall_fn vread_tsc(void)
-{
-	cycle_t ret;
-	u64 last;
-
-	/*
-	 * 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();
-
-	last = VVAR(vsyscall_gtod_data).clock.cycle_last;
-
-	if (likely(ret >= last))
-		return ret;
-
-	/*
-	 * 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;
-}
-#endif
-
 static void resume_tsc(struct clocksource *cs)
 {
 	clocksource_tsc.cycle_last = 0;

new file mode 100644
index 0000000..a81aa9e
@@ -0,0 +1,36 @@
+/* This code runs in userspace. */
+
+#define DISABLE_BRANCH_PROFILING
+#include <asm/vgtod.h>
+
+notrace cycle_t __vsyscall_fn vread_tsc(void)
+{
+	cycle_t ret;
+	u64 last;
+
+	/*
+	 * 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();
+
+	last = VVAR(vsyscall_gtod_data).clock.cycle_last;
+
+	if (likely(ret >= last))
+		return ret;
+
+	/*
+	 * 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;
+}

index 28b2c00..e6e9f90 100644
@@ -2,7 +2,7 @@
  * Copyright 2006 Andi Kleen, SUSE Labs.
  * Subject to the GNU Public License, v.2
  *
- * Fast user context implementation of clock_gettime and gettimeofday.
+ * Fast user context implementation of clock_gettime, gettimeofday, and time.
  *
  * The code should have no internal unresolved relocations.
  * Check with readelf after changing.

@@ -160,3 +160,36 @@ 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;
+}
+
+notrace time_t __vdso_time(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);
+
+		result = VVAR(vsyscall_gtod_data).wall_time_sec;
+
+	} while (read_seqretry(&VVAR(vsyscall_gtod_data).lock, seq));
+
+	if (t)
+		*t = result;
+	return result;
+}
+int time(time_t *t)
+	__attribute__((weak, alias("__vdso_time")));

index e6e9f90..a69929e 100644
@@ -180,12 +180,8 @@ notrace time_t __vdso_time(time_t *t)
 	if (unlikely(!VVAR(vsyscall_gtod_data).sysctl_enabled))
 		return time_syscall(t);
 
-	do {
-		seq = read_seqbegin(&VVAR(vsyscall_gtod_data).lock);
-
-		result = VVAR(vsyscall_gtod_data).wall_time_sec;
-
-	} while (read_seqretry(&VVAR(vsyscall_gtod_data).lock, seq));
+	/* This is atomic on x86_64 so we don't need any locks. */
+	result = ACCESS_ONCE(VVAR(vsyscall_gtod_data).wall_time_sec);
 
 	if (t)
 		*t = result;