#include <linux/seqlock.h>
#include <linux/jiffies.h>
#include <linux/sysctl.h>
+#include <linux/clocksource.h>
#include <linux/getcpu.h>
#include <linux/cpu.h>
#include <linux/smp.h>
#include <asm/vsyscall.h>
#include <asm/pgtable.h>
#include <asm/page.h>
+#include <asm/unistd.h>
#include <asm/fixmap.h>
#include <asm/errno.h>
#include <asm/io.h>
#define __vsyscall(nr) __attribute__ ((unused,__section__(".vsyscall_" #nr)))
#define __syscall_clobber "r11","rcx","memory"
+#define __pa_vsymbol(x) \
+ ({unsigned long v; \
+ extern char __vsyscall_0; \
+ asm("" : "=r" (v) : "0" (x)); \
+ ((v - VSYSCALL_FIRST_PAGE) + __pa_symbol(&__vsyscall_0)); })
-int __sysctl_vsyscall __section_sysctl_vsyscall = 1;
-seqlock_t __xtime_lock __section_xtime_lock = SEQLOCK_UNLOCKED;
+/*
+ * vsyscall_gtod_data contains data that is :
+ * - readonly from vsyscalls
+ * - writen by timer interrupt or systcl (/proc/sys/kernel/vsyscall64)
+ * Try to keep this structure as small as possible to avoid cache line ping pongs
+ */
+struct vsyscall_gtod_data_t {
+ seqlock_t lock;
+
+ /* open coded 'struct timespec' */
+ 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);
+ cycle_t cycle_last;
+ cycle_t mask;
+ u32 mult;
+ u32 shift;
+ } clock;
+};
int __vgetcpu_mode __section_vgetcpu_mode;
-#include <asm/unistd.h>
-
-static __always_inline void timeval_normalize(struct timeval * tv)
+struct vsyscall_gtod_data_t __vsyscall_gtod_data __section_vsyscall_gtod_data =
{
- time_t __sec;
-
- __sec = tv->tv_usec / 1000000;
- if (__sec) {
- tv->tv_usec %= 1000000;
- tv->tv_sec += __sec;
- }
-}
+ .lock = SEQLOCK_UNLOCKED,
+ .sysctl_enabled = 1,
+};
-static __always_inline void do_vgettimeofday(struct timeval * tv)
+void update_vsyscall(struct timespec *wall_time, struct clocksource *clock)
{
- long sequence, t;
- unsigned long sec, usec;
-
- do {
- sequence = read_seqbegin(&__xtime_lock);
-
- sec = __xtime.tv_sec;
- usec = __xtime.tv_nsec / 1000;
-
- if (__vxtime.mode != VXTIME_HPET) {
- t = get_cycles_sync();
- if (t < __vxtime.last_tsc)
- t = __vxtime.last_tsc;
- usec += ((t - __vxtime.last_tsc) *
- __vxtime.tsc_quot) >> 32;
- /* See comment in x86_64 do_gettimeofday. */
- } else {
- usec += ((readl((void __iomem *)
- fix_to_virt(VSYSCALL_HPET) + 0xf0) -
- __vxtime.last) * __vxtime.quot) >> 32;
- }
- } while (read_seqretry(&__xtime_lock, sequence));
-
- tv->tv_sec = sec + usec / 1000000;
- tv->tv_usec = usec % 1000000;
+ unsigned long flags;
+
+ write_seqlock_irqsave(&vsyscall_gtod_data.lock, flags);
+ /* copy vsyscall data */
+ vsyscall_gtod_data.clock.vread = clock->vread;
+ vsyscall_gtod_data.clock.cycle_last = clock->cycle_last;
+ vsyscall_gtod_data.clock.mask = clock->mask;
+ vsyscall_gtod_data.clock.mult = clock->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.sys_tz = sys_tz;
+ write_sequnlock_irqrestore(&vsyscall_gtod_data.lock, flags);
}
-/* RED-PEN may want to readd seq locking, but then the variable should be write-once. */
+/* RED-PEN may want to readd seq locking, but then the variable should be
+ * write-once.
+ */
static __always_inline void do_get_tz(struct timezone * tz)
{
- *tz = __sys_tz;
+ *tz = __vsyscall_gtod_data.sys_tz;
}
static __always_inline int gettimeofday(struct timeval *tv, struct timezone *tz)
int ret;
asm volatile("vsysc2: syscall"
: "=a" (ret)
- : "0" (__NR_gettimeofday),"D" (tv),"S" (tz) : __syscall_clobber );
+ : "0" (__NR_gettimeofday),"D" (tv),"S" (tz)
+ : __syscall_clobber );
return ret;
}
return secs;
}
+static __always_inline void do_vgettimeofday(struct timeval * tv)
+{
+ cycle_t now, base, mask, cycle_delta;
+ unsigned seq;
+ unsigned long mult, shift, nsec;
+ cycle_t (*vread)(void);
+ do {
+ seq = read_seqbegin(&__vsyscall_gtod_data.lock);
+
+ vread = __vsyscall_gtod_data.clock.vread;
+ if (unlikely(!__vsyscall_gtod_data.sysctl_enabled || !vread)) {
+ gettimeofday(tv,NULL);
+ return;
+ }
+ now = vread();
+ base = __vsyscall_gtod_data.clock.cycle_last;
+ mask = __vsyscall_gtod_data.clock.mask;
+ mult = __vsyscall_gtod_data.clock.mult;
+ shift = __vsyscall_gtod_data.clock.shift;
+
+ tv->tv_sec = __vsyscall_gtod_data.wall_time_sec;
+ nsec = __vsyscall_gtod_data.wall_time_nsec;
+ } while (read_seqretry(&__vsyscall_gtod_data.lock, seq));
+
+ /* calculate interval: */
+ cycle_delta = (now - base) & mask;
+ /* convert to nsecs: */
+ nsec += (cycle_delta * mult) >> shift;
+
+ while (nsec >= NSEC_PER_SEC) {
+ tv->tv_sec += 1;
+ nsec -= NSEC_PER_SEC;
+ }
+ tv->tv_usec = nsec / NSEC_PER_USEC;
+}
+
int __vsyscall(0) vgettimeofday(struct timeval * tv, struct timezone * tz)
{
- if (!__sysctl_vsyscall)
- return gettimeofday(tv,tz);
if (tv)
do_vgettimeofday(tv);
if (tz)
* unlikely */
time_t __vsyscall(1) vtime(time_t *t)
{
- if (!__sysctl_vsyscall)
+ time_t result;
+ if (unlikely(!__vsyscall_gtod_data.sysctl_enabled))
return time_syscall(t);
- else if (t)
- *t = __xtime.tv_sec;
- return __xtime.tv_sec;
+ result = __vsyscall_gtod_data.wall_time_sec;
+ if (t)
+ *t = result;
+ return result;
}
/* Fast way to get current CPU and node.
return ret;
/* gcc has some trouble with __va(__pa()), so just do it this
way. */
- map1 = ioremap(__pa_symbol(&vsysc1), 2);
+ map1 = ioremap(__pa_vsymbol(&vsysc1), 2);
if (!map1)
return -ENOMEM;
- map2 = ioremap(__pa_symbol(&vsysc2), 2);
+ map2 = ioremap(__pa_vsymbol(&vsysc2), 2);
if (!map2) {
ret = -ENOMEM;
goto out;
}
- if (!sysctl_vsyscall) {
+ if (!vsyscall_gtod_data.sysctl_enabled) {
writew(SYSCALL, map1);
writew(SYSCALL, map2);
} else {
static ctl_table kernel_table2[] = {
{ .ctl_name = 99, .procname = "vsyscall64",
- .data = &sysctl_vsyscall, .maxlen = sizeof(int), .mode = 0644,
+ .data = &vsyscall_gtod_data.sysctl_enabled, .maxlen = sizeof(int),
+ .mode = 0644,
.strategy = vsyscall_sysctl_nostrat,
.proc_handler = vsyscall_sysctl_change },
{}