diff --git a/lib/vdso/gettimeofday.c b/lib/vdso/gettimeofday.c
index e630e7ff57f1..25244b677823 100644
--- a/lib/vdso/gettimeofday.c
+++ b/lib/vdso/gettimeofday.c
@@ -38,6 +38,51 @@ u64 vdso_calc_delta(u64 cycles, u64 last, u64 mask, u32 mult)
}
#endif
+#ifndef CONFIG_VDSO_TIMENS
+static __always_inline
+const struct vdso_data *__arch_get_timens_vdso_data(void)
+{
+ return NULL;
+}
+#endif
+
+static int do_hres_timens(const struct vdso_data *vdns, clockid_t clk,
+ struct __kernel_timespec *ts)
+{
+ const struct vdso_data *vd = __arch_get_timens_vdso_data();
+ const struct vdso_timestamp *vdso_ts = &vd->basetime[clk];
+ const struct timens_offset *offs = &vdns->offset[clk];
+ u64 cycles, last, ns;
+ s64 sec;
+ u32 seq;
+
+ do {
+ seq = vdso_read_begin(vd);
+ cycles = __arch_get_hw_counter(vd->clock_mode);
+ ns = vdso_ts->nsec;
+ last = vd->cycle_last;
+ if (unlikely((s64)cycles < 0))
+ return -1;
+
+ ns += vdso_calc_delta(cycles, last, vd->mask, vd->mult);
+ ns >>= vd->shift;
+ sec = vdso_ts->sec;
+ } while (unlikely(vdso_read_retry(vd, seq)));
+
+ /* Add the namespace offset */
+ sec += offs->sec;
+ ns += offs->nsec;
+
+ /*
+ * Do this outside the loop: a race inside the loop could result
+ * in __iter_div_u64_rem() being extremely slow.
+ */
+ ts->tv_sec = sec + __iter_div_u64_rem(ns, NSEC_PER_SEC, &ns);
+ ts->tv_nsec = ns;
+
+ return 0;
+}
+
static int do_hres(const struct vdso_data *vd, clockid_t clk,
struct __kernel_timespec *ts)
{@@ -46,7 +91,28 @@ static int do_hres(const struct vdso_data *vd, clockid_t clk,
u32 seq;
do {
- seq = vdso_read_begin(vd);
+ /*
+ * Open coded to handle VCLOCK_TIMENS. Time namespace
+ * enabled tasks have a special VVAR page installed which
+ * has vd->seq set to 1 and vd->clock_mode set to
+ * VCLOCK_TIMENS. For non time namespace affected tasks
+ * this does not affect performance because if vd->seq is
+ * odd, i.e. a concurrent update is in progress the extra
+ * check for vd->clock_mode is just a few extra
+ * instructions while spin waiting for vd->seq to become
+ * even again.
+ */
+ while (1) {
+ seq = READ_ONCE(vd->seq);
+ if (likely(!(seq & 1)))
+ break;
+ if (IS_ENABLED(CONFIG_VDSO_TIMENS) &&
+ vd->clock_mode == VCLOCK_TIMENS)
+ return do_hres_timens(vd, clk, ts);
+ cpu_relax();
+ }
+ smp_rmb();
+
cycles = __arch_get_hw_counter(vd->clock_mode);
ns = vdso_ts->nsec;
last = vd->cycle_last;@@ -68,6 +134,34 @@ static int do_hres(const struct vdso_data *vd, clockid_t clk,
return 0;
}
+static void do_coarse_timens(const struct vdso_data *vdns, clockid_t clk,
+ struct __kernel_timespec *ts)
+{
+ const struct vdso_data *vd = __arch_get_timens_vdso_data();
+ const struct vdso_timestamp *vdso_ts = &vd->basetime[clk];
+ const struct timens_offset *offs = &vdns->offset[clk];
+ u64 nsec;
+ s64 sec;
+ s32 seq;
+
+ do {
+ seq = vdso_read_begin(vd);
+ sec = vdso_ts->sec;
+ nsec = vdso_ts->nsec;
+ } while (unlikely(vdso_read_retry(vd, seq)));
+
+ /* Add the namespace offset */
+ sec += offs->sec;
+ nsec += offs->nsec;
+
+ /*
+ * Do this outside the loop: a race inside the loop could result
+ * in __iter_div_u64_rem() being extremely slow.
+ */
+ ts->tv_sec = sec + __iter_div_u64_rem(nsec, NSEC_PER_SEC, &nsec);
+ ts->tv_nsec = nsec;
+}
+
static void do_coarse(const struct vdso_data *vd, clockid_t clk,
struct __kernel_timespec *ts)
{@@ -75,7 +169,23 @@ static void do_coarse(const struct vdso_data *vd, clockid_t clk,
u32 seq;
do {
- seq = vdso_read_begin(vd);
+ /*
+ * Open coded to handle VCLOCK_TIMENS. See comment in
+ * do_hres().
+ */
+ while (1) {
+ seq = READ_ONCE(vd->seq);
+ if (likely(!(seq & 1)))
+ break;
+ if (IS_ENABLED(CONFIG_VDSO_TIMENS) &&
+ vd->clock_mode == VCLOCK_TIMENS) {
+ do_coarse_timens(vd, clk, ts);
+ return;
+ }
+ cpu_relax();
+ }
+ smp_rmb();
+
ts->tv_sec = vdso_ts->sec;
ts->tv_nsec = vdso_ts->nsec;
} while (unlikely(vdso_read_retry(vd, seq)));@@ -156,6 +266,10 @@ __cvdso_gettimeofday(struct __kernel_old_timeval *tv, struct timezone *tz)
}
if (unlikely(tz != NULL)) {
+ if (IS_ENABLED(CONFIG_VDSO_TIMENS) &&
+ vd->clock_mode == VCLOCK_TIMENS)
+ vd = __arch_get_timens_vdso_data();
+
tz->tz_minuteswest = vd[CS_HRES_COARSE].tz_minuteswest;
tz->tz_dsttime = vd[CS_HRES_COARSE].tz_dsttime;
}@@ -167,7 +281,12 @@ __cvdso_gettimeofday(struct __kernel_old_timeval *tv, struct timezone *tz)
static __maybe_unused time_t __cvdso_time(time_t *time)
{
const struct vdso_data *vd = __arch_get_vdso_data();
- time_t t = READ_ONCE(vd[CS_HRES_COARSE].basetime[CLOCK_REALTIME].sec);
+ time_t t;
+
+ if (IS_ENABLED(CONFIG_VDSO_TIMENS) && vd->clock_mode == VCLOCK_TIMENS)
+ vd = __arch_get_timens_vdso_data();
+
+ t = READ_ONCE(vd[CS_HRES_COARSE].basetime[CLOCK_REALTIME].sec);
if (time)
*time = t;@@ -189,6 +308,9 @@ int __cvdso_clock_getres_common(clockid_t clock, struct __kernel_timespec *res)
if (unlikely((u32) clock >= MAX_CLOCKS))
return -1;
+ if (IS_ENABLED(CONFIG_VDSO_TIMENS) && vd->clock_mode == VCLOCK_TIMENS)
+ vd = __arch_get_timens_vdso_data();
+
hrtimer_res = READ_ONCE(vd[CS_HRES_COARSE].hrtimer_res);
/*
* Convert the clockid to a bitmask and use it to check which