#define CS_RAW 1
#define CS_BASES (CS_RAW + 1)
+#define VCLOCK_TIMENS UINT_MAX
+
/**
* struct vdso_timestamp - basetime per clock_id
* @sec: seconds
* @mult: clocksource multiplier
* @shift: clocksource shift
* @basetime[clock_id]: basetime per clock_id
+ * @offset[clock_id]: time namespace offset per clock_id
* @tz_minuteswest: minutes west of Greenwich
* @tz_dsttime: type of DST correction
* @hrtimer_res: hrtimer resolution
*
* vdso_data will be accessed by 64 bit and compat code at the same time
* so we should be careful before modifying this structure.
+ *
+ * @basetime is used to store the base time for the system wide time getter
+ * VVAR page.
+ *
+ * @offset is used by the special time namespace VVAR pages which are
+ * installed instead of the real VVAR page. These namespace pages must set
+ * @seq to 1 and @clock_mode to VLOCK_TIMENS to force the code into the
+ * time namespace slow path. The namespace aware functions retrieve the
+ * real system wide VVAR page, read host time and add the per clock offset.
+ * For clocks which are not affected by time namespace adjustment the
+ * offset must be zero.
*/
struct vdso_data {
u32 seq;
u32 mult;
u32 shift;
- struct vdso_timestamp basetime[VDSO_BASES];
+ union {
+ struct vdso_timestamp basetime[VDSO_BASES];
+ struct timens_offset offset[VDSO_BASES];
+ };
s32 tz_minuteswest;
s32 tz_dsttime;
}
#endif
+#ifdef CONFIG_TIME_NS
+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 timens_offset *offs = &vdns->offset[clk];
+ const struct vdso_timestamp *vdso_ts;
+ u64 cycles, last, ns;
+ u32 seq;
+ s64 sec;
+
+ if (clk != CLOCK_MONOTONIC_RAW)
+ vd = &vd[CS_HRES_COARSE];
+ else
+ vd = &vd[CS_RAW];
+ vdso_ts = &vd->basetime[clk];
+
+ 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;
+}
+#else
+static __always_inline const struct vdso_data *__arch_get_timens_vdso_data(void)
+{
+ return NULL;
+}
+
+static int do_hres_timens(const struct vdso_data *vdns, clockid_t clk,
+ struct __kernel_timespec *ts)
+{
+ return -EINVAL;
+}
+#endif
+
static __always_inline int do_hres(const struct vdso_data *vd, clockid_t clk,
- struct __kernel_timespec *ts)
+ struct __kernel_timespec *ts)
{
const struct vdso_timestamp *vdso_ts = &vd->basetime[clk];
u64 cycles, last, sec, ns;
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 (unlikely((seq = READ_ONCE(vd->seq)) & 1)) {
+ if (IS_ENABLED(CONFIG_TIME_NS) &&
+ 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;
return 0;
}
+#ifdef CONFIG_TIME_NS
+static int 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;
+ return 0;
+}
+#else
+static int do_coarse_timens(const struct vdso_data *vdns, clockid_t clk,
+ struct __kernel_timespec *ts)
+{
+ return -1;
+}
+#endif
+
static __always_inline int do_coarse(const struct vdso_data *vd, clockid_t clk,
struct __kernel_timespec *ts)
{
u32 seq;
do {
- seq = vdso_read_begin(vd);
+ /*
+ * Open coded to handle VCLOCK_TIMENS. See comment in
+ * do_hres().
+ */
+ while ((seq = READ_ONCE(vd->seq)) & 1) {
+ if (IS_ENABLED(CONFIG_TIME_NS) &&
+ vd->clock_mode == VCLOCK_TIMENS)
+ return do_coarse_timens(vd, clk, ts);
+ cpu_relax();
+ }
+ smp_rmb();
+
ts->tv_sec = vdso_ts->sec;
ts->tv_nsec = vdso_ts->nsec;
} while (unlikely(vdso_read_retry(vd, seq)));
}
if (unlikely(tz != NULL)) {
+ if (IS_ENABLED(CONFIG_TIME_NS) &&
+ 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;
}
static __maybe_unused __kernel_old_time_t __cvdso_time(__kernel_old_time_t *time)
{
const struct vdso_data *vd = __arch_get_vdso_data();
- __kernel_old_time_t t = READ_ONCE(vd[CS_HRES_COARSE].basetime[CLOCK_REALTIME].sec);
+ __kernel_old_time_t t;
+
+ if (IS_ENABLED(CONFIG_TIME_NS) && 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;
if (unlikely((u32) clock >= MAX_CLOCKS))
return -1;
+ if (IS_ENABLED(CONFIG_TIME_NS) && 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