Merge tag 'timers-core-2020-01-27' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull timer updates from Thomas Gleixner:
 "The timekeeping and timers departement provides:

   - Time namespace support:

     If a container migrates from one host to another then it expects
     that clocks based on MONOTONIC and BOOTTIME are not subject to
     disruption. Due to different boot time and non-suspended runtime
     these clocks can differ significantly on two hosts, in the worst
     case time goes backwards which is a violation of the POSIX
     requirements.

     The time namespace addresses this problem. It allows to set offsets
     for clock MONOTONIC and BOOTTIME once after creation and before
     tasks are associated with the namespace. These offsets are taken
     into account by timers and timekeeping including the VDSO.

     Offsets for wall clock based clocks (REALTIME/TAI) are not provided
     by this mechanism. While in theory possible, the overhead and code
     complexity would be immense and not justified by the esoteric
     potential use cases which were discussed at Plumbers '18.

     The overhead for tasks in the root namespace (ie where host time
     offsets = 0) is in the noise and great effort was made to ensure
     that especially in the VDSO. If time namespace is disabled in the
     kernel configuration the code is compiled out.

     Kudos to Andrei Vagin and Dmitry Sofanov who implemented this
     feature and kept on for more than a year addressing review
     comments, finding better solutions. A pleasant experience.

   - Overhaul of the alarmtimer device dependency handling to ensure
     that the init/suspend/resume ordering is correct.

   - A new clocksource/event driver for Microchip PIT64

   - Suspend/resume support for the Hyper-V clocksource

   - The usual pile of fixes, updates and improvements mostly in the
     driver code"

* tag 'timers-core-2020-01-27' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (71 commits)
  alarmtimer: Make alarmtimer_get_rtcdev() a stub when CONFIG_RTC_CLASS=n
  alarmtimer: Use wakeup source from alarmtimer platform device
  alarmtimer: Make alarmtimer platform device child of RTC device
  alarmtimer: Update alarmtimer_get_rtcdev() docs to reflect reality
  hrtimer: Add missing sparse annotation for __run_timer()
  lib/vdso: Only read hrtimer_res when needed in __cvdso_clock_getres()
  MIPS: vdso: Define BUILD_VDSO32 when building a 32bit kernel
  clocksource/drivers/hyper-v: Set TSC clocksource as default w/ InvariantTSC
  clocksource/drivers/hyper-v: Untangle stimers and timesync from clocksources
  clocksource/drivers/timer-microchip-pit64b: Fix sparse warning
  clocksource/drivers/exynos_mct: Rename Exynos to lowercase
  clocksource/drivers/timer-ti-dm: Fix uninitialized pointer access
  clocksource/drivers/timer-ti-dm: Switch to platform_get_irq
  clocksource/drivers/timer-ti-dm: Convert to devm_platform_ioremap_resource
  clocksource/drivers/em_sti: Fix variable declaration in em_sti_probe
  clocksource/drivers/em_sti: Convert to devm_platform_ioremap_resource
  clocksource/drivers/bcm2835_timer: Fix memory leak of timer
  clocksource/drivers/cadence-ttc: Use ttc driver as platform driver
  clocksource/drivers/timer-microchip-pit64b: Add Microchip PIT64B support
  clocksource/drivers/hyper-v: Reserve PAGE_SIZE space for tsc page
  ...

2 files changed, 170 insertions, 40 deletions

diff --git a/lib/vdso/Kconfig b/lib/vdso/Kconfig
index 9fe698ff62ec..d883ac299508 100644
--- a/lib/vdso/Kconfig
+++ b/lib/vdso/Kconfig
@@ -24,4 +24,10 @@ config GENERIC_COMPAT_VDSO
 	help
 	  This config option enables the compat VDSO layer.
 
+config GENERIC_VDSO_TIME_NS
+	bool
+	help
+	  Selected by architectures which support time namespaces in the
+	  VDSO
+
 endif
diff --git a/lib/vdso/gettimeofday.c b/lib/vdso/gettimeofday.c
index 42bd8ab955fa..f8b8ec5e63ac 100644
--- a/lib/vdso/gettimeofday.c
+++ b/lib/vdso/gettimeofday.c
@@ -38,12 +38,22 @@ u64 vdso_calc_delta(u64 cycles, u64 last, u64 mask, u32 mult)
 }
 #endif
 
-static int do_hres(const struct vdso_data *vd, clockid_t clk,
-		   struct __kernel_timespec *ts)
+#ifdef CONFIG_TIME_NS
+static int do_hres_timens(const struct vdso_data *vdns, clockid_t clk,
+			  struct __kernel_timespec *ts)
 {
-	const struct vdso_timestamp *vdso_ts = &vd->basetime[clk];
-	u64 cycles, last, sec, ns;
+	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);
@@ -58,6 +68,10 @@ static int do_hres(const struct vdso_data *vd, clockid_t clk,
 		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.
@@ -67,18 +81,128 @@ static int do_hres(const struct vdso_data *vd, clockid_t clk,
 
 	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 void do_coarse(const struct vdso_data *vd, clockid_t clk,
-		      struct __kernel_timespec *ts)
+static __always_inline int do_hres(const struct vdso_data *vd, clockid_t clk,
+				   struct __kernel_timespec *ts)
 {
 	const struct vdso_timestamp *vdso_ts = &vd->basetime[clk];
+	u64 cycles, last, sec, ns;
 	u32 seq;
 
 	do {
+		/*
+		 * 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;
+		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)));
+
+	/*
+	 * 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;
+}
+
+#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)
+{
+	const struct vdso_timestamp *vdso_ts = &vd->basetime[clk];
+	u32 seq;
+
+	do {
+		/*
+		 * 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)));
+
+	return 0;
 }
 
 static __maybe_unused int
@@ -96,15 +220,16 @@ __cvdso_clock_gettime_common(clockid_t clock, struct __kernel_timespec *ts)
 	 * clocks are handled in the VDSO directly.
 	 */
 	msk = 1U << clock;
-	if (likely(msk & VDSO_HRES)) {
-		return do_hres(&vd[CS_HRES_COARSE], clock, ts);
-	} else if (msk & VDSO_COARSE) {
-		do_coarse(&vd[CS_HRES_COARSE], clock, ts);
-		return 0;
-	} else if (msk & VDSO_RAW) {
-		return do_hres(&vd[CS_RAW], clock, ts);
-	}
-	return -1;
+	if (likely(msk & VDSO_HRES))
+		vd = &vd[CS_HRES_COARSE];
+	else if (msk & VDSO_COARSE)
+		return do_coarse(&vd[CS_HRES_COARSE], clock, ts);
+	else if (msk & VDSO_RAW)
+		vd = &vd[CS_RAW];
+	else
+		return -1;
+
+	return do_hres(vd, clock, ts);
 }
 
 static __maybe_unused int
@@ -117,6 +242,7 @@ __cvdso_clock_gettime(clockid_t clock, struct __kernel_timespec *ts)
 	return 0;
 }
 
+#ifdef BUILD_VDSO32
 static __maybe_unused int
 __cvdso_clock_gettime32(clockid_t clock, struct old_timespec32 *res)
 {
@@ -125,20 +251,16 @@ __cvdso_clock_gettime32(clockid_t clock, struct old_timespec32 *res)
 
 	ret = __cvdso_clock_gettime_common(clock, &ts);
 
-#ifdef VDSO_HAS_32BIT_FALLBACK
 	if (unlikely(ret))
 		return clock_gettime32_fallback(clock, res);
-#else
-	if (unlikely(ret))
-		ret = clock_gettime_fallback(clock, &ts);
-#endif
 
-	if (likely(!ret)) {
-		res->tv_sec = ts.tv_sec;
-		res->tv_nsec = ts.tv_nsec;
-	}
+	/* For ret == 0 */
+	res->tv_sec = ts.tv_sec;
+	res->tv_nsec = ts.tv_nsec;
+
 	return ret;
 }
+#endif /* BUILD_VDSO32 */
 
 static __maybe_unused int
 __cvdso_gettimeofday(struct __kernel_old_timeval *tv, struct timezone *tz)
@@ -156,6 +278,10 @@ __cvdso_gettimeofday(struct __kernel_old_timeval *tv, struct timezone *tz)
 	}
 
 	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;
 	}
@@ -167,7 +293,12 @@ __cvdso_gettimeofday(struct __kernel_old_timeval *tv, struct timezone *tz)
 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;
@@ -181,7 +312,6 @@ static __maybe_unused
 int __cvdso_clock_getres_common(clockid_t clock, struct __kernel_timespec *res)
 {
 	const struct vdso_data *vd = __arch_get_vdso_data();
-	u64 hrtimer_res;
 	u32 msk;
 	u64 ns;
 
@@ -189,27 +319,24 @@ int __cvdso_clock_getres_common(clockid_t clock, struct __kernel_timespec *res)
 	if (unlikely((u32) clock >= MAX_CLOCKS))
 		return -1;
 
-	hrtimer_res = READ_ONCE(vd[CS_HRES_COARSE].hrtimer_res);
+	if (IS_ENABLED(CONFIG_TIME_NS) && vd->clock_mode == VCLOCK_TIMENS)
+		vd = __arch_get_timens_vdso_data();
+
 	/*
 	 * Convert the clockid to a bitmask and use it to check which
 	 * clocks are handled in the VDSO directly.
 	 */
 	msk = 1U << clock;
-	if (msk & VDSO_HRES) {
+	if (msk & (VDSO_HRES | VDSO_RAW)) {
 		/*
 		 * Preserves the behaviour of posix_get_hrtimer_res().
 		 */
-		ns = hrtimer_res;
+		ns = READ_ONCE(vd[CS_HRES_COARSE].hrtimer_res);
 	} else if (msk & VDSO_COARSE) {
 		/*
 		 * Preserves the behaviour of posix_get_coarse_res().
 		 */
 		ns = LOW_RES_NSEC;
-	} else if (msk & VDSO_RAW) {
-		/*
-		 * Preserves the behaviour of posix_get_hrtimer_res().
-		 */
-		ns = hrtimer_res;
 	} else {
 		return -1;
 	}
@@ -231,6 +358,7 @@ int __cvdso_clock_getres(clockid_t clock, struct __kernel_timespec *res)
 	return 0;
 }
 
+#ifdef BUILD_VDSO32
 static __maybe_unused int
 __cvdso_clock_getres_time32(clockid_t clock, struct old_timespec32 *res)
 {
@@ -239,18 +367,14 @@ __cvdso_clock_getres_time32(clockid_t clock, struct old_timespec32 *res)
 
 	ret = __cvdso_clock_getres_common(clock, &ts);
 
-#ifdef VDSO_HAS_32BIT_FALLBACK
 	if (unlikely(ret))
 		return clock_getres32_fallback(clock, res);
-#else
-	if (unlikely(ret))
-		ret = clock_getres_fallback(clock, &ts);
-#endif
 
-	if (likely(!ret && res)) {
+	if (likely(res)) {
 		res->tv_sec = ts.tv_sec;
 		res->tv_nsec = ts.tv_nsec;
 	}
 	return ret;
 }
+#endif /* BUILD_VDSO32 */
 #endif /* VDSO_HAS_CLOCK_GETRES */