Merge branch 'x86-vdso-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull x86 vdso updates from Ingo Molnar:
 "Two main changes:

   - Cleanups, simplifications and CLOCK_TAI support (Thomas Gleixner)

   - Improve code generation (Andy Lutomirski)"

* 'x86-vdso-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  x86/vdso: Rearrange do_hres() to improve code generation
  x86/vdso: Document vgtod_ts better
  x86/vdso: Remove "memory" clobbers in the vDSO syscall fallbacks
  x66/vdso: Add CLOCK_TAI support
  x86/vdso: Move cycle_last handling into the caller
  x86/vdso: Simplify the invalid vclock case
  x86/vdso: Replace the clockid switch case
  x86/vdso: Collapse coarse functions
  x86/vdso: Collapse high resolution functions
  x86/vdso: Introduce and use vgtod_ts
  x86/vdso: Use unsigned int consistently for vsyscall_gtod_data:: Seq
  x86/vdso: Enforce 64bit clocksource
  x86/time: Implement clocksource_arch_init()
  clocksource: Provide clocksource_arch_init()

arch/x86/Kconfig

@@ -48,6 +48,7 @@ config X86
 	select ACPI_SYSTEM_POWER_STATES_SUPPORT	if ACPI
 	select ANON_INODES
 	select ARCH_CLOCKSOURCE_DATA
+	select ARCH_CLOCKSOURCE_INIT
 	select ARCH_DISCARD_MEMBLOCK
 	select ARCH_HAS_ACPI_TABLE_UPGRADE	if ACPI
 	select ARCH_HAS_DEBUG_VIRTUAL

arch/x86/entry/vdso/vclock_gettime.c

@@ -45,21 +45,10 @@ notrace static long vdso_fallback_gettime(long clock, struct timespec *ts)
 	long ret;
 	asm ("syscall" : "=a" (ret), "=m" (*ts) :
 	     "0" (__NR_clock_gettime), "D" (clock), "S" (ts) :
-	     "memory", "rcx", "r11");
+	     "rcx", "r11");
 	return ret;
 }
 
-notrace static long vdso_fallback_gtod(struct timeval *tv, struct timezone *tz)
-{
-	long ret;
-
-	asm ("syscall" : "=a" (ret), "=m" (*tv), "=m" (*tz) :
-	     "0" (__NR_gettimeofday), "D" (tv), "S" (tz) :
-	     "memory", "rcx", "r11");
-	return ret;
-}
-
-
 #else
 
 notrace static long vdso_fallback_gettime(long clock, struct timespec *ts)
@@ -73,22 +62,7 @@ notrace static long vdso_fallback_gettime(long clock, struct timespec *ts)
 		"mov %%edx, %%ebx \n"
 		: "=a" (ret), "=m" (*ts)
 		: "0" (__NR_clock_gettime), [clock] "g" (clock), "c" (ts)
-		: "memory", "edx");
-	return ret;
-}
-
-notrace static long vdso_fallback_gtod(struct timeval *tv, struct timezone *tz)
-{
-	long ret;
-
-	asm (
-		"mov %%ebx, %%edx \n"
-		"mov %[tv], %%ebx \n"
-		"call __kernel_vsyscall \n"
-		"mov %%edx, %%ebx \n"
-		: "=a" (ret), "=m" (*tv), "=m" (*tz)
-		: "0" (__NR_gettimeofday), [tv] "g" (tv), "c" (tz)
-		: "memory", "edx");
+		: "edx");
 	return ret;
 }
 
@@ -100,12 +74,11 @@ static notrace const struct pvclock_vsyscall_time_info *get_pvti0(void)
 	return (const struct pvclock_vsyscall_time_info *)&pvclock_page;
 }
 
-static notrace u64 vread_pvclock(int *mode)
+static notrace u64 vread_pvclock(void)
 {
 	const struct pvclock_vcpu_time_info *pvti = &get_pvti0()->pvti;
-	u64 ret;
-	u64 last;
 	u32 version;
+	u64 ret;
 
 	/*
 	 * Note: The kernel and hypervisor must guarantee that cpu ID
@@ -132,175 +105,112 @@ static notrace u64 vread_pvclock(int *mode)
 	do {
 		version = pvclock_read_begin(pvti);
 
-		if (unlikely(!(pvti->flags & PVCLOCK_TSC_STABLE_BIT))) {
-			*mode = VCLOCK_NONE;
-			return 0;
-		}
+		if (unlikely(!(pvti->flags & PVCLOCK_TSC_STABLE_BIT)))
+			return U64_MAX;
 
 		ret = __pvclock_read_cycles(pvti, rdtsc_ordered());
 	} while (pvclock_read_retry(pvti, version));
 
-	/* refer to vread_tsc() comment for rationale */
-	last = gtod->cycle_last;
-
-	if (likely(ret >= last))
-		return ret;
-
-	return last;
+	return ret;
 }
 #endif
 #ifdef CONFIG_HYPERV_TSCPAGE
-static notrace u64 vread_hvclock(int *mode)
+static notrace u64 vread_hvclock(void)
 {
 	const struct ms_hyperv_tsc_page *tsc_pg =
 		(const struct ms_hyperv_tsc_page *)&hvclock_page;
-	u64 current_tick = hv_read_tsc_page(tsc_pg);
 
-	if (current_tick != U64_MAX)
-		return current_tick;
-
-	*mode = VCLOCK_NONE;
-	return 0;
+	return hv_read_tsc_page(tsc_pg);
 }
 #endif
 
-notrace static u64 vread_tsc(void)
+notrace static inline u64 vgetcyc(int mode)
 {
-	u64 ret = (u64)rdtsc_ordered();
-	u64 last = gtod->cycle_last;
-
-	if (likely(ret >= last))
-		return ret;
-
-	/*
-	 * GCC likes to generate cmov here, but this branch is extremely
-	 * predictable (it's just a function 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;
-}
-
-notrace static inline u64 vgetsns(int *mode)
-{
-	u64 v;
-	cycles_t cycles;
-
-	if (gtod->vclock_mode == VCLOCK_TSC)
-		cycles = vread_tsc();
+	if (mode == VCLOCK_TSC)
+		return (u64)rdtsc_ordered();
 #ifdef CONFIG_PARAVIRT_CLOCK
-	else if (gtod->vclock_mode == VCLOCK_PVCLOCK)
-		cycles = vread_pvclock(mode);
+	else if (mode == VCLOCK_PVCLOCK)
+		return vread_pvclock();
 #endif
 #ifdef CONFIG_HYPERV_TSCPAGE
-	else if (gtod->vclock_mode == VCLOCK_HVCLOCK)
-		cycles = vread_hvclock(mode);
+	else if (mode == VCLOCK_HVCLOCK)
+		return vread_hvclock();
 #endif
-	else
-		return 0;
-	v = (cycles - gtod->cycle_last) & gtod->mask;
-	return v * gtod->mult;
+	return U64_MAX;
 }
 
-/* Code size doesn't matter (vdso is 4k anyway) and this is faster. */
-notrace static int __always_inline do_realtime(struct timespec *ts)
+notrace static int do_hres(clockid_t clk, struct timespec *ts)
 {
-	unsigned long seq;
-	u64 ns;
-	int mode;
+	struct vgtod_ts *base = &gtod->basetime[clk];
+	u64 cycles, last, sec, ns;
+	unsigned int seq;
 
 	do {
 		seq = gtod_read_begin(gtod);
-		mode = gtod->vclock_mode;
-		ts->tv_sec = gtod->wall_time_sec;
-		ns = gtod->wall_time_snsec;
-		ns += vgetsns(&mode);
+		cycles = vgetcyc(gtod->vclock_mode);
+		ns = base->nsec;
+		last = gtod->cycle_last;
+		if (unlikely((s64)cycles < 0))
+			return vdso_fallback_gettime(clk, ts);
+		if (cycles > last)
+			ns += (cycles - last) * gtod->mult;
 		ns >>= gtod->shift;
+		sec = base->sec;
 	} while (unlikely(gtod_read_retry(gtod, seq)));
 
-	ts->tv_sec += __iter_div_u64_rem(ns, NSEC_PER_SEC, &ns);
+	/*
+	 * 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 mode;
+	return 0;
 }
 
-notrace static int __always_inline do_monotonic(struct timespec *ts)
+notrace static void do_coarse(clockid_t clk, struct timespec *ts)
 {
-	unsigned long seq;
-	u64 ns;
-	int mode;
+	struct vgtod_ts *base = &gtod->basetime[clk];
+	unsigned int seq;
 
 	do {
 		seq = gtod_read_begin(gtod);
-		mode = gtod->vclock_mode;
-		ts->tv_sec = gtod->monotonic_time_sec;
-		ns = gtod->monotonic_time_snsec;
-		ns += vgetsns(&mode);
-		ns >>= gtod->shift;
-	} while (unlikely(gtod_read_retry(gtod, seq)));
-
-	ts->tv_sec += __iter_div_u64_rem(ns, NSEC_PER_SEC, &ns);
-	ts->tv_nsec = ns;
-
-	return mode;
-}
-
-notrace static void do_realtime_coarse(struct timespec *ts)
-{
-	unsigned long seq;
-	do {
-		seq = gtod_read_begin(gtod);
-		ts->tv_sec = gtod->wall_time_coarse_sec;
-		ts->tv_nsec = gtod->wall_time_coarse_nsec;
-	} while (unlikely(gtod_read_retry(gtod, seq)));
-}
-
-notrace static void do_monotonic_coarse(struct timespec *ts)
-{
-	unsigned long seq;
-	do {
-		seq = gtod_read_begin(gtod);
-		ts->tv_sec = gtod->monotonic_time_coarse_sec;
-		ts->tv_nsec = gtod->monotonic_time_coarse_nsec;
+		ts->tv_sec = base->sec;
+		ts->tv_nsec = base->nsec;
 	} while (unlikely(gtod_read_retry(gtod, seq)));
 }
 
 notrace int __vdso_clock_gettime(clockid_t clock, struct timespec *ts)
 {
-	switch (clock) {
-	case CLOCK_REALTIME:
-		if (do_realtime(ts) == VCLOCK_NONE)
-			goto fallback;
-		break;
-	case CLOCK_MONOTONIC:
-		if (do_monotonic(ts) == VCLOCK_NONE)
-			goto fallback;
-		break;
-	case CLOCK_REALTIME_COARSE:
-		do_realtime_coarse(ts);
-		break;
-	case CLOCK_MONOTONIC_COARSE:
-		do_monotonic_coarse(ts);
-		break;
-	default:
-		goto fallback;
-	}
+	unsigned int msk;
 
-	return 0;
-fallback:
+	/* Sort out negative (CPU/FD) and invalid clocks */
+	if (unlikely((unsigned int) clock >= MAX_CLOCKS))
+		return vdso_fallback_gettime(clock, ts);
+
+	/*
+	 * Convert the clockid to a bitmask and use it to check which
+	 * clocks are handled in the VDSO directly.
+	 */
+	msk = 1U << clock;
+	if (likely(msk & VGTOD_HRES)) {
+		return do_hres(clock, ts);
+	} else if (msk & VGTOD_COARSE) {
+		do_coarse(clock, ts);
+		return 0;
+	}
 	return vdso_fallback_gettime(clock, ts);
 }
+
 int clock_gettime(clockid_t, struct timespec *)
 	__attribute__((weak, alias("__vdso_clock_gettime")));
 
 notrace int __vdso_gettimeofday(struct timeval *tv, struct timezone *tz)
 {
 	if (likely(tv != NULL)) {
-		if (unlikely(do_realtime((struct timespec *)tv) == VCLOCK_NONE))
-			return vdso_fallback_gtod(tv, tz);
+		struct timespec *ts = (struct timespec *) tv;
+
+		do_hres(CLOCK_REALTIME, ts);
 		tv->tv_usec /= 1000;
 	}
 	if (unlikely(tz != NULL)) {
@@ -320,7 +230,7 @@ int gettimeofday(struct timeval *, struct timezone *)
 notrace time_t __vdso_time(time_t *t)
 {
 	/* This is atomic on x86 so we don't need any locks. */
-	time_t result = READ_ONCE(gtod->wall_time_sec);
+	time_t result = READ_ONCE(gtod->basetime[CLOCK_REALTIME].sec);
 
 	if (t)
 		*t = result;

arch/x86/entry/vsyscall/vsyscall_gtod.c

@@ -31,6 +31,8 @@ void update_vsyscall(struct timekeeper *tk)
 {
 	int vclock_mode = tk->tkr_mono.clock->archdata.vclock_mode;
 	struct vsyscall_gtod_data *vdata = &vsyscall_gtod_data;
+	struct vgtod_ts *base;
+	u64 nsec;
 
 	/* Mark the new vclock used. */
 	BUILD_BUG_ON(VCLOCK_MAX >= 32);
@@ -45,34 +47,37 @@ void update_vsyscall(struct timekeeper *tk)
 	vdata->mult		= tk->tkr_mono.mult;
 	vdata->shift		= tk->tkr_mono.shift;
 
-	vdata->wall_time_sec		= tk->xtime_sec;
-	vdata->wall_time_snsec		= tk->tkr_mono.xtime_nsec;
+	base = &vdata->basetime[CLOCK_REALTIME];
+	base->sec = tk->xtime_sec;
+	base->nsec = tk->tkr_mono.xtime_nsec;
 
-	vdata->monotonic_time_sec	= tk->xtime_sec
-					+ tk->wall_to_monotonic.tv_sec;
-	vdata->monotonic_time_snsec	= tk->tkr_mono.xtime_nsec
-					+ ((u64)tk->wall_to_monotonic.tv_nsec
-						<< tk->tkr_mono.shift);
-	while (vdata->monotonic_time_snsec >=
-					(((u64)NSEC_PER_SEC) << tk->tkr_mono.shift)) {
-		vdata->monotonic_time_snsec -=
-					((u64)NSEC_PER_SEC) << tk->tkr_mono.shift;
-		vdata->monotonic_time_sec++;
+	base = &vdata->basetime[CLOCK_TAI];
+	base->sec = tk->xtime_sec + (s64)tk->tai_offset;
+	base->nsec = tk->tkr_mono.xtime_nsec;
+
+	base = &vdata->basetime[CLOCK_MONOTONIC];
+	base->sec = tk->xtime_sec + tk->wall_to_monotonic.tv_sec;
+	nsec = tk->tkr_mono.xtime_nsec;
+	nsec +=	((u64)tk->wall_to_monotonic.tv_nsec << tk->tkr_mono.shift);
+	while (nsec >= (((u64)NSEC_PER_SEC) << tk->tkr_mono.shift)) {
+		nsec -= ((u64)NSEC_PER_SEC) << tk->tkr_mono.shift;
+		base->sec++;
 	}
+	base->nsec = nsec;
 
-	vdata->wall_time_coarse_sec	= tk->xtime_sec;
-	vdata->wall_time_coarse_nsec	= (long)(tk->tkr_mono.xtime_nsec >>
-						 tk->tkr_mono.shift);
+	base = &vdata->basetime[CLOCK_REALTIME_COARSE];
+	base->sec = tk->xtime_sec;
+	base->nsec = tk->tkr_mono.xtime_nsec >> tk->tkr_mono.shift;
 
-	vdata->monotonic_time_coarse_sec =
-		vdata->wall_time_coarse_sec + tk->wall_to_monotonic.tv_sec;
-	vdata->monotonic_time_coarse_nsec =
-		vdata->wall_time_coarse_nsec + tk->wall_to_monotonic.tv_nsec;
-
-	while (vdata->monotonic_time_coarse_nsec >= NSEC_PER_SEC) {
-		vdata->monotonic_time_coarse_nsec -= NSEC_PER_SEC;
-		vdata->monotonic_time_coarse_sec++;
+	base = &vdata->basetime[CLOCK_MONOTONIC_COARSE];
+	base->sec = tk->xtime_sec + tk->wall_to_monotonic.tv_sec;
+	nsec = tk->tkr_mono.xtime_nsec >> tk->tkr_mono.shift;
+	nsec += tk->wall_to_monotonic.tv_nsec;
+	while (nsec >= NSEC_PER_SEC) {
+		nsec -= NSEC_PER_SEC;
+		base->sec++;
 	}
+	base->nsec = nsec;
 
 	gtod_write_end(vdata);
 }

arch/x86/include/asm/vgtod.h

@@ -5,33 +5,46 @@
 #include <linux/compiler.h>
 #include <linux/clocksource.h>
 
+#include <uapi/linux/time.h>
+
 #ifdef BUILD_VDSO32_64
 typedef u64 gtod_long_t;
 #else
 typedef unsigned long gtod_long_t;
 #endif
+
+/*
+ * There is one of these objects in the vvar page for each
+ * vDSO-accelerated clockid.  For high-resolution clocks, this encodes
+ * the time corresponding to vsyscall_gtod_data.cycle_last.  For coarse
+ * clocks, this encodes the actual time.
+ *
+ * To confuse the reader, for high-resolution clocks, nsec is left-shifted
+ * by vsyscall_gtod_data.shift.
+ */
+struct vgtod_ts {
+	u64		sec;
+	u64		nsec;
+};
+
+#define VGTOD_BASES	(CLOCK_TAI + 1)
+#define VGTOD_HRES	(BIT(CLOCK_REALTIME) | BIT(CLOCK_MONOTONIC) | BIT(CLOCK_TAI))
+#define VGTOD_COARSE	(BIT(CLOCK_REALTIME_COARSE) | BIT(CLOCK_MONOTONIC_COARSE))
+
 /*
  * vsyscall_gtod_data will be accessed by 32 and 64 bit code at the same time
  * so be carefull by modifying this structure.
  */
 struct vsyscall_gtod_data {
-	unsigned seq;
+	unsigned int	seq;
 
-	int vclock_mode;
-	u64	cycle_last;
-	u64	mask;
-	u32	mult;
-	u32	shift;
+	int		vclock_mode;
+	u64		cycle_last;
+	u64		mask;
+	u32		mult;
+	u32		shift;
 
-	/* open coded 'struct timespec' */
-	u64		wall_time_snsec;
-	gtod_long_t	wall_time_sec;
-	gtod_long_t	monotonic_time_sec;
-	u64		monotonic_time_snsec;
-	gtod_long_t	wall_time_coarse_sec;
-	gtod_long_t	wall_time_coarse_nsec;
-	gtod_long_t	monotonic_time_coarse_sec;
-	gtod_long_t	monotonic_time_coarse_nsec;
+	struct vgtod_ts	basetime[VGTOD_BASES];
 
 	int		tz_minuteswest;
 	int		tz_dsttime;
@@ -44,9 +57,9 @@ static inline bool vclock_was_used(int vclock)
 	return READ_ONCE(vclocks_used) & (1 << vclock);
 }
 
-static inline unsigned gtod_read_begin(const struct vsyscall_gtod_data *s)
+static inline unsigned int gtod_read_begin(const struct vsyscall_gtod_data *s)
 {
-	unsigned ret;
+	unsigned int ret;
 
 repeat:
 	ret = READ_ONCE(s->seq);
@@ -59,7 +72,7 @@ repeat:
 }
 
 static inline int gtod_read_retry(const struct vsyscall_gtod_data *s,
-					unsigned start)
+				  unsigned int start)
 {
 	smp_rmb();
 	return unlikely(s->seq != start);

arch/x86/kernel/time.c

@@ -10,6 +10,7 @@
  *
  */
 
+#include <linux/clocksource.h>
 #include <linux/clockchips.h>
 #include <linux/interrupt.h>
 #include <linux/irq.h>
@@ -105,3 +106,24 @@ void __init time_init(void)
 {
 	late_time_init = x86_late_time_init;
 }
+
+/*
+ * Sanity check the vdso related archdata content.
+ */
+void clocksource_arch_init(struct clocksource *cs)
+{
+	if (cs->archdata.vclock_mode == VCLOCK_NONE)
+		return;
+
+	if (cs->archdata.vclock_mode > VCLOCK_MAX) {
+		pr_warn("clocksource %s registered with invalid vclock_mode %d. Disabling vclock.\n",
+			cs->name, cs->archdata.vclock_mode);
+		cs->archdata.vclock_mode = VCLOCK_NONE;
+	}
+
+	if (cs->mask != CLOCKSOURCE_MASK(64)) {
+		pr_warn("clocksource %s registered with invalid mask %016llx. Disabling vclock.\n",
+			cs->name, cs->mask);
+		cs->archdata.vclock_mode = VCLOCK_NONE;
+	}
+}

include/linux/clocksource.h

@@ -241,6 +241,11 @@ static inline void __clocksource_update_freq_khz(struct clocksource *cs, u32 khz
 	__clocksource_update_freq_scale(cs, 1000, khz);
 }
 
+#ifdef CONFIG_ARCH_CLOCKSOURCE_INIT
+extern void clocksource_arch_init(struct clocksource *cs);
+#else
+static inline void clocksource_arch_init(struct clocksource *cs) { }
+#endif
 
 extern int timekeeping_notify(struct clocksource *clock);
 

kernel/time/Kconfig

@@ -12,6 +12,10 @@ config CLOCKSOURCE_WATCHDOG
 config ARCH_CLOCKSOURCE_DATA
 	bool
 
+# Architecture has extra clocksource init called from registration
+config ARCH_CLOCKSOURCE_INIT
+	bool
+
 # Clocksources require validation of the clocksource against the last
 # cycle update - x86/TSC misfeature
 config CLOCKSOURCE_VALIDATE_LAST_CYCLE

kernel/time/clocksource.c

@@ -937,6 +937,8 @@ int __clocksource_register_scale(struct clocksource *cs, u32 scale, u32 freq)
 {
 	unsigned long flags;
 
+	clocksource_arch_init(cs);
+
 	/* Initialize mult/shift and max_idle_ns */
 	__clocksource_update_freq_scale(cs, scale, freq);