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

Pull timer and time updates from Thomas Gleixner:
 "A rather large update of timers, timekeeping & co

   - Core timekeeping code is year-2038 safe now for 32bit machines.
     Now we just need to fix all in kernel users and the gazillion of
     user space interfaces which rely on timespec/timeval :)

   - Better cache layout for the timekeeping internal data structures.

   - Proper nanosecond based interfaces for in kernel users.

   - Tree wide cleanup of code which wants nanoseconds but does hoops
     and loops to convert back and forth from timespecs.  Some of it
     definitely belongs into the ugly code museum.

   - Consolidation of the timekeeping interface zoo.

   - A fast NMI safe accessor to clock monotonic for tracing.  This is a
     long standing request to support correlated user/kernel space
     traces.  With proper NTP frequency correction it's also suitable
     for correlation of traces accross separate machines.

   - Checkpoint/restart support for timerfd.

   - A few NOHZ[_FULL] improvements in the [hr]timer code.

   - Code move from kernel to kernel/time of all time* related code.

   - New clocksource/event drivers from the ARM universe.  I'm really
     impressed that despite an architected timer in the newer chips SoC
     manufacturers insist on inventing new and differently broken SoC
     specific timers.

[ Ed. "Impressed"? I don't think that word means what you think it means ]

   - Another round of code move from arch to drivers.  Looks like most
     of the legacy mess in ARM regarding timers is sorted out except for
     a few obnoxious strongholds.

   - The usual updates and fixlets all over the place"

* 'timers-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (114 commits)
  timekeeping: Fixup typo in update_vsyscall_old definition
  clocksource: document some basic timekeeping concepts
  timekeeping: Use cached ntp_tick_length when accumulating error
  timekeeping: Rework frequency adjustments to work better w/ nohz
  timekeeping: Minor fixup for timespec64->timespec assignment
  ftrace: Provide trace clocks monotonic
  timekeeping: Provide fast and NMI safe access to CLOCK_MONOTONIC
  seqcount: Add raw_write_seqcount_latch()
  seqcount: Provide raw_read_seqcount()
  timekeeping: Use tk_read_base as argument for timekeeping_get_ns()
  timekeeping: Create struct tk_read_base and use it in struct timekeeper
  timekeeping: Restructure the timekeeper some more
  clocksource: Get rid of cycle_last
  clocksource: Move cycle_last validation to core code
  clocksource: Make delta calculation a function
  wireless: ath9k: Get rid of timespec conversions
  drm: vmwgfx: Use nsec based interfaces
  drm: i915: Use nsec based interfaces
  timekeeping: Provide ktime_get_raw()
  hangcheck-timer: Use ktime_get_ns()
  ...

4 files changed, 43 insertions, 65 deletions

diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 6b71f041729..6cfeb082a42 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -108,9 +108,9 @@ config X86
 	select CLOCKSOURCE_WATCHDOG
 	select GENERIC_CLOCKEVENTS
 	select ARCH_CLOCKSOURCE_DATA
+	select CLOCKSOURCE_VALIDATE_LAST_CYCLE
 	select GENERIC_CLOCKEVENTS_BROADCAST if X86_64 || (X86_32 && X86_LOCAL_APIC)
 	select GENERIC_TIME_VSYSCALL
-	select KTIME_SCALAR if X86_32
 	select GENERIC_STRNCPY_FROM_USER
 	select GENERIC_STRNLEN_USER
 	select HAVE_CONTEXT_TRACKING if X86_64
diff --git a/arch/x86/kernel/tsc.c b/arch/x86/kernel/tsc.c
index 56b0c338061..b6025f9e36c 100644
--- a/arch/x86/kernel/tsc.c
+++ b/arch/x86/kernel/tsc.c
@@ -950,7 +950,7 @@ core_initcall(cpufreq_tsc);
 static struct clocksource clocksource_tsc;
 
 /*
- * We compare the TSC to the cycle_last value in the clocksource
+ * We used to compare the TSC to the cycle_last value in the clocksource
  * structure to avoid a nasty time-warp. This can be observed in a
  * very small window right after one CPU updated cycle_last under
  * xtime/vsyscall_gtod lock and the other CPU reads a TSC value which
@@ -960,26 +960,23 @@ static struct clocksource clocksource_tsc;
  * due to the unsigned delta calculation of the time keeping core
  * code, which is necessary to support wrapping clocksources like pm
  * timer.
+ *
+ * This sanity check is now done in the core timekeeping code.
+ * checking the result of read_tsc() - cycle_last for being negative.
+ * That works because CLOCKSOURCE_MASK(64) does not mask out any bit.
  */
 static cycle_t read_tsc(struct clocksource *cs)
 {
-	cycle_t ret = (cycle_t)get_cycles();
-
-	return ret >= clocksource_tsc.cycle_last ?
-		ret : clocksource_tsc.cycle_last;
-}
-
-static void resume_tsc(struct clocksource *cs)
-{
-	if (!boot_cpu_has(X86_FEATURE_NONSTOP_TSC_S3))
-		clocksource_tsc.cycle_last = 0;
+	return (cycle_t)get_cycles();
 }
 
+/*
+ * .mask MUST be CLOCKSOURCE_MASK(64). See comment above read_tsc()
+ */
 static struct clocksource clocksource_tsc = {
 	.name                   = "tsc",
 	.rating                 = 300,
 	.read                   = read_tsc,
-	.resume			= resume_tsc,
 	.mask                   = CLOCKSOURCE_MASK(64),
 	.flags                  = CLOCK_SOURCE_IS_CONTINUOUS |
 				  CLOCK_SOURCE_MUST_VERIFY,
diff --git a/arch/x86/kernel/vsyscall_gtod.c b/arch/x86/kernel/vsyscall_gtod.c
index 9531fbb123b..c7d791f32b9 100644
--- a/arch/x86/kernel/vsyscall_gtod.c
+++ b/arch/x86/kernel/vsyscall_gtod.c
@@ -31,29 +31,30 @@ void update_vsyscall(struct timekeeper *tk)
 	gtod_write_begin(vdata);
 
 	/* copy vsyscall data */
-	vdata->vclock_mode	= tk->clock->archdata.vclock_mode;
-	vdata->cycle_last	= tk->clock->cycle_last;
-	vdata->mask		= tk->clock->mask;
-	vdata->mult		= tk->mult;
-	vdata->shift		= tk->shift;
+	vdata->vclock_mode	= tk->tkr.clock->archdata.vclock_mode;
+	vdata->cycle_last	= tk->tkr.cycle_last;
+	vdata->mask		= tk->tkr.mask;
+	vdata->mult		= tk->tkr.mult;
+	vdata->shift		= tk->tkr.shift;
 
 	vdata->wall_time_sec		= tk->xtime_sec;
-	vdata->wall_time_snsec		= tk->xtime_nsec;
+	vdata->wall_time_snsec		= tk->tkr.xtime_nsec;
 
 	vdata->monotonic_time_sec	= tk->xtime_sec
 					+ tk->wall_to_monotonic.tv_sec;
-	vdata->monotonic_time_snsec	= tk->xtime_nsec
+	vdata->monotonic_time_snsec	= tk->tkr.xtime_nsec
 					+ ((u64)tk->wall_to_monotonic.tv_nsec
-						<< tk->shift);
+						<< tk->tkr.shift);
 	while (vdata->monotonic_time_snsec >=
-					(((u64)NSEC_PER_SEC) << tk->shift)) {
+					(((u64)NSEC_PER_SEC) << tk->tkr.shift)) {
 		vdata->monotonic_time_snsec -=
-					((u64)NSEC_PER_SEC) << tk->shift;
+					((u64)NSEC_PER_SEC) << tk->tkr.shift;
 		vdata->monotonic_time_sec++;
 	}
 
 	vdata->wall_time_coarse_sec	= tk->xtime_sec;
-	vdata->wall_time_coarse_nsec	= (long)(tk->xtime_nsec >> tk->shift);
+	vdata->wall_time_coarse_nsec	= (long)(tk->tkr.xtime_nsec >>
+						 tk->tkr.shift);
 
 	vdata->monotonic_time_coarse_sec =
 		vdata->wall_time_coarse_sec + tk->wall_to_monotonic.tv_sec;
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index b86d329b953..ca3d760dd58 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -1020,9 +1020,8 @@ struct pvclock_gtod_data {
 		u32	shift;
 	} clock;
 
-	/* open coded 'struct timespec' */
-	u64		monotonic_time_snsec;
-	time_t		monotonic_time_sec;
+	u64		boot_ns;
+	u64		nsec_base;
 };
 
 static struct pvclock_gtod_data pvclock_gtod_data;
@@ -1030,27 +1029,21 @@ static struct pvclock_gtod_data pvclock_gtod_data;
 static void update_pvclock_gtod(struct timekeeper *tk)
 {
 	struct pvclock_gtod_data *vdata = &pvclock_gtod_data;
+	u64 boot_ns;
+
+	boot_ns = ktime_to_ns(ktime_add(tk->tkr.base_mono, tk->offs_boot));
 
 	write_seqcount_begin(&vdata->seq);
 
 	/* copy pvclock gtod data */
-	vdata->clock.vclock_mode	= tk->clock->archdata.vclock_mode;
-	vdata->clock.cycle_last		= tk->clock->cycle_last;
-	vdata->clock.mask		= tk->clock->mask;
-	vdata->clock.mult		= tk->mult;
-	vdata->clock.shift		= tk->shift;
-
-	vdata->monotonic_time_sec	= tk->xtime_sec
-					+ tk->wall_to_monotonic.tv_sec;
-	vdata->monotonic_time_snsec	= tk->xtime_nsec
-					+ (tk->wall_to_monotonic.tv_nsec
-						<< tk->shift);
-	while (vdata->monotonic_time_snsec >=
-					(((u64)NSEC_PER_SEC) << tk->shift)) {
-		vdata->monotonic_time_snsec -=
-					((u64)NSEC_PER_SEC) << tk->shift;
-		vdata->monotonic_time_sec++;
-	}
+	vdata->clock.vclock_mode	= tk->tkr.clock->archdata.vclock_mode;
+	vdata->clock.cycle_last		= tk->tkr.cycle_last;
+	vdata->clock.mask		= tk->tkr.mask;
+	vdata->clock.mult		= tk->tkr.mult;
+	vdata->clock.shift		= tk->tkr.shift;
+
+	vdata->boot_ns			= boot_ns;
+	vdata->nsec_base		= tk->tkr.xtime_nsec;
 
 	write_seqcount_end(&vdata->seq);
 }
@@ -1145,11 +1138,7 @@ static void kvm_get_time_scale(uint32_t scaled_khz, uint32_t base_khz,
 
 static inline u64 get_kernel_ns(void)
 {
-	struct timespec ts;
-
-	ktime_get_ts(&ts);
-	monotonic_to_bootbased(&ts);
-	return timespec_to_ns(&ts);
+	return ktime_get_boot_ns();
 }
 
 #ifdef CONFIG_X86_64
@@ -1414,23 +1403,22 @@ static inline u64 vgettsc(cycle_t *cycle_now)
 	return v * gtod->clock.mult;
 }
 
-static int do_monotonic(struct timespec *ts, cycle_t *cycle_now)
+static int do_monotonic_boot(s64 *t, cycle_t *cycle_now)
 {
+	struct pvclock_gtod_data *gtod = &pvclock_gtod_data;
 	unsigned long seq;
-	u64 ns;
 	int mode;
-	struct pvclock_gtod_data *gtod = &pvclock_gtod_data;
+	u64 ns;
 
-	ts->tv_nsec = 0;
 	do {
 		seq = read_seqcount_begin(&gtod->seq);
 		mode = gtod->clock.vclock_mode;
-		ts->tv_sec = gtod->monotonic_time_sec;
-		ns = gtod->monotonic_time_snsec;
+		ns = gtod->nsec_base;
 		ns += vgettsc(cycle_now);
 		ns >>= gtod->clock.shift;
+		ns += gtod->boot_ns;
 	} while (unlikely(read_seqcount_retry(&gtod->seq, seq)));
-	timespec_add_ns(ts, ns);
+	*t = ns;
 
 	return mode;
 }
@@ -1438,19 +1426,11 @@ static int do_monotonic(struct timespec *ts, cycle_t *cycle_now)
 /* returns true if host is using tsc clocksource */
 static bool kvm_get_time_and_clockread(s64 *kernel_ns, cycle_t *cycle_now)
 {
-	struct timespec ts;
-
 	/* checked again under seqlock below */
 	if (pvclock_gtod_data.clock.vclock_mode != VCLOCK_TSC)
 		return false;
 
-	if (do_monotonic(&ts, cycle_now) != VCLOCK_TSC)
-		return false;
-
-	monotonic_to_bootbased(&ts);
-	*kernel_ns = timespec_to_ns(&ts);
-
-	return true;
+	return do_monotonic_boot(kernel_ns, cycle_now) == VCLOCK_TSC;
 }
 #endif