sched/clock/x86: Mark sched_clock() noinstr

In order to use sched_clock() from noinstr code, mark it and all it's
implenentations noinstr.

The whole pvclock thing (used by KVM/Xen) is a bit of a pain,
since it calls out to watchdogs, create a
pvclock_clocksource_read_nowd() variant doesn't do that and can be
noinstr.

Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Link: https://lore.kernel.org/r/20230126151323.702003578@infradead.org

4 files changed, 22 insertions, 12 deletions

diff --git a/arch/x86/kernel/cpu/vmware.c b/arch/x86/kernel/cpu/vmware.c
index 02039ec3597d..11f83d07925e 100644
--- a/arch/x86/kernel/cpu/vmware.c
+++ b/arch/x86/kernel/cpu/vmware.c
@@ -143,7 +143,7 @@ static __init int parse_no_stealacc(char *arg)
 }
 early_param("no-steal-acc", parse_no_stealacc);
 
-static unsigned long long notrace vmware_sched_clock(void)
+static noinstr u64 vmware_sched_clock(void)
 {
 	unsigned long long ns;
 
diff --git a/arch/x86/kernel/kvmclock.c b/arch/x86/kernel/kvmclock.c
index 16333ba1904b..0f35d44c56fe 100644
--- a/arch/x86/kernel/kvmclock.c
+++ b/arch/x86/kernel/kvmclock.c
@@ -71,12 +71,12 @@ static int kvm_set_wallclock(const struct timespec64 *now)
 	return -ENODEV;
 }
 
-static u64 kvm_clock_read(void)
+static noinstr u64 kvm_clock_read(void)
 {
 	u64 ret;
 
 	preempt_disable_notrace();
-	ret = pvclock_clocksource_read(this_cpu_pvti());
+	ret = pvclock_clocksource_read_nowd(this_cpu_pvti());
 	preempt_enable_notrace();
 	return ret;
 }
@@ -86,7 +86,7 @@ static u64 kvm_clock_get_cycles(struct clocksource *cs)
 	return kvm_clock_read();
 }
 
-static u64 kvm_sched_clock_read(void)
+static noinstr u64 kvm_sched_clock_read(void)
 {
 	return kvm_clock_read() - kvm_sched_clock_offset;
 }
diff --git a/arch/x86/kernel/pvclock.c b/arch/x86/kernel/pvclock.c
index 5a2a517dd61b..56acf53a782a 100644
--- a/arch/x86/kernel/pvclock.c
+++ b/arch/x86/kernel/pvclock.c
@@ -64,7 +64,8 @@ u8 pvclock_read_flags(struct pvclock_vcpu_time_info *src)
 	return flags & valid_flags;
 }
 
-u64 pvclock_clocksource_read(struct pvclock_vcpu_time_info *src)
+static __always_inline
+u64 __pvclock_clocksource_read(struct pvclock_vcpu_time_info *src, bool dowd)
 {
 	unsigned version;
 	u64 ret;
@@ -77,7 +78,7 @@ u64 pvclock_clocksource_read(struct pvclock_vcpu_time_info *src)
 		flags = src->flags;
 	} while (pvclock_read_retry(src, version));
 
-	if (unlikely((flags & PVCLOCK_GUEST_STOPPED) != 0)) {
+	if (dowd && unlikely((flags & PVCLOCK_GUEST_STOPPED) != 0)) {
 		src->flags &= ~PVCLOCK_GUEST_STOPPED;
 		pvclock_touch_watchdogs();
 	}
@@ -100,15 +101,25 @@ u64 pvclock_clocksource_read(struct pvclock_vcpu_time_info *src)
 	 * updating at the same time, and one of them could be slightly behind,
 	 * making the assumption that last_value always go forward fail to hold.
 	 */
-	last = atomic64_read(&last_value);
+	last = arch_atomic64_read(&last_value);
 	do {
 		if (ret <= last)
 			return last;
-	} while (!atomic64_try_cmpxchg(&last_value, &last, ret));
+	} while (!arch_atomic64_try_cmpxchg(&last_value, &last, ret));
 
 	return ret;
 }
 
+u64 pvclock_clocksource_read(struct pvclock_vcpu_time_info *src)
+{
+	return __pvclock_clocksource_read(src, true);
+}
+
+noinstr u64 pvclock_clocksource_read_nowd(struct pvclock_vcpu_time_info *src)
+{
+	return __pvclock_clocksource_read(src, false);
+}
+
 void pvclock_read_wallclock(struct pvclock_wall_clock *wall_clock,
 			    struct pvclock_vcpu_time_info *vcpu_time,
 			    struct timespec64 *ts)
diff --git a/arch/x86/kernel/tsc.c b/arch/x86/kernel/tsc.c
index a78e73da4a74..8c33936b017d 100644
--- a/arch/x86/kernel/tsc.c
+++ b/arch/x86/kernel/tsc.c
@@ -215,7 +215,7 @@ static void __init cyc2ns_init_secondary_cpus(void)
 /*
  * Scheduler clock - returns current time in nanosec units.
  */
-u64 native_sched_clock(void)
+noinstr u64 native_sched_clock(void)
 {
 	if (static_branch_likely(&__use_tsc)) {
 		u64 tsc_now = rdtsc();
@@ -248,7 +248,7 @@ u64 native_sched_clock_from_tsc(u64 tsc)
 /* We need to define a real function for sched_clock, to override the
    weak default version */
 #ifdef CONFIG_PARAVIRT
-unsigned long long sched_clock(void)
+noinstr u64 sched_clock(void)
 {
 	return paravirt_sched_clock();
 }
@@ -258,8 +258,7 @@ bool using_native_sched_clock(void)
 	return static_call_query(pv_sched_clock) == native_sched_clock;
 }
 #else
-unsigned long long
-sched_clock(void) __attribute__((alias("native_sched_clock")));
+u64 sched_clock(void) __attribute__((alias("native_sched_clock")));
 
 bool using_native_sched_clock(void) { return true; }
 #endif