[tip: sched/core] sched/clock: Provide local_clock_noinstr()

["tip-bot2 for Peter Zijlstra" <tip-bot2@xxxxxxxxxxxxx>]

The following commit has been merged into the sched/core branch of tip:

Commit-ID:     fb7d4948c4da2dbd26da4b7ec76bbd2f19ff862a
Gitweb:        https://git.kernel.org/tip/fb7d4948c4da2dbd26da4b7ec76bbd2f19ff862a
Author:        Peter Zijlstra <peterz@xxxxxxxxxxxxx>
AuthorDate:    Fri, 19 May 2023 12:21:10 +02:00
Committer:     Peter Zijlstra <peterz@xxxxxxxxxxxxx>
CommitterDate: Mon, 05 Jun 2023 21:11:09 +02:00

sched/clock: Provide local_clock_noinstr()

Now that all ARCH_WANTS_NO_INSTR architectures (arm64, loongarch,
s390, x86) provide sched_clock_noinstr(), use this to provide
local_clock_noinstr().

This local_clock_noinstr() will be safe to use from noinstr code with
the assumption that any such noinstr code is non-preemptible (it had
better be, entry code will have IRQs disabled while __cpuidle must
have preemption disabled).

Specifically, preempt_enable_notrace(), a common part of many a
sched_clock() implementation calls out to schedule() -- even though,
per the above, it will never trigger -- which frustrates noinstr
validation.

  vmlinux.o: warning: objtool: local_clock+0xb5: call to preempt_schedule_notrace_thunk() leaves .noinstr.text section

Signed-off-by: Peter Zijlstra (Intel) <peterz@xxxxxxxxxxxxx>
Tested-by: Michael Kelley <mikelley@xxxxxxxxxxxxx>  # Hyper-V
Link: https://lore.kernel.org/r/20230519102715.978624636@xxxxxxxxxxxxx
---
 include/linux/sched/clock.h | 17 ++++++++++++++++-
 kernel/sched/clock.c        | 19 +++++++++++++------
 2 files changed, 29 insertions(+), 7 deletions(-)

diff --git a/include/linux/sched/clock.h b/include/linux/sched/clock.h
index ca008f7..196f0ca 100644
--- a/include/linux/sched/clock.h
+++ b/include/linux/sched/clock.h
@@ -12,7 +12,16 @@
  *
  * Please use one of the three interfaces below.
  */
-extern unsigned long long notrace sched_clock(void);
+extern u64 sched_clock(void);
+
+#if defined(CONFIG_ARCH_WANTS_NO_INSTR) || defined(CONFIG_GENERIC_SCHED_CLOCK)
+extern u64 sched_clock_noinstr(void);
+#else
+static __always_inline u64 sched_clock_noinstr(void)
+{
+	return sched_clock();
+}
+#endif
 
 /*
  * See the comment in kernel/sched/clock.c
@@ -45,6 +54,11 @@ static inline u64 cpu_clock(int cpu)
 	return sched_clock();
 }
 
+static __always_inline u64 local_clock_noinstr(void)
+{
+	return sched_clock_noinstr();
+}
+
 static __always_inline u64 local_clock(void)
 {
 	return sched_clock();
@@ -79,6 +93,7 @@ static inline u64 cpu_clock(int cpu)
 	return sched_clock_cpu(cpu);
 }
 
+extern u64 local_clock_noinstr(void);
 extern u64 local_clock(void);
 
 #endif
diff --git a/kernel/sched/clock.c b/kernel/sched/clock.c
index b5cc2b5..5a575a0 100644
--- a/kernel/sched/clock.c
+++ b/kernel/sched/clock.c
@@ -266,7 +266,7 @@ static __always_inline u64 sched_clock_local(struct sched_clock_data *scd)
 	s64 delta;
 
 again:
-	now = sched_clock();
+	now = sched_clock_noinstr();
 	delta = now - scd->tick_raw;
 	if (unlikely(delta < 0))
 		delta = 0;
@@ -293,22 +293,29 @@ again:
 	return clock;
 }
 
-noinstr u64 local_clock(void)
+noinstr u64 local_clock_noinstr(void)
 {
 	u64 clock;
 
 	if (static_branch_likely(&__sched_clock_stable))
-		return sched_clock() + __sched_clock_offset;
+		return sched_clock_noinstr() + __sched_clock_offset;
 
 	if (!static_branch_likely(&sched_clock_running))
-		return sched_clock();
+		return sched_clock_noinstr();
 
-	preempt_disable_notrace();
 	clock = sched_clock_local(this_scd());
-	preempt_enable_notrace();
 
 	return clock;
 }
+
+u64 local_clock(void)
+{
+	u64 now;
+	preempt_disable_notrace();
+	now = local_clock_noinstr();
+	preempt_enable_notrace();
+	return now;
+}
 EXPORT_SYMBOL_GPL(local_clock);
 
 static notrace u64 sched_clock_remote(struct sched_clock_data *scd)