[PATCH V7 02/11] sched: Indicate if thread got rescheduled

[Prakash Sangappa <prakash.sangappa@oracle.com>]

Use a bit in rseq flags to indicate if the thread got rescheduled
after the cpu time extension was graned. The user thread can check this
flag before calling sched_yield() to yield the cpu.

Signed-off-by: Prakash Sangappa <prakash.sangappa@oracle.com>
---
 include/linux/sched.h     |  2 ++
 include/uapi/linux/rseq.h | 10 ++++++++++
 kernel/rseq.c             | 13 +++++++++++++
 kernel/sched/core.c       |  5 ++---
 4 files changed, 27 insertions(+), 3 deletions(-)

diff --git a/include/linux/sched.h b/include/linux/sched.h
index 5d2819afd481..5df055f2dd9e 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -2258,6 +2258,7 @@ unsigned long sched_cpu_util(int cpu);
 extern bool __rseq_delay_resched(void);
 extern void rseq_delay_resched_arm_timer(void);
 extern void rseq_delay_resched_tick(void);
+extern void rseq_delay_resched_clear(struct task_struct *tsk);
 static inline bool rseq_delay_set_need_resched(void)
 {
     if (current->rseq_delay_resched == RSEQ_RESCHED_DELAY_REQUESTED) {
@@ -2271,6 +2272,7 @@ static inline bool __rseq_delay_resched(void) { return false; }
 static inline void rseq_delay_resched_arm_timer(void) { }
 static inline void rseq_delay_resched_tick(void) { }
 static inline bool rseq_delay_set_need_resched(void) { return false; }
+static inline void rseq_delay_resched_clear(struct task_struct *tsk) { }
 #endif
 
 #ifdef CONFIG_SCHED_CORE
diff --git a/include/uapi/linux/rseq.h b/include/uapi/linux/rseq.h
index 25fc636b17d5..f4813d931387 100644
--- a/include/uapi/linux/rseq.h
+++ b/include/uapi/linux/rseq.h
@@ -27,6 +27,7 @@ enum rseq_cs_flags_bit {
 	RSEQ_CS_FLAG_NO_RESTART_ON_SIGNAL_BIT	= 1,
 	RSEQ_CS_FLAG_NO_RESTART_ON_MIGRATE_BIT	= 2,
 	RSEQ_CS_FLAG_DELAY_RESCHED_BIT		= 3,
+	RSEQ_CS_FLAG_RESCHEDULED_BIT		= 4,
 };
 
 enum rseq_cs_flags {
@@ -38,6 +39,9 @@ enum rseq_cs_flags {
 		(1U << RSEQ_CS_FLAG_NO_RESTART_ON_MIGRATE_BIT),
 	RSEQ_CS_FLAG_DELAY_RESCHED		=
 		(1U << RSEQ_CS_FLAG_DELAY_RESCHED_BIT),
+	RSEQ_CS_FLAG_RESCHEDULED		=
+		(1U << RSEQ_CS_FLAG_RESCHEDULED_BIT),
+
 };
 
 /*
@@ -135,6 +139,12 @@ struct rseq {
 	 *     Request by user thread to delay preemption. With use
 	 *     of a timer, kernel grants extra cpu time upto 30us for this
 	 *     thread before being rescheduled.
+	 * - RSEQ_CS_FLAG_RESCHEDULED
+	 *     Set by kernel if the thread was rescheduled in the extra time
+	 *     granted due to request RSEQ_CS_DELAY_RESCHED. This bit is
+	 *     checked by the thread before calling sched_yield() to yield
+	 *     cpu. User thread sets this bit to 0, when setting
+	 *     RSEQ_CS_DELAY_RESCHED to request preemption delay.
 	 */
 	__u32 flags;
 
diff --git a/kernel/rseq.c b/kernel/rseq.c
index 8b6af4e12142..6331b653b402 100644
--- a/kernel/rseq.c
+++ b/kernel/rseq.c
@@ -480,6 +480,19 @@ void rseq_delay_resched_tick(void)
 	if (current->rseq_delay_resched == RSEQ_RESCHED_DELAY_REQUESTED)
 		set_tsk_need_resched(current);
 }
+
+void rseq_delay_resched_clear(struct task_struct *tsk)
+{
+	u32 flags;
+
+	if (tsk->rseq_delay_resched == RSEQ_RESCHED_DELAY_REQUESTED) {
+		tsk->rseq_delay_resched = RSEQ_RESCHED_DELAY_PROBE;
+		if (copy_from_user_nofault(&flags, &tsk->rseq->flags, sizeof(flags)))
+                        return;
+                flags |= RSEQ_CS_FLAG_RESCHEDULED;
+                copy_to_user_nofault(&tsk->rseq->flags, &flags, sizeof(flags));
+	}
+}
 #endif /* CONFIG_RSEQ_RESCHED_DELAY */
 
 #ifdef CONFIG_DEBUG_RSEQ
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index e75ecbb2c1f7..ba1e4f6981cd 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -6752,9 +6752,8 @@ static void __sched notrace __schedule(int sched_mode)
 picked:
 	clear_tsk_need_resched(prev);
 	clear_preempt_need_resched();
-	if (IS_ENABLED(CONFIG_RSEQ_RESCHED_DELAY) &&
-	    prev->rseq_delay_resched == RSEQ_RESCHED_DELAY_REQUESTED)
-		prev->rseq_delay_resched = RSEQ_RESCHED_DELAY_PROBE;
+	if(IS_ENABLED(CONFIG_RSEQ_RESCHED_DELAY))
+		rseq_delay_resched_clear(prev);
 	rq->last_seen_need_resched_ns = 0;
 
 	is_switch = prev != next;
-- 
2.43.5