Sched: Scheduler time slice extension

Add support for a thread to request extending its execution time slice on
the cpu. The extra cpu time granted would help in allowing the thread to
complete executing the critical section and drop any locks without getting
preempted. The thread would request this cpu time extension, by setting a
bit in the restartable sequences(rseq) structure registered with the kernel.

Kernel will grant a 50us extension on the cpu, when it sees the bit set.
With the help of a timer, kernel force preempts the thread if it is still
running on the cpu when the 50us timer expires. The thread should yield
the cpu after completing the critical section.

Orabug: 37583007

Suggested-by: Peter Ziljstra <[email protected]>
Signed-off-by: Prakash Sangappa <[email protected]>
Reviewed-by: Chris Hyser <[email protected]>

Author: Prakash Sangappa

include/linux/entry-common.h

@@ -302,7 +302,8 @@ void arch_do_signal_or_restart(struct pt_regs *regs);
  * exit_to_user_mode_loop - do any pending work before leaving to user space
  */
 unsigned long exit_to_user_mode_loop(struct pt_regs *regs,
-				     unsigned long ti_work);
+				     unsigned long ti_work,
+				     bool irq);
 
 /**
  * exit_to_user_mode_prepare - call exit_to_user_mode_loop() if required
@@ -314,7 +315,8 @@ unsigned long exit_to_user_mode_loop(struct pt_regs *regs,
  *    EXIT_TO_USER_MODE_WORK are set
  * 4) check that interrupts are still disabled
  */
-static __always_inline void exit_to_user_mode_prepare(struct pt_regs *regs)
+static __always_inline void exit_to_user_mode_prepare(struct pt_regs *regs,
+						bool irq)
 {
 	unsigned long ti_work;
 
@@ -325,7 +327,10 @@ static __always_inline void exit_to_user_mode_prepare(struct pt_regs *regs)
 
 	ti_work = read_thread_flags();
 	if (unlikely(ti_work & EXIT_TO_USER_MODE_WORK))
-		ti_work = exit_to_user_mode_loop(regs, ti_work);
+		ti_work = exit_to_user_mode_loop(regs, ti_work, irq);
+
+	if (irq)
+		rseq_delay_resched_fini();
 
 	arch_exit_to_user_mode_prepare(regs, ti_work);
 

include/linux/sched.h

@@ -327,6 +327,7 @@ extern int __must_check io_schedule_prepare(void);
 extern void io_schedule_finish(int token);
 extern long io_schedule_timeout(long timeout);
 extern void io_schedule(void);
+extern void hrtick_local_start(u64 delay);
 
 /**
  * struct prev_cputime - snapshot of system and user cputime
@@ -933,6 +934,9 @@ struct task_struct {
 	struct plist_node		pushable_tasks;
 	struct rb_node			pushable_dl_tasks;
 #endif
+#ifdef CONFIG_RSEQ
+	unsigned			rseq_sched_delay:1;
+#endif
 
 	struct mm_struct		*mm;
 	struct mm_struct		*active_mm;
@@ -2208,6 +2212,20 @@ static inline bool owner_on_cpu(struct task_struct *owner)
 unsigned long sched_cpu_util(int cpu);
 #endif /* CONFIG_SMP */
 
+#ifdef CONFIG_RSEQ
+
+extern bool rseq_delay_resched(void);
+extern void rseq_delay_resched_fini(void);
+extern void rseq_delay_resched_tick(void);
+
+#else
+
+static inline bool rseq_delay_resched(void) { return false; }
+static inline void rseq_delay_resched_fini(void) { }
+static inline void rseq_delay_resched_tick(void) { }
+
+#endif
+
 #ifdef CONFIG_SCHED_CORE
 extern void sched_core_free(struct task_struct *tsk);
 extern void sched_core_fork(struct task_struct *p);

include/uapi/linux/rseq.h

@@ -26,6 +26,7 @@ enum rseq_cs_flags_bit {
 	RSEQ_CS_FLAG_NO_RESTART_ON_PREEMPT_BIT	= 0,
 	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,
 };
 
 enum rseq_cs_flags {
@@ -35,6 +36,8 @@ enum rseq_cs_flags {
 		(1U << RSEQ_CS_FLAG_NO_RESTART_ON_SIGNAL_BIT),
 	RSEQ_CS_FLAG_NO_RESTART_ON_MIGRATE	=
 		(1U << RSEQ_CS_FLAG_NO_RESTART_ON_MIGRATE_BIT),
+	RSEQ_CS_FLAG_DELAY_RESCHED		=
+		(1U << RSEQ_CS_FLAG_DELAY_RESCHED_BIT),
 };
 
 /*
@@ -128,6 +131,8 @@ struct rseq {
 	 * - RSEQ_CS_FLAG_NO_RESTART_ON_MIGRATE
 	 *     Inhibit instruction sequence block restart on migration for
 	 *     this thread.
+	 * - RSEQ_CS_DELAY_RESCHED
+	 *     Try delay resched...
 	 */
 	__u32 flags;
 

kernel/entry/common.c

@@ -89,7 +89,8 @@ void __weak arch_do_signal_or_restart(struct pt_regs *regs) { }
  * @ti_work:	TIF work flags as read by the caller
  */
 __always_inline unsigned long exit_to_user_mode_loop(struct pt_regs *regs,
-						     unsigned long ti_work)
+						     unsigned long ti_work,
+						     bool irq)
 {
 	/*
 	 * Before returning to user space ensure that all pending work
@@ -99,8 +100,12 @@ __always_inline unsigned long exit_to_user_mode_loop(struct pt_regs *regs,
 
 		local_irq_enable_exit_to_user(ti_work);
 
-		if (ti_work & _TIF_NEED_RESCHED)
-			schedule();
+		if (ti_work & _TIF_NEED_RESCHED) {
+			if (irq && rseq_delay_resched())
+				clear_tsk_need_resched(current);
+			else
+				schedule();
+		}
 
 		if (ti_work & _TIF_UPROBE)
 			uprobe_notify_resume(regs);
@@ -208,7 +213,7 @@ static __always_inline void __syscall_exit_to_user_mode_work(struct pt_regs *reg
 {
 	syscall_exit_to_user_mode_prepare(regs);
 	local_irq_disable_exit_to_user();
-	exit_to_user_mode_prepare(regs);
+	exit_to_user_mode_prepare(regs, false);
 }
 
 void syscall_exit_to_user_mode_work(struct pt_regs *regs)
@@ -232,7 +237,7 @@ noinstr void irqentry_enter_from_user_mode(struct pt_regs *regs)
 noinstr void irqentry_exit_to_user_mode(struct pt_regs *regs)
 {
 	instrumentation_begin();
-	exit_to_user_mode_prepare(regs);
+	exit_to_user_mode_prepare(regs, true);
 	instrumentation_end();
 	exit_to_user_mode();
 }

kernel/rseq.c

@@ -339,6 +339,62 @@ void __rseq_handle_notify_resume(struct ksignal *ksig, struct pt_regs *regs)
 	force_sigsegv(sig);
 }
 
+bool rseq_delay_resched(void)
+{
+	struct task_struct *t = current;
+	u32 flags;
+
+	if (!IS_ENABLED(CONFIG_SCHED_HRTICK))
+		return false;
+
+	if (!t->rseq)
+		return false;
+
+	if (t->rseq_sched_delay)
+		return false;
+
+	if (copy_from_user_nofault(&flags, &t->rseq->flags, sizeof(flags)))
+		return false;
+
+	if (!(flags & RSEQ_CS_FLAG_DELAY_RESCHED))
+		return false;
+
+	flags &= ~RSEQ_CS_FLAG_DELAY_RESCHED;
+	if (copy_to_user_nofault(&t->rseq->flags, &flags, sizeof(flags)))
+		return false;
+
+	t->rseq_sched_delay = 1;
+
+	return true;
+}
+
+void rseq_delay_resched_fini(void)
+{
+#ifdef CONFIG_SCHED_HRTICK
+	extern void hrtick_local_start(u64 delay);
+	struct task_struct *t = current;
+	/*
+	 * IRQs off, guaranteed to return to userspace, start timer on this CPU
+	 * to limit the resched-overdraft.
+	 *
+	 * If your critical section is longer than 50 us you get to keep the
+	 * pieces.
+	 */
+	if (t->rseq_sched_delay)
+		hrtick_local_start(50 * NSEC_PER_USEC);
+#endif
+}
+
+void rseq_delay_resched_tick(void)
+{
+#ifdef CONFIG_SCHED_HRTICK
+	struct task_struct *t = current;
+
+	if (t->rseq_sched_delay)
+		set_tsk_need_resched(t);
+#endif
+}
+
 #ifdef CONFIG_DEBUG_RSEQ
 
 /*

kernel/sched/core.c

@@ -817,6 +817,7 @@ void update_rq_clock(struct rq *rq)
 
 static void hrtick_clear(struct rq *rq)
 {
+	rseq_delay_resched_tick();
 	if (hrtimer_active(&rq->hrtick_timer))
 		hrtimer_cancel(&rq->hrtick_timer);
 }
@@ -832,6 +833,8 @@ static enum hrtimer_restart hrtick(struct hrtimer *timer)
 
 	WARN_ON_ONCE(cpu_of(rq) != smp_processor_id());
 
+	rseq_delay_resched_tick();
+
 	rq_lock(rq, &rf);
 	update_rq_clock(rq);
 	rq->curr->sched_class->task_tick(rq, rq->curr, 1);
@@ -905,6 +908,16 @@ void hrtick_start(struct rq *rq, u64 delay)
 
 #endif /* CONFIG_SMP */
 
+void hrtick_local_start(u64 delay)
+{
+	struct rq *rq = this_rq();
+	struct rq_flags rf;
+
+	rq_lock(rq, &rf);
+	hrtick_start(rq, delay);
+	rq_unlock(rq, &rf);
+}
+
 static void hrtick_rq_init(struct rq *rq)
 {
 #ifdef CONFIG_SMP
@@ -6663,6 +6676,9 @@ static void __sched notrace __schedule(int sched_mode)
 picked:
 	clear_tsk_need_resched(prev);
 	clear_preempt_need_resched();
+#ifdef CONFIG_RSEQ
+	prev->rseq_sched_delay = 0;
+#endif
 #ifdef CONFIG_SCHED_DEBUG
 	rq->last_seen_need_resched_ns = 0;
 #endif

kernel/sched/syscalls.c

@@ -1419,6 +1419,14 @@ static void do_sched_yield(void)
  */
 SYSCALL_DEFINE0(sched_yield)
 {
+
+#ifdef CONFIG_RSEQ
+	if (current->rseq_sched_delay) {
+		schedule();
+		return 0;
+	}
+#endif
+
 	do_sched_yield();
 	return 0;
 }