sched/core: Introduce SM_IDLE and an idle re-entry fast-path in __schedule()

Since commit b2a02fc4 ("smp: Optimize
send_call_function_single_ipi()") an idle CPU in TIF_POLLING_NRFLAG mode
can be pulled out of idle by setting TIF_NEED_RESCHED flag to service an
IPI without actually sending an interrupt. Even in cases where the IPI
handler does not queue a task on the idle CPU, do_idle() will call
__schedule() since need_resched() returns true in these cases.

Introduce and use SM_IDLE to identify call to __schedule() from
schedule_idle() and shorten the idle re-entry time by skipping
pick_next_task() when nr_running is 0 and the previous task is the idle
task.

With the SM_IDLE fast-path, the time taken to complete a fixed set of
IPIs using ipistorm improves noticeably. Following are the numbers
from a dual socket Intel Ice Lake Xeon server (2 x 32C/64T) and
3rd Generation AMD EPYC system (2 x 64C/128T) (boost on, C2 disabled)
running ipistorm between CPU8 and CPU16:

cmdline: insmod ipistorm.ko numipi=100000 single=1 offset=8 cpulist=8 wait=1

   ==================================================================
   Test          : ipistorm (modified)
   Units         : Normalized runtime
   Interpretation: Lower is better
   Statistic     : AMean
   ======================= Intel Ice Lake Xeon ======================
   kernel:				time [pct imp]
   tip:sched/core			1.00 [baseline]
   tip:sched/core + SM_IDLE		0.80 [20.51%]
   ==================== 3rd Generation AMD EPYC =====================
   kernel:				time [pct imp]
   tip:sched/core			1.00 [baseline]
   tip:sched/core + SM_IDLE		0.90 [10.17%]
   ==================================================================

[ kprateek: Commit message, SM_RTLOCK_WAIT fix ]
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Not-yet-signed-off-by: Peter Zijlstra <peterz@infradead.org>
Signed-off-by: K Prateek Nayak <kprateek.nayak@amd.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Acked-by: Vincent Guittot <vincent.guittot@linaro.org>
Link: https://lore.kernel.org/r/20240809092240.6921-1-kprateek.nayak@amd.com

kernel/sched/core.c

@@ -6410,19 +6410,12 @@ pick_next_task(struct rq *rq, struct task_struct *prev, struct rq_flags *rf)
  * Constants for the sched_mode argument of __schedule().
  *
  * The mode argument allows RT enabled kernels to differentiate a
- * preemption from blocking on an 'sleeping' spin/rwlock. Note that
- * SM_MASK_PREEMPT for !RT has all bits set, which allows the compiler to
- * optimize the AND operation out and just check for zero.
+ * preemption from blocking on an 'sleeping' spin/rwlock.
  */
-#define SM_NONE			0x0
-#define SM_PREEMPT		0x1
-#define SM_RTLOCK_WAIT		0x2
-
-#ifndef CONFIG_PREEMPT_RT
-# define SM_MASK_PREEMPT	(~0U)
-#else
-# define SM_MASK_PREEMPT	SM_PREEMPT
-#endif
+#define SM_IDLE			(-1)
+#define SM_NONE			0
+#define SM_PREEMPT		1
+#define SM_RTLOCK_WAIT		2
 
 /*
  * __schedule() is the main scheduler function.
@@ -6463,9 +6456,14 @@ pick_next_task(struct rq *rq, struct task_struct *prev, struct rq_flags *rf)
  *
  * WARNING: must be called with preemption disabled!
  */
-static void __sched notrace __schedule(unsigned int sched_mode)
+static void __sched notrace __schedule(int sched_mode)
 {
 	struct task_struct *prev, *next;
+	/*
+	 * On PREEMPT_RT kernel, SM_RTLOCK_WAIT is noted
+	 * as a preemption by schedule_debug() and RCU.
+	 */
+	bool preempt = sched_mode > SM_NONE;
 	unsigned long *switch_count;
 	unsigned long prev_state;
 	struct rq_flags rf;
@@ -6476,13 +6474,13 @@ static void __sched notrace __schedule(unsigned int sched_mode)
 	rq = cpu_rq(cpu);
 	prev = rq->curr;
 
-	schedule_debug(prev, !!sched_mode);
+	schedule_debug(prev, preempt);
 
 	if (sched_feat(HRTICK) || sched_feat(HRTICK_DL))
 		hrtick_clear(rq);
 
 	local_irq_disable();
-	rcu_note_context_switch(!!sched_mode);
+	rcu_note_context_switch(preempt);
 
 	/*
 	 * Make sure that signal_pending_state()->signal_pending() below
@@ -6511,12 +6509,20 @@ static void __sched notrace __schedule(unsigned int sched_mode)
 
 	switch_count = &prev->nivcsw;
 
+	/* Task state changes only considers SM_PREEMPT as preemption */
+	preempt = sched_mode == SM_PREEMPT;
+
 	/*
 	 * We must load prev->state once (task_struct::state is volatile), such
 	 * that we form a control dependency vs deactivate_task() below.
 	 */
 	prev_state = READ_ONCE(prev->__state);
-	if (!(sched_mode & SM_MASK_PREEMPT) && prev_state) {
+	if (sched_mode == SM_IDLE) {
+		if (!rq->nr_running) {
+			next = prev;
+			goto picked;
+		}
+	} else if (!preempt && prev_state) {
 		if (signal_pending_state(prev_state, prev)) {
 			WRITE_ONCE(prev->__state, TASK_RUNNING);
 		} else {
@@ -6547,6 +6553,7 @@ static void __sched notrace __schedule(unsigned int sched_mode)
 	}
 
 	next = pick_next_task(rq, prev, &rf);
+picked:
 	clear_tsk_need_resched(prev);
 	clear_preempt_need_resched();
 #ifdef CONFIG_SCHED_DEBUG
@@ -6588,7 +6595,7 @@ static void __sched notrace __schedule(unsigned int sched_mode)
 		psi_account_irqtime(rq, prev, next);
 		psi_sched_switch(prev, next, !task_on_rq_queued(prev));
 
-		trace_sched_switch(sched_mode & SM_MASK_PREEMPT, prev, next, prev_state);
+		trace_sched_switch(preempt, prev, next, prev_state);
 
 		/* Also unlocks the rq: */
 		rq = context_switch(rq, prev, next, &rf);
@@ -6664,7 +6671,7 @@ static void sched_update_worker(struct task_struct *tsk)
 	}
 }
 
-static __always_inline void __schedule_loop(unsigned int sched_mode)
+static __always_inline void __schedule_loop(int sched_mode)
 {
 	do {
 		preempt_disable();
@@ -6709,7 +6716,7 @@ void __sched schedule_idle(void)
 	 */
 	WARN_ON_ONCE(current->__state);
 	do {
-		__schedule(SM_NONE);
+		__schedule(SM_IDLE);
 	} while (need_resched());
 }