[PATCH v2 8/9] irqentry: define irqentry_exit_allow_resched()

From: Ankur Arora <ankur.a.arora@oracle.com>
To: linux-kernel@vger.kernel.org, linux-mm@kvack.org, x86@kernel.org
Cc: akpm@linux-foundation.org, luto@kernel.org, bp@alien8.de,
	dave.hansen@linux.intel.com, hpa@zytor.com, mingo@redhat.com,
	juri.lelli@redhat.com, vincent.guittot@linaro.org,
	willy@infradead.org, mgorman@suse.de, peterz@infradead.org,
	rostedt@goodmis.org, tglx@linutronix.de, jon.grimm@amd.com,
	bharata@amd.com, raghavendra.kt@amd.com,
	boris.ostrovsky@oracle.com, konrad.wilk@oracle.com,
	Ankur Arora <ankur.a.arora@oracle.com>
Subject: [PATCH v2 8/9] irqentry: define irqentry_exit_allow_resched()
Date: Wed, 30 Aug 2023 11:49:57 -0700	[thread overview]
Message-ID: <20230830184958.2333078-9-ankur.a.arora@oracle.com> (raw)
In-Reply-To: <20230830184958.2333078-1-ankur.a.arora@oracle.com>

Threads marked with TIF_ALLOW_RESCHED are preemptible, but do
not have explicit preemption points.

Handle them as we do preempt_model_full(), by rescheduling in the
irqentry_exit path by calling irqentry_exit_code_resched().

Co-developed-by: Peter Zijlstra <peterz@infradead.org>
Signed-off-by: Ankur Arora <ankur.a.arora@oracle.com>
---
 include/linux/entry-common.h | 13 +++++++++++++
 kernel/entry/common.c        | 13 ++++++++++++-
 kernel/sched/core.c          | 32 +++++++++++++++++---------------
 3 files changed, 42 insertions(+), 16 deletions(-)

diff --git a/include/linux/entry-common.h b/include/linux/entry-common.h
index d95ab85f96ba..3716c223a703 100644
--- a/include/linux/entry-common.h
+++ b/include/linux/entry-common.h
@@ -415,10 +415,23 @@ irqentry_state_t noinstr irqentry_enter(struct pt_regs *regs);
  * Conditional reschedule with additional sanity checks.
  */
 void raw_irqentry_exit_cond_resched(void);
+
+/**
+ * irqentry_exit_allow_resched - Conditionally reschedule on return from interrupt
+ * for tasks that are explicitly marked TIF_ALLOW_RESCHED.
+ *
+ * Enabled for both preempt_model_none() and preempt_model_voluntary().
+ */
+void irqentry_exit_allow_resched(void);
+
 #ifdef CONFIG_PREEMPT_DYNAMIC
 #if defined(CONFIG_HAVE_PREEMPT_DYNAMIC_CALL)
 #define irqentry_exit_cond_resched_dynamic_enabled	raw_irqentry_exit_cond_resched
+#ifdef TIF_RESCHED_ALLOW
+#define irqentry_exit_cond_resched_dynamic_disabled	irqentry_exit_allow_resched
+#else
 #define irqentry_exit_cond_resched_dynamic_disabled	NULL
+#endif
 DECLARE_STATIC_CALL(irqentry_exit_cond_resched, raw_irqentry_exit_cond_resched);
 #define irqentry_exit_cond_resched()	static_call(irqentry_exit_cond_resched)()
 #elif defined(CONFIG_HAVE_PREEMPT_DYNAMIC_KEY)
diff --git a/kernel/entry/common.c b/kernel/entry/common.c
index d7ee4bc3f2ba..b4cee897d6f6 100644
--- a/kernel/entry/common.c
+++ b/kernel/entry/common.c
@@ -389,6 +389,13 @@ void raw_irqentry_exit_cond_resched(void)
 			preempt_schedule_irq();
 	}
 }
+
+void irqentry_exit_allow_resched(void)
+{
+	if (resched_allowed())
+		raw_irqentry_exit_cond_resched();
+}
+
 #ifdef CONFIG_PREEMPT_DYNAMIC
 #if defined(CONFIG_HAVE_PREEMPT_DYNAMIC_CALL)
 DEFINE_STATIC_CALL(irqentry_exit_cond_resched, raw_irqentry_exit_cond_resched);
@@ -396,8 +403,10 @@ DEFINE_STATIC_CALL(irqentry_exit_cond_resched, raw_irqentry_exit_cond_resched);
 DEFINE_STATIC_KEY_TRUE(sk_dynamic_irqentry_exit_cond_resched);
 void dynamic_irqentry_exit_cond_resched(void)
 {
-	if (!static_branch_unlikely(&sk_dynamic_irqentry_exit_cond_resched))
+	if (!static_branch_unlikely(&sk_dynamic_irqentry_exit_cond_resched)) {
+		irqentry_exit_allow_resched();
 		return;
+	}
 	raw_irqentry_exit_cond_resched();
 }
 #endif
@@ -430,6 +439,8 @@ noinstr void irqentry_exit(struct pt_regs *regs, irqentry_state_t state)
 		instrumentation_begin();
 		if (IS_ENABLED(CONFIG_PREEMPTION))
 			irqentry_exit_cond_resched();
+		else
+			irqentry_exit_allow_resched();
 
 		/* Covers both tracing and lockdep */
 		trace_hardirqs_on();
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 2299a5cfbfb9..3c1b1b0cd575 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -6570,6 +6570,8 @@ pick_next_task(struct rq *rq, struct task_struct *prev, struct rq_flags *rf)
  *          - explicit schedule() call
  *          - return from syscall or exception to user-space
  *          - return from interrupt-handler to user-space
+ *          - return from interrupt-handler for a task marked
+ *            with allow_resched()
  *
  * WARNING: must be called with preemption disabled!
  */
@@ -8692,25 +8694,25 @@ EXPORT_SYMBOL(__cond_resched_rwlock_write);
  *
  *
  * NONE:
- *   cond_resched               <- __cond_resched
- *   might_resched              <- RET0
- *   preempt_schedule           <- NOP
- *   preempt_schedule_notrace   <- NOP
- *   irqentry_exit_cond_resched <- NOP
+ *   cond_resched                <- __cond_resched
+ *   might_resched               <- RET0
+ *   preempt_schedule            <- NOP
+ *   preempt_schedule_notrace    <- NOP
+ *   irqentry_exit_cond_resched  <- irqentry_exit_allow_resched
  *
  * VOLUNTARY:
- *   cond_resched               <- __cond_resched
- *   might_resched              <- __cond_resched
- *   preempt_schedule           <- NOP
- *   preempt_schedule_notrace   <- NOP
- *   irqentry_exit_cond_resched <- NOP
+ *   cond_resched                <- __cond_resched
+ *   might_resched               <- __cond_resched
+ *   preempt_schedule            <- NOP
+ *   preempt_schedule_notrace    <- NOP
+ *   irqentry_exit_cond_resched  <- irqentry_exit_allow_resched
  *
  * FULL:
- *   cond_resched               <- RET0
- *   might_resched              <- RET0
- *   preempt_schedule           <- preempt_schedule
- *   preempt_schedule_notrace   <- preempt_schedule_notrace
- *   irqentry_exit_cond_resched <- irqentry_exit_cond_resched
+ *   cond_resched                <- RET0
+ *   might_resched               <- RET0
+ *   preempt_schedule            <- preempt_schedule
+ *   preempt_schedule_notrace    <- preempt_schedule_notrace
+ *   irqentry_exit_cond_resched  <- irqentry_exit_cond_resched
  */
 
 enum {
-- 
2.31.1

