79 lines
2.7 KiB
Diff
79 lines
2.7 KiB
Diff
|
From 39f2bfe0177d3f56c9feac4e70424e4952949e2a Mon Sep 17 00:00:00 2001
|
||
|
|
From: Sean Christopherson <seanjc@google.com>
|
||
|
|
Date: Wed, 10 Jan 2024 13:47:23 -0800
|
||
|
|
Subject: [PATCH] sched/core: Drop spinlocks on contention iff kernel is
|
||
|
|
preemptible
|
||
|
|
|
||
|
|
Use preempt_model_preemptible() to detect a preemptible kernel when
|
||
|
|
deciding whether or not to reschedule in order to drop a contended
|
||
|
|
spinlock or rwlock. Because PREEMPT_DYNAMIC selects PREEMPTION, kernels
|
||
|
|
built with PREEMPT_DYNAMIC=y will yield contended locks even if the live
|
||
|
|
preemption model is "none" or "voluntary". In short, make kernels with
|
||
|
|
dynamically selected models behave the same as kernels with statically
|
||
|
|
selected models.
|
||
|
|
|
||
|
|
Somewhat counter-intuitively, NOT yielding a lock can provide better
|
||
|
|
latency for the relevant tasks/processes. E.g. KVM x86's mmu_lock, a
|
||
|
|
rwlock, is often contended between an invalidation event (takes mmu_lock
|
||
|
|
for write) and a vCPU servicing a guest page fault (takes mmu_lock for
|
||
|
|
read). For _some_ setups, letting the invalidation task complete even
|
||
|
|
if there is mmu_lock contention provides lower latency for *all* tasks,
|
||
|
|
i.e. the invalidation completes sooner *and* the vCPU services the guest
|
||
|
|
page fault sooner.
|
||
|
|
|
||
|
|
But even KVM's mmu_lock behavior isn't uniform, e.g. the "best" behavior
|
||
|
|
can vary depending on the host VMM, the guest workload, the number of
|
||
|
|
vCPUs, the number of pCPUs in the host, why there is lock contention, etc.
|
||
|
|
|
||
|
|
In other words, simply deleting the CONFIG_PREEMPTION guard (or doing the
|
||
|
|
opposite and removing contention yielding entirely) needs to come with a
|
||
|
|
big pile of data proving that changing the status quo is a net positive.
|
||
|
|
|
||
|
|
Cc: Valentin Schneider <valentin.schneider@arm.com>
|
||
|
|
Cc: Peter Zijlstra (Intel) <peterz@infradead.org>
|
||
|
|
Cc: Marco Elver <elver@google.com>
|
||
|
|
Cc: Frederic Weisbecker <frederic@kernel.org>
|
||
|
|
Cc: David Matlack <dmatlack@google.com>
|
||
|
|
Signed-off-by: Sean Christopherson <seanjc@google.com>
|
||
|
|
---
|
||
|
|
include/linux/sched.h | 14 ++++++--------
|
||
|
|
1 file changed, 6 insertions(+), 8 deletions(-)
|
||
|
|
|
||
|
|
diff --git a/include/linux/sched.h b/include/linux/sched.h
|
||
|
|
index 292c31697248..a274bc85f222 100644
|
||
|
|
--- a/include/linux/sched.h
|
||
|
|
+++ b/include/linux/sched.h
|
||
|
|
@@ -2234,11 +2234,10 @@ static inline bool preempt_model_preemptible(void)
|
||
|
|
*/
|
||
|
|
static inline int spin_needbreak(spinlock_t *lock)
|
||
|
|
{
|
||
|
|
-#ifdef CONFIG_PREEMPTION
|
||
|
|
+ if (!preempt_model_preemptible())
|
||
|
|
+ return 0;
|
||
|
|
+
|
||
|
|
return spin_is_contended(lock);
|
||
|
|
-#else
|
||
|
|
- return 0;
|
||
|
|
-#endif
|
||
|
|
}
|
||
|
|
|
||
|
|
/*
|
||
|
|
@@ -2251,11 +2250,10 @@ static inline int spin_needbreak(spinlock_t *lock)
|
||
|
|
*/
|
||
|
|
static inline int rwlock_needbreak(rwlock_t *lock)
|
||
|
|
{
|
||
|
|
-#ifdef CONFIG_PREEMPTION
|
||
|
|
+ if (!preempt_model_preemptible())
|
||
|
|
+ return 0;
|
||
|
|
+
|
||
|
|
return rwlock_is_contended(lock);
|
||
|
|
-#else
|
||
|
|
- return 0;
|
||
|
|
-#endif
|
||
|
|
}
|
||
|
|
|
||
|
|
static __always_inline bool need_resched(void)
|
||
|
|
--
|
||
|
|
2.39.2
|
||
|
|
|