Message-ID: <20240906051205.530219-2-andrii@kernel.org>
Date: Thu,  5 Sep 2024 22:12:04 -0700
From: Andrii Nakryiko <andrii@...nel.org>
To: linux-trace-kernel@...r.kernel.org,
	peterz@...radead.org,
	oleg@...hat.com
Cc: rostedt@...dmis.org,
	mhiramat@...nel.org,
	bpf@...r.kernel.org,
	linux-kernel@...r.kernel.org,
	jolsa@...nel.org,
	paulmck@...nel.org,
	willy@...radead.org,
	surenb@...gle.com,
	akpm@...ux-foundation.org,
	linux-mm@...ck.org,
	mjguzik@...il.com,
	brauner@...nel.org,
	jannh@...gle.com,
	Andrii Nakryiko <andrii@...nel.org>
Subject: [PATCH 1/2] mm: introduce mmap_lock_speculation_{start|end}

From: Suren Baghdasaryan <surenb@...gle.com>

Add helper functions to speculatively perform operations without
read-locking mmap_lock, expecting that mmap_lock will not be
write-locked and mm is not modified from under us.

A few will-it-scale ([0]) bechmarks were run with and without the
changes in this patch on a beefy server. The test script below was used.
Most of background activity on the server was stopped, but there could
still be some sporadic sources of noise. And frankly, will-it-scale
benchmarks themselves aren't 100% noise-free and do fluctuate somewhat.
Also malloc1 benchmark was getting stuck for some reason, so it was
skipped from benchmarks. But I think it was still useful as a bit of
sanity check, but take all of them with a grain of salt.

Benchmark script:

  # cat will_it_scale.sh
  #!/bin/bash

  set -eufo pipefail

  for b in page_fault1 page_fault2 page_fault3 malloc2; do
          for p in 40; do
                  echo BENCH $b CPU$p $(will-it-scale/${b}_threads -m -t$p -s60 | grep average)
          done;
  done;

Before (w/o this patch)
=======================
BENCH page_fault1 CPU40 average:5403940
BENCH page_fault2 CPU40 average:5019159
BENCH page_fault3 CPU40 average:971057
BENCH malloc2 CPU40 average:1364730680

After (w/ this patch)
=====================
BENCH page_fault1 CPU40 average:5485892
BENCH page_fault2 CPU40 average:5047923
BENCH page_fault3 CPU40 average:982953
BENCH malloc2 CPU40 average:1361339890

Results seem to be within the noise of measurements, but perhaps mm
folks might have better benchmarks to try.

  [0] https://github.com/antonblanchard/will-it-scale

Suggested-by: Peter Zijlstra <peterz@...radead.org>
Signed-off-by: Suren Baghdasaryan <surenb@...gle.com>
Signed-off-by: Andrii Nakryiko <andrii@...nel.org>
---
 include/linux/mm_types.h  |  3 +++
 include/linux/mmap_lock.h | 53 +++++++++++++++++++++++++++++++--------
 kernel/fork.c             |  3 ---
 3 files changed, 46 insertions(+), 13 deletions(-)

diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h
index 485424979254..d5e3f907eea4 100644
--- a/include/linux/mm_types.h
+++ b/include/linux/mm_types.h
@@ -876,6 +876,9 @@ struct mm_struct {
 		 * Roughly speaking, incrementing the sequence number is
 		 * equivalent to releasing locks on VMAs; reading the sequence
 		 * number can be part of taking a read lock on a VMA.
+		 * Incremented every time mmap_lock is write-locked/unlocked.
+		 * Initialized to 0, therefore odd values indicate mmap_lock
+		 * is write-locked and even values that it's released.
 		 *
 		 * Can be modified under write mmap_lock using RELEASE
 		 * semantics.
diff --git a/include/linux/mmap_lock.h b/include/linux/mmap_lock.h
index de9dc20b01ba..5410ce741d75 100644
--- a/include/linux/mmap_lock.h
+++ b/include/linux/mmap_lock.h
@@ -71,15 +71,12 @@ static inline void mmap_assert_write_locked(const struct mm_struct *mm)
 }
 
 #ifdef CONFIG_PER_VMA_LOCK
-/*
- * Drop all currently-held per-VMA locks.
- * This is called from the mmap_lock implementation directly before releasing
- * a write-locked mmap_lock (or downgrading it to read-locked).
- * This should normally NOT be called manually from other places.
- * If you want to call this manually anyway, keep in mind that this will release
- * *all* VMA write locks, including ones from further up the stack.
- */
-static inline void vma_end_write_all(struct mm_struct *mm)
+static inline void init_mm_lock_seq(struct mm_struct *mm)
+{
+	mm->mm_lock_seq = 0;
+}
+
+static inline void inc_mm_lock_seq(struct mm_struct *mm)
 {
 	mmap_assert_write_locked(mm);
 	/*
@@ -91,19 +88,52 @@ static inline void vma_end_write_all(struct mm_struct *mm)
 	 */
 	smp_store_release(&mm->mm_lock_seq, mm->mm_lock_seq + 1);
 }
+
+static inline bool mmap_lock_speculation_start(struct mm_struct *mm, int *seq)
+{
+	/* Pairs with RELEASE semantics in inc_mm_lock_seq(). */
+	*seq = smp_load_acquire(&mm->mm_lock_seq);
+	/* Allow speculation if mmap_lock is not write-locked */
+	return (*seq & 1) == 0;
+}
+
+static inline bool mmap_lock_speculation_end(struct mm_struct *mm, int seq)
+{
+	/* Pairs with RELEASE semantics in inc_mm_lock_seq(). */
+	return seq == smp_load_acquire(&mm->mm_lock_seq);
+}
+
 #else
-static inline void vma_end_write_all(struct mm_struct *mm) {}
+static inline void init_mm_lock_seq(struct mm_struct *mm) {}
+static inline void inc_mm_lock_seq(struct mm_struct *mm) {}
+static inline bool mmap_lock_speculation_start(struct mm_struct *mm, int *seq) { return false; }
+static inline bool mmap_lock_speculation_end(struct mm_struct *mm, int seq) { return false; }
 #endif
 
+/*
+ * Drop all currently-held per-VMA locks.
+ * This is called from the mmap_lock implementation directly before releasing
+ * a write-locked mmap_lock (or downgrading it to read-locked).
+ * This should normally NOT be called manually from other places.
+ * If you want to call this manually anyway, keep in mind that this will release
+ * *all* VMA write locks, including ones from further up the stack.
+ */
+static inline void vma_end_write_all(struct mm_struct *mm)
+{
+	inc_mm_lock_seq(mm);
+}
+
 static inline void mmap_init_lock(struct mm_struct *mm)
 {
 	init_rwsem(&mm->mmap_lock);
+	init_mm_lock_seq(mm);
 }
 
 static inline void mmap_write_lock(struct mm_struct *mm)
 {
 	__mmap_lock_trace_start_locking(mm, true);
 	down_write(&mm->mmap_lock);
+	inc_mm_lock_seq(mm);
 	__mmap_lock_trace_acquire_returned(mm, true, true);
 }
 
@@ -111,6 +141,7 @@ static inline void mmap_write_lock_nested(struct mm_struct *mm, int subclass)
 {
 	__mmap_lock_trace_start_locking(mm, true);
 	down_write_nested(&mm->mmap_lock, subclass);
+	inc_mm_lock_seq(mm);
 	__mmap_lock_trace_acquire_returned(mm, true, true);
 }
 
@@ -120,6 +151,8 @@ static inline int mmap_write_lock_killable(struct mm_struct *mm)
 
 	__mmap_lock_trace_start_locking(mm, true);
 	ret = down_write_killable(&mm->mmap_lock);
+	if (!ret)
+		inc_mm_lock_seq(mm);
 	__mmap_lock_trace_acquire_returned(mm, true, ret == 0);
 	return ret;
 }
diff --git a/kernel/fork.c b/kernel/fork.c
index 18bdc87209d0..c44b71d354ee 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -1259,9 +1259,6 @@ static struct mm_struct *mm_init(struct mm_struct *mm, struct task_struct *p,
 	seqcount_init(&mm->write_protect_seq);
 	mmap_init_lock(mm);
 	INIT_LIST_HEAD(&mm->mmlist);
-#ifdef CONFIG_PER_VMA_LOCK
-	mm->mm_lock_seq = 0;
-#endif
 	mm_pgtables_bytes_init(mm);
 	mm->map_count = 0;
 	mm->locked_vm = 0;
-- 
2.43.5

Powered by blists - more mailing lists