[PATCH v2 1/1] mm: introduce mmap_lock_speculation_{start|end}

From: Suren Baghdasaryan
Date: Thu Sep 12 2024 - 17:02:45 EST


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.

Suggested-by: Peter Zijlstra <peterz@xxxxxxxxxxxxx>
Signed-off-by: Suren Baghdasaryan <surenb@xxxxxxxxxx>
Signed-off-by: Andrii Nakryiko <andrii@xxxxxxxxxx>
---
Changes since v1 [1]:
- Made memory barriers in inc_mm_lock_seq and mmap_lock_speculation_end
more strict, per Jann Horn

[1] https://lore.kernel.org/all/20240906051205.530219-2-andrii@xxxxxxxxxx/

include/linux/mm_types.h | 3 ++
include/linux/mmap_lock.h | 74 ++++++++++++++++++++++++++++++++-------
kernel/fork.c | 3 --
3 files changed, 65 insertions(+), 15 deletions(-)

diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h
index 6e3bdf8e38bc..5d8cdebd42bc 100644
--- a/include/linux/mm_types.h
+++ b/include/linux/mm_types.h
@@ -887,6 +887,9 @@ 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..a281519d0c12 100644
--- a/include/linux/mmap_lock.h
+++ b/include/linux/mmap_lock.h
@@ -71,39 +71,86 @@ static inline void mmap_assert_write_locked(const struct mm_struct *mm)
}

#ifdef CONFIG_PER_VMA_LOCK
+static inline void init_mm_lock_seq(struct mm_struct *mm)
+{
+ mm->mm_lock_seq = 0;
+}
+
/*
- * 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.
+ * Increment mm->mm_lock_seq when mmap_lock is write-locked (ACQUIRE semantics)
+ * or write-unlocked (RELEASE semantics).
*/
-static inline void vma_end_write_all(struct mm_struct *mm)
+static inline void inc_mm_lock_seq(struct mm_struct *mm, bool acquire)
{
mmap_assert_write_locked(mm);
/*
* Nobody can concurrently modify mm->mm_lock_seq due to exclusive
* mmap_lock being held.
- * We need RELEASE semantics here to ensure that preceding stores into
- * the VMA take effect before we unlock it with this store.
- * Pairs with ACQUIRE semantics in vma_start_read().
*/
- smp_store_release(&mm->mm_lock_seq, mm->mm_lock_seq + 1);
+
+ if (acquire) {
+ WRITE_ONCE(mm->mm_lock_seq, mm->mm_lock_seq + 1);
+ /*
+ * For ACQUIRE semantics we should ensure no following stores are
+ * reordered to appear before the mm->mm_lock_seq modification.
+ */
+ smp_wmb();
+ } else {
+ /*
+ * We need RELEASE semantics here to ensure that preceding stores
+ * into the VMA take effect before we unlock it with this store.
+ * Pairs with ACQUIRE semantics in vma_start_read().
+ */
+ 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 ACQUIRE semantics in inc_mm_lock_seq(). */
+ smp_rmb();
+ return seq == READ_ONCE(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, bool acquire) {}
+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, false);
+}
+
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, true);
__mmap_lock_trace_acquire_returned(mm, true, true);
}

@@ -111,6 +158,7 @@ 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, true);
__mmap_lock_trace_acquire_returned(mm, true, true);
}

@@ -120,6 +168,8 @@ 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, true);
__mmap_lock_trace_acquire_returned(mm, true, ret == 0);
return ret;
}
diff --git a/kernel/fork.c b/kernel/fork.c
index 61070248a7d3..c86e87ed172b 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;

base-commit: 015bdfcb183759674ba1bd732c3393014e35708b
--
2.46.0.662.g92d0881bb0-goog