@@ -710,7 +710,7 @@ static inline bool vma_start_read(struct vm_area_struct *vma)
* we don't rely on for anything - the mm_lock_seq read against which we
* need ordering is below.
*/
- if (READ_ONCE(vma->vm_lock_seq) == READ_ONCE(vma->vm_mm->mm_lock_seq))
+ if (READ_ONCE(vma->vm_lock_seq) == READ_ONCE(vma->vm_mm->mm_lock_seq.sequence))
return false;
if (unlikely(down_read_trylock(&vma->vm_lock->lock) == 0))
@@ -727,7 +727,7 @@ static inline bool vma_start_read(struct vm_area_struct *vma)
* after it has been unlocked.
* This pairs with RELEASE semantics in vma_end_write_all().
*/
- if (unlikely(vma->vm_lock_seq == smp_load_acquire(&vma->vm_mm->mm_lock_seq))) {
+ if (unlikely(vma->vm_lock_seq == raw_read_seqcount(&vma->vm_mm->mm_lock_seq))) {
up_read(&vma->vm_lock->lock);
return false;
}
@@ -742,7 +742,7 @@ static inline void vma_end_read(struct vm_area_struct *vma)
}
/* WARNING! Can only be used if mmap_lock is expected to be write-locked */
-static bool __is_vma_write_locked(struct vm_area_struct *vma, int *mm_lock_seq)
+static bool __is_vma_write_locked(struct vm_area_struct *vma, unsigned int *mm_lock_seq)
{
mmap_assert_write_locked(vma->vm_mm);
@@ -750,7 +750,7 @@ static bool __is_vma_write_locked(struct vm_area_struct *vma, int *mm_lock_seq)
* current task is holding mmap_write_lock, both vma->vm_lock_seq and
* mm->mm_lock_seq can't be concurrently modified.
*/
- *mm_lock_seq = vma->vm_mm->mm_lock_seq;
+ *mm_lock_seq = vma->vm_mm->mm_lock_seq.sequence;
return (vma->vm_lock_seq == *mm_lock_seq);
}
@@ -761,7 +761,7 @@ static bool __is_vma_write_locked(struct vm_area_struct *vma, int *mm_lock_seq)
*/
static inline void vma_start_write(struct vm_area_struct *vma)
{
- int mm_lock_seq;
+ unsigned int mm_lock_seq;
if (__is_vma_write_locked(vma, &mm_lock_seq))
return;
@@ -779,7 +779,7 @@ static inline void vma_start_write(struct vm_area_struct *vma)
static inline void vma_assert_write_locked(struct vm_area_struct *vma)
{
- int mm_lock_seq;
+ unsigned int mm_lock_seq;
VM_BUG_ON_VMA(!__is_vma_write_locked(vma, &mm_lock_seq), vma);
}
@@ -715,7 +715,7 @@ struct vm_area_struct {
* counter reuse can only lead to occasional unnecessary use of the
* slowpath.
*/
- int vm_lock_seq;
+ unsigned int vm_lock_seq;
/* Unstable RCU readers are allowed to read this. */
struct vma_lock *vm_lock;
#endif
@@ -909,6 +909,9 @@ 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.
@@ -917,7 +920,7 @@ struct mm_struct {
* Can be read with ACQUIRE semantics if not holding write
* mmap_lock.
*/
- int mm_lock_seq;
+ seqcount_t mm_lock_seq;
#endif
@@ -71,39 +71,38 @@ 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 mm_lock_seqcount_init(struct mm_struct *mm)
{
- 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);
+ seqcount_init(&mm->mm_lock_seq);
+}
+
+static inline void mm_lock_seqcount_begin(struct mm_struct *mm)
+{
+ do_raw_write_seqcount_begin(&mm->mm_lock_seq);
+}
+
+static inline void mm_lock_seqcount_end(struct mm_struct *mm)
+{
+ do_raw_write_seqcount_end(&mm->mm_lock_seq);
}
+
#else
-static inline void vma_end_write_all(struct mm_struct *mm) {}
+static inline void mm_lock_seqcount_init(struct mm_struct *mm) {}
+static inline void mm_lock_seqcount_begin(struct mm_struct *mm) {}
+static inline void mm_lock_seqcount_end(struct mm_struct *mm) {}
#endif
static inline void mmap_init_lock(struct mm_struct *mm)
{
init_rwsem(&mm->mmap_lock);
+ mm_lock_seqcount_init(mm);
}
static inline void mmap_write_lock(struct mm_struct *mm)
{
__mmap_lock_trace_start_locking(mm, true);
down_write(&mm->mmap_lock);
+ mm_lock_seqcount_begin(mm);
__mmap_lock_trace_acquire_returned(mm, true, true);
}
@@ -111,6 +110,7 @@ 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);
+ mm_lock_seqcount_begin(mm);
__mmap_lock_trace_acquire_returned(mm, true, true);
}
@@ -120,10 +120,27 @@ 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)
+ mm_lock_seqcount_begin(mm);
__mmap_lock_trace_acquire_returned(mm, true, ret == 0);
return ret;
}
+/*
+ * 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)
+{
+ mmap_assert_write_locked(mm);
+ ASSERT_EXCLUSIVE_WRITER(mm->mm_lock_seq);
+ mm_lock_seqcount_end(mm);
+}
+
static inline void mmap_write_unlock(struct mm_struct *mm)
{
__mmap_lock_trace_released(mm, true);
@@ -449,7 +449,7 @@ static bool vma_lock_alloc(struct vm_area_struct *vma)
return false;
init_rwsem(&vma->vm_lock->lock);
- vma->vm_lock_seq = -1;
+ vma->vm_lock_seq = UINT_MAX;
return true;
}
@@ -1262,9 +1262,6 @@ 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;
@@ -40,7 +40,7 @@ struct mm_struct init_mm = {
.arg_lock = __SPIN_LOCK_UNLOCKED(init_mm.arg_lock),
.mmlist = LIST_HEAD_INIT(init_mm.mmlist),
#ifdef CONFIG_PER_VMA_LOCK
- .mm_lock_seq = 0,
+ .mm_lock_seq = SEQCNT_ZERO(init_mm.mm_lock_seq),
#endif
.user_ns = &init_user_ns,
.cpu_bitmap = CPU_BITS_NONE,
@@ -87,7 +87,7 @@ static struct vm_area_struct *alloc_and_link_vma(struct mm_struct *mm,
* begun. Linking to the tree will have caused this to be incremented,
* which means we will get a false positive otherwise.
*/
- vma->vm_lock_seq = -1;
+ vma->vm_lock_seq = UINT_MAX;
return vma;
}
@@ -212,7 +212,7 @@ static bool vma_write_started(struct vm_area_struct *vma)
int seq = vma->vm_lock_seq;
/* We reset after each check. */
- vma->vm_lock_seq = -1;
+ vma->vm_lock_seq = UINT_MAX;
/* The vma_start_write() stub simply increments this value. */
return seq > -1;
@@ -231,7 +231,7 @@ struct vm_area_struct {
* counter reuse can only lead to occasional unnecessary use of the
* slowpath.
*/
- int vm_lock_seq;
+ unsigned int vm_lock_seq;
struct vma_lock *vm_lock;
#endif
@@ -406,7 +406,7 @@ static inline bool vma_lock_alloc(struct vm_area_struct *vma)
return false;
init_rwsem(&vma->vm_lock->lock);
- vma->vm_lock_seq = -1;
+ vma->vm_lock_seq = UINT_MAX;
return true;
}
Convert mm_lock_seq to be seqcount_t and change all mmap_write_lock variants to increment it, in-line with the usual seqcount usage pattern. This lets us check whether the mmap_lock is write-locked by checking mm_lock_seq.sequence counter (odd=locked, even=unlocked). This will be used when implementing mmap_lock speculation functions. As a result vm_lock_seq is also change to be unsigned to match the type of mm_lock_seq.sequence. Suggested-by: Peter Zijlstra <peterz@infradead.org> Signed-off-by: Suren Baghdasaryan <surenb@google.com> --- Changes since v1 [1] - Added ASSERT_EXCLUSIVE_WRITER() instead of a comment in vma_end_write_all, per Peter Zijlstra [1] https://lore.kernel.org/all/20241024205231.1944747-1-surenb@google.com/ include/linux/mm.h | 12 +++---- include/linux/mm_types.h | 7 ++-- include/linux/mmap_lock.h | 55 +++++++++++++++++++++----------- kernel/fork.c | 5 +-- mm/init-mm.c | 2 +- tools/testing/vma/vma.c | 4 +-- tools/testing/vma/vma_internal.h | 4 +-- 7 files changed, 53 insertions(+), 36 deletions(-)