mm: add per-VMA lock and helper functions to control it

Introduce per-VMA locking.  The lock implementation relies on a per-vma
and per-mm sequence counters to note exclusive locking:

  - read lock - (implemented by vma_start_read) requires the vma
    (vm_lock_seq) and mm (mm_lock_seq) sequence counters to differ.
    If they match then there must be a vma exclusive lock held somewhere.
  - read unlock - (implemented by vma_end_read) is a trivial vma->lock
    unlock.
  - write lock - (vma_start_write) requires the mmap_lock to be held
    exclusively and the current mm counter is assigned to the vma counter.
    This will allow multiple vmas to be locked under a single mmap_lock
    write lock (e.g. during vma merging). The vma counter is modified
    under exclusive vma lock.
  - write unlock - (vma_end_write_all) is a batch release of all vma
    locks held. It doesn't pair with a specific vma_start_write! It is
    done before exclusive mmap_lock is released by incrementing mm
    sequence counter (mm_lock_seq).
  - write downgrade - if the mmap_lock is downgraded to the read lock, all
    vma write locks are released as well (effectivelly same as write
    unlock).

Link: https://lkml.kernel.org/r/20230227173632.3292573-13-surenb@google.com
Signed-off-by: Suren Baghdasaryan <surenb@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>

5 files changed, 110 insertions, 0 deletions

diff --git a/include/linux/mm.h b/include/linux/mm.h
index 55d02356146c..53bfb42663ea 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -624,6 +624,87 @@ struct vm_operations_struct {
 					  unsigned long addr);
 };
 
+#ifdef CONFIG_PER_VMA_LOCK
+static inline void vma_init_lock(struct vm_area_struct *vma)
+{
+	init_rwsem(&vma->lock);
+	vma->vm_lock_seq = -1;
+}
+
+/*
+ * Try to read-lock a vma. The function is allowed to occasionally yield false
+ * locked result to avoid performance overhead, in which case we fall back to
+ * using mmap_lock. The function should never yield false unlocked result.
+ */
+static inline bool vma_start_read(struct vm_area_struct *vma)
+{
+	/* Check before locking. A race might cause false locked result. */
+	if (vma->vm_lock_seq == READ_ONCE(vma->vm_mm->mm_lock_seq))
+		return false;
+
+	if (unlikely(down_read_trylock(&vma->lock) == 0))
+		return false;
+
+	/*
+	 * Overflow might produce false locked result.
+	 * False unlocked result is impossible because we modify and check
+	 * vma->vm_lock_seq under vma->lock protection and mm->mm_lock_seq
+	 * modification invalidates all existing locks.
+	 */
+	if (unlikely(vma->vm_lock_seq == READ_ONCE(vma->vm_mm->mm_lock_seq))) {
+		up_read(&vma->lock);
+		return false;
+	}
+	return true;
+}
+
+static inline void vma_end_read(struct vm_area_struct *vma)
+{
+	rcu_read_lock(); /* keeps vma alive till the end of up_read */
+	up_read(&vma->lock);
+	rcu_read_unlock();
+}
+
+static inline void vma_start_write(struct vm_area_struct *vma)
+{
+	int mm_lock_seq;
+
+	mmap_assert_write_locked(vma->vm_mm);
+
+	/*
+	 * 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 = READ_ONCE(vma->vm_mm->mm_lock_seq);
+	if (vma->vm_lock_seq == mm_lock_seq)
+		return;
+
+	down_write(&vma->lock);
+	vma->vm_lock_seq = mm_lock_seq;
+	up_write(&vma->lock);
+}
+
+static inline void vma_assert_write_locked(struct vm_area_struct *vma)
+{
+	mmap_assert_write_locked(vma->vm_mm);
+	/*
+	 * current task is holding mmap_write_lock, both vma->vm_lock_seq and
+	 * mm->mm_lock_seq can't be concurrently modified.
+	 */
+	VM_BUG_ON_VMA(vma->vm_lock_seq != READ_ONCE(vma->vm_mm->mm_lock_seq), vma);
+}
+
+#else /* CONFIG_PER_VMA_LOCK */
+
+static inline void vma_init_lock(struct vm_area_struct *vma) {}
+static inline bool vma_start_read(struct vm_area_struct *vma)
+		{ return false; }
+static inline void vma_end_read(struct vm_area_struct *vma) {}
+static inline void vma_start_write(struct vm_area_struct *vma) {}
+static inline void vma_assert_write_locked(struct vm_area_struct *vma) {}
+
+#endif /* CONFIG_PER_VMA_LOCK */
+
 static inline void vma_init(struct vm_area_struct *vma, struct mm_struct *mm)
 {
 	static const struct vm_operations_struct dummy_vm_ops = {};
@@ -632,6 +713,7 @@ static inline void vma_init(struct vm_area_struct *vma, struct mm_struct *mm)
 	vma->vm_mm = mm;
 	vma->vm_ops = &dummy_vm_ops;
 	INIT_LIST_HEAD(&vma->anon_vma_chain);
+	vma_init_lock(vma);
 }
 
 /* Use when VMA is not part of the VMA tree and needs no locking */
diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h
index f203e2562e00..843a45893991 100644
--- a/include/linux/mm_types.h
+++ b/include/linux/mm_types.h
@@ -503,6 +503,11 @@ struct vm_area_struct {
 		vm_flags_t __private __vm_flags;
 	};
 
+#ifdef CONFIG_PER_VMA_LOCK
+	int vm_lock_seq;
+	struct rw_semaphore lock;
+#endif
+
 	/*
 	 * For areas with an address space and backing store,
 	 * linkage into the address_space->i_mmap interval tree.
@@ -639,6 +644,9 @@ struct mm_struct {
 					  * init_mm.mmlist, and are protected
 					  * by mmlist_lock
 					  */
+#ifdef CONFIG_PER_VMA_LOCK
+		int mm_lock_seq;
+#endif
 
 
 		unsigned long hiwater_rss; /* High-watermark of RSS usage */
diff --git a/include/linux/mmap_lock.h b/include/linux/mmap_lock.h
index e49ba91bb1f0..aab8f1b28d26 100644
--- a/include/linux/mmap_lock.h
+++ b/include/linux/mmap_lock.h
@@ -72,6 +72,17 @@ static inline void mmap_assert_write_locked(struct mm_struct *mm)
 	VM_BUG_ON_MM(!rwsem_is_locked(&mm->mmap_lock), mm);
 }
 
+#ifdef CONFIG_PER_VMA_LOCK
+static inline void vma_end_write_all(struct mm_struct *mm)
+{
+	mmap_assert_write_locked(mm);
+	/* No races during update due to exclusive mmap_lock being held */
+	WRITE_ONCE(mm->mm_lock_seq, mm->mm_lock_seq + 1);
+}
+#else
+static inline void vma_end_write_all(struct mm_struct *mm) {}
+#endif
+
 static inline void mmap_init_lock(struct mm_struct *mm)
 {
 	init_rwsem(&mm->mmap_lock);
@@ -114,12 +125,14 @@ static inline bool mmap_write_trylock(struct mm_struct *mm)
 static inline void mmap_write_unlock(struct mm_struct *mm)
 {
 	__mmap_lock_trace_released(mm, true);
+	vma_end_write_all(mm);
 	up_write(&mm->mmap_lock);
 }
 
 static inline void mmap_write_downgrade(struct mm_struct *mm)
 {
 	__mmap_lock_trace_acquire_returned(mm, false, true);
+	vma_end_write_all(mm);
 	downgrade_write(&mm->mmap_lock);
 }
 
diff --git a/kernel/fork.c b/kernel/fork.c
index 93ec6e14bb65..0907776d8ed4 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -474,6 +474,7 @@ struct vm_area_struct *vm_area_dup(struct vm_area_struct *orig)
 		 */
 		data_race(memcpy(new, orig, sizeof(*new)));
 		INIT_LIST_HEAD(&new->anon_vma_chain);
+		vma_init_lock(new);
 		dup_anon_vma_name(orig, new);
 	}
 	return new;
@@ -1208,6 +1209,9 @@ 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;
diff --git a/mm/init-mm.c b/mm/init-mm.c
index c9327abb771c..33269314e060 100644
--- a/mm/init-mm.c
+++ b/mm/init-mm.c
@@ -37,6 +37,9 @@ struct mm_struct init_mm = {
 	.page_table_lock =  __SPIN_LOCK_UNLOCKED(init_mm.page_table_lock),
 	.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,
+#endif
 	.user_ns	= &init_user_ns,
 	.cpu_bitmap	= CPU_BITS_NONE,
 #ifdef CONFIG_IOMMU_SVA