fs/proc/task_mmu: read proc/pid/maps under per-vma lock

With maple_tree supporting vma tree traversal under RCU and per-vma locks,
/proc/pid/maps can be read while holding individual vma locks instead of
locking the entire address space.

A completely lockless approach (walking vma tree under RCU) would be quite
complex with the main issue being get_vma_name() using callbacks which
might not work correctly with a stable vma copy, requiring original
(unstable) vma - see special_mapping_name() for example.

When per-vma lock acquisition fails, we take the mmap_lock for reading,
lock the vma, release the mmap_lock and continue.  This fallback to mmap
read lock guarantees the reader to make forward progress even during lock
contention.  This will interfere with the writer but for a very short time
while we are acquiring the per-vma lock and only when there was contention
on the vma reader is interested in.

We shouldn't see a repeated fallback to mmap read locks in practice, as
this require a very unlikely series of lock contentions (for instance due
to repeated vma split operations).  However even if this did somehow
happen, we would still progress.

One case requiring special handling is when a vma changes between the time
it was found and the time it got locked.  A problematic case would be if a
vma got shrunk so that its vm_start moved higher in the address space and
a new vma was installed at the beginning:

reader found:               |--------VMA A--------|
VMA is modified:            |-VMA B-|----VMA A----|
reader locks modified VMA A
reader reports VMA A:       |  gap  |----VMA A----|

This would result in reporting a gap in the address space that does not
exist.  To prevent this we retry the lookup after locking the vma, however
we do that only when we identify a gap and detect that the address space
was changed after we found the vma.

This change is designed to reduce mmap_lock contention and prevent a
process reading /proc/pid/maps files (often a low priority task, such as
monitoring/data collection services) from blocking address space updates. 
Note that this change has a userspace visible disadvantage: it allows for
sub-page data tearing as opposed to the previous mechanism where data
tearing could happen only between pages of generated output data.  Since
current userspace considers data tearing between pages to be acceptable,
we assume is will be able to handle sub-page data tearing as well.

Link: https://lkml.kernel.org/r/20250719182854.3166724-7-surenb@google.com
Signed-off-by: Suren Baghdasaryan <surenb@google.com>
Reviewed-by: Vlastimil Babka <vbabka@suse.cz>
Cc: Alexey Dobriyan <adobriyan@gmail.com>
Cc: Andrii Nakryiko <andrii@kernel.org>
Cc: Christian Brauner <brauner@kernel.org>
Cc: Christophe Leroy <christophe.leroy@csgroup.eu>
Cc: David Hildenbrand <david@redhat.com>
Cc: Jann Horn <jannh@google.com>
Cc: Jeongjun Park <aha310510@gmail.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Josef Bacik <josef@toxicpanda.com>
Cc: Kalesh Singh <kaleshsingh@google.com>
Cc: Liam Howlett <liam.howlett@oracle.com>
Cc: Lorenzo Stoakes <lorenzo.stoakes@oracle.com>
Cc: Matthew Wilcox (Oracle) <willy@infradead.org>
Cc: Michal Hocko <mhocko@kernel.org>
Cc: Oscar Salvador <osalvador@suse.de>
Cc: "Paul E . McKenney" <paulmck@kernel.org>
Cc: Peter Xu <peterx@redhat.com>
Cc: Ryan Roberts <ryan.roberts@arm.com>
Cc: Shuah Khan <shuah@kernel.org>
Cc: Thomas Weißschuh <linux@weissschuh.net>
Cc: T.J. Mercier <tjmercier@google.com>
Cc: Ye Bin <yebin10@huawei.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>

1 files changed, 133 insertions, 8 deletions

diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c
index 90237df1ed33..3d6d8a9f13fc 100644
--- a/fs/proc/task_mmu.c
+++ b/fs/proc/task_mmu.c
@@ -130,13 +130,132 @@ static void release_task_mempolicy(struct proc_maps_private *priv)
 }
 #endif
 
-static struct vm_area_struct *proc_get_vma(struct proc_maps_private *priv,
-						loff_t *ppos)
+#ifdef CONFIG_PER_VMA_LOCK
+
+static void unlock_vma(struct proc_maps_private *priv)
+{
+	if (priv->locked_vma) {
+		vma_end_read(priv->locked_vma);
+		priv->locked_vma = NULL;
+	}
+}
+
+static const struct seq_operations proc_pid_maps_op;
+
+static inline bool lock_vma_range(struct seq_file *m,
+				  struct proc_maps_private *priv)
+{
+	/*
+	 * smaps and numa_maps perform page table walk, therefore require
+	 * mmap_lock but maps can be read with locking just the vma and
+	 * walking the vma tree under rcu read protection.
+	 */
+	if (m->op != &proc_pid_maps_op) {
+		if (mmap_read_lock_killable(priv->mm))
+			return false;
+
+		priv->mmap_locked = true;
+	} else {
+		rcu_read_lock();
+		priv->locked_vma = NULL;
+		priv->mmap_locked = false;
+	}
+
+	return true;
+}
+
+static inline void unlock_vma_range(struct proc_maps_private *priv)
+{
+	if (priv->mmap_locked) {
+		mmap_read_unlock(priv->mm);
+	} else {
+		unlock_vma(priv);
+		rcu_read_unlock();
+	}
+}
+
+static struct vm_area_struct *get_next_vma(struct proc_maps_private *priv,
+					   loff_t last_pos)
+{
+	struct vm_area_struct *vma;
+
+	if (priv->mmap_locked)
+		return vma_next(&priv->iter);
+
+	unlock_vma(priv);
+	vma = lock_next_vma(priv->mm, &priv->iter, last_pos);
+	if (!IS_ERR_OR_NULL(vma))
+		priv->locked_vma = vma;
+
+	return vma;
+}
+
+static inline bool fallback_to_mmap_lock(struct proc_maps_private *priv,
+					 loff_t pos)
 {
-	struct vm_area_struct *vma = vma_next(&priv->iter);
+	if (priv->mmap_locked)
+		return false;
+
+	rcu_read_unlock();
+	mmap_read_lock(priv->mm);
+	/* Reinitialize the iterator after taking mmap_lock */
+	vma_iter_set(&priv->iter, pos);
+	priv->mmap_locked = true;
 
+	return true;
+}
+
+#else /* CONFIG_PER_VMA_LOCK */
+
+static inline bool lock_vma_range(struct seq_file *m,
+				  struct proc_maps_private *priv)
+{
+	return mmap_read_lock_killable(priv->mm) == 0;
+}
+
+static inline void unlock_vma_range(struct proc_maps_private *priv)
+{
+	mmap_read_unlock(priv->mm);
+}
+
+static struct vm_area_struct *get_next_vma(struct proc_maps_private *priv,
+					   loff_t last_pos)
+{
+	return vma_next(&priv->iter);
+}
+
+static inline bool fallback_to_mmap_lock(struct proc_maps_private *priv,
+					 loff_t pos)
+{
+	return false;
+}
+
+#endif /* CONFIG_PER_VMA_LOCK */
+
+static struct vm_area_struct *proc_get_vma(struct seq_file *m, loff_t *ppos)
+{
+	struct proc_maps_private *priv = m->private;
+	struct vm_area_struct *vma;
+
+retry:
+	vma = get_next_vma(priv, *ppos);
+	/* EINTR of EAGAIN is possible */
+	if (IS_ERR(vma)) {
+		if (PTR_ERR(vma) == -EAGAIN && fallback_to_mmap_lock(priv, *ppos))
+			goto retry;
+
+		return vma;
+	}
+
+	/* Store previous position to be able to restart if needed */
+	priv->last_pos = *ppos;
 	if (vma) {
-		*ppos = vma->vm_start;
+		/*
+		 * Track the end of the reported vma to ensure position changes
+		 * even if previous vma was merged with the next vma and we
+		 * found the extended vma with the same vm_start.
+		 */
+		*ppos = vma->vm_end;
 	} else {
 		*ppos = SENTINEL_VMA_GATE;
 		vma = get_gate_vma(priv->mm);
@@ -166,19 +285,25 @@ static void *m_start(struct seq_file *m, loff_t *ppos)
 		return NULL;
 	}
 
-	if (mmap_read_lock_killable(mm)) {
+	if (!lock_vma_range(m, priv)) {
 		mmput(mm);
 		put_task_struct(priv->task);
 		priv->task = NULL;
 		return ERR_PTR(-EINTR);
 	}
 
+	/*
+	 * Reset current position if last_addr was set before
+	 * and it's not a sentinel.
+	 */
+	if (last_addr > 0)
+		*ppos = last_addr = priv->last_pos;
 	vma_iter_init(&priv->iter, mm, (unsigned long)last_addr);
 	hold_task_mempolicy(priv);
 	if (last_addr == SENTINEL_VMA_GATE)
 		return get_gate_vma(mm);
 
-	return proc_get_vma(priv, ppos);
+	return proc_get_vma(m, ppos);
 }
 
 static void *m_next(struct seq_file *m, void *v, loff_t *ppos)
@@ -187,7 +312,7 @@ static void *m_next(struct seq_file *m, void *v, loff_t *ppos)
 		*ppos = SENTINEL_VMA_END;
 		return NULL;
 	}
-	return proc_get_vma(m->private, ppos);
+	return proc_get_vma(m, ppos);
 }
 
 static void m_stop(struct seq_file *m, void *v)
@@ -199,7 +324,7 @@ static void m_stop(struct seq_file *m, void *v)
 		return;
 
 	release_task_mempolicy(priv);
-	mmap_read_unlock(mm);
+	unlock_vma_range(priv);
 	mmput(mm);
 	put_task_struct(priv->task);
 	priv->task = NULL;