| lists.openwall.net | lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC | |
|
Open Source and information security mailing list archives
| ||
|
Message-ID: <20250731013405.4066346-2-surenb@google.com>
Date: Wed, 30 Jul 2025 18:34:04 -0700
From: Suren Baghdasaryan <surenb@...gle.com>
To: akpm@...ux-foundation.org
Cc: jannh@...gle.com, Liam.Howlett@...cle.com, lorenzo.stoakes@...cle.com,
vbabka@...e.cz, pfalcato@...e.de, linux-mm@...ck.org,
linux-kernel@...r.kernel.org, surenb@...gle.com
Subject: [PATCH 2/2] mm: change vma_start_read() to drop RCU lock on failure
vma_start_read() can drop and reacquire RCU lock in certain failure
cases. It's not apparent that the RCU session started by the caller of
this function might be interrupted when vma_start_read() fails to lock
the vma. This might become a source of subtle bugs and to prevent that
we change the locking rules for vma_start_read() to drop RCU read lock
upon failure. This way it's more obvious that RCU-protected objects are
unsafe after vma locking fails.
Suggested-by: Vlastimil Babka <vbabka@...e.cz>
Signed-off-by: Suren Baghdasaryan <surenb@...gle.com>
---
mm/mmap_lock.c | 76 +++++++++++++++++++++++++++++---------------------
1 file changed, 44 insertions(+), 32 deletions(-)
diff --git a/mm/mmap_lock.c b/mm/mmap_lock.c
index 10826f347a9f..0129db8f652f 100644
--- a/mm/mmap_lock.c
+++ b/mm/mmap_lock.c
@@ -136,15 +136,21 @@ void vma_mark_detached(struct vm_area_struct *vma)
* Returns the vma on success, NULL on failure to lock and EAGAIN if vma got
* detached.
*
- * WARNING! The vma passed to this function cannot be used if the function
- * fails to lock it because in certain cases RCU lock is dropped and then
- * reacquired. Once RCU lock is dropped the vma can be concurently freed.
+ * WARNING! On entrance to this function RCU read lock should be held and it
+ * is released if function fails to lock the vma, therefore vma passed to this
+ * function cannot be used if the function fails to lock it.
+ * When vma is successfully locked, RCU read lock is kept intact and RCU read
+ * session is not interrupted. This is important when locking is done while
+ * walking the vma tree under RCU using vma_iterator because if the RCU lock
+ * is dropped, the iterator becomes invalid.
*/
static inline struct vm_area_struct *vma_start_read(struct mm_struct *mm,
struct vm_area_struct *vma)
{
+ struct mm_struct *other_mm;
int oldcnt;
+ RCU_LOCKDEP_WARN(!rcu_read_lock_held(), "no rcu lock held");
/*
* Check before locking. A race might cause false locked result.
* We can use READ_ONCE() for the mm_lock_seq here, and don't need
@@ -152,8 +158,10 @@ static inline struct vm_area_struct *vma_start_read(struct mm_struct *mm,
* 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(mm->mm_lock_seq.sequence))
- return NULL;
+ if (READ_ONCE(vma->vm_lock_seq) == READ_ONCE(mm->mm_lock_seq.sequence)) {
+ vma = NULL;
+ goto err;
+ }
/*
* If VMA_LOCK_OFFSET is set, __refcount_inc_not_zero_limited_acquire()
@@ -164,7 +172,8 @@ static inline struct vm_area_struct *vma_start_read(struct mm_struct *mm,
if (unlikely(!__refcount_inc_not_zero_limited_acquire(&vma->vm_refcnt, &oldcnt,
VMA_REF_LIMIT))) {
/* return EAGAIN if vma got detached from under us */
- return oldcnt ? NULL : ERR_PTR(-EAGAIN);
+ vma = oldcnt ? NULL : ERR_PTR(-EAGAIN);
+ goto err;
}
rwsem_acquire_read(&vma->vmlock_dep_map, 0, 1, _RET_IP_);
@@ -175,23 +184,8 @@ static inline struct vm_area_struct *vma_start_read(struct mm_struct *mm,
* is dropped and before rcuwait_wake_up(mm) is called. Grab it before
* releasing vma->vm_refcnt.
*/
- if (unlikely(vma->vm_mm != mm)) {
- /* Use a copy of vm_mm in case vma is freed after we drop vm_refcnt */
- struct mm_struct *other_mm = vma->vm_mm;
-
- /*
- * __mmdrop() is a heavy operation and we don't need RCU
- * protection here. Release RCU lock during these operations.
- * We reinstate the RCU read lock as the caller expects it to
- * be held when this function returns even on error.
- */
- rcu_read_unlock();
- mmgrab(other_mm);
- vma_refcount_put(vma);
- mmdrop(other_mm);
- rcu_read_lock();
- return NULL;
- }
+ if (unlikely(vma->vm_mm != mm))
+ goto err_unstable;
/*
* Overflow of vm_lock_seq/mm_lock_seq might produce false locked result.
@@ -206,10 +200,26 @@ static inline struct vm_area_struct *vma_start_read(struct mm_struct *mm,
*/
if (unlikely(vma->vm_lock_seq == raw_read_seqcount(&mm->mm_lock_seq))) {
vma_refcount_put(vma);
- return NULL;
+ vma = NULL;
+ goto err;
}
return vma;
+err:
+ rcu_read_unlock();
+
+ return vma;
+err_unstable:
+ /* Use a copy of vm_mm in case vma is freed after we drop vm_refcnt */
+ other_mm = vma->vm_mm;
+
+ /* __mmdrop() is a heavy operation, do it after dropping RCU lock. */
+ rcu_read_unlock();
+ mmgrab(other_mm);
+ vma_refcount_put(vma);
+ mmdrop(other_mm);
+
+ return NULL;
}
/*
@@ -223,8 +233,8 @@ struct vm_area_struct *lock_vma_under_rcu(struct mm_struct *mm,
MA_STATE(mas, &mm->mm_mt, address, address);
struct vm_area_struct *vma;
- rcu_read_lock();
retry:
+ rcu_read_lock();
vma = mas_walk(&mas);
if (!vma)
goto inval;
@@ -241,6 +251,9 @@ struct vm_area_struct *lock_vma_under_rcu(struct mm_struct *mm,
/* Failed to lock the VMA */
goto inval;
}
+
+ rcu_read_unlock();
+
/*
* At this point, we have a stable reference to a VMA: The VMA is
* locked and we know it hasn't already been isolated.
@@ -249,16 +262,14 @@ struct vm_area_struct *lock_vma_under_rcu(struct mm_struct *mm,
*/
/* Check if the vma we locked is the right one. */
- if (unlikely(address < vma->vm_start || address >= vma->vm_end))
- goto inval_end_read;
+ if (unlikely(address < vma->vm_start || address >= vma->vm_end)) {
+ vma_end_read(vma);
+ goto inval;
+ }
- rcu_read_unlock();
return vma;
-inval_end_read:
- vma_end_read(vma);
inval:
- rcu_read_unlock();
count_vm_vma_lock_event(VMA_LOCK_ABORT);
return NULL;
}
@@ -313,6 +324,7 @@ struct vm_area_struct *lock_next_vma(struct mm_struct *mm,
*/
if (PTR_ERR(vma) == -EAGAIN) {
/* reset to search from the last address */
+ rcu_read_lock();
vma_iter_set(vmi, from_addr);
goto retry;
}
@@ -342,9 +354,9 @@ struct vm_area_struct *lock_next_vma(struct mm_struct *mm,
return vma;
fallback_unlock:
+ rcu_read_unlock();
vma_end_read(vma);
fallback:
- rcu_read_unlock();
vma = lock_next_vma_under_mmap_lock(mm, vmi, from_addr);
rcu_read_lock();
/* Reinitialize the iterator after re-entering rcu read section */
--
2.50.1.552.g942d659e1b-goog
Powered by blists - more mailing lists