After we drop the i_pages lock, the inode can be freed at any time. The get_unlocked_entry() code has no choice but to reacquire the lock, so it can't be used here. Create a new wait_entry_unlocked() which takes care not to acquire the lock or dereference the address_space in any way.
Fixes: c2a7d2a11552 ("filesystem-dax: Introduce dax_lock_mapping_entry()") Cc: stable@vger.kernel.org Signed-off-by: Matthew Wilcox willy@infradead.org --- fs/dax.c | 26 +++++++++++++++++++++++--- 1 file changed, 23 insertions(+), 3 deletions(-)
diff --git a/fs/dax.c b/fs/dax.c index e69fc231833b..cf1805645d18 100644 --- a/fs/dax.c +++ b/fs/dax.c @@ -232,6 +232,28 @@ static void *get_unlocked_entry(struct xa_state *xas) } }
+/* + * The only thing keeping the address space around is the i_pages lock + * (it's cycled in clear_inode() after removing the entries from i_pages) + * After we call xas_unlock_irq(), we cannot touch xas->xa. + */ +static void wait_entry_unlocked(struct xa_state *xas, void *entry) +{ + struct wait_exceptional_entry_queue ewait; + wait_queue_head_t *wq; + + init_wait(&ewait.wait); + ewait.wait.func = wake_exceptional_entry_func; + + wq = dax_entry_waitqueue(xas, entry, &ewait.key); + prepare_to_wait_exclusive(wq, &ewait.wait, TASK_UNINTERRUPTIBLE); + xas_unlock_irq(xas); + schedule(); + finish_wait(wq, &ewait.wait); + if (waitqueue_active(wq)) + __wake_up(wq, TASK_NORMAL, 1, &ewait.key); +} + static void put_unlocked_entry(struct xa_state *xas, void *entry) { /* If we were the only waiter woken, wake the next one */ @@ -389,9 +411,7 @@ bool dax_lock_mapping_entry(struct page *page) entry = xas_load(&xas); if (dax_is_locked(entry)) { rcu_read_unlock(); - entry = get_unlocked_entry(&xas); - xas_unlock_irq(&xas); - put_unlocked_entry(&xas, entry); + wait_entry_unlocked(&xas, entry); rcu_read_lock(); continue; }
On Tue 27-11-18 13:16:34, Matthew Wilcox wrote:
After we drop the i_pages lock, the inode can be freed at any time. The get_unlocked_entry() code has no choice but to reacquire the lock, so it can't be used here. Create a new wait_entry_unlocked() which takes care not to acquire the lock or dereference the address_space in any way.
Fixes: c2a7d2a11552 ("filesystem-dax: Introduce dax_lock_mapping_entry()") Cc: stable@vger.kernel.org Signed-off-by: Matthew Wilcox willy@infradead.org
The patch looks good. You can add:
Reviewed-by: Jan Kara jack@suse.cz
Just one nit below:
+/*
- The only thing keeping the address space around is the i_pages lock
- (it's cycled in clear_inode() after removing the entries from i_pages)
- After we call xas_unlock_irq(), we cannot touch xas->xa.
- */
+static void wait_entry_unlocked(struct xa_state *xas, void *entry) +{
- struct wait_exceptional_entry_queue ewait;
- wait_queue_head_t *wq;
- init_wait(&ewait.wait);
- ewait.wait.func = wake_exceptional_entry_func;
- wq = dax_entry_waitqueue(xas, entry, &ewait.key);
- prepare_to_wait_exclusive(wq, &ewait.wait, TASK_UNINTERRUPTIBLE);
- xas_unlock_irq(xas);
- schedule();
- finish_wait(wq, &ewait.wait);
Can we add a comment here like:
/* * Entry lock waits are exclusive. Wake up the next waiter since we * aren't sure we will acquire the entry lock and thus wake the * next waiter up on unlock. */
Because I always wonder for a moment why this is needed.
- if (waitqueue_active(wq))
__wake_up(wq, TASK_NORMAL, 1, &ewait.key);+}
Honza
On Wed, Nov 28, 2018 at 3:54 AM Jan Kara jack@suse.cz wrote:
On Tue 27-11-18 13:16:34, Matthew Wilcox wrote:
After we drop the i_pages lock, the inode can be freed at any time. The get_unlocked_entry() code has no choice but to reacquire the lock, so it can't be used here. Create a new wait_entry_unlocked() which takes care not to acquire the lock or dereference the address_space in any way.
Fixes: c2a7d2a11552 ("filesystem-dax: Introduce dax_lock_mapping_entry()") Cc: stable@vger.kernel.org Signed-off-by: Matthew Wilcox willy@infradead.org
The patch looks good. You can add:
Reviewed-by: Jan Kara jack@suse.cz
Just one nit below:
+/*
- The only thing keeping the address space around is the i_pages lock
- (it's cycled in clear_inode() after removing the entries from i_pages)
- After we call xas_unlock_irq(), we cannot touch xas->xa.
- */
+static void wait_entry_unlocked(struct xa_state *xas, void *entry) +{
struct wait_exceptional_entry_queue ewait;wait_queue_head_t *wq;init_wait(&ewait.wait);ewait.wait.func = wake_exceptional_entry_func;wq = dax_entry_waitqueue(xas, entry, &ewait.key);prepare_to_wait_exclusive(wq, &ewait.wait, TASK_UNINTERRUPTIBLE);xas_unlock_irq(xas);schedule();finish_wait(wq, &ewait.wait);Can we add a comment here like:
/* * Entry lock waits are exclusive. Wake up the next waiter since we * aren't sure we will acquire the entry lock and thus wake the * next waiter up on unlock. */Because I always wonder for a moment why this is needed.
Looks good, I'll add that when applying.
On Wed, Nov 28, 2018 at 09:08:40AM -0800, Dan Williams wrote:
Can we add a comment here like:
/* * Entry lock waits are exclusive. Wake up the next waiter since we * aren't sure we will acquire the entry lock and thus wake the * next waiter up on unlock. */Because I always wonder for a moment why this is needed.
Looks good, I'll add that when applying.
Thanks.
From: Matthew Wilcox willy@infradead.org
After we drop the i_pages lock, the inode can be freed at any time. The get_unlocked_entry() code has no choice but to reacquire the lock, so it can't be used here. Create a new wait_entry_unlocked() which takes care not to acquire the lock or dereference the address_space in any way.
Fixes: c2a7d2a11552 ("filesystem-dax: Introduce dax_lock_mapping_entry()") Cc: stable@vger.kernel.org Signed-off-by: Matthew Wilcox willy@infradead.org Reviewed-by: Jan Kara jack@suse.cz Signed-off-by: Dan Williams dan.j.williams@intel.com --- fs/dax.c | 32 +++++++++++++++++++++++++++++--- 1 file changed, 29 insertions(+), 3 deletions(-)
diff --git a/fs/dax.c b/fs/dax.c index e69fc231833b..3f592dc18d67 100644 --- a/fs/dax.c +++ b/fs/dax.c @@ -232,6 +232,34 @@ static void *get_unlocked_entry(struct xa_state *xas) } }
+/* + * The only thing keeping the address space around is the i_pages lock + * (it's cycled in clear_inode() after removing the entries from i_pages) + * After we call xas_unlock_irq(), we cannot touch xas->xa. + */ +static void wait_entry_unlocked(struct xa_state *xas, void *entry) +{ + struct wait_exceptional_entry_queue ewait; + wait_queue_head_t *wq; + + init_wait(&ewait.wait); + ewait.wait.func = wake_exceptional_entry_func; + + wq = dax_entry_waitqueue(xas, entry, &ewait.key); + prepare_to_wait_exclusive(wq, &ewait.wait, TASK_UNINTERRUPTIBLE); + xas_unlock_irq(xas); + schedule(); + finish_wait(wq, &ewait.wait); + + /* + * Entry lock waits are exclusive. Wake up the next waiter since + * we aren't sure we will acquire the entry lock and thus wake + * the next waiter up on unlock. + */ + if (waitqueue_active(wq)) + __wake_up(wq, TASK_NORMAL, 1, &ewait.key); +} + static void put_unlocked_entry(struct xa_state *xas, void *entry) { /* If we were the only waiter woken, wake the next one */ @@ -389,9 +417,7 @@ bool dax_lock_mapping_entry(struct page *page) entry = xas_load(&xas); if (dax_is_locked(entry)) { rcu_read_unlock(); - entry = get_unlocked_entry(&xas); - xas_unlock_irq(&xas); - put_unlocked_entry(&xas, entry); + wait_entry_unlocked(&xas, entry); rcu_read_lock(); continue; }
linux-stable-mirror@lists.linaro.org
-
Dan Williams -
Jan Kara -
Matthew Wilcox