4.9-stable patches

added patches:
	btrfs-ensure-replaced-device-doesn-t-have-pending-chunk-allocation.patch

diff --git a/queue-4.9/btrfs-ensure-replaced-device-doesn-t-have-pending-chunk-allocation.patch b/queue-4.9/btrfs-ensure-replaced-device-doesn-t-have-pending-chunk-allocation.patch
new file mode 100644 (file)
index 0000000..9b72ff9
--- /dev/null
+++ b/queue-4.9/btrfs-ensure-replaced-device-doesn-t-have-pending-chunk-allocation.patch
@@ -0,0 +1,122 @@
+From debd1c065d2037919a7da67baf55cc683fee09f0 Mon Sep 17 00:00:00 2001
+From: Nikolay Borisov <nborisov@suse.com>
+Date: Fri, 17 May 2019 10:44:25 +0300
+Subject: btrfs: Ensure replaced device doesn't have pending chunk allocation
+
+From: Nikolay Borisov <nborisov@suse.com>
+
+commit debd1c065d2037919a7da67baf55cc683fee09f0 upstream.
+
+Recent FITRIM work, namely bbbf7243d62d ("btrfs: combine device update
+operations during transaction commit") combined the way certain
+operations are recoded in a transaction. As a result an ASSERT was added
+in dev_replace_finish to ensure the new code works correctly.
+Unfortunately I got reports that it's possible to trigger the assert,
+meaning that during a device replace it's possible to have an unfinished
+chunk allocation on the source device.
+
+This is supposed to be prevented by the fact that a transaction is
+committed before finishing the replace oepration and alter acquiring the
+chunk mutex. This is not sufficient since by the time the transaction is
+committed and the chunk mutex acquired it's possible to allocate a chunk
+depending on the workload being executed on the replaced device. This
+bug has been present ever since device replace was introduced but there
+was never code which checks for it.
+
+The correct way to fix is to ensure that there is no pending device
+modification operation when the chunk mutex is acquire and if there is
+repeat transaction commit. Unfortunately it's not possible to just
+exclude the source device from btrfs_fs_devices::dev_alloc_list since
+this causes ENOSPC to be hit in transaction commit.
+
+Fixing that in another way would need to add special cases to handle the
+last writes and forbid new ones. The looped transaction fix is more
+obvious, and can be easily backported. The runtime of dev-replace is
+long so there's no noticeable delay caused by that.
+
+Reported-by: David Sterba <dsterba@suse.com>
+Fixes: 391cd9df81ac ("Btrfs: fix unprotected alloc list insertion during the finishing procedure of replace")
+CC: stable@vger.kernel.org # 4.4+
+Signed-off-by: Nikolay Borisov <nborisov@suse.com>
+Reviewed-by: David Sterba <dsterba@suse.com>
+Signed-off-by: David Sterba <dsterba@suse.com>
+Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
+
+---
+ fs/btrfs/dev-replace.c |   29 +++++++++++++++++++----------
+ fs/btrfs/volumes.c     |    2 ++
+ fs/btrfs/volumes.h     |    5 +++++
+ 3 files changed, 26 insertions(+), 10 deletions(-)
+
+--- a/fs/btrfs/dev-replace.c
++++ b/fs/btrfs/dev-replace.c
+@@ -511,18 +511,27 @@ static int btrfs_dev_replace_finishing(s
+       }
+       btrfs_wait_ordered_roots(root->fs_info, -1, 0, (u64)-1);
+ 
+-      trans = btrfs_start_transaction(root, 0);
+-      if (IS_ERR(trans)) {
+-              mutex_unlock(&dev_replace->lock_finishing_cancel_unmount);
+-              return PTR_ERR(trans);
++      while (1) {
++              trans = btrfs_start_transaction(root, 0);
++              if (IS_ERR(trans)) {
++                      mutex_unlock(&dev_replace->lock_finishing_cancel_unmount);
++                      return PTR_ERR(trans);
++              }
++              ret = btrfs_commit_transaction(trans, root);
++              WARN_ON(ret);
++              mutex_lock(&uuid_mutex);
++              /* keep away write_all_supers() during the finishing procedure */
++              mutex_lock(&root->fs_info->fs_devices->device_list_mutex);
++              mutex_lock(&root->fs_info->chunk_mutex);
++              if (src_device->has_pending_chunks) {
++                      mutex_unlock(&root->fs_info->chunk_mutex);
++                      mutex_unlock(&root->fs_info->fs_devices->device_list_mutex);
++                      mutex_unlock(&uuid_mutex);
++              } else {
++                      break;
++              }
+       }
+-      ret = btrfs_commit_transaction(trans, root);
+-      WARN_ON(ret);
+ 
+-      mutex_lock(&uuid_mutex);
+-      /* keep away write_all_supers() during the finishing procedure */
+-      mutex_lock(&root->fs_info->fs_devices->device_list_mutex);
+-      mutex_lock(&root->fs_info->chunk_mutex);
+       btrfs_dev_replace_lock(dev_replace, 1);
+       dev_replace->replace_state =
+               scrub_ret ? BTRFS_IOCTL_DEV_REPLACE_STATE_CANCELED
+--- a/fs/btrfs/volumes.c
++++ b/fs/btrfs/volumes.c
+@@ -4876,6 +4876,7 @@ static int __btrfs_alloc_chunk(struct bt
+       for (i = 0; i < map->num_stripes; i++) {
+               num_bytes = map->stripes[i].dev->bytes_used + stripe_size;
+               btrfs_device_set_bytes_used(map->stripes[i].dev, num_bytes);
++              map->stripes[i].dev->has_pending_chunks = true;
+       }
+ 
+       spin_lock(&extent_root->fs_info->free_chunk_lock);
+@@ -7250,6 +7251,7 @@ void btrfs_update_commit_device_bytes_us
+               for (i = 0; i < map->num_stripes; i++) {
+                       dev = map->stripes[i].dev;
+                       dev->commit_bytes_used = dev->bytes_used;
++                      dev->has_pending_chunks = false;
+               }
+       }
+       unlock_chunks(root);
+--- a/fs/btrfs/volumes.h
++++ b/fs/btrfs/volumes.h
+@@ -62,6 +62,11 @@ struct btrfs_device {
+ 
+       spinlock_t io_lock ____cacheline_aligned;
+       int running_pending;
++      /* When true means this device has pending chunk alloc in
++       * current transaction. Protected by chunk_mutex.
++       */
++      bool has_pending_chunks;
++
+       /* regular prio bios */
+       struct btrfs_pending_bios pending_bios;
+       /* WRITE_SYNC bios */

diff --git a/queue-4.9/series b/queue-4.9/series
index b56c32a48b728fb97a17e1217419c80a5974855a..6273550f65948b0bceb6cb502ce899b630281490 100644 (file)
--- a/queue-4.9/series
+++ b/queue-4.9/series
@@ -89,3 +89,4 @@ alsa-usb-audio-fix-sign-unintended-sign-extension-on-left-shifts.patch
 lib-mpi-fix-karactx-leak-in-mpi_powm.patch
 drm-imx-notify-drm-core-before-sending-event-during-crtc-disable.patch
 drm-imx-only-send-event-on-crtc-disable-if-kept-disabled.patch
+btrfs-ensure-replaced-device-doesn-t-have-pending-chunk-allocation.patch