Merge tag 'v6.11' into for-6.12/block

Merge in 6.11 final to get the fix for preventing deadlocks on an
elevator switch, as there's a fixup for that patch.

* tag 'v6.11': (1788 commits)
  Linux 6.11
  Revert "KVM: VMX: Always honor guest PAT on CPUs that support self-snoop"
  pinctrl: pinctrl-cy8c95x0: Fix regcache
  cifs: Fix signature miscalculation
  mm: avoid leaving partial pfn mappings around in error case
  drm/xe/client: add missing bo locking in show_meminfo()
  drm/xe/client: fix deadlock in show_meminfo()
  drm/xe/oa: Enable Xe2+ PES disaggregation
  drm/xe/display: fix compat IS_DISPLAY_STEP() range end
  drm/xe: Fix access_ok check in user_fence_create
  drm/xe: Fix possible UAF in guc_exec_queue_process_msg
  drm/xe: Remove fence check from send_tlb_invalidation
  drm/xe/gt: Remove double include
  net: netfilter: move nf flowtable bpf initialization in nf_flow_table_module_init()
  PCI: Fix potential deadlock in pcim_intx()
  workqueue: Clear worker->pool in the worker thread context
  net: tighten bad gso csum offset check in virtio_net_hdr
  netlink: specs: mptcp: fix port endianness
  net: dpaa: Pad packets to ETH_ZLEN
  mptcp: pm: Fix uaf in __timer_delete_sync
  ...

1 files changed, 18 insertions, 10 deletions

diff --git a/fs/btrfs/direct-io.c b/fs/btrfs/direct-io.c
index f9fb2db6a1e4..364bce34f034 100644
--- a/fs/btrfs/direct-io.c
+++ b/fs/btrfs/direct-io.c
@@ -856,21 +856,27 @@ relock:
 	 * So here we disable page faults in the iov_iter and then retry if we
 	 * got -EFAULT, faulting in the pages before the retry.
 	 */
+again:
 	from->nofault = true;
 	dio = btrfs_dio_write(iocb, from, written);
 	from->nofault = false;
 
-	/*
-	 * iomap_dio_complete() will call btrfs_sync_file() if we have a dsync
-	 * iocb, and that needs to lock the inode. So unlock it before calling
-	 * iomap_dio_complete() to avoid a deadlock.
-	 */
-	btrfs_inode_unlock(BTRFS_I(inode), ilock_flags);
-
-	if (IS_ERR_OR_NULL(dio))
+	if (IS_ERR_OR_NULL(dio)) {
 		ret = PTR_ERR_OR_ZERO(dio);
-	else
+	} else {
+		/*
+		 * If we have a synchronous write, we must make sure the fsync
+		 * triggered by the iomap_dio_complete() call below doesn't
+		 * deadlock on the inode lock - we are already holding it and we
+		 * can't call it after unlocking because we may need to complete
+		 * partial writes due to the input buffer (or parts of it) not
+		 * being already faulted in.
+		 */
+		ASSERT(current->journal_info == NULL);
+		current->journal_info = BTRFS_TRANS_DIO_WRITE_STUB;
 		ret = iomap_dio_complete(dio);
+		current->journal_info = NULL;
+	}
 
 	/* No increment (+=) because iomap returns a cumulative value. */
 	if (ret > 0)
@@ -897,10 +903,12 @@ relock:
 		} else {
 			fault_in_iov_iter_readable(from, left);
 			prev_left = left;
-			goto relock;
+			goto again;
 		}
 	}
 
+	btrfs_inode_unlock(BTRFS_I(inode), ilock_flags);
+
 	/*
 	 * If 'ret' is -ENOTBLK or we have not written all data, then it means
 	 * we must fallback to buffered IO.