4.19-stable patches

added patches:
	xfs-fix-deadlock-between-agi-and-agf-with-rename_whiteout.patch

diff --git a/queue-4.19/series b/queue-4.19/series
index fdeb03793df694a6d5ac3974ea44e5ca824d74be..f1856e25188092063f9ea156e5c4da9535ce2c48 100644 (file)
--- a/queue-4.19/series
+++ b/queue-4.19/series
@@ -127,3 +127,4 @@ usb-dwc3-gadget-fix-request-completion-check.patch
 usb-f_fs-clear-os-extended-descriptor-counts-to-zero-in-ffs_data_reset.patch
 xhci-prevent-bus-suspend-if-a-roothub-port-detected-a-over-current-condition.patch
 serial-sh-sci-make-sure-status-register-scxsr-is-read-in-correct-sequence.patch
+xfs-fix-deadlock-between-agi-and-agf-with-rename_whiteout.patch

diff --git a/queue-4.19/xfs-fix-deadlock-between-agi-and-agf-with-rename_whiteout.patch b/queue-4.19/xfs-fix-deadlock-between-agi-and-agf-with-rename_whiteout.patch
new file mode 100644 (file)
index 0000000..8953451
--- /dev/null
+++ b/queue-4.19/xfs-fix-deadlock-between-agi-and-agf-with-rename_whiteout.patch
@@ -0,0 +1,210 @@
+From bc56ad8c74b8588685c2875de0df8ab6974828ef Mon Sep 17 00:00:00 2001
+From: kaixuxia <xiakaixu1987@gmail.com>
+Date: Tue, 3 Sep 2019 21:06:50 -0700
+Subject: xfs: Fix deadlock between AGI and AGF with RENAME_WHITEOUT
+
+From: kaixuxia <xiakaixu1987@gmail.com>
+
+commit bc56ad8c74b8588685c2875de0df8ab6974828ef upstream.
+
+When performing rename operation with RENAME_WHITEOUT flag, we will
+hold AGF lock to allocate or free extents in manipulating the dirents
+firstly, and then doing the xfs_iunlink_remove() call last to hold
+AGI lock to modify the tmpfile info, so we the lock order AGI->AGF.
+
+The big problem here is that we have an ordering constraint on AGF
+and AGI locking - inode allocation locks the AGI, then can allocate
+a new extent for new inodes, locking the AGF after the AGI. Hence
+the ordering that is imposed by other parts of the code is AGI before
+AGF. So we get an ABBA deadlock between the AGI and AGF here.
+
+Process A:
+Call trace:
+ ? __schedule+0x2bd/0x620
+ schedule+0x33/0x90
+ schedule_timeout+0x17d/0x290
+ __down_common+0xef/0x125
+ ? xfs_buf_find+0x215/0x6c0 [xfs]
+ down+0x3b/0x50
+ xfs_buf_lock+0x34/0xf0 [xfs]
+ xfs_buf_find+0x215/0x6c0 [xfs]
+ xfs_buf_get_map+0x37/0x230 [xfs]
+ xfs_buf_read_map+0x29/0x190 [xfs]
+ xfs_trans_read_buf_map+0x13d/0x520 [xfs]
+ xfs_read_agf+0xa6/0x180 [xfs]
+ ? schedule_timeout+0x17d/0x290
+ xfs_alloc_read_agf+0x52/0x1f0 [xfs]
+ xfs_alloc_fix_freelist+0x432/0x590 [xfs]
+ ? down+0x3b/0x50
+ ? xfs_buf_lock+0x34/0xf0 [xfs]
+ ? xfs_buf_find+0x215/0x6c0 [xfs]
+ xfs_alloc_vextent+0x301/0x6c0 [xfs]
+ xfs_ialloc_ag_alloc+0x182/0x700 [xfs]
+ ? _xfs_trans_bjoin+0x72/0xf0 [xfs]
+ xfs_dialloc+0x116/0x290 [xfs]
+ xfs_ialloc+0x6d/0x5e0 [xfs]
+ ? xfs_log_reserve+0x165/0x280 [xfs]
+ xfs_dir_ialloc+0x8c/0x240 [xfs]
+ xfs_create+0x35a/0x610 [xfs]
+ xfs_generic_create+0x1f1/0x2f0 [xfs]
+ ...
+
+Process B:
+Call trace:
+ ? __schedule+0x2bd/0x620
+ ? xfs_bmapi_allocate+0x245/0x380 [xfs]
+ schedule+0x33/0x90
+ schedule_timeout+0x17d/0x290
+ ? xfs_buf_find+0x1fd/0x6c0 [xfs]
+ __down_common+0xef/0x125
+ ? xfs_buf_get_map+0x37/0x230 [xfs]
+ ? xfs_buf_find+0x215/0x6c0 [xfs]
+ down+0x3b/0x50
+ xfs_buf_lock+0x34/0xf0 [xfs]
+ xfs_buf_find+0x215/0x6c0 [xfs]
+ xfs_buf_get_map+0x37/0x230 [xfs]
+ xfs_buf_read_map+0x29/0x190 [xfs]
+ xfs_trans_read_buf_map+0x13d/0x520 [xfs]
+ xfs_read_agi+0xa8/0x160 [xfs]
+ xfs_iunlink_remove+0x6f/0x2a0 [xfs]
+ ? current_time+0x46/0x80
+ ? xfs_trans_ichgtime+0x39/0xb0 [xfs]
+ xfs_rename+0x57a/0xae0 [xfs]
+ xfs_vn_rename+0xe4/0x150 [xfs]
+ ...
+
+In this patch we move the xfs_iunlink_remove() call to
+before acquiring the AGF lock to preserve correct AGI/AGF locking
+order.
+
+[Minor massage required due to upstream change making xfs_bumplink() a
+void function where as in the 4.19.y tree the return value is checked,
+even though it is always zero. Only change was to the last code block
+removed by the patch. Functionally equivalent to upstream.]
+
+Signed-off-by: kaixuxia <kaixuxia@tencent.com>
+Reviewed-by: Brian Foster <bfoster@redhat.com>
+Reviewed-by: Darrick J. Wong <darrick.wong@oracle.com>
+Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
+Signed-off-by: Suraj Jitindar Singh <surajjs@amazon.com>
+Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
+
+---
+ fs/xfs/xfs_inode.c |   85 ++++++++++++++++++++++++++---------------------------
+ 1 file changed, 42 insertions(+), 43 deletions(-)
+
+--- a/fs/xfs/xfs_inode.c
++++ b/fs/xfs/xfs_inode.c
+@@ -2949,7 +2949,8 @@ xfs_rename(
+                                       spaceres);
+ 
+       /*
+-       * Set up the target.
++       * Check for expected errors before we dirty the transaction
++       * so we can return an error without a transaction abort.
+        */
+       if (target_ip == NULL) {
+               /*
+@@ -2961,6 +2962,46 @@ xfs_rename(
+                       if (error)
+                               goto out_trans_cancel;
+               }
++      } else {
++              /*
++               * If target exists and it's a directory, check that whether
++               * it can be destroyed.
++               */
++              if (S_ISDIR(VFS_I(target_ip)->i_mode) &&
++                  (!xfs_dir_isempty(target_ip) ||
++                   (VFS_I(target_ip)->i_nlink > 2))) {
++                      error = -EEXIST;
++                      goto out_trans_cancel;
++              }
++      }
++
++      /*
++       * Directory entry creation below may acquire the AGF. Remove
++       * the whiteout from the unlinked list first to preserve correct
++       * AGI/AGF locking order. This dirties the transaction so failures
++       * after this point will abort and log recovery will clean up the
++       * mess.
++       *
++       * For whiteouts, we need to bump the link count on the whiteout
++       * inode. After this point, we have a real link, clear the tmpfile
++       * state flag from the inode so it doesn't accidentally get misused
++       * in future.
++       */
++      if (wip) {
++              ASSERT(VFS_I(wip)->i_nlink == 0);
++              error = xfs_iunlink_remove(tp, wip);
++              if (error)
++                      goto out_trans_cancel;
++
++              xfs_bumplink(tp, wip);
++              xfs_trans_log_inode(tp, wip, XFS_ILOG_CORE);
++              VFS_I(wip)->i_state &= ~I_LINKABLE;
++      }
++
++      /*
++       * Set up the target.
++       */
++      if (target_ip == NULL) {
+               /*
+                * If target does not exist and the rename crosses
+                * directories, adjust the target directory link count
+@@ -2981,22 +3022,6 @@ xfs_rename(
+               }
+       } else { /* target_ip != NULL */
+               /*
+-               * If target exists and it's a directory, check that both
+-               * target and source are directories and that target can be
+-               * destroyed, or that neither is a directory.
+-               */
+-              if (S_ISDIR(VFS_I(target_ip)->i_mode)) {
+-                      /*
+-                       * Make sure target dir is empty.
+-                       */
+-                      if (!(xfs_dir_isempty(target_ip)) ||
+-                          (VFS_I(target_ip)->i_nlink > 2)) {
+-                              error = -EEXIST;
+-                              goto out_trans_cancel;
+-                      }
+-              }
+-
+-              /*
+                * Link the source inode under the target name.
+                * If the source inode is a directory and we are moving
+                * it across directories, its ".." entry will be
+@@ -3086,32 +3111,6 @@ xfs_rename(
+       if (error)
+               goto out_trans_cancel;
+ 
+-      /*
+-       * For whiteouts, we need to bump the link count on the whiteout inode.
+-       * This means that failures all the way up to this point leave the inode
+-       * on the unlinked list and so cleanup is a simple matter of dropping
+-       * the remaining reference to it. If we fail here after bumping the link
+-       * count, we're shutting down the filesystem so we'll never see the
+-       * intermediate state on disk.
+-       */
+-      if (wip) {
+-              ASSERT(VFS_I(wip)->i_nlink == 0);
+-              error = xfs_bumplink(tp, wip);
+-              if (error)
+-                      goto out_trans_cancel;
+-              error = xfs_iunlink_remove(tp, wip);
+-              if (error)
+-                      goto out_trans_cancel;
+-              xfs_trans_log_inode(tp, wip, XFS_ILOG_CORE);
+-
+-              /*
+-               * Now we have a real link, clear the "I'm a tmpfile" state
+-               * flag from the inode so it doesn't accidentally get misused in
+-               * future.
+-               */
+-              VFS_I(wip)->i_state &= ~I_LINKABLE;
+-      }
+-
+       xfs_trans_ichgtime(tp, src_dp, XFS_ICHGTIME_MOD | XFS_ICHGTIME_CHG);
+       xfs_trans_log_inode(tp, src_dp, XFS_ILOG_CORE);
+       if (new_parent)