xfs: fix deadlock and streamline xfs_getfsmap performance

Refactor xfs_getfsmap to improve its performance: instead of indirectly
calling a function that copies one record to userspace at a time, create
a shadow buffer in the kernel and copy the whole array once at the end.
On the author's computer, this reduces the runtime on his /home by ~20%.

This also eliminates a deadlock when running GETFSMAP against the
realtime device.  The current code locks the rtbitmap to create
fsmappings and copies them into userspace, having not released the
rtbitmap lock.  If the userspace buffer is an mmap of a sparse file that
itself resides on the realtime device, the write page fault will recurse
into the fs for allocation, which will deadlock on the rtbitmap lock.

Fixes: 4c934c7dd60c ("xfs: report realtime space information via the rtbitmap")
Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Chandan Babu R <chandanrlinux@gmail.com>

1 files changed, 25 insertions, 20 deletions

diff --git a/fs/xfs/xfs_fsmap.c b/fs/xfs/xfs_fsmap.c
index aa36e7daf82c..9ce5e7d5bf8f 100644
--- a/fs/xfs/xfs_fsmap.c
+++ b/fs/xfs/xfs_fsmap.c
@@ -26,7 +26,7 @@
 #include "xfs_rtalloc.h"
 
 /* Convert an xfs_fsmap to an fsmap. */
-void
+static void
 xfs_fsmap_from_internal(
 	struct fsmap		*dest,
 	struct xfs_fsmap	*src)
@@ -155,8 +155,7 @@ xfs_fsmap_owner_from_rmap(
 /* getfsmap query state */
 struct xfs_getfsmap_info {
 	struct xfs_fsmap_head	*head;
-	xfs_fsmap_format_t	formatter;	/* formatting fn */
-	void			*format_arg;	/* format buffer */
+	struct fsmap		*fsmap_recs;	/* mapping records */
 	struct xfs_buf		*agf_bp;	/* AGF, for refcount queries */
 	xfs_daddr_t		next_daddr;	/* next daddr we expect */
 	u64			missing_owner;	/* owner of holes */
@@ -224,6 +223,20 @@ xfs_getfsmap_is_shared(
 	return 0;
 }
 
+static inline void
+xfs_getfsmap_format(
+	struct xfs_mount		*mp,
+	struct xfs_fsmap		*xfm,
+	struct xfs_getfsmap_info	*info)
+{
+	struct fsmap			*rec;
+
+	trace_xfs_getfsmap_mapping(mp, xfm);
+
+	rec = &info->fsmap_recs[info->head->fmh_entries++];
+	xfs_fsmap_from_internal(rec, xfm);
+}
+
 /*
  * Format a reverse mapping for getfsmap, having translated rm_startblock
  * into the appropriate daddr units.
@@ -288,10 +301,7 @@ xfs_getfsmap_helper(
 		fmr.fmr_offset = 0;
 		fmr.fmr_length = rec_daddr - info->next_daddr;
 		fmr.fmr_flags = FMR_OF_SPECIAL_OWNER;
-		error = info->formatter(&fmr, info->format_arg);
-		if (error)
-			return error;
-		info->head->fmh_entries++;
+		xfs_getfsmap_format(mp, &fmr, info);
 	}
 
 	if (info->last)
@@ -323,11 +333,8 @@ xfs_getfsmap_helper(
 		if (shared)
 			fmr.fmr_flags |= FMR_OF_SHARED;
 	}
-	error = info->formatter(&fmr, info->format_arg);
-	if (error)
-		return error;
-	info->head->fmh_entries++;
 
+	xfs_getfsmap_format(mp, &fmr, info);
 out:
 	rec_daddr += XFS_FSB_TO_BB(mp, rec->rm_blockcount);
 	if (info->next_daddr < rec_daddr)
@@ -795,11 +802,11 @@ xfs_getfsmap_check_keys(
 #endif /* CONFIG_XFS_RT */
 
 /*
- * Get filesystem's extents as described in head, and format for
- * output.  Calls formatter to fill the user's buffer until all
- * extents are mapped, until the passed-in head->fmh_count slots have
- * been filled, or until the formatter short-circuits the loop, if it
- * is tracking filled-in extents on its own.
+ * Get filesystem's extents as described in head, and format for output. Fills
+ * in the supplied records array until there are no more reverse mappings to
+ * return or head.fmh_entries == head.fmh_count.  In the second case, this
+ * function returns -ECANCELED to indicate that more records would have been
+ * returned.
  *
  * Key to Confusion
  * ----------------
@@ -819,8 +826,7 @@ int
 xfs_getfsmap(
 	struct xfs_mount		*mp,
 	struct xfs_fsmap_head		*head,
-	xfs_fsmap_format_t		formatter,
-	void				*arg)
+	struct fsmap			*fsmap_recs)
 {
 	struct xfs_trans		*tp = NULL;
 	struct xfs_fsmap		dkeys[2];	/* per-dev keys */
@@ -895,8 +901,7 @@ xfs_getfsmap(
 
 	info.next_daddr = head->fmh_keys[0].fmr_physical +
 			  head->fmh_keys[0].fmr_length;
-	info.formatter = formatter;
-	info.format_arg = arg;
+	info.fsmap_recs = fsmap_recs;
 	info.head = head;
 
 	/*