Merge tag 'xfs-6.11-merge-3' of git://git.kernel.org/pub/scm/fs/xfs/xfs-linux

Pull xfs updates from Chandan Babu:
 "Major changes in this release are limited to enabling FITRIM on
  realtime devices and Byte-based grant head log reservation tracking.

  The remaining changes are limited to fixes and cleanups included in
  this pull request.

  Core:

   - Enable FITRIM on the realtime device

   - Introduce byte-based grant head log reservation tracking instead of
     physical log location tracking.

     This allows grant head to track a full 64 bit bytes space and hence
     overcome the limit of 4GB indexing that has been present until now

  Fixes:

   - xfs_flush_unmap_range() and xfs_prepare_shift() should consider RT
     extents in the flush unmap range

   - Implement bounds check when traversing log operations during log
     replay

   - Prevent out of bounds access when traversing a directory data block

   - Prevent incorrect ENOSPC when concurrently performing file creation
     and file writes

   - Fix rtalloc rotoring when delalloc is in use

  Cleanups:

   - Clean up I/O path inode locking helpers and the page fault handler

   - xfs: hoist inode operations to libxfs in anticipation of the
     metadata inode directory feature, which maintains a directory tree
     of metadata inodes. This will be necessary for further enhancements
     to the realtime feature, subvolume support

   - Clean up some warts in the extent freeing log intent code

   - Clean up the refcount and rmap intent code before adding support
     for realtime devices

   - Provide the correct email address for sysfs ABI documentation"

* tag 'xfs-6.11-merge-3' of git://git.kernel.org/pub/scm/fs/xfs/xfs-linux: (80 commits)
  xfs: fix rtalloc rotoring when delalloc is in use
  xfs: get rid of xfs_ag_resv_rmapbt_alloc
  xfs: skip flushing log items during push
  xfs: grant heads track byte counts, not LSNs
  xfs: pass the full grant head to accounting functions
  xfs: track log space pinned by the AIL
  xfs: collapse xlog_state_set_callback in caller
  xfs: l_last_sync_lsn is really AIL state
  xfs: ensure log tail is always up to date
  xfs: background AIL push should target physical space
  xfs: AIL doesn't need manual pushing
  xfs: move and rename xfs_trans_committed_bulk
  xfs: fix the contact address for the sysfs ABI documentation
  xfs: Avoid races with cnt_btree lastrec updates
  xfs: move xfs_refcount_update_defer_add to xfs_refcount_item.c
  xfs: simplify usage of the rcur local variable in xfs_refcount_finish_one
  xfs: don't bother calling xfs_refcount_finish_one_cleanup in xfs_refcount_finish_one
  xfs: reuse xfs_refcount_update_cancel_item
  xfs: add a ci_entry helper
  xfs: remove xfs_trans_set_refcount_flags
  ...

1 files changed, 279 insertions, 24 deletions

diff --git a/fs/xfs/xfs_discard.c b/fs/xfs/xfs_discard.c
index 25fe3b932b5a..6f0fc7fe1f2b 100644
--- a/fs/xfs/xfs_discard.c
+++ b/fs/xfs/xfs_discard.c
@@ -20,6 +20,7 @@
 #include "xfs_log.h"
 #include "xfs_ag.h"
 #include "xfs_health.h"
+#include "xfs_rtbitmap.h"
 
 /*
  * Notes on an efficient, low latency fstrim algorithm
@@ -322,7 +323,7 @@ xfs_trim_should_stop(void)
  * we found in the last batch as the key to start the next.
  */
 static int
-xfs_trim_extents(
+xfs_trim_perag_extents(
 	struct xfs_perag	*pag,
 	xfs_agblock_t		start,
 	xfs_agblock_t		end,
@@ -383,6 +384,259 @@ xfs_trim_extents(
 
 }
 
+static int
+xfs_trim_datadev_extents(
+	struct xfs_mount	*mp,
+	xfs_daddr_t		start,
+	xfs_daddr_t		end,
+	xfs_extlen_t		minlen,
+	uint64_t		*blocks_trimmed)
+{
+	xfs_agnumber_t		start_agno, end_agno;
+	xfs_agblock_t		start_agbno, end_agbno;
+	xfs_daddr_t		ddev_end;
+	struct xfs_perag	*pag;
+	int			last_error = 0, error;
+
+	ddev_end = min_t(xfs_daddr_t, end,
+			 XFS_FSB_TO_BB(mp, mp->m_sb.sb_dblocks) - 1);
+
+	start_agno = xfs_daddr_to_agno(mp, start);
+	start_agbno = xfs_daddr_to_agbno(mp, start);
+	end_agno = xfs_daddr_to_agno(mp, ddev_end);
+	end_agbno = xfs_daddr_to_agbno(mp, ddev_end);
+
+	for_each_perag_range(mp, start_agno, end_agno, pag) {
+		xfs_agblock_t	agend = pag->block_count;
+
+		if (start_agno == end_agno)
+			agend = end_agbno;
+		error = xfs_trim_perag_extents(pag, start_agbno, agend, minlen,
+				blocks_trimmed);
+		if (error)
+			last_error = error;
+
+		if (xfs_trim_should_stop()) {
+			xfs_perag_rele(pag);
+			break;
+		}
+		start_agbno = 0;
+	}
+
+	return last_error;
+}
+
+#ifdef CONFIG_XFS_RT
+struct xfs_trim_rtdev {
+	/* list of rt extents to free */
+	struct list_head	extent_list;
+
+	/* pointer to count of blocks trimmed */
+	uint64_t		*blocks_trimmed;
+
+	/* minimum length that caller allows us to trim */
+	xfs_rtblock_t		minlen_fsb;
+
+	/* restart point for the rtbitmap walk */
+	xfs_rtxnum_t		restart_rtx;
+
+	/* stopping point for the current rtbitmap walk */
+	xfs_rtxnum_t		stop_rtx;
+};
+
+struct xfs_rtx_busy {
+	struct list_head	list;
+	xfs_rtblock_t		bno;
+	xfs_rtblock_t		length;
+};
+
+static void
+xfs_discard_free_rtdev_extents(
+	struct xfs_trim_rtdev	*tr)
+{
+	struct xfs_rtx_busy	*busyp, *n;
+
+	list_for_each_entry_safe(busyp, n, &tr->extent_list, list) {
+		list_del_init(&busyp->list);
+		kfree(busyp);
+	}
+}
+
+/*
+ * Walk the discard list and issue discards on all the busy extents in the
+ * list. We plug and chain the bios so that we only need a single completion
+ * call to clear all the busy extents once the discards are complete.
+ */
+static int
+xfs_discard_rtdev_extents(
+	struct xfs_mount	*mp,
+	struct xfs_trim_rtdev	*tr)
+{
+	struct block_device	*bdev = mp->m_rtdev_targp->bt_bdev;
+	struct xfs_rtx_busy	*busyp;
+	struct bio		*bio = NULL;
+	struct blk_plug		plug;
+	xfs_rtblock_t		start = NULLRTBLOCK, length = 0;
+	int			error = 0;
+
+	blk_start_plug(&plug);
+	list_for_each_entry(busyp, &tr->extent_list, list) {
+		if (start == NULLRTBLOCK)
+			start = busyp->bno;
+		length += busyp->length;
+
+		trace_xfs_discard_rtextent(mp, busyp->bno, busyp->length);
+
+		error = __blkdev_issue_discard(bdev,
+				XFS_FSB_TO_BB(mp, busyp->bno),
+				XFS_FSB_TO_BB(mp, busyp->length),
+				GFP_NOFS, &bio);
+		if (error)
+			break;
+	}
+	xfs_discard_free_rtdev_extents(tr);
+
+	if (bio) {
+		error = submit_bio_wait(bio);
+		if (error == -EOPNOTSUPP)
+			error = 0;
+		if (error)
+			xfs_info(mp,
+	 "discard failed for rtextent [0x%llx,%llu], error %d",
+				 (unsigned long long)start,
+				 (unsigned long long)length,
+				 error);
+		bio_put(bio);
+	}
+	blk_finish_plug(&plug);
+
+	return error;
+}
+
+static int
+xfs_trim_gather_rtextent(
+	struct xfs_mount		*mp,
+	struct xfs_trans		*tp,
+	const struct xfs_rtalloc_rec	*rec,
+	void				*priv)
+{
+	struct xfs_trim_rtdev		*tr = priv;
+	struct xfs_rtx_busy		*busyp;
+	xfs_rtblock_t			rbno, rlen;
+
+	if (rec->ar_startext > tr->stop_rtx) {
+		/*
+		 * If we've scanned a large number of rtbitmap blocks, update
+		 * the cursor to point at this extent so we restart the next
+		 * batch from this extent.
+		 */
+		tr->restart_rtx = rec->ar_startext;
+		return -ECANCELED;
+	}
+
+	rbno = xfs_rtx_to_rtb(mp, rec->ar_startext);
+	rlen = xfs_rtx_to_rtb(mp, rec->ar_extcount);
+
+	/* Ignore too small. */
+	if (rlen < tr->minlen_fsb) {
+		trace_xfs_discard_rttoosmall(mp, rbno, rlen);
+		return 0;
+	}
+
+	busyp = kzalloc(sizeof(struct xfs_rtx_busy), GFP_KERNEL);
+	if (!busyp)
+		return -ENOMEM;
+
+	busyp->bno = rbno;
+	busyp->length = rlen;
+	INIT_LIST_HEAD(&busyp->list);
+	list_add_tail(&busyp->list, &tr->extent_list);
+	*tr->blocks_trimmed += rlen;
+
+	tr->restart_rtx = rec->ar_startext + rec->ar_extcount;
+	return 0;
+}
+
+static int
+xfs_trim_rtdev_extents(
+	struct xfs_mount	*mp,
+	xfs_daddr_t		start,
+	xfs_daddr_t		end,
+	xfs_daddr_t		minlen,
+	uint64_t		*blocks_trimmed)
+{
+	struct xfs_rtalloc_rec	low = { };
+	struct xfs_rtalloc_rec	high = { };
+	struct xfs_trim_rtdev	tr = {
+		.blocks_trimmed	= blocks_trimmed,
+		.minlen_fsb	= XFS_BB_TO_FSB(mp, minlen),
+	};
+	struct xfs_trans	*tp;
+	xfs_daddr_t		rtdev_daddr;
+	int			error;
+
+	INIT_LIST_HEAD(&tr.extent_list);
+
+	/* Shift the start and end downwards to match the rt device. */
+	rtdev_daddr = XFS_FSB_TO_BB(mp, mp->m_sb.sb_dblocks);
+	if (start > rtdev_daddr)
+		start -= rtdev_daddr;
+	else
+		start = 0;
+
+	if (end <= rtdev_daddr)
+		return 0;
+	end -= rtdev_daddr;
+
+	error = xfs_trans_alloc_empty(mp, &tp);
+	if (error)
+		return error;
+
+	end = min_t(xfs_daddr_t, end,
+			XFS_FSB_TO_BB(mp, mp->m_sb.sb_rblocks) - 1);
+
+	/* Convert the rt blocks to rt extents */
+	low.ar_startext = xfs_rtb_to_rtxup(mp, XFS_BB_TO_FSB(mp, start));
+	high.ar_startext = xfs_rtb_to_rtx(mp, XFS_BB_TO_FSBT(mp, end));
+
+	/*
+	 * Walk the free ranges between low and high.  The query_range function
+	 * trims the extents returned.
+	 */
+	do {
+		tr.stop_rtx = low.ar_startext + (mp->m_sb.sb_blocksize * NBBY);
+		xfs_rtbitmap_lock_shared(mp, XFS_RBMLOCK_BITMAP);
+		error = xfs_rtalloc_query_range(mp, tp, &low, &high,
+				xfs_trim_gather_rtextent, &tr);
+
+		if (error == -ECANCELED)
+			error = 0;
+		if (error) {
+			xfs_rtbitmap_unlock_shared(mp, XFS_RBMLOCK_BITMAP);
+			xfs_discard_free_rtdev_extents(&tr);
+			break;
+		}
+
+		if (list_empty(&tr.extent_list)) {
+			xfs_rtbitmap_unlock_shared(mp, XFS_RBMLOCK_BITMAP);
+			break;
+		}
+
+		error = xfs_discard_rtdev_extents(mp, &tr);
+		xfs_rtbitmap_unlock_shared(mp, XFS_RBMLOCK_BITMAP);
+		if (error)
+			break;
+
+		low.ar_startext = tr.restart_rtx;
+	} while (!xfs_trim_should_stop() && low.ar_startext <= high.ar_startext);
+
+	xfs_trans_cancel(tp);
+	return error;
+}
+#else
+# define xfs_trim_rtdev_extents(m,s,e,n,b)	(-EOPNOTSUPP)
+#endif /* CONFIG_XFS_RT */
+
 /*
  * trim a range of the filesystem.
  *
@@ -391,28 +645,37 @@ xfs_trim_extents(
  * addressing. FSB addressing is sparse (AGNO|AGBNO), while the incoming format
  * is a linear address range. Hence we need to use DADDR based conversions and
  * comparisons for determining the correct offset and regions to trim.
+ *
+ * The realtime device is mapped into the FITRIM "address space" immediately
+ * after the data device.
  */
 int
 xfs_ioc_trim(
 	struct xfs_mount		*mp,
 	struct fstrim_range __user	*urange)
 {
-	struct xfs_perag	*pag;
 	unsigned int		granularity =
 		bdev_discard_granularity(mp->m_ddev_targp->bt_bdev);
+	struct block_device	*rt_bdev = NULL;
 	struct fstrim_range	range;
 	xfs_daddr_t		start, end;
 	xfs_extlen_t		minlen;
-	xfs_agnumber_t		start_agno, end_agno;
-	xfs_agblock_t		start_agbno, end_agbno;
+	xfs_rfsblock_t		max_blocks;
 	uint64_t		blocks_trimmed = 0;
 	int			error, last_error = 0;
 
 	if (!capable(CAP_SYS_ADMIN))
 		return -EPERM;
-	if (!bdev_max_discard_sectors(mp->m_ddev_targp->bt_bdev))
+	if (mp->m_rtdev_targp &&
+	    bdev_max_discard_sectors(mp->m_rtdev_targp->bt_bdev))
+		rt_bdev = mp->m_rtdev_targp->bt_bdev;
+	if (!bdev_max_discard_sectors(mp->m_ddev_targp->bt_bdev) && !rt_bdev)
 		return -EOPNOTSUPP;
 
+	if (rt_bdev)
+		granularity = max(granularity,
+				  bdev_discard_granularity(rt_bdev));
+
 	/*
 	 * We haven't recovered the log, so we cannot use our bnobt-guided
 	 * storage zapping commands.
@@ -433,35 +696,27 @@ xfs_ioc_trim(
 	 * used by the fstrim application.  In the end it really doesn't
 	 * matter as trimming blocks is an advisory interface.
 	 */
-	if (range.start >= XFS_FSB_TO_B(mp, mp->m_sb.sb_dblocks) ||
+	max_blocks = mp->m_sb.sb_dblocks + mp->m_sb.sb_rblocks;
+	if (range.start >= XFS_FSB_TO_B(mp, max_blocks) ||
 	    range.minlen > XFS_FSB_TO_B(mp, mp->m_ag_max_usable) ||
 	    range.len < mp->m_sb.sb_blocksize)
 		return -EINVAL;
 
 	start = BTOBB(range.start);
-	end = min_t(xfs_daddr_t, start + BTOBBT(range.len),
-		    XFS_FSB_TO_BB(mp, mp->m_sb.sb_dblocks)) - 1;
+	end = start + BTOBBT(range.len) - 1;
 
-	start_agno = xfs_daddr_to_agno(mp, start);
-	start_agbno = xfs_daddr_to_agbno(mp, start);
-	end_agno = xfs_daddr_to_agno(mp, end);
-	end_agbno = xfs_daddr_to_agbno(mp, end);
-
-	for_each_perag_range(mp, start_agno, end_agno, pag) {
-		xfs_agblock_t	agend = pag->block_count;
-
-		if (start_agno == end_agno)
-			agend = end_agbno;
-		error = xfs_trim_extents(pag, start_agbno, agend, minlen,
+	if (bdev_max_discard_sectors(mp->m_ddev_targp->bt_bdev)) {
+		error = xfs_trim_datadev_extents(mp, start, end, minlen,
 				&blocks_trimmed);
 		if (error)
 			last_error = error;
+	}
 
-		if (xfs_trim_should_stop()) {
-			xfs_perag_rele(pag);
-			break;
-		}
-		start_agbno = 0;
+	if (rt_bdev && !xfs_trim_should_stop()) {
+		error = xfs_trim_rtdev_extents(mp, start, end, minlen,
+				&blocks_trimmed);
+		if (error)
+			last_error = error;
 	}
 
 	if (last_error)