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, 175 insertions, 2 deletions

diff --git a/fs/xfs/xfs_log_cil.c b/fs/xfs/xfs_log_cil.c
index f51cbc6405c1..391a938d690c 100644
--- a/fs/xfs/xfs_log_cil.c
+++ b/fs/xfs/xfs_log_cil.c
@@ -694,6 +694,180 @@ xlog_cil_insert_items(
 	}
 }
 
+static inline void
+xlog_cil_ail_insert_batch(
+	struct xfs_ail		*ailp,
+	struct xfs_ail_cursor	*cur,
+	struct xfs_log_item	**log_items,
+	int			nr_items,
+	xfs_lsn_t		commit_lsn)
+{
+	int	i;
+
+	spin_lock(&ailp->ail_lock);
+	/* xfs_trans_ail_update_bulk drops ailp->ail_lock */
+	xfs_trans_ail_update_bulk(ailp, cur, log_items, nr_items, commit_lsn);
+
+	for (i = 0; i < nr_items; i++) {
+		struct xfs_log_item *lip = log_items[i];
+
+		if (lip->li_ops->iop_unpin)
+			lip->li_ops->iop_unpin(lip, 0);
+	}
+}
+
+/*
+ * Take the checkpoint's log vector chain of items and insert the attached log
+ * items into the AIL. This uses bulk insertion techniques to minimise AIL lock
+ * traffic.
+ *
+ * The AIL tracks log items via the start record LSN of the checkpoint,
+ * not the commit record LSN. This is because we can pipeline multiple
+ * checkpoints, and so the start record of checkpoint N+1 can be
+ * written before the commit record of checkpoint N. i.e:
+ *
+ *   start N			commit N
+ *	+-------------+------------+----------------+
+ *		  start N+1			commit N+1
+ *
+ * The tail of the log cannot be moved to the LSN of commit N when all
+ * the items of that checkpoint are written back, because then the
+ * start record for N+1 is no longer in the active portion of the log
+ * and recovery will fail/corrupt the filesystem.
+ *
+ * Hence when all the log items in checkpoint N are written back, the
+ * tail of the log most now only move as far forwards as the start LSN
+ * of checkpoint N+1.
+ *
+ * If we are called with the aborted flag set, it is because a log write during
+ * a CIL checkpoint commit has failed. In this case, all the items in the
+ * checkpoint have already gone through iop_committed and iop_committing, which
+ * means that checkpoint commit abort handling is treated exactly the same as an
+ * iclog write error even though we haven't started any IO yet. Hence in this
+ * case all we need to do is iop_committed processing, followed by an
+ * iop_unpin(aborted) call.
+ *
+ * The AIL cursor is used to optimise the insert process. If commit_lsn is not
+ * at the end of the AIL, the insert cursor avoids the need to walk the AIL to
+ * find the insertion point on every xfs_log_item_batch_insert() call. This
+ * saves a lot of needless list walking and is a net win, even though it
+ * slightly increases that amount of AIL lock traffic to set it up and tear it
+ * down.
+ */
+static void
+xlog_cil_ail_insert(
+	struct xfs_cil_ctx	*ctx,
+	bool			aborted)
+{
+#define LOG_ITEM_BATCH_SIZE	32
+	struct xfs_ail		*ailp = ctx->cil->xc_log->l_ailp;
+	struct xfs_log_item	*log_items[LOG_ITEM_BATCH_SIZE];
+	struct xfs_log_vec	*lv;
+	struct xfs_ail_cursor	cur;
+	xfs_lsn_t		old_head;
+	int			i = 0;
+
+	/*
+	 * Update the AIL head LSN with the commit record LSN of this
+	 * checkpoint. As iclogs are always completed in order, this should
+	 * always be the same (as iclogs can contain multiple commit records) or
+	 * higher LSN than the current head. We do this before insertion of the
+	 * items so that log space checks during insertion will reflect the
+	 * space that this checkpoint has already consumed.  We call
+	 * xfs_ail_update_finish() so that tail space and space-based wakeups
+	 * will be recalculated appropriately.
+	 */
+	ASSERT(XFS_LSN_CMP(ctx->commit_lsn, ailp->ail_head_lsn) >= 0 ||
+			aborted);
+	spin_lock(&ailp->ail_lock);
+	xfs_trans_ail_cursor_last(ailp, &cur, ctx->start_lsn);
+	old_head = ailp->ail_head_lsn;
+	ailp->ail_head_lsn = ctx->commit_lsn;
+	/* xfs_ail_update_finish() drops the ail_lock */
+	xfs_ail_update_finish(ailp, NULLCOMMITLSN);
+
+	/*
+	 * We move the AIL head forwards to account for the space used in the
+	 * log before we remove that space from the grant heads. This prevents a
+	 * transient condition where reservation space appears to become
+	 * available on return, only for it to disappear again immediately as
+	 * the AIL head update accounts in the log tail space.
+	 */
+	smp_wmb();	/* paired with smp_rmb in xlog_grant_space_left */
+	xlog_grant_return_space(ailp->ail_log, old_head, ailp->ail_head_lsn);
+
+	/* unpin all the log items */
+	list_for_each_entry(lv, &ctx->lv_chain, lv_list) {
+		struct xfs_log_item	*lip = lv->lv_item;
+		xfs_lsn_t		item_lsn;
+
+		if (aborted)
+			set_bit(XFS_LI_ABORTED, &lip->li_flags);
+
+		if (lip->li_ops->flags & XFS_ITEM_RELEASE_WHEN_COMMITTED) {
+			lip->li_ops->iop_release(lip);
+			continue;
+		}
+
+		if (lip->li_ops->iop_committed)
+			item_lsn = lip->li_ops->iop_committed(lip,
+					ctx->start_lsn);
+		else
+			item_lsn = ctx->start_lsn;
+
+		/* item_lsn of -1 means the item needs no further processing */
+		if (XFS_LSN_CMP(item_lsn, (xfs_lsn_t)-1) == 0)
+			continue;
+
+		/*
+		 * if we are aborting the operation, no point in inserting the
+		 * object into the AIL as we are in a shutdown situation.
+		 */
+		if (aborted) {
+			ASSERT(xlog_is_shutdown(ailp->ail_log));
+			if (lip->li_ops->iop_unpin)
+				lip->li_ops->iop_unpin(lip, 1);
+			continue;
+		}
+
+		if (item_lsn != ctx->start_lsn) {
+
+			/*
+			 * Not a bulk update option due to unusual item_lsn.
+			 * Push into AIL immediately, rechecking the lsn once
+			 * we have the ail lock. Then unpin the item. This does
+			 * not affect the AIL cursor the bulk insert path is
+			 * using.
+			 */
+			spin_lock(&ailp->ail_lock);
+			if (XFS_LSN_CMP(item_lsn, lip->li_lsn) > 0)
+				xfs_trans_ail_update(ailp, lip, item_lsn);
+			else
+				spin_unlock(&ailp->ail_lock);
+			if (lip->li_ops->iop_unpin)
+				lip->li_ops->iop_unpin(lip, 0);
+			continue;
+		}
+
+		/* Item is a candidate for bulk AIL insert.  */
+		log_items[i++] = lv->lv_item;
+		if (i >= LOG_ITEM_BATCH_SIZE) {
+			xlog_cil_ail_insert_batch(ailp, &cur, log_items,
+					LOG_ITEM_BATCH_SIZE, ctx->start_lsn);
+			i = 0;
+		}
+	}
+
+	/* make sure we insert the remainder! */
+	if (i)
+		xlog_cil_ail_insert_batch(ailp, &cur, log_items, i,
+				ctx->start_lsn);
+
+	spin_lock(&ailp->ail_lock);
+	xfs_trans_ail_cursor_done(&cur);
+	spin_unlock(&ailp->ail_lock);
+}
+
 static void
 xlog_cil_free_logvec(
 	struct list_head	*lv_chain)
@@ -733,8 +907,7 @@ xlog_cil_committed(
 		spin_unlock(&ctx->cil->xc_push_lock);
 	}
 
-	xfs_trans_committed_bulk(ctx->cil->xc_log->l_ailp, &ctx->lv_chain,
-					ctx->start_lsn, abort);
+	xlog_cil_ail_insert(ctx, abort);
 
 	xfs_extent_busy_sort(&ctx->busy_extents.extent_list);
 	xfs_extent_busy_clear(mp, &ctx->busy_extents.extent_list,