Merge tag 'xfs-5.9-merge-7' of git://git.kernel.org/pub/scm/fs/xfs/xfs-linux

Pull xfs updates from Darrick Wong:
 "There are quite a few changes in this release, the most notable of
  which is that we've made inode flushing fully asynchronous, and we no
  longer block memory reclaim on this.

  Furthermore, we have fixed a long-standing bug in the quota code where
  soft limit warnings and inode limits were never tracked properly.

  Moving further down the line, the reflink control loops have been
  redesigned to behave more efficiently; and numerous small bugs have
  been fixed (see below). The xattr and quota code have been extensively
  refactored in preparation for more new features coming down the line.

  Finally, the behavior of DAX between ext4 and xfs has been stabilized,
  which gets us a step closer to removing the experimental tag from that
  feature.

  We have a few new contributors this time around. Welcome, all!

  I anticipate a second pull request next week for a few small bugfixes
  that have been trickling in, but this is it for big changes.

  Summary:

   - Fix some btree block pingponging problems when swapping extents

   - Redesign the reflink copy loop so that we only run one remapping
     operation per transaction. This helps us avoid running out of block
     reservation on highly deduped filesystems.

   - Take the MMAPLOCK around filemap_map_pages.

   - Make inode reclaim fully async so that we avoid stalling processes
     on flushing inodes to disk.

   - Reduce inode cluster buffer RMW cycles by attaching the buffer to
     dirty inodes so we won't let go of the cluster buffer when we know
     we're going to need it soon.

   - Add some more checks to the realtime bitmap file scrubber.

   - Don't trip false lockdep warnings in fs freeze.

   - Remove various redundant lines of code.

   - Remove unnecessary calls to xfs_perag_{get,put}.

   - Preserve I_VERSION state across remounts.

   - Fix an unmount hang due to AIL going to sleep with a non-empty
     delwri buffer list.

   - Fix an error in the inode allocation space reservation macro that
     caused regressions in generic/531.

   - Fix a potential livelock when dquot flush fails because the dquot
     buffer is locked.

   - Fix a miscalculation when reserving inode quota that could cause
     users to exceed a hardlimit.

   - Refactor struct xfs_dquot to use native types for incore fields
     instead of abusing the ondisk struct for this purpose. This will
     eventually enable proper y2038+ support, but for now it merely
     cleans up the quota function declarations.

   - Actually increment the quota softlimit warning counter so that soft
     failures turn into hard(er) failures when they exceed the softlimit
     warning counter limits set by the administrator.

   - Split incore dquot state flags into their own field and namespace,
     to avoid mixing them with quota type flags.

   - Create a new quota type flags namespace so that we can make it
     obvious when a quota function takes a quota type (user, group,
     project) as an argument.

   - Rename the ondisk dquot flags field to type, as that more
     accurately represents what we store in it.

   - Drop our bespoke memory allocation flags in favor of GFP_*.

   - Rearrange the xattr functions so that we no longer mix metadata
     updates and transaction management (e.g. rolling complex
     transactions) in the same functions. This work will prepare us for
     atomic xattr operations (itself a prerequisite for directory
     backrefs) in future release cycles.

   - Support FS_DAX_FL (aka FS_XFLAG_DAX) via GETFLAGS/SETFLAGS"

* tag 'xfs-5.9-merge-7' of git://git.kernel.org/pub/scm/fs/xfs/xfs-linux: (117 commits)
  fs/xfs: Support that ioctl(SETXFLAGS/GETXFLAGS) can set/get inode DAX on XFS.
  xfs: Lift -ENOSPC handler from xfs_attr_leaf_addname
  xfs: Simplify xfs_attr_node_addname
  xfs: Simplify xfs_attr_leaf_addname
  xfs: Add helper function xfs_attr_node_removename_rmt
  xfs: Add helper function xfs_attr_node_removename_setup
  xfs: Add remote block helper functions
  xfs: Add helper function xfs_attr_leaf_mark_incomplete
  xfs: Add helpers xfs_attr_is_shortform and xfs_attr_set_shortform
  xfs: Remove xfs_trans_roll in xfs_attr_node_removename
  xfs: Remove unneeded xfs_trans_roll_inode calls
  xfs: Add helper function xfs_attr_node_shrink
  xfs: Pull up xfs_attr_rmtval_invalidate
  xfs: Refactor xfs_attr_rmtval_remove
  xfs: Pull up trans roll in xfs_attr3_leaf_clearflag
  xfs: Factor out xfs_attr_rmtval_invalidate
  xfs: Pull up trans roll from xfs_attr3_leaf_setflag
  xfs: Refactor xfs_attr_try_sf_addname
  xfs: Split apart xfs_attr_leaf_addname
  xfs: Pull up trans handling in xfs_attr3_leaf_flipflags
  ...

Author: torvalds

fs/xfs/kmem.c

@@ -115,24 +115,3 @@ kmem_realloc(const void *old, size_t newsize, xfs_km_flags_t flags)
 		congestion_wait(BLK_RW_ASYNC, HZ/50);
 	} while (1);
 }
-
-void *
-kmem_zone_alloc(kmem_zone_t *zone, xfs_km_flags_t flags)
-{
-	int	retries = 0;
-	gfp_t	lflags = kmem_flags_convert(flags);
-	void	*ptr;
-
-	trace_kmem_zone_alloc(kmem_cache_size(zone), flags, _RET_IP_);
-	do {
-		ptr = kmem_cache_alloc(zone, lflags);
-		if (ptr || (flags & KM_MAYFAIL))
-			return ptr;
-		if (!(++retries % 100))
-			xfs_err(NULL,
-		"%s(%u) possible memory allocation deadlock in %s (mode:0x%x)",
-				current->comm, current->pid,
-				__func__, lflags);
-		congestion_wait(BLK_RW_ASYNC, HZ/50);
-	} while (1);
-}

fs/xfs/kmem.h

@@ -85,14 +85,6 @@ kmem_zalloc_large(size_t size, xfs_km_flags_t flags)
 #define kmem_zone	kmem_cache
 #define kmem_zone_t	struct kmem_cache
 
-extern void *kmem_zone_alloc(kmem_zone_t *, xfs_km_flags_t);
-
-static inline void *
-kmem_zone_zalloc(kmem_zone_t *zone, xfs_km_flags_t flags)
-{
-	return kmem_zone_alloc(zone, flags | KM_ZERO);
-}
-
 static inline struct page *
 kmem_to_page(void *addr)
 {

fs/xfs/libxfs/xfs_ag.c

@@ -563,7 +563,8 @@ xfs_ag_get_geometry(
 	error = xfs_alloc_read_agf(mp, NULL, agno, 0, &agf_bp);
 	if (error)
 		goto out_agi;
-	pag = xfs_perag_get(mp, agno);
+
+	pag = agi_bp->b_pag;
 
 	/* Fill out form. */
 	memset(ageo, 0, sizeof(*ageo));
@@ -583,7 +584,6 @@ xfs_ag_get_geometry(
 	xfs_ag_geom_health(pag, ageo);
 
 	/* Release resources. */
-	xfs_perag_put(pag);
 	xfs_buf_relse(agf_bp);
 out_agi:
 	xfs_buf_relse(agi_bp);

fs/xfs/libxfs/xfs_ag_resv.h

@@ -37,16 +37,4 @@ xfs_ag_resv_rmapbt_alloc(
 	xfs_perag_put(pag);
 }
 
-static inline void
-xfs_ag_resv_rmapbt_free(
-	struct xfs_mount	*mp,
-	xfs_agnumber_t		agno)
-{
-	struct xfs_perag	*pag;
-
-	pag = xfs_perag_get(mp, agno);
-	xfs_ag_resv_free_extent(pag, XFS_AG_RESV_RMAPBT, NULL, 1);
-	xfs_perag_put(pag);
-}
-
 #endif	/* __XFS_AG_RESV_H__ */

fs/xfs/libxfs/xfs_alloc.c

@@ -710,13 +710,12 @@ xfs_alloc_read_agfl(
 STATIC int
 xfs_alloc_update_counters(
 	struct xfs_trans	*tp,
-	struct xfs_perag	*pag,
 	struct xfs_buf		*agbp,
 	long			len)
 {
 	struct xfs_agf		*agf = agbp->b_addr;
 
-	pag->pagf_freeblks += len;
+	agbp->b_pag->pagf_freeblks += len;
 	be32_add_cpu(&agf->agf_freeblks, len);
 
 	xfs_trans_agblocks_delta(tp, len);
@@ -1175,8 +1174,7 @@ xfs_alloc_ag_vextent(
 	}
 
 	if (!args->wasfromfl) {
-		error = xfs_alloc_update_counters(args->tp, args->pag,
-						  args->agbp,
+		error = xfs_alloc_update_counters(args->tp, args->agbp,
 						  -((long)(args->len)));
 		if (error)
 			return error;
@@ -1887,7 +1885,6 @@ xfs_free_ag_extent(
 	enum xfs_ag_resv_type		type)
 {
 	struct xfs_mount		*mp;
-	struct xfs_perag		*pag;
 	struct xfs_btree_cur		*bno_cur;
 	struct xfs_btree_cur		*cnt_cur;
 	xfs_agblock_t			gtbno; /* start of right neighbor */
@@ -2167,10 +2164,8 @@ xfs_free_ag_extent(
 	/*
 	 * Update the freespace totals in the ag and superblock.
 	 */
-	pag = xfs_perag_get(mp, agno);
-	error = xfs_alloc_update_counters(tp, pag, agbp, len);
-	xfs_ag_resv_free_extent(pag, type, tp, len);
-	xfs_perag_put(pag);
+	error = xfs_alloc_update_counters(tp, agbp, len);
+	xfs_ag_resv_free_extent(agbp->b_pag, type, tp, len);
 	if (error)
 		goto error0;
 
@@ -2467,7 +2462,8 @@ xfs_defer_agfl_block(
 	ASSERT(xfs_bmap_free_item_zone != NULL);
 	ASSERT(oinfo != NULL);
 
-	new = kmem_zone_alloc(xfs_bmap_free_item_zone, 0);
+	new = kmem_cache_alloc(xfs_bmap_free_item_zone,
+			       GFP_KERNEL | __GFP_NOFAIL);
 	new->xefi_startblock = XFS_AGB_TO_FSB(mp, agno, agbno);
 	new->xefi_blockcount = 1;
 	new->xefi_oinfo = *oinfo;
@@ -2689,7 +2685,7 @@ xfs_alloc_get_freelist(
 	if (be32_to_cpu(agf->agf_flfirst) == xfs_agfl_size(mp))
 		agf->agf_flfirst = 0;
 
-	pag = xfs_perag_get(mp, be32_to_cpu(agf->agf_seqno));
+	pag = agbp->b_pag;
 	ASSERT(!pag->pagf_agflreset);
 	be32_add_cpu(&agf->agf_flcount, -1);
 	xfs_trans_agflist_delta(tp, -1);
@@ -2701,7 +2697,6 @@ xfs_alloc_get_freelist(
 		pag->pagf_btreeblks++;
 		logflags |= XFS_AGF_BTREEBLKS;
 	}
-	xfs_perag_put(pag);
 
 	xfs_alloc_log_agf(tp, agbp, logflags);
 	*bnop = bno;
@@ -2797,7 +2792,7 @@ xfs_alloc_put_freelist(
 	if (be32_to_cpu(agf->agf_fllast) == xfs_agfl_size(mp))
 		agf->agf_fllast = 0;
 
-	pag = xfs_perag_get(mp, be32_to_cpu(agf->agf_seqno));
+	pag = agbp->b_pag;
 	ASSERT(!pag->pagf_agflreset);
 	be32_add_cpu(&agf->agf_flcount, 1);
 	xfs_trans_agflist_delta(tp, 1);
@@ -2809,7 +2804,6 @@ xfs_alloc_put_freelist(
 		pag->pagf_btreeblks--;
 		logflags |= XFS_AGF_BTREEBLKS;
 	}
-	xfs_perag_put(pag);
 
 	xfs_alloc_log_agf(tp, agbp, logflags);
 
@@ -3006,7 +3000,7 @@ xfs_alloc_read_agf(
 	ASSERT(!(*bpp)->b_error);
 
 	agf = (*bpp)->b_addr;
-	pag = xfs_perag_get(mp, agno);
+	pag = (*bpp)->b_pag;
 	if (!pag->pagf_init) {
 		pag->pagf_freeblks = be32_to_cpu(agf->agf_freeblks);
 		pag->pagf_btreeblks = be32_to_cpu(agf->agf_btreeblks);
@@ -3034,7 +3028,6 @@ xfs_alloc_read_agf(
 		       be32_to_cpu(agf->agf_levels[XFS_BTNUM_CNTi]));
 	}
 #endif
-	xfs_perag_put(pag);
 	return 0;
 }
 

fs/xfs/libxfs/xfs_alloc_btree.c

@@ -38,16 +38,14 @@ xfs_allocbt_set_root(
 {
 	struct xfs_buf		*agbp = cur->bc_ag.agbp;
 	struct xfs_agf		*agf = agbp->b_addr;
-	xfs_agnumber_t		seqno = be32_to_cpu(agf->agf_seqno);
 	int			btnum = cur->bc_btnum;
-	struct xfs_perag	*pag = xfs_perag_get(cur->bc_mp, seqno);
+	struct xfs_perag	*pag = agbp->b_pag;
 
 	ASSERT(ptr->s != 0);
 
 	agf->agf_roots[btnum] = ptr->s;
 	be32_add_cpu(&agf->agf_levels[btnum], inc);
 	pag->pagf_levels[btnum] += inc;
-	xfs_perag_put(pag);
 
 	xfs_alloc_log_agf(cur->bc_tp, agbp, XFS_AGF_ROOTS | XFS_AGF_LEVELS);
 }
@@ -115,7 +113,6 @@ xfs_allocbt_update_lastrec(
 	int			reason)
 {
 	struct xfs_agf		*agf = cur->bc_ag.agbp->b_addr;
-	xfs_agnumber_t		seqno = be32_to_cpu(agf->agf_seqno);
 	struct xfs_perag	*pag;
 	__be32			len;
 	int			numrecs;
@@ -160,9 +157,8 @@ xfs_allocbt_update_lastrec(
 	}
 
 	agf->agf_longest = len;
-	pag = xfs_perag_get(cur->bc_mp, seqno);
+	pag = cur->bc_ag.agbp->b_pag;
 	pag->pagf_longest = be32_to_cpu(len);
-	xfs_perag_put(pag);
 	xfs_alloc_log_agf(cur->bc_tp, cur->bc_ag.agbp, XFS_AGF_LONGEST);
 }
 
@@ -484,7 +480,7 @@ xfs_allocbt_init_common(
 
 	ASSERT(btnum == XFS_BTNUM_BNO || btnum == XFS_BTNUM_CNT);
 
-	cur = kmem_zone_zalloc(xfs_btree_cur_zone, KM_NOFS);
+	cur = kmem_cache_zalloc(xfs_btree_cur_zone, GFP_NOFS | __GFP_NOFAIL);
 
 	cur->bc_tp = tp;
 	cur->bc_mp = mp;