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
  ...

1 files changed, 89 insertions, 40 deletions

diff --git a/fs/xfs/xfs_dquot.h b/fs/xfs/xfs_dquot.h
index 71e36c85e20b..282a65da93c7 100644
--- a/fs/xfs/xfs_dquot.h
+++ b/fs/xfs/xfs_dquot.h
@@ -27,26 +27,53 @@ enum {
 	XFS_QLOWSP_MAX
 };
 
+struct xfs_dquot_res {
+	/* Total resources allocated and reserved. */
+	xfs_qcnt_t		reserved;
+
+	/* Total resources allocated. */
+	xfs_qcnt_t		count;
+
+	/* Absolute and preferred limits. */
+	xfs_qcnt_t		hardlimit;
+	xfs_qcnt_t		softlimit;
+
+	/*
+	 * For root dquots, this is the default grace period, in seconds.
+	 * Otherwise, this is when the quota grace period expires,
+	 * in seconds since the Unix epoch.
+	 */
+	time64_t		timer;
+
+	/*
+	 * For root dquots, this is the maximum number of warnings that will
+	 * be issued for this quota type.  Otherwise, this is the number of
+	 * warnings issued against this quota.  Note that none of this is
+	 * implemented.
+	 */
+	xfs_qwarncnt_t		warnings;
+};
+
 /*
  * The incore dquot structure
  */
 struct xfs_dquot {
-	uint			dq_flags;
 	struct list_head	q_lru;
 	struct xfs_mount	*q_mount;
+	xfs_dqtype_t		q_type;
+	uint16_t		q_flags;
+	xfs_dqid_t		q_id;
 	uint			q_nrefs;
-	xfs_daddr_t		q_blkno;
 	int			q_bufoffset;
+	xfs_daddr_t		q_blkno;
 	xfs_fileoff_t		q_fileoffset;
 
-	struct xfs_disk_dquot	q_core;
+	struct xfs_dquot_res	q_blk;	/* regular blocks */
+	struct xfs_dquot_res	q_ino;	/* inodes */
+	struct xfs_dquot_res	q_rtb;	/* realtime blocks */
+
 	struct xfs_dq_logitem	q_logitem;
-	/* total regular nblks used+reserved */
-	xfs_qcnt_t		q_res_bcount;
-	/* total inos allocd+reserved */
-	xfs_qcnt_t		q_res_icount;
-	/* total realtime blks used+reserved */
-	xfs_qcnt_t		q_res_rtbcount;
+
 	xfs_qcnt_t		q_prealloc_lo_wmark;
 	xfs_qcnt_t		q_prealloc_hi_wmark;
 	int64_t			q_low_space[XFS_QLOWSP_MAX];
@@ -101,34 +128,59 @@ static inline void xfs_dqunlock(struct xfs_dquot *dqp)
 	mutex_unlock(&dqp->q_qlock);
 }
 
-static inline int xfs_this_quota_on(struct xfs_mount *mp, int type)
+static inline int
+xfs_dquot_type(const struct xfs_dquot *dqp)
 {
-	switch (type & XFS_DQ_ALLTYPES) {
-	case XFS_DQ_USER:
+	return dqp->q_type & XFS_DQTYPE_REC_MASK;
+}
+
+static inline int xfs_this_quota_on(struct xfs_mount *mp, xfs_dqtype_t type)
+{
+	switch (type) {
+	case XFS_DQTYPE_USER:
 		return XFS_IS_UQUOTA_ON(mp);
-	case XFS_DQ_GROUP:
+	case XFS_DQTYPE_GROUP:
 		return XFS_IS_GQUOTA_ON(mp);
-	case XFS_DQ_PROJ:
+	case XFS_DQTYPE_PROJ:
 		return XFS_IS_PQUOTA_ON(mp);
 	default:
 		return 0;
 	}
 }
 
-static inline struct xfs_dquot *xfs_inode_dquot(struct xfs_inode *ip, int type)
+static inline struct xfs_dquot *xfs_inode_dquot(
+	struct xfs_inode	*ip,
+	xfs_dqtype_t		type)
 {
-	switch (type & XFS_DQ_ALLTYPES) {
-	case XFS_DQ_USER:
+	switch (type) {
+	case XFS_DQTYPE_USER:
 		return ip->i_udquot;
-	case XFS_DQ_GROUP:
+	case XFS_DQTYPE_GROUP:
 		return ip->i_gdquot;
-	case XFS_DQ_PROJ:
+	case XFS_DQTYPE_PROJ:
 		return ip->i_pdquot;
 	default:
 		return NULL;
 	}
 }
 
+/* Decide if the dquot's limits are actually being enforced. */
+static inline bool
+xfs_dquot_is_enforced(
+	const struct xfs_dquot	*dqp)
+{
+	switch (xfs_dquot_type(dqp)) {
+	case XFS_DQTYPE_USER:
+		return XFS_IS_UQUOTA_ENFORCED(dqp->q_mount);
+	case XFS_DQTYPE_GROUP:
+		return XFS_IS_GQUOTA_ENFORCED(dqp->q_mount);
+	case XFS_DQTYPE_PROJ:
+		return XFS_IS_PQUOTA_ENFORCED(dqp->q_mount);
+	}
+	ASSERT(0);
+	return false;
+}
+
 /*
  * Check whether a dquot is under low free space conditions. We assume the quota
  * is enabled and enforced.
@@ -137,38 +189,35 @@ static inline bool xfs_dquot_lowsp(struct xfs_dquot *dqp)
 {
 	int64_t freesp;
 
-	freesp = be64_to_cpu(dqp->q_core.d_blk_hardlimit) - dqp->q_res_bcount;
+	freesp = dqp->q_blk.hardlimit - dqp->q_blk.reserved;
 	if (freesp < dqp->q_low_space[XFS_QLOWSP_1_PCNT])
 		return true;
 
 	return false;
 }
 
+void xfs_dquot_to_disk(struct xfs_disk_dquot *ddqp, struct xfs_dquot *dqp);
+
 #define XFS_DQ_IS_LOCKED(dqp)	(mutex_is_locked(&((dqp)->q_qlock)))
-#define XFS_DQ_IS_DIRTY(dqp)	((dqp)->dq_flags & XFS_DQ_DIRTY)
-#define XFS_QM_ISUDQ(dqp)	((dqp)->dq_flags & XFS_DQ_USER)
-#define XFS_QM_ISPDQ(dqp)	((dqp)->dq_flags & XFS_DQ_PROJ)
-#define XFS_QM_ISGDQ(dqp)	((dqp)->dq_flags & XFS_DQ_GROUP)
+#define XFS_DQ_IS_DIRTY(dqp)	((dqp)->q_flags & XFS_DQFLAG_DIRTY)
 
 void		xfs_qm_dqdestroy(struct xfs_dquot *dqp);
 int		xfs_qm_dqflush(struct xfs_dquot *dqp, struct xfs_buf **bpp);
 void		xfs_qm_dqunpin_wait(struct xfs_dquot *dqp);
-void		xfs_qm_adjust_dqtimers(struct xfs_mount *mp,
-						struct xfs_dquot *d);
-void		xfs_qm_adjust_dqlimits(struct xfs_mount *mp,
-						struct xfs_dquot *d);
-xfs_dqid_t	xfs_qm_id_for_quotatype(struct xfs_inode *ip, uint type);
+void		xfs_qm_adjust_dqtimers(struct xfs_dquot *d);
+void		xfs_qm_adjust_dqlimits(struct xfs_dquot *d);
+xfs_dqid_t	xfs_qm_id_for_quotatype(struct xfs_inode *ip,
+				xfs_dqtype_t type);
 int		xfs_qm_dqget(struct xfs_mount *mp, xfs_dqid_t id,
-					uint type, bool can_alloc,
-					struct xfs_dquot **dqpp);
-int		xfs_qm_dqget_inode(struct xfs_inode *ip, uint type,
-						bool can_alloc,
-						struct xfs_dquot **dqpp);
+				xfs_dqtype_t type, bool can_alloc,
+				struct xfs_dquot **dqpp);
+int		xfs_qm_dqget_inode(struct xfs_inode *ip, xfs_dqtype_t type,
+				bool can_alloc, struct xfs_dquot **dqpp);
 int		xfs_qm_dqget_next(struct xfs_mount *mp, xfs_dqid_t id,
-					uint type, struct xfs_dquot **dqpp);
+				xfs_dqtype_t type, struct xfs_dquot **dqpp);
 int		xfs_qm_dqget_uncached(struct xfs_mount *mp,
-						xfs_dqid_t id, uint type,
-						struct xfs_dquot **dqpp);
+				xfs_dqid_t id, xfs_dqtype_t type,
+				struct xfs_dquot **dqpp);
 void		xfs_qm_dqput(struct xfs_dquot *dqp);
 
 void		xfs_dqlock2(struct xfs_dquot *, struct xfs_dquot *);
@@ -183,9 +232,9 @@ static inline struct xfs_dquot *xfs_qm_dqhold(struct xfs_dquot *dqp)
 	return dqp;
 }
 
-typedef int (*xfs_qm_dqiterate_fn)(struct xfs_dquot *dq, uint dqtype,
-		void *priv);
-int xfs_qm_dqiterate(struct xfs_mount *mp, uint dqtype,
+typedef int (*xfs_qm_dqiterate_fn)(struct xfs_dquot *dq,
+		xfs_dqtype_t type, void *priv);
+int xfs_qm_dqiterate(struct xfs_mount *mp, xfs_dqtype_t type,
 		xfs_qm_dqiterate_fn iter_fn, void *priv);
 
 #endif /* __XFS_DQUOT_H__ */