Merge tag 'inode-walk-cleanups-5.14_2021-06-03' of...

Merge tag 'inode-walk-cleanups-5.14_2021-06-03' of https://git.kernel.org/pub/scm/linux/kernel/git/djwong/xfs-linux into xfs-5.14-merge2

xfs: clean up incore inode walk functions

This ambitious series aims to cleans up redundant inode walk code in
xfs_icache.c, hide implementation details of the quotaoff dquot release
code, and eliminates indirect function calls from incore inode walks.

The first thing it does is to move all the code that quotaoff calls to
release dquots from all incore inodes into xfs_icache.c.  Next, it
separates the goal of an inode walk from the actual radix tree tags that
may or may not be involved and drops the kludgy XFS_ICI_NO_TAG thing.
Finally, we split the speculative preallocation (blockgc) and quotaoff
dquot release code paths into separate functions so that we can keep the
implementations cohesive.

Christoph suggested last cycle that we 'simply' change quotaoff not to
allow deactivating quota entirely, but as these cleanups are to enable
one major change in behavior (deferred inode inactivation) I do not want
to add a second behavior change (quotaoff) as a dependency.

To be blunt: Additional cleanups are not in scope for this series.

Next, I made two observations about incore inode radix tree walks --
since there's a 1:1 mapping between the walk goal and the per-inode
processing function passed in, we can use the goal to make a direct call
to the processing function.  Furthermore, the only caller to supply a
nonzero iter_flags argument is quotaoff, and there's only one INEW flag.

From that observation, I concluded that it's quite possible to remove
two parameters from the xfs_inode_walk* function signatures -- the
iter_flags, and the execute function pointer.  The middle of the series
moves the INEW functionality into the one piece (quotaoff) that wants
it, and removes the indirect calls.

The final observation is that the inode reclaim walk loop is now almost
the same as xfs_inode_walk, so it's silly to maintain two copies.  Merge
the reclaim loop code into xfs_inode_walk.

Lastly, refactor the per-ag radix tagging functions since there's
duplicated code that can be consolidated.

This series is a prerequisite for the next two patchsets, since deferred
inode inactivation will add another inode radix tree tag and iterator
function to xfs_inode_walk.

v2: walk the vfs inode list when running quotaoff instead of the radix
    tree, then rework the (now completely internal) inode walk function
    to take the tag as the main parameter.
v3: merge the reclaim loop into xfs_inode_walk, then consolidate the
    radix tree tagging functions
v4: rebase to 5.13-rc4
v5: combine with the quotaoff patchset, reorder functions to minimize
    forward declarations, split inode walk goals from radix tree tags
    to reduce conceptual confusion
v6: start moving the inode cache code towards the xfs_icwalk prefix

* tag 'inode-walk-cleanups-5.14_2021-06-03' of https://git.kernel.org/pub/scm/linux/kernel/git/djwong/xfs-linux:
  xfs: refactor per-AG inode tagging functions
  xfs: merge xfs_reclaim_inodes_ag into xfs_inode_walk_ag
  xfs: pass struct xfs_eofblocks to the inode scan callback
  xfs: fix radix tree tag signs
  xfs: make the icwalk processing functions clean up the grab state
  xfs: clean up inode state flag tests in xfs_blockgc_igrab
  xfs: remove indirect calls from xfs_inode_walk{,_ag}
  xfs: remove iter_flags parameter from xfs_inode_walk_*
  xfs: move xfs_inew_wait call into xfs_dqrele_inode
  xfs: separate the dqrele_all inode grab logic from xfs_inode_walk_ag_grab
  xfs: pass the goal of the incore inode walk to xfs_inode_walk()
  xfs: rename xfs_inode_walk functions to xfs_icwalk
  xfs: move the inode walk functions further down
  xfs: detach inode dquots at the end of inactivation
  xfs: move the quotaoff dqrele inode walk into xfs_icache.c

[djwong: added variable names to function declarations while fixing
merge conflicts]
Signed-off-by: Darrick J. Wong <djwong@kernel.org>

fs/xfs/libxfs/xfs_ag.c

@@ -64,7 +64,7 @@ struct xfs_perag *
 xfs_perag_get_tag(
 	struct xfs_mount	*mp,
 	xfs_agnumber_t		first,
-	int			tag)
+	unsigned int		tag)
 {
 	struct xfs_perag	*pag;
 	int			found;

fs/xfs/libxfs/xfs_ag.h

@@ -106,12 +106,12 @@ struct xfs_perag {
 
 int xfs_initialize_perag(struct xfs_mount *mp, xfs_agnumber_t agcount,
 			xfs_agnumber_t *maxagi);
-int xfs_initialize_perag_data(struct xfs_mount *, xfs_agnumber_t);
+int xfs_initialize_perag_data(struct xfs_mount *mp, xfs_agnumber_t agno);
 void xfs_free_perag(struct xfs_mount *mp);
 
-struct xfs_perag *xfs_perag_get(struct xfs_mount *, xfs_agnumber_t);
-struct xfs_perag *xfs_perag_get_tag(struct xfs_mount *, xfs_agnumber_t,
-				   int tag);
+struct xfs_perag *xfs_perag_get(struct xfs_mount *mp, xfs_agnumber_t agno);
+struct xfs_perag *xfs_perag_get_tag(struct xfs_mount *mp, xfs_agnumber_t agno,
+		unsigned int tag);
 void xfs_perag_put(struct xfs_perag *pag);
 
 /*

fs/xfs/xfs_icache.h

@@ -15,17 +15,9 @@ struct xfs_eofblocks {
 	kgid_t		eof_gid;
 	prid_t		eof_prid;
 	__u64		eof_min_file_size;
+	int		icw_scan_limit;
 };
 
-/*
- * tags for inode radix tree
- */
-#define XFS_ICI_NO_TAG		(-1)	/* special flag for an untagged lookup
-					   in xfs_inode_walk */
-#define XFS_ICI_RECLAIM_TAG	0	/* inode is to be reclaimed */
-/* Inode has speculative preallocations (posteof or cow) to clean. */
-#define XFS_ICI_BLOCKGC_TAG	1
-
 /*
  * Flags for xfs_iget()
  */
@@ -34,11 +26,6 @@ struct xfs_eofblocks {
 #define XFS_IGET_DONTCACHE	0x4
 #define XFS_IGET_INCORE		0x8	/* don't read from disk or reinit */
 
-/*
- * flags for AG inode iterator
- */
-#define XFS_INODE_WALK_INEW_WAIT	0x1	/* wait on new inodes */
-
 int xfs_iget(struct xfs_mount *mp, struct xfs_trans *tp, xfs_ino_t ino,
 	     uint flags, uint lock_flags, xfs_inode_t **ipp);
 
@@ -52,7 +39,7 @@ void xfs_reclaim_inodes(struct xfs_mount *mp);
 int xfs_reclaim_inodes_count(struct xfs_mount *mp);
 long xfs_reclaim_inodes_nr(struct xfs_mount *mp, int nr_to_scan);
 
-void xfs_inode_set_reclaim_tag(struct xfs_inode *ip);
+void xfs_inode_mark_reclaimable(struct xfs_inode *ip);
 
 int xfs_blockgc_free_dquots(struct xfs_mount *mp, struct xfs_dquot *udqp,
 		struct xfs_dquot *gdqp, struct xfs_dquot *pdqp,
@@ -68,9 +55,11 @@ void xfs_inode_clear_cowblocks_tag(struct xfs_inode *ip);
 
 void xfs_blockgc_worker(struct work_struct *work);
 
-int xfs_inode_walk(struct xfs_mount *mp, int iter_flags,
-	int (*execute)(struct xfs_inode *ip, void *args),
-	void *args, int tag);
+#ifdef CONFIG_XFS_QUOTA
+int xfs_dqrele_all_inodes(struct xfs_mount *mp, unsigned int qflags);
+#else
+# define xfs_dqrele_all_inodes(mp, qflags)	(0)
+#endif
 
 int xfs_icache_inode_is_allocated(struct xfs_mount *mp, struct xfs_trans *tp,
 				  xfs_ino_t ino, bool *inuse);

fs/xfs/xfs_inode.c

@@ -1676,7 +1676,7 @@ xfs_inactive(
 	 */
 	if (VFS_I(ip)->i_mode == 0) {
 		ASSERT(ip->i_df.if_broot_bytes == 0);
-		return;
+		goto out;
 	}
 
 	mp = ip->i_mount;
@@ -1684,11 +1684,11 @@ xfs_inactive(
 
 	/* If this is a read-only mount, don't do this (would generate I/O) */
 	if (mp->m_flags & XFS_MOUNT_RDONLY)
-		return;
+		goto out;
 
 	/* Metadata inodes require explicit resource cleanup. */
 	if (xfs_is_metadata_inode(ip))
-		return;
+		goto out;
 
 	/* Try to clean out the cow blocks if there are any. */
 	if (xfs_inode_has_cow_data(ip))
@@ -1707,7 +1707,7 @@ xfs_inactive(
 		if (xfs_can_free_eofblocks(ip, true))
 			xfs_free_eofblocks(ip);
 
-		return;
+		goto out;
 	}
 
 	if (S_ISREG(VFS_I(ip)->i_mode) &&
@@ -1717,14 +1717,14 @@ xfs_inactive(
 
 	error = xfs_qm_dqattach(ip);
 	if (error)
-		return;
+		goto out;
 
 	if (S_ISLNK(VFS_I(ip)->i_mode))
 		error = xfs_inactive_symlink(ip);
 	else if (truncate)
 		error = xfs_inactive_truncate(ip);
 	if (error)
-		return;
+		goto out;
 
 	/*
 	 * If there are attributes associated with the file then blow them away
@@ -1734,7 +1734,7 @@ xfs_inactive(
 	if (XFS_IFORK_Q(ip)) {
 		error = xfs_attr_inactive(ip);
 		if (error)
-			return;
+			goto out;
 	}
 
 	ASSERT(!ip->i_afp);
@@ -1743,12 +1743,12 @@ xfs_inactive(
 	/*
 	 * Free the inode.
 	 */
-	error = xfs_inactive_ifree(ip);
-	if (error)
-		return;
+	xfs_inactive_ifree(ip);
 
+out:
 	/*
-	 * Release the dquots held by inode, if any.
+	 * We're done making metadata updates for this inode, so we can release
+	 * the attached dquots.
 	 */
 	xfs_qm_dqdetach(ip);
 }

fs/xfs/xfs_qm.h

@@ -142,7 +142,6 @@ extern void		xfs_qm_destroy_quotainfo(struct xfs_mount *);
 
 /* dquot stuff */
 extern void		xfs_qm_dqpurge_all(struct xfs_mount *, uint);
-extern void		xfs_qm_dqrele_all_inodes(struct xfs_mount *, uint);
 
 /* quota ops */
 extern int		xfs_qm_scall_trunc_qfiles(struct xfs_mount *, uint);

fs/xfs/xfs_qm_syscalls.c

@@ -201,7 +201,8 @@ xfs_qm_scall_quotaoff(
 	 * depend on the quota inodes (and other things) being valid as long as
 	 * we keep the lock(s).
 	 */
-	xfs_qm_dqrele_all_inodes(mp, flags);
+	error = xfs_dqrele_all_inodes(mp, flags);
+	ASSERT(!error);
 
 	/*
 	 * Next we make the changes in the quota flag in the mount struct.
@@ -747,54 +748,3 @@ xfs_qm_scall_getquota_next(
 	xfs_qm_dqput(dqp);
 	return error;
 }
-
-STATIC int
-xfs_dqrele_inode(
-	struct xfs_inode	*ip,
-	void			*args)
-{
-	uint			*flags = args;
-
-	/* skip quota inodes */
-	if (ip == ip->i_mount->m_quotainfo->qi_uquotaip ||
-	    ip == ip->i_mount->m_quotainfo->qi_gquotaip ||
-	    ip == ip->i_mount->m_quotainfo->qi_pquotaip) {
-		ASSERT(ip->i_udquot == NULL);
-		ASSERT(ip->i_gdquot == NULL);
-		ASSERT(ip->i_pdquot == NULL);
-		return 0;
-	}
-
-	xfs_ilock(ip, XFS_ILOCK_EXCL);
-	if ((*flags & XFS_UQUOTA_ACCT) && ip->i_udquot) {
-		xfs_qm_dqrele(ip->i_udquot);
-		ip->i_udquot = NULL;
-	}
-	if ((*flags & XFS_GQUOTA_ACCT) && ip->i_gdquot) {
-		xfs_qm_dqrele(ip->i_gdquot);
-		ip->i_gdquot = NULL;
-	}
-	if ((*flags & XFS_PQUOTA_ACCT) && ip->i_pdquot) {
-		xfs_qm_dqrele(ip->i_pdquot);
-		ip->i_pdquot = NULL;
-	}
-	xfs_iunlock(ip, XFS_ILOCK_EXCL);
-	return 0;
-}
-
-
-/*
- * Go thru all the inodes in the file system, releasing their dquots.
- *
- * Note that the mount structure gets modified to indicate that quotas are off
- * AFTER this, in the case of quotaoff.
- */
-void
-xfs_qm_dqrele_all_inodes(
-	struct xfs_mount	*mp,
-	uint			flags)
-{
-	ASSERT(mp->m_quotainfo);
-	xfs_inode_walk(mp, XFS_INODE_WALK_INEW_WAIT, xfs_dqrele_inode,
-			&flags, XFS_ICI_NO_TAG);
-}

fs/xfs/xfs_super.c

@@ -668,7 +668,7 @@ xfs_fs_destroy_inode(
 	 * reclaim path handles this more efficiently than we can here, so
 	 * simply let background reclaim tear down all inodes.
 	 */
-	xfs_inode_set_reclaim_tag(ip);
+	xfs_inode_mark_reclaimable(ip);
 }
 
 static void

fs/xfs/xfs_trace.h

@@ -153,10 +153,8 @@ DEFINE_EVENT(xfs_perag_class, name,	\
 DEFINE_PERAG_REF_EVENT(xfs_perag_get);
 DEFINE_PERAG_REF_EVENT(xfs_perag_get_tag);
 DEFINE_PERAG_REF_EVENT(xfs_perag_put);
-DEFINE_PERAG_REF_EVENT(xfs_perag_set_reclaim);
-DEFINE_PERAG_REF_EVENT(xfs_perag_clear_reclaim);
-DEFINE_PERAG_REF_EVENT(xfs_perag_set_blockgc);
-DEFINE_PERAG_REF_EVENT(xfs_perag_clear_blockgc);
+DEFINE_PERAG_REF_EVENT(xfs_perag_set_inode_tag);
+DEFINE_PERAG_REF_EVENT(xfs_perag_clear_inode_tag);
 
 DECLARE_EVENT_CLASS(xfs_ag_class,
 	TP_PROTO(struct xfs_mount *mp, xfs_agnumber_t agno),
@@ -3898,6 +3896,7 @@ DECLARE_EVENT_CLASS(xfs_eofblocks_class,
 		__field(uint32_t, gid)
 		__field(prid_t, prid)
 		__field(__u64, min_file_size)
+		__field(int, scan_limit)
 		__field(unsigned long, caller_ip)
 	),
 	TP_fast_assign(
@@ -3909,15 +3908,17 @@ DECLARE_EVENT_CLASS(xfs_eofblocks_class,
 						eofb->eof_gid) : 0;
 		__entry->prid = eofb ? eofb->eof_prid : 0;
 		__entry->min_file_size = eofb ? eofb->eof_min_file_size : 0;
+		__entry->scan_limit = eofb ? eofb->icw_scan_limit : 0;
 		__entry->caller_ip = caller_ip;
 	),
-	TP_printk("dev %d:%d flags 0x%x uid %u gid %u prid %u minsize %llu caller %pS",
+	TP_printk("dev %d:%d flags 0x%x uid %u gid %u prid %u minsize %llu scan_limit %d caller %pS",
 		  MAJOR(__entry->dev), MINOR(__entry->dev),
 		  __entry->flags,
 		  __entry->uid,
 		  __entry->gid,
 		  __entry->prid,
 		  __entry->min_file_size,
+		  __entry->scan_limit,
 		  (char *)__entry->caller_ip)
 );
 #define DEFINE_EOFBLOCKS_EVENT(name)	\