1 files changed, 227 insertions, 211 deletions

diff --git a/fs/xfs/xfs_icache.c b/fs/xfs/xfs_icache.c
index deb99300d171..1d7720a0c068 100644
--- a/fs/xfs/xfs_icache.c
+++ b/fs/xfs/xfs_icache.c
@@ -916,69 +916,6 @@ xfs_inode_walk(
 }
 
 /*
- * Background scanning to trim post-EOF preallocated space. This is queued
- * based on the 'speculative_prealloc_lifetime' tunable (5m by default).
- */
-void
-xfs_queue_eofblocks(
-	struct xfs_mount *mp)
-{
-	rcu_read_lock();
-	if (radix_tree_tagged(&mp->m_perag_tree, XFS_ICI_EOFBLOCKS_TAG))
-		queue_delayed_work(mp->m_eofblocks_workqueue,
-				   &mp->m_eofblocks_work,
-				   msecs_to_jiffies(xfs_eofb_secs * 1000));
-	rcu_read_unlock();
-}
-
-void
-xfs_eofblocks_worker(
-	struct work_struct *work)
-{
-	struct xfs_mount *mp = container_of(to_delayed_work(work),
-				struct xfs_mount, m_eofblocks_work);
-
-	if (!sb_start_write_trylock(mp->m_super))
-		return;
-	xfs_icache_free_eofblocks(mp, NULL);
-	sb_end_write(mp->m_super);
-
-	xfs_queue_eofblocks(mp);
-}
-
-/*
- * Background scanning to trim preallocated CoW space. This is queued
- * based on the 'speculative_cow_prealloc_lifetime' tunable (5m by default).
- * (We'll just piggyback on the post-EOF prealloc space workqueue.)
- */
-void
-xfs_queue_cowblocks(
-	struct xfs_mount *mp)
-{
-	rcu_read_lock();
-	if (radix_tree_tagged(&mp->m_perag_tree, XFS_ICI_COWBLOCKS_TAG))
-		queue_delayed_work(mp->m_eofblocks_workqueue,
-				   &mp->m_cowblocks_work,
-				   msecs_to_jiffies(xfs_cowb_secs * 1000));
-	rcu_read_unlock();
-}
-
-void
-xfs_cowblocks_worker(
-	struct work_struct *work)
-{
-	struct xfs_mount *mp = container_of(to_delayed_work(work),
-				struct xfs_mount, m_cowblocks_work);
-
-	if (!sb_start_write_trylock(mp->m_super))
-		return;
-	xfs_icache_free_cowblocks(mp, NULL);
-	sb_end_write(mp->m_super);
-
-	xfs_queue_cowblocks(mp);
-}
-
-/*
  * Grab the inode for reclaim exclusively.
  *
  * We have found this inode via a lookup under RCU, so the inode may have
@@ -1346,14 +1283,17 @@ xfs_reclaim_worker(
 STATIC int
 xfs_inode_free_eofblocks(
 	struct xfs_inode	*ip,
-	void			*args)
+	void			*args,
+	unsigned int		*lockflags)
 {
 	struct xfs_eofblocks	*eofb = args;
 	bool			wait;
-	int			ret;
 
 	wait = eofb && (eofb->eof_flags & XFS_EOF_FLAGS_SYNC);
 
+	if (!xfs_iflags_test(ip, XFS_IEOFBLOCKS))
+		return 0;
+
 	if (!xfs_can_free_eofblocks(ip, false)) {
 		/* inode could be preallocated or append-only */
 		trace_xfs_inode_free_eofblocks_invalid(ip);
@@ -1380,130 +1320,68 @@ xfs_inode_free_eofblocks(
 			return -EAGAIN;
 		return 0;
 	}
+	*lockflags |= XFS_IOLOCK_EXCL;
 
-	ret = xfs_free_eofblocks(ip);
-	xfs_iunlock(ip, XFS_IOLOCK_EXCL);
-
-	return ret;
-}
-
-int
-xfs_icache_free_eofblocks(
-	struct xfs_mount	*mp,
-	struct xfs_eofblocks	*eofb)
-{
-	return xfs_inode_walk(mp, 0, xfs_inode_free_eofblocks, eofb,
-			XFS_ICI_EOFBLOCKS_TAG);
+	return xfs_free_eofblocks(ip);
 }
 
 /*
- * Run eofblocks scans on the quotas applicable to the inode. For inodes with
- * multiple quotas, we don't know exactly which quota caused an allocation
- * failure. We make a best effort by including each quota under low free space
- * conditions (less than 1% free space) in the scan.
+ * Background scanning to trim preallocated space. This is queued based on the
+ * 'speculative_prealloc_lifetime' tunable (5m by default).
  */
-static int
-__xfs_inode_free_quota_eofblocks(
-	struct xfs_inode	*ip,
-	int			(*execute)(struct xfs_mount *mp,
-					   struct xfs_eofblocks	*eofb))
-{
-	int scan = 0;
-	struct xfs_eofblocks eofb = {0};
-	struct xfs_dquot *dq;
-
-	/*
-	 * Run a sync scan to increase effectiveness and use the union filter to
-	 * cover all applicable quotas in a single scan.
-	 */
-	eofb.eof_flags = XFS_EOF_FLAGS_UNION|XFS_EOF_FLAGS_SYNC;
-
-	if (XFS_IS_UQUOTA_ENFORCED(ip->i_mount)) {
-		dq = xfs_inode_dquot(ip, XFS_DQTYPE_USER);
-		if (dq && xfs_dquot_lowsp(dq)) {
-			eofb.eof_uid = VFS_I(ip)->i_uid;
-			eofb.eof_flags |= XFS_EOF_FLAGS_UID;
-			scan = 1;
-		}
-	}
-
-	if (XFS_IS_GQUOTA_ENFORCED(ip->i_mount)) {
-		dq = xfs_inode_dquot(ip, XFS_DQTYPE_GROUP);
-		if (dq && xfs_dquot_lowsp(dq)) {
-			eofb.eof_gid = VFS_I(ip)->i_gid;
-			eofb.eof_flags |= XFS_EOF_FLAGS_GID;
-			scan = 1;
-		}
-	}
-
-	if (scan)
-		execute(ip->i_mount, &eofb);
-
-	return scan;
-}
-
-int
-xfs_inode_free_quota_eofblocks(
-	struct xfs_inode *ip)
-{
-	return __xfs_inode_free_quota_eofblocks(ip, xfs_icache_free_eofblocks);
-}
-
-static inline unsigned long
-xfs_iflag_for_tag(
-	int		tag)
+static inline void
+xfs_blockgc_queue(
+	struct xfs_perag	*pag)
 {
-	switch (tag) {
-	case XFS_ICI_EOFBLOCKS_TAG:
-		return XFS_IEOFBLOCKS;
-	case XFS_ICI_COWBLOCKS_TAG:
-		return XFS_ICOWBLOCKS;
-	default:
-		ASSERT(0);
-		return 0;
-	}
+	rcu_read_lock();
+	if (radix_tree_tagged(&pag->pag_ici_root, XFS_ICI_BLOCKGC_TAG))
+		queue_delayed_work(pag->pag_mount->m_blockgc_workqueue,
+				   &pag->pag_blockgc_work,
+				   msecs_to_jiffies(xfs_blockgc_secs * 1000));
+	rcu_read_unlock();
 }
 
 static void
-__xfs_inode_set_blocks_tag(
-	xfs_inode_t	*ip,
-	void		(*execute)(struct xfs_mount *mp),
-	void		(*set_tp)(struct xfs_mount *mp, xfs_agnumber_t agno,
-				  int error, unsigned long caller_ip),
-	int		tag)
+xfs_blockgc_set_iflag(
+	struct xfs_inode	*ip,
+	unsigned long		iflag)
 {
-	struct xfs_mount *mp = ip->i_mount;
-	struct xfs_perag *pag;
-	int tagged;
+	struct xfs_mount	*mp = ip->i_mount;
+	struct xfs_perag	*pag;
+	int			tagged;
+
+	ASSERT((iflag & ~(XFS_IEOFBLOCKS | XFS_ICOWBLOCKS)) == 0);
 
 	/*
 	 * Don't bother locking the AG and looking up in the radix trees
 	 * if we already know that we have the tag set.
 	 */
-	if (ip->i_flags & xfs_iflag_for_tag(tag))
+	if (ip->i_flags & iflag)
 		return;
 	spin_lock(&ip->i_flags_lock);
-	ip->i_flags |= xfs_iflag_for_tag(tag);
+	ip->i_flags |= iflag;
 	spin_unlock(&ip->i_flags_lock);
 
 	pag = xfs_perag_get(mp, XFS_INO_TO_AGNO(mp, ip->i_ino));
 	spin_lock(&pag->pag_ici_lock);
 
-	tagged = radix_tree_tagged(&pag->pag_ici_root, tag);
+	tagged = radix_tree_tagged(&pag->pag_ici_root, XFS_ICI_BLOCKGC_TAG);
 	radix_tree_tag_set(&pag->pag_ici_root,
-			   XFS_INO_TO_AGINO(ip->i_mount, ip->i_ino), tag);
+			   XFS_INO_TO_AGINO(ip->i_mount, ip->i_ino),
+			   XFS_ICI_BLOCKGC_TAG);
 	if (!tagged) {
-		/* propagate the eofblocks tag up into the perag radix tree */
+		/* propagate the blockgc tag up into the perag radix tree */
 		spin_lock(&ip->i_mount->m_perag_lock);
 		radix_tree_tag_set(&ip->i_mount->m_perag_tree,
 				   XFS_INO_TO_AGNO(ip->i_mount, ip->i_ino),
-				   tag);
+				   XFS_ICI_BLOCKGC_TAG);
 		spin_unlock(&ip->i_mount->m_perag_lock);
 
 		/* kick off background trimming */
-		execute(ip->i_mount);
+		xfs_blockgc_queue(pag);
 
-		set_tp(ip->i_mount, pag->pag_agno, -1, _RET_IP_);
+		trace_xfs_perag_set_blockgc(ip->i_mount, pag->pag_agno, -1,
+				_RET_IP_);
 	}
 
 	spin_unlock(&pag->pag_ici_lock);
@@ -1515,38 +1393,43 @@ xfs_inode_set_eofblocks_tag(
 	xfs_inode_t	*ip)
 {
 	trace_xfs_inode_set_eofblocks_tag(ip);
-	return __xfs_inode_set_blocks_tag(ip, xfs_queue_eofblocks,
-			trace_xfs_perag_set_eofblocks,
-			XFS_ICI_EOFBLOCKS_TAG);
+	return xfs_blockgc_set_iflag(ip, XFS_IEOFBLOCKS);
 }
 
 static void
-__xfs_inode_clear_blocks_tag(
-	xfs_inode_t	*ip,
-	void		(*clear_tp)(struct xfs_mount *mp, xfs_agnumber_t agno,
-				    int error, unsigned long caller_ip),
-	int		tag)
+xfs_blockgc_clear_iflag(
+	struct xfs_inode	*ip,
+	unsigned long		iflag)
 {
-	struct xfs_mount *mp = ip->i_mount;
-	struct xfs_perag *pag;
+	struct xfs_mount	*mp = ip->i_mount;
+	struct xfs_perag	*pag;
+	bool			clear_tag;
+
+	ASSERT((iflag & ~(XFS_IEOFBLOCKS | XFS_ICOWBLOCKS)) == 0);
 
 	spin_lock(&ip->i_flags_lock);
-	ip->i_flags &= ~xfs_iflag_for_tag(tag);
+	ip->i_flags &= ~iflag;
+	clear_tag = (ip->i_flags & (XFS_IEOFBLOCKS | XFS_ICOWBLOCKS)) == 0;
 	spin_unlock(&ip->i_flags_lock);
 
+	if (!clear_tag)
+		return;
+
 	pag = xfs_perag_get(mp, XFS_INO_TO_AGNO(mp, ip->i_ino));
 	spin_lock(&pag->pag_ici_lock);
 
 	radix_tree_tag_clear(&pag->pag_ici_root,
-			     XFS_INO_TO_AGINO(ip->i_mount, ip->i_ino), tag);
-	if (!radix_tree_tagged(&pag->pag_ici_root, tag)) {
-		/* clear the eofblocks tag from the perag radix tree */
+			     XFS_INO_TO_AGINO(ip->i_mount, ip->i_ino),
+			     XFS_ICI_BLOCKGC_TAG);
+	if (!radix_tree_tagged(&pag->pag_ici_root, XFS_ICI_BLOCKGC_TAG)) {
+		/* clear the blockgc tag from the perag radix tree */
 		spin_lock(&ip->i_mount->m_perag_lock);
 		radix_tree_tag_clear(&ip->i_mount->m_perag_tree,
 				     XFS_INO_TO_AGNO(ip->i_mount, ip->i_ino),
-				     tag);
+				     XFS_ICI_BLOCKGC_TAG);
 		spin_unlock(&ip->i_mount->m_perag_lock);
-		clear_tp(ip->i_mount, pag->pag_agno, -1, _RET_IP_);
+		trace_xfs_perag_clear_blockgc(ip->i_mount, pag->pag_agno, -1,
+				_RET_IP_);
 	}
 
 	spin_unlock(&pag->pag_ici_lock);
@@ -1558,8 +1441,7 @@ xfs_inode_clear_eofblocks_tag(
 	xfs_inode_t	*ip)
 {
 	trace_xfs_inode_clear_eofblocks_tag(ip);
-	return __xfs_inode_clear_blocks_tag(ip,
-			trace_xfs_perag_clear_eofblocks, XFS_ICI_EOFBLOCKS_TAG);
+	return xfs_blockgc_clear_iflag(ip, XFS_IEOFBLOCKS);
 }
 
 /*
@@ -1609,20 +1491,42 @@ xfs_prep_free_cowblocks(
 STATIC int
 xfs_inode_free_cowblocks(
 	struct xfs_inode	*ip,
-	void			*args)
+	void			*args,
+	unsigned int		*lockflags)
 {
 	struct xfs_eofblocks	*eofb = args;
+	bool			wait;
 	int			ret = 0;
 
+	wait = eofb && (eofb->eof_flags & XFS_EOF_FLAGS_SYNC);
+
+	if (!xfs_iflags_test(ip, XFS_ICOWBLOCKS))
+		return 0;
+
 	if (!xfs_prep_free_cowblocks(ip))
 		return 0;
 
 	if (!xfs_inode_matches_eofb(ip, eofb))
 		return 0;
 
-	/* Free the CoW blocks */
-	xfs_ilock(ip, XFS_IOLOCK_EXCL);
-	xfs_ilock(ip, XFS_MMAPLOCK_EXCL);
+	/*
+	 * If the caller is waiting, return -EAGAIN to keep the background
+	 * scanner moving and revisit the inode in a subsequent pass.
+	 */
+	if (!(*lockflags & XFS_IOLOCK_EXCL) &&
+	    !xfs_ilock_nowait(ip, XFS_IOLOCK_EXCL)) {
+		if (wait)
+			return -EAGAIN;
+		return 0;
+	}
+	*lockflags |= XFS_IOLOCK_EXCL;
+
+	if (!xfs_ilock_nowait(ip, XFS_MMAPLOCK_EXCL)) {
+		if (wait)
+			return -EAGAIN;
+		return 0;
+	}
+	*lockflags |= XFS_MMAPLOCK_EXCL;
 
 	/*
 	 * Check again, nobody else should be able to dirty blocks or change
@@ -1630,37 +1534,15 @@ xfs_inode_free_cowblocks(
 	 */
 	if (xfs_prep_free_cowblocks(ip))
 		ret = xfs_reflink_cancel_cow_range(ip, 0, NULLFILEOFF, false);
-
-	xfs_iunlock(ip, XFS_MMAPLOCK_EXCL);
-	xfs_iunlock(ip, XFS_IOLOCK_EXCL);
-
 	return ret;
 }
 
-int
-xfs_icache_free_cowblocks(
-	struct xfs_mount	*mp,
-	struct xfs_eofblocks	*eofb)
-{
-	return xfs_inode_walk(mp, 0, xfs_inode_free_cowblocks, eofb,
-			XFS_ICI_COWBLOCKS_TAG);
-}
-
-int
-xfs_inode_free_quota_cowblocks(
-	struct xfs_inode *ip)
-{
-	return __xfs_inode_free_quota_eofblocks(ip, xfs_icache_free_cowblocks);
-}
-
 void
 xfs_inode_set_cowblocks_tag(
 	xfs_inode_t	*ip)
 {
 	trace_xfs_inode_set_cowblocks_tag(ip);
-	return __xfs_inode_set_blocks_tag(ip, xfs_queue_cowblocks,
-			trace_xfs_perag_set_cowblocks,
-			XFS_ICI_COWBLOCKS_TAG);
+	return xfs_blockgc_set_iflag(ip, XFS_ICOWBLOCKS);
 }
 
 void
@@ -1668,24 +1550,158 @@ xfs_inode_clear_cowblocks_tag(
 	xfs_inode_t	*ip)
 {
 	trace_xfs_inode_clear_cowblocks_tag(ip);
-	return __xfs_inode_clear_blocks_tag(ip,
-			trace_xfs_perag_clear_cowblocks, XFS_ICI_COWBLOCKS_TAG);
+	return xfs_blockgc_clear_iflag(ip, XFS_ICOWBLOCKS);
 }
 
+#define for_each_perag_tag(mp, next_agno, pag, tag) \
+	for ((next_agno) = 0, (pag) = xfs_perag_get_tag((mp), 0, (tag)); \
+		(pag) != NULL; \
+		(next_agno) = (pag)->pag_agno + 1, \
+		xfs_perag_put(pag), \
+		(pag) = xfs_perag_get_tag((mp), (next_agno), (tag)))
+
+
 /* Disable post-EOF and CoW block auto-reclamation. */
 void
-xfs_stop_block_reaping(
+xfs_blockgc_stop(
 	struct xfs_mount	*mp)
 {
-	cancel_delayed_work_sync(&mp->m_eofblocks_work);
-	cancel_delayed_work_sync(&mp->m_cowblocks_work);
+	struct xfs_perag	*pag;
+	xfs_agnumber_t		agno;
+
+	for_each_perag_tag(mp, agno, pag, XFS_ICI_BLOCKGC_TAG)
+		cancel_delayed_work_sync(&pag->pag_blockgc_work);
 }
 
 /* Enable post-EOF and CoW block auto-reclamation. */
 void
-xfs_start_block_reaping(
+xfs_blockgc_start(
 	struct xfs_mount	*mp)
 {
-	xfs_queue_eofblocks(mp);
-	xfs_queue_cowblocks(mp);
+	struct xfs_perag	*pag;
+	xfs_agnumber_t		agno;
+
+	for_each_perag_tag(mp, agno, pag, XFS_ICI_BLOCKGC_TAG)
+		xfs_blockgc_queue(pag);
+}
+
+/* Scan one incore inode for block preallocations that we can remove. */
+static int
+xfs_blockgc_scan_inode(
+	struct xfs_inode	*ip,
+	void			*args)
+{
+	unsigned int		lockflags = 0;
+	int			error;
+
+	error = xfs_inode_free_eofblocks(ip, args, &lockflags);
+	if (error)
+		goto unlock;
+
+	error = xfs_inode_free_cowblocks(ip, args, &lockflags);
+unlock:
+	if (lockflags)
+		xfs_iunlock(ip, lockflags);
+	return error;
+}
+
+/* Background worker that trims preallocated space. */
+void
+xfs_blockgc_worker(
+	struct work_struct	*work)
+{
+	struct xfs_perag	*pag = container_of(to_delayed_work(work),
+					struct xfs_perag, pag_blockgc_work);
+	struct xfs_mount	*mp = pag->pag_mount;
+	int			error;
+
+	if (!sb_start_write_trylock(mp->m_super))
+		return;
+	error = xfs_inode_walk_ag(pag, 0, xfs_blockgc_scan_inode, NULL,
+			XFS_ICI_BLOCKGC_TAG);
+	if (error)
+		xfs_info(mp, "AG %u preallocation gc worker failed, err=%d",
+				pag->pag_agno, error);
+	sb_end_write(mp->m_super);
+	xfs_blockgc_queue(pag);
+}
+
+/*
+ * Try to free space in the filesystem by purging eofblocks and cowblocks.
+ */
+int
+xfs_blockgc_free_space(
+	struct xfs_mount	*mp,
+	struct xfs_eofblocks	*eofb)
+{
+	trace_xfs_blockgc_free_space(mp, eofb, _RET_IP_);
+
+	return xfs_inode_walk(mp, 0, xfs_blockgc_scan_inode, eofb,
+			XFS_ICI_BLOCKGC_TAG);
+}
+
+/*
+ * Run cow/eofblocks scans on the supplied dquots.  We don't know exactly which
+ * quota caused an allocation failure, so we make a best effort by including
+ * each quota under low free space conditions (less than 1% free space) in the
+ * scan.
+ *
+ * Callers must not hold any inode's ILOCK.  If requesting a synchronous scan
+ * (XFS_EOF_FLAGS_SYNC), the caller also must not hold any inode's IOLOCK or
+ * MMAPLOCK.
+ */
+int
+xfs_blockgc_free_dquots(
+	struct xfs_mount	*mp,
+	struct xfs_dquot	*udqp,
+	struct xfs_dquot	*gdqp,
+	struct xfs_dquot	*pdqp,
+	unsigned int		eof_flags)
+{
+	struct xfs_eofblocks	eofb = {0};
+	bool			do_work = false;
+
+	if (!udqp && !gdqp && !pdqp)
+		return 0;
+
+	/*
+	 * Run a scan to free blocks using the union filter to cover all
+	 * applicable quotas in a single scan.
+	 */
+	eofb.eof_flags = XFS_EOF_FLAGS_UNION | eof_flags;
+
+	if (XFS_IS_UQUOTA_ENFORCED(mp) && udqp && xfs_dquot_lowsp(udqp)) {
+		eofb.eof_uid = make_kuid(mp->m_super->s_user_ns, udqp->q_id);
+		eofb.eof_flags |= XFS_EOF_FLAGS_UID;
+		do_work = true;
+	}
+
+	if (XFS_IS_UQUOTA_ENFORCED(mp) && gdqp && xfs_dquot_lowsp(gdqp)) {
+		eofb.eof_gid = make_kgid(mp->m_super->s_user_ns, gdqp->q_id);
+		eofb.eof_flags |= XFS_EOF_FLAGS_GID;
+		do_work = true;
+	}
+
+	if (XFS_IS_PQUOTA_ENFORCED(mp) && pdqp && xfs_dquot_lowsp(pdqp)) {
+		eofb.eof_prid = pdqp->q_id;
+		eofb.eof_flags |= XFS_EOF_FLAGS_PRID;
+		do_work = true;
+	}
+
+	if (!do_work)
+		return 0;
+
+	return xfs_blockgc_free_space(mp, &eofb);
+}
+
+/* Run cow/eofblocks scans on the quotas attached to the inode. */
+int
+xfs_blockgc_free_quota(
+	struct xfs_inode	*ip,
+	unsigned int		eof_flags)
+{
+	return xfs_blockgc_free_dquots(ip->i_mount,
+			xfs_inode_dquot(ip, XFS_DQTYPE_USER),
+			xfs_inode_dquot(ip, XFS_DQTYPE_GROUP),
+			xfs_inode_dquot(ip, XFS_DQTYPE_PROJ), eof_flags);
 }