1 files changed, 69 insertions, 170 deletions

diff --git a/fs/xfs/libxfs/xfs_ag.c b/fs/xfs/libxfs/xfs_ag.c
index 1531bd0ee359..5ca8d0106827 100644
--- a/fs/xfs/libxfs/xfs_ag.c
+++ b/fs/xfs/libxfs/xfs_ag.c
@@ -46,7 +46,7 @@ xfs_perag_get(
 	struct xfs_perag	*pag;
 
 	rcu_read_lock();
-	pag = radix_tree_lookup(&mp->m_perag_tree, agno);
+	pag = xa_load(&mp->m_perags, agno);
 	if (pag) {
 		trace_xfs_perag_get(pag, _RET_IP_);
 		ASSERT(atomic_read(&pag->pag_ref) >= 0);
@@ -56,31 +56,6 @@ xfs_perag_get(
 	return pag;
 }
 
-/*
- * search from @first to find the next perag with the given tag set.
- */
-struct xfs_perag *
-xfs_perag_get_tag(
-	struct xfs_mount	*mp,
-	xfs_agnumber_t		first,
-	unsigned int		tag)
-{
-	struct xfs_perag	*pag;
-	int			found;
-
-	rcu_read_lock();
-	found = radix_tree_gang_lookup_tag(&mp->m_perag_tree,
-					(void **)&pag, first, 1, tag);
-	if (found <= 0) {
-		rcu_read_unlock();
-		return NULL;
-	}
-	trace_xfs_perag_get_tag(pag, _RET_IP_);
-	atomic_inc(&pag->pag_ref);
-	rcu_read_unlock();
-	return pag;
-}
-
 /* Get a passive reference to the given perag. */
 struct xfs_perag *
 xfs_perag_hold(
@@ -117,7 +92,7 @@ xfs_perag_grab(
 	struct xfs_perag	*pag;
 
 	rcu_read_lock();
-	pag = radix_tree_lookup(&mp->m_perag_tree, agno);
+	pag = xa_load(&mp->m_perags, agno);
 	if (pag) {
 		trace_xfs_perag_grab(pag, _RET_IP_);
 		if (!atomic_inc_not_zero(&pag->pag_active_ref))
@@ -127,32 +102,6 @@ xfs_perag_grab(
 	return pag;
 }
 
-/*
- * search from @first to find the next perag with the given tag set.
- */
-struct xfs_perag *
-xfs_perag_grab_tag(
-	struct xfs_mount	*mp,
-	xfs_agnumber_t		first,
-	int			tag)
-{
-	struct xfs_perag	*pag;
-	int			found;
-
-	rcu_read_lock();
-	found = radix_tree_gang_lookup_tag(&mp->m_perag_tree,
-					(void **)&pag, first, 1, tag);
-	if (found <= 0) {
-		rcu_read_unlock();
-		return NULL;
-	}
-	trace_xfs_perag_grab_tag(pag, _RET_IP_);
-	if (!atomic_inc_not_zero(&pag->pag_active_ref))
-		pag = NULL;
-	rcu_read_unlock();
-	return pag;
-}
-
 void
 xfs_perag_rele(
 	struct xfs_perag	*pag)
@@ -194,7 +143,7 @@ xfs_initialize_perag_data(
 		pag = xfs_perag_get(mp, index);
 		error = xfs_alloc_read_agf(pag, NULL, 0, NULL);
 		if (!error)
-			error = xfs_ialloc_read_agi(pag, NULL, NULL);
+			error = xfs_ialloc_read_agi(pag, NULL, 0, NULL);
 		if (error) {
 			xfs_perag_put(pag);
 			return error;
@@ -217,6 +166,7 @@ xfs_initialize_perag_data(
 	 */
 	if (fdblocks > sbp->sb_dblocks || ifree > ialloc) {
 		xfs_alert(mp, "AGF corruption. Please run xfs_repair.");
+		xfs_fs_mark_sick(mp, XFS_SICK_FS_COUNTERS);
 		error = -EFSCORRUPTED;
 		goto out;
 	}
@@ -234,42 +184,33 @@ out:
 	return error;
 }
 
-STATIC void
-__xfs_free_perag(
-	struct rcu_head	*head)
-{
-	struct xfs_perag *pag = container_of(head, struct xfs_perag, rcu_head);
-
-	ASSERT(!delayed_work_pending(&pag->pag_blockgc_work));
-	kmem_free(pag);
-}
-
 /*
- * Free up the per-ag resources associated with the mount structure.
+ * Free up the per-ag resources  within the specified AG range.
  */
 void
-xfs_free_perag(
-	struct xfs_mount	*mp)
+xfs_free_perag_range(
+	struct xfs_mount	*mp,
+	xfs_agnumber_t		first_agno,
+	xfs_agnumber_t		end_agno)
+
 {
-	struct xfs_perag	*pag;
 	xfs_agnumber_t		agno;
 
-	for (agno = 0; agno < mp->m_sb.sb_agcount; agno++) {
-		spin_lock(&mp->m_perag_lock);
-		pag = radix_tree_delete(&mp->m_perag_tree, agno);
-		spin_unlock(&mp->m_perag_lock);
+	for (agno = first_agno; agno < end_agno; agno++) {
+		struct xfs_perag	*pag = xa_erase(&mp->m_perags, agno);
+
 		ASSERT(pag);
 		XFS_IS_CORRUPT(pag->pag_mount, atomic_read(&pag->pag_ref) != 0);
 		xfs_defer_drain_free(&pag->pag_intents_drain);
 
 		cancel_delayed_work_sync(&pag->pag_blockgc_work);
-		xfs_buf_hash_destroy(pag);
+		xfs_buf_cache_destroy(&pag->pag_bcache);
 
 		/* drop the mount's active reference */
 		xfs_perag_rele(pag);
 		XFS_IS_CORRUPT(pag->pag_mount,
 				atomic_read(&pag->pag_active_ref) != 0);
-		call_rcu(&pag->rcu_head, __xfs_free_perag);
+		kfree_rcu_mightsleep(pag);
 	}
 }
 
@@ -332,56 +273,37 @@ xfs_agino_range(
 	return __xfs_agino_range(mp, xfs_ag_block_count(mp, agno), first, last);
 }
 
-/*
- * Free perag within the specified AG range, it is only used to free unused
- * perags under the error handling path.
- */
-void
-xfs_free_unused_perag_range(
+int
+xfs_update_last_ag_size(
 	struct xfs_mount	*mp,
-	xfs_agnumber_t		agstart,
-	xfs_agnumber_t		agend)
+	xfs_agnumber_t		prev_agcount)
 {
-	struct xfs_perag	*pag;
-	xfs_agnumber_t		index;
+	struct xfs_perag	*pag = xfs_perag_grab(mp, prev_agcount - 1);
 
-	for (index = agstart; index < agend; index++) {
-		spin_lock(&mp->m_perag_lock);
-		pag = radix_tree_delete(&mp->m_perag_tree, index);
-		spin_unlock(&mp->m_perag_lock);
-		if (!pag)
-			break;
-		xfs_buf_hash_destroy(pag);
-		xfs_defer_drain_free(&pag->pag_intents_drain);
-		kmem_free(pag);
-	}
+	if (!pag)
+		return -EFSCORRUPTED;
+	pag->block_count = __xfs_ag_block_count(mp, prev_agcount - 1,
+			mp->m_sb.sb_agcount, mp->m_sb.sb_dblocks);
+	__xfs_agino_range(mp, pag->block_count, &pag->agino_min,
+			&pag->agino_max);
+	xfs_perag_rele(pag);
+	return 0;
 }
 
 int
 xfs_initialize_perag(
 	struct xfs_mount	*mp,
-	xfs_agnumber_t		agcount,
+	xfs_agnumber_t		old_agcount,
+	xfs_agnumber_t		new_agcount,
 	xfs_rfsblock_t		dblocks,
 	xfs_agnumber_t		*maxagi)
 {
 	struct xfs_perag	*pag;
 	xfs_agnumber_t		index;
-	xfs_agnumber_t		first_initialised = NULLAGNUMBER;
 	int			error;
 
-	/*
-	 * Walk the current per-ag tree so we don't try to initialise AGs
-	 * that already exist (growfs case). Allocate and insert all the
-	 * AGs we don't find ready for initialisation.
-	 */
-	for (index = 0; index < agcount; index++) {
-		pag = xfs_perag_get(mp, index);
-		if (pag) {
-			xfs_perag_put(pag);
-			continue;
-		}
-
-		pag = kmem_zalloc(sizeof(*pag), KM_MAYFAIL);
+	for (index = old_agcount; index < new_agcount; index++) {
+		pag = kzalloc(sizeof(*pag), GFP_KERNEL);
 		if (!pag) {
 			error = -ENOMEM;
 			goto out_unwind_new_pags;
@@ -389,20 +311,11 @@ xfs_initialize_perag(
 		pag->pag_agno = index;
 		pag->pag_mount = mp;
 
-		error = radix_tree_preload(GFP_NOFS);
-		if (error)
-			goto out_free_pag;
-
-		spin_lock(&mp->m_perag_lock);
-		if (radix_tree_insert(&mp->m_perag_tree, index, pag)) {
-			WARN_ON_ONCE(1);
-			spin_unlock(&mp->m_perag_lock);
-			radix_tree_preload_end();
-			error = -EEXIST;
+		error = xa_insert(&mp->m_perags, index, pag, GFP_KERNEL);
+		if (error) {
+			WARN_ON_ONCE(error == -EBUSY);
 			goto out_free_pag;
 		}
-		spin_unlock(&mp->m_perag_lock);
-		radix_tree_preload_end();
 
 #ifdef __KERNEL__
 		/* Place kernel structure only init below this point. */
@@ -416,30 +329,27 @@ xfs_initialize_perag(
 		init_waitqueue_head(&pag->pag_active_wq);
 		pag->pagb_count = 0;
 		pag->pagb_tree = RB_ROOT;
+		xfs_hooks_init(&pag->pag_rmap_update_hooks);
 #endif /* __KERNEL__ */
 
-		error = xfs_buf_hash_init(pag);
+		error = xfs_buf_cache_init(&pag->pag_bcache);
 		if (error)
 			goto out_remove_pag;
 
 		/* Active ref owned by mount indicates AG is online. */
 		atomic_set(&pag->pag_active_ref, 1);
 
-		/* first new pag is fully initialized */
-		if (first_initialised == NULLAGNUMBER)
-			first_initialised = index;
-
 		/*
 		 * Pre-calculated geometry
 		 */
-		pag->block_count = __xfs_ag_block_count(mp, index, agcount,
+		pag->block_count = __xfs_ag_block_count(mp, index, new_agcount,
 				dblocks);
 		pag->min_block = XFS_AGFL_BLOCK(mp);
 		__xfs_agino_range(mp, pag->block_count, &pag->agino_min,
 				&pag->agino_max);
 	}
 
-	index = xfs_set_inode_alloc(mp, agcount);
+	index = xfs_set_inode_alloc(mp, new_agcount);
 
 	if (maxagi)
 		*maxagi = index;
@@ -449,14 +359,11 @@ xfs_initialize_perag(
 
 out_remove_pag:
 	xfs_defer_drain_free(&pag->pag_intents_drain);
-	spin_lock(&mp->m_perag_lock);
-	radix_tree_delete(&mp->m_perag_tree, index);
-	spin_unlock(&mp->m_perag_lock);
+	pag = xa_erase(&mp->m_perags, index);
 out_free_pag:
-	kmem_free(pag);
+	kfree(pag);
 out_unwind_new_pags:
-	/* unwind any prior newly initialized pags */
-	xfs_free_unused_perag_range(mp, first_initialised, agcount);
+	xfs_free_perag_range(mp, old_agcount, index);
 	return error;
 }
 
@@ -491,7 +398,7 @@ xfs_btroot_init(
 	struct xfs_buf		*bp,
 	struct aghdr_init_data	*id)
 {
-	xfs_btree_init_block(mp, bp, id->type, 0, 0, id->agno);
+	xfs_btree_init_buf(mp, bp, id->bc_ops, 0, 0, id->agno);
 }
 
 /* Finish initializing a free space btree. */
@@ -549,7 +456,7 @@ xfs_freesp_init_recs(
 }
 
 /*
- * Alloc btree root block init functions
+ * bnobt/cntbt btree root block init functions
  */
 static void
 xfs_bnoroot_init(
@@ -557,17 +464,7 @@ xfs_bnoroot_init(
 	struct xfs_buf		*bp,
 	struct aghdr_init_data	*id)
 {
-	xfs_btree_init_block(mp, bp, XFS_BTNUM_BNO, 0, 0, id->agno);
-	xfs_freesp_init_recs(mp, bp, id);
-}
-
-static void
-xfs_cntroot_init(
-	struct xfs_mount	*mp,
-	struct xfs_buf		*bp,
-	struct aghdr_init_data	*id)
-{
-	xfs_btree_init_block(mp, bp, XFS_BTNUM_CNT, 0, 0, id->agno);
+	xfs_btree_init_buf(mp, bp, id->bc_ops, 0, 0, id->agno);
 	xfs_freesp_init_recs(mp, bp, id);
 }
 
@@ -583,7 +480,7 @@ xfs_rmaproot_init(
 	struct xfs_btree_block	*block = XFS_BUF_TO_BLOCK(bp);
 	struct xfs_rmap_rec	*rrec;
 
-	xfs_btree_init_block(mp, bp, XFS_BTNUM_RMAP, 0, 4, id->agno);
+	xfs_btree_init_buf(mp, bp, id->bc_ops, 0, 4, id->agno);
 
 	/*
 	 * mark the AG header regions as static metadata The BNO
@@ -678,14 +575,13 @@ xfs_agfblock_init(
 	agf->agf_versionnum = cpu_to_be32(XFS_AGF_VERSION);
 	agf->agf_seqno = cpu_to_be32(id->agno);
 	agf->agf_length = cpu_to_be32(id->agsize);
-	agf->agf_roots[XFS_BTNUM_BNOi] = cpu_to_be32(XFS_BNO_BLOCK(mp));
-	agf->agf_roots[XFS_BTNUM_CNTi] = cpu_to_be32(XFS_CNT_BLOCK(mp));
-	agf->agf_levels[XFS_BTNUM_BNOi] = cpu_to_be32(1);
-	agf->agf_levels[XFS_BTNUM_CNTi] = cpu_to_be32(1);
+	agf->agf_bno_root = cpu_to_be32(XFS_BNO_BLOCK(mp));
+	agf->agf_cnt_root = cpu_to_be32(XFS_CNT_BLOCK(mp));
+	agf->agf_bno_level = cpu_to_be32(1);
+	agf->agf_cnt_level = cpu_to_be32(1);
 	if (xfs_has_rmapbt(mp)) {
-		agf->agf_roots[XFS_BTNUM_RMAPi] =
-					cpu_to_be32(XFS_RMAP_BLOCK(mp));
-		agf->agf_levels[XFS_BTNUM_RMAPi] = cpu_to_be32(1);
+		agf->agf_rmap_root = cpu_to_be32(XFS_RMAP_BLOCK(mp));
+		agf->agf_rmap_level = cpu_to_be32(1);
 		agf->agf_rmap_blocks = cpu_to_be32(1);
 	}
 
@@ -796,7 +692,7 @@ struct xfs_aghdr_grow_data {
 	size_t			numblks;
 	const struct xfs_buf_ops *ops;
 	aghdr_init_work_f	work;
-	xfs_btnum_t		type;
+	const struct xfs_btree_ops *bc_ops;
 	bool			need_init;
 };
 
@@ -850,13 +746,15 @@ xfs_ag_init_headers(
 		.numblks = BTOBB(mp->m_sb.sb_blocksize),
 		.ops = &xfs_bnobt_buf_ops,
 		.work = &xfs_bnoroot_init,
+		.bc_ops = &xfs_bnobt_ops,
 		.need_init = true
 	},
 	{ /* CNT root block */
 		.daddr = XFS_AGB_TO_DADDR(mp, id->agno, XFS_CNT_BLOCK(mp)),
 		.numblks = BTOBB(mp->m_sb.sb_blocksize),
 		.ops = &xfs_cntbt_buf_ops,
-		.work = &xfs_cntroot_init,
+		.work = &xfs_bnoroot_init,
+		.bc_ops = &xfs_cntbt_ops,
 		.need_init = true
 	},
 	{ /* INO root block */
@@ -864,7 +762,7 @@ xfs_ag_init_headers(
 		.numblks = BTOBB(mp->m_sb.sb_blocksize),
 		.ops = &xfs_inobt_buf_ops,
 		.work = &xfs_btroot_init,
-		.type = XFS_BTNUM_INO,
+		.bc_ops = &xfs_inobt_ops,
 		.need_init = true
 	},
 	{ /* FINO root block */
@@ -872,7 +770,7 @@ xfs_ag_init_headers(
 		.numblks = BTOBB(mp->m_sb.sb_blocksize),
 		.ops = &xfs_finobt_buf_ops,
 		.work = &xfs_btroot_init,
-		.type = XFS_BTNUM_FINO,
+		.bc_ops = &xfs_finobt_ops,
 		.need_init =  xfs_has_finobt(mp)
 	},
 	{ /* RMAP root block */
@@ -880,6 +778,7 @@ xfs_ag_init_headers(
 		.numblks = BTOBB(mp->m_sb.sb_blocksize),
 		.ops = &xfs_rmapbt_buf_ops,
 		.work = &xfs_rmaproot_init,
+		.bc_ops = &xfs_rmapbt_ops,
 		.need_init = xfs_has_rmapbt(mp)
 	},
 	{ /* REFC root block */
@@ -887,7 +786,7 @@ xfs_ag_init_headers(
 		.numblks = BTOBB(mp->m_sb.sb_blocksize),
 		.ops = &xfs_refcountbt_buf_ops,
 		.work = &xfs_btroot_init,
-		.type = XFS_BTNUM_REFC,
+		.bc_ops = &xfs_refcountbt_ops,
 		.need_init = xfs_has_reflink(mp)
 	},
 	{ /* NULL terminating block */
@@ -905,7 +804,7 @@ xfs_ag_init_headers(
 
 		id->daddr = dp->daddr;
 		id->numblks = dp->numblks;
-		id->type = dp->type;
+		id->bc_ops = dp->bc_ops;
 		error = xfs_ag_init_hdr(mp, id, dp->work, dp->ops);
 		if (error)
 			break;
@@ -937,7 +836,7 @@ xfs_ag_shrink_space(
 	int			error, err2;
 
 	ASSERT(pag->pag_agno == mp->m_sb.sb_agcount - 1);
-	error = xfs_ialloc_read_agi(pag, *tpp, &agibp);
+	error = xfs_ialloc_read_agi(pag, *tpp, 0, &agibp);
 	if (error)
 		return error;
 
@@ -950,8 +849,10 @@ xfs_ag_shrink_space(
 	agf = agfbp->b_addr;
 	aglen = be32_to_cpu(agi->agi_length);
 	/* some extra paranoid checks before we shrink the ag */
-	if (XFS_IS_CORRUPT(mp, agf->agf_length != agi->agi_length))
+	if (XFS_IS_CORRUPT(mp, agf->agf_length != agi->agi_length)) {
+		xfs_ag_mark_sick(pag, XFS_SICK_AG_AGF);
 		return -EFSCORRUPTED;
+	}
 	if (delta >= aglen)
 		return -EINVAL;
 
@@ -967,9 +868,7 @@ xfs_ag_shrink_space(
 	 * Disable perag reservations so it doesn't cause the allocation request
 	 * to fail. We'll reestablish reservation before we return.
 	 */
-	error = xfs_ag_resv_free(pag);
-	if (error)
-		return error;
+	xfs_ag_resv_free(pag);
 
 	/* internal log shouldn't also show up in the free space btrees */
 	error = xfs_alloc_vextent_exact_bno(&args,
@@ -1013,8 +912,8 @@ xfs_ag_shrink_space(
 		if (err2 != -ENOSPC)
 			goto resv_err;
 
-		err2 = __xfs_free_extent_later(*tpp, args.fsbno, delta, NULL,
-				XFS_AG_RESV_NONE, true);
+		err2 = xfs_free_extent_later(*tpp, args.fsbno, delta, NULL,
+				XFS_AG_RESV_NONE, XFS_FREE_EXTENT_SKIP_DISCARD);
 		if (err2)
 			goto resv_err;
 
@@ -1066,7 +965,7 @@ xfs_ag_extend_space(
 
 	ASSERT(pag->pag_agno == pag->pag_mount->m_sb.sb_agcount - 1);
 
-	error = xfs_ialloc_read_agi(pag, tp, &bp);
+	error = xfs_ialloc_read_agi(pag, tp, 0, &bp);
 	if (error)
 		return error;
 
@@ -1123,7 +1022,7 @@ xfs_ag_get_geometry(
 	int			error;
 
 	/* Lock the AG headers. */
-	error = xfs_ialloc_read_agi(pag, NULL, &agi_bp);
+	error = xfs_ialloc_read_agi(pag, NULL, 0, &agi_bp);
 	if (error)
 		return error;
 	error = xfs_alloc_read_agf(pag, NULL, 0, &agf_bp);