1 files changed, 428 insertions, 129 deletions

diff --git a/fs/xfs/xfs_mount.c b/fs/xfs/xfs_mount.c
index df370eb5dc15..29276fe60df9 100644
--- a/fs/xfs/xfs_mount.c
+++ b/fs/xfs/xfs_mount.c
@@ -34,7 +34,13 @@
 #include "xfs_health.h"
 #include "xfs_trace.h"
 #include "xfs_ag.h"
+#include "xfs_rtbitmap.h"
+#include "xfs_metafile.h"
+#include "xfs_rtgroup.h"
+#include "xfs_rtrmap_btree.h"
+#include "xfs_rtrefcount_btree.h"
 #include "scrub/stats.h"
+#include "xfs_zone_alloc.h"
 
 static DEFINE_MUTEX(xfs_uuid_table_mutex);
 static int xfs_uuid_table_size;
@@ -131,11 +137,15 @@ xfs_sb_validate_fsb_count(
 	xfs_sb_t	*sbp,
 	uint64_t	nblocks)
 {
-	ASSERT(PAGE_SHIFT >= sbp->sb_blocklog);
+	uint64_t		max_bytes;
+
 	ASSERT(sbp->sb_blocklog >= BBSHIFT);
 
+	if (check_shl_overflow(nblocks, sbp->sb_blocklog, &max_bytes))
+		return -EFBIG;
+
 	/* Limited by ULONG_MAX of page cache index */
-	if (nblocks >> (PAGE_SHIFT - sbp->sb_blocklog) > ULONG_MAX)
+	if (max_bytes >> PAGE_SHIFT > ULONG_MAX)
 		return -EFBIG;
 	return 0;
 }
@@ -172,14 +182,11 @@ xfs_readsb(
 
 	/*
 	 * Allocate a (locked) buffer to hold the superblock. This will be kept
-	 * around at all times to optimize access to the superblock. Therefore,
-	 * set XBF_NO_IOACCT to make sure it doesn't hold the buftarg count
-	 * elevated.
+	 * around at all times to optimize access to the superblock.
 	 */
 reread:
 	error = xfs_buf_read_uncached(mp->m_ddev_targp, XFS_SB_DADDR,
-				      BTOBB(sector_size), XBF_NO_IOACCT, &bp,
-				      buf_ops);
+				      BTOBB(sector_size), &bp, buf_ops);
 	if (error) {
 		if (loud)
 			xfs_warn(mp, "SB validate failed with error %d.", error);
@@ -230,6 +237,13 @@ reread:
 	mp->m_features |= xfs_sb_version_to_features(sbp);
 	xfs_reinit_percpu_counters(mp);
 
+	/*
+	 * If logged xattrs are enabled after log recovery finishes, then set
+	 * the opstate so that log recovery will work properly.
+	 */
+	if (xfs_sb_version_haslogxattrs(&mp->m_sb))
+		xfs_set_using_logged_xattrs(mp);
+
 	/* no need to be quiet anymore, so reset the buf ops */
 	bp->b_ops = &xfs_sb_buf_ops;
 
@@ -400,7 +414,7 @@ xfs_check_sizes(
 	}
 	error = xfs_buf_read_uncached(mp->m_ddev_targp,
 					d - XFS_FSS_TO_BB(mp, 1),
-					XFS_FSS_TO_BB(mp, 1), 0, &bp, NULL);
+					XFS_FSS_TO_BB(mp, 1), &bp, NULL);
 	if (error) {
 		xfs_warn(mp, "last sector read failed");
 		return error;
@@ -417,7 +431,7 @@ xfs_check_sizes(
 	}
 	error = xfs_buf_read_uncached(mp->m_logdev_targp,
 					d - XFS_FSB_TO_BB(mp, 1),
-					XFS_FSB_TO_BB(mp, 1), 0, &bp, NULL);
+					XFS_FSB_TO_BB(mp, 1), &bp, NULL);
 	if (error) {
 		xfs_warn(mp, "log device read failed");
 		return error;
@@ -448,22 +462,38 @@ xfs_mount_reset_sbqflags(
 	return xfs_sync_sb(mp, false);
 }
 
+static const char *const xfs_free_pool_name[] = {
+	[XC_FREE_BLOCKS]	= "free blocks",
+	[XC_FREE_RTEXTENTS]	= "free rt extents",
+	[XC_FREE_RTAVAILABLE]	= "available rt extents",
+};
+
 uint64_t
-xfs_default_resblks(xfs_mount_t *mp)
+xfs_default_resblks(
+	struct xfs_mount	*mp,
+	enum xfs_free_counter	ctr)
 {
-	uint64_t resblks;
-
-	/*
-	 * We default to 5% or 8192 fsbs of space reserved, whichever is
-	 * smaller.  This is intended to cover concurrent allocation
-	 * transactions when we initially hit enospc. These each require a 4
-	 * block reservation. Hence by default we cover roughly 2000 concurrent
-	 * allocation reservations.
-	 */
-	resblks = mp->m_sb.sb_dblocks;
-	do_div(resblks, 20);
-	resblks = min_t(uint64_t, resblks, 8192);
-	return resblks;
+	switch (ctr) {
+	case XC_FREE_BLOCKS:
+		/*
+		 * Default to 5% or 8192 FSBs of space reserved, whichever is
+		 * smaller.
+		 *
+		 * This is intended to cover concurrent allocation transactions
+		 * when we initially hit ENOSPC.  These each require a 4 block
+		 * reservation. Hence by default we cover roughly 2000
+		 * concurrent allocation reservations.
+		 */
+		return min(div_u64(mp->m_sb.sb_dblocks, 20), 8192ULL);
+	case XC_FREE_RTEXTENTS:
+	case XC_FREE_RTAVAILABLE:
+		if (IS_ENABLED(CONFIG_XFS_RT) && xfs_has_zoned(mp))
+			return xfs_zoned_default_resblks(mp, ctr);
+		return 0;
+	default:
+		ASSERT(0);
+		return 0;
+	}
 }
 
 /* Ensure the summary counts are correct. */
@@ -530,7 +560,7 @@ xfs_check_summary_counts(
 	 * If we're mounting the rt volume after recovering the log, recompute
 	 * frextents from the rtbitmap file to fix the inconsistency.
 	 */
-	if (xfs_has_realtime(mp) && !xfs_is_clean(mp)) {
+	if (xfs_has_realtime(mp) && !xfs_has_zoned(mp) && !xfs_is_clean(mp)) {
 		error = xfs_rtalloc_reinit_frextents(mp);
 		if (error)
 			return error;
@@ -587,7 +617,7 @@ xfs_unmount_flush_inodes(
 	xfs_extent_busy_wait_all(mp);
 	flush_workqueue(xfs_discard_wq);
 
-	set_bit(XFS_OPSTATE_UNMOUNTING, &mp->m_opstate);
+	xfs_set_unmounting(mp);
 
 	xfs_ail_push_all_sync(mp->m_ail);
 	xfs_inodegc_stop(mp);
@@ -608,6 +638,22 @@ xfs_mount_setup_inode_geom(
 	xfs_ialloc_setup_geometry(mp);
 }
 
+/* Mount the metadata directory tree root. */
+STATIC int
+xfs_mount_setup_metadir(
+	struct xfs_mount	*mp)
+{
+	int			error;
+
+	/* Load the metadata directory root inode into memory. */
+	error = xfs_metafile_iget(mp, mp->m_sb.sb_metadirino, XFS_METAFILE_DIR,
+			&mp->m_metadirip);
+	if (error)
+		xfs_warn(mp, "Failed to load metadir root directory, error %d",
+				error);
+	return error;
+}
+
 /* Compute maximum possible height for per-AG btree types for this fs. */
 static inline void
 xfs_agbtree_compute_maxlevels(
@@ -620,6 +666,167 @@ xfs_agbtree_compute_maxlevels(
 	mp->m_agbtree_maxlevels = max(levels, mp->m_refc_maxlevels);
 }
 
+/* Maximum atomic write IO size that the kernel allows. */
+static inline xfs_extlen_t xfs_calc_atomic_write_max(struct xfs_mount *mp)
+{
+	return rounddown_pow_of_two(XFS_B_TO_FSB(mp, MAX_RW_COUNT));
+}
+
+static inline unsigned int max_pow_of_two_factor(const unsigned int nr)
+{
+	return 1 << (ffs(nr) - 1);
+}
+
+/*
+ * If the data device advertises atomic write support, limit the size of data
+ * device atomic writes to the greatest power-of-two factor of the AG size so
+ * that every atomic write unit aligns with the start of every AG.  This is
+ * required so that the per-AG allocations for an atomic write will always be
+ * aligned compatibly with the alignment requirements of the storage.
+ *
+ * If the data device doesn't advertise atomic writes, then there are no
+ * alignment restrictions and the largest out-of-place write we can do
+ * ourselves is the number of blocks that user files can allocate from any AG.
+ */
+static inline xfs_extlen_t xfs_calc_perag_awu_max(struct xfs_mount *mp)
+{
+	if (mp->m_ddev_targp->bt_bdev_awu_min > 0)
+		return max_pow_of_two_factor(mp->m_sb.sb_agblocks);
+	return rounddown_pow_of_two(mp->m_ag_max_usable);
+}
+
+/*
+ * Reflink on the realtime device requires rtgroups, and atomic writes require
+ * reflink.
+ *
+ * If the realtime device advertises atomic write support, limit the size of
+ * data device atomic writes to the greatest power-of-two factor of the rtgroup
+ * size so that every atomic write unit aligns with the start of every rtgroup.
+ * This is required so that the per-rtgroup allocations for an atomic write
+ * will always be aligned compatibly with the alignment requirements of the
+ * storage.
+ *
+ * If the rt device doesn't advertise atomic writes, then there are no
+ * alignment restrictions and the largest out-of-place write we can do
+ * ourselves is the number of blocks that user files can allocate from any
+ * rtgroup.
+ */
+static inline xfs_extlen_t xfs_calc_rtgroup_awu_max(struct xfs_mount *mp)
+{
+	struct xfs_groups	*rgs = &mp->m_groups[XG_TYPE_RTG];
+
+	if (rgs->blocks == 0)
+		return 0;
+	if (mp->m_rtdev_targp && mp->m_rtdev_targp->bt_bdev_awu_min > 0)
+		return max_pow_of_two_factor(rgs->blocks);
+	return rounddown_pow_of_two(rgs->blocks);
+}
+
+/* Compute the maximum atomic write unit size for each section. */
+static inline void
+xfs_calc_atomic_write_unit_max(
+	struct xfs_mount	*mp)
+{
+	struct xfs_groups	*ags = &mp->m_groups[XG_TYPE_AG];
+	struct xfs_groups	*rgs = &mp->m_groups[XG_TYPE_RTG];
+
+	const xfs_extlen_t	max_write = xfs_calc_atomic_write_max(mp);
+	const xfs_extlen_t	max_ioend = xfs_reflink_max_atomic_cow(mp);
+	const xfs_extlen_t	max_agsize = xfs_calc_perag_awu_max(mp);
+	const xfs_extlen_t	max_rgsize = xfs_calc_rtgroup_awu_max(mp);
+
+	ags->awu_max = min3(max_write, max_ioend, max_agsize);
+	rgs->awu_max = min3(max_write, max_ioend, max_rgsize);
+
+	trace_xfs_calc_atomic_write_unit_max(mp, max_write, max_ioend,
+			max_agsize, max_rgsize);
+}
+
+/*
+ * Try to set the atomic write maximum to a new value that we got from
+ * userspace via mount option.
+ */
+int
+xfs_set_max_atomic_write_opt(
+	struct xfs_mount	*mp,
+	unsigned long long	new_max_bytes)
+{
+	const xfs_filblks_t	new_max_fsbs = XFS_B_TO_FSBT(mp, new_max_bytes);
+	const xfs_extlen_t	max_write = xfs_calc_atomic_write_max(mp);
+	const xfs_extlen_t	max_group =
+		max(mp->m_groups[XG_TYPE_AG].blocks,
+		    mp->m_groups[XG_TYPE_RTG].blocks);
+	const xfs_extlen_t	max_group_write =
+		max(xfs_calc_perag_awu_max(mp), xfs_calc_rtgroup_awu_max(mp));
+	int			error;
+
+	if (new_max_bytes == 0)
+		goto set_limit;
+
+	ASSERT(max_write <= U32_MAX);
+
+	/* generic_atomic_write_valid enforces power of two length */
+	if (!is_power_of_2(new_max_bytes)) {
+		xfs_warn(mp,
+ "max atomic write size of %llu bytes is not a power of 2",
+				new_max_bytes);
+		return -EINVAL;
+	}
+
+	if (new_max_bytes & mp->m_blockmask) {
+		xfs_warn(mp,
+ "max atomic write size of %llu bytes not aligned with fsblock",
+				new_max_bytes);
+		return -EINVAL;
+	}
+
+	if (new_max_fsbs > max_write) {
+		xfs_warn(mp,
+ "max atomic write size of %lluk cannot be larger than max write size %lluk",
+				new_max_bytes >> 10,
+				XFS_FSB_TO_B(mp, max_write) >> 10);
+		return -EINVAL;
+	}
+
+	if (new_max_fsbs > max_group) {
+		xfs_warn(mp,
+ "max atomic write size of %lluk cannot be larger than allocation group size %lluk",
+				new_max_bytes >> 10,
+				XFS_FSB_TO_B(mp, max_group) >> 10);
+		return -EINVAL;
+	}
+
+	if (new_max_fsbs > max_group_write) {
+		xfs_warn(mp,
+ "max atomic write size of %lluk cannot be larger than max allocation group write size %lluk",
+				new_max_bytes >> 10,
+				XFS_FSB_TO_B(mp, max_group_write) >> 10);
+		return -EINVAL;
+	}
+
+set_limit:
+	error = xfs_calc_atomic_write_reservation(mp, new_max_fsbs);
+	if (error) {
+		xfs_warn(mp,
+ "cannot support completing atomic writes of %lluk",
+				new_max_bytes >> 10);
+		return error;
+	}
+
+	xfs_calc_atomic_write_unit_max(mp);
+	mp->m_awu_max_bytes = new_max_bytes;
+	return 0;
+}
+
+/* Compute maximum possible height for realtime btree types for this fs. */
+static inline void
+xfs_rtbtree_compute_maxlevels(
+	struct xfs_mount	*mp)
+{
+	mp->m_rtbtree_maxlevels = max(mp->m_rtrmap_maxlevels,
+				      mp->m_rtrefc_maxlevels);
+}
+
 /*
  * This function does the following on an initial mount of a file system:
  *	- reads the superblock from disk and init the mount struct
@@ -640,6 +847,7 @@ xfs_mountfs(
 	uint			quotamount = 0;
 	uint			quotaflags = 0;
 	int			error = 0;
+	int			i;
 
 	xfs_sb_mount_common(mp, sbp);
 
@@ -688,9 +896,12 @@ xfs_mountfs(
 	xfs_bmap_compute_maxlevels(mp, XFS_ATTR_FORK);
 	xfs_mount_setup_inode_geom(mp);
 	xfs_rmapbt_compute_maxlevels(mp);
+	xfs_rtrmapbt_compute_maxlevels(mp);
 	xfs_refcountbt_compute_maxlevels(mp);
+	xfs_rtrefcountbt_compute_maxlevels(mp);
 
 	xfs_agbtree_compute_maxlevels(mp);
+	xfs_rtbtree_compute_maxlevels(mp);
 
 	/*
 	 * Check if sb_agblocks is aligned at stripe boundary.  If sb_agblocks
@@ -706,27 +917,15 @@ xfs_mountfs(
 	/* enable fail_at_unmount as default */
 	mp->m_fail_unmount = true;
 
-	super_set_sysfs_name_id(mp->m_super);
-
-	error = xfs_sysfs_init(&mp->m_kobj, &xfs_mp_ktype,
-			       NULL, mp->m_super->s_id);
+	error = xfs_mount_sysfs_init(mp);
 	if (error)
-		goto out;
-
-	error = xfs_sysfs_init(&mp->m_stats.xs_kobj, &xfs_stats_ktype,
-			       &mp->m_kobj, "stats");
-	if (error)
-		goto out_remove_sysfs;
+		goto out_remove_scrub_stats;
 
 	xchk_stats_register(mp->m_scrub_stats, mp->m_debugfs);
 
-	error = xfs_error_sysfs_init(mp);
-	if (error)
-		goto out_remove_scrub_stats;
-
 	error = xfs_errortag_init(mp);
 	if (error)
-		goto out_remove_error_sysfs;
+		goto out_remove_sysfs;
 
 	error = xfs_uuid_mount(mp);
 	if (error)
@@ -798,17 +997,24 @@ xfs_mountfs(
 	/*
 	 * Allocate and initialize the per-ag data.
 	 */
-	error = xfs_initialize_perag(mp, sbp->sb_agcount, mp->m_sb.sb_dblocks,
-			&mp->m_maxagi);
+	error = xfs_initialize_perag(mp, 0, sbp->sb_agcount,
+			mp->m_sb.sb_dblocks, &mp->m_maxagi);
 	if (error) {
 		xfs_warn(mp, "Failed per-ag init: %d", error);
 		goto out_free_dir;
 	}
 
+	error = xfs_initialize_rtgroups(mp, 0, sbp->sb_rgcount,
+			mp->m_sb.sb_rextents);
+	if (error) {
+		xfs_warn(mp, "Failed rtgroup init: %d", error);
+		goto out_free_perag;
+	}
+
 	if (XFS_IS_CORRUPT(mp, !sbp->sb_logblocks)) {
 		xfs_warn(mp, "no log defined");
 		error = -EFSCORRUPTED;
-		goto out_free_perag;
+		goto out_free_rtgroup;
 	}
 
 	error = xfs_inodegc_register_shrinker(mp);
@@ -816,6 +1022,13 @@ xfs_mountfs(
 		goto out_fail_wait;
 
 	/*
+	 * If we're resuming quota status, pick up the preliminary qflags from
+	 * the ondisk superblock so that we know if we should recover dquots.
+	 */
+	if (xfs_is_resuming_quotaon(mp))
+		xfs_qm_resume_quotaon(mp);
+
+	/*
 	 * Log's mount-time initialization. The first part of recovery can place
 	 * some items on the AIL, to be handled when recovery is finished or
 	 * cancelled.
@@ -828,6 +1041,23 @@ xfs_mountfs(
 		goto out_inodegc_shrinker;
 	}
 
+	/*
+	 * If we're resuming quota status and recovered the log, re-sample the
+	 * qflags from the ondisk superblock now that we've recovered it, just
+	 * in case someone shut down enforcement just before a crash.
+	 */
+	if (xfs_clear_resuming_quotaon(mp) && xlog_recovery_needed(mp->m_log))
+		xfs_qm_resume_quotaon(mp);
+
+	/*
+	 * If logged xattrs are still enabled after log recovery finishes, then
+	 * they'll be available until unmount.  Otherwise, turn them off.
+	 */
+	if (xfs_sb_version_haslogxattrs(&mp->m_sb))
+		xfs_set_using_logged_xattrs(mp);
+	else
+		xfs_clear_using_logged_xattrs(mp);
+
 	/* Enable background inode inactivation workers. */
 	xfs_inodegc_start(mp);
 	xfs_blockgc_start(mp);
@@ -845,6 +1075,12 @@ xfs_mountfs(
 		mp->m_features |= XFS_FEAT_ATTR2;
 	}
 
+	if (xfs_has_metadir(mp)) {
+		error = xfs_mount_setup_metadir(mp);
+		if (error)
+			goto out_free_metadir;
+	}
+
 	/*
 	 * Get and sanity-check the root inode.
 	 * Save the pointer to it in the mount structure.
@@ -855,7 +1091,7 @@ xfs_mountfs(
 		xfs_warn(mp,
 			"Failed to read root inode 0x%llx, error %d",
 			sbp->sb_rootino, -error);
-		goto out_log_dealloc;
+		goto out_free_metadir;
 	}
 
 	ASSERT(rip != NULL);
@@ -953,6 +1189,12 @@ xfs_mountfs(
 	if (xfs_is_readonly(mp) && !xfs_has_norecovery(mp))
 		xfs_log_clean(mp);
 
+	if (xfs_has_zoned(mp)) {
+		error = xfs_mount_zones(mp);
+		if (error)
+			goto out_rtunmount;
+	}
+
 	/*
 	 * Complete the quota initialisation, post-log-replay component.
 	 */
@@ -968,35 +1210,55 @@ xfs_mountfs(
 	 * privileged transactions. This is needed so that transaction
 	 * space required for critical operations can dip into this pool
 	 * when at ENOSPC. This is needed for operations like create with
-	 * attr, unwritten extent conversion at ENOSPC, etc. Data allocations
-	 * are not allowed to use this reserved space.
+	 * attr, unwritten extent conversion at ENOSPC, garbage collection
+	 * etc. Data allocations are not allowed to use this reserved space.
 	 *
 	 * This may drive us straight to ENOSPC on mount, but that implies
 	 * we were already there on the last unmount. Warn if this occurs.
 	 */
 	if (!xfs_is_readonly(mp)) {
-		error = xfs_reserve_blocks(mp, xfs_default_resblks(mp));
-		if (error)
-			xfs_warn(mp,
-	"Unable to allocate reserve blocks. Continuing without reserve pool.");
+		for (i = 0; i < XC_FREE_NR; i++) {
+			error = xfs_reserve_blocks(mp, i,
+					xfs_default_resblks(mp, i));
+			if (error)
+				xfs_warn(mp,
+"Unable to allocate reserve blocks. Continuing without reserve pool for %s.",
+					xfs_free_pool_name[i]);
+		}
 
 		/* Reserve AG blocks for future btree expansion. */
 		error = xfs_fs_reserve_ag_blocks(mp);
 		if (error && error != -ENOSPC)
 			goto out_agresv;
+
+		xfs_zone_gc_start(mp);
 	}
 
+	/*
+	 * Pre-calculate atomic write unit max.  This involves computations
+	 * derived from transaction reservations, so we must do this after the
+	 * log is fully initialized.
+	 */
+	error = xfs_set_max_atomic_write_opt(mp, mp->m_awu_max_bytes);
+	if (error)
+		goto out_agresv;
+
 	return 0;
 
  out_agresv:
 	xfs_fs_unreserve_ag_blocks(mp);
 	xfs_qm_unmount_quotas(mp);
+	if (xfs_has_zoned(mp))
+		xfs_unmount_zones(mp);
  out_rtunmount:
 	xfs_rtunmount_inodes(mp);
  out_rele_rip:
 	xfs_irele(rip);
 	/* Clean out dquots that might be in memory after quotacheck. */
 	xfs_qm_unmount(mp);
+ out_free_metadir:
+	if (mp->m_metadirip)
+		xfs_irele(mp->m_metadirip);
 
 	/*
 	 * Inactivate all inodes that might still be in memory after a log
@@ -1018,7 +1280,6 @@ xfs_mountfs(
 	 * quota inodes.
 	 */
 	xfs_unmount_flush_inodes(mp);
- out_log_dealloc:
 	xfs_log_mount_cancel(mp);
  out_inodegc_shrinker:
 	shrinker_free(mp->m_inodegc_shrinker);
@@ -1026,21 +1287,20 @@ xfs_mountfs(
 	if (mp->m_logdev_targp && mp->m_logdev_targp != mp->m_ddev_targp)
 		xfs_buftarg_drain(mp->m_logdev_targp);
 	xfs_buftarg_drain(mp->m_ddev_targp);
+ out_free_rtgroup:
+	xfs_free_rtgroups(mp, 0, mp->m_sb.sb_rgcount);
  out_free_perag:
-	xfs_free_perag(mp);
+	xfs_free_perag_range(mp, 0, mp->m_sb.sb_agcount);
  out_free_dir:
 	xfs_da_unmount(mp);
  out_remove_uuid:
 	xfs_uuid_unmount(mp);
  out_remove_errortag:
 	xfs_errortag_del(mp);
- out_remove_error_sysfs:
-	xfs_error_sysfs_del(mp);
+ out_remove_sysfs:
+	xfs_mount_sysfs_del(mp);
  out_remove_scrub_stats:
 	xchk_stats_unregister(mp->m_scrub_stats);
-	xfs_sysfs_del(&mp->m_stats.xs_kobj);
- out_remove_sysfs:
-	xfs_sysfs_del(&mp->m_kobj);
  out:
 	return error;
 }
@@ -1066,10 +1326,16 @@ xfs_unmountfs(
 	xfs_inodegc_flush(mp);
 
 	xfs_blockgc_stop(mp);
+	if (!test_bit(XFS_OPSTATE_READONLY, &mp->m_opstate))
+		xfs_zone_gc_stop(mp);
 	xfs_fs_unreserve_ag_blocks(mp);
 	xfs_qm_unmount_quotas(mp);
+	if (xfs_has_zoned(mp))
+		xfs_unmount_zones(mp);
 	xfs_rtunmount_inodes(mp);
 	xfs_irele(mp->m_rootip);
+	if (mp->m_metadirip)
+		xfs_irele(mp->m_metadirip);
 
 	xfs_unmount_flush_inodes(mp);
 
@@ -1089,12 +1355,17 @@ xfs_unmountfs(
 	 * we only every apply deltas to the superblock and hence the incore
 	 * value does not matter....
 	 */
-	error = xfs_reserve_blocks(mp, 0);
+	error = xfs_reserve_blocks(mp, XC_FREE_BLOCKS, 0);
 	if (error)
 		xfs_warn(mp, "Unable to free reserved block pool. "
 				"Freespace may not be correct on next mount.");
 	xfs_unmount_check(mp);
 
+	/*
+	 * Indicate that it's ok to clear log incompat bits before cleaning
+	 * the log and writing the unmount record.
+	 */
+	xfs_set_done_with_log_incompat(mp);
 	xfs_log_unmount(mp);
 	xfs_da_unmount(mp);
 	xfs_uuid_unmount(mp);
@@ -1103,13 +1374,11 @@ xfs_unmountfs(
 	xfs_errortag_clearall(mp);
 #endif
 	shrinker_free(mp->m_inodegc_shrinker);
-	xfs_free_perag(mp);
-
+	xfs_free_rtgroups(mp, 0, mp->m_sb.sb_rgcount);
+	xfs_free_perag_range(mp, 0, mp->m_sb.sb_agcount);
 	xfs_errortag_del(mp);
-	xfs_error_sysfs_del(mp);
 	xchk_stats_unregister(mp->m_scrub_stats);
-	xfs_sysfs_del(&mp->m_stats.xs_kobj);
-	xfs_sysfs_del(&mp->m_kobj);
+	xfs_mount_sysfs_del(mp);
 }
 
 /*
@@ -1131,49 +1400,67 @@ xfs_fs_writable(
 	return true;
 }
 
-/* Adjust m_fdblocks or m_frextents. */
-int
-xfs_mod_freecounter(
+/*
+ * Estimate the amount of free space that is not available to userspace and is
+ * not explicitly reserved from the incore fdblocks.  This includes:
+ *
+ * - The minimum number of blocks needed to support splitting a bmap btree
+ * - The blocks currently in use by the freespace btrees because they record
+ *   the actual blocks that will fill per-AG metadata space reservations
+ */
+uint64_t
+xfs_freecounter_unavailable(
 	struct xfs_mount	*mp,
-	struct percpu_counter	*counter,
-	int64_t			delta,
-	bool			rsvd)
+	enum xfs_free_counter	ctr)
 {
-	int64_t			lcounter;
-	long long		res_used;
-	uint64_t		set_aside = 0;
-	s32			batch;
-	bool			has_resv_pool;
+	if (ctr != XC_FREE_BLOCKS)
+		return 0;
+	return mp->m_alloc_set_aside + atomic64_read(&mp->m_allocbt_blks);
+}
 
-	ASSERT(counter == &mp->m_fdblocks || counter == &mp->m_frextents);
-	has_resv_pool = (counter == &mp->m_fdblocks);
-	if (rsvd)
-		ASSERT(has_resv_pool);
+void
+xfs_add_freecounter(
+	struct xfs_mount	*mp,
+	enum xfs_free_counter	ctr,
+	uint64_t		delta)
+{
+	struct xfs_freecounter	*counter = &mp->m_free[ctr];
+	uint64_t		res_used;
 
-	if (delta > 0) {
-		/*
-		 * If the reserve pool is depleted, put blocks back into it
-		 * first. Most of the time the pool is full.
-		 */
-		if (likely(!has_resv_pool ||
-			   mp->m_resblks == mp->m_resblks_avail)) {
-			percpu_counter_add(counter, delta);
-			return 0;
-		}
+	/*
+	 * If the reserve pool is depleted, put blocks back into it first.
+	 * Most of the time the pool is full.
+	 */
+	if (likely(counter->res_avail == counter->res_total)) {
+		percpu_counter_add(&counter->count, delta);
+		return;
+	}
 
-		spin_lock(&mp->m_sb_lock);
-		res_used = (long long)(mp->m_resblks - mp->m_resblks_avail);
-
-		if (res_used > delta) {
-			mp->m_resblks_avail += delta;
-		} else {
-			delta -= res_used;
-			mp->m_resblks_avail = mp->m_resblks;
-			percpu_counter_add(counter, delta);
-		}
-		spin_unlock(&mp->m_sb_lock);
-		return 0;
+	spin_lock(&mp->m_sb_lock);
+	res_used = counter->res_total - counter->res_avail;
+	if (res_used > delta) {
+		counter->res_avail += delta;
+	} else {
+		delta -= res_used;
+		counter->res_avail = counter->res_total;
+		percpu_counter_add(&counter->count, delta);
 	}
+	spin_unlock(&mp->m_sb_lock);
+}
+
+
+/* Adjust in-core free blocks or RT extents. */
+int
+xfs_dec_freecounter(
+	struct xfs_mount	*mp,
+	enum xfs_free_counter	ctr,
+	uint64_t		delta,
+	bool			rsvd)
+{
+	struct xfs_freecounter	*counter = &mp->m_free[ctr];
+	s32			batch;
+
+	ASSERT(ctr < XC_FREE_NR);
 
 	/*
 	 * Taking blocks away, need to be more accurate the closer we
@@ -1183,7 +1470,7 @@ xfs_mod_freecounter(
 	 * then make everything serialise as we are real close to
 	 * ENOSPC.
 	 */
-	if (__percpu_counter_compare(counter, 2 * XFS_FDBLOCKS_BATCH,
+	if (__percpu_counter_compare(&counter->count, 2 * XFS_FDBLOCKS_BATCH,
 				     XFS_FDBLOCKS_BATCH) < 0)
 		batch = 1;
 	else
@@ -1200,34 +1487,34 @@ xfs_mod_freecounter(
 	 * problems (i.e. transaction abort, pagecache discards, etc.) than
 	 * slightly premature -ENOSPC.
 	 */
-	if (has_resv_pool)
-		set_aside = xfs_fdblocks_unavailable(mp);
-	percpu_counter_add_batch(counter, delta, batch);
-	if (__percpu_counter_compare(counter, set_aside,
-				     XFS_FDBLOCKS_BATCH) >= 0) {
-		/* we had space! */
-		return 0;
-	}
-
-	/*
-	 * lock up the sb for dipping into reserves before releasing the space
-	 * that took us to ENOSPC.
-	 */
-	spin_lock(&mp->m_sb_lock);
-	percpu_counter_add(counter, -delta);
-	if (!has_resv_pool || !rsvd)
-		goto fdblocks_enospc;
-
-	lcounter = (long long)mp->m_resblks_avail + delta;
-	if (lcounter >= 0) {
-		mp->m_resblks_avail = lcounter;
+	percpu_counter_add_batch(&counter->count, -((int64_t)delta), batch);
+	if (__percpu_counter_compare(&counter->count,
+			xfs_freecounter_unavailable(mp, ctr),
+			XFS_FDBLOCKS_BATCH) < 0) {
+		/*
+		 * Lock up the sb for dipping into reserves before releasing the
+		 * space that took us to ENOSPC.
+		 */
+		spin_lock(&mp->m_sb_lock);
+		percpu_counter_add(&counter->count, delta);
+		if (!rsvd)
+			goto fdblocks_enospc;
+		if (delta > counter->res_avail) {
+			if (ctr == XC_FREE_BLOCKS)
+				xfs_warn_once(mp,
+"Reserve blocks depleted! Consider increasing reserve pool size.");
+			goto fdblocks_enospc;
+		}
+		counter->res_avail -= delta;
+		trace_xfs_freecounter_reserved(mp, ctr, delta, _RET_IP_);
 		spin_unlock(&mp->m_sb_lock);
-		return 0;
 	}
-	xfs_warn_once(mp,
-"Reserve blocks depleted! Consider increasing reserve pool size.");
+
+	/* we had space! */
+	return 0;
 
 fdblocks_enospc:
+	trace_xfs_freecounter_enospc(mp, ctr, delta, _RET_IP_);
 	spin_unlock(&mp->m_sb_lock);
 	return -ENOSPC;
 }
@@ -1364,7 +1651,8 @@ xfs_clear_incompat_log_features(
 	if (!xfs_has_crc(mp) ||
 	    !xfs_sb_has_incompat_log_feature(&mp->m_sb,
 				XFS_SB_FEAT_INCOMPAT_LOG_ALL) ||
-	    xfs_is_shutdown(mp))
+	    xfs_is_shutdown(mp) ||
+	    !xfs_is_done_with_log_incompat(mp))
 		return false;
 
 	/*
@@ -1399,9 +1687,20 @@ xfs_clear_incompat_log_features(
 #define XFS_DELALLOC_BATCH	(4096)
 void
 xfs_mod_delalloc(
-	struct xfs_mount	*mp,
-	int64_t			delta)
+	struct xfs_inode	*ip,
+	int64_t			data_delta,
+	int64_t			ind_delta)
 {
-	percpu_counter_add_batch(&mp->m_delalloc_blks, delta,
+	struct xfs_mount	*mp = ip->i_mount;
+
+	if (XFS_IS_REALTIME_INODE(ip)) {
+		percpu_counter_add_batch(&mp->m_delalloc_rtextents,
+				xfs_blen_to_rtbxlen(mp, data_delta),
+				XFS_DELALLOC_BATCH);
+		if (!ind_delta)
+			return;
+		data_delta = 0;
+	}
+	percpu_counter_add_batch(&mp->m_delalloc_blks, data_delta + ind_delta,
 			XFS_DELALLOC_BATCH);
 }