1 files changed, 216 insertions, 96 deletions
diff --git a/fs/xfs/xfs_super.c b/fs/xfs/xfs_super.c
index 394fdf3bb535..53944cc7af24 100644
--- a/fs/xfs/xfs_super.c
+++ b/fs/xfs/xfs_super.c
@@ -46,6 +46,7 @@
 #include "xfs_exchmaps_item.h"
 #include "xfs_parent.h"
 #include "xfs_rtalloc.h"
+#include "xfs_zone_alloc.h"
 #include "scrub/stats.h"
 #include "scrub/rcbag_btree.h"
 
@@ -109,7 +110,8 @@ enum {
 	Opt_filestreams, Opt_quota, Opt_noquota, Opt_usrquota, Opt_grpquota,
 	Opt_prjquota, Opt_uquota, Opt_gquota, Opt_pquota,
 	Opt_uqnoenforce, Opt_gqnoenforce, Opt_pqnoenforce, Opt_qnoenforce,
-	Opt_discard, Opt_nodiscard, Opt_dax, Opt_dax_enum,
+	Opt_discard, Opt_nodiscard, Opt_dax, Opt_dax_enum, Opt_max_open_zones,
+	Opt_lifetime, Opt_nolifetime,
 };
 
 static const struct fs_parameter_spec xfs_fs_parameters[] = {
@@ -154,6 +156,9 @@ static const struct fs_parameter_spec xfs_fs_parameters[] = {
 	fsparam_flag("nodiscard",	Opt_nodiscard),
 	fsparam_flag("dax",		Opt_dax),
 	fsparam_enum("dax",		Opt_dax_enum, dax_param_enums),
+	fsparam_u32("max_open_zones",	Opt_max_open_zones),
+	fsparam_flag("lifetime",	Opt_lifetime),
+	fsparam_flag("nolifetime",	Opt_nolifetime),
 	{}
 };
 
@@ -182,6 +187,7 @@ xfs_fs_show_options(
 		{ XFS_FEAT_LARGE_IOSIZE,	",largeio" },
 		{ XFS_FEAT_DAX_ALWAYS,		",dax=always" },
 		{ XFS_FEAT_DAX_NEVER,		",dax=never" },
+		{ XFS_FEAT_NOLIFETIME,		",nolifetime" },
 		{ 0, NULL }
 	};
 	struct xfs_mount	*mp = XFS_M(root->d_sb);
@@ -233,6 +239,9 @@ xfs_fs_show_options(
 	if (!(mp->m_qflags & XFS_ALL_QUOTA_ACCT))
 		seq_puts(m, ",noquota");
 
+	if (mp->m_max_open_zones)
+		seq_printf(m, ",max_open_zones=%u", mp->m_max_open_zones);
+
 	return 0;
 }
 
@@ -533,7 +542,15 @@ xfs_setup_devices(
 		if (error)
 			return error;
 	}
-	if (mp->m_rtdev_targp) {
+
+	if (mp->m_sb.sb_rtstart) {
+		if (mp->m_rtdev_targp) {
+			xfs_warn(mp,
+		"can't use internal and external rtdev at the same time");
+			return -EINVAL;
+		}
+		mp->m_rtdev_targp = mp->m_ddev_targp;
+	} else if (mp->m_rtname) {
 		error = xfs_setsize_buftarg(mp->m_rtdev_targp,
 					    mp->m_sb.sb_sectsize);
 		if (error)
@@ -757,7 +774,7 @@ xfs_mount_free(
 {
 	if (mp->m_logdev_targp && mp->m_logdev_targp != mp->m_ddev_targp)
 		xfs_free_buftarg(mp->m_logdev_targp);
-	if (mp->m_rtdev_targp)
+	if (mp->m_rtdev_targp && mp->m_rtdev_targp != mp->m_ddev_targp)
 		xfs_free_buftarg(mp->m_rtdev_targp);
 	if (mp->m_ddev_targp)
 		xfs_free_buftarg(mp->m_ddev_targp);
@@ -814,25 +831,85 @@ xfs_fs_sync_fs(
 	if (sb->s_writers.frozen == SB_FREEZE_PAGEFAULT) {
 		xfs_inodegc_stop(mp);
 		xfs_blockgc_stop(mp);
+		xfs_zone_gc_stop(mp);
 	}
 
 	return 0;
 }
 
+static xfs_extlen_t
+xfs_internal_log_size(
+	struct xfs_mount	*mp)
+{
+	if (!mp->m_sb.sb_logstart)
+		return 0;
+	return mp->m_sb.sb_logblocks;
+}
+
+static void
+xfs_statfs_data(
+	struct xfs_mount	*mp,
+	struct kstatfs		*st)
+{
+	int64_t			fdblocks =
+		xfs_sum_freecounter(mp, XC_FREE_BLOCKS);
+
+	/* make sure st->f_bfree does not underflow */
+	st->f_bfree = max(0LL,
+		fdblocks - xfs_freecounter_unavailable(mp, XC_FREE_BLOCKS));
+
+	/*
+	 * sb_dblocks can change during growfs, but nothing cares about reporting
+	 * the old or new value during growfs.
+	 */
+	st->f_blocks = mp->m_sb.sb_dblocks - xfs_internal_log_size(mp);
+}
+
+/*
+ * When stat(v)fs is called on a file with the realtime bit set or a directory
+ * with the rtinherit bit, report freespace information for the RT device
+ * instead of the main data device.
+ */
+static void
+xfs_statfs_rt(
+	struct xfs_mount	*mp,
+	struct kstatfs		*st)
+{
+	st->f_bfree = xfs_rtbxlen_to_blen(mp,
+			xfs_sum_freecounter(mp, XC_FREE_RTEXTENTS));
+	st->f_blocks = mp->m_sb.sb_rblocks - xfs_rtbxlen_to_blen(mp,
+			mp->m_free[XC_FREE_RTEXTENTS].res_total);
+}
+
+static void
+xfs_statfs_inodes(
+	struct xfs_mount	*mp,
+	struct kstatfs		*st)
+{
+	uint64_t		icount = percpu_counter_sum(&mp->m_icount);
+	uint64_t		ifree = percpu_counter_sum(&mp->m_ifree);
+	uint64_t		fakeinos = XFS_FSB_TO_INO(mp, st->f_bfree);
+
+	st->f_files = min(icount + fakeinos, (uint64_t)XFS_MAXINUMBER);
+	if (M_IGEO(mp)->maxicount)
+		st->f_files = min_t(typeof(st->f_files), st->f_files,
+					M_IGEO(mp)->maxicount);
+
+	/* If sb_icount overshot maxicount, report actual allocation */
+	st->f_files = max_t(typeof(st->f_files), st->f_files,
+			mp->m_sb.sb_icount);
+
+	/* Make sure st->f_ffree does not underflow */
+	st->f_ffree = max_t(int64_t, 0, st->f_files - (icount - ifree));
+}
+
 STATIC int
 xfs_fs_statfs(
 	struct dentry		*dentry,
-	struct kstatfs		*statp)
+	struct kstatfs		*st)
 {
 	struct xfs_mount	*mp = XFS_M(dentry->d_sb);
-	xfs_sb_t		*sbp = &mp->m_sb;
 	struct xfs_inode	*ip = XFS_I(d_inode(dentry));
-	uint64_t		fakeinos, id;
-	uint64_t		icount;
-	uint64_t		ifree;
-	uint64_t		fdblocks;
-	xfs_extlen_t		lsize;
-	int64_t			ffree;
 
 	/*
 	 * Expedite background inodegc but don't wait. We do not want to block
@@ -840,80 +917,58 @@ xfs_fs_statfs(
 	 */
 	xfs_inodegc_push(mp);
 
-	statp->f_type = XFS_SUPER_MAGIC;
-	statp->f_namelen = MAXNAMELEN - 1;
-
-	id = huge_encode_dev(mp->m_ddev_targp->bt_dev);
-	statp->f_fsid = u64_to_fsid(id);
-
-	icount = percpu_counter_sum(&mp->m_icount);
-	ifree = percpu_counter_sum(&mp->m_ifree);
-	fdblocks = percpu_counter_sum(&mp->m_fdblocks);
+	st->f_type = XFS_SUPER_MAGIC;
+	st->f_namelen = MAXNAMELEN - 1;
+	st->f_bsize = mp->m_sb.sb_blocksize;
+	st->f_fsid = u64_to_fsid(huge_encode_dev(mp->m_ddev_targp->bt_dev));
 
-	spin_lock(&mp->m_sb_lock);
-	statp->f_bsize = sbp->sb_blocksize;
-	lsize = sbp->sb_logstart ? sbp->sb_logblocks : 0;
-	statp->f_blocks = sbp->sb_dblocks - lsize;
-	spin_unlock(&mp->m_sb_lock);
-
-	/* make sure statp->f_bfree does not underflow */
-	statp->f_bfree = max_t(int64_t, 0,
-				fdblocks - xfs_fdblocks_unavailable(mp));
-	statp->f_bavail = statp->f_bfree;
-
-	fakeinos = XFS_FSB_TO_INO(mp, statp->f_bfree);
-	statp->f_files = min(icount + fakeinos, (uint64_t)XFS_MAXINUMBER);
-	if (M_IGEO(mp)->maxicount)
-		statp->f_files = min_t(typeof(statp->f_files),
-					statp->f_files,
-					M_IGEO(mp)->maxicount);
-
-	/* If sb_icount overshot maxicount, report actual allocation */
-	statp->f_files = max_t(typeof(statp->f_files),
-					statp->f_files,
-					sbp->sb_icount);
-
-	/* make sure statp->f_ffree does not underflow */
-	ffree = statp->f_files - (icount - ifree);
-	statp->f_ffree = max_t(int64_t, ffree, 0);
+	xfs_statfs_data(mp, st);
+	xfs_statfs_inodes(mp, st);
 
 	if (XFS_IS_REALTIME_MOUNT(mp) &&
-	    (ip->i_diflags & (XFS_DIFLAG_RTINHERIT | XFS_DIFLAG_REALTIME))) {
-		s64	freertx;
-
-		statp->f_blocks = sbp->sb_rblocks;
-		freertx = percpu_counter_sum_positive(&mp->m_frextents);
-		statp->f_bavail = statp->f_bfree =
-			xfs_rtbxlen_to_blen(mp, freertx);
-	}
+	    (ip->i_diflags & (XFS_DIFLAG_RTINHERIT | XFS_DIFLAG_REALTIME)))
+		xfs_statfs_rt(mp, st);
 
 	if ((ip->i_diflags & XFS_DIFLAG_PROJINHERIT) &&
 	    ((mp->m_qflags & (XFS_PQUOTA_ACCT|XFS_PQUOTA_ENFD))) ==
 			      (XFS_PQUOTA_ACCT|XFS_PQUOTA_ENFD))
-		xfs_qm_statvfs(ip, statp);
+		xfs_qm_statvfs(ip, st);
 
+	/*
+	 * XFS does not distinguish between blocks available to privileged and
+	 * unprivileged users.
+	 */
+	st->f_bavail = st->f_bfree;
 	return 0;
 }
 
 STATIC void
-xfs_save_resvblks(struct xfs_mount *mp)
+xfs_save_resvblks(
+	struct xfs_mount	*mp)
 {
-	mp->m_resblks_save = mp->m_resblks;
-	xfs_reserve_blocks(mp, 0);
+	enum xfs_free_counter	i;
+
+	for (i = 0; i < XC_FREE_NR; i++) {
+		mp->m_free[i].res_saved = mp->m_free[i].res_total;
+		xfs_reserve_blocks(mp, i, 0);
+	}
 }
 
 STATIC void
-xfs_restore_resvblks(struct xfs_mount *mp)
+xfs_restore_resvblks(
+	struct xfs_mount	*mp)
 {
-	uint64_t resblks;
+	uint64_t		resblks;
+	enum xfs_free_counter	i;
 
-	if (mp->m_resblks_save) {
-		resblks = mp->m_resblks_save;
-		mp->m_resblks_save = 0;
-	} else
-		resblks = xfs_default_resblks(mp);
-
-	xfs_reserve_blocks(mp, resblks);
+	for (i = 0; i < XC_FREE_NR; i++) {
+		if (mp->m_free[i].res_saved) {
+			resblks = mp->m_free[i].res_saved;
+			mp->m_free[i].res_saved = 0;
+		} else
+			resblks = xfs_default_resblks(mp, i);
+		xfs_reserve_blocks(mp, i, resblks);
+	}
 }
 
 /*
@@ -950,6 +1005,7 @@ xfs_fs_freeze(
 	if (ret && !xfs_is_readonly(mp)) {
 		xfs_blockgc_start(mp);
 		xfs_inodegc_start(mp);
+		xfs_zone_gc_start(mp);
 	}
 
 	return ret;
@@ -971,6 +1027,7 @@ xfs_fs_unfreeze(
 	 * filesystem.
 	 */
 	if (!xfs_is_readonly(mp)) {
+		xfs_zone_gc_start(mp);
 		xfs_blockgc_start(mp);
 		xfs_inodegc_start(mp);
 	}
@@ -1032,6 +1089,19 @@ xfs_finish_flags(
 		return -EINVAL;
 	}
 
+	if (!xfs_has_zoned(mp)) {
+		if (mp->m_max_open_zones) {
+			xfs_warn(mp,
+"max_open_zones mount option only supported on zoned file systems.");
+			return -EINVAL;
+		}
+		if (mp->m_features & XFS_FEAT_NOLIFETIME) {
+			xfs_warn(mp,
+"nolifetime mount option only supported on zoned file systems.");
+			return -EINVAL;
+		}
+	}
+
 	return 0;
 }
 
@@ -1039,7 +1109,8 @@ static int
 xfs_init_percpu_counters(
 	struct xfs_mount	*mp)
 {
-	int		error;
+	int			error;
+	int			i;
 
 	error = percpu_counter_init(&mp->m_icount, 0, GFP_KERNEL);
 	if (error)
@@ -1049,30 +1120,29 @@ xfs_init_percpu_counters(
 	if (error)
 		goto free_icount;
 
-	error = percpu_counter_init(&mp->m_fdblocks, 0, GFP_KERNEL);
-	if (error)
-		goto free_ifree;
-
 	error = percpu_counter_init(&mp->m_delalloc_blks, 0, GFP_KERNEL);
 	if (error)
-		goto free_fdblocks;
+		goto free_ifree;
 
 	error = percpu_counter_init(&mp->m_delalloc_rtextents, 0, GFP_KERNEL);
 	if (error)
 		goto free_delalloc;
 
-	error = percpu_counter_init(&mp->m_frextents, 0, GFP_KERNEL);
-	if (error)
-		goto free_delalloc_rt;
+	for (i = 0; i < XC_FREE_NR; i++) {
+		error = percpu_counter_init(&mp->m_free[i].count, 0,
+				GFP_KERNEL);
+		if (error)
+			goto free_freecounters;
+	}
 
 	return 0;
 
-free_delalloc_rt:
+free_freecounters:
+	while (--i > 0)
+		percpu_counter_destroy(&mp->m_free[i].count);
 	percpu_counter_destroy(&mp->m_delalloc_rtextents);
 free_delalloc:
 	percpu_counter_destroy(&mp->m_delalloc_blks);
-free_fdblocks:
-	percpu_counter_destroy(&mp->m_fdblocks);
 free_ifree:
 	percpu_counter_destroy(&mp->m_ifree);
 free_icount:
@@ -1086,24 +1156,28 @@ xfs_reinit_percpu_counters(
 {
 	percpu_counter_set(&mp->m_icount, mp->m_sb.sb_icount);
 	percpu_counter_set(&mp->m_ifree, mp->m_sb.sb_ifree);
-	percpu_counter_set(&mp->m_fdblocks, mp->m_sb.sb_fdblocks);
-	percpu_counter_set(&mp->m_frextents, mp->m_sb.sb_frextents);
+	xfs_set_freecounter(mp, XC_FREE_BLOCKS, mp->m_sb.sb_fdblocks);
+	if (!xfs_has_zoned(mp))
+		xfs_set_freecounter(mp, XC_FREE_RTEXTENTS,
+				mp->m_sb.sb_frextents);
 }
 
 static void
 xfs_destroy_percpu_counters(
 	struct xfs_mount	*mp)
 {
+	enum xfs_free_counter	i;
+
+	for (i = 0; i < XC_FREE_NR; i++)
+		percpu_counter_destroy(&mp->m_free[i].count);
 	percpu_counter_destroy(&mp->m_icount);
 	percpu_counter_destroy(&mp->m_ifree);
-	percpu_counter_destroy(&mp->m_fdblocks);
 	ASSERT(xfs_is_shutdown(mp) ||
 	       percpu_counter_sum(&mp->m_delalloc_rtextents) == 0);
 	percpu_counter_destroy(&mp->m_delalloc_rtextents);
 	ASSERT(xfs_is_shutdown(mp) ||
 	       percpu_counter_sum(&mp->m_delalloc_blks) == 0);
 	percpu_counter_destroy(&mp->m_delalloc_blks);
-	percpu_counter_destroy(&mp->m_frextents);
 }
 
 static int
@@ -1184,6 +1258,18 @@ xfs_fs_shutdown(
 	xfs_force_shutdown(XFS_M(sb), SHUTDOWN_DEVICE_REMOVED);
 }
 
+static int
+xfs_fs_show_stats(
+	struct seq_file		*m,
+	struct dentry		*root)
+{
+	struct xfs_mount	*mp = XFS_M(root->d_sb);
+
+	if (xfs_has_zoned(mp) && IS_ENABLED(CONFIG_XFS_RT))
+		xfs_zoned_show_stats(m, mp);
+	return 0;
+}
+
 static const struct super_operations xfs_super_operations = {
 	.alloc_inode		= xfs_fs_alloc_inode,
 	.destroy_inode		= xfs_fs_destroy_inode,
@@ -1198,6 +1284,7 @@ static const struct super_operations xfs_super_operations = {
 	.nr_cached_objects	= xfs_fs_nr_cached_objects,
 	.free_cached_objects	= xfs_fs_free_cached_objects,
 	.shutdown		= xfs_fs_shutdown,
+	.show_stats		= xfs_fs_show_stats,
 };
 
 static int
@@ -1410,6 +1497,15 @@ xfs_fs_parse_param(
 		xfs_fs_warn_deprecated(fc, param, XFS_FEAT_NOATTR2, true);
 		parsing_mp->m_features |= XFS_FEAT_NOATTR2;
 		return 0;
+	case Opt_max_open_zones:
+		parsing_mp->m_max_open_zones = result.uint_32;
+		return 0;
+	case Opt_lifetime:
+		parsing_mp->m_features &= ~XFS_FEAT_NOLIFETIME;
+		return 0;
+	case Opt_nolifetime:
+		parsing_mp->m_features |= XFS_FEAT_NOLIFETIME;
+		return 0;
 	default:
 		xfs_warn(parsing_mp, "unknown mount option [%s].", param->key);
 		return -EINVAL;
@@ -1635,8 +1731,12 @@ xfs_fs_fill_super(
 #endif
 	}
 
-	/* Filesystem claims it needs repair, so refuse the mount. */
-	if (xfs_has_needsrepair(mp)) {
+	/*
+	 * Filesystem claims it needs repair, so refuse the mount unless
+	 * norecovery is also specified, in which case the filesystem can
+	 * be mounted with no risk of further damage.
+	 */
+	if (xfs_has_needsrepair(mp) && !xfs_has_norecovery(mp)) {
 		xfs_warn(mp, "Filesystem needs repair.  Please run xfs_repair.");
 		error = -EFSCORRUPTED;
 		goto out_free_sb;
@@ -1730,7 +1830,7 @@ xfs_fs_fill_super(
 		sb->s_time_max = XFS_LEGACY_TIME_MAX;
 	}
 	trace_xfs_inode_timestamp_range(mp, sb->s_time_min, sb->s_time_max);
-	sb->s_iflags |= SB_I_CGROUPWB;
+	sb->s_iflags |= SB_I_CGROUPWB | SB_I_ALLOW_HSM;
 
 	set_posix_acl_flag(sb);
 
@@ -1750,13 +1850,31 @@ xfs_fs_fill_super(
 		mp->m_features &= ~XFS_FEAT_DISCARD;
 	}
 
-	if (xfs_has_metadir(mp))
+	if (xfs_has_zoned(mp)) {
+		if (!xfs_has_metadir(mp)) {
+			xfs_alert(mp,
+		"metadir feature required for zoned realtime devices.");
+			error = -EINVAL;
+			goto out_filestream_unmount;
+		}
+		xfs_warn_experimental(mp, XFS_EXPERIMENTAL_ZONED);
+	} else if (xfs_has_metadir(mp)) {
 		xfs_warn_experimental(mp, XFS_EXPERIMENTAL_METADIR);
+	}
 
 	if (xfs_has_reflink(mp)) {
-		if (mp->m_sb.sb_rblocks) {
+		if (xfs_has_realtime(mp) &&
+		    !xfs_reflink_supports_rextsize(mp, mp->m_sb.sb_rextsize)) {
+			xfs_alert(mp,
+	"reflink not compatible with realtime extent size %u!",
+					mp->m_sb.sb_rextsize);
+			error = -EINVAL;
+			goto out_filestream_unmount;
+		}
+
+		if (xfs_has_zoned(mp)) {
 			xfs_alert(mp,
-	"reflink not compatible with realtime device!");
+	"reflink not compatible with zoned RT device!");
 			error = -EINVAL;
 			goto out_filestream_unmount;
 		}
@@ -1767,12 +1885,6 @@ xfs_fs_fill_super(
 		}
 	}
 
-	if (xfs_has_rmapbt(mp) && mp->m_sb.sb_rblocks) {
-		xfs_alert(mp,
-	"reverse mapping btree not compatible with realtime device!");
-		error = -EINVAL;
-		goto out_filestream_unmount;
-	}
 
 	if (xfs_has_exchange_range(mp))
 		xfs_warn_experimental(mp, XFS_EXPERIMENTAL_EXCHRANGE);
@@ -1891,6 +2003,9 @@ xfs_remount_rw(
 	/* Re-enable the background inode inactivation worker. */
 	xfs_inodegc_start(mp);
 
+	/* Restart zone reclaim */
+	xfs_zone_gc_start(mp);
+
 	return 0;
 }
 
@@ -1935,6 +2050,9 @@ xfs_remount_ro(
 	 */
 	xfs_inodegc_stop(mp);
 
+	/* Stop zone reclaim */
+	xfs_zone_gc_stop(mp);
+
 	/* Free the per-AG metadata reservation pool. */
 	xfs_fs_unreserve_ag_blocks(mp);
 
@@ -2056,6 +2174,7 @@ xfs_init_fs_context(
 	for (i = 0; i < XG_TYPE_MAX; i++)
 		xa_init(&mp->m_groups[i].xa);
 	mutex_init(&mp->m_growlock);
+	mutex_init(&mp->m_metafile_resv_lock);
 	INIT_WORK(&mp->m_flush_inodes_work, xfs_flush_inodes_worker);
 	INIT_DELAYED_WORK(&mp->m_reclaim_work, xfs_reclaim_worker);
 	mp->m_kobj.kobject.kset = xfs_kset;
@@ -2096,7 +2215,8 @@ static struct file_system_type xfs_fs_type = {
 	.init_fs_context	= xfs_init_fs_context,
 	.parameters		= xfs_fs_parameters,
 	.kill_sb		= xfs_kill_sb,
-	.fs_flags		= FS_REQUIRES_DEV | FS_ALLOW_IDMAP | FS_MGTIME,
+	.fs_flags		= FS_REQUIRES_DEV | FS_ALLOW_IDMAP | FS_MGTIME |
+				  FS_LBS,
 };
 MODULE_ALIAS_FS("xfs");