1 files changed, 564 insertions, 83 deletions

diff --git a/fs/xfs/libxfs/xfs_sb.c b/fs/xfs/libxfs/xfs_sb.c
index f4e84aa1d50a..cdd16dd805d7 100644
--- a/fs/xfs/libxfs/xfs_sb.c
+++ b/fs/xfs/libxfs/xfs_sb.c
@@ -25,24 +25,81 @@
 #include "xfs_da_format.h"
 #include "xfs_health.h"
 #include "xfs_ag.h"
+#include "xfs_rtbitmap.h"
+#include "xfs_exchrange.h"
+#include "xfs_rtgroup.h"
+#include "xfs_rtrmap_btree.h"
+#include "xfs_rtrefcount_btree.h"
 
 /*
  * Physical superblock buffer manipulations. Shared with libxfs in userspace.
  */
 
 /*
- * We support all XFS versions newer than a v4 superblock with V2 directories.
+ * Check that all the V4 feature bits that the V5 filesystem format requires are
+ * correctly set.
+ */
+static bool
+xfs_sb_validate_v5_features(
+	struct xfs_sb	*sbp)
+{
+	/* We must not have any unknown V4 feature bits set */
+	if (sbp->sb_versionnum & ~XFS_SB_VERSION_OKBITS)
+		return false;
+
+	/*
+	 * The CRC bit is considered an invalid V4 flag, so we have to add it
+	 * manually to the OKBITS mask.
+	 */
+	if (sbp->sb_features2 & ~(XFS_SB_VERSION2_OKBITS |
+				  XFS_SB_VERSION2_CRCBIT))
+		return false;
+
+	/* Now check all the required V4 feature flags are set. */
+
+#define V5_VERS_FLAGS	(XFS_SB_VERSION_NLINKBIT	| \
+			XFS_SB_VERSION_ALIGNBIT		| \
+			XFS_SB_VERSION_LOGV2BIT		| \
+			XFS_SB_VERSION_EXTFLGBIT	| \
+			XFS_SB_VERSION_DIRV2BIT		| \
+			XFS_SB_VERSION_MOREBITSBIT)
+
+#define V5_FEAT_FLAGS	(XFS_SB_VERSION2_LAZYSBCOUNTBIT	| \
+			XFS_SB_VERSION2_ATTR2BIT	| \
+			XFS_SB_VERSION2_PROJID32BIT	| \
+			XFS_SB_VERSION2_CRCBIT)
+
+	if ((sbp->sb_versionnum & V5_VERS_FLAGS) != V5_VERS_FLAGS)
+		return false;
+	if ((sbp->sb_features2 & V5_FEAT_FLAGS) != V5_FEAT_FLAGS)
+		return false;
+	return true;
+}
+
+/*
+ * We current support XFS v5 formats with known features and v4 superblocks with
+ * at least V2 directories.
  */
 bool
 xfs_sb_good_version(
 	struct xfs_sb	*sbp)
 {
-	/* all v5 filesystems are supported */
+	/*
+	 * All v5 filesystems are supported, but we must check that all the
+	 * required v4 feature flags are enabled correctly as the code checks
+	 * those flags and not for v5 support.
+	 */
 	if (xfs_sb_is_v5(sbp))
-		return true;
+		return xfs_sb_validate_v5_features(sbp);
 
 	/* versions prior to v4 are not supported */
-	if (XFS_SB_VERSION_NUM(sbp) < XFS_SB_VERSION_4)
+	if (XFS_SB_VERSION_NUM(sbp) != XFS_SB_VERSION_4)
+		return false;
+
+	/* We must not have any unknown v4 feature bits set */
+	if ((sbp->sb_versionnum & ~XFS_SB_VERSION_OKBITS) ||
+	    ((sbp->sb_versionnum & XFS_SB_VERSION_MOREBITSBIT) &&
+	     (sbp->sb_features2 & ~XFS_SB_VERSION2_OKBITS)))
 		return false;
 
 	/* V4 filesystems need v2 directories and unwritten extents */
@@ -51,12 +108,6 @@ xfs_sb_good_version(
 	if (!(sbp->sb_versionnum & XFS_SB_VERSION_EXTFLGBIT))
 		return false;
 
-	/* And must not have any unknown v4 feature bits set */
-	if ((sbp->sb_versionnum & ~XFS_SB_VERSION_OKBITS) ||
-	    ((sbp->sb_versionnum & XFS_SB_VERSION_MOREBITSBIT) &&
-	     (sbp->sb_features2 & ~XFS_SB_VERSION2_OKBITS)))
-		return false;
-
 	/* It's a supported v4 filesystem */
 	return true;
 }
@@ -70,6 +121,8 @@ xfs_sb_version_to_features(
 	/* optional V4 features */
 	if (sbp->sb_rblocks > 0)
 		features |= XFS_FEAT_REALTIME;
+	if (sbp->sb_versionnum & XFS_SB_VERSION_NLINKBIT)
+		features |= XFS_FEAT_NLINK;
 	if (sbp->sb_versionnum & XFS_SB_VERSION_ATTRBIT)
 		features |= XFS_FEAT_ATTR;
 	if (sbp->sb_versionnum & XFS_SB_VERSION_QUOTABIT)
@@ -89,8 +142,6 @@ xfs_sb_version_to_features(
 	if (sbp->sb_versionnum & XFS_SB_VERSION_MOREBITSBIT) {
 		if (sbp->sb_features2 & XFS_SB_VERSION2_LAZYSBCOUNTBIT)
 			features |= XFS_FEAT_LAZYSBCOUNT;
-		if (sbp->sb_features2 & XFS_SB_VERSION2_ATTR2BIT)
-			features |= XFS_FEAT_ATTR2;
 		if (sbp->sb_features2 & XFS_SB_VERSION2_PROJID32BIT)
 			features |= XFS_FEAT_PROJID32;
 		if (sbp->sb_features2 & XFS_SB_VERSION2_FTYPE)
@@ -102,7 +153,7 @@ xfs_sb_version_to_features(
 
 	/* Always on V5 features */
 	features |= XFS_FEAT_ALIGN | XFS_FEAT_LOGV2 | XFS_FEAT_EXTFLG |
-		    XFS_FEAT_LAZYSBCOUNT | XFS_FEAT_ATTR2 | XFS_FEAT_PROJID32 |
+		    XFS_FEAT_LAZYSBCOUNT | XFS_FEAT_PROJID32 |
 		    XFS_FEAT_V3INODES | XFS_FEAT_CRC | XFS_FEAT_PQUOTINO;
 
 	/* Optional V5 features */
@@ -124,6 +175,17 @@ xfs_sb_version_to_features(
 		features |= XFS_FEAT_BIGTIME;
 	if (sbp->sb_features_incompat & XFS_SB_FEAT_INCOMPAT_NEEDSREPAIR)
 		features |= XFS_FEAT_NEEDSREPAIR;
+	if (sbp->sb_features_incompat & XFS_SB_FEAT_INCOMPAT_NREXT64)
+		features |= XFS_FEAT_NREXT64;
+	if (sbp->sb_features_incompat & XFS_SB_FEAT_INCOMPAT_EXCHRANGE)
+		features |= XFS_FEAT_EXCHANGE_RANGE;
+	if (sbp->sb_features_incompat & XFS_SB_FEAT_INCOMPAT_PARENT)
+		features |= XFS_FEAT_PARENT;
+	if (sbp->sb_features_incompat & XFS_SB_FEAT_INCOMPAT_METADIR)
+		features |= XFS_FEAT_METADIR;
+	if (sbp->sb_features_incompat & XFS_SB_FEAT_INCOMPAT_ZONED)
+		features |= XFS_FEAT_ZONED;
+
 	return features;
 }
 
@@ -175,6 +237,73 @@ xfs_validate_sb_read(
 	return 0;
 }
 
+/* Return the number of extents covered by a single rt bitmap file */
+static xfs_rtbxlen_t
+xfs_extents_per_rbm(
+	struct xfs_sb		*sbp)
+{
+	if (xfs_sb_is_v5(sbp) &&
+	    (sbp->sb_features_incompat & XFS_SB_FEAT_INCOMPAT_METADIR))
+		return sbp->sb_rgextents;
+	return sbp->sb_rextents;
+}
+
+/*
+ * Return the payload size of a single rt bitmap block (without the metadata
+ * header if any).
+ */
+static inline unsigned int
+xfs_rtbmblock_size(
+	struct xfs_sb		*sbp)
+{
+	if (xfs_sb_is_v5(sbp) &&
+	    (sbp->sb_features_incompat & XFS_SB_FEAT_INCOMPAT_METADIR))
+		return sbp->sb_blocksize - sizeof(struct xfs_rtbuf_blkinfo);
+	return sbp->sb_blocksize;
+}
+
+static uint64_t
+xfs_expected_rbmblocks(
+	struct xfs_sb		*sbp)
+{
+	if (xfs_sb_is_v5(sbp) &&
+	    (sbp->sb_features_incompat & XFS_SB_FEAT_INCOMPAT_ZONED))
+		return 0;
+	return howmany_64(xfs_extents_per_rbm(sbp),
+			  NBBY * xfs_rtbmblock_size(sbp));
+}
+
+/* Validate the realtime geometry */
+bool
+xfs_validate_rt_geometry(
+	struct xfs_sb		*sbp)
+{
+	if (xfs_sb_is_v5(sbp) &&
+	    (sbp->sb_features_incompat & XFS_SB_FEAT_INCOMPAT_ZONED)) {
+		if (sbp->sb_rextsize != 1)
+			return false;
+	} else {
+		if (sbp->sb_rextsize * sbp->sb_blocksize > XFS_MAX_RTEXTSIZE ||
+		    sbp->sb_rextsize * sbp->sb_blocksize < XFS_MIN_RTEXTSIZE)
+			return false;
+	}
+
+	if (sbp->sb_rblocks == 0) {
+		if (sbp->sb_rextents != 0 || sbp->sb_rbmblocks != 0 ||
+		    sbp->sb_rextslog != 0 || sbp->sb_frextents != 0)
+			return false;
+		return true;
+	}
+
+	if (sbp->sb_rextents == 0 ||
+	    sbp->sb_rextents != div_u64(sbp->sb_rblocks, sbp->sb_rextsize) ||
+	    sbp->sb_rextslog != xfs_compute_rextslog(sbp->sb_rextents) ||
+	    sbp->sb_rbmblocks != xfs_expected_rbmblocks(sbp))
+		return false;
+
+	return true;
+}
+
 /* Check all the superblock fields we care about when writing one out. */
 STATIC int
 xfs_validate_sb_write(
@@ -208,14 +337,8 @@ xfs_validate_sb_write(
 	 * the kernel cannot support since we checked for unsupported bits in
 	 * the read verifier, which means that memory is corrupt.
 	 */
-	if (xfs_sb_has_compat_feature(sbp, XFS_SB_FEAT_COMPAT_UNKNOWN)) {
-		xfs_warn(mp,
-"Corruption detected in superblock compatible features (0x%x)!",
-			(sbp->sb_features_compat & XFS_SB_FEAT_COMPAT_UNKNOWN));
-		return -EFSCORRUPTED;
-	}
-
-	if (xfs_sb_has_ro_compat_feature(sbp, XFS_SB_FEAT_RO_COMPAT_UNKNOWN)) {
+	if (!xfs_is_readonly(mp) &&
+	    xfs_sb_has_ro_compat_feature(sbp, XFS_SB_FEAT_RO_COMPAT_UNKNOWN)) {
 		xfs_alert(mp,
 "Corruption detected in superblock read-only compatible features (0x%x)!",
 			(sbp->sb_features_ro_compat &
@@ -249,6 +372,106 @@ xfs_validate_sb_write(
 	return 0;
 }
 
+int
+xfs_compute_rgblklog(
+	xfs_rtxlen_t	rgextents,
+	xfs_rgblock_t	rextsize)
+{
+	uint64_t	rgblocks = (uint64_t)rgextents * rextsize;
+
+	return xfs_highbit64(rgblocks - 1) + 1;
+}
+
+static int
+xfs_validate_sb_rtgroups(
+	struct xfs_mount	*mp,
+	struct xfs_sb		*sbp)
+{
+	uint64_t		groups;
+	int			rgblklog;
+
+	if (sbp->sb_rextsize == 0) {
+		xfs_warn(mp,
+"Realtime extent size must not be zero.");
+		return -EINVAL;
+	}
+
+	if (sbp->sb_rgextents > XFS_MAX_RGBLOCKS / sbp->sb_rextsize) {
+		xfs_warn(mp,
+"Realtime group size (%u) must be less than %u rt extents.",
+				sbp->sb_rgextents,
+				XFS_MAX_RGBLOCKS / sbp->sb_rextsize);
+		return -EINVAL;
+	}
+
+	if (sbp->sb_rgextents < XFS_MIN_RGEXTENTS) {
+		xfs_warn(mp,
+"Realtime group size (%u) must be at least %u rt extents.",
+				sbp->sb_rgextents, XFS_MIN_RGEXTENTS);
+		return -EINVAL;
+	}
+
+	if (sbp->sb_rgcount > XFS_MAX_RGNUMBER) {
+		xfs_warn(mp,
+"Realtime groups (%u) must be less than %u.",
+				sbp->sb_rgcount, XFS_MAX_RGNUMBER);
+		return -EINVAL;
+	}
+
+	groups = howmany_64(sbp->sb_rextents, sbp->sb_rgextents);
+	if (groups != sbp->sb_rgcount) {
+		xfs_warn(mp,
+"Realtime groups (%u) do not cover the entire rt section; need (%llu) groups.",
+				sbp->sb_rgcount, groups);
+		return -EINVAL;
+	}
+
+	/* Exchange-range is required for fsr to work on realtime files */
+	if (!(sbp->sb_features_incompat & XFS_SB_FEAT_INCOMPAT_EXCHRANGE)) {
+		xfs_warn(mp,
+"Realtime groups feature requires exchange-range support.");
+		return -EINVAL;
+	}
+
+	rgblklog = xfs_compute_rgblklog(sbp->sb_rgextents, sbp->sb_rextsize);
+	if (sbp->sb_rgblklog != rgblklog) {
+		xfs_warn(mp,
+"Realtime group log (%d) does not match expected value (%d).",
+				sbp->sb_rgblklog, rgblklog);
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+static int
+xfs_validate_sb_zoned(
+	struct xfs_mount	*mp,
+	struct xfs_sb		*sbp)
+{
+	if (sbp->sb_frextents != 0) {
+		xfs_warn(mp,
+"sb_frextents must be zero for zoned file systems.");
+		return -EINVAL;
+	}
+
+	if (sbp->sb_rtstart && sbp->sb_rtstart < sbp->sb_dblocks) {
+		xfs_warn(mp,
+"sb_rtstart (%lld) overlaps sb_dblocks (%lld).",
+			sbp->sb_rtstart, sbp->sb_dblocks);
+		return -EINVAL;
+	}
+
+	if (sbp->sb_rtreserved && sbp->sb_rtreserved >= sbp->sb_rblocks) {
+		xfs_warn(mp,
+"sb_rtreserved (%lld) larger than sb_rblocks (%lld).",
+			sbp->sb_rtreserved, sbp->sb_rblocks);
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
 /* Check the validity of the SB. */
 STATIC int
 xfs_validate_sb_common(
@@ -260,14 +483,18 @@ xfs_validate_sb_common(
 	uint32_t		agcount = 0;
 	uint32_t		rem;
 	bool			has_dalign;
+	int			error;
 
 	if (!xfs_verify_magic(bp, dsb->sb_magicnum)) {
-		xfs_warn(mp, "bad magic number");
+		xfs_warn(mp,
+"Superblock has bad magic number 0x%x. Not an XFS filesystem?",
+			be32_to_cpu(dsb->sb_magicnum));
 		return -EWRONGFS;
 	}
 
 	if (!xfs_sb_good_version(sbp)) {
-		xfs_warn(mp, "bad version");
+		xfs_warn(mp,
+"Superblock has unknown features enabled or corrupted feature masks.");
 		return -EWRONGFS;
 	}
 
@@ -305,6 +532,38 @@ xfs_validate_sb_common(
 					 sbp->sb_inoalignmt, align);
 				return -EINVAL;
 			}
+
+			if (sbp->sb_spino_align &&
+			    (sbp->sb_spino_align > sbp->sb_inoalignmt ||
+			     (sbp->sb_inoalignmt % sbp->sb_spino_align) != 0)) {
+				xfs_warn(mp,
+"Sparse inode alignment (%u) is invalid, must be integer factor of (%u).",
+					sbp->sb_spino_align,
+					sbp->sb_inoalignmt);
+				return -EINVAL;
+			}
+		} else if (sbp->sb_spino_align) {
+			xfs_warn(mp,
+				"Sparse inode alignment (%u) should be zero.",
+				sbp->sb_spino_align);
+			return -EINVAL;
+		}
+
+		if (sbp->sb_features_incompat & XFS_SB_FEAT_INCOMPAT_METADIR) {
+			if (memchr_inv(sbp->sb_pad, 0, sizeof(sbp->sb_pad))) {
+				xfs_warn(mp,
+"Metadir superblock padding fields must be zero.");
+				return -EINVAL;
+			}
+
+			error = xfs_validate_sb_rtgroups(mp, sbp);
+			if (error)
+				return error;
+		}
+		if (sbp->sb_features_incompat & XFS_SB_FEAT_INCOMPAT_ZONED) {
+			error = xfs_validate_sb_zoned(mp, sbp);
+			if (error)
+				return error;
 		}
 	} else if (sbp->sb_qflags & (XFS_PQUOTA_ENFD | XFS_GQUOTA_ENFD |
 				XFS_PQUOTA_CHKD | XFS_GQUOTA_CHKD)) {
@@ -358,7 +617,6 @@ xfs_validate_sb_common(
 	    sbp->sb_inodelog < XFS_DINODE_MIN_LOG			||
 	    sbp->sb_inodelog > XFS_DINODE_MAX_LOG			||
 	    sbp->sb_inodesize != (1 << sbp->sb_inodelog)		||
-	    sbp->sb_logsunit > XLOG_MAX_RECORD_BSIZE			||
 	    sbp->sb_inopblock != howmany(sbp->sb_blocksize,sbp->sb_inodesize) ||
 	    XFS_FSB_TO_B(mp, sbp->sb_agblocks) < XFS_MIN_AG_BYTES	||
 	    XFS_FSB_TO_B(mp, sbp->sb_agblocks) > XFS_MAX_AG_BYTES	||
@@ -376,38 +634,68 @@ xfs_validate_sb_common(
 		return -EFSCORRUPTED;
 	}
 
-	/* Validate the realtime geometry; stolen from xfs_repair */
-	if (sbp->sb_rextsize * sbp->sb_blocksize > XFS_MAX_RTEXTSIZE ||
-	    sbp->sb_rextsize * sbp->sb_blocksize < XFS_MIN_RTEXTSIZE) {
+	/*
+	 * Logs that are too large are not supported at all. Reject them
+	 * outright. Logs that are too small are tolerated on v4 filesystems,
+	 * but we can only check that when mounting the log. Hence we skip
+	 * those checks here.
+	 */
+	if (sbp->sb_logblocks > XFS_MAX_LOG_BLOCKS) {
 		xfs_notice(mp,
-			"realtime extent sanity check failed");
+		"Log size 0x%x blocks too large, maximum size is 0x%llx blocks",
+			 sbp->sb_logblocks, XFS_MAX_LOG_BLOCKS);
 		return -EFSCORRUPTED;
 	}
 
-	if (sbp->sb_rblocks == 0) {
-		if (sbp->sb_rextents != 0 || sbp->sb_rbmblocks != 0 ||
-		    sbp->sb_rextslog != 0 || sbp->sb_frextents != 0) {
+	if (XFS_FSB_TO_B(mp, sbp->sb_logblocks) > XFS_MAX_LOG_BYTES) {
+		xfs_warn(mp,
+		"log size 0x%llx bytes too large, maximum size is 0x%llx bytes",
+			 XFS_FSB_TO_B(mp, sbp->sb_logblocks),
+			 XFS_MAX_LOG_BYTES);
+		return -EFSCORRUPTED;
+	}
+
+	/*
+	 * Do not allow filesystems with corrupted log sector or stripe units to
+	 * be mounted. We cannot safely size the iclogs or write to the log if
+	 * the log stripe unit is not valid.
+	 */
+	if (sbp->sb_versionnum & XFS_SB_VERSION_SECTORBIT) {
+		if (sbp->sb_logsectsize != (1U << sbp->sb_logsectlog)) {
 			xfs_notice(mp,
-				"realtime zeroed geometry check failed");
+			"log sector size in bytes/log2 (0x%x/0x%x) must match",
+				sbp->sb_logsectsize, 1U << sbp->sb_logsectlog);
 			return -EFSCORRUPTED;
 		}
-	} else {
-		uint64_t	rexts;
-		uint64_t	rbmblocks;
-
-		rexts = div_u64(sbp->sb_rblocks, sbp->sb_rextsize);
-		rbmblocks = howmany_64(sbp->sb_rextents,
-				       NBBY * sbp->sb_blocksize);
+	} else if (sbp->sb_logsectsize || sbp->sb_logsectlog) {
+		xfs_notice(mp,
+		"log sector size in bytes/log2 (0x%x/0x%x) are not zero",
+			sbp->sb_logsectsize, sbp->sb_logsectlog);
+		return -EFSCORRUPTED;
+	}
 
-		if (sbp->sb_rextents != rexts ||
-		    sbp->sb_rextslog != xfs_highbit32(sbp->sb_rextents) ||
-		    sbp->sb_rbmblocks != rbmblocks) {
+	if (sbp->sb_logsunit > 1) {
+		if (sbp->sb_logsunit % sbp->sb_blocksize) {
+			xfs_notice(mp,
+		"log stripe unit 0x%x bytes must be a multiple of block size",
+				sbp->sb_logsunit);
+			return -EFSCORRUPTED;
+		}
+		if (sbp->sb_logsunit > XLOG_MAX_RECORD_BSIZE) {
 			xfs_notice(mp,
-				"realtime geometry sanity check failed");
+		"log stripe unit 0x%x bytes over maximum size (0x%x bytes)",
+				sbp->sb_logsunit, XLOG_MAX_RECORD_BSIZE);
 			return -EFSCORRUPTED;
 		}
 	}
 
+	if (!xfs_validate_rt_geometry(sbp)) {
+		xfs_notice(mp,
+			"realtime %sgeometry check failed",
+			sbp->sb_rblocks ? "" : "zeroed ");
+		return -EFSCORRUPTED;
+	}
+
 	/*
 	 * Either (sb_unit and !hasdalign) or (!sb_unit and hasdalign)
 	 * would imply the image is corrupted.
@@ -419,7 +707,8 @@ xfs_validate_sb_common(
 	}
 
 	if (!xfs_validate_stripe_geometry(mp, XFS_FSB_TO_B(mp, sbp->sb_unit),
-			XFS_FSB_TO_B(mp, sbp->sb_width), 0, false))
+			XFS_FSB_TO_B(mp, sbp->sb_width), 0,
+			xfs_buf_daddr(bp) == XFS_SB_DADDR, false))
 		return -EFSCORRUPTED;
 
 	/*
@@ -443,6 +732,14 @@ xfs_validate_sb_common(
 void
 xfs_sb_quota_from_disk(struct xfs_sb *sbp)
 {
+	if (xfs_sb_is_v5(sbp) &&
+	    (sbp->sb_features_incompat & XFS_SB_FEAT_INCOMPAT_METADIR)) {
+		sbp->sb_uquotino = NULLFSINO;
+		sbp->sb_gquotino = NULLFSINO;
+		sbp->sb_pquotino = NULLFSINO;
+		return;
+	}
+
 	/*
 	 * older mkfs doesn't initialize quota inodes to NULLFSINO. This
 	 * leads to in-core values having two different values for a quota
@@ -566,6 +863,28 @@ __xfs_sb_from_disk(
 	/* Convert on-disk flags to in-memory flags? */
 	if (convert_xquota)
 		xfs_sb_quota_from_disk(to);
+
+	if (to->sb_features_incompat & XFS_SB_FEAT_INCOMPAT_METADIR) {
+		to->sb_metadirino = be64_to_cpu(from->sb_metadirino);
+		to->sb_rgblklog = from->sb_rgblklog;
+		memcpy(to->sb_pad, from->sb_pad, sizeof(to->sb_pad));
+		to->sb_rgcount = be32_to_cpu(from->sb_rgcount);
+		to->sb_rgextents = be32_to_cpu(from->sb_rgextents);
+		to->sb_rbmino = NULLFSINO;
+		to->sb_rsumino = NULLFSINO;
+	} else {
+		to->sb_metadirino = NULLFSINO;
+		to->sb_rgcount = 1;
+		to->sb_rgextents = 0;
+	}
+
+	if (to->sb_features_incompat & XFS_SB_FEAT_INCOMPAT_ZONED) {
+		to->sb_rtstart = be64_to_cpu(from->sb_rtstart);
+		to->sb_rtreserved = be64_to_cpu(from->sb_rtreserved);
+	} else {
+		to->sb_rtstart = 0;
+		to->sb_rtreserved = 0;
+	}
 }
 
 void
@@ -583,6 +902,15 @@ xfs_sb_quota_to_disk(
 {
 	uint16_t	qflags = from->sb_qflags;
 
+	if (xfs_sb_is_v5(from) &&
+	    (from->sb_features_incompat & XFS_SB_FEAT_INCOMPAT_METADIR)) {
+		to->sb_qflags = cpu_to_be16(from->sb_qflags);
+		to->sb_uquotino = cpu_to_be64(0);
+		to->sb_gquotino = cpu_to_be64(0);
+		to->sb_pquotino = cpu_to_be64(0);
+		return;
+	}
+
 	to->sb_uquotino = cpu_to_be64(from->sb_uquotino);
 
 	/*
@@ -713,6 +1041,21 @@ xfs_sb_to_disk(
 	to->sb_lsn = cpu_to_be64(from->sb_lsn);
 	if (from->sb_features_incompat & XFS_SB_FEAT_INCOMPAT_META_UUID)
 		uuid_copy(&to->sb_meta_uuid, &from->sb_meta_uuid);
+
+	if (from->sb_features_incompat & XFS_SB_FEAT_INCOMPAT_METADIR) {
+		to->sb_metadirino = cpu_to_be64(from->sb_metadirino);
+		to->sb_rgblklog = from->sb_rgblklog;
+		memset(to->sb_pad, 0, sizeof(to->sb_pad));
+		to->sb_rgcount = cpu_to_be32(from->sb_rgcount);
+		to->sb_rgextents = cpu_to_be32(from->sb_rgextents);
+		to->sb_rbmino = cpu_to_be64(0);
+		to->sb_rsumino = cpu_to_be64(0);
+	}
+
+	if (from->sb_features_incompat & XFS_SB_FEAT_INCOMPAT_ZONED) {
+		to->sb_rtstart = cpu_to_be64(from->sb_rtstart);
+		to->sb_rtreserved = cpu_to_be64(from->sb_rtreserved);
+	}
 }
 
 /*
@@ -842,6 +1185,49 @@ const struct xfs_buf_ops xfs_sb_quiet_buf_ops = {
 	.verify_write = xfs_sb_write_verify,
 };
 
+/* Compute cached rt geometry from the incore sb. */
+void
+xfs_sb_mount_rextsize(
+	struct xfs_mount	*mp,
+	struct xfs_sb		*sbp)
+{
+	struct xfs_groups	*rgs = &mp->m_groups[XG_TYPE_RTG];
+
+	mp->m_rtxblklog = log2_if_power2(sbp->sb_rextsize);
+	mp->m_rtxblkmask = mask64_if_power2(sbp->sb_rextsize);
+
+	if (xfs_sb_is_v5(sbp) &&
+	    (sbp->sb_features_incompat & XFS_SB_FEAT_INCOMPAT_METADIR)) {
+		rgs->blocks = sbp->sb_rgextents * sbp->sb_rextsize;
+		rgs->blklog = mp->m_sb.sb_rgblklog;
+		rgs->blkmask = xfs_mask32lo(mp->m_sb.sb_rgblklog);
+		rgs->start_fsb = mp->m_sb.sb_rtstart;
+		if (xfs_sb_has_incompat_feature(sbp,
+				XFS_SB_FEAT_INCOMPAT_ZONE_GAPS))
+			rgs->has_daddr_gaps = true;
+	} else {
+		rgs->blocks = 0;
+		rgs->blklog = 0;
+		rgs->blkmask = (uint64_t)-1;
+	}
+}
+
+/* Update incore sb rt extent size, then recompute the cached rt geometry. */
+void
+xfs_mount_sb_set_rextsize(
+	struct xfs_mount	*mp,
+	struct xfs_sb		*sbp,
+	xfs_agblock_t		rextsize)
+{
+	sbp->sb_rextsize = rextsize;
+	if (xfs_sb_is_v5(sbp) &&
+	    (sbp->sb_features_incompat & XFS_SB_FEAT_INCOMPAT_METADIR))
+		sbp->sb_rgblklog = xfs_compute_rgblklog(sbp->sb_rgextents,
+							rextsize);
+
+	xfs_sb_mount_rextsize(mp, sbp);
+}
+
 /*
  * xfs_mount_common
  *
@@ -856,36 +1242,57 @@ xfs_sb_mount_common(
 	struct xfs_mount	*mp,
 	struct xfs_sb		*sbp)
 {
-	mp->m_agfrotor = mp->m_agirotor = 0;
+	struct xfs_groups	*ags = &mp->m_groups[XG_TYPE_AG];
+
+	mp->m_agfrotor = 0;
+	atomic_set(&mp->m_agirotor, 0);
 	mp->m_maxagi = mp->m_sb.sb_agcount;
 	mp->m_blkbit_log = sbp->sb_blocklog + XFS_NBBYLOG;
 	mp->m_blkbb_log = sbp->sb_blocklog - BBSHIFT;
 	mp->m_sectbb_log = sbp->sb_sectlog - BBSHIFT;
 	mp->m_agno_log = xfs_highbit32(sbp->sb_agcount - 1) + 1;
 	mp->m_blockmask = sbp->sb_blocksize - 1;
-	mp->m_blockwsize = sbp->sb_blocksize >> XFS_WORDLOG;
-	mp->m_blockwmask = mp->m_blockwsize - 1;
+	mp->m_blockwsize = xfs_rtbmblock_size(sbp) >> XFS_WORDLOG;
+	mp->m_rtx_per_rbmblock = mp->m_blockwsize << XFS_NBWORDLOG;
+
+	ags->blocks = mp->m_sb.sb_agblocks;
+	ags->blklog = mp->m_sb.sb_agblklog;
+	ags->blkmask = xfs_mask32lo(mp->m_sb.sb_agblklog);
+
+	xfs_sb_mount_rextsize(mp, sbp);
 
-	mp->m_alloc_mxr[0] = xfs_allocbt_maxrecs(mp, sbp->sb_blocksize, 1);
-	mp->m_alloc_mxr[1] = xfs_allocbt_maxrecs(mp, sbp->sb_blocksize, 0);
+	mp->m_alloc_mxr[0] = xfs_allocbt_maxrecs(mp, sbp->sb_blocksize, true);
+	mp->m_alloc_mxr[1] = xfs_allocbt_maxrecs(mp, sbp->sb_blocksize, false);
 	mp->m_alloc_mnr[0] = mp->m_alloc_mxr[0] / 2;
 	mp->m_alloc_mnr[1] = mp->m_alloc_mxr[1] / 2;
 
-	mp->m_bmap_dmxr[0] = xfs_bmbt_maxrecs(mp, sbp->sb_blocksize, 1);
-	mp->m_bmap_dmxr[1] = xfs_bmbt_maxrecs(mp, sbp->sb_blocksize, 0);
+	mp->m_bmap_dmxr[0] = xfs_bmbt_maxrecs(mp, sbp->sb_blocksize, true);
+	mp->m_bmap_dmxr[1] = xfs_bmbt_maxrecs(mp, sbp->sb_blocksize, false);
 	mp->m_bmap_dmnr[0] = mp->m_bmap_dmxr[0] / 2;
 	mp->m_bmap_dmnr[1] = mp->m_bmap_dmxr[1] / 2;
 
-	mp->m_rmap_mxr[0] = xfs_rmapbt_maxrecs(sbp->sb_blocksize, 1);
-	mp->m_rmap_mxr[1] = xfs_rmapbt_maxrecs(sbp->sb_blocksize, 0);
+	mp->m_rmap_mxr[0] = xfs_rmapbt_maxrecs(mp, sbp->sb_blocksize, true);
+	mp->m_rmap_mxr[1] = xfs_rmapbt_maxrecs(mp, sbp->sb_blocksize, false);
 	mp->m_rmap_mnr[0] = mp->m_rmap_mxr[0] / 2;
 	mp->m_rmap_mnr[1] = mp->m_rmap_mxr[1] / 2;
 
-	mp->m_refc_mxr[0] = xfs_refcountbt_maxrecs(sbp->sb_blocksize, true);
-	mp->m_refc_mxr[1] = xfs_refcountbt_maxrecs(sbp->sb_blocksize, false);
+	mp->m_rtrmap_mxr[0] = xfs_rtrmapbt_maxrecs(mp, sbp->sb_blocksize, true);
+	mp->m_rtrmap_mxr[1] = xfs_rtrmapbt_maxrecs(mp, sbp->sb_blocksize, false);
+	mp->m_rtrmap_mnr[0] = mp->m_rtrmap_mxr[0] / 2;
+	mp->m_rtrmap_mnr[1] = mp->m_rtrmap_mxr[1] / 2;
+
+	mp->m_refc_mxr[0] = xfs_refcountbt_maxrecs(mp, sbp->sb_blocksize, true);
+	mp->m_refc_mxr[1] = xfs_refcountbt_maxrecs(mp, sbp->sb_blocksize, false);
 	mp->m_refc_mnr[0] = mp->m_refc_mxr[0] / 2;
 	mp->m_refc_mnr[1] = mp->m_refc_mxr[1] / 2;
 
+	mp->m_rtrefc_mxr[0] = xfs_rtrefcountbt_maxrecs(mp, sbp->sb_blocksize,
+			true);
+	mp->m_rtrefc_mxr[1] = xfs_rtrefcountbt_maxrecs(mp, sbp->sb_blocksize,
+			false);
+	mp->m_rtrefc_mnr[0] = mp->m_rtrefc_mxr[0] / 2;
+	mp->m_rtrefc_mnr[1] = mp->m_rtrefc_mxr[1] / 2;
+
 	mp->m_bsize = XFS_FSB_TO_BB(mp, 1);
 	mp->m_alloc_set_aside = xfs_alloc_set_aside(mp);
 	mp->m_ag_max_usable = xfs_alloc_ag_max_usable(mp);
@@ -913,9 +1320,22 @@ xfs_log_sb(
 	 * the counters from the AGF block counts.
 	 */
 	if (xfs_has_lazysbcount(mp)) {
-		mp->m_sb.sb_icount = percpu_counter_sum(&mp->m_icount);
-		mp->m_sb.sb_ifree = percpu_counter_sum(&mp->m_ifree);
-		mp->m_sb.sb_fdblocks = percpu_counter_sum(&mp->m_fdblocks);
+		mp->m_sb.sb_icount = percpu_counter_sum_positive(&mp->m_icount);
+		mp->m_sb.sb_ifree = min_t(uint64_t,
+				percpu_counter_sum_positive(&mp->m_ifree),
+				mp->m_sb.sb_icount);
+		mp->m_sb.sb_fdblocks = xfs_sum_freecounter(mp, XC_FREE_BLOCKS);
+	}
+
+	/*
+	 * sb_frextents was added to the lazy sb counters when the rt groups
+	 * feature was introduced.  This counter can go negative due to the way
+	 * we handle nearly-lockless reservations, so we must use the _positive
+	 * variant here to avoid writing out nonsense frextents.
+	 */
+	if (xfs_has_rtgroups(mp) && !xfs_has_zoned(mp)) {
+		mp->m_sb.sb_frextents =
+				xfs_sum_freecounter(mp, XC_FREE_RTEXTENTS);
 	}
 
 	xfs_sb_to_disk(bp->b_addr, &mp->m_sb);
@@ -967,18 +1387,17 @@ int
 xfs_update_secondary_sbs(
 	struct xfs_mount	*mp)
 {
-	struct xfs_perag	*pag;
-	xfs_agnumber_t		agno = 1;
+	struct xfs_perag	*pag = NULL;
 	int			saved_error = 0;
 	int			error = 0;
 	LIST_HEAD		(buffer_list);
 
 	/* update secondary superblocks. */
-	for_each_perag_from(mp, agno, pag) {
+	while ((pag = xfs_perag_next_from(mp, pag, 1))) {
 		struct xfs_buf		*bp;
 
 		error = xfs_buf_get(mp->m_ddev_targp,
-				 XFS_AG_DADDR(mp, pag->pag_agno, XFS_SB_DADDR),
+				 XFS_AG_DADDR(mp, pag_agno(pag), XFS_SB_DADDR),
 				 XFS_FSS_TO_BB(mp, 1), &bp);
 		/*
 		 * If we get an error reading or writing alternate superblocks,
@@ -990,7 +1409,7 @@ xfs_update_secondary_sbs(
 		if (error) {
 			xfs_warn(mp,
 		"error allocating secondary superblock for ag %d",
-				pag->pag_agno);
+				pag_agno(pag));
 			if (!saved_error)
 				saved_error = error;
 			continue;
@@ -1004,26 +1423,22 @@ xfs_update_secondary_sbs(
 		xfs_buf_relse(bp);
 
 		/* don't hold too many buffers at once */
-		if (agno % 16)
+		if (pag_agno(pag) % 16)
 			continue;
 
 		error = xfs_buf_delwri_submit(&buffer_list);
 		if (error) {
 			xfs_warn(mp,
 		"write error %d updating a secondary superblock near ag %d",
-				error, pag->pag_agno);
+				error, pag_agno(pag));
 			if (!saved_error)
 				saved_error = error;
 			continue;
 		}
 	}
 	error = xfs_buf_delwri_submit(&buffer_list);
-	if (error) {
-		xfs_warn(mp,
-		"write error %d updating a secondary superblock near ag %d",
-			error, agno);
-	}
-
+	if (error)
+		xfs_warn(mp, "error %d writing secondary superblocks", error);
 	return saved_error ? saved_error : error;
 }
 
@@ -1033,10 +1448,12 @@ xfs_update_secondary_sbs(
  */
 int
 xfs_sync_sb_buf(
-	struct xfs_mount	*mp)
+	struct xfs_mount	*mp,
+	bool			update_rtsb)
 {
 	struct xfs_trans	*tp;
 	struct xfs_buf		*bp;
+	struct xfs_buf		*rtsb_bp = NULL;
 	int			error;
 
 	error = xfs_trans_alloc(mp, &M_RES(mp)->tr_sb, 0, 0, 0, &tp);
@@ -1046,6 +1463,11 @@ xfs_sync_sb_buf(
 	bp = xfs_trans_getsb(tp);
 	xfs_log_sb(tp);
 	xfs_trans_bhold(tp, bp);
+	if (update_rtsb) {
+		rtsb_bp = xfs_log_rtsb(tp, bp);
+		if (rtsb_bp)
+			xfs_trans_bhold(tp, rtsb_bp);
+	}
 	xfs_trans_set_sync(tp);
 	error = xfs_trans_commit(tp);
 	if (error)
@@ -1054,7 +1476,11 @@ xfs_sync_sb_buf(
 	 * write out the sb buffer to get the changes to disk
 	 */
 	error = xfs_bwrite(bp);
+	if (!error && rtsb_bp)
+		error = xfs_bwrite(rtsb_bp);
 out:
+	if (rtsb_bp)
+		xfs_buf_relse(rtsb_bp);
 	xfs_buf_relse(bp);
 	return error;
 }
@@ -1096,7 +1522,8 @@ xfs_fs_geometry(
 	geo->version = XFS_FSOP_GEOM_VERSION;
 	geo->flags = XFS_FSOP_GEOM_FLAGS_NLINK |
 		     XFS_FSOP_GEOM_FLAGS_DIRV2 |
-		     XFS_FSOP_GEOM_FLAGS_EXTFLG;
+		     XFS_FSOP_GEOM_FLAGS_EXTFLG |
+		     XFS_FSOP_GEOM_FLAGS_ATTR2;
 	if (xfs_has_attr(mp))
 		geo->flags |= XFS_FSOP_GEOM_FLAGS_ATTR;
 	if (xfs_has_quota(mp))
@@ -1109,8 +1536,6 @@ xfs_fs_geometry(
 		geo->flags |= XFS_FSOP_GEOM_FLAGS_DIRV2CI;
 	if (xfs_has_lazysbcount(mp))
 		geo->flags |= XFS_FSOP_GEOM_FLAGS_LAZYSB;
-	if (xfs_has_attr2(mp))
-		geo->flags |= XFS_FSOP_GEOM_FLAGS_ATTR2;
 	if (xfs_has_projid32(mp))
 		geo->flags |= XFS_FSOP_GEOM_FLAGS_PROJID32;
 	if (xfs_has_crc(mp))
@@ -1129,12 +1554,22 @@ xfs_fs_geometry(
 		geo->flags |= XFS_FSOP_GEOM_FLAGS_BIGTIME;
 	if (xfs_has_inobtcounts(mp))
 		geo->flags |= XFS_FSOP_GEOM_FLAGS_INOBTCNT;
+	if (xfs_has_parent(mp))
+		geo->flags |= XFS_FSOP_GEOM_FLAGS_PARENT;
 	if (xfs_has_sector(mp)) {
 		geo->flags |= XFS_FSOP_GEOM_FLAGS_SECTOR;
 		geo->logsectsize = sbp->sb_logsectsize;
 	} else {
 		geo->logsectsize = BBSIZE;
 	}
+	if (xfs_has_large_extent_counts(mp))
+		geo->flags |= XFS_FSOP_GEOM_FLAGS_NREXT64;
+	if (xfs_has_exchange_range(mp))
+		geo->flags |= XFS_FSOP_GEOM_FLAGS_EXCHANGE_RANGE;
+	if (xfs_has_metadir(mp))
+		geo->flags |= XFS_FSOP_GEOM_FLAGS_METADIR;
+	if (xfs_has_zoned(mp))
+		geo->flags |= XFS_FSOP_GEOM_FLAGS_ZONED;
 	geo->rtsectsize = sbp->sb_blocksize;
 	geo->dirblocksize = xfs_dir2_dirblock_bytes(sbp);
 
@@ -1150,6 +1585,15 @@ xfs_fs_geometry(
 		return;
 
 	geo->version = XFS_FSOP_GEOM_VERSION_V5;
+
+	if (xfs_has_rtgroups(mp)) {
+		geo->rgcount = sbp->sb_rgcount;
+		geo->rgextents = sbp->sb_rgextents;
+	}
+	if (xfs_has_zoned(mp)) {
+		geo->rtstart = sbp->sb_rtstart;
+		geo->rtreserved = sbp->sb_rtreserved;
+	}
 }
 
 /* Read a secondary superblock. */
@@ -1167,6 +1611,8 @@ xfs_sb_read_secondary(
 	error = xfs_trans_read_buf(mp, tp, mp->m_ddev_targp,
 			XFS_AG_DADDR(mp, agno, XFS_SB_BLOCK(mp)),
 			XFS_FSS_TO_BB(mp, 1), 0, &bp, &xfs_sb_buf_ops);
+	if (xfs_metadata_is_sick(error))
+		xfs_agno_mark_sick(mp, agno, XFS_SICK_AG_SB);
 	if (error)
 		return error;
 	xfs_buf_set_ref(bp, XFS_SSB_REF);
@@ -1198,8 +1644,10 @@ xfs_sb_get_secondary(
 }
 
 /*
- * sunit, swidth, sectorsize(optional with 0) should be all in bytes,
- * so users won't be confused by values in error messages.
+ * sunit, swidth, sectorsize(optional with 0) should be all in bytes, so users
+ * won't be confused by values in error messages.  This function returns false
+ * if the stripe geometry is invalid and the caller is unable to repair the
+ * stripe configuration later in the mount process.
  */
 bool
 xfs_validate_stripe_geometry(
@@ -1207,20 +1655,21 @@ xfs_validate_stripe_geometry(
 	__s64			sunit,
 	__s64			swidth,
 	int			sectorsize,
+	bool			may_repair,
 	bool			silent)
 {
 	if (swidth > INT_MAX) {
 		if (!silent)
 			xfs_notice(mp,
 "stripe width (%lld) is too large", swidth);
-		return false;
+		goto check_override;
 	}
 
 	if (sunit > swidth) {
 		if (!silent)
 			xfs_notice(mp,
 "stripe unit (%lld) is larger than the stripe width (%lld)", sunit, swidth);
-		return false;
+		goto check_override;
 	}
 
 	if (sectorsize && (int)sunit % sectorsize) {
@@ -1228,21 +1677,21 @@ xfs_validate_stripe_geometry(
 			xfs_notice(mp,
 "stripe unit (%lld) must be a multiple of the sector size (%d)",
 				   sunit, sectorsize);
-		return false;
+		goto check_override;
 	}
 
 	if (sunit && !swidth) {
 		if (!silent)
 			xfs_notice(mp,
 "invalid stripe unit (%lld) and stripe width of 0", sunit);
-		return false;
+		goto check_override;
 	}
 
 	if (!sunit && swidth) {
 		if (!silent)
 			xfs_notice(mp,
 "invalid stripe width (%lld) and stripe unit of 0", swidth);
-		return false;
+		goto check_override;
 	}
 
 	if (sunit && (int)swidth % (int)sunit) {
@@ -1250,7 +1699,39 @@ xfs_validate_stripe_geometry(
 			xfs_notice(mp,
 "stripe width (%lld) must be a multiple of the stripe unit (%lld)",
 				   swidth, sunit);
-		return false;
+		goto check_override;
 	}
 	return true;
+
+check_override:
+	if (!may_repair)
+		return false;
+	/*
+	 * During mount, mp->m_dalign will not be set unless the sunit mount
+	 * option was set. If it was set, ignore the bad stripe alignment values
+	 * and allow the validation and overwrite later in the mount process to
+	 * attempt to overwrite the bad stripe alignment values with the values
+	 * supplied by mount options.
+	 */
+	if (!mp->m_dalign)
+		return false;
+	if (!silent)
+		xfs_notice(mp,
+"Will try to correct with specified mount options sunit (%d) and swidth (%d)",
+			BBTOB(mp->m_dalign), BBTOB(mp->m_swidth));
+	return true;
+}
+
+/*
+ * Compute the maximum level number of the realtime summary file, as defined by
+ * mkfs.  The historic use of highbit32 on a 64-bit quantity prohibited correct
+ * use of rt volumes with more than 2^32 extents.
+ */
+uint8_t
+xfs_compute_rextslog(
+	xfs_rtbxlen_t		rtextents)
+{
+	if (!rtextents)
+		return 0;
+	return xfs_highbit64(rtextents);
 }