1 files changed, 194 insertions, 79 deletions

diff --git a/fs/xfs/xfs_inode_item_recover.c b/fs/xfs/xfs_inode_item_recover.c
index 239dd2e3384e..9d1999d41be1 100644
--- a/fs/xfs/xfs_inode_item_recover.c
+++ b/fs/xfs/xfs_inode_item_recover.c
@@ -22,19 +22,21 @@
 #include "xfs_log_recover.h"
 #include "xfs_icache.h"
 #include "xfs_bmap_btree.h"
+#include "xfs_rtrmap_btree.h"
+#include "xfs_rtrefcount_btree.h"
 
 STATIC void
 xlog_recover_inode_ra_pass2(
 	struct xlog                     *log,
 	struct xlog_recover_item        *item)
 {
-	if (item->ri_buf[0].i_len == sizeof(struct xfs_inode_log_format)) {
-		struct xfs_inode_log_format	*ilfp = item->ri_buf[0].i_addr;
+	if (item->ri_buf[0].iov_len == sizeof(struct xfs_inode_log_format)) {
+		struct xfs_inode_log_format	*ilfp = item->ri_buf[0].iov_base;
 
 		xlog_buf_readahead(log, ilfp->ilf_blkno, ilfp->ilf_len,
 				   &xfs_inode_buf_ra_ops);
 	} else {
-		struct xfs_inode_log_format_32	*ilfp = item->ri_buf[0].i_addr;
+		struct xfs_inode_log_format_32	*ilfp = item->ri_buf[0].iov_base;
 
 		xlog_buf_readahead(log, ilfp->ilf_blkno, ilfp->ilf_len,
 				   &xfs_inode_buf_ra_ops);
@@ -142,6 +144,29 @@ xfs_log_dinode_to_disk_ts(
 	return ts;
 }
 
+static inline bool xfs_log_dinode_has_large_extent_counts(
+		const struct xfs_log_dinode *ld)
+{
+	return ld->di_version >= 3 &&
+	       (ld->di_flags2 & XFS_DIFLAG2_NREXT64);
+}
+
+static inline void
+xfs_log_dinode_to_disk_iext_counters(
+	struct xfs_log_dinode	*from,
+	struct xfs_dinode	*to)
+{
+	if (xfs_log_dinode_has_large_extent_counts(from)) {
+		to->di_big_nextents = cpu_to_be64(from->di_big_nextents);
+		to->di_big_anextents = cpu_to_be32(from->di_big_anextents);
+		to->di_nrext64_pad = cpu_to_be16(from->di_nrext64_pad);
+	} else {
+		to->di_nextents = cpu_to_be32(from->di_nextents);
+		to->di_anextents = cpu_to_be16(from->di_anextents);
+	}
+
+}
+
 STATIC void
 xfs_log_dinode_to_disk(
 	struct xfs_log_dinode	*from,
@@ -152,13 +177,12 @@ xfs_log_dinode_to_disk(
 	to->di_mode = cpu_to_be16(from->di_mode);
 	to->di_version = from->di_version;
 	to->di_format = from->di_format;
-	to->di_onlink = 0;
+	to->di_metatype = cpu_to_be16(from->di_metatype);
 	to->di_uid = cpu_to_be32(from->di_uid);
 	to->di_gid = cpu_to_be32(from->di_gid);
 	to->di_nlink = cpu_to_be32(from->di_nlink);
 	to->di_projid_lo = cpu_to_be16(from->di_projid_lo);
 	to->di_projid_hi = cpu_to_be16(from->di_projid_hi);
-	memcpy(to->di_pad, from->di_pad, sizeof(to->di_pad));
 
 	to->di_atime = xfs_log_dinode_to_disk_ts(from, from->di_atime);
 	to->di_mtime = xfs_log_dinode_to_disk_ts(from, from->di_mtime);
@@ -167,8 +191,6 @@ xfs_log_dinode_to_disk(
 	to->di_size = cpu_to_be64(from->di_size);
 	to->di_nblocks = cpu_to_be64(from->di_nblocks);
 	to->di_extsize = cpu_to_be32(from->di_extsize);
-	to->di_nextents = cpu_to_be32(from->di_nextents);
-	to->di_anextents = cpu_to_be16(from->di_anextents);
 	to->di_forkoff = from->di_forkoff;
 	to->di_aformat = from->di_aformat;
 	to->di_dmevmask = cpu_to_be32(from->di_dmevmask);
@@ -181,15 +203,105 @@ xfs_log_dinode_to_disk(
 		to->di_crtime = xfs_log_dinode_to_disk_ts(from,
 							  from->di_crtime);
 		to->di_flags2 = cpu_to_be64(from->di_flags2);
+		/* also covers the di_used_blocks union arm: */
 		to->di_cowextsize = cpu_to_be32(from->di_cowextsize);
 		to->di_ino = cpu_to_be64(from->di_ino);
 		to->di_lsn = cpu_to_be64(lsn);
-		memcpy(to->di_pad2, from->di_pad2, sizeof(to->di_pad2));
+		memset(to->di_pad2, 0, sizeof(to->di_pad2));
 		uuid_copy(&to->di_uuid, &from->di_uuid);
-		to->di_flushiter = 0;
+		to->di_v3_pad = 0;
 	} else {
 		to->di_flushiter = cpu_to_be16(from->di_flushiter);
+		memset(to->di_v2_pad, 0, sizeof(to->di_v2_pad));
+	}
+
+	xfs_log_dinode_to_disk_iext_counters(from, to);
+}
+
+STATIC int
+xlog_dinode_verify_extent_counts(
+	struct xfs_mount	*mp,
+	struct xfs_log_dinode	*ldip)
+{
+	xfs_extnum_t		nextents;
+	xfs_aextnum_t		anextents;
+
+	if (xfs_log_dinode_has_large_extent_counts(ldip)) {
+		if (!xfs_has_large_extent_counts(mp) ||
+		    (ldip->di_nrext64_pad != 0)) {
+			XFS_CORRUPTION_ERROR(
+				"Bad log dinode large extent count format",
+				XFS_ERRLEVEL_LOW, mp, ldip, sizeof(*ldip));
+			xfs_alert(mp,
+				"Bad inode 0x%llx, large extent counts %d, padding 0x%x",
+				ldip->di_ino, xfs_has_large_extent_counts(mp),
+				ldip->di_nrext64_pad);
+			return -EFSCORRUPTED;
+		}
+
+		nextents = ldip->di_big_nextents;
+		anextents = ldip->di_big_anextents;
+	} else {
+		if (ldip->di_version == 3 && ldip->di_v3_pad != 0) {
+			XFS_CORRUPTION_ERROR(
+				"Bad log dinode di_v3_pad",
+				XFS_ERRLEVEL_LOW, mp, ldip, sizeof(*ldip));
+			xfs_alert(mp,
+				"Bad inode 0x%llx, di_v3_pad 0x%llx",
+				ldip->di_ino, ldip->di_v3_pad);
+			return -EFSCORRUPTED;
+		}
+
+		nextents = ldip->di_nextents;
+		anextents = ldip->di_anextents;
+	}
+
+	if (unlikely(nextents + anextents > ldip->di_nblocks)) {
+		XFS_CORRUPTION_ERROR("Bad log dinode extent counts",
+				XFS_ERRLEVEL_LOW, mp, ldip, sizeof(*ldip));
+		xfs_alert(mp,
+			"Bad inode 0x%llx, large extent counts %d, nextents 0x%llx, anextents 0x%x, nblocks 0x%llx",
+			ldip->di_ino, xfs_has_large_extent_counts(mp), nextents,
+			anextents, ldip->di_nblocks);
+		return -EFSCORRUPTED;
+	}
+
+	return 0;
+}
+
+static inline int
+xlog_recover_inode_dbroot(
+	struct xfs_mount	*mp,
+	void			*src,
+	unsigned int		len,
+	struct xfs_dinode	*dip)
+{
+	void			*dfork = XFS_DFORK_DPTR(dip);
+	unsigned int		dsize = XFS_DFORK_DSIZE(dip, mp);
+
+	switch (dip->di_format) {
+	case XFS_DINODE_FMT_BTREE:
+		xfs_bmbt_to_bmdr(mp, src, len, dfork, dsize);
+		break;
+	case XFS_DINODE_FMT_META_BTREE:
+		switch (be16_to_cpu(dip->di_metatype)) {
+		case XFS_METAFILE_RTRMAP:
+			xfs_rtrmapbt_to_disk(mp, src, len, dfork, dsize);
+			return 0;
+		case XFS_METAFILE_RTREFCOUNT:
+			xfs_rtrefcountbt_to_disk(mp, src, len, dfork, dsize);
+			return 0;
+		default:
+			ASSERT(0);
+			return -EFSCORRUPTED;
+		}
+		break;
+	default:
+		ASSERT(0);
+		return -EFSCORRUPTED;
 	}
+
+	return 0;
 }
 
 STATIC int
@@ -212,11 +324,13 @@ xlog_recover_inode_commit_pass2(
 	struct xfs_log_dinode		*ldip;
 	uint				isize;
 	int				need_free = 0;
+	xfs_failaddr_t			fa;
 
-	if (item->ri_buf[0].i_len == sizeof(struct xfs_inode_log_format)) {
-		in_f = item->ri_buf[0].i_addr;
+	if (item->ri_buf[0].iov_len == sizeof(struct xfs_inode_log_format)) {
+		in_f = item->ri_buf[0].iov_base;
 	} else {
-		in_f = kmem_alloc(sizeof(struct xfs_inode_log_format), 0);
+		in_f = kmalloc(sizeof(struct xfs_inode_log_format),
+				GFP_KERNEL | __GFP_NOFAIL);
 		need_free = 1;
 		error = xfs_inode_item_format_convert(&item->ri_buf[0], in_f);
 		if (error)
@@ -247,15 +361,15 @@ xlog_recover_inode_commit_pass2(
 	 */
 	if (XFS_IS_CORRUPT(mp, !xfs_verify_magic16(bp, dip->di_magic))) {
 		xfs_alert(mp,
-	"%s: Bad inode magic number, dip = "PTR_FMT", dino bp = "PTR_FMT", ino = %Ld",
+	"%s: Bad inode magic number, dip = "PTR_FMT", dino bp = "PTR_FMT", ino = %lld",
 			__func__, dip, bp, in_f->ilf_ino);
 		error = -EFSCORRUPTED;
 		goto out_release;
 	}
-	ldip = item->ri_buf[1].i_addr;
+	ldip = item->ri_buf[1].iov_base;
 	if (XFS_IS_CORRUPT(mp, ldip->di_magic != XFS_DINODE_MAGIC)) {
 		xfs_alert(mp,
-			"%s: Bad inode log record, rec ptr "PTR_FMT", ino %Ld",
+			"%s: Bad inode log record, rec ptr "PTR_FMT", ino %lld",
 			__func__, item, in_f->ilf_ino);
 		error = -EFSCORRUPTED;
 		goto out_release;
@@ -295,35 +409,37 @@ xlog_recover_inode_commit_pass2(
 	 * superblock flag to determine whether we need to look at di_flushiter
 	 * to skip replay when the on disk inode is newer than the log one
 	 */
-	if (!xfs_has_v3inodes(mp) &&
-	    ldip->di_flushiter < be16_to_cpu(dip->di_flushiter)) {
-		/*
-		 * Deal with the wrap case, DI_MAX_FLUSH is less
-		 * than smaller numbers
-		 */
-		if (be16_to_cpu(dip->di_flushiter) == DI_MAX_FLUSH &&
-		    ldip->di_flushiter < (DI_MAX_FLUSH >> 1)) {
-			/* do nothing */
-		} else {
-			trace_xfs_log_recover_inode_skip(log, in_f);
-			error = 0;
-			goto out_release;
+	if (!xfs_has_v3inodes(mp)) {
+		if (ldip->di_flushiter < be16_to_cpu(dip->di_flushiter)) {
+			/*
+			 * Deal with the wrap case, DI_MAX_FLUSH is less
+			 * than smaller numbers
+			 */
+			if (be16_to_cpu(dip->di_flushiter) == DI_MAX_FLUSH &&
+			    ldip->di_flushiter < (DI_MAX_FLUSH >> 1)) {
+				/* do nothing */
+			} else {
+				trace_xfs_log_recover_inode_skip(log, in_f);
+				error = 0;
+				goto out_release;
+			}
 		}
+
+		/* Take the opportunity to reset the flush iteration count */
+		ldip->di_flushiter = 0;
 	}
 
-	/* Take the opportunity to reset the flush iteration count */
-	ldip->di_flushiter = 0;
 
 	if (unlikely(S_ISREG(ldip->di_mode))) {
-		if ((ldip->di_format != XFS_DINODE_FMT_EXTENTS) &&
-		    (ldip->di_format != XFS_DINODE_FMT_BTREE)) {
-			XFS_CORRUPTION_ERROR("xlog_recover_inode_pass2(3)",
-					 XFS_ERRLEVEL_LOW, mp, ldip,
-					 sizeof(*ldip));
+		if (ldip->di_format != XFS_DINODE_FMT_EXTENTS &&
+		    ldip->di_format != XFS_DINODE_FMT_BTREE &&
+		    ldip->di_format != XFS_DINODE_FMT_META_BTREE) {
+			XFS_CORRUPTION_ERROR(
+				"Bad log dinode data fork format for regular file",
+				XFS_ERRLEVEL_LOW, mp, ldip, sizeof(*ldip));
 			xfs_alert(mp,
-		"%s: Bad regular inode log record, rec ptr "PTR_FMT", "
-		"ino ptr = "PTR_FMT", ino bp = "PTR_FMT", ino %Ld",
-				__func__, item, dip, bp, in_f->ilf_ino);
+				"Bad inode 0x%llx, data fork format 0x%x",
+				in_f->ilf_ino, ldip->di_format);
 			error = -EFSCORRUPTED;
 			goto out_release;
 		}
@@ -331,49 +447,37 @@ xlog_recover_inode_commit_pass2(
 		if ((ldip->di_format != XFS_DINODE_FMT_EXTENTS) &&
 		    (ldip->di_format != XFS_DINODE_FMT_BTREE) &&
 		    (ldip->di_format != XFS_DINODE_FMT_LOCAL)) {
-			XFS_CORRUPTION_ERROR("xlog_recover_inode_pass2(4)",
-					     XFS_ERRLEVEL_LOW, mp, ldip,
-					     sizeof(*ldip));
+			XFS_CORRUPTION_ERROR(
+				"Bad log dinode data fork format for directory",
+				XFS_ERRLEVEL_LOW, mp, ldip, sizeof(*ldip));
 			xfs_alert(mp,
-		"%s: Bad dir inode log record, rec ptr "PTR_FMT", "
-		"ino ptr = "PTR_FMT", ino bp = "PTR_FMT", ino %Ld",
-				__func__, item, dip, bp, in_f->ilf_ino);
+				"Bad inode 0x%llx, data fork format 0x%x",
+				in_f->ilf_ino, ldip->di_format);
 			error = -EFSCORRUPTED;
 			goto out_release;
 		}
 	}
-	if (unlikely(ldip->di_nextents + ldip->di_anextents > ldip->di_nblocks)){
-		XFS_CORRUPTION_ERROR("xlog_recover_inode_pass2(5)",
-				     XFS_ERRLEVEL_LOW, mp, ldip,
-				     sizeof(*ldip));
-		xfs_alert(mp,
-	"%s: Bad inode log record, rec ptr "PTR_FMT", dino ptr "PTR_FMT", "
-	"dino bp "PTR_FMT", ino %Ld, total extents = %d, nblocks = %Ld",
-			__func__, item, dip, bp, in_f->ilf_ino,
-			ldip->di_nextents + ldip->di_anextents,
-			ldip->di_nblocks);
-		error = -EFSCORRUPTED;
+
+	error = xlog_dinode_verify_extent_counts(mp, ldip);
+	if (error)
 		goto out_release;
-	}
+
 	if (unlikely(ldip->di_forkoff > mp->m_sb.sb_inodesize)) {
-		XFS_CORRUPTION_ERROR("xlog_recover_inode_pass2(6)",
-				     XFS_ERRLEVEL_LOW, mp, ldip,
-				     sizeof(*ldip));
+		XFS_CORRUPTION_ERROR("Bad log dinode fork offset",
+				XFS_ERRLEVEL_LOW, mp, ldip, sizeof(*ldip));
 		xfs_alert(mp,
-	"%s: Bad inode log record, rec ptr "PTR_FMT", dino ptr "PTR_FMT", "
-	"dino bp "PTR_FMT", ino %Ld, forkoff 0x%x", __func__,
-			item, dip, bp, in_f->ilf_ino, ldip->di_forkoff);
+			"Bad inode 0x%llx, di_forkoff 0x%x",
+			in_f->ilf_ino, ldip->di_forkoff);
 		error = -EFSCORRUPTED;
 		goto out_release;
 	}
 	isize = xfs_log_dinode_size(mp);
-	if (unlikely(item->ri_buf[1].i_len > isize)) {
-		XFS_CORRUPTION_ERROR("xlog_recover_inode_pass2(7)",
-				     XFS_ERRLEVEL_LOW, mp, ldip,
-				     sizeof(*ldip));
+	if (unlikely(item->ri_buf[1].iov_len > isize)) {
+		XFS_CORRUPTION_ERROR("Bad log dinode size", XFS_ERRLEVEL_LOW,
+				     mp, ldip, sizeof(*ldip));
 		xfs_alert(mp,
-			"%s: Bad inode log record length %d, rec ptr "PTR_FMT,
-			__func__, item->ri_buf[1].i_len, item);
+			"Bad inode 0x%llx log dinode size 0x%zx",
+			in_f->ilf_ino, item->ri_buf[1].iov_len);
 		error = -EFSCORRUPTED;
 		goto out_release;
 	}
@@ -396,12 +500,12 @@ xlog_recover_inode_commit_pass2(
 
 	if (in_f->ilf_size == 2)
 		goto out_owner_change;
-	len = item->ri_buf[2].i_len;
-	src = item->ri_buf[2].i_addr;
+	len = item->ri_buf[2].iov_len;
+	src = item->ri_buf[2].iov_base;
 	ASSERT(in_f->ilf_size <= 4);
 	ASSERT((in_f->ilf_size == 3) || (fields & XFS_ILOG_AFORK));
 	ASSERT(!(fields & XFS_ILOG_DFORK) ||
-	       (len == in_f->ilf_dsize));
+	       (len == xlog_calc_iovec_len(in_f->ilf_dsize)));
 
 	switch (fields & XFS_ILOG_DFORK) {
 	case XFS_ILOG_DDATA:
@@ -410,9 +514,9 @@ xlog_recover_inode_commit_pass2(
 		break;
 
 	case XFS_ILOG_DBROOT:
-		xfs_bmbt_to_bmdr(mp, (struct xfs_btree_block *)src, len,
-				 (struct xfs_bmdr_block *)XFS_DFORK_DPTR(dip),
-				 XFS_DFORK_DSIZE(dip, mp));
+		error = xlog_recover_inode_dbroot(mp, src, len, dip);
+		if (error)
+			goto out_release;
 		break;
 
 	default:
@@ -434,9 +538,9 @@ xlog_recover_inode_commit_pass2(
 		} else {
 			attr_index = 2;
 		}
-		len = item->ri_buf[attr_index].i_len;
-		src = item->ri_buf[attr_index].i_addr;
-		ASSERT(len == in_f->ilf_asize);
+		len = item->ri_buf[attr_index].iov_len;
+		src = item->ri_buf[attr_index].iov_base;
+		ASSERT(len == xlog_calc_iovec_len(in_f->ilf_asize));
 
 		switch (in_f->ilf_fields & XFS_ILOG_AFORK) {
 		case XFS_ILOG_ADATA:
@@ -467,8 +571,19 @@ out_owner_change:
 	    (dip->di_mode != 0))
 		error = xfs_recover_inode_owner_change(mp, dip, in_f,
 						       buffer_list);
-	/* re-generate the checksum. */
+	/* re-generate the checksum and validate the recovered inode. */
 	xfs_dinode_calc_crc(log->l_mp, dip);
+	fa = xfs_dinode_verify(log->l_mp, in_f->ilf_ino, dip);
+	if (fa) {
+		XFS_CORRUPTION_ERROR(
+			"Bad dinode after recovery",
+				XFS_ERRLEVEL_LOW, mp, dip, sizeof(*dip));
+		xfs_alert(mp,
+			"Metadata corruption detected at %pS, inode 0x%llx",
+			fa, in_f->ilf_ino);
+		error = -EFSCORRUPTED;
+		goto out_release;
+	}
 
 	ASSERT(bp->b_mount == mp);
 	bp->b_flags |= _XBF_LOGRECOVERY;
@@ -478,7 +593,7 @@ out_release:
 	xfs_buf_relse(bp);
 error:
 	if (need_free)
-		kmem_free(in_f);
+		kfree(in_f);
 	return error;
 }