Merge tag 'xfs-fixes-6.19-rc2' of git://git.kernel.org/pub/scm/fs/xfs/xfs-linux

Pull xfs fixes from Carlos Maiolino:
 "This contains a few fixes for zoned devices support, an UAF and a
  compiler warning, and some cleaning up"

* tag 'xfs-fixes-6.19-rc2' of git://git.kernel.org/pub/scm/fs/xfs/xfs-linux:
  xfs: fix the zoned RT growfs check for zone alignment
  xfs: validate that zoned RT devices are zone aligned
  xfs: fix XFS_ERRTAG_FORCE_ZERO_RANGE for zoned file system
  xfs: fix a memory leak in xfs_buf_item_init()
  xfs: fix stupid compiler warning
  xfs: fix a UAF problem in xattr repair
  xfs: ignore discard return value

Author: torvalds

fs/xfs/libxfs/xfs_sb.c

@@ -301,6 +301,21 @@ xfs_validate_rt_geometry(
 	    sbp->sb_rbmblocks != xfs_expected_rbmblocks(sbp))
 		return false;
 
+	if (xfs_sb_is_v5(sbp) &&
+	    (sbp->sb_features_incompat & XFS_SB_FEAT_INCOMPAT_ZONED)) {
+		uint32_t		mod;
+
+		/*
+		 * Zoned RT devices must be aligned to the RT group size,
+		 * because garbage collection assumes that all zones have the
+		 * same size to avoid insane complexity if that weren't the
+		 * case.
+		 */
+		div_u64_rem(sbp->sb_rextents, sbp->sb_rgextents, &mod);
+		if (mod)
+			return false;
+	}
+
 	return true;
 }
 

fs/xfs/scrub/attr_repair.c

@@ -333,7 +333,6 @@ xrep_xattr_salvage_remote_attr(
 		.attr_filter		= ent->flags & XFS_ATTR_NSP_ONDISK_MASK,
 		.namelen		= rentry->namelen,
 		.name			= rentry->name,
-		.value			= ab->value,
 		.valuelen		= be32_to_cpu(rentry->valuelen),
 	};
 	unsigned int			namesize;
@@ -363,6 +362,7 @@ xrep_xattr_salvage_remote_attr(
 		error = -EDEADLOCK;
 	if (error)
 		return error;
+	args.value = ab->value;
 
 	/* Look up the remote value and stash it for reconstruction. */
 	error = xfs_attr3_leaf_getvalue(leaf_bp, &args);

fs/xfs/xfs_attr_item.c

@@ -737,7 +737,7 @@ xfs_attr_recover_work(
 	struct xfs_attri_log_item	*attrip = ATTRI_ITEM(lip);
 	struct xfs_attr_intent		*attr;
 	struct xfs_mount		*mp = lip->li_log->l_mp;
-	struct xfs_inode		*ip;
+	struct xfs_inode		*ip = NULL;
 	struct xfs_da_args		*args;
 	struct xfs_trans		*tp;
 	struct xfs_trans_res		resv;

fs/xfs/xfs_buf_item.c

@@ -896,6 +896,7 @@ xfs_buf_item_init(
 		map_size = DIV_ROUND_UP(chunks, NBWORD);
 
 		if (map_size > XFS_BLF_DATAMAP_SIZE) {
+			xfs_buf_item_free_format(bip);
 			kmem_cache_free(xfs_buf_item_cache, bip);
 			xfs_err(mp,
 	"buffer item dirty bitmap (%u uints) too small to reflect %u bytes!",

fs/xfs/xfs_discard.c

@@ -108,15 +108,14 @@ xfs_discard_endio(
  * list. We plug and chain the bios so that we only need a single completion
  * call to clear all the busy extents once the discards are complete.
  */
-int
+void
 xfs_discard_extents(
 	struct xfs_mount	*mp,
 	struct xfs_busy_extents	*extents)
 {
 	struct xfs_extent_busy	*busyp;
 	struct bio		*bio = NULL;
 	struct blk_plug		plug;
-	int			error = 0;
 
 	blk_start_plug(&plug);
 	list_for_each_entry(busyp, &extents->extent_list, list) {
@@ -126,18 +125,10 @@ xfs_discard_extents(
 
 		trace_xfs_discard_extent(xg, busyp->bno, busyp->length);
 
-		error = __blkdev_issue_discard(btp->bt_bdev,
+		__blkdev_issue_discard(btp->bt_bdev,
 				xfs_gbno_to_daddr(xg, busyp->bno),
 				XFS_FSB_TO_BB(mp, busyp->length),
 				GFP_KERNEL, &bio);
-		if (error && error != -EOPNOTSUPP) {
-			xfs_info(mp,
-	 "discard failed for extent [0x%llx,%u], error %d",
-				 (unsigned long long)busyp->bno,
-				 busyp->length,
-				 error);
-			break;
-		}
 	}
 
 	if (bio) {
@@ -148,8 +139,6 @@ xfs_discard_extents(
 		xfs_discard_endio_work(&extents->endio_work);
 	}
 	blk_finish_plug(&plug);
-
-	return error;
 }
 
 /*
@@ -385,9 +374,7 @@ xfs_trim_perag_extents(
 		 * list  after this function call, as it may have been freed by
 		 * the time control returns to us.
 		 */
-		error = xfs_discard_extents(pag_mount(pag), extents);
-		if (error)
-			break;
+		xfs_discard_extents(pag_mount(pag), extents);
 
 		if (xfs_trim_should_stop())
 			break;
@@ -496,12 +483,10 @@ xfs_discard_rtdev_extents(
 
 		trace_xfs_discard_rtextent(mp, busyp->bno, busyp->length);
 
-		error = __blkdev_issue_discard(bdev,
+		__blkdev_issue_discard(bdev,
 				xfs_rtb_to_daddr(mp, busyp->bno),
 				XFS_FSB_TO_BB(mp, busyp->length),
 				GFP_NOFS, &bio);
-		if (error)
-			break;
 	}
 	xfs_discard_free_rtdev_extents(tr);
 
@@ -741,9 +726,7 @@ xfs_trim_rtgroup_extents(
 		 * list  after this function call, as it may have been freed by
 		 * the time control returns to us.
 		 */
-		error = xfs_discard_extents(rtg_mount(rtg), tr.extents);
-		if (error)
-			break;
+		xfs_discard_extents(rtg_mount(rtg), tr.extents);
 
 		low = tr.restart_rtx;
 	} while (!xfs_trim_should_stop() && low <= high);

fs/xfs/xfs_discard.h

@@ -6,7 +6,7 @@ struct fstrim_range;
 struct xfs_mount;
 struct xfs_busy_extents;
 
-int xfs_discard_extents(struct xfs_mount *mp, struct xfs_busy_extents *busy);
+void xfs_discard_extents(struct xfs_mount *mp, struct xfs_busy_extents *busy);
 int xfs_ioc_trim(struct xfs_mount *mp, struct fstrim_range __user *fstrim);
 
 #endif /* XFS_DISCARD_H */

fs/xfs/xfs_file.c

@@ -1240,6 +1240,38 @@ xfs_falloc_insert_range(
 	return xfs_insert_file_space(XFS_I(inode), offset, len);
 }
 
+/*
+ * For various operations we need to zero up to one block at each end of
+ * the affected range.  For zoned file systems this will require a space
+ * allocation, for which we need a reservation ahead of time.
+ */
+#define XFS_ZONED_ZERO_EDGE_SPACE_RES		2
+
+/*
+ * Zero range implements a full zeroing mechanism but is only used in limited
+ * situations. It is more efficient to allocate unwritten extents than to
+ * perform zeroing here, so use an errortag to randomly force zeroing on DEBUG
+ * kernels for added test coverage.
+ *
+ * On zoned file systems, the error is already injected by
+ * xfs_file_zoned_fallocate, which then reserves the additional space needed.
+ * We only check for this extra space reservation here.
+ */
+static inline bool
+xfs_falloc_force_zero(
+	struct xfs_inode		*ip,
+	struct xfs_zone_alloc_ctx	*ac)
+{
+	if (xfs_is_zoned_inode(ip)) {
+		if (ac->reserved_blocks > XFS_ZONED_ZERO_EDGE_SPACE_RES) {
+			ASSERT(IS_ENABLED(CONFIG_XFS_DEBUG));
+			return true;
+		}
+		return false;
+	}
+	return XFS_TEST_ERROR(ip->i_mount, XFS_ERRTAG_FORCE_ZERO_RANGE);
+}
+
 /*
  * Punch a hole and prealloc the range.  We use a hole punch rather than
  * unwritten extent conversion for two reasons:
@@ -1268,14 +1300,7 @@ xfs_falloc_zero_range(
 	if (error)
 		return error;
 
-	/*
-	 * Zero range implements a full zeroing mechanism but is only used in
-	 * limited situations. It is more efficient to allocate unwritten
-	 * extents than to perform zeroing here, so use an errortag to randomly
-	 * force zeroing on DEBUG kernels for added test coverage.
-	 */
-	if (XFS_TEST_ERROR(ip->i_mount,
-			   XFS_ERRTAG_FORCE_ZERO_RANGE)) {
+	if (xfs_falloc_force_zero(ip, ac)) {
 		error = xfs_zero_range(ip, offset, len, ac, NULL);
 	} else {
 		error = xfs_free_file_space(ip, offset, len, ac);
@@ -1423,13 +1448,26 @@ xfs_file_zoned_fallocate(
 {
 	struct xfs_zone_alloc_ctx ac = { };
 	struct xfs_inode	*ip = XFS_I(file_inode(file));
+	struct xfs_mount	*mp = ip->i_mount;
+	xfs_filblks_t		count_fsb;
 	int			error;
 
-	error = xfs_zoned_space_reserve(ip->i_mount, 2, XFS_ZR_RESERVED, &ac);
+	/*
+	 * If full zeroing is forced by the error injection knob, we need a
+	 * space reservation that covers the entire range.  See the comment in
+	 * xfs_zoned_write_space_reserve for the rationale for the calculation.
+	 * Otherwise just reserve space for the two boundary blocks.
+	 */
+	count_fsb = XFS_ZONED_ZERO_EDGE_SPACE_RES;
+	if ((mode & FALLOC_FL_MODE_MASK) == FALLOC_FL_ZERO_RANGE &&
+	    XFS_TEST_ERROR(mp, XFS_ERRTAG_FORCE_ZERO_RANGE))
+		count_fsb += XFS_B_TO_FSB(mp, len) + 1;
+
+	error = xfs_zoned_space_reserve(mp, count_fsb, XFS_ZR_RESERVED, &ac);
 	if (error)
 		return error;
 	error = __xfs_file_fallocate(file, mode, offset, len, &ac);
-	xfs_zoned_space_unreserve(ip->i_mount, &ac);
+	xfs_zoned_space_unreserve(mp, &ac);
 	return error;
 }
 

fs/xfs/xfs_rtalloc.c

@@ -1255,29 +1255,31 @@ xfs_growfs_check_rtgeom(
 	min_logfsbs = min_t(xfs_extlen_t, xfs_log_calc_minimum_size(nmp),
 			nmp->m_rsumblocks * 2);
 
-	kfree(nmp);
-
 	trace_xfs_growfs_check_rtgeom(mp, min_logfsbs);
 
 	if (min_logfsbs > mp->m_sb.sb_logblocks)
-		return -EINVAL;
+		goto out_inval;
 
 	if (xfs_has_zoned(mp)) {
 		uint32_t	gblocks = mp->m_groups[XG_TYPE_RTG].blocks;
 		uint32_t	rem;
 
 		if (rextsize != 1)
 			return -EINVAL;
-		div_u64_rem(mp->m_sb.sb_rblocks, gblocks, &rem);
+		div_u64_rem(nmp->m_sb.sb_rblocks, gblocks, &rem);
 		if (rem) {
 			xfs_warn(mp,
 "new RT volume size (%lld) not aligned to RT group size (%d)",
-				mp->m_sb.sb_rblocks, gblocks);
-			return -EINVAL;
+				nmp->m_sb.sb_rblocks, gblocks);
+			goto out_inval;
 		}
 	}
 
+	kfree(nmp);
 	return 0;
+out_inval:
+	kfree(nmp);
+	return -EINVAL;
 }
 
 /*