Merge tag 'xfs-6.5-merge-5' of git://git.kernel.org/pub/scm/fs/xfs/xfs-linux

Pull more xfs updates from Darrick Wong:

 - Fix some ordering problems with log items during log recovery

 - Don't deadlock the system by trying to flush busy freed extents while
   holding on to busy freed extents

 - Improve validation of log geometry parameters when reading the
   primary superblock

 - Validate the length field in the AGF header

 - Fix recordset filtering bugs when re-calling GETFSMAP to return more
   results when the resultset didn't previously fit in the caller's
   buffer

 - Fix integer overflows in GETFSMAP when working with rt volumes larger
   than 2^32 fsblocks

 - Fix GETFSMAP reporting the undefined space beyond the last rtextent

 - Fix filtering bugs in GETFSMAP's log device backend if the log ever
   becomes longer than 2^32 fsblocks

 - Improve validation of file offsets in the GETFSMAP range parameters

 - Fix an off by one bug in the pmem media failure notification
   computation

 - Validate the length field in the AGI header too

* tag 'xfs-6.5-merge-5' of git://git.kernel.org/pub/scm/fs/xfs/xfs-linux:
  xfs: Remove unneeded semicolon
  xfs: AGI length should be bounds checked
  xfs: fix the calculation for "end" and "length"
  xfs: fix xfs_btree_query_range callers to initialize btree rec fully
  xfs: validate fsmap offsets specified in the query keys
  xfs: fix logdev fsmap query result filtering
  xfs: clean up the rtbitmap fsmap backend
  xfs: fix getfsmap reporting past the last rt extent
  xfs: fix integer overflows in the fsmap rtbitmap and logdev backends
  xfs: fix interval filtering in multi-step fsmap queries
  xfs: fix bounds check in xfs_defer_agfl_block()
  xfs: AGF length has never been bounds checked
  xfs: journal geometry is not properly bounds checked
  xfs: don't block in busy flushing when freeing extents
  xfs: allow extent free intents to be retried
  xfs: pass alloc flags through to xfs_extent_busy_flush()
  xfs: use deferred frees for btree block freeing
  xfs: don't reverse order of items in bulk AIL insertion
  xfs: remove redundant initializations of pointers drop_leaf and save_leaf

fs/xfs/libxfs/xfs_ag.c

@@ -985,7 +985,7 @@ xfs_ag_shrink_space(
 			goto resv_err;
 
 		err2 = __xfs_free_extent_later(*tpp, args.fsbno, delta, NULL,
-				true);
+				XFS_AG_RESV_NONE, true);
 		if (err2)
 			goto resv_err;
 

fs/xfs/libxfs/xfs_alloc.h

@@ -19,11 +19,12 @@ unsigned int xfs_agfl_size(struct xfs_mount *mp);
 /*
  * Flags for xfs_alloc_fix_freelist.
  */
-#define	XFS_ALLOC_FLAG_TRYLOCK	0x00000001  /* use trylock for buffer locking */
-#define	XFS_ALLOC_FLAG_FREEING	0x00000002  /* indicate caller is freeing extents*/
-#define	XFS_ALLOC_FLAG_NORMAP	0x00000004  /* don't modify the rmapbt */
-#define	XFS_ALLOC_FLAG_NOSHRINK	0x00000008  /* don't shrink the freelist */
-#define	XFS_ALLOC_FLAG_CHECK	0x00000010  /* test only, don't modify args */
+#define	XFS_ALLOC_FLAG_TRYLOCK	(1U << 0)  /* use trylock for buffer locking */
+#define	XFS_ALLOC_FLAG_FREEING	(1U << 1)  /* indicate caller is freeing extents*/
+#define	XFS_ALLOC_FLAG_NORMAP	(1U << 2)  /* don't modify the rmapbt */
+#define	XFS_ALLOC_FLAG_NOSHRINK	(1U << 3)  /* don't shrink the freelist */
+#define	XFS_ALLOC_FLAG_CHECK	(1U << 4)  /* test only, don't modify args */
+#define	XFS_ALLOC_FLAG_TRYFLUSH	(1U << 5)  /* don't wait in busy extent flush */
 
 /*
  * Argument structure for xfs_alloc routines.
@@ -195,7 +196,7 @@ int xfs_alloc_read_agfl(struct xfs_perag *pag, struct xfs_trans *tp,
 		struct xfs_buf **bpp);
 int xfs_free_agfl_block(struct xfs_trans *, xfs_agnumber_t, xfs_agblock_t,
 			struct xfs_buf *, struct xfs_owner_info *);
-int xfs_alloc_fix_freelist(struct xfs_alloc_arg *args, int flags);
+int xfs_alloc_fix_freelist(struct xfs_alloc_arg *args, uint32_t alloc_flags);
 int xfs_free_extent_fix_freelist(struct xfs_trans *tp, struct xfs_perag *pag,
 		struct xfs_buf **agbp);
 
@@ -232,7 +233,7 @@ xfs_buf_to_agfl_bno(
 
 int __xfs_free_extent_later(struct xfs_trans *tp, xfs_fsblock_t bno,
 		xfs_filblks_t len, const struct xfs_owner_info *oinfo,
-		bool skip_discard);
+		enum xfs_ag_resv_type type, bool skip_discard);
 
 /*
  * List of extents to be free "later".
@@ -245,6 +246,7 @@ struct xfs_extent_free_item {
 	xfs_extlen_t		xefi_blockcount;/* number of blocks in extent */
 	struct xfs_perag	*xefi_pag;
 	unsigned int		xefi_flags;
+	enum xfs_ag_resv_type	xefi_agresv;
 };
 
 void xfs_extent_free_get_group(struct xfs_mount *mp,
@@ -259,9 +261,10 @@ xfs_free_extent_later(
 	struct xfs_trans		*tp,
 	xfs_fsblock_t			bno,
 	xfs_filblks_t			len,
-	const struct xfs_owner_info	*oinfo)
+	const struct xfs_owner_info	*oinfo,
+	enum xfs_ag_resv_type		type)
 {
-	return __xfs_free_extent_later(tp, bno, len, oinfo, false);
+	return __xfs_free_extent_later(tp, bno, len, oinfo, type, false);
 }
 
 
@@ -270,4 +273,7 @@ extern struct kmem_cache	*xfs_extfree_item_cache;
 int __init xfs_extfree_intent_init_cache(void);
 void xfs_extfree_intent_destroy_cache(void);
 
+xfs_failaddr_t xfs_validate_ag_length(struct xfs_buf *bp, uint32_t seqno,
+		uint32_t length);
+
 #endif	/* __XFS_ALLOC_H__ */

fs/xfs/libxfs/xfs_attr_leaf.c

@@ -2293,8 +2293,6 @@ xfs_attr3_leaf_unbalance(
 
 	trace_xfs_attr_leaf_unbalance(state->args);
 
-	drop_leaf = drop_blk->bp->b_addr;
-	save_leaf = save_blk->bp->b_addr;
 	xfs_attr3_leaf_hdr_from_disk(state->args->geo, &drophdr, drop_leaf);
 	xfs_attr3_leaf_hdr_from_disk(state->args->geo, &savehdr, save_leaf);
 	entry = xfs_attr3_leaf_entryp(drop_leaf);

fs/xfs/libxfs/xfs_bmap.c

@@ -574,7 +574,8 @@ xfs_bmap_btree_to_extents(
 		return error;
 
 	xfs_rmap_ino_bmbt_owner(&oinfo, ip->i_ino, whichfork);
-	error = xfs_free_extent_later(cur->bc_tp, cbno, 1, &oinfo);
+	error = xfs_free_extent_later(cur->bc_tp, cbno, 1, &oinfo,
+			XFS_AG_RESV_NONE);
 	if (error)
 		return error;
 
@@ -5236,8 +5237,9 @@ xfs_bmap_del_extent_real(
 		} else {
 			error = __xfs_free_extent_later(tp, del->br_startblock,
 					del->br_blockcount, NULL,
-					(bflags & XFS_BMAPI_NODISCARD) ||
-					del->br_state == XFS_EXT_UNWRITTEN);
+					XFS_AG_RESV_NONE,
+					((bflags & XFS_BMAPI_NODISCARD) ||
+					del->br_state == XFS_EXT_UNWRITTEN));
 			if (error)
 				goto done;
 		}

fs/xfs/libxfs/xfs_bmap_btree.c

@@ -271,7 +271,8 @@ xfs_bmbt_free_block(
 	int			error;
 
 	xfs_rmap_ino_bmbt_owner(&oinfo, ip->i_ino, cur->bc_ino.whichfork);
-	error = xfs_free_extent_later(cur->bc_tp, fsbno, 1, &oinfo);
+	error = xfs_free_extent_later(cur->bc_tp, fsbno, 1, &oinfo,
+			XFS_AG_RESV_NONE);
 	if (error)
 		return error;
 

fs/xfs/libxfs/xfs_ialloc.c

@@ -1853,8 +1853,8 @@ xfs_difree_inode_chunk(
 		/* not sparse, calculate extent info directly */
 		return xfs_free_extent_later(tp,
 				XFS_AGB_TO_FSB(mp, agno, sagbno),
-				M_IGEO(mp)->ialloc_blks,
-				&XFS_RMAP_OINFO_INODES);
+				M_IGEO(mp)->ialloc_blks, &XFS_RMAP_OINFO_INODES,
+				XFS_AG_RESV_NONE);
 	}
 
 	/* holemask is only 16-bits (fits in an unsigned long) */
@@ -1899,8 +1899,8 @@ xfs_difree_inode_chunk(
 		ASSERT(agbno % mp->m_sb.sb_spino_align == 0);
 		ASSERT(contigblk % mp->m_sb.sb_spino_align == 0);
 		error = xfs_free_extent_later(tp,
-				XFS_AGB_TO_FSB(mp, agno, agbno),
-				contigblk, &XFS_RMAP_OINFO_INODES);
+				XFS_AGB_TO_FSB(mp, agno, agbno), contigblk,
+				&XFS_RMAP_OINFO_INODES, XFS_AG_RESV_NONE);
 		if (error)
 			return error;
 
@@ -2490,6 +2490,9 @@ xfs_agi_verify(
 {
 	struct xfs_mount	*mp = bp->b_mount;
 	struct xfs_agi		*agi = bp->b_addr;
+	xfs_failaddr_t		fa;
+	uint32_t		agi_seqno = be32_to_cpu(agi->agi_seqno);
+	uint32_t		agi_length = be32_to_cpu(agi->agi_length);
 	int			i;
 
 	if (xfs_has_crc(mp)) {
@@ -2507,6 +2510,10 @@ xfs_agi_verify(
 	if (!XFS_AGI_GOOD_VERSION(be32_to_cpu(agi->agi_versionnum)))
 		return __this_address;
 
+	fa = xfs_validate_ag_length(bp, agi_seqno, agi_length);
+	if (fa)
+		return fa;
+
 	if (be32_to_cpu(agi->agi_level) < 1 ||
 	    be32_to_cpu(agi->agi_level) > M_IGEO(mp)->inobt_maxlevels)
 		return __this_address;
@@ -2516,15 +2523,6 @@ xfs_agi_verify(
 	     be32_to_cpu(agi->agi_free_level) > M_IGEO(mp)->inobt_maxlevels))
 		return __this_address;
 
-	/*
-	 * during growfs operations, the perag is not fully initialised,
-	 * so we can't use it for any useful checking. growfs ensures we can't
-	 * use it by using uncached buffers that don't have the perag attached
-	 * so we can detect and avoid this problem.
-	 */
-	if (bp->b_pag && be32_to_cpu(agi->agi_seqno) != bp->b_pag->pag_agno)
-		return __this_address;
-
 	for (i = 0; i < XFS_AGI_UNLINKED_BUCKETS; i++) {
 		if (agi->agi_unlinked[i] == cpu_to_be32(NULLAGINO))
 			continue;

fs/xfs/libxfs/xfs_ialloc_btree.c

@@ -160,8 +160,7 @@ __xfs_inobt_free_block(
 
 	xfs_inobt_mod_blockcount(cur, -1);
 	fsbno = XFS_DADDR_TO_FSB(cur->bc_mp, xfs_buf_daddr(bp));
-	return xfs_free_extent(cur->bc_tp, cur->bc_ag.pag,
-			XFS_FSB_TO_AGBNO(cur->bc_mp, fsbno), 1,
+	return xfs_free_extent_later(cur->bc_tp, fsbno, 1,
 			&XFS_RMAP_OINFO_INOBT, resv);
 }
 

fs/xfs/libxfs/xfs_refcount.c

@@ -1152,7 +1152,8 @@ xfs_refcount_adjust_extents(
 						cur->bc_ag.pag->pag_agno,
 						tmp.rc_startblock);
 				error = xfs_free_extent_later(cur->bc_tp, fsbno,
-						  tmp.rc_blockcount, NULL);
+						  tmp.rc_blockcount, NULL,
+						  XFS_AG_RESV_NONE);
 				if (error)
 					goto out_error;
 			}
@@ -1213,7 +1214,8 @@ xfs_refcount_adjust_extents(
 					cur->bc_ag.pag->pag_agno,
 					ext.rc_startblock);
 			error = xfs_free_extent_later(cur->bc_tp, fsbno,
-					ext.rc_blockcount, NULL);
+					ext.rc_blockcount, NULL,
+					XFS_AG_RESV_NONE);
 			if (error)
 				goto out_error;
 		}
@@ -1919,8 +1921,13 @@ xfs_refcount_recover_cow_leftovers(
 	struct xfs_buf			*agbp;
 	struct xfs_refcount_recovery	*rr, *n;
 	struct list_head		debris;
-	union xfs_btree_irec		low;
-	union xfs_btree_irec		high;
+	union xfs_btree_irec		low = {
+		.rc.rc_domain		= XFS_REFC_DOMAIN_COW,
+	};
+	union xfs_btree_irec		high = {
+		.rc.rc_domain		= XFS_REFC_DOMAIN_COW,
+		.rc.rc_startblock	= -1U,
+	};
 	xfs_fsblock_t			fsb;
 	int				error;
 
@@ -1951,10 +1958,6 @@ xfs_refcount_recover_cow_leftovers(
 	cur = xfs_refcountbt_init_cursor(mp, tp, agbp, pag);
 
 	/* Find all the leftover CoW staging extents. */
-	memset(&low, 0, sizeof(low));
-	memset(&high, 0, sizeof(high));
-	low.rc.rc_domain = high.rc.rc_domain = XFS_REFC_DOMAIN_COW;
-	high.rc.rc_startblock = -1U;
 	error = xfs_btree_query_range(cur, &low, &high,
 			xfs_refcount_recover_extent, &debris);
 	xfs_btree_del_cursor(cur, error);
@@ -1981,7 +1984,8 @@ xfs_refcount_recover_cow_leftovers(
 
 		/* Free the block. */
 		error = xfs_free_extent_later(tp, fsb,
-				rr->rr_rrec.rc_blockcount, NULL);
+				rr->rr_rrec.rc_blockcount, NULL,
+				XFS_AG_RESV_NONE);
 		if (error)
 			goto out_trans;
 

fs/xfs/libxfs/xfs_refcount_btree.c

@@ -106,19 +106,13 @@ xfs_refcountbt_free_block(
 	struct xfs_buf		*agbp = cur->bc_ag.agbp;
 	struct xfs_agf		*agf = agbp->b_addr;
 	xfs_fsblock_t		fsbno = XFS_DADDR_TO_FSB(mp, xfs_buf_daddr(bp));
-	int			error;
 
 	trace_xfs_refcountbt_free_block(cur->bc_mp, cur->bc_ag.pag->pag_agno,
 			XFS_FSB_TO_AGBNO(cur->bc_mp, fsbno), 1);
 	be32_add_cpu(&agf->agf_refcount_blocks, -1);
 	xfs_alloc_log_agf(cur->bc_tp, agbp, XFS_AGF_REFCOUNT_BLOCKS);
-	error = xfs_free_extent(cur->bc_tp, cur->bc_ag.pag,
-			XFS_FSB_TO_AGBNO(cur->bc_mp, fsbno), 1,
+	return xfs_free_extent_later(cur->bc_tp, fsbno, 1,
 			&XFS_RMAP_OINFO_REFC, XFS_AG_RESV_METADATA);
-	if (error)
-		return error;
-
-	return error;
 }
 
 STATIC int

fs/xfs/libxfs/xfs_rmap.c

@@ -2389,14 +2389,10 @@ xfs_rmap_query_range(
 	xfs_rmap_query_range_fn			fn,
 	void					*priv)
 {
-	union xfs_btree_irec			low_brec;
-	union xfs_btree_irec			high_brec;
-	struct xfs_rmap_query_range_info	query;
+	union xfs_btree_irec			low_brec = { .r = *low_rec };
+	union xfs_btree_irec			high_brec = { .r = *high_rec };
+	struct xfs_rmap_query_range_info	query = { .priv = priv, .fn = fn };
 
-	low_brec.r = *low_rec;
-	high_brec.r = *high_rec;
-	query.priv = priv;
-	query.fn = fn;
 	return xfs_btree_query_range(cur, &low_brec, &high_brec,
 			xfs_rmap_query_range_helper, &query);
 }

fs/xfs/libxfs/xfs_sb.c

@@ -412,7 +412,6 @@ 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	||
@@ -430,6 +429,61 @@ xfs_validate_sb_common(
 		return -EFSCORRUPTED;
 	}
 
+	/*
+	 * 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,
+		"Log size 0x%x blocks too large, maximum size is 0x%llx blocks",
+			 sbp->sb_logblocks, XFS_MAX_LOG_BLOCKS);
+		return -EFSCORRUPTED;
+	}
+
+	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,
+			"log sector size in bytes/log2 (0x%x/0x%x) must match",
+				sbp->sb_logsectsize, 1U << sbp->sb_logsectlog);
+			return -EFSCORRUPTED;
+		}
+	} 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_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,
+		"log stripe unit 0x%x bytes over maximum size (0x%x bytes)",
+				sbp->sb_logsunit, XLOG_MAX_RECORD_BSIZE);
+			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) {

fs/xfs/xfs_extent_busy.c

@@ -566,20 +566,45 @@ xfs_extent_busy_clear(
 
 /*
  * Flush out all busy extents for this AG.
+ *
+ * If the current transaction is holding busy extents, the caller may not want
+ * to wait for committed busy extents to resolve. If we are being told just to
+ * try a flush or progress has been made since we last skipped a busy extent,
+ * return immediately to allow the caller to try again.
+ *
+ * If we are freeing extents, we might actually be holding the only free extents
+ * in the transaction busy list and the log force won't resolve that situation.
+ * In this case, we must return -EAGAIN to avoid a deadlock by informing the
+ * caller it needs to commit the busy extents it holds before retrying the
+ * extent free operation.
  */
-void
+int
 xfs_extent_busy_flush(
-	struct xfs_mount	*mp,
+	struct xfs_trans	*tp,
 	struct xfs_perag	*pag,
-	unsigned		busy_gen)
+	unsigned		busy_gen,
+	uint32_t		alloc_flags)
 {
 	DEFINE_WAIT		(wait);
 	int			error;
 
-	error = xfs_log_force(mp, XFS_LOG_SYNC);
+	error = xfs_log_force(tp->t_mountp, XFS_LOG_SYNC);
 	if (error)
-		return;
+		return error;
+
+	/* Avoid deadlocks on uncommitted busy extents. */
+	if (!list_empty(&tp->t_busy)) {
+		if (alloc_flags & XFS_ALLOC_FLAG_TRYFLUSH)
+			return 0;
+
+		if (busy_gen != READ_ONCE(pag->pagb_gen))
+			return 0;
+
+		if (alloc_flags & XFS_ALLOC_FLAG_FREEING)
+			return -EAGAIN;
+	}
 
+	/* Wait for committed busy extents to resolve. */
 	do {
 		prepare_to_wait(&pag->pagb_wait, &wait, TASK_KILLABLE);
 		if  (busy_gen != READ_ONCE(pag->pagb_gen))
@@ -588,6 +613,7 @@ xfs_extent_busy_flush(
 	} while (1);
 
 	finish_wait(&pag->pagb_wait, &wait);
+	return 0;
 }
 
 void

fs/xfs/xfs_extent_busy.h

@@ -51,9 +51,9 @@ bool
 xfs_extent_busy_trim(struct xfs_alloc_arg *args, xfs_agblock_t *bno,
 		xfs_extlen_t *len, unsigned *busy_gen);
 
-void
-xfs_extent_busy_flush(struct xfs_mount *mp, struct xfs_perag *pag,
-	unsigned busy_gen);
+int
+xfs_extent_busy_flush(struct xfs_trans *tp, struct xfs_perag *pag,
+		unsigned busy_gen, uint32_t alloc_flags);
 
 void
 xfs_extent_busy_wait_all(struct xfs_mount *mp);

fs/xfs/xfs_extfree_item.c

@@ -336,6 +336,34 @@ xfs_trans_get_efd(
 	return efdp;
 }
 
+/*
+ * Fill the EFD with all extents from the EFI when we need to roll the
+ * transaction and continue with a new EFI.
+ *
+ * This simply copies all the extents in the EFI to the EFD rather than make
+ * assumptions about which extents in the EFI have already been processed. We
+ * currently keep the xefi list in the same order as the EFI extent list, but
+ * that may not always be the case. Copying everything avoids leaving a landmine
+ * were we fail to cancel all the extents in an EFI if the xefi list is
+ * processed in a different order to the extents in the EFI.
+ */
+static void
+xfs_efd_from_efi(
+	struct xfs_efd_log_item	*efdp)
+{
+	struct xfs_efi_log_item *efip = efdp->efd_efip;
+	uint                    i;
+
+	ASSERT(efip->efi_format.efi_nextents > 0);
+	ASSERT(efdp->efd_next_extent < efip->efi_format.efi_nextents);
+
+	for (i = 0; i < efip->efi_format.efi_nextents; i++) {
+	       efdp->efd_format.efd_extents[i] =
+		       efip->efi_format.efi_extents[i];
+	}
+	efdp->efd_next_extent = efip->efi_format.efi_nextents;
+}
+
 /*
  * Free an extent and log it to the EFD. Note that the transaction is marked
  * dirty regardless of whether the extent free succeeds or fails to support the
@@ -365,7 +393,7 @@ xfs_trans_free_extent(
 			agbno, xefi->xefi_blockcount);
 
 	error = __xfs_free_extent(tp, xefi->xefi_pag, agbno,
-			xefi->xefi_blockcount, &oinfo, XFS_AG_RESV_NONE,
+			xefi->xefi_blockcount, &oinfo, xefi->xefi_agresv,
 			xefi->xefi_flags & XFS_EFI_SKIP_DISCARD);
 
 	/*
@@ -378,6 +406,17 @@ xfs_trans_free_extent(
 	tp->t_flags |= XFS_TRANS_DIRTY | XFS_TRANS_HAS_INTENT_DONE;
 	set_bit(XFS_LI_DIRTY, &efdp->efd_item.li_flags);
 
+	/*
+	 * If we need a new transaction to make progress, the caller will log a
+	 * new EFI with the current contents. It will also log an EFD to cancel
+	 * the existing EFI, and so we need to copy all the unprocessed extents
+	 * in this EFI to the EFD so this works correctly.
+	 */
+	if (error == -EAGAIN) {
+		xfs_efd_from_efi(efdp);
+		return error;
+	}
+
 	next_extent = efdp->efd_next_extent;
 	ASSERT(next_extent < efdp->efd_format.efd_nextents);
 	extp = &(efdp->efd_format.efd_extents[next_extent]);
@@ -495,6 +534,13 @@ xfs_extent_free_finish_item(
 
 	error = xfs_trans_free_extent(tp, EFD_ITEM(done), xefi);
 
+	/*
+	 * Don't free the XEFI if we need a new transaction to complete
+	 * processing of it.
+	 */
+	if (error == -EAGAIN)
+		return error;
+
 	xfs_extent_free_put_group(xefi);
 	kmem_cache_free(xfs_extfree_item_cache, xefi);
 	return error;
@@ -620,6 +666,7 @@ xfs_efi_item_recover(
 	struct xfs_trans		*tp;
 	int				i;
 	int				error = 0;
+	bool				requeue_only = false;
 
 	/*
 	 * First check the validity of the extents described by the
@@ -644,6 +691,7 @@ xfs_efi_item_recover(
 	for (i = 0; i < efip->efi_format.efi_nextents; i++) {
 		struct xfs_extent_free_item	fake = {
 			.xefi_owner		= XFS_RMAP_OWN_UNKNOWN,
+			.xefi_agresv		= XFS_AG_RESV_NONE,
 		};
 		struct xfs_extent		*extp;
 
@@ -652,9 +700,28 @@ xfs_efi_item_recover(
 		fake.xefi_startblock = extp->ext_start;
 		fake.xefi_blockcount = extp->ext_len;
 
+		if (!requeue_only) {
 			xfs_extent_free_get_group(mp, &fake);
 			error = xfs_trans_free_extent(tp, efdp, &fake);
 			xfs_extent_free_put_group(&fake);
+		}
+
+		/*
+		 * If we can't free the extent without potentially deadlocking,
+		 * requeue the rest of the extents to a new so that they get
+		 * run again later with a new transaction context.
+		 */
+		if (error == -EAGAIN || requeue_only) {
+			error = xfs_free_extent_later(tp, fake.xefi_startblock,
+					fake.xefi_blockcount,
+					&XFS_RMAP_OINFO_ANY_OWNER,
+					fake.xefi_agresv);
+			if (!error) {
+				requeue_only = true;
+				continue;
+			}
+		}
+
 		if (error == -EFSCORRUPTED)
 			XFS_CORRUPTION_ERROR(__func__, XFS_ERRLEVEL_LOW, mp,
 					extp, sizeof(*extp));

fs/xfs/xfs_log.c

@@ -639,7 +639,6 @@ xfs_log_mount(
 	int		num_bblks)
 {
 	struct xlog	*log;
-	bool		fatal = xfs_has_crc(mp);
 	int		error = 0;
 	int		min_logfsbs;
 
@@ -663,53 +662,37 @@ xfs_log_mount(
 	mp->m_log = log;
 
 	/*
-	 * Validate the given log space and drop a critical message via syslog
-	 * if the log size is too small that would lead to some unexpected
-	 * situations in transaction log space reservation stage.
+	 * Now that we have set up the log and it's internal geometry
+	 * parameters, we can validate the given log space and drop a critical
+	 * message via syslog if the log size is too small. A log that is too
+	 * small can lead to unexpected situations in transaction log space
+	 * reservation stage. The superblock verifier has already validated all
+	 * the other log geometry constraints, so we don't have to check those
+	 * here.
 	 *
-	 * Note: we can't just reject the mount if the validation fails.  This
-	 * would mean that people would have to downgrade their kernel just to
-	 * remedy the situation as there is no way to grow the log (short of
-	 * black magic surgery with xfs_db).
+	 * Note: For v4 filesystems, we can't just reject the mount if the
+	 * validation fails.  This would mean that people would have to
+	 * downgrade their kernel just to remedy the situation as there is no
+	 * way to grow the log (short of black magic surgery with xfs_db).
 	 *
-	 * We can, however, reject mounts for CRC format filesystems, as the
+	 * We can, however, reject mounts for V5 format filesystems, as the
 	 * mkfs binary being used to make the filesystem should never create a
 	 * filesystem with a log that is too small.
 	 */
 	min_logfsbs = xfs_log_calc_minimum_size(mp);
-
 	if (mp->m_sb.sb_logblocks < min_logfsbs) {
 		xfs_warn(mp,
 		"Log size %d blocks too small, minimum size is %d blocks",
 			 mp->m_sb.sb_logblocks, min_logfsbs);
-		error = -EINVAL;
-	} else if (mp->m_sb.sb_logblocks > XFS_MAX_LOG_BLOCKS) {
-		xfs_warn(mp,
-		"Log size %d blocks too large, maximum size is %lld blocks",
-			 mp->m_sb.sb_logblocks, XFS_MAX_LOG_BLOCKS);
-		error = -EINVAL;
-	} else if (XFS_FSB_TO_B(mp, mp->m_sb.sb_logblocks) > XFS_MAX_LOG_BYTES) {
-		xfs_warn(mp,
-		"log size %lld bytes too large, maximum size is %lld bytes",
-			 XFS_FSB_TO_B(mp, mp->m_sb.sb_logblocks),
-			 XFS_MAX_LOG_BYTES);
-		error = -EINVAL;
-	} else if (mp->m_sb.sb_logsunit > 1 &&
-		   mp->m_sb.sb_logsunit % mp->m_sb.sb_blocksize) {
-		xfs_warn(mp,
-		"log stripe unit %u bytes must be a multiple of block size",
-			 mp->m_sb.sb_logsunit);
-		error = -EINVAL;
-		fatal = true;
-	}
-	if (error) {
+
 		/*
 		 * Log check errors are always fatal on v5; or whenever bad
 		 * metadata leads to a crash.
 		 */
-		if (fatal) {
+		if (xfs_has_crc(mp)) {
 			xfs_crit(mp, "AAIEEE! Log failed size checks. Abort!");
 			ASSERT(0);
+			error = -EINVAL;
 			goto out_free_log;
 		}
 		xfs_crit(mp, "Log size out of supported range.");

fs/xfs/xfs_notify_failure.c

@@ -114,7 +114,8 @@ xfs_dax_notify_ddev_failure(
 	int			error = 0;
 	xfs_fsblock_t		fsbno = XFS_DADDR_TO_FSB(mp, daddr);
 	xfs_agnumber_t		agno = XFS_FSB_TO_AGNO(mp, fsbno);
-	xfs_fsblock_t		end_fsbno = XFS_DADDR_TO_FSB(mp, daddr + bblen);
+	xfs_fsblock_t		end_fsbno = XFS_DADDR_TO_FSB(mp,
+							     daddr + bblen - 1);
 	xfs_agnumber_t		end_agno = XFS_FSB_TO_AGNO(mp, end_fsbno);
 
 	error = xfs_trans_alloc_empty(mp, &tp);
@@ -210,7 +211,7 @@ xfs_dax_notify_failure(
 	ddev_end = ddev_start + bdev_nr_bytes(mp->m_ddev_targp->bt_bdev) - 1;
 
 	/* Ignore the range out of filesystem area */
-	if (offset + len < ddev_start)
+	if (offset + len - 1 < ddev_start)
 		return -ENXIO;
 	if (offset > ddev_end)
 		return -ENXIO;
@@ -222,8 +223,8 @@ xfs_dax_notify_failure(
 		len -= ddev_start - offset;
 		offset = 0;
 	}
-	if (offset + len > ddev_end)
-		len -= ddev_end - offset;
+	if (offset + len - 1 > ddev_end)
+		len = ddev_end - offset + 1;
 
 	return xfs_dax_notify_ddev_failure(mp, BTOBB(offset), BTOBB(len),
 			mf_flags);

fs/xfs/xfs_reflink.c

@@ -617,7 +617,8 @@ xfs_reflink_cancel_cow_blocks(
 					del.br_blockcount);
 
 			error = xfs_free_extent_later(*tpp, del.br_startblock,
-					  del.br_blockcount, NULL);
+					del.br_blockcount, NULL,
+					XFS_AG_RESV_NONE);
 			if (error)
 				break;
 

fs/xfs/xfs_trace.h

@@ -3623,6 +3623,31 @@ DEFINE_FSMAP_EVENT(xfs_fsmap_low_key);
 DEFINE_FSMAP_EVENT(xfs_fsmap_high_key);
 DEFINE_FSMAP_EVENT(xfs_fsmap_mapping);
 
+DECLARE_EVENT_CLASS(xfs_fsmap_linear_class,
+	TP_PROTO(struct xfs_mount *mp, u32 keydev, uint64_t bno),
+	TP_ARGS(mp, keydev, bno),
+	TP_STRUCT__entry(
+		__field(dev_t, dev)
+		__field(dev_t, keydev)
+		__field(xfs_fsblock_t, bno)
+	),
+	TP_fast_assign(
+		__entry->dev = mp->m_super->s_dev;
+		__entry->keydev = new_decode_dev(keydev);
+		__entry->bno = bno;
+	),
+	TP_printk("dev %d:%d keydev %d:%d bno 0x%llx",
+		  MAJOR(__entry->dev), MINOR(__entry->dev),
+		  MAJOR(__entry->keydev), MINOR(__entry->keydev),
+		  __entry->bno)
+)
+#define DEFINE_FSMAP_LINEAR_EVENT(name) \
+DEFINE_EVENT(xfs_fsmap_linear_class, name, \
+	TP_PROTO(struct xfs_mount *mp, u32 keydev, uint64_t bno), \
+	TP_ARGS(mp, keydev, bno))
+DEFINE_FSMAP_LINEAR_EVENT(xfs_fsmap_low_key_linear);
+DEFINE_FSMAP_LINEAR_EVENT(xfs_fsmap_high_key_linear);
+
 DECLARE_EVENT_CLASS(xfs_getfsmap_class,
 	TP_PROTO(struct xfs_mount *mp, struct xfs_fsmap *fsmap),
 	TP_ARGS(mp, fsmap),

fs/xfs/xfs_trans_ail.c

@@ -823,7 +823,7 @@ xfs_trans_ail_update_bulk(
 			trace_xfs_ail_insert(lip, 0, lsn);
 		}
 		lip->li_lsn = lsn;
-		list_add(&lip->li_ail, &tmp);
+		list_add_tail(&lip->li_ail, &tmp);
 	}
 
 	if (!list_empty(&tmp))