Merge tag 'xfs-6.8-merge-3' of git://git.kernel.org/pub/scm/fs/xfs/xf…

…s-linux

Pull xfs updates from Chandan Babu:
 "New features/functionality:
   - Online repair:
       - Reserve disk space for online repairs
       - Fix misinteraction between the AIL and btree bulkloader because
         of which the bulk load fails to queue a buffer for writeback if
         it happens to be on the AIL list
       - Prevent transaction reservation overflows when reaping blocks
         during online repair
       - Whenever possible, bulkloader now copies multiple records into
         a block
       - Support repairing of
           1. Per-AG free space, inode and refcount btrees
           2. Ondisk inodes
           3. File data and attribute fork mappings
       - Verify the contents of
           1. Inode and data fork of realtime bitmap file
           2. Quota files
   - Introduce MF_MEM_PRE_REMOVE. This will be used to notify tasks
     about a pmem device being removed

  Bug fixes:
   - Fix memory leak of recovered attri intent items
   - Fix UAF during log intent recovery
   - Fix realtime geometry integer overflows
   - Prevent scrub from live locking in xchk_iget
   - Prevent fs shutdown when removing files during low free disk space
   - Prevent transaction reservation overflow when extending an RT
     device
   - Prevent incorrect warning from being printed when extending a
     filesystem
   - Fix an off-by-one error in xreap_agextent_binval
   - Serialize access to perag radix tree during deletion operation
   - Fix perag memory leak during growfs
   - Allow allocation of minlen realtime extent when the maximum sized
     realtime free extent is minlen in size

  Cleanups:
   - Remove duplicate boilerplate code spread across functionality
     associated with different log items
   - Cleanup resblks interfaces
   - Pass defer ops pointer to defer helpers instead of an enum
   - Initialize di_crc in xfs_log_dinode to prevent KMSAN warnings
   - Use static_assert() instead of BUILD_BUG_ON_MSG() to validate size
     of structures and structure member offsets. This is done in order
     to be able to share the code with userspace
   - Move XFS documentation under a new directory specific to XFS
   - Do not invoke deferred ops' ->create_done callback if the deferred
     operation does not have an intent item associated with it
   - Remove duplicate inclusion of header files from scrub/health.c
   - Refactor Realtime code
   - Cleanup attr code"

* tag 'xfs-6.8-merge-3' of git://git.kernel.org/pub/scm/fs/xfs/xfs-linux: (123 commits)
  xfs: use the op name in trace_xlog_intent_recovery_failed
  xfs: fix a use after free in xfs_defer_finish_recovery
  xfs: turn the XFS_DA_OP_REPLACE checks in xfs_attr_shortform_addname into asserts
  xfs: remove xfs_attr_sf_hdr_t
  xfs: remove struct xfs_attr_shortform
  xfs: use xfs_attr_sf_findname in xfs_attr_shortform_getvalue
  xfs: remove xfs_attr_shortform_lookup
  xfs: simplify xfs_attr_sf_findname
  xfs: move the xfs_attr_sf_lookup tracepoint
  xfs: return if_data from xfs_idata_realloc
  xfs: make if_data a void pointer
  xfs: fold xfs_rtallocate_extent into xfs_bmap_rtalloc
  xfs: simplify and optimize the RT allocation fallback cascade
  xfs: reorder the minlen and prod calculations in xfs_bmap_rtalloc
  xfs: remove XFS_RTMIN/XFS_RTMAX
  xfs: remove rt-wrappers from xfs_format.h
  xfs: factor out a xfs_rtalloc_sumlevel helper
  xfs: tidy up xfs_rtallocate_extent_exact
  xfs: merge the calls to xfs_rtallocate_range in xfs_rtallocate_block
  xfs: reflow the tail end of xfs_rtallocate_extent_block
  ...

Documentation/filesystems/index.rst

@@ -121,8 +121,5 @@ Documentation for filesystem implementations.
    udf
    virtiofs
    vfat
-   xfs-delayed-logging-design
-   xfs-maintainer-entry-profile
-   xfs-self-describing-metadata
-   xfs-online-fsck-design
+   xfs/index
    zonefs

Documentation/filesystems/xfs/index.rst

@@ -0,0 +1,14 @@
+.. SPDX-License-Identifier: GPL-2.0
+
+============================
+XFS Filesystem Documentation
+============================
+
+.. toctree::
+   :maxdepth: 2
+   :numbered:
+
+   xfs-delayed-logging-design
+   xfs-maintainer-entry-profile
+   xfs-self-describing-metadata
+   xfs-online-fsck-design

Documentation/filesystems/xfs-online-fsck-design.rst → Documentation/filesystems/xfs/xfs-online-fsck-design.rst

@@ -962,7 +962,7 @@ disk, but these buffer verifiers cannot provide any consistency checking
 between metadata structures.
 
 For more information, please see the documentation for
-Documentation/filesystems/xfs-self-describing-metadata.rst
+Documentation/filesystems/xfs/xfs-self-describing-metadata.rst
 
 Reverse Mapping
 ---------------

Documentation/maintainer/maintainer-entry-profile.rst

@@ -105,4 +105,4 @@ to do something different in the near future.
    ../driver-api/media/maintainer-entry-profile
    ../driver-api/vfio-pci-device-specific-driver-acceptance
    ../nvme/feature-and-quirk-policy
-   ../filesystems/xfs-maintainer-entry-profile
+   ../filesystems/xfs/xfs-maintainer-entry-profile

MAINTAINERS

@@ -23846,10 +23846,10 @@ S:	Supported
 W:	http://xfs.org/
 C:	irc://irc.oftc.net/xfs
 T:	git git://git.kernel.org/pub/scm/fs/xfs/xfs-linux.git
-P:	Documentation/filesystems/xfs-maintainer-entry-profile.rst
+P:	Documentation/filesystems/xfs/xfs-maintainer-entry-profile.rst
 F:	Documentation/ABI/testing/sysfs-fs-xfs
 F:	Documentation/admin-guide/xfs.rst
-F:	Documentation/filesystems/xfs-*
+F:	Documentation/filesystems/xfs/*
 F:	fs/xfs/
 F:	include/uapi/linux/dqblk_xfs.h
 F:	include/uapi/linux/fsmap.h

drivers/dax/super.c

@@ -326,7 +326,8 @@ void kill_dax(struct dax_device *dax_dev)
 		return;
 
 	if (dax_dev->holder_data != NULL)
-		dax_holder_notify_failure(dax_dev, 0, U64_MAX, 0);
+		dax_holder_notify_failure(dax_dev, 0, U64_MAX,
+				MF_MEM_PRE_REMOVE);
 
 	clear_bit(DAXDEV_ALIVE, &dax_dev->flags);
 	synchronize_srcu(&dax_srcu);

fs/xfs/Makefile

@@ -145,6 +145,7 @@ ifeq ($(CONFIG_XFS_ONLINE_SCRUB),y)
 
 xfs-y				+= $(addprefix scrub/, \
 				   trace.o \
+				   agb_bitmap.o \
 				   agheader.o \
 				   alloc.o \
 				   attr.o \
@@ -175,14 +176,32 @@ xfs-$(CONFIG_XFS_RT)		+= $(addprefix scrub/, \
 				   rtsummary.o \
 				   )
 
-xfs-$(CONFIG_XFS_QUOTA)		+= scrub/quota.o
+xfs-$(CONFIG_XFS_QUOTA)		+= $(addprefix scrub/, \
+				   dqiterate.o \
+				   quota.o \
+				   )
 
 # online repair
 ifeq ($(CONFIG_XFS_ONLINE_REPAIR),y)
 xfs-y				+= $(addprefix scrub/, \
 				   agheader_repair.o \
+				   alloc_repair.o \
+				   bmap_repair.o \
+				   cow_repair.o \
+				   ialloc_repair.o \
+				   inode_repair.o \
+				   newbt.o \
 				   reap.o \
+				   refcount_repair.o \
 				   repair.o \
 				   )
+
+xfs-$(CONFIG_XFS_RT)		+= $(addprefix scrub/, \
+				   rtbitmap_repair.o \
+				   )
+
+xfs-$(CONFIG_XFS_QUOTA)		+= $(addprefix scrub/, \
+				   quota_repair.o \
+				   )
 endif
 endif

fs/xfs/libxfs/xfs_ag.c

@@ -332,6 +332,31 @@ xfs_agino_range(
 	return __xfs_agino_range(mp, xfs_ag_block_count(mp, agno), first, last);
 }
 
+/*
+ * Free perag within the specified AG range, it is only used to free unused
+ * perags under the error handling path.
+ */
+void
+xfs_free_unused_perag_range(
+	struct xfs_mount	*mp,
+	xfs_agnumber_t		agstart,
+	xfs_agnumber_t		agend)
+{
+	struct xfs_perag	*pag;
+	xfs_agnumber_t		index;
+
+	for (index = agstart; index < agend; index++) {
+		spin_lock(&mp->m_perag_lock);
+		pag = radix_tree_delete(&mp->m_perag_tree, index);
+		spin_unlock(&mp->m_perag_lock);
+		if (!pag)
+			break;
+		xfs_buf_hash_destroy(pag);
+		xfs_defer_drain_free(&pag->pag_intents_drain);
+		kmem_free(pag);
+	}
+}
+
 int
 xfs_initialize_perag(
 	struct xfs_mount	*mp,
@@ -424,19 +449,14 @@ xfs_initialize_perag(
 
 out_remove_pag:
 	xfs_defer_drain_free(&pag->pag_intents_drain);
+	spin_lock(&mp->m_perag_lock);
 	radix_tree_delete(&mp->m_perag_tree, index);
+	spin_unlock(&mp->m_perag_lock);
 out_free_pag:
 	kmem_free(pag);
 out_unwind_new_pags:
 	/* unwind any prior newly initialized pags */
-	for (index = first_initialised; index < agcount; index++) {
-		pag = radix_tree_delete(&mp->m_perag_tree, index);
-		if (!pag)
-			break;
-		xfs_buf_hash_destroy(pag);
-		xfs_defer_drain_free(&pag->pag_intents_drain);
-		kmem_free(pag);
-	}
+	xfs_free_unused_perag_range(mp, first_initialised, agcount);
 	return error;
 }
 
@@ -984,7 +1004,7 @@ xfs_ag_shrink_space(
 		if (err2 != -ENOSPC)
 			goto resv_err;
 
-		err2 = __xfs_free_extent_later(*tpp, args.fsbno, delta, NULL,
+		err2 = xfs_free_extent_later(*tpp, args.fsbno, delta, NULL,
 				XFS_AG_RESV_NONE, true);
 		if (err2)
 			goto resv_err;

fs/xfs/libxfs/xfs_ag.h

@@ -80,6 +80,16 @@ struct xfs_perag {
 	 */
 	uint16_t	pag_checked;
 	uint16_t	pag_sick;
+
+#ifdef CONFIG_XFS_ONLINE_REPAIR
+	/*
+	 * Alternate btree heights so that online repair won't trip the write
+	 * verifiers while rebuilding the AG btrees.
+	 */
+	uint8_t		pagf_repair_levels[XFS_BTNUM_AGF];
+	uint8_t		pagf_repair_refcount_level;
+#endif
+
 	spinlock_t	pag_state_lock;
 
 	spinlock_t	pagb_lock;	/* lock for pagb_tree */
@@ -133,6 +143,8 @@ __XFS_AG_OPSTATE(prefers_metadata, PREFERS_METADATA)
 __XFS_AG_OPSTATE(allows_inodes, ALLOWS_INODES)
 __XFS_AG_OPSTATE(agfl_needs_reset, AGFL_NEEDS_RESET)
 
+void xfs_free_unused_perag_range(struct xfs_mount *mp, xfs_agnumber_t agstart,
+			xfs_agnumber_t agend);
 int xfs_initialize_perag(struct xfs_mount *mp, xfs_agnumber_t agcount,
 			xfs_rfsblock_t dcount, xfs_agnumber_t *maxagi);
 int xfs_initialize_perag_data(struct xfs_mount *mp, xfs_agnumber_t agno);

fs/xfs/libxfs/xfs_ag_resv.c

@@ -411,6 +411,8 @@ xfs_ag_resv_free_extent(
 		fallthrough;
 	case XFS_AG_RESV_NONE:
 		xfs_trans_mod_sb(tp, XFS_TRANS_SB_FDBLOCKS, (int64_t)len);
+		fallthrough;
+	case XFS_AG_RESV_IGNORE:
 		return;
 	}
 

fs/xfs/libxfs/xfs_alloc.c

@@ -246,11 +246,9 @@ xfs_alloc_btrec_to_irec(
 /* Simple checks for free space records. */
 xfs_failaddr_t
 xfs_alloc_check_irec(
-	struct xfs_btree_cur		*cur,
-	const struct xfs_alloc_rec_incore *irec)
+	struct xfs_perag			*pag,
+	const struct xfs_alloc_rec_incore	*irec)
 {
-	struct xfs_perag		*pag = cur->bc_ag.pag;
-
 	if (irec->ar_blockcount == 0)
 		return __this_address;
 
@@ -299,7 +297,7 @@ xfs_alloc_get_rec(
 		return error;
 
 	xfs_alloc_btrec_to_irec(rec, &irec);
-	fa = xfs_alloc_check_irec(cur, &irec);
+	fa = xfs_alloc_check_irec(cur->bc_ag.pag, &irec);
 	if (fa)
 		return xfs_alloc_complain_bad_rec(cur, fa, &irec);
 
@@ -2514,22 +2512,23 @@ xfs_defer_agfl_block(
 	trace_xfs_agfl_free_defer(mp, agno, 0, agbno, 1);
 
 	xfs_extent_free_get_group(mp, xefi);
-	xfs_defer_add(tp, XFS_DEFER_OPS_TYPE_AGFL_FREE, &xefi->xefi_list);
+	xfs_defer_add(tp, &xefi->xefi_list, &xfs_agfl_free_defer_type);
 	return 0;
 }
 
 /*
  * Add the extent to the list of extents to be free at transaction end.
  * The list is maintained sorted (by block number).
  */
-int
-__xfs_free_extent_later(
+static int
+xfs_defer_extent_free(
 	struct xfs_trans		*tp,
 	xfs_fsblock_t			bno,
 	xfs_filblks_t			len,
 	const struct xfs_owner_info	*oinfo,
 	enum xfs_ag_resv_type		type,
-	bool				skip_discard)
+	bool				skip_discard,
+	struct xfs_defer_pending	**dfpp)
 {
 	struct xfs_extent_free_item	*xefi;
 	struct xfs_mount		*mp = tp->t_mountp;
@@ -2577,10 +2576,105 @@ __xfs_free_extent_later(
 			XFS_FSB_TO_AGBNO(tp->t_mountp, bno), len);
 
 	xfs_extent_free_get_group(mp, xefi);
-	xfs_defer_add(tp, XFS_DEFER_OPS_TYPE_FREE, &xefi->xefi_list);
+	*dfpp = xfs_defer_add(tp, &xefi->xefi_list, &xfs_extent_free_defer_type);
 	return 0;
 }
 
+int
+xfs_free_extent_later(
+	struct xfs_trans		*tp,
+	xfs_fsblock_t			bno,
+	xfs_filblks_t			len,
+	const struct xfs_owner_info	*oinfo,
+	enum xfs_ag_resv_type		type,
+	bool				skip_discard)
+{
+	struct xfs_defer_pending	*dontcare = NULL;
+
+	return xfs_defer_extent_free(tp, bno, len, oinfo, type, skip_discard,
+			&dontcare);
+}
+
+/*
+ * Set up automatic freeing of unwritten space in the filesystem.
+ *
+ * This function attached a paused deferred extent free item to the
+ * transaction.  Pausing means that the EFI will be logged in the next
+ * transaction commit, but the pending EFI will not be finished until the
+ * pending item is unpaused.
+ *
+ * If the system goes down after the EFI has been persisted to the log but
+ * before the pending item is unpaused, log recovery will find the EFI, fail to
+ * find the EFD, and free the space.
+ *
+ * If the pending item is unpaused, the next transaction commit will log an EFD
+ * without freeing the space.
+ *
+ * Caller must ensure that the tp, fsbno, len, oinfo, and resv flags of the
+ * @args structure are set to the relevant values.
+ */
+int
+xfs_alloc_schedule_autoreap(
+	const struct xfs_alloc_arg	*args,
+	bool				skip_discard,
+	struct xfs_alloc_autoreap	*aarp)
+{
+	int				error;
+
+	error = xfs_defer_extent_free(args->tp, args->fsbno, args->len,
+			&args->oinfo, args->resv, skip_discard, &aarp->dfp);
+	if (error)
+		return error;
+
+	xfs_defer_item_pause(args->tp, aarp->dfp);
+	return 0;
+}
+
+/*
+ * Cancel automatic freeing of unwritten space in the filesystem.
+ *
+ * Earlier, we created a paused deferred extent free item and attached it to
+ * this transaction so that we could automatically roll back a new space
+ * allocation if the system went down.  Now we want to cancel the paused work
+ * item by marking the EFI stale so we don't actually free the space, unpausing
+ * the pending item and logging an EFD.
+ *
+ * The caller generally should have already mapped the space into the ondisk
+ * filesystem.  If the reserved space was partially used, the caller must call
+ * xfs_free_extent_later to create a new EFI to free the unused space.
+ */
+void
+xfs_alloc_cancel_autoreap(
+	struct xfs_trans		*tp,
+	struct xfs_alloc_autoreap	*aarp)
+{
+	struct xfs_defer_pending	*dfp = aarp->dfp;
+	struct xfs_extent_free_item	*xefi;
+
+	if (!dfp)
+		return;
+
+	list_for_each_entry(xefi, &dfp->dfp_work, xefi_list)
+		xefi->xefi_flags |= XFS_EFI_CANCELLED;
+
+	xfs_defer_item_unpause(tp, dfp);
+}
+
+/*
+ * Commit automatic freeing of unwritten space in the filesystem.
+ *
+ * This unpauses an earlier _schedule_autoreap and commits to freeing the
+ * allocated space.  Call this if none of the reserved space was used.
+ */
+void
+xfs_alloc_commit_autoreap(
+	struct xfs_trans		*tp,
+	struct xfs_alloc_autoreap	*aarp)
+{
+	if (aarp->dfp)
+		xfs_defer_item_unpause(tp, aarp->dfp);
+}
+
 #ifdef DEBUG
 /*
  * Check if an AGF has a free extent record whose length is equal to
@@ -3848,7 +3942,7 @@ xfs_alloc_query_range_helper(
 	xfs_failaddr_t				fa;
 
 	xfs_alloc_btrec_to_irec(rec, &irec);
-	fa = xfs_alloc_check_irec(cur, &irec);
+	fa = xfs_alloc_check_irec(cur->bc_ag.pag, &irec);
 	if (fa)
 		return xfs_alloc_complain_bad_rec(cur, fa, &irec);