Merge tag 'xfs-fixes-6.14-rc4' of git://git.kernel.org/pub/scm/fs/xfs/xfs-linux

Pull xfs fixes from Carlos Maiolino:
 "Just a collection of bug fixes, nothing really stands out"

* tag 'xfs-fixes-6.14-rc4' of git://git.kernel.org/pub/scm/fs/xfs/xfs-linux:
  xfs: flush inodegc before swapon
  xfs: rename xfs_iomap_swapfile_activate to xfs_vm_swap_activate
  xfs: Do not allow norecovery mount with quotacheck
  xfs: do not check NEEDSREPAIR if ro,norecovery mount.
  xfs: fix data fork format filtering during inode repair
  xfs: fix online repair probing when CONFIG_XFS_ONLINE_REPAIR=n

Author: torvalds

fs/xfs/scrub/common.h

@@ -224,7 +224,6 @@ static inline bool xchk_skip_xref(struct xfs_scrub_metadata *sm)
 bool xchk_dir_looks_zapped(struct xfs_inode *dp);
 bool xchk_pptr_looks_zapped(struct xfs_inode *ip);
 
-#ifdef CONFIG_XFS_ONLINE_REPAIR
 /* Decide if a repair is required. */
 static inline bool xchk_needs_repair(const struct xfs_scrub_metadata *sm)
 {
@@ -244,10 +243,6 @@ static inline bool xchk_could_repair(const struct xfs_scrub *sc)
 	return (sc->sm->sm_flags & XFS_SCRUB_IFLAG_REPAIR) &&
 		!(sc->flags & XREP_ALREADY_FIXED);
 }
-#else
-# define xchk_needs_repair(sc)		(false)
-# define xchk_could_repair(sc)		(false)
-#endif /* CONFIG_XFS_ONLINE_REPAIR */
 
 int xchk_metadata_inode_forks(struct xfs_scrub *sc);
 

fs/xfs/scrub/inode_repair.c

@@ -1055,9 +1055,17 @@ xrep_dinode_check_dfork(
 			return true;
 		break;
 	case S_IFREG:
-		if (fmt == XFS_DINODE_FMT_LOCAL)
+		switch (fmt) {
+		case XFS_DINODE_FMT_LOCAL:
 			return true;
-		fallthrough;
+		case XFS_DINODE_FMT_EXTENTS:
+		case XFS_DINODE_FMT_BTREE:
+		case XFS_DINODE_FMT_META_BTREE:
+			break;
+		default:
+			return true;
+		}
+		break;
 	case S_IFLNK:
 	case S_IFDIR:
 		switch (fmt) {

fs/xfs/scrub/repair.h

@@ -191,7 +191,16 @@ int xrep_reset_metafile_resv(struct xfs_scrub *sc);
 #else
 
 #define xrep_ino_dqattach(sc)	(0)
-#define xrep_will_attempt(sc)	(false)
+
+/*
+ * When online repair is not built into the kernel, we still want to attempt
+ * the repair so that the stub xrep_attempt below will return EOPNOTSUPP.
+ */
+static inline bool xrep_will_attempt(const struct xfs_scrub *sc)
+{
+	return (sc->sm->sm_flags & XFS_SCRUB_IFLAG_FORCE_REBUILD) ||
+		xchk_needs_repair(sc->sm);
+}
 
 static inline int
 xrep_attempt(

fs/xfs/scrub/scrub.c

@@ -149,6 +149,18 @@ xchk_probe(
 	if (xchk_should_terminate(sc, &error))
 		return error;
 
+	/*
+	 * If the caller is probing to see if repair works but repair isn't
+	 * built into the kernel, return EOPNOTSUPP because that's the signal
+	 * that userspace expects.  If online repair is built in, set the
+	 * CORRUPT flag (without any of the usual tracing/logging) to force us
+	 * into xrep_probe.
+	 */
+	if (xchk_could_repair(sc)) {
+		if (!IS_ENABLED(CONFIG_XFS_ONLINE_REPAIR))
+			return -EOPNOTSUPP;
+		sc->sm->sm_flags |= XFS_SCRUB_OFLAG_CORRUPT;
+	}
 	return 0;
 }
 

fs/xfs/xfs_aops.c

@@ -19,6 +19,7 @@
 #include "xfs_reflink.h"
 #include "xfs_errortag.h"
 #include "xfs_error.h"
+#include "xfs_icache.h"
 
 struct xfs_writepage_ctx {
 	struct iomap_writepage_ctx ctx;
@@ -528,12 +529,44 @@ xfs_vm_readahead(
 }
 
 static int
-xfs_iomap_swapfile_activate(
+xfs_vm_swap_activate(
 	struct swap_info_struct		*sis,
 	struct file			*swap_file,
 	sector_t			*span)
 {
-	sis->bdev = xfs_inode_buftarg(XFS_I(file_inode(swap_file)))->bt_bdev;
+	struct xfs_inode		*ip = XFS_I(file_inode(swap_file));
+
+	/*
+	 * Swap file activation can race against concurrent shared extent
+	 * removal in files that have been cloned.  If this happens,
+	 * iomap_swapfile_iter() can fail because it encountered a shared
+	 * extent even though an operation is in progress to remove those
+	 * shared extents.
+	 *
+	 * This race becomes problematic when we defer extent removal
+	 * operations beyond the end of a syscall (i.e. use async background
+	 * processing algorithms).  Users think the extents are no longer
+	 * shared, but iomap_swapfile_iter() still sees them as shared
+	 * because the refcountbt entries for the extents being removed have
+	 * not yet been updated.  Hence the swapon call fails unexpectedly.
+	 *
+	 * The race condition is currently most obvious from the unlink()
+	 * operation as extent removal is deferred until after the last
+	 * reference to the inode goes away.  We then process the extent
+	 * removal asynchronously, hence triggers the "syscall completed but
+	 * work not done" condition mentioned above.  To close this race
+	 * window, we need to flush any pending inodegc operations to ensure
+	 * they have updated the refcountbt records before we try to map the
+	 * swapfile.
+	 */
+	xfs_inodegc_flush(ip->i_mount);
+
+	/*
+	 * Direct the swap code to the correct block device when this file
+	 * sits on the RT device.
+	 */
+	sis->bdev = xfs_inode_buftarg(ip)->bt_bdev;
+
 	return iomap_swapfile_activate(sis, swap_file, span,
 			&xfs_read_iomap_ops);
 }
@@ -549,11 +582,11 @@ const struct address_space_operations xfs_address_space_operations = {
 	.migrate_folio		= filemap_migrate_folio,
 	.is_partially_uptodate  = iomap_is_partially_uptodate,
 	.error_remove_folio	= generic_error_remove_folio,
-	.swap_activate		= xfs_iomap_swapfile_activate,
+	.swap_activate		= xfs_vm_swap_activate,
 };
 
 const struct address_space_operations xfs_dax_aops = {
 	.writepages		= xfs_dax_writepages,
 	.dirty_folio		= noop_dirty_folio,
-	.swap_activate		= xfs_iomap_swapfile_activate,
+	.swap_activate		= xfs_vm_swap_activate,
 };

fs/xfs/xfs_qm_bhv.c

@@ -78,6 +78,28 @@ xfs_qm_statvfs(
 	}
 }
 
+STATIC int
+xfs_qm_validate_state_change(
+	struct xfs_mount	*mp,
+	uint			uqd,
+	uint			gqd,
+	uint			pqd)
+{
+	int state;
+
+	/* Is quota state changing? */
+	state = ((uqd && !XFS_IS_UQUOTA_ON(mp)) ||
+		(!uqd &&  XFS_IS_UQUOTA_ON(mp)) ||
+		 (gqd && !XFS_IS_GQUOTA_ON(mp)) ||
+		(!gqd &&  XFS_IS_GQUOTA_ON(mp)) ||
+		 (pqd && !XFS_IS_PQUOTA_ON(mp)) ||
+		(!pqd &&  XFS_IS_PQUOTA_ON(mp)));
+
+	return  state &&
+		(xfs_dev_is_read_only(mp, "changing quota state") ||
+		xfs_has_norecovery(mp));
+}
+
 int
 xfs_qm_newmount(
 	xfs_mount_t	*mp,
@@ -97,24 +119,25 @@ xfs_qm_newmount(
 	}
 
 	/*
-	 * If the device itself is read-only, we can't allow
-	 * the user to change the state of quota on the mount -
-	 * this would generate a transaction on the ro device,
-	 * which would lead to an I/O error and shutdown
+	 * If the device itself is read-only and/or in norecovery
+	 * mode, we can't allow the user to change the state of
+	 * quota on the mount - this would generate a transaction
+	 * on the ro device, which would lead to an I/O error and
+	 * shutdown.
 	 */
 
-	if (((uquotaondisk && !XFS_IS_UQUOTA_ON(mp)) ||
-	    (!uquotaondisk &&  XFS_IS_UQUOTA_ON(mp)) ||
-	     (gquotaondisk && !XFS_IS_GQUOTA_ON(mp)) ||
-	    (!gquotaondisk &&  XFS_IS_GQUOTA_ON(mp)) ||
-	     (pquotaondisk && !XFS_IS_PQUOTA_ON(mp)) ||
-	    (!pquotaondisk &&  XFS_IS_PQUOTA_ON(mp)))  &&
-	    xfs_dev_is_read_only(mp, "changing quota state")) {
-		xfs_warn(mp, "please mount with%s%s%s%s.",
-			(!quotaondisk ? "out quota" : ""),
-			(uquotaondisk ? " usrquota" : ""),
-			(gquotaondisk ? " grpquota" : ""),
-			(pquotaondisk ? " prjquota" : ""));
+	if (xfs_qm_validate_state_change(mp, uquotaondisk,
+			    gquotaondisk, pquotaondisk)) {
+
+		if (xfs_has_metadir(mp))
+			xfs_warn(mp,
+		"metadir enabled, please mount without any quota mount options");
+		else
+			xfs_warn(mp, "please mount with%s%s%s%s.",
+				(!quotaondisk ? "out quota" : ""),
+				(uquotaondisk ? " usrquota" : ""),
+				(gquotaondisk ? " grpquota" : ""),
+				(pquotaondisk ? " prjquota" : ""));
 		return -EPERM;
 	}
 

fs/xfs/xfs_super.c

@@ -1661,8 +1661,12 @@ xfs_fs_fill_super(
 #endif
 	}
 
-	/* Filesystem claims it needs repair, so refuse the mount. */
-	if (xfs_has_needsrepair(mp)) {
+	/*
+	 * Filesystem claims it needs repair, so refuse the mount unless
+	 * norecovery is also specified, in which case the filesystem can
+	 * be mounted with no risk of further damage.
+	 */
+	if (xfs_has_needsrepair(mp) && !xfs_has_norecovery(mp)) {
 		xfs_warn(mp, "Filesystem needs repair.  Please run xfs_repair.");
 		error = -EFSCORRUPTED;
 		goto out_free_sb;