Merge tag 'v6.9-rc1' into sched/core, to pick up fixes and to refresh the branch

Signed-off-by: Ingo Molnar <mingo@kernel.org>

1 files changed, 158 insertions, 74 deletions

diff --git a/fs/xfs/libxfs/xfs_ialloc.c b/fs/xfs/libxfs/xfs_ialloc.c
index 2361a22035b0..e5ac3e5430c4 100644
--- a/fs/xfs/libxfs/xfs_ialloc.c
+++ b/fs/xfs/libxfs/xfs_ialloc.c
@@ -27,6 +27,7 @@
 #include "xfs_log.h"
 #include "xfs_rmap.h"
 #include "xfs_ag.h"
+#include "xfs_health.h"
 
 /*
  * Lookup a record by ino in the btree given by cur.
@@ -140,13 +141,13 @@ xfs_inobt_complain_bad_rec(
 	struct xfs_mount		*mp = cur->bc_mp;
 
 	xfs_warn(mp,
-		"%s Inode BTree record corruption in AG %d detected at %pS!",
-		cur->bc_btnum == XFS_BTNUM_INO ? "Used" : "Free",
-		cur->bc_ag.pag->pag_agno, fa);
+		"%sbt record corruption in AG %d detected at %pS!",
+		cur->bc_ops->name, cur->bc_ag.pag->pag_agno, fa);
 	xfs_warn(mp,
 "start inode 0x%x, count 0x%x, free 0x%x freemask 0x%llx, holemask 0x%x",
 		irec->ir_startino, irec->ir_count, irec->ir_freecount,
 		irec->ir_free, irec->ir_holemask);
+	xfs_btree_mark_sick(cur);
 	return -EFSCORRUPTED;
 }
 
@@ -205,14 +206,17 @@ xfs_inobt_insert(
 	struct xfs_buf		*agbp,
 	xfs_agino_t		newino,
 	xfs_agino_t		newlen,
-	xfs_btnum_t		btnum)
+	bool			is_finobt)
 {
 	struct xfs_btree_cur	*cur;
 	xfs_agino_t		thisino;
 	int			i;
 	int			error;
 
-	cur = xfs_inobt_init_cursor(pag, tp, agbp, btnum);
+	if (is_finobt)
+		cur = xfs_finobt_init_cursor(pag, tp, agbp);
+	else
+		cur = xfs_inobt_init_cursor(pag, tp, agbp);
 
 	for (thisino = newino;
 	     thisino < newino + newlen;
@@ -528,16 +532,14 @@ __xfs_inobt_rec_merge(
 }
 
 /*
- * Insert a new sparse inode chunk into the associated inode btree. The inode
- * record for the sparse chunk is pre-aligned to a startino that should match
- * any pre-existing sparse inode record in the tree. This allows sparse chunks
- * to fill over time.
+ * Insert a new sparse inode chunk into the associated inode allocation btree.
+ * The inode record for the sparse chunk is pre-aligned to a startino that
+ * should match any pre-existing sparse inode record in the tree. This allows
+ * sparse chunks to fill over time.
  *
- * This function supports two modes of handling preexisting records depending on
- * the merge flag. If merge is true, the provided record is merged with the
+ * If no preexisting record exists, the provided record is inserted.
+ * If there is a preexisting record, the provided record is merged with the
  * existing record and updated in place. The merged record is returned in nrec.
- * If merge is false, an existing record is replaced with the provided record.
- * If no preexisting record exists, the provided record is always inserted.
  *
  * It is considered corruption if a merge is requested and not possible. Given
  * the sparse inode alignment constraints, this should never happen.
@@ -547,9 +549,7 @@ xfs_inobt_insert_sprec(
 	struct xfs_perag		*pag,
 	struct xfs_trans		*tp,
 	struct xfs_buf			*agbp,
-	int				btnum,
-	struct xfs_inobt_rec_incore	*nrec,	/* in/out: new/merged rec. */
-	bool				merge)	/* merge or replace */
+	struct xfs_inobt_rec_incore	*nrec)	/* in/out: new/merged rec. */
 {
 	struct xfs_mount		*mp = pag->pag_mount;
 	struct xfs_btree_cur		*cur;
@@ -557,7 +557,7 @@ xfs_inobt_insert_sprec(
 	int				i;
 	struct xfs_inobt_rec_incore	rec;
 
-	cur = xfs_inobt_init_cursor(pag, tp, agbp, btnum);
+	cur = xfs_inobt_init_cursor(pag, tp, agbp);
 
 	/* the new record is pre-aligned so we know where to look */
 	error = xfs_inobt_lookup(cur, nrec->ir_startino, XFS_LOOKUP_EQ, &i);
@@ -571,6 +571,7 @@ xfs_inobt_insert_sprec(
 		if (error)
 			goto error;
 		if (XFS_IS_CORRUPT(mp, i != 1)) {
+			xfs_btree_mark_sick(cur);
 			error = -EFSCORRUPTED;
 			goto error;
 		}
@@ -579,45 +580,45 @@ xfs_inobt_insert_sprec(
 	}
 
 	/*
-	 * A record exists at this startino. Merge or replace the record
-	 * depending on what we've been asked to do.
+	 * A record exists at this startino.  Merge the records.
 	 */
-	if (merge) {
-		error = xfs_inobt_get_rec(cur, &rec, &i);
-		if (error)
-			goto error;
-		if (XFS_IS_CORRUPT(mp, i != 1)) {
-			error = -EFSCORRUPTED;
-			goto error;
-		}
-		if (XFS_IS_CORRUPT(mp, rec.ir_startino != nrec->ir_startino)) {
-			error = -EFSCORRUPTED;
-			goto error;
-		}
+	error = xfs_inobt_get_rec(cur, &rec, &i);
+	if (error)
+		goto error;
+	if (XFS_IS_CORRUPT(mp, i != 1)) {
+		xfs_btree_mark_sick(cur);
+		error = -EFSCORRUPTED;
+		goto error;
+	}
+	if (XFS_IS_CORRUPT(mp, rec.ir_startino != nrec->ir_startino)) {
+		xfs_btree_mark_sick(cur);
+		error = -EFSCORRUPTED;
+		goto error;
+	}
 
-		/*
-		 * This should never fail. If we have coexisting records that
-		 * cannot merge, something is seriously wrong.
-		 */
-		if (XFS_IS_CORRUPT(mp, !__xfs_inobt_can_merge(nrec, &rec))) {
-			error = -EFSCORRUPTED;
-			goto error;
-		}
+	/*
+	 * This should never fail. If we have coexisting records that
+	 * cannot merge, something is seriously wrong.
+	 */
+	if (XFS_IS_CORRUPT(mp, !__xfs_inobt_can_merge(nrec, &rec))) {
+		xfs_btree_mark_sick(cur);
+		error = -EFSCORRUPTED;
+		goto error;
+	}
 
-		trace_xfs_irec_merge_pre(mp, pag->pag_agno, rec.ir_startino,
-					 rec.ir_holemask, nrec->ir_startino,
-					 nrec->ir_holemask);
+	trace_xfs_irec_merge_pre(mp, pag->pag_agno, rec.ir_startino,
+				 rec.ir_holemask, nrec->ir_startino,
+				 nrec->ir_holemask);
 
-		/* merge to nrec to output the updated record */
-		__xfs_inobt_rec_merge(nrec, &rec);
+	/* merge to nrec to output the updated record */
+	__xfs_inobt_rec_merge(nrec, &rec);
 
-		trace_xfs_irec_merge_post(mp, pag->pag_agno, nrec->ir_startino,
-					  nrec->ir_holemask);
+	trace_xfs_irec_merge_post(mp, pag->pag_agno, nrec->ir_startino,
+				  nrec->ir_holemask);
 
-		error = xfs_inobt_rec_check_count(mp, nrec);
-		if (error)
-			goto error;
-	}
+	error = xfs_inobt_rec_check_count(mp, nrec);
+	if (error)
+		goto error;
 
 	error = xfs_inobt_update(cur, nrec);
 	if (error)
@@ -632,6 +633,59 @@ error:
 }
 
 /*
+ * Insert a new sparse inode chunk into the free inode btree. The inode
+ * record for the sparse chunk is pre-aligned to a startino that should match
+ * any pre-existing sparse inode record in the tree. This allows sparse chunks
+ * to fill over time.
+ *
+ * The new record is always inserted, overwriting a pre-existing record if
+ * there is one.
+ */
+STATIC int
+xfs_finobt_insert_sprec(
+	struct xfs_perag		*pag,
+	struct xfs_trans		*tp,
+	struct xfs_buf			*agbp,
+	struct xfs_inobt_rec_incore	*nrec)	/* in/out: new rec. */
+{
+	struct xfs_mount		*mp = pag->pag_mount;
+	struct xfs_btree_cur		*cur;
+	int				error;
+	int				i;
+
+	cur = xfs_finobt_init_cursor(pag, tp, agbp);
+
+	/* the new record is pre-aligned so we know where to look */
+	error = xfs_inobt_lookup(cur, nrec->ir_startino, XFS_LOOKUP_EQ, &i);
+	if (error)
+		goto error;
+	/* if nothing there, insert a new record and return */
+	if (i == 0) {
+		error = xfs_inobt_insert_rec(cur, nrec->ir_holemask,
+					     nrec->ir_count, nrec->ir_freecount,
+					     nrec->ir_free, &i);
+		if (error)
+			goto error;
+		if (XFS_IS_CORRUPT(mp, i != 1)) {
+			xfs_btree_mark_sick(cur);
+			error = -EFSCORRUPTED;
+			goto error;
+		}
+	} else {
+		error = xfs_inobt_update(cur, nrec);
+		if (error)
+			goto error;
+	}
+
+	xfs_btree_del_cursor(cur, XFS_BTREE_NOERROR);
+	return 0;
+error:
+	xfs_btree_del_cursor(cur, XFS_BTREE_ERROR);
+	return error;
+}
+
+
+/*
  * Allocate new inodes in the allocation group specified by agbp.  Returns 0 if
  * inodes were allocated in this AG; -EAGAIN if there was no space in this AG so
  * the caller knows it can try another AG, a hard -ENOSPC when over the maximum
@@ -857,8 +911,7 @@ sparse_alloc:
 		 * if necessary. If a merge does occur, rec is updated to the
 		 * merged record.
 		 */
-		error = xfs_inobt_insert_sprec(pag, tp, agbp,
-				XFS_BTNUM_INO, &rec, true);
+		error = xfs_inobt_insert_sprec(pag, tp, agbp, &rec);
 		if (error == -EFSCORRUPTED) {
 			xfs_alert(args.mp,
 	"invalid sparse inode record: ino 0x%llx holemask 0x%x count %u",
@@ -882,21 +935,19 @@ sparse_alloc:
 		 * existing record with this one.
 		 */
 		if (xfs_has_finobt(args.mp)) {
-			error = xfs_inobt_insert_sprec(pag, tp, agbp,
-				       XFS_BTNUM_FINO, &rec, false);
+			error = xfs_finobt_insert_sprec(pag, tp, agbp, &rec);
 			if (error)
 				return error;
 		}
 	} else {
 		/* full chunk - insert new records to both btrees */
-		error = xfs_inobt_insert(pag, tp, agbp, newino, newlen,
-					 XFS_BTNUM_INO);
+		error = xfs_inobt_insert(pag, tp, agbp, newino, newlen, false);
 		if (error)
 			return error;
 
 		if (xfs_has_finobt(args.mp)) {
 			error = xfs_inobt_insert(pag, tp, agbp, newino,
-						 newlen, XFS_BTNUM_FINO);
+						 newlen, true);
 			if (error)
 				return error;
 		}
@@ -949,8 +1000,10 @@ xfs_ialloc_next_rec(
 		error = xfs_inobt_get_rec(cur, rec, &i);
 		if (error)
 			return error;
-		if (XFS_IS_CORRUPT(cur->bc_mp, i != 1))
+		if (XFS_IS_CORRUPT(cur->bc_mp, i != 1)) {
+			xfs_btree_mark_sick(cur);
 			return -EFSCORRUPTED;
+		}
 	}
 
 	return 0;
@@ -974,8 +1027,10 @@ xfs_ialloc_get_rec(
 		error = xfs_inobt_get_rec(cur, rec, &i);
 		if (error)
 			return error;
-		if (XFS_IS_CORRUPT(cur->bc_mp, i != 1))
+		if (XFS_IS_CORRUPT(cur->bc_mp, i != 1)) {
+			xfs_btree_mark_sick(cur);
 			return -EFSCORRUPTED;
+		}
 	}
 
 	return 0;
@@ -1030,7 +1085,7 @@ xfs_dialloc_ag_inobt(
 	ASSERT(pag->pagi_freecount > 0);
 
  restart_pagno:
-	cur = xfs_inobt_init_cursor(pag, tp, agbp, XFS_BTNUM_INO);
+	cur = xfs_inobt_init_cursor(pag, tp, agbp);
 	/*
 	 * If pagino is 0 (this is the root inode allocation) use newino.
 	 * This must work because we've just allocated some.
@@ -1053,6 +1108,7 @@ xfs_dialloc_ag_inobt(
 		if (error)
 			goto error0;
 		if (XFS_IS_CORRUPT(mp, i != 1)) {
+			xfs_btree_mark_sick(cur);
 			error = -EFSCORRUPTED;
 			goto error0;
 		}
@@ -1061,6 +1117,7 @@ xfs_dialloc_ag_inobt(
 		if (error)
 			goto error0;
 		if (XFS_IS_CORRUPT(mp, j != 1)) {
+			xfs_btree_mark_sick(cur);
 			error = -EFSCORRUPTED;
 			goto error0;
 		}
@@ -1219,6 +1276,7 @@ xfs_dialloc_ag_inobt(
 	if (error)
 		goto error0;
 	if (XFS_IS_CORRUPT(mp, i != 1)) {
+		xfs_btree_mark_sick(cur);
 		error = -EFSCORRUPTED;
 		goto error0;
 	}
@@ -1228,6 +1286,7 @@ xfs_dialloc_ag_inobt(
 		if (error)
 			goto error0;
 		if (XFS_IS_CORRUPT(mp, i != 1)) {
+			xfs_btree_mark_sick(cur);
 			error = -EFSCORRUPTED;
 			goto error0;
 		}
@@ -1237,6 +1296,7 @@ xfs_dialloc_ag_inobt(
 		if (error)
 			goto error0;
 		if (XFS_IS_CORRUPT(mp, i != 1)) {
+			xfs_btree_mark_sick(cur);
 			error = -EFSCORRUPTED;
 			goto error0;
 		}
@@ -1297,8 +1357,10 @@ xfs_dialloc_ag_finobt_near(
 		error = xfs_inobt_get_rec(lcur, rec, &i);
 		if (error)
 			return error;
-		if (XFS_IS_CORRUPT(lcur->bc_mp, i != 1))
+		if (XFS_IS_CORRUPT(lcur->bc_mp, i != 1)) {
+			xfs_btree_mark_sick(lcur);
 			return -EFSCORRUPTED;
+		}
 
 		/*
 		 * See if we've landed in the parent inode record. The finobt
@@ -1322,12 +1384,14 @@ xfs_dialloc_ag_finobt_near(
 		if (error)
 			goto error_rcur;
 		if (XFS_IS_CORRUPT(lcur->bc_mp, j != 1)) {
+			xfs_btree_mark_sick(lcur);
 			error = -EFSCORRUPTED;
 			goto error_rcur;
 		}
 	}
 
 	if (XFS_IS_CORRUPT(lcur->bc_mp, i != 1 && j != 1)) {
+		xfs_btree_mark_sick(lcur);
 		error = -EFSCORRUPTED;
 		goto error_rcur;
 	}
@@ -1383,8 +1447,10 @@ xfs_dialloc_ag_finobt_newino(
 			error = xfs_inobt_get_rec(cur, rec, &i);
 			if (error)
 				return error;
-			if (XFS_IS_CORRUPT(cur->bc_mp, i != 1))
+			if (XFS_IS_CORRUPT(cur->bc_mp, i != 1)) {
+				xfs_btree_mark_sick(cur);
 				return -EFSCORRUPTED;
+			}
 			return 0;
 		}
 	}
@@ -1395,14 +1461,18 @@ xfs_dialloc_ag_finobt_newino(
 	error = xfs_inobt_lookup(cur, 0, XFS_LOOKUP_GE, &i);
 	if (error)
 		return error;
-	if (XFS_IS_CORRUPT(cur->bc_mp, i != 1))
+	if (XFS_IS_CORRUPT(cur->bc_mp, i != 1)) {
+		xfs_btree_mark_sick(cur);
 		return -EFSCORRUPTED;
+	}
 
 	error = xfs_inobt_get_rec(cur, rec, &i);
 	if (error)
 		return error;
-	if (XFS_IS_CORRUPT(cur->bc_mp, i != 1))
+	if (XFS_IS_CORRUPT(cur->bc_mp, i != 1)) {
+		xfs_btree_mark_sick(cur);
 		return -EFSCORRUPTED;
+	}
 
 	return 0;
 }
@@ -1424,14 +1494,18 @@ xfs_dialloc_ag_update_inobt(
 	error = xfs_inobt_lookup(cur, frec->ir_startino, XFS_LOOKUP_EQ, &i);
 	if (error)
 		return error;
-	if (XFS_IS_CORRUPT(cur->bc_mp, i != 1))
+	if (XFS_IS_CORRUPT(cur->bc_mp, i != 1)) {
+		xfs_btree_mark_sick(cur);
 		return -EFSCORRUPTED;
+	}
 
 	error = xfs_inobt_get_rec(cur, &rec, &i);
 	if (error)
 		return error;
-	if (XFS_IS_CORRUPT(cur->bc_mp, i != 1))
+	if (XFS_IS_CORRUPT(cur->bc_mp, i != 1)) {
+		xfs_btree_mark_sick(cur);
 		return -EFSCORRUPTED;
+	}
 	ASSERT((XFS_AGINO_TO_OFFSET(cur->bc_mp, rec.ir_startino) %
 				   XFS_INODES_PER_CHUNK) == 0);
 
@@ -1440,8 +1514,10 @@ xfs_dialloc_ag_update_inobt(
 
 	if (XFS_IS_CORRUPT(cur->bc_mp,
 			   rec.ir_free != frec->ir_free ||
-			   rec.ir_freecount != frec->ir_freecount))
+			   rec.ir_freecount != frec->ir_freecount)) {
+		xfs_btree_mark_sick(cur);
 		return -EFSCORRUPTED;
+	}
 
 	return xfs_inobt_update(cur, &rec);
 }
@@ -1483,7 +1559,7 @@ xfs_dialloc_ag(
 	if (!pagino)
 		pagino = be32_to_cpu(agi->agi_newino);
 
-	cur = xfs_inobt_init_cursor(pag, tp, agbp, XFS_BTNUM_FINO);
+	cur = xfs_finobt_init_cursor(pag, tp, agbp);
 
 	error = xfs_check_agi_freecount(cur);
 	if (error)
@@ -1526,7 +1602,7 @@ xfs_dialloc_ag(
 	 * the original freecount. If all is well, make the equivalent update to
 	 * the inobt using the finobt record and offset information.
 	 */
-	icur = xfs_inobt_init_cursor(pag, tp, agbp, XFS_BTNUM_INO);
+	icur = xfs_inobt_init_cursor(pag, tp, agbp);
 
 	error = xfs_check_agi_freecount(icur);
 	if (error)
@@ -1943,7 +2019,7 @@ xfs_difree_inobt(
 	/*
 	 * Initialize the cursor.
 	 */
-	cur = xfs_inobt_init_cursor(pag, tp, agbp, XFS_BTNUM_INO);
+	cur = xfs_inobt_init_cursor(pag, tp, agbp);
 
 	error = xfs_check_agi_freecount(cur);
 	if (error)
@@ -1958,6 +2034,7 @@ xfs_difree_inobt(
 		goto error0;
 	}
 	if (XFS_IS_CORRUPT(mp, i != 1)) {
+		xfs_btree_mark_sick(cur);
 		error = -EFSCORRUPTED;
 		goto error0;
 	}
@@ -1968,6 +2045,7 @@ xfs_difree_inobt(
 		goto error0;
 	}
 	if (XFS_IS_CORRUPT(mp, i != 1)) {
+		xfs_btree_mark_sick(cur);
 		error = -EFSCORRUPTED;
 		goto error0;
 	}
@@ -2068,7 +2146,7 @@ xfs_difree_finobt(
 	int				error;
 	int				i;
 
-	cur = xfs_inobt_init_cursor(pag, tp, agbp, XFS_BTNUM_FINO);
+	cur = xfs_finobt_init_cursor(pag, tp, agbp);
 
 	error = xfs_inobt_lookup(cur, ibtrec->ir_startino, XFS_LOOKUP_EQ, &i);
 	if (error)
@@ -2080,6 +2158,7 @@ xfs_difree_finobt(
 		 * something is out of sync.
 		 */
 		if (XFS_IS_CORRUPT(mp, ibtrec->ir_freecount != 1)) {
+			xfs_btree_mark_sick(cur);
 			error = -EFSCORRUPTED;
 			goto error;
 		}
@@ -2106,6 +2185,7 @@ xfs_difree_finobt(
 	if (error)
 		goto error;
 	if (XFS_IS_CORRUPT(mp, i != 1)) {
+		xfs_btree_mark_sick(cur);
 		error = -EFSCORRUPTED;
 		goto error;
 	}
@@ -2116,6 +2196,7 @@ xfs_difree_finobt(
 	if (XFS_IS_CORRUPT(mp,
 			   rec.ir_free != ibtrec->ir_free ||
 			   rec.ir_freecount != ibtrec->ir_freecount)) {
+		xfs_btree_mark_sick(cur);
 		error = -EFSCORRUPTED;
 		goto error;
 	}
@@ -2265,7 +2346,7 @@ xfs_imap_lookup(
 	 * we have a record, we need to ensure it contains the inode number
 	 * we are looking up.
 	 */
-	cur = xfs_inobt_init_cursor(pag, tp, agbp, XFS_BTNUM_INO);
+	cur = xfs_inobt_init_cursor(pag, tp, agbp);
 	error = xfs_inobt_lookup(cur, agino, XFS_LOOKUP_LE, &i);
 	if (!error) {
 		if (i)
@@ -2604,6 +2685,8 @@ xfs_read_agi(
 	error = xfs_trans_read_buf(mp, tp, mp->m_ddev_targp,
 			XFS_AG_DADDR(mp, pag->pag_agno, XFS_AGI_DADDR(mp)),
 			XFS_FSS_TO_BB(mp, 1), 0, agibpp, &xfs_agi_buf_ops);
+	if (xfs_metadata_is_sick(error))
+		xfs_ag_mark_sick(pag, XFS_SICK_AG_AGI);
 	if (error)
 		return error;
 	if (tp)
@@ -2765,7 +2848,7 @@ xfs_ialloc_count_inodes(
 	struct xfs_ialloc_count_inodes	ci = {0};
 	int				error;
 
-	ASSERT(cur->bc_btnum == XFS_BTNUM_INO);
+	ASSERT(xfs_btree_is_ino(cur->bc_ops));
 	error = xfs_btree_query_all(cur, xfs_ialloc_count_inodes_rec, &ci);
 	if (error)
 		return error;
@@ -2982,7 +3065,7 @@ xfs_ialloc_check_shrink(
 	if (!xfs_has_sparseinodes(pag->pag_mount))
 		return 0;
 
-	cur = xfs_inobt_init_cursor(pag, tp, agibp, XFS_BTNUM_INO);
+	cur = xfs_inobt_init_cursor(pag, tp, agibp);
 
 	/* Look up the inobt record that would correspond to the new EOFS. */
 	agino = XFS_AGB_TO_AGINO(pag->pag_mount, new_length);
@@ -2995,6 +3078,7 @@ xfs_ialloc_check_shrink(
 		goto out;
 
 	if (!has) {
+		xfs_ag_mark_sick(pag, XFS_SICK_AG_INOBT);
 		error = -EFSCORRUPTED;
 		goto out;
 	}