3 files changed, 103 insertions, 1 deletions

diff --git a/fs/xfs/libxfs/xfs_alloc.c b/fs/xfs/libxfs/xfs_alloc.c
index c3702cda010a..e567551402a6 100644
--- a/fs/xfs/libxfs/xfs_alloc.c
+++ b/fs/xfs/libxfs/xfs_alloc.c
@@ -2035,6 +2035,93 @@ xfs_alloc_space_available(
 }
 
 /*
+ * Check the agfl fields of the agf for inconsistency or corruption. The purpose
+ * is to detect an agfl header padding mismatch between current and early v5
+ * kernels. This problem manifests as a 1-slot size difference between the
+ * on-disk flcount and the active [first, last] range of a wrapped agfl. This
+ * may also catch variants of agfl count corruption unrelated to padding. Either
+ * way, we'll reset the agfl and warn the user.
+ *
+ * Return true if a reset is required before the agfl can be used, false
+ * otherwise.
+ */
+static bool
+xfs_agfl_needs_reset(
+	struct xfs_mount	*mp,
+	struct xfs_agf		*agf)
+{
+	uint32_t		f = be32_to_cpu(agf->agf_flfirst);
+	uint32_t		l = be32_to_cpu(agf->agf_fllast);
+	uint32_t		c = be32_to_cpu(agf->agf_flcount);
+	int			agfl_size = XFS_AGFL_SIZE(mp);
+	int			active;
+
+	/* no agfl header on v4 supers */
+	if (!xfs_sb_version_hascrc(&mp->m_sb))
+		return false;
+
+	/*
+	 * The agf read verifier catches severe corruption of these fields.
+	 * Repeat some sanity checks to cover a packed -> unpacked mismatch if
+	 * the verifier allows it.
+	 */
+	if (f >= agfl_size || l >= agfl_size)
+		return true;
+	if (c > agfl_size)
+		return true;
+
+	/*
+	 * Check consistency between the on-disk count and the active range. An
+	 * agfl padding mismatch manifests as an inconsistent flcount.
+	 */
+	if (c && l >= f)
+		active = l - f + 1;
+	else if (c)
+		active = agfl_size - f + l + 1;
+	else
+		active = 0;
+
+	return active != c;
+}
+
+/*
+ * Reset the agfl to an empty state. Ignore/drop any existing blocks since the
+ * agfl content cannot be trusted. Warn the user that a repair is required to
+ * recover leaked blocks.
+ *
+ * The purpose of this mechanism is to handle filesystems affected by the agfl
+ * header padding mismatch problem. A reset keeps the filesystem online with a
+ * relatively minor free space accounting inconsistency rather than suffer the
+ * inevitable crash from use of an invalid agfl block.
+ */
+static void
+xfs_agfl_reset(
+	struct xfs_trans	*tp,
+	struct xfs_buf		*agbp,
+	struct xfs_perag	*pag)
+{
+	struct xfs_mount	*mp = tp->t_mountp;
+	struct xfs_agf		*agf = XFS_BUF_TO_AGF(agbp);
+
+	ASSERT(pag->pagf_agflreset);
+	trace_xfs_agfl_reset(mp, agf, 0, _RET_IP_);
+
+	xfs_warn(mp,
+	       "WARNING: Reset corrupted AGFL on AG %u. %d blocks leaked. "
+	       "Please unmount and run xfs_repair.",
+	         pag->pag_agno, pag->pagf_flcount);
+
+	agf->agf_flfirst = 0;
+	agf->agf_fllast = cpu_to_be32(XFS_AGFL_SIZE(mp) - 1);
+	agf->agf_flcount = 0;
+	xfs_alloc_log_agf(tp, agbp, XFS_AGF_FLFIRST | XFS_AGF_FLLAST |
+				    XFS_AGF_FLCOUNT);
+
+	pag->pagf_flcount = 0;
+	pag->pagf_agflreset = false;
+}
+
+/*
  * Decide whether to use this allocation group for this allocation.
  * If so, fix up the btree freelist's size.
  */
@@ -2095,6 +2182,10 @@ xfs_alloc_fix_freelist(
 		}
 	}
 
+	/* reset a padding mismatched agfl before final free space check */
+	if (pag->pagf_agflreset)
+		xfs_agfl_reset(tp, agbp, pag);
+
 	/* If there isn't enough total space or single-extent, reject it. */
 	need = xfs_alloc_min_freelist(mp, pag);
 	if (!xfs_alloc_space_available(args, need, flags))
@@ -2251,6 +2342,7 @@ xfs_alloc_get_freelist(
 		agf->agf_flfirst = 0;
 
 	pag = xfs_perag_get(mp, be32_to_cpu(agf->agf_seqno));
+	ASSERT(!pag->pagf_agflreset);
 	be32_add_cpu(&agf->agf_flcount, -1);
 	xfs_trans_agflist_delta(tp, -1);
 	pag->pagf_flcount--;
@@ -2362,6 +2454,7 @@ xfs_alloc_put_freelist(
 		agf->agf_fllast = 0;
 
 	pag = xfs_perag_get(mp, be32_to_cpu(agf->agf_seqno));
+	ASSERT(!pag->pagf_agflreset);
 	be32_add_cpu(&agf->agf_flcount, 1);
 	xfs_trans_agflist_delta(tp, 1);
 	pag->pagf_flcount++;
@@ -2568,6 +2661,7 @@ xfs_alloc_read_agf(
 		pag->pagb_count = 0;
 		pag->pagb_tree = RB_ROOT;
 		pag->pagf_init = 1;
+		pag->pagf_agflreset = xfs_agfl_needs_reset(mp, agf);
 	}
 #ifdef DEBUG
 	else if (!XFS_FORCED_SHUTDOWN(mp)) {
diff --git a/fs/xfs/xfs_mount.h b/fs/xfs/xfs_mount.h
index 5415f9031ef8..7cb099e1c84c 100644
--- a/fs/xfs/xfs_mount.h
+++ b/fs/xfs/xfs_mount.h
@@ -368,6 +368,7 @@ typedef struct xfs_perag {
 	char		pagi_inodeok;	/* The agi is ok for inodes */
 	__uint8_t	pagf_levels[XFS_BTNUM_AGF];
 					/* # of levels in bno & cnt btree */
+	bool		pagf_agflreset; /* agfl requires reset before use */
 	__uint32_t	pagf_flcount;	/* count of blocks in freelist */
 	xfs_extlen_t	pagf_freeblks;	/* total free blocks */
 	xfs_extlen_t	pagf_longest;	/* longest free space */
diff --git a/fs/xfs/xfs_trace.h b/fs/xfs/xfs_trace.h
index bdf69e1c7410..42a7c0da898f 100644
--- a/fs/xfs/xfs_trace.h
+++ b/fs/xfs/xfs_trace.h
@@ -1516,7 +1516,7 @@ TRACE_EVENT(xfs_trans_commit_lsn,
 		  __entry->lsn)
 );
 
-TRACE_EVENT(xfs_agf,
+DECLARE_EVENT_CLASS(xfs_agf_class,
 	TP_PROTO(struct xfs_mount *mp, struct xfs_agf *agf, int flags,
 		 unsigned long caller_ip),
 	TP_ARGS(mp, agf, flags, caller_ip),
@@ -1572,6 +1572,13 @@ TRACE_EVENT(xfs_agf,
 		  __entry->longest,
 		  (void *)__entry->caller_ip)
 );
+#define DEFINE_AGF_EVENT(name) \
+DEFINE_EVENT(xfs_agf_class, name, \
+	TP_PROTO(struct xfs_mount *mp, struct xfs_agf *agf, int flags, \
+		 unsigned long caller_ip), \
+	TP_ARGS(mp, agf, flags, caller_ip))
+DEFINE_AGF_EVENT(xfs_agf);
+DEFINE_AGF_EVENT(xfs_agfl_reset);
 
 TRACE_EVENT(xfs_free_extent,
 	TP_PROTO(struct xfs_mount *mp, xfs_agnumber_t agno, xfs_agblock_t agbno,