xfs: convert log tail checking to a warning

On the Power platform, the log tail debug checks fire excessively
causing the system to panic early in testing. The debug checks are
known to be racy, though on x86_64 there is no evidence that they
trigger at all.

We want to keep the checks active on debug systems to alert us to
problems with log space accounting, but we need to reduce the impact
of a racy check on testing on the Power platform.

As a result, convert the ASSERT conditions to warnings, and
allow them to fire only once per filesystem mount. This will prevent
false positives from interfering with testing, whilst still
providing us with the indication that they may be a problem with log
space accounting should that occur.

Signed-off-by: Dave Chinner <dchinner@redhat.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Alex Elder <aelder@sgi.com>

2 files changed, 25 insertions, 8 deletions

diff --git a/fs/xfs/xfs_log.c b/fs/xfs/xfs_log.c
index 24643169e632..b612ce4520ae 100644
--- a/fs/xfs/xfs_log.c
+++ b/fs/xfs/xfs_log.c
@@ -3407,6 +3407,17 @@ xlog_verify_dest_ptr(
                 xfs_emerg(log->l_mp, "%s: invalid ptr", __func__);
 }
 
+/*
+ * Check to make sure the grant write head didn't just over lap the tail.  If
+ * the cycles are the same, we can't be overlapping.  Otherwise, make sure that
+ * the cycles differ by exactly one and check the byte count.
+ *
+ * This check is run unlocked, so can give false positives. Rather than assert
+ * on failures, use a warn-once flag and a panic tag to allow the admin to
+ * determine if they want to panic the machine when such an error occurs. For
+ * debug kernels this will have the same effect as using an assert but, unlinke
+ * an assert, it can be turned off at runtime.
+ */
 STATIC void
 xlog_verify_grant_tail(
         struct log      *log)
@@ -3414,17 +3425,22 @@ xlog_verify_grant_tail(
         int             tail_cycle, tail_blocks;
         int             cycle, space;
 
-        /*
-         * Check to make sure the grant write head didn't just over lap the
-         * tail.  If the cycles are the same, we can't be overlapping.
-         * Otherwise, make sure that the cycles differ by exactly one and
-         * check the byte count.
-         */
         xlog_crack_grant_head(&log->l_grant_write_head, &cycle, &space);
         xlog_crack_atomic_lsn(&log->l_tail_lsn, &tail_cycle, &tail_blocks);
         if (tail_cycle != cycle) {
-                ASSERT(cycle - 1 == tail_cycle);
-                ASSERT(space <= BBTOB(tail_blocks));
+                if (cycle - 1 != tail_cycle &&
+                    !(log->l_flags & XLOG_TAIL_WARN)) {
+                        xfs_alert_tag(log->l_mp, XFS_PTAG_LOGRES,
+                                "%s: cycle - 1 != tail_cycle", __func__);
+                        log->l_flags |= XLOG_TAIL_WARN;
+                }
+
+                if (space > BBTOB(tail_blocks) &&
+                    !(log->l_flags & XLOG_TAIL_WARN)) {
+                        xfs_alert_tag(log->l_mp, XFS_PTAG_LOGRES,
+                                "%s: space > BBTOB(tail_blocks)", __func__);
+                        log->l_flags |= XLOG_TAIL_WARN;
+                }
         }
 }
 
diff --git a/fs/xfs/xfs_log_priv.h b/fs/xfs/xfs_log_priv.h
index 15dbf1f9c2be..bc988d4ef958 100644
--- a/fs/xfs/xfs_log_priv.h
+++ b/fs/xfs/xfs_log_priv.h
@@ -144,6 +144,7 @@ static inline uint xlog_get_client_id(__be32 i)
 #define XLOG_RECOVERY_NEEDED    0x4     /* log was recovered */
 #define XLOG_IO_ERROR           0x8     /* log hit an I/O error, and being
                                            shutdown */
+#define XLOG_TAIL_WARN          0x10    /* log tail verify warning issued */
 
 #ifdef __KERNEL__
 /*