[017/110] xfs: report fs corruption errors to the health tracking system

Commit Message

Darrick J. Wong March 26, 2024, 3:32 a.m. UTC

From: Darrick J. Wong <[e-mail]>

Source kernel commit: 50645ce8822d23ae3e002d3bee775fa8c315f957

Whenever we encounter corrupt fs metadata, we should report that to the
health monitoring system for later reporting.  A convenient program for
identifying places to insert xfs_*_mark_sick calls is as follows:

#!/bin/bash

# Detect missing calls to xfs_*_mark_sick

filter=cat
tty -s && filter=less

git grep -B3 EFSCORRUPTED fs/xfs/*.[ch] fs/xfs/libxfs/*.[ch] fs/xfs/scrub/*.[ch] | awk '
BEGIN {
ignore = 0;
lineno = 0;
delete lines;
}
{
if ($0 == "--") {
if (!ignore) {
for (i = 0; i < lineno; i++) {
print(lines[i]);
}
printf("--\n");
}
delete lines;
lineno = 0;
ignore = 0;
} else if ($0 ~ /mark_sick/) {
ignore = 1;
} else if ($0 ~ /if .fa/) {
ignore = 1;
} else if ($0 ~ /failaddr/) {
ignore = 1;
} else if ($0 ~ /_verifier_error/) {
ignore = 1;
} else if ($0 ~ /^ \* .*EFSCORRUPTED/) {
ignore = 1;
} else if ($0 ~ /== -EFSCORRUPTED/) {
ignore = 1;
} else if ($0 ~ /!= -EFSCORRUPTED/) {
ignore = 1;
} else {
lines[lineno++] = $0;
}
}
' | $filter

Signed-off-by: Darrick J. Wong <[e-mail]>
Reviewed-by: Christoph Hellwig <[e-mail]>
---
 libxfs/util.c   |    1 +
 libxfs/xfs_ag.c |    1 +
 2 files changed, 2 insertions(+)

Patch

diff --git a/libxfs/util.c b/libxfs/util.c
index 8cea0c1500b4..26339171ff82 100644
--- a/libxfs/util.c
+++ b/libxfs/util.c
@@ -728,3 +728,4 @@  xfs_fs_mark_healthy(
 }
 
 void xfs_ag_geom_health(struct xfs_perag *pag, struct xfs_ag_geometry *ageo) { }
+void xfs_fs_mark_sick(struct xfs_mount *mp, unsigned int mask) { }
diff --git a/libxfs/xfs_ag.c b/libxfs/xfs_ag.c
index 86024ddfd74a..e001ac11ca85 100644
--- a/libxfs/xfs_ag.c
+++ b/libxfs/xfs_ag.c
@@ -215,6 +215,7 @@  xfs_initialize_perag_data(
 	 */
 	if (fdblocks > sbp->sb_dblocks || ifree > ialloc) {
 		xfs_alert(mp, "AGF corruption. Please run xfs_repair.");
+		xfs_fs_mark_sick(mp, XFS_SICK_FS_COUNTERS);
 		error = -EFSCORRUPTED;
 		goto out;
 	}