summaryrefslogtreecommitdiff
diff options
context:
space:
mode:
authorSeongJae Park <sj@kernel.org>2025-05-12 17:27:10 -0700
committerAndrew Morton <akpm@linux-foundation.org>2025-05-22 14:55:38 -0700
commit591c4c78be06360fe31b31401564bdb2d2b79995 (patch)
tree3ca87cfb4fe203a40092285bdf0e0fed72b5f25c
parent2aad4edf6e1018b28b7000faec56b7b6e585c8e1 (diff)
downloadlinux-591c4c78be06360fe31b31401564bdb2d2b79995.tar.gz
linux-591c4c78be06360fe31b31401564bdb2d2b79995.zip
mm/damon/core: warn and fix nr_accesses[_bp] corruption
Patch series "mm/damon: minor fixups and improvements for code, tests, and documents". Yet another batch of miscellaneous DAMON changes. Fix and improve minor problems in code, tests and documents. This patch (of 6): For a bug such as double aggregation reset[1], ->nr_accesses and/or ->nr_accesses_bp of damon_region could be corrupted. Such corruption can make monitoring results pretty inaccurate, so the root causing bug should be investigated. Meanwhile, the corruption itself can easily be fixed but silently fixing it will hide the bug. Fix the corruption as soon as found, but WARN_ONCE() so that we can be aware of the existence of the bug while keeping the system running in a more sane way. Link: https://lkml.kernel.org/r/20250513002715.40126-1-sj@kernel.org Link: https://lkml.kernel.org/r/20250513002715.40126-2-sj@kernel.org Link: https://lore.kernel.org/20250302214145.356806-1-sj@kernel.org [1] Signed-off-by: SeongJae Park <sj@kernel.org> Cc: Brendan Higgins <brendan.higgins@linux.dev> Cc: David Gow <davidgow@google.com> Cc: Jonathan Corbet <corbet@lwn.net> Cc: Shuah Khan <shuah@kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
-rw-r--r--mm/damon/core.c14
1 files changed, 14 insertions, 0 deletions
diff --git a/mm/damon/core.c b/mm/damon/core.c
index 587fb9a4fef8..0bb71e2ab713 100644
--- a/mm/damon/core.c
+++ b/mm/damon/core.c
@@ -1392,6 +1392,19 @@ int damos_walk(struct damon_ctx *ctx, struct damos_walk_control *control)
}
/*
+ * Warn and fix corrupted ->nr_accesses[_bp] for investigations and preventing
+ * the problem being propagated.
+ */
+static void damon_warn_fix_nr_accesses_corruption(struct damon_region *r)
+{
+ if (r->nr_accesses_bp == r->nr_accesses * 10000)
+ return;
+ WARN_ONCE(true, "invalid nr_accesses_bp at reset: %u %u\n",
+ r->nr_accesses_bp, r->nr_accesses);
+ r->nr_accesses_bp = r->nr_accesses * 10000;
+}
+
+/*
* Reset the aggregated monitoring results ('nr_accesses' of each region).
*/
static void kdamond_reset_aggregated(struct damon_ctx *c)
@@ -1404,6 +1417,7 @@ static void kdamond_reset_aggregated(struct damon_ctx *c)
damon_for_each_region(r, t) {
trace_damon_aggregated(ti, r, damon_nr_regions(t));
+ damon_warn_fix_nr_accesses_corruption(r);
r->last_nr_accesses = r->nr_accesses;
r->nr_accesses = 0;
}