On Tue, Dec 16, 2025 at 06:02:51AM -0800, Thomas Ballasi wrote:

Memory reclaim events are currently difficult to attribute to
specific cgroups, making debugging memory pressure issues
challenging.  This patch adds memory cgroup ID (memcg_id) to key
vmscan tracepoints to enable better correlation and analysis.

For operations not associated with a specific cgroup, the field
is defaulted to 0.

Signed-off-by: Thomas Ballasi <redacted>
---

...

+		__entry->memcg_id = sc->memcg ? mem_cgroup_id(sc->memcg) : 0;

...

+		__entry->memcg_id = sc->memcg ? mem_cgroup_id(sc->memcg) : 0;

...

...

 	trace_mm_vmscan_memcg_softlimit_reclaim_begin(sc.order,
-						      sc.gfp_mask);
+						      sc.gfp_mask,
+						      mem_cgroup_id(memcg));
 

...

+	trace_mm_vmscan_memcg_softlimit_reclaim_end(sc.nr_reclaimed, mem_cgroup_id(memcg));

...

+	trace_mm_vmscan_memcg_reclaim_begin(0, sc.gfp_mask, mem_cgroup_id(memcg));

...

+	trace_mm_vmscan_memcg_reclaim_end(nr_reclaimed, mem_cgroup_id(memcg));

Please don't use mem_cgroup_id() here as it is an ID internal to memcg.
Use cgroup_id(memcg->css.cgroup) instead which is inode number and is
exposed to the userspace.