From bffa47f1ca00952def6b5cc6feda3889033d1c29 Mon Sep 17 00:00:00 2001
From: David Stevens <stevensd@google.com>
Date: Fri, 4 Sep 2026 10:31:45 -0700
Subject: [PATCH] memcg: don't call schedule_work when no spinning is allowed

Memcg charging can be done from any context, but calling schedule_work()
isn't safe from an NMI.  If memory.high is breached from a context where
spinning isn't allowed, use irq_work to schedule the reclaim work.

Found this via code inspection.  I spent a little bit trying to trigger it
for real, but the only way I managed was by writing a hacky driver absuing
alloc_pages_nolock().

Link: https://lore.kernel.org/20260904173145.2028377-1-stevensd@google.com
Fixes: 3ac4638a734a ("memcg: make memcg_rstat_updated nmi safe")
Signed-off-by: David Stevens <stevensd@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Acked-by: Michal Hocko <mhocko@suse.com>
Reviewed-by: Johannes Weiner <hannes@cmpxchg.org>
Acked-by: Shakeel Butt <shakeel.butt@linux.dev>
Cc: Lorenzo Stoakes <ljs@kernel.org>
Cc: Muchun Song <muchun.song@linux.dev>
Cc: Roman Gushchin <roman.gushchin@linux.dev>
---
 include/linux/memcontrol.h |  2 ++
 mm/memcontrol.c            | 13 ++++++++++++-
 2 files changed, 14 insertions(+), 1 deletion(-)

diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h
index c0c9805b6f03..4f720791a31c 100644
--- a/include/linux/memcontrol.h
+++ b/include/linux/memcontrol.h
@@ -23,6 +23,7 @@
 #include <linux/writeback.h>
 #include <linux/page-flags.h>
 #include <linux/shrinker.h>
+#include <linux/irq_work_types.h>
 
 struct mem_cgroup;
 struct obj_cgroup;
@@ -233,6 +234,7 @@ struct mem_cgroup {
 #endif
 
 	/* Range enforcement for interrupt charges */
+	struct irq_work high_irq_work;
 	struct work_struct high_work;
 
 	__cacheline_group_end_aligned(memcg_write_hot);
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index e539881f58f1..3e14e0ce9e7e 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -62,6 +62,7 @@
 #include <linux/seq_buf.h>
 #include <linux/sched/isolation.h>
 #include <linux/kmemleak.h>
+#include <linux/irq_work.h>
 #include "internal.h"
 #include "swap.h"
 #include "swap_table.h"
@@ -2424,6 +2425,11 @@ static void high_work_func(struct work_struct *work)
 	reclaim_high(memcg, MEMCG_CHARGE_BATCH, GFP_KERNEL);
 }
 
+static void high_irq_work_func(struct irq_work *work)
+{
+	schedule_work(&container_of(work, struct mem_cgroup, high_irq_work)->high_work);
+}
+
 /*
  * Clamp the maximum sleep time per allocation batch to 2 seconds. This is
  * enough to still cause a significant slowdown in most cases, while still
@@ -2832,7 +2838,10 @@ static int try_charge_memcg(struct mem_cgroup *memcg, gfp_t gfp_mask,
 		/* Don't bother a random interrupted task */
 		if (!in_task()) {
 			if (mem_high) {
-				schedule_work(&memcg->high_work);
+				if (allow_spinning)
+					schedule_work(&memcg->high_work);
+				else
+					irq_work_queue(&memcg->high_irq_work);
 				break;
 			}
 			continue;
@@ -4207,6 +4216,7 @@ static struct mem_cgroup *mem_cgroup_alloc(struct mem_cgroup *parent)
 		goto fail;
 
 	INIT_WORK(&memcg->high_work, high_work_func);
+	init_irq_work(&memcg->high_irq_work, high_irq_work_func);
 	vmpressure_init(&memcg->vmpressure);
 	INIT_LIST_HEAD(&memcg->memory_peaks);
 	INIT_LIST_HEAD(&memcg->swap_peaks);
@@ -4415,6 +4425,7 @@ static void mem_cgroup_css_free(struct cgroup_subsys_state *css)
 		static_branch_dec(&memcg_bpf_enabled_key);
 
 	vmpressure_cleanup(&memcg->vmpressure);
+	irq_work_sync(&memcg->high_irq_work);
 	cancel_work_sync(&memcg->high_work);
 	free_shrinker_info(memcg);
 	mem_cgroup_free(memcg);