Skip to contentSkip to conversation

memcg-dont-call-schedule_work-when-no-spinning-is-allowed.patch removed from -mm tree

merged mm-stable Andrew Morton 1 participant 1 message Oct 9

lore
Share & tools
lore

Andrew Morton

author tree notice Applied
#0 lore raw

The quilt patch titled
Subject: memcg: don't call schedule_work when no spinning is allowed
has been removed from the -mm tree. Its filename was
memcg-dont-call-schedule_work-when-no-spinning-is-allowed.patch

This patch was dropped because it was merged into the mm-stable branch of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm

------------------------------------------------------
From: David Stevens <[email protected]>
Subject: memcg: don't call schedule_work when no spinning is allowed
Date: Fri, 4 Sep 2026 10:31:45 -0700

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/[email protected] open here
Fixes 3ac4638a734a ("memcg: make memcg_rstat_updated nmi safe")
Signed-off-by David Stevens <[email protected]>
Signed-off-by Andrew Morton <[email protected]>
Acked-by Michal Hocko <[email protected]>
Reviewed-by Johannes Weiner <[email protected]>
Acked-by Shakeel Butt <[email protected]>
Cc Lorenzo Stoakes <[email protected]>
Cc Muchun Song <[email protected]>
Cc Roman Gushchin <[email protected]>

---

 include/linux/memcontrol.h |    2 ++
 mm/memcontrol.c            |   13 ++++++++++++-
 2 files changed, 14 insertions(+), 1 deletion(-)
include/linux/memcontrol.h renamed from include/linux/memcontrol.h~memcg-dont-call-schedule_work-when-no-spinning-is-allowed +2 -0
@@ -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);
mm/memcontrol.c renamed from mm/memcontrol.c~memcg-dont-call-schedule_work-when-no-spinning-is-allowed +12 -1
@@ -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_s
 	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 @@ done_restock:
 		/* 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_all
 		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 c
 		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);

_

Patches currently in -mm which might be from [email protected] are