mm: memcg: use READ_ONCE()/WRITE_ONCE() to access stock->nr_pages

A memcg pointer in the per-cpu stock can be accessed by
drain_all_stock() and consume_stock() in parallel, causing a potential
race, which is believed to e harmless.

KCSAN shows this data-race clearly in the splat below:

	BUG: KCSAN: data-race in drain_all_stock.part.0 / try_charge_memcg

	write to 0xffff88903f8b0788 of 4 bytes by task 35901 on cpu 2:
	try_charge_memcg (mm/memcontrol.c:2323 mm/memcontrol.c:2746)
	__mem_cgroup_charge (mm/memcontrol.c:7287 mm/memcontrol.c:7301)
	do_anonymous_page (mm/memory.c:1054 mm/memory.c:4375 mm/memory.c:4433)
	__handle_mm_fault (mm/memory.c:3878 mm/memory.c:5300 mm/memory.c:5441)
	handle_mm_fault (mm/memory.c:5606)
	do_user_addr_fault (arch/x86/mm/fault.c:1363)
	exc_page_fault (./arch/x86/include/asm/irqflags.h:37
		        ./arch/x86/include/asm/irqflags.h:72
			arch/x86/mm/fault.c:1513
			arch/x86/mm/fault.c:1563)
	asm_exc_page_fault (./arch/x86/include/asm/idtentry.h:623)

	read to 0xffff88903f8b0788 of 4 bytes by task 287 on cpu 27:
	drain_all_stock.part.0 (mm/memcontrol.c:2433)
	mem_cgroup_css_offline (mm/memcontrol.c:5398 mm/memcontrol.c:5687)
	css_killed_work_fn (kernel/cgroup/cgroup.c:5521 kernel/cgroup/cgroup.c:5794)
	process_one_work (kernel/workqueue.c:3254)
	worker_thread (kernel/workqueue.c:3329 kernel/workqueue.c:3416)
	kthread (kernel/kthread.c:388)
	ret_from_fork (arch/x86/kernel/process.c:147)
	ret_from_fork_asm (arch/x86/entry/entry_64.S:257)

	value changed: 0x00000014 -> 0x00000013

This happens because drain_all_stock() is reading stock->nr_pages, while
consume_stock() might be updating the same address, causing a potential
data-race.

Make the shared addresses bulletproof regarding to reads and writes,
similarly to what stock->cached_objcg and stock->cached.
Annotate all accesses to stock->nr_pages with READ_ONCE()/WRITE_ONCE().

Link: https://lkml.kernel.org/r/20240501095420.679208-1-leitao@debian.org
Signed-off-by: Breno Leitao <leitao@debian.org>
Acked-by: Shakeel Butt <shakeel.butt@linux.dev>
Reviewed-by: Roman Gushchin <roman.gushchin@linux.dev>
Acked-by: Michal Hocko <mhocko@suse.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Muchun Song <songmuchun@bytedance.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>

diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index e6302f42e40f13177817e00ca6d06cead4da2f50..2103ae77cf8d443d5781ae9b8067216e6ffb36bf 100644 (file)
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -2468,6 +2468,7 @@ static void memcg_account_kmem(struct mem_cgroup *memcg, int nr_pages)
 static bool consume_stock(struct mem_cgroup *memcg, unsigned int nr_pages)
 {
        struct memcg_stock_pcp *stock;
+       unsigned int stock_pages;
        unsigned long flags;
        bool ret = false;
 
@@ -2477,8 +2478,9 @@ static bool consume_stock(struct mem_cgroup *memcg, unsigned int nr_pages)
        local_lock_irqsave(&memcg_stock.stock_lock, flags);
 
        stock = this_cpu_ptr(&memcg_stock);
-       if (memcg == READ_ONCE(stock->cached) && stock->nr_pages >= nr_pages) {
-               stock->nr_pages -= nr_pages;
+       stock_pages = READ_ONCE(stock->nr_pages);
+       if (memcg == READ_ONCE(stock->cached) && stock_pages >= nr_pages) {
+               WRITE_ONCE(stock->nr_pages, stock_pages - nr_pages);
                ret = true;
        }
 
@@ -2492,16 +2494,18 @@ static bool consume_stock(struct mem_cgroup *memcg, unsigned int nr_pages)
  */
 static void drain_stock(struct memcg_stock_pcp *stock)
 {
+       unsigned int stock_pages = READ_ONCE(stock->nr_pages);
        struct mem_cgroup *old = READ_ONCE(stock->cached);
 
        if (!old)
                return;
 
-       if (stock->nr_pages) {
-               page_counter_uncharge(&old->memory, stock->nr_pages);
+       if (stock_pages) {
+               page_counter_uncharge(&old->memory, stock_pages);
                if (do_memsw_account())
-                       page_counter_uncharge(&old->memsw, stock->nr_pages);
-               stock->nr_pages = 0;
+                       page_counter_uncharge(&old->memsw, stock_pages);
+
+               WRITE_ONCE(stock->nr_pages, 0);
        }
 
        css_put(&old->css);
@@ -2537,6 +2541,7 @@ static void drain_local_stock(struct work_struct *dummy)
 static void __refill_stock(struct mem_cgroup *memcg, unsigned int nr_pages)
 {
        struct memcg_stock_pcp *stock;
+       unsigned int stock_pages;
 
        stock = this_cpu_ptr(&memcg_stock);
        if (READ_ONCE(stock->cached) != memcg) { /* reset if necessary */
@@ -2544,9 +2549,10 @@ static void __refill_stock(struct mem_cgroup *memcg, unsigned int nr_pages)
                css_get(&memcg->css);
                WRITE_ONCE(stock->cached, memcg);
        }
-       stock->nr_pages += nr_pages;
+       stock_pages = READ_ONCE(stock->nr_pages) + nr_pages;
+       WRITE_ONCE(stock->nr_pages, stock_pages);
 
-       if (stock->nr_pages > MEMCG_CHARGE_BATCH)
+       if (stock_pages > MEMCG_CHARGE_BATCH)
                drain_stock(stock);
 }
 
@@ -2585,7 +2591,7 @@ static void drain_all_stock(struct mem_cgroup *root_memcg)
 
                rcu_read_lock();
                memcg = READ_ONCE(stock->cached);
-               if (memcg && stock->nr_pages &&
+               if (memcg && READ_ONCE(stock->nr_pages) &&
                    mem_cgroup_is_descendant(memcg, root_memcg))
                        flush = true;
                else if (obj_stock_flush_required(stock, root_memcg))