[PATCH 6/8][SRU][OEM-5.17] mm/memcg: protect memcg_stock with a local_lock_t
AceLan Kao
acelan.kao at canonical.com
Wed Sep 21 03:19:22 UTC 2022
From: Sebastian Andrzej Siewior <bigeasy at linutronix.de>
BugLink: https://launchpad.net/bugs/1990330
The members of the per-CPU structure memcg_stock_pcp are protected by
disabling interrupts. This is not working on PREEMPT_RT because it
creates atomic context in which actions are performed which require
preemptible context. One example is obj_cgroup_release().
The IRQ-disable sections can be replaced with local_lock_t which
preserves the explicit disabling of interrupts while keeps the code
preemptible on PREEMPT_RT.
drain_obj_stock() drops a reference on obj_cgroup which leads to an
invocat= ion of obj_cgroup_release() if it is the last object. This in
turn leads to recursive locking of the local_lock_t. To avoid this,
obj_cgroup_release() = is invoked outside of the locked section.
obj_cgroup_uncharge_pages() can be invoked with the local_lock_t
acquired a= nd without it. This will lead later to a recursion in
refill_stock(). To avoid the locking recursion provide
obj_cgroup_uncharge_pages_locked() which uses the locked version of
refill_stock().
- Replace disabling interrupts for memcg_stock with a local_lock_t.
- Let drain_obj_stock() return the old struct obj_cgroup which is
passed to obj_cgroup_put() outside of the locked section.
- Provide obj_cgroup_uncharge_pages_locked() which uses the locked
version of refill_stock() to avoid recursive locking in
drain_obj_stock().
Link: https://lkml.kernel.org/r/20220209014709.GA26885@xsang-OptiPlex-9020
Link: https://lkml.kernel.org/r/20220226204144.1008339-6-bigeasy@linutronix.de
Signed-off-by: Sebastian Andrzej Siewior <bigeasy at linutronix.de>
Reported-by: kernel test robot <oliver.sang at intel.com>
Acked-by: Michal Hocko <mhocko at suse.com>
Cc: Johannes Weiner <hannes at cmpxchg.org>
Cc: Michal Koutný <mkoutny at suse.com>
Cc: Peter Zijlstra <peterz at infradead.org>
Cc: Roman Gushchin <roman.gushchin at linux.dev>
Cc: Shakeel Butt <shakeelb at google.com>
Cc: Thomas Gleixner <tglx at linutronix.de>
Cc: Vladimir Davydov <vdavydov.dev at gmail.com>
Cc: Waiman Long <longman at redhat.com>
Signed-off-by: Andrew Morton <akpm at linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds at linux-foundation.org>
(cherry picked from commit 5675114623872300aa9fcd72aef2b8b7f421fe12)
Signed-off-by: Chia-Lin Kao (AceLan) <acelan.kao at canonical.com>
---
mm/memcontrol.c | 59 +++++++++++++++++++++++++++++++------------------
1 file changed, 38 insertions(+), 21 deletions(-)
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 0c10ee59056b..a0da8c7d5808 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -2153,6 +2153,7 @@ void unlock_page_memcg(struct page *page)
}
struct memcg_stock_pcp {
+ local_lock_t stock_lock;
struct mem_cgroup *cached; /* this never be root cgroup */
unsigned int nr_pages;
@@ -2168,18 +2169,21 @@ struct memcg_stock_pcp {
unsigned long flags;
#define FLUSHING_CACHED_CHARGE 0
};
-static DEFINE_PER_CPU(struct memcg_stock_pcp, memcg_stock);
+static DEFINE_PER_CPU(struct memcg_stock_pcp, memcg_stock) = {
+ .stock_lock = INIT_LOCAL_LOCK(stock_lock),
+};
static DEFINE_MUTEX(percpu_charge_mutex);
#ifdef CONFIG_MEMCG_KMEM
-static void drain_obj_stock(struct memcg_stock_pcp *stock);
+static struct obj_cgroup *drain_obj_stock(struct memcg_stock_pcp *stock);
static bool obj_stock_flush_required(struct memcg_stock_pcp *stock,
struct mem_cgroup *root_memcg);
static void memcg_account_kmem(struct mem_cgroup *memcg, int nr_pages);
#else
-static inline void drain_obj_stock(struct memcg_stock_pcp *stock)
+static inline struct obj_cgroup *drain_obj_stock(struct memcg_stock_pcp *stock)
{
+ return NULL;
}
static bool obj_stock_flush_required(struct memcg_stock_pcp *stock,
struct mem_cgroup *root_memcg)
@@ -2211,7 +2215,7 @@ static bool consume_stock(struct mem_cgroup *memcg, unsigned int nr_pages)
if (nr_pages > MEMCG_CHARGE_BATCH)
return ret;
- local_irq_save(flags);
+ local_lock_irqsave(&memcg_stock.stock_lock, flags);
stock = this_cpu_ptr(&memcg_stock);
if (memcg == stock->cached && stock->nr_pages >= nr_pages) {
@@ -2219,7 +2223,7 @@ static bool consume_stock(struct mem_cgroup *memcg, unsigned int nr_pages)
ret = true;
}
- local_irq_restore(flags);
+ local_unlock_irqrestore(&memcg_stock.stock_lock, flags);
return ret;
}
@@ -2248,6 +2252,7 @@ static void drain_stock(struct memcg_stock_pcp *stock)
static void drain_local_stock(struct work_struct *dummy)
{
struct memcg_stock_pcp *stock;
+ struct obj_cgroup *old = NULL;
unsigned long flags;
/*
@@ -2255,14 +2260,16 @@ static void drain_local_stock(struct work_struct *dummy)
* drain_stock races is that we always operate on local CPU stock
* here with IRQ disabled
*/
- local_irq_save(flags);
+ local_lock_irqsave(&memcg_stock.stock_lock, flags);
stock = this_cpu_ptr(&memcg_stock);
- drain_obj_stock(stock);
+ old = drain_obj_stock(stock);
drain_stock(stock);
clear_bit(FLUSHING_CACHED_CHARGE, &stock->flags);
- local_irq_restore(flags);
+ local_unlock_irqrestore(&memcg_stock.stock_lock, flags);
+ if (old)
+ obj_cgroup_put(old);
}
/*
@@ -2289,9 +2296,9 @@ static void refill_stock(struct mem_cgroup *memcg, unsigned int nr_pages)
{
unsigned long flags;
- local_irq_save(flags);
+ local_lock_irqsave(&memcg_stock.stock_lock, flags);
__refill_stock(memcg, nr_pages);
- local_irq_restore(flags);
+ local_unlock_irqrestore(&memcg_stock.stock_lock, flags);
}
/*
@@ -3118,10 +3125,11 @@ void mod_objcg_state(struct obj_cgroup *objcg, struct pglist_data *pgdat,
enum node_stat_item idx, int nr)
{
struct memcg_stock_pcp *stock;
+ struct obj_cgroup *old = NULL;
unsigned long flags;
int *bytes;
- local_irq_save(flags);
+ local_lock_irqsave(&memcg_stock.stock_lock, flags);
stock = this_cpu_ptr(&memcg_stock);
/*
@@ -3130,7 +3138,7 @@ void mod_objcg_state(struct obj_cgroup *objcg, struct pglist_data *pgdat,
* changes.
*/
if (stock->cached_objcg != objcg) {
- drain_obj_stock(stock);
+ old = drain_obj_stock(stock);
obj_cgroup_get(objcg);
stock->nr_bytes = atomic_read(&objcg->nr_charged_bytes)
? atomic_xchg(&objcg->nr_charged_bytes, 0) : 0;
@@ -3174,7 +3182,9 @@ void mod_objcg_state(struct obj_cgroup *objcg, struct pglist_data *pgdat,
if (nr)
mod_objcg_mlstate(objcg, pgdat, idx, nr);
- local_irq_restore(flags);
+ local_unlock_irqrestore(&memcg_stock.stock_lock, flags);
+ if (old)
+ obj_cgroup_put(old);
}
static bool consume_obj_stock(struct obj_cgroup *objcg, unsigned int nr_bytes)
@@ -3183,7 +3193,7 @@ static bool consume_obj_stock(struct obj_cgroup *objcg, unsigned int nr_bytes)
unsigned long flags;
bool ret = false;
- local_irq_save(flags);
+ local_lock_irqsave(&memcg_stock.stock_lock, flags);
stock = this_cpu_ptr(&memcg_stock);
if (objcg == stock->cached_objcg && stock->nr_bytes >= nr_bytes) {
@@ -3191,17 +3201,17 @@ static bool consume_obj_stock(struct obj_cgroup *objcg, unsigned int nr_bytes)
ret = true;
}
- local_irq_restore(flags);
+ local_unlock_irqrestore(&memcg_stock.stock_lock, flags);
return ret;
}
-static void drain_obj_stock(struct memcg_stock_pcp *stock)
+static struct obj_cgroup *drain_obj_stock(struct memcg_stock_pcp *stock)
{
struct obj_cgroup *old = stock->cached_objcg;
if (!old)
- return;
+ return NULL;
if (stock->nr_bytes) {
unsigned int nr_pages = stock->nr_bytes >> PAGE_SHIFT;
@@ -3251,8 +3261,12 @@ static void drain_obj_stock(struct memcg_stock_pcp *stock)
stock->cached_pgdat = NULL;
}
- obj_cgroup_put(old);
stock->cached_objcg = NULL;
+ /*
+ * The `old' objects needs to be released by the caller via
+ * obj_cgroup_put() outside of memcg_stock_pcp::stock_lock.
+ */
+ return old;
}
static bool obj_stock_flush_required(struct memcg_stock_pcp *stock,
@@ -3273,14 +3287,15 @@ static void refill_obj_stock(struct obj_cgroup *objcg, unsigned int nr_bytes,
bool allow_uncharge)
{
struct memcg_stock_pcp *stock;
+ struct obj_cgroup *old = NULL;
unsigned long flags;
unsigned int nr_pages = 0;
- local_irq_save(flags);
+ local_lock_irqsave(&memcg_stock.stock_lock, flags);
stock = this_cpu_ptr(&memcg_stock);
if (stock->cached_objcg != objcg) { /* reset if necessary */
- drain_obj_stock(stock);
+ old = drain_obj_stock(stock);
obj_cgroup_get(objcg);
stock->cached_objcg = objcg;
stock->nr_bytes = atomic_read(&objcg->nr_charged_bytes)
@@ -3294,7 +3309,9 @@ static void refill_obj_stock(struct obj_cgroup *objcg, unsigned int nr_bytes,
stock->nr_bytes &= (PAGE_SIZE - 1);
}
- local_irq_restore(flags);
+ local_unlock_irqrestore(&memcg_stock.stock_lock, flags);
+ if (old)
+ obj_cgroup_put(old);
if (nr_pages)
obj_cgroup_uncharge_pages(objcg, nr_pages);
--
2.25.1
More information about the kernel-team
mailing list