@@ -553,6 +553,16 @@ static inline bool folio_memcg_kmem(struct folio *folio)
return folio->memcg_data & MEMCG_DATA_KMEM;
}
+static inline bool current_objcg_needs_update(struct obj_cgroup *objcg)
+{
+ return (struct obj_cgroup *)((unsigned long)objcg & 0x1);
+}
+
+static inline struct obj_cgroup *
+current_objcg_without_update_flag(struct obj_cgroup *objcg)
+{
+ return (struct obj_cgroup *)((unsigned long)objcg & ~0x1);
+}
#else
static inline bool folio_memcg_kmem(struct folio *folio)
@@ -1443,6 +1443,10 @@ struct task_struct {
struct mem_cgroup *active_memcg;
#endif
+#ifdef CONFIG_MEMCG_KMEM
+ struct obj_cgroup *objcg;
+#endif
+
#ifdef CONFIG_BLK_CGROUP
struct gendisk *throttle_disk;
#endif
@@ -3001,6 +3001,47 @@ static struct obj_cgroup *__get_obj_cgroup_from_memcg(struct mem_cgroup *memcg)
return objcg;
}
+static struct obj_cgroup *current_objcg_update(struct obj_cgroup *old)
+{
+ struct mem_cgroup *memcg;
+ struct obj_cgroup *objcg = NULL, *tmp = old;
+
+ old = current_objcg_without_update_flag(old);
+ if (old)
+ obj_cgroup_put(old);
+
+ rcu_read_lock();
+ do {
+ /* Atomically drop the update bit, */
+ WARN_ON_ONCE(cmpxchg(¤t->objcg, tmp, 0) != tmp);
+
+ /* ...obtain the new objcg pointer */
+ memcg = mem_cgroup_from_task(current);
+ for (; memcg != root_mem_cgroup; memcg = parent_mem_cgroup(memcg)) {
+ objcg = rcu_dereference(memcg->objcg);
+ if (objcg && obj_cgroup_tryget(objcg))
+ break;
+ objcg = NULL;
+ }
+
+ /*
+ * ...and try atomically set up a new objcg pointer. If it
+ * fails, it means the update flag was set concurrently, so
+ * the whole procedure should be repeated.
+ */
+ tmp = 0;
+ } while (!try_cmpxchg(¤t->objcg, &tmp, objcg));
+ rcu_read_unlock();
+
+ return objcg;
+}
+
+static inline void current_objcg_set_needs_update(struct task_struct *task)
+{
+ /* atomically set the update bit */
+ set_bit(0, (unsigned long *)¤t->objcg);
+}
+
__always_inline struct obj_cgroup *get_obj_cgroup_from_current(void)
{
struct mem_cgroup *memcg;
@@ -3008,19 +3049,26 @@ __always_inline struct obj_cgroup *get_obj_cgroup_from_current(void)
if (in_task()) {
memcg = current->active_memcg;
+ if (unlikely(memcg))
+ goto from_memcg;
- /* Memcg to charge can't be determined. */
- if (likely(!memcg) && (!current->mm || (current->flags & PF_KTHREAD)))
- return NULL;
+ objcg = READ_ONCE(current->objcg);
+ if (unlikely(current_objcg_needs_update(objcg)))
+ objcg = current_objcg_update(objcg);
+
+ if (objcg) {
+ obj_cgroup_get(objcg);
+ return objcg;
+ }
} else {
memcg = this_cpu_read(int_active_memcg);
- if (likely(!memcg))
- return NULL;
+ if (unlikely(memcg))
+ goto from_memcg;
}
+ return NULL;
+from_memcg:
rcu_read_lock();
- if (!memcg)
- memcg = mem_cgroup_from_task(current);
objcg = __get_obj_cgroup_from_memcg(memcg);
rcu_read_unlock();
return objcg;
@@ -6345,6 +6393,7 @@ static void mem_cgroup_move_task(void)
mem_cgroup_clear_mc();
}
}
+
#else /* !CONFIG_MMU */
static int mem_cgroup_can_attach(struct cgroup_taskset *tset)
{
@@ -6358,8 +6407,27 @@ static void mem_cgroup_move_task(void)
}
#endif
+#ifdef CONFIG_MEMCG_KMEM
+static void mem_cgroup_fork(struct task_struct *task)
+{
+ /*
+ * Set the update flag to cause task->objcg to be initialized lazily
+ * on the first allocation.
+ */
+ task->objcg = (struct obj_cgroup *)0x1;
+}
+
+static void mem_cgroup_exit(struct task_struct *task)
+{
+ struct obj_cgroup *objcg = current_objcg_without_update_flag(task->objcg);
+
+ if (objcg)
+ obj_cgroup_put(objcg);
+}
+#endif
+
#ifdef CONFIG_LRU_GEN
-static void mem_cgroup_attach(struct cgroup_taskset *tset)
+static void mem_cgroup_lru_gen_attach(struct cgroup_taskset *tset)
{
struct task_struct *task;
struct cgroup_subsys_state *css;
@@ -6377,10 +6445,29 @@ static void mem_cgroup_attach(struct cgroup_taskset *tset)
task_unlock(task);
}
#else
+static void mem_cgroup_lru_gen_attach(struct cgroup_taskset *tset) {}
+#endif /* CONFIG_LRU_GEN */
+
+#ifdef CONFIG_MEMCG_KMEM
+static void mem_cgroup_kmem_attach(struct cgroup_taskset *tset)
+{
+ struct task_struct *task;
+ struct cgroup_subsys_state *css;
+
+ cgroup_taskset_for_each(task, css, tset)
+ current_objcg_set_needs_update(task);
+}
+#else
+static void mem_cgroup_kmem_attach(struct cgroup_taskset *tset) {}
+#endif /* CONFIG_MEMCG_KMEM */
+
+#if defined(CONFIG_LRU_GEN) || defined(CONFIG_MEMCG_KMEM)
static void mem_cgroup_attach(struct cgroup_taskset *tset)
{
+ mem_cgroup_lru_gen_attach(tset);
+ mem_cgroup_kmem_attach(tset);
}
-#endif /* CONFIG_LRU_GEN */
+#endif
static int seq_puts_memcg_tunable(struct seq_file *m, unsigned long value)
{
@@ -6824,9 +6911,15 @@ struct cgroup_subsys memory_cgrp_subsys = {
.css_reset = mem_cgroup_css_reset,
.css_rstat_flush = mem_cgroup_css_rstat_flush,
.can_attach = mem_cgroup_can_attach,
+#if defined(CONFIG_LRU_GEN) || defined(CONFIG_MEMCG_KMEM)
.attach = mem_cgroup_attach,
+#endif
.cancel_attach = mem_cgroup_cancel_attach,
.post_attach = mem_cgroup_move_task,
+#ifdef CONFIG_MEMCG_KMEM
+ .fork = mem_cgroup_fork,
+ .exit = mem_cgroup_exit,
+#endif
.dfl_cftypes = memory_files,
.legacy_cftypes = mem_cgroup_legacy_files,
.early_init = 0,
To charge a freshly allocated kernel object to a memory cgroup, the kernel needs to obtain an objcg pointer. Currently it does it indirectly by obtaining the memcg pointer first and then calling to __get_obj_cgroup_from_memcg(). Usually tasks spend their entire life belonging to the same object cgroup. So it makes sense to save the objcg pointer on task_struct directly, so it can be obtained faster. It requires some work on fork, exit and cgroup migrate paths, but these paths are way colder. To avoid any costly synchronization the following rules are applied: 1) A task sets it's objcg pointer itself. 2) If a task is being migrated to another cgroup, the least significant bit of the objcg pointer is set atomically. 3) On the allocation path the objcg pointer is obtained locklessly using the READ_ONCE() macro and the least significant bit is checked. If it's set, the following procedure is used to update it locklessly: - task->objcg is zeroed using cmpxcg - new objcg pointer is obtained - task->objcg is updated using try_cmpxchg - operation is repeated if try_cmpxcg fails It guarantees that no updates will be lost if task migration is racing against objcg pointer update. It also allows to keep both read and write paths fully lockless. Because the task is keeping a reference to the objcg, it can't go away while the task is alive. This commit doesn't change the way the remote memcg charging works. Signed-off-by: Roman Gushchin (Cruise) <roman.gushchin@linux.dev> --- include/linux/memcontrol.h | 10 ++++ include/linux/sched.h | 4 ++ mm/memcontrol.c | 111 ++++++++++++++++++++++++++++++++++--- 3 files changed, 116 insertions(+), 9 deletions(-)