diff --git a/Documentation/cgroup-v1/memory.txt b/Documentation/cgroup-v1/memory.txt index 946e69103cdd..cefb63639070 100644 --- a/Documentation/cgroup-v1/memory.txt +++ b/Documentation/cgroup-v1/memory.txt @@ -789,23 +789,46 @@ way to trigger. Applications should do whatever they can to help the system. It might be too late to consult with vmstat or any other statistics, so it's advisable to take an immediate action. -The events are propagated upward until the event is handled, i.e. the -events are not pass-through. Here is what this means: for example you have -three cgroups: A->B->C. Now you set up an event listener on cgroups A, B -and C, and suppose group C experiences some pressure. In this situation, -only group C will receive the notification, i.e. groups A and B will not -receive it. This is done to avoid excessive "broadcasting" of messages, -which disturbs the system and which is especially bad if we are low on -memory or thrashing. So, organize the cgroups wisely, or propagate the -events manually (or, ask us to implement the pass-through events, -explaining why would you need them.) +By default, events are propagated upward until the event is handled, i.e. the +events are not pass-through. For example, you have three cgroups: A->B->C. Now +you set up an event listener on cgroups A, B and C, and suppose group C +experiences some pressure. In this situation, only group C will receive the +notification, i.e. groups A and B will not receive it. This is done to avoid +excessive "broadcasting" of messages, which disturbs the system and which is +especially bad if we are low on memory or thrashing. Group B, will receive +notification only if there are no event listers for group C. + +There are three optional modes that specify different propagation behavior: + + - "default": this is the default behavior specified above. This mode is the + same as omitting the optional mode parameter, preserved by backwards + compatibility. + + - "hierarchy": events always propagate up to the root, similar to the default + behavior, except that propagation continues regardless of whether there are + event listeners at each level, with the "hierarchy" mode. In the above + example, groups A, B, and C will receive notification of memory pressure. + + - "local": events are pass-through, i.e. they only receive notifications when + memory pressure is experienced in the memcg for which the notification is + registered. In the above example, group C will receive notification if + registered for "local" notification and the group experiences memory + pressure. However, group B will never receive notification, regardless if + there is an event listener for group C or not, if group B is registered for + local notification. + +The level and event notification mode ("hierarchy" or "local", if necessary) are +specified by a comma-delimited string, i.e. "low,hierarchy" specifies +hierarchical, pass-through, notification for all ancestor memcgs. Notification +that is the default, non pass-through behavior, does not specify a mode. +"medium,local" specifies pass-through notification for the medium level. The file memory.pressure_level is only used to setup an eventfd. To register a notification, an application must: - create an eventfd using eventfd(2); - open memory.pressure_level; -- write string like " " +- write string as " " to cgroup.event_control. Application will be notified through eventfd when memory pressure is at @@ -821,7 +844,7 @@ Test: # cd /sys/fs/cgroup/memory/ # mkdir foo # cd foo - # cgroup_event_listener memory.pressure_level low & + # cgroup_event_listener memory.pressure_level low,hierarchy & # echo 8000000 > memory.limit_in_bytes # echo 8000000 > memory.memsw.limit_in_bytes # echo $$ > tasks diff --git a/mm/vmpressure.c b/mm/vmpressure.c index ce0618bfa8d0..85350ce2d25d 100644 --- a/mm/vmpressure.c +++ b/mm/vmpressure.c @@ -93,12 +93,25 @@ enum vmpressure_levels { VMPRESSURE_NUM_LEVELS, }; +enum vmpressure_modes { + VMPRESSURE_NO_PASSTHROUGH = 0, + VMPRESSURE_HIERARCHY, + VMPRESSURE_LOCAL, + VMPRESSURE_NUM_MODES, +}; + static const char * const vmpressure_str_levels[] = { [VMPRESSURE_LOW] = "low", [VMPRESSURE_MEDIUM] = "medium", [VMPRESSURE_CRITICAL] = "critical", }; +static const char * const vmpressure_str_modes[] = { + [VMPRESSURE_NO_PASSTHROUGH] = "default", + [VMPRESSURE_HIERARCHY] = "hierarchy", + [VMPRESSURE_LOCAL] = "local", +}; + static enum vmpressure_levels vmpressure_level(unsigned long pressure) { if (pressure >= vmpressure_level_critical) @@ -141,27 +154,31 @@ static enum vmpressure_levels vmpressure_calc_level(unsigned long scanned, struct vmpressure_event { struct eventfd_ctx *efd; enum vmpressure_levels level; + enum vmpressure_modes mode; struct list_head node; }; static bool vmpressure_event(struct vmpressure *vmpr, - enum vmpressure_levels level) + const enum vmpressure_levels level, + bool ancestor, bool signalled) { struct vmpressure_event *ev; - bool signalled = false; + bool ret = false; mutex_lock(&vmpr->events_lock); - list_for_each_entry(ev, &vmpr->events, node) { - if (level >= ev->level) { - eventfd_signal(ev->efd, 1); - signalled = true; - } + if (ancestor && ev->mode == VMPRESSURE_LOCAL) + continue; + if (signalled && ev->mode == VMPRESSURE_NO_PASSTHROUGH) + continue; + if (level < ev->level) + continue; + eventfd_signal(ev->efd, 1); + ret = true; } - mutex_unlock(&vmpr->events_lock); - return signalled; + return ret; } static void vmpressure_work_fn(struct work_struct *work) @@ -170,6 +187,8 @@ static void vmpressure_work_fn(struct work_struct *work) unsigned long scanned; unsigned long reclaimed; enum vmpressure_levels level; + bool ancestor = false; + bool signalled = false; spin_lock(&vmpr->sr_lock); /* @@ -194,12 +213,9 @@ static void vmpressure_work_fn(struct work_struct *work) level = vmpressure_calc_level(scanned, reclaimed); do { - if (vmpressure_event(vmpr, level)) - break; - /* - * If not handled, propagate the event upward into the - * hierarchy. - */ + if (vmpressure_event(vmpr, level, ancestor, signalled)) + signalled = true; + ancestor = true; } while ((vmpr = vmpressure_parent(vmpr))); } @@ -326,17 +342,40 @@ void vmpressure_prio(gfp_t gfp, struct mem_cgroup *memcg, int prio) vmpressure(gfp, memcg, true, vmpressure_win, 0); } +static enum vmpressure_levels str_to_level(const char *arg) +{ + enum vmpressure_levels level; + + for (level = 0; level < VMPRESSURE_NUM_LEVELS; level++) + if (!strcmp(vmpressure_str_levels[level], arg)) + return level; + return -1; +} + +static enum vmpressure_modes str_to_mode(const char *arg) +{ + enum vmpressure_modes mode; + + for (mode = 0; mode < VMPRESSURE_NUM_MODES; mode++) + if (!strcmp(vmpressure_str_modes[mode], arg)) + return mode; + return -1; +} + +#define MAX_VMPRESSURE_ARGS_LEN (strlen("critical") + strlen("hierarchy") + 2) + /** * vmpressure_register_event() - Bind vmpressure notifications to an eventfd * @memcg: memcg that is interested in vmpressure notifications * @eventfd: eventfd context to link notifications with - * @args: event arguments (used to set up a pressure level threshold) + * @args: event arguments (pressure level threshold, optional mode) * * This function associates eventfd context with the vmpressure * infrastructure, so that the notifications will be delivered to the - * @eventfd. The @args parameter is a string that denotes pressure level - * threshold (one of vmpressure_str_levels, i.e. "low", "medium", or - * "critical"). + * @eventfd. The @args parameter is a comma-delimited string that denotes a + * pressure level threshold (one of vmpressure_str_levels, i.e. "low", "medium", + * or "critical") and an optional mode (one of vmpressure_str_modes, i.e. + * "hierarchy" or "local"). * * To be used as memcg event method. */ @@ -345,28 +384,53 @@ int vmpressure_register_event(struct mem_cgroup *memcg, { struct vmpressure *vmpr = memcg_to_vmpressure(memcg); struct vmpressure_event *ev; - int level; + enum vmpressure_modes mode = VMPRESSURE_NO_PASSTHROUGH; + enum vmpressure_levels level = -1; + char *spec, *spec_orig; + char *token; + int ret = 0; - for (level = 0; level < VMPRESSURE_NUM_LEVELS; level++) { - if (!strcmp(vmpressure_str_levels[level], args)) - break; + spec_orig = spec = kzalloc(MAX_VMPRESSURE_ARGS_LEN + 1, GFP_KERNEL); + if (!spec) { + ret = -ENOMEM; + goto out; + } + strncpy(spec, args, MAX_VMPRESSURE_ARGS_LEN); + + /* Find required level */ + token = strsep(&spec, ","); + level = str_to_level(token); + if (level == -1) { + ret = -EINVAL; + goto out; } - if (level >= VMPRESSURE_NUM_LEVELS) - return -EINVAL; + /* Find optional mode */ + token = strsep(&spec, ","); + if (token) { + mode = str_to_mode(token); + if (mode == -1) { + ret = -EINVAL; + goto out; + } + } ev = kzalloc(sizeof(*ev), GFP_KERNEL); - if (!ev) - return -ENOMEM; + if (!ev) { + ret = -ENOMEM; + goto out; + } ev->efd = eventfd; ev->level = level; + ev->mode = mode; mutex_lock(&vmpr->events_lock); list_add(&ev->node, &vmpr->events); mutex_unlock(&vmpr->events_lock); - - return 0; +out: + kfree(spec_orig); + return ret; } /**