diff --git a/drivers/staging/android/lowmemorykiller.c b/drivers/staging/android/lowmemorykiller.c index 303a6b8d80bc4b4626ac926e0da9270cdf415c4d..9acb8bf5dd242a3d83989eedfc1629380946b664 100644 --- a/drivers/staging/android/lowmemorykiller.c +++ b/drivers/staging/android/lowmemorykiller.c @@ -37,24 +37,12 @@ #include <linux/mm.h> #include <linux/oom.h> #include <linux/sched.h> +#include <linux/swap.h> #include <linux/rcupdate.h> #include <linux/notifier.h> -#include <linux/mutex.h> -#include <linux/delay.h> -#include <linux/swap.h> -#include <linux/fs.h> -#include <linux/cpuset.h> -#include <linux/show_mem_notifier.h> -#include <linux/vmpressure.h> #define CREATE_TRACE_POINTS -#include <trace/events/almk.h> - -#ifdef CONFIG_HIGHMEM -#define _ZONE ZONE_HIGHMEM -#else -#define _ZONE ZONE_NORMAL -#endif +#include "trace/lowmemorykiller.h" static uint32_t lowmem_debug_level = 1; static short lowmem_adj[6] = { @@ -71,7 +59,6 @@ static int lowmem_minfree[6] = { 16 * 1024, /* 64MB */ }; static int lowmem_minfree_size = 4; -static int lmk_fast_run = 1; static unsigned long lowmem_deathpending_timeout; @@ -81,280 +68,6 @@ static unsigned long lowmem_deathpending_timeout; pr_info(x); \ } while (0) -static atomic_t shift_adj = ATOMIC_INIT(0); -static short adj_max_shift = 353; - -/* User knob to enable/disable adaptive lmk feature */ -static int enable_adaptive_lmk; -module_param_named(enable_adaptive_lmk, enable_adaptive_lmk, int, - S_IRUGO | S_IWUSR); - -/* - * This parameter controls the behaviour of LMK when vmpressure is in - * the range of 90-94. Adaptive lmk triggers based on number of file - * pages wrt vmpressure_file_min, when vmpressure is in the range of - * 90-94. Usually this is a pseudo minfree value, higher than the - * highest configured value in minfree array. - */ -static int vmpressure_file_min; -module_param_named(vmpressure_file_min, vmpressure_file_min, int, - S_IRUGO | S_IWUSR); - -enum { - VMPRESSURE_NO_ADJUST = 0, - VMPRESSURE_ADJUST_ENCROACH, - VMPRESSURE_ADJUST_NORMAL, -}; - -int adjust_minadj(short *min_score_adj) -{ - int ret = VMPRESSURE_NO_ADJUST; - - if (!enable_adaptive_lmk) - return 0; - - if (atomic_read(&shift_adj) && - (*min_score_adj > adj_max_shift)) { - if (*min_score_adj == OOM_SCORE_ADJ_MAX + 1) - ret = VMPRESSURE_ADJUST_ENCROACH; - else - ret = VMPRESSURE_ADJUST_NORMAL; - *min_score_adj = adj_max_shift; - } - atomic_set(&shift_adj, 0); - - return ret; -} - -static int lmk_vmpressure_notifier(struct notifier_block *nb, - unsigned long action, void *data) -{ - int other_free, other_file; - unsigned long pressure = action; - int array_size = ARRAY_SIZE(lowmem_adj); - - if (!enable_adaptive_lmk) - return 0; - - if (pressure >= 95) { - other_file = global_page_state(NR_FILE_PAGES) - - global_page_state(NR_SHMEM) - - total_swapcache_pages(); - other_free = global_page_state(NR_FREE_PAGES); - - atomic_set(&shift_adj, 1); - trace_almk_vmpressure(pressure, other_free, other_file); - } else if (pressure >= 90) { - if (lowmem_adj_size < array_size) - array_size = lowmem_adj_size; - if (lowmem_minfree_size < array_size) - array_size = lowmem_minfree_size; - - other_file = global_page_state(NR_FILE_PAGES) - - global_page_state(NR_SHMEM) - - total_swapcache_pages(); - - other_free = global_page_state(NR_FREE_PAGES); - - if ((other_free < lowmem_minfree[array_size - 1]) && - (other_file < vmpressure_file_min)) { - atomic_set(&shift_adj, 1); - trace_almk_vmpressure(pressure, other_free, - other_file); - } - } - - return 0; -} - -static struct notifier_block lmk_vmpr_nb = { - .notifier_call = lmk_vmpressure_notifier, -}; - -static int test_task_flag(struct task_struct *p, int flag) -{ - struct task_struct *t = p; - - do { - task_lock(t); - if (test_tsk_thread_flag(t, flag)) { - task_unlock(t); - return 1; - } - task_unlock(t); - } while_each_thread(p, t); - - return 0; -} - -static DEFINE_MUTEX(scan_mutex); - -int can_use_cma_pages(gfp_t gfp_mask) -{ - int can_use = 0; - int mtype = allocflags_to_migratetype(gfp_mask); - int i = 0; - int *mtype_fallbacks = get_migratetype_fallbacks(mtype); - - if (is_migrate_cma(mtype)) { - can_use = 1; - } else { - for (i = 0;; i++) { - int fallbacktype = mtype_fallbacks[i]; - - if (is_migrate_cma(fallbacktype)) { - can_use = 1; - break; - } - - if (fallbacktype == MIGRATE_RESERVE) - break; - } - } - return can_use; -} - -void tune_lmk_zone_param(struct zonelist *zonelist, int classzone_idx, - int *other_free, int *other_file, - int use_cma_pages) -{ - struct zone *zone; - struct zoneref *zoneref; - int zone_idx; - - for_each_zone_zonelist(zone, zoneref, zonelist, MAX_NR_ZONES) { - zone_idx = zonelist_zone_idx(zoneref); - if (zone_idx == ZONE_MOVABLE) { - if (!use_cma_pages) - *other_free -= - zone_page_state(zone, NR_FREE_CMA_PAGES); - continue; - } - - if (zone_idx > classzone_idx) { - if (other_free != NULL) - *other_free -= zone_page_state(zone, - NR_FREE_PAGES); - if (other_file != NULL) - *other_file -= zone_page_state(zone, - NR_FILE_PAGES) - - zone_page_state(zone, NR_SHMEM); - } else if (zone_idx < classzone_idx) { - if (zone_watermark_ok(zone, 0, 0, classzone_idx, 0)) { - if (!use_cma_pages) { - *other_free -= min( - zone->lowmem_reserve[classzone_idx] + - zone_page_state( - zone, NR_FREE_CMA_PAGES), - zone_page_state( - zone, NR_FREE_PAGES)); - } else { - *other_free -= - zone->lowmem_reserve[classzone_idx]; - } - } else { - *other_free -= - zone_page_state(zone, NR_FREE_PAGES); - } - } - } -} - -#ifdef CONFIG_HIGHMEM -void adjust_gfp_mask(gfp_t *gfp_mask) -{ - struct zone *preferred_zone; - struct zonelist *zonelist; - enum zone_type high_zoneidx; - - if (current_is_kswapd()) { - zonelist = node_zonelist(0, *gfp_mask); - high_zoneidx = gfp_zone(*gfp_mask); - first_zones_zonelist(zonelist, high_zoneidx, NULL, - &preferred_zone); - - if (high_zoneidx == ZONE_NORMAL) { - if (zone_watermark_ok_safe(preferred_zone, 0, - high_wmark_pages(preferred_zone), 0, - 0)) - *gfp_mask |= __GFP_HIGHMEM; - } else if (high_zoneidx == ZONE_HIGHMEM) { - *gfp_mask |= __GFP_HIGHMEM; - } - } -} -#else -void adjust_gfp_mask(gfp_t *unused) -{ -} -#endif - -void tune_lmk_param(int *other_free, int *other_file, struct shrink_control *sc) -{ - gfp_t gfp_mask; - struct zone *preferred_zone; - struct zonelist *zonelist; - enum zone_type high_zoneidx, classzone_idx; - unsigned long balance_gap; - int use_cma_pages; - - gfp_mask = sc->gfp_mask; - adjust_gfp_mask(&gfp_mask); - - zonelist = node_zonelist(0, gfp_mask); - high_zoneidx = gfp_zone(gfp_mask); - first_zones_zonelist(zonelist, high_zoneidx, NULL, &preferred_zone); - classzone_idx = zone_idx(preferred_zone); - use_cma_pages = can_use_cma_pages(gfp_mask); - - balance_gap = min(low_wmark_pages(preferred_zone), - (preferred_zone->present_pages + - KSWAPD_ZONE_BALANCE_GAP_RATIO-1) / - KSWAPD_ZONE_BALANCE_GAP_RATIO); - - if (likely(current_is_kswapd() && zone_watermark_ok(preferred_zone, 0, - high_wmark_pages(preferred_zone) + SWAP_CLUSTER_MAX + - balance_gap, 0, 0))) { - if (lmk_fast_run) - tune_lmk_zone_param(zonelist, classzone_idx, other_free, - other_file, use_cma_pages); - else - tune_lmk_zone_param(zonelist, classzone_idx, other_free, - NULL, use_cma_pages); - - if (zone_watermark_ok(preferred_zone, 0, 0, _ZONE, 0)) { - if (!use_cma_pages) { - *other_free -= min( - preferred_zone->lowmem_reserve[_ZONE] - + zone_page_state( - preferred_zone, NR_FREE_CMA_PAGES), - zone_page_state( - preferred_zone, NR_FREE_PAGES)); - } else { - *other_free -= - preferred_zone->lowmem_reserve[_ZONE]; - } - } else { - *other_free -= zone_page_state(preferred_zone, - NR_FREE_PAGES); - } - - lowmem_print(4, "lowmem_shrink of kswapd tunning for highmem " - "ofree %d, %d\n", *other_free, *other_file); - } else { - tune_lmk_zone_param(zonelist, classzone_idx, other_free, - other_file, use_cma_pages); - - if (!use_cma_pages) { - *other_free -= - zone_page_state(preferred_zone, NR_FREE_CMA_PAGES); - } - - lowmem_print(4, "lowmem_shrink tunning for others ofree %d, " - "%d\n", *other_free, *other_file); - } -} - static int lowmem_shrink(struct shrinker *s, struct shrink_control *sc) { struct task_struct *tsk; @@ -362,32 +75,14 @@ static int lowmem_shrink(struct shrinker *s, struct shrink_control *sc) int rem = 0; int tasksize; int i; - int ret = 0; short min_score_adj = OOM_SCORE_ADJ_MAX + 1; int minfree = 0; int selected_tasksize = 0; short selected_oom_score_adj; int array_size = ARRAY_SIZE(lowmem_adj); - int other_free; - int other_file; - unsigned long nr_to_scan = sc->nr_to_scan; - - if (nr_to_scan > 0) { - if (mutex_lock_interruptible(&scan_mutex) < 0) - return 0; - } - - other_free = global_page_state(NR_FREE_PAGES); - - if (global_page_state(NR_SHMEM) + total_swapcache_pages() < - global_page_state(NR_FILE_PAGES)) - other_file = global_page_state(NR_FILE_PAGES) - - global_page_state(NR_SHMEM) - - total_swapcache_pages(); - else - other_file = 0; - - tune_lmk_param(&other_free, &other_file, sc); + int other_free = global_page_state(NR_FREE_PAGES) - totalreserve_pages; + int other_file = global_page_state(NR_FILE_PAGES) - + global_page_state(NR_SHMEM); if (lowmem_adj_size < array_size) array_size = lowmem_adj_size; @@ -400,28 +95,17 @@ static int lowmem_shrink(struct shrinker *s, struct shrink_control *sc) break; } } - if (nr_to_scan > 0) { - ret = adjust_minadj(&min_score_adj); + if (sc->nr_to_scan > 0) lowmem_print(3, "lowmem_shrink %lu, %x, ofree %d %d, ma %hd\n", - nr_to_scan, sc->gfp_mask, other_free, + sc->nr_to_scan, sc->gfp_mask, other_free, other_file, min_score_adj); - } - rem = global_page_state(NR_ACTIVE_ANON) + global_page_state(NR_ACTIVE_FILE) + global_page_state(NR_INACTIVE_ANON) + global_page_state(NR_INACTIVE_FILE); - if (nr_to_scan <= 0 || min_score_adj == OOM_SCORE_ADJ_MAX + 1) { + if (sc->nr_to_scan <= 0 || min_score_adj == OOM_SCORE_ADJ_MAX + 1) { lowmem_print(5, "lowmem_shrink %lu, %x, return %d\n", - nr_to_scan, sc->gfp_mask, rem); - - if (nr_to_scan > 0) - mutex_unlock(&scan_mutex); - - if ((min_score_adj == OOM_SCORE_ADJ_MAX + 1) && - (nr_to_scan > 0)) - trace_almk_shrink(0, ret, other_free, other_file, 0); - + sc->nr_to_scan, sc->gfp_mask, rem); return rem; } selected_oom_score_adj = min_score_adj; @@ -434,24 +118,16 @@ static int lowmem_shrink(struct shrinker *s, struct shrink_control *sc) if (tsk->flags & PF_KTHREAD) continue; - /* if task no longer has any memory ignore it */ - if (test_task_flag(tsk, TIF_MM_RELEASED)) - continue; - - if (time_before_eq(jiffies, lowmem_deathpending_timeout)) { - if (test_task_flag(tsk, TIF_MEMDIE)) { - rcu_read_unlock(); - /* give the system time to free up the memory */ - msleep_interruptible(20); - mutex_unlock(&scan_mutex); - return 0; - } - } - p = find_lock_task_mm(tsk); if (!p) continue; + if (test_tsk_thread_flag(p, TIF_MEMDIE) && + time_before_eq(jiffies, lowmem_deathpending_timeout)) { + task_unlock(p); + rcu_read_unlock(); + return 0; + } oom_score_adj = p->signal->oom_score_adj; if (oom_score_adj < min_score_adj) { task_unlock(p); @@ -471,70 +147,33 @@ static int lowmem_shrink(struct shrinker *s, struct shrink_control *sc) selected = p; selected_tasksize = tasksize; selected_oom_score_adj = oom_score_adj; - lowmem_print(3, "select '%s' (%d), adj %hd, size %d, to kill\n", + lowmem_print(2, "select '%s' (%d), adj %hd, size %d, to kill\n", p->comm, p->pid, oom_score_adj, tasksize); } if (selected) { + long cache_size = other_file * (long)(PAGE_SIZE / 1024); + long cache_limit = minfree * (long)(PAGE_SIZE / 1024); + long free = other_free * (long)(PAGE_SIZE / 1024); + trace_lowmemory_kill(selected, cache_size, cache_limit, free); lowmem_print(1, "Killing '%s' (%d), adj %hd,\n" \ " to free %ldkB on behalf of '%s' (%d) because\n" \ " cache %ldkB is below limit %ldkB for oom_score_adj %hd\n" \ - " Free memory is %ldkB above reserved.\n" \ - " Free CMA is %ldkB\n" \ - " Total reserve is %ldkB\n" \ - " Total free pages is %ldkB\n" \ - " Total file cache is %ldkB\n" \ - " Slab Reclaimable is %ldkB\n" \ - " Slab UnReclaimable is %ldkB\n" \ - " Total Slab is %ldkB\n" \ - " GFP mask is 0x%x\n", + " Free memory is %ldkB above reserved\n", selected->comm, selected->pid, selected_oom_score_adj, selected_tasksize * (long)(PAGE_SIZE / 1024), current->comm, current->pid, - other_file * (long)(PAGE_SIZE / 1024), - minfree * (long)(PAGE_SIZE / 1024), + cache_size, cache_limit, min_score_adj, - other_free * (long)(PAGE_SIZE / 1024), - global_page_state(NR_FREE_CMA_PAGES) * - (long)(PAGE_SIZE / 1024), - totalreserve_pages * (long)(PAGE_SIZE / 1024), - global_page_state(NR_FREE_PAGES) * - (long)(PAGE_SIZE / 1024), - global_page_state(NR_FILE_PAGES) * - (long)(PAGE_SIZE / 1024), - global_page_state(NR_SLAB_RECLAIMABLE) * - (long)(PAGE_SIZE / 1024), - global_page_state(NR_SLAB_UNRECLAIMABLE) * - (long)(PAGE_SIZE / 1024), - global_page_state(NR_SLAB_RECLAIMABLE) * - (long)(PAGE_SIZE / 1024) + - global_page_state(NR_SLAB_UNRECLAIMABLE) * - (long)(PAGE_SIZE / 1024), - sc->gfp_mask); - - if (lowmem_debug_level >= 2 && selected_oom_score_adj == 0) { - show_mem(SHOW_MEM_FILTER_NODES); - dump_tasks(NULL, NULL); - show_mem_call_notifiers(); - } - + free); lowmem_deathpending_timeout = jiffies + HZ; send_sig(SIGKILL, selected, 0); set_tsk_thread_flag(selected, TIF_MEMDIE); rem -= selected_tasksize; - rcu_read_unlock(); - /* give the system time to free up the memory */ - msleep_interruptible(20); - trace_almk_shrink(selected_tasksize, ret, - other_free, other_file, selected_oom_score_adj); - } else { - trace_almk_shrink(1, ret, other_free, other_file, 0); - rcu_read_unlock(); } - lowmem_print(4, "lowmem_shrink %lu, %x, return %d\n", - nr_to_scan, sc->gfp_mask, rem); - mutex_unlock(&scan_mutex); + sc->nr_to_scan, sc->gfp_mask, rem); + rcu_read_unlock(); return rem; } @@ -546,7 +185,6 @@ static struct shrinker lowmem_shrinker = { static int __init lowmem_init(void) { register_shrinker(&lowmem_shrinker); - vmpressure_notifier_register(&lmk_vmpr_nb); return 0; } @@ -646,7 +284,6 @@ module_param_array_named(adj, lowmem_adj, short, &lowmem_adj_size, module_param_array_named(minfree, lowmem_minfree, uint, &lowmem_minfree_size, S_IRUGO | S_IWUSR); module_param_named(debug_level, lowmem_debug_level, uint, S_IRUGO | S_IWUSR); -module_param_named(lmk_fast_run, lmk_fast_run, int, S_IRUGO | S_IWUSR); module_init(lowmem_init); module_exit(lowmem_exit); diff --git a/drivers/staging/android/trace/lowmemorykiller.h b/drivers/staging/android/trace/lowmemorykiller.h new file mode 100644 index 0000000000000000000000000000000000000000..f43d3fae75eeb236a785b5bd3b8c4ca2d79808a3 --- /dev/null +++ b/drivers/staging/android/trace/lowmemorykiller.h @@ -0,0 +1,41 @@ +#undef TRACE_SYSTEM +#define TRACE_INCLUDE_PATH ../../drivers/staging/android/trace +#define TRACE_SYSTEM lowmemorykiller + +#if !defined(_TRACE_LOWMEMORYKILLER_H) || defined(TRACE_HEADER_MULTI_READ) +#define _TRACE_LOWMEMORYKILLER_H + +#include <linux/tracepoint.h> + +TRACE_EVENT(lowmemory_kill, + TP_PROTO(struct task_struct *killed_task, long cache_size, \ + long cache_limit, long free), + + TP_ARGS(killed_task, cache_size, cache_limit, free), + + TP_STRUCT__entry( + __array(char, comm, TASK_COMM_LEN) + __field(pid_t, pid) + __field(long, pagecache_size) + __field(long, pagecache_limit) + __field(long, free) + ), + + TP_fast_assign( + memcpy(__entry->comm, killed_task->comm, TASK_COMM_LEN); + __entry->pid = killed_task->pid; + __entry->pagecache_size = cache_size; + __entry->pagecache_limit = cache_limit; + __entry->free = free; + ), + + TP_printk("%s (%d), page cache %ldkB (limit %ldkB), free %ldKb", + __entry->comm, __entry->pid, __entry->pagecache_size, + __entry->pagecache_limit, __entry->free) +); + + +#endif /* if !defined(_TRACE_LOWMEMORYKILLER_H) || defined(TRACE_HEADER_MULTI_READ) */ + +/* This part must be outside protection */ +#include <trace/define_trace.h>