From f183324133ea535db4127f9fad3e19725ca88bf3 Mon Sep 17 00:00:00 2001 From: Roman Gushchin Date: Wed, 7 Apr 2021 20:57:36 -0700 Subject: percpu: implement partial chunk depopulation From Roman ("percpu: partial chunk depopulation"): In our [Facebook] production experience the percpu memory allocator is sometimes struggling with returning the memory to the system. A typical example is a creation of several thousands memory cgroups (each has several chunks of the percpu data used for vmstats, vmevents, ref counters etc). Deletion and complete releasing of these cgroups doesn't always lead to a shrinkage of the percpu memory, so that sometimes there are several GB's of memory wasted. The underlying problem is the fragmentation: to release an underlying chunk all percpu allocations should be released first. The percpu allocator tends to top up chunks to improve the utilization. It means new small-ish allocations (e.g. percpu ref counters) are placed onto almost filled old-ish chunks, effectively pinning them in memory. This patchset solves this problem by implementing a partial depopulation of percpu chunks: chunks with many empty pages are being asynchronously depopulated and the pages are returned to the system. To illustrate the problem the following script can be used: -- cd /sys/fs/cgroup mkdir percpu_test echo "+memory" > percpu_test/cgroup.subtree_control cat /proc/meminfo | grep Percpu for i in `seq 1 1000`; do mkdir percpu_test/cg_"${i}" for j in `seq 1 10`; do mkdir percpu_test/cg_"${i}"_"${j}" done done cat /proc/meminfo | grep Percpu for i in `seq 1 1000`; do for j in `seq 1 10`; do rmdir percpu_test/cg_"${i}"_"${j}" done done sleep 10 cat /proc/meminfo | grep Percpu for i in `seq 1 1000`; do rmdir percpu_test/cg_"${i}" done rmdir percpu_test -- It creates 11000 memory cgroups and removes every 10 out of 11. It prints the initial size of the percpu memory, the size after creating all cgroups and the size after deleting most of them. Results: vanilla: ./percpu_test.sh Percpu: 7488 kB Percpu: 481152 kB Percpu: 481152 kB with this patchset applied: ./percpu_test.sh Percpu: 7488 kB Percpu: 481408 kB Percpu: 135552 kB The total size of the percpu memory was reduced by more than 3.5 times. This patch: This patch implements partial depopulation of percpu chunks. As of now, a chunk can be depopulated only as a part of the final destruction, if there are no more outstanding allocations. However to minimize a memory waste it might be useful to depopulate a partially filed chunk, if a small number of outstanding allocations prevents the chunk from being fully reclaimed. This patch implements the following depopulation process: it scans over the chunk pages, looks for a range of empty and populated pages and performs the depopulation. To avoid races with new allocations, the chunk is previously isolated. After the depopulation the chunk is sidelined to a special list or freed. New allocations prefer using active chunks to sidelined chunks. If a sidelined chunk is used, it is reintegrated to the active lists. The depopulation is scheduled on the free path if the chunk is all of the following: 1) has more than 1/4 of total pages free and populated 2) the system has enough free percpu pages aside of this chunk 3) isn't the reserved chunk 4) isn't the first chunk If it's already depopulated but got free populated pages, it's a good target too. The chunk is moved to a special slot, pcpu_to_depopulate_slot, chunk->isolated is set, and the balance work item is scheduled. On isolation, these pages are removed from the pcpu_nr_empty_pop_pages. It is constantly replaced to the to_depopulate_slot when it meets these qualifications. pcpu_reclaim_populated() iterates over the to_depopulate_slot until it becomes empty. The depopulation is performed in the reverse direction to keep populated pages close to the beginning. Depopulated chunks are sidelined to preferentially avoid them for new allocations. When no active chunk can suffice a new allocation, sidelined chunks are first checked before creating a new chunk. Signed-off-by: Roman Gushchin Co-developed-by: Dennis Zhou Signed-off-by: Dennis Zhou Tested-by: Pratik Sampat Signed-off-by: Dennis Zhou --- mm/percpu-vm.c | 30 ++++++++++++++++++++++++++++++ 1 file changed, 30 insertions(+) (limited to 'mm/percpu-vm.c') diff --git a/mm/percpu-vm.c b/mm/percpu-vm.c index e46f7a6917f9..c75f6f24f2d5 100644 --- a/mm/percpu-vm.c +++ b/mm/percpu-vm.c @@ -377,3 +377,33 @@ static int __init pcpu_verify_alloc_info(const struct pcpu_alloc_info *ai) /* no extra restriction */ return 0; } + +/** + * pcpu_should_reclaim_chunk - determine if a chunk should go into reclaim + * @chunk: chunk of interest + * + * This is the entry point for percpu reclaim. If a chunk qualifies, it is then + * isolated and managed in separate lists at the back of pcpu_slot: sidelined + * and to_depopulate respectively. The to_depopulate list holds chunks slated + * for depopulation. They no longer contribute to pcpu_nr_empty_pop_pages once + * they are on this list. Once depopulated, they are moved onto the sidelined + * list which enables them to be pulled back in for allocation if no other chunk + * can suffice the allocation. + */ +static bool pcpu_should_reclaim_chunk(struct pcpu_chunk *chunk) +{ + /* do not reclaim either the first chunk or reserved chunk */ + if (chunk == pcpu_first_chunk || chunk == pcpu_reserved_chunk) + return false; + + /* + * If it is isolated, it may be on the sidelined list so move it back to + * the to_depopulate list. If we hit at least 1/4 pages empty pages AND + * there is no system-wide shortage of empty pages aside from this + * chunk, move it to the to_depopulate list. + */ + return ((chunk->isolated && chunk->nr_empty_pop_pages) || + (pcpu_nr_empty_pop_pages[pcpu_chunk_type(chunk)] > + PCPU_EMPTY_POP_PAGES_HIGH + chunk->nr_empty_pop_pages && + chunk->nr_empty_pop_pages >= chunk->nr_pages / 4)); +} -- cgit v1.2.3-70-g09d2 From faf65dde844affa9e360ccaa4bd231c2a04b87ea Mon Sep 17 00:00:00 2001 From: Roman Gushchin Date: Wed, 2 Jun 2021 18:09:31 -0700 Subject: percpu: rework memcg accounting The current implementation of the memcg accounting of the percpu memory is based on the idea of having two separate sets of chunks for accounted and non-accounted memory. This approach has an advantage of not wasting any extra memory for memcg data for non-accounted chunks, however it complicates the code and leads to a higher chunks number due to a lower chunk utilization. Instead of having two chunk types it's possible to declare all* chunks memcg-aware unless the kernel memory accounting is disabled globally by a boot option. The size of objcg_array is usually small in comparison to chunks themselves (it obviously depends on the number of CPUs), so even if some chunk will have no accounted allocations, the memory waste isn't significant and will likely be compensated by a higher chunk utilization. Also, with time more and more percpu allocations will likely become accounted. * The first chunk is initialized before the memory cgroup subsystem, so we don't know for sure whether we need to allocate obj_cgroups. Because it's small, let's make it free for use. Then we don't need to allocate obj_cgroups for it. Signed-off-by: Roman Gushchin Signed-off-by: Dennis Zhou --- mm/percpu-internal.h | 52 +------------------- mm/percpu-km.c | 5 +- mm/percpu-stats.c | 46 ++++++------------ mm/percpu-vm.c | 11 ++--- mm/percpu.c | 134 ++++++++++++++++++++------------------------------- 5 files changed, 76 insertions(+), 172 deletions(-) (limited to 'mm/percpu-vm.c') diff --git a/mm/percpu-internal.h b/mm/percpu-internal.h index 10604dce806f..b6dc22904088 100644 --- a/mm/percpu-internal.h +++ b/mm/percpu-internal.h @@ -5,25 +5,6 @@ #include #include -/* - * There are two chunk types: root and memcg-aware. - * Chunks of each type have separate slots list. - * - * Memcg-aware chunks have an attached vector of obj_cgroup pointers, which is - * used to store memcg membership data of a percpu object. Obj_cgroups are - * ref-counted pointers to a memory cgroup with an ability to switch dynamically - * to the parent memory cgroup. This allows to reclaim a deleted memory cgroup - * without reclaiming of all outstanding objects, which hold a reference at it. - */ -enum pcpu_chunk_type { - PCPU_CHUNK_ROOT, -#ifdef CONFIG_MEMCG_KMEM - PCPU_CHUNK_MEMCG, -#endif - PCPU_NR_CHUNK_TYPES, - PCPU_FAIL_ALLOC = PCPU_NR_CHUNK_TYPES -}; - /* * pcpu_block_md is the metadata block struct. * Each chunk's bitmap is split into a number of full blocks. @@ -91,7 +72,7 @@ extern struct list_head *pcpu_chunk_lists; extern int pcpu_nr_slots; extern int pcpu_sidelined_slot; extern int pcpu_to_depopulate_slot; -extern int pcpu_nr_empty_pop_pages[]; +extern int pcpu_nr_empty_pop_pages; extern struct pcpu_chunk *pcpu_first_chunk; extern struct pcpu_chunk *pcpu_reserved_chunk; @@ -132,37 +113,6 @@ static inline int pcpu_chunk_map_bits(struct pcpu_chunk *chunk) return pcpu_nr_pages_to_map_bits(chunk->nr_pages); } -#ifdef CONFIG_MEMCG_KMEM -static inline enum pcpu_chunk_type pcpu_chunk_type(struct pcpu_chunk *chunk) -{ - if (chunk->obj_cgroups) - return PCPU_CHUNK_MEMCG; - return PCPU_CHUNK_ROOT; -} - -static inline bool pcpu_is_memcg_chunk(enum pcpu_chunk_type chunk_type) -{ - return chunk_type == PCPU_CHUNK_MEMCG; -} - -#else -static inline enum pcpu_chunk_type pcpu_chunk_type(struct pcpu_chunk *chunk) -{ - return PCPU_CHUNK_ROOT; -} - -static inline bool pcpu_is_memcg_chunk(enum pcpu_chunk_type chunk_type) -{ - return false; -} -#endif - -static inline struct list_head *pcpu_chunk_list(enum pcpu_chunk_type chunk_type) -{ - return &pcpu_chunk_lists[pcpu_nr_slots * - pcpu_is_memcg_chunk(chunk_type)]; -} - #ifdef CONFIG_PERCPU_STATS #include diff --git a/mm/percpu-km.c b/mm/percpu-km.c index c84a9f781a6c..c9d529dc7651 100644 --- a/mm/percpu-km.c +++ b/mm/percpu-km.c @@ -44,8 +44,7 @@ static void pcpu_depopulate_chunk(struct pcpu_chunk *chunk, /* nada */ } -static struct pcpu_chunk *pcpu_create_chunk(enum pcpu_chunk_type type, - gfp_t gfp) +static struct pcpu_chunk *pcpu_create_chunk(gfp_t gfp) { const int nr_pages = pcpu_group_sizes[0] >> PAGE_SHIFT; struct pcpu_chunk *chunk; @@ -53,7 +52,7 @@ static struct pcpu_chunk *pcpu_create_chunk(enum pcpu_chunk_type type, unsigned long flags; int i; - chunk = pcpu_alloc_chunk(type, gfp); + chunk = pcpu_alloc_chunk(gfp); if (!chunk) return NULL; diff --git a/mm/percpu-stats.c b/mm/percpu-stats.c index 2125981acfb9..c6bd092ff7a3 100644 --- a/mm/percpu-stats.c +++ b/mm/percpu-stats.c @@ -34,15 +34,11 @@ static int find_max_nr_alloc(void) { struct pcpu_chunk *chunk; int slot, max_nr_alloc; - enum pcpu_chunk_type type; max_nr_alloc = 0; - for (type = 0; type < PCPU_NR_CHUNK_TYPES; type++) - for (slot = 0; slot < pcpu_nr_slots; slot++) - list_for_each_entry(chunk, &pcpu_chunk_list(type)[slot], - list) - max_nr_alloc = max(max_nr_alloc, - chunk->nr_alloc); + for (slot = 0; slot < pcpu_nr_slots; slot++) + list_for_each_entry(chunk, &pcpu_chunk_lists[slot], list) + max_nr_alloc = max(max_nr_alloc, chunk->nr_alloc); return max_nr_alloc; } @@ -133,9 +129,6 @@ static void chunk_map_stats(struct seq_file *m, struct pcpu_chunk *chunk, P("cur_min_alloc", cur_min_alloc); P("cur_med_alloc", cur_med_alloc); P("cur_max_alloc", cur_max_alloc); -#ifdef CONFIG_MEMCG_KMEM - P("memcg_aware", pcpu_is_memcg_chunk(pcpu_chunk_type(chunk))); -#endif seq_putc(m, '\n'); } @@ -144,8 +137,6 @@ static int percpu_stats_show(struct seq_file *m, void *v) struct pcpu_chunk *chunk; int slot, max_nr_alloc; int *buffer; - enum pcpu_chunk_type type; - int nr_empty_pop_pages; alloc_buffer: spin_lock_irq(&pcpu_lock); @@ -166,10 +157,6 @@ alloc_buffer: goto alloc_buffer; } - nr_empty_pop_pages = 0; - for (type = 0; type < PCPU_NR_CHUNK_TYPES; type++) - nr_empty_pop_pages += pcpu_nr_empty_pop_pages[type]; - #define PL(X) \ seq_printf(m, " %-20s: %12lld\n", #X, (long long int)pcpu_stats_ai.X) @@ -201,7 +188,7 @@ alloc_buffer: PU(nr_max_chunks); PU(min_alloc_size); PU(max_alloc_size); - P("empty_pop_pages", nr_empty_pop_pages); + P("empty_pop_pages", pcpu_nr_empty_pop_pages); seq_putc(m, '\n'); #undef PU @@ -215,20 +202,17 @@ alloc_buffer: chunk_map_stats(m, pcpu_reserved_chunk, buffer); } - for (type = 0; type < PCPU_NR_CHUNK_TYPES; type++) { - for (slot = 0; slot < pcpu_nr_slots; slot++) { - list_for_each_entry(chunk, &pcpu_chunk_list(type)[slot], - list) { - if (chunk == pcpu_first_chunk) - seq_puts(m, "Chunk: <- First Chunk\n"); - else if (slot == pcpu_to_depopulate_slot) - seq_puts(m, "Chunk (to_depopulate)\n"); - else if (slot == pcpu_sidelined_slot) - seq_puts(m, "Chunk (sidelined):\n"); - else - seq_puts(m, "Chunk:\n"); - chunk_map_stats(m, chunk, buffer); - } + for (slot = 0; slot < pcpu_nr_slots; slot++) { + list_for_each_entry(chunk, &pcpu_chunk_lists[slot], list) { + if (chunk == pcpu_first_chunk) + seq_puts(m, "Chunk: <- First Chunk\n"); + else if (slot == pcpu_to_depopulate_slot) + seq_puts(m, "Chunk (to_depopulate)\n"); + else if (slot == pcpu_sidelined_slot) + seq_puts(m, "Chunk (sidelined):\n"); + else + seq_puts(m, "Chunk:\n"); + chunk_map_stats(m, chunk, buffer); } } diff --git a/mm/percpu-vm.c b/mm/percpu-vm.c index c75f6f24f2d5..057546f5555e 100644 --- a/mm/percpu-vm.c +++ b/mm/percpu-vm.c @@ -328,13 +328,12 @@ static void pcpu_depopulate_chunk(struct pcpu_chunk *chunk, pcpu_free_pages(chunk, pages, page_start, page_end); } -static struct pcpu_chunk *pcpu_create_chunk(enum pcpu_chunk_type type, - gfp_t gfp) +static struct pcpu_chunk *pcpu_create_chunk(gfp_t gfp) { struct pcpu_chunk *chunk; struct vm_struct **vms; - chunk = pcpu_alloc_chunk(type, gfp); + chunk = pcpu_alloc_chunk(gfp); if (!chunk) return NULL; @@ -403,7 +402,7 @@ static bool pcpu_should_reclaim_chunk(struct pcpu_chunk *chunk) * chunk, move it to the to_depopulate list. */ return ((chunk->isolated && chunk->nr_empty_pop_pages) || - (pcpu_nr_empty_pop_pages[pcpu_chunk_type(chunk)] > - PCPU_EMPTY_POP_PAGES_HIGH + chunk->nr_empty_pop_pages && - chunk->nr_empty_pop_pages >= chunk->nr_pages / 4)); + (pcpu_nr_empty_pop_pages > + (PCPU_EMPTY_POP_PAGES_HIGH + chunk->nr_empty_pop_pages) && + chunk->nr_empty_pop_pages >= chunk->nr_pages / 4)); } diff --git a/mm/percpu.c b/mm/percpu.c index 3135e56ce8d4..e7b9ca82e9aa 100644 --- a/mm/percpu.c +++ b/mm/percpu.c @@ -179,10 +179,10 @@ struct list_head *pcpu_chunk_lists __ro_after_init; /* chunk list slots */ static LIST_HEAD(pcpu_map_extend_chunks); /* - * The number of empty populated pages by chunk type, protected by pcpu_lock. + * The number of empty populated pages, protected by pcpu_lock. * The reserved chunk doesn't contribute to the count. */ -int pcpu_nr_empty_pop_pages[PCPU_NR_CHUNK_TYPES]; +int pcpu_nr_empty_pop_pages; /* * The number of populated pages in use by the allocator, protected by @@ -532,13 +532,10 @@ static void __pcpu_chunk_move(struct pcpu_chunk *chunk, int slot, bool move_front) { if (chunk != pcpu_reserved_chunk) { - struct list_head *pcpu_slot; - - pcpu_slot = pcpu_chunk_list(pcpu_chunk_type(chunk)); if (move_front) - list_move(&chunk->list, &pcpu_slot[slot]); + list_move(&chunk->list, &pcpu_chunk_lists[slot]); else - list_move_tail(&chunk->list, &pcpu_slot[slot]); + list_move_tail(&chunk->list, &pcpu_chunk_lists[slot]); } } @@ -574,27 +571,22 @@ static void pcpu_chunk_relocate(struct pcpu_chunk *chunk, int oslot) static void pcpu_isolate_chunk(struct pcpu_chunk *chunk) { - enum pcpu_chunk_type type = pcpu_chunk_type(chunk); - struct list_head *pcpu_slot = pcpu_chunk_list(type); - lockdep_assert_held(&pcpu_lock); if (!chunk->isolated) { chunk->isolated = true; - pcpu_nr_empty_pop_pages[type] -= chunk->nr_empty_pop_pages; + pcpu_nr_empty_pop_pages -= chunk->nr_empty_pop_pages; } - list_move(&chunk->list, &pcpu_slot[pcpu_to_depopulate_slot]); + list_move(&chunk->list, &pcpu_chunk_lists[pcpu_to_depopulate_slot]); } static void pcpu_reintegrate_chunk(struct pcpu_chunk *chunk) { - enum pcpu_chunk_type type = pcpu_chunk_type(chunk); - lockdep_assert_held(&pcpu_lock); if (chunk->isolated) { chunk->isolated = false; - pcpu_nr_empty_pop_pages[type] += chunk->nr_empty_pop_pages; + pcpu_nr_empty_pop_pages += chunk->nr_empty_pop_pages; pcpu_chunk_relocate(chunk, -1); } } @@ -612,7 +604,7 @@ static inline void pcpu_update_empty_pages(struct pcpu_chunk *chunk, int nr) { chunk->nr_empty_pop_pages += nr; if (chunk != pcpu_reserved_chunk && !chunk->isolated) - pcpu_nr_empty_pop_pages[pcpu_chunk_type(chunk)] += nr; + pcpu_nr_empty_pop_pages += nr; } /* @@ -1405,7 +1397,7 @@ static struct pcpu_chunk * __init pcpu_alloc_first_chunk(unsigned long tmp_addr, alloc_size); #ifdef CONFIG_MEMCG_KMEM - /* first chunk isn't memcg-aware */ + /* first chunk is free to use */ chunk->obj_cgroups = NULL; #endif pcpu_init_md_blocks(chunk); @@ -1447,7 +1439,7 @@ static struct pcpu_chunk * __init pcpu_alloc_first_chunk(unsigned long tmp_addr, return chunk; } -static struct pcpu_chunk *pcpu_alloc_chunk(enum pcpu_chunk_type type, gfp_t gfp) +static struct pcpu_chunk *pcpu_alloc_chunk(gfp_t gfp) { struct pcpu_chunk *chunk; int region_bits; @@ -1476,7 +1468,7 @@ static struct pcpu_chunk *pcpu_alloc_chunk(enum pcpu_chunk_type type, gfp_t gfp) goto md_blocks_fail; #ifdef CONFIG_MEMCG_KMEM - if (pcpu_is_memcg_chunk(type)) { + if (!mem_cgroup_kmem_disabled()) { chunk->obj_cgroups = pcpu_mem_zalloc(pcpu_chunk_map_bits(chunk) * sizeof(struct obj_cgroup *), gfp); @@ -1589,8 +1581,7 @@ static int pcpu_populate_chunk(struct pcpu_chunk *chunk, int page_start, int page_end, gfp_t gfp); static void pcpu_depopulate_chunk(struct pcpu_chunk *chunk, int page_start, int page_end); -static struct pcpu_chunk *pcpu_create_chunk(enum pcpu_chunk_type type, - gfp_t gfp); +static struct pcpu_chunk *pcpu_create_chunk(gfp_t gfp); static void pcpu_destroy_chunk(struct pcpu_chunk *chunk); static struct page *pcpu_addr_to_page(void *addr); static int __init pcpu_verify_alloc_info(const struct pcpu_alloc_info *ai); @@ -1633,25 +1624,25 @@ static struct pcpu_chunk *pcpu_chunk_addr_search(void *addr) } #ifdef CONFIG_MEMCG_KMEM -static enum pcpu_chunk_type pcpu_memcg_pre_alloc_hook(size_t size, gfp_t gfp, - struct obj_cgroup **objcgp) +static bool pcpu_memcg_pre_alloc_hook(size_t size, gfp_t gfp, + struct obj_cgroup **objcgp) { struct obj_cgroup *objcg; if (!memcg_kmem_enabled() || !(gfp & __GFP_ACCOUNT)) - return PCPU_CHUNK_ROOT; + return true; objcg = get_obj_cgroup_from_current(); if (!objcg) - return PCPU_CHUNK_ROOT; + return true; if (obj_cgroup_charge(objcg, gfp, size * num_possible_cpus())) { obj_cgroup_put(objcg); - return PCPU_FAIL_ALLOC; + return false; } *objcgp = objcg; - return PCPU_CHUNK_MEMCG; + return true; } static void pcpu_memcg_post_alloc_hook(struct obj_cgroup *objcg, @@ -1661,7 +1652,7 @@ static void pcpu_memcg_post_alloc_hook(struct obj_cgroup *objcg, if (!objcg) return; - if (chunk) { + if (likely(chunk && chunk->obj_cgroups)) { chunk->obj_cgroups[off >> PCPU_MIN_ALLOC_SHIFT] = objcg; rcu_read_lock(); @@ -1678,10 +1669,12 @@ static void pcpu_memcg_free_hook(struct pcpu_chunk *chunk, int off, size_t size) { struct obj_cgroup *objcg; - if (!pcpu_is_memcg_chunk(pcpu_chunk_type(chunk))) + if (unlikely(!chunk->obj_cgroups)) return; objcg = chunk->obj_cgroups[off >> PCPU_MIN_ALLOC_SHIFT]; + if (!objcg) + return; chunk->obj_cgroups[off >> PCPU_MIN_ALLOC_SHIFT] = NULL; obj_cgroup_uncharge(objcg, size * num_possible_cpus()); @@ -1695,10 +1688,10 @@ static void pcpu_memcg_free_hook(struct pcpu_chunk *chunk, int off, size_t size) } #else /* CONFIG_MEMCG_KMEM */ -static enum pcpu_chunk_type +static bool pcpu_memcg_pre_alloc_hook(size_t size, gfp_t gfp, struct obj_cgroup **objcgp) { - return PCPU_CHUNK_ROOT; + return true; } static void pcpu_memcg_post_alloc_hook(struct obj_cgroup *objcg, @@ -1733,8 +1726,6 @@ static void __percpu *pcpu_alloc(size_t size, size_t align, bool reserved, gfp_t pcpu_gfp; bool is_atomic; bool do_warn; - enum pcpu_chunk_type type; - struct list_head *pcpu_slot; struct obj_cgroup *objcg = NULL; static int warn_limit = 10; struct pcpu_chunk *chunk, *next; @@ -1770,10 +1761,8 @@ static void __percpu *pcpu_alloc(size_t size, size_t align, bool reserved, return NULL; } - type = pcpu_memcg_pre_alloc_hook(size, gfp, &objcg); - if (unlikely(type == PCPU_FAIL_ALLOC)) + if (unlikely(!pcpu_memcg_pre_alloc_hook(size, gfp, &objcg))) return NULL; - pcpu_slot = pcpu_chunk_list(type); if (!is_atomic) { /* @@ -1812,7 +1801,8 @@ static void __percpu *pcpu_alloc(size_t size, size_t align, bool reserved, restart: /* search through normal chunks */ for (slot = pcpu_size_to_slot(size); slot <= pcpu_free_slot; slot++) { - list_for_each_entry_safe(chunk, next, &pcpu_slot[slot], list) { + list_for_each_entry_safe(chunk, next, &pcpu_chunk_lists[slot], + list) { off = pcpu_find_block_fit(chunk, bits, bit_align, is_atomic); if (off < 0) { @@ -1841,8 +1831,8 @@ restart: goto fail; } - if (list_empty(&pcpu_slot[pcpu_free_slot])) { - chunk = pcpu_create_chunk(type, pcpu_gfp); + if (list_empty(&pcpu_chunk_lists[pcpu_free_slot])) { + chunk = pcpu_create_chunk(pcpu_gfp); if (!chunk) { err = "failed to allocate new chunk"; goto fail; @@ -1886,7 +1876,7 @@ area_found: mutex_unlock(&pcpu_alloc_mutex); } - if (pcpu_nr_empty_pop_pages[type] < PCPU_EMPTY_POP_PAGES_LOW) + if (pcpu_nr_empty_pop_pages < PCPU_EMPTY_POP_PAGES_LOW) pcpu_schedule_balance_work(); /* clear the areas and return address relative to base address */ @@ -1985,18 +1975,16 @@ void __percpu *__alloc_reserved_percpu(size_t size, size_t align) /** * pcpu_balance_free - manage the amount of free chunks - * @type: chunk type * @empty_only: free chunks only if there are no populated pages * * If empty_only is %false, reclaim all fully free chunks regardless of the * number of populated pages. Otherwise, only reclaim chunks that have no * populated pages. */ -static void pcpu_balance_free(enum pcpu_chunk_type type, bool empty_only) +static void pcpu_balance_free(bool empty_only) { LIST_HEAD(to_free); - struct list_head *pcpu_slot = pcpu_chunk_list(type); - struct list_head *free_head = &pcpu_slot[pcpu_free_slot]; + struct list_head *free_head = &pcpu_chunk_lists[pcpu_free_slot]; struct pcpu_chunk *chunk, *next; /* @@ -2035,7 +2023,6 @@ static void pcpu_balance_free(enum pcpu_chunk_type type, bool empty_only) /** * pcpu_balance_populated - manage the amount of populated pages - * @type: chunk type * * Maintain a certain amount of populated pages to satisfy atomic allocations. * It is possible that this is called when physical memory is scarce causing @@ -2043,11 +2030,10 @@ static void pcpu_balance_free(enum pcpu_chunk_type type, bool empty_only) * allocation causes the failure as it is possible that requests can be * serviced from already backed regions. */ -static void pcpu_balance_populated(enum pcpu_chunk_type type) +static void pcpu_balance_populated(void) { /* gfp flags passed to underlying allocators */ const gfp_t gfp = GFP_KERNEL | __GFP_NORETRY | __GFP_NOWARN; - struct list_head *pcpu_slot = pcpu_chunk_list(type); struct pcpu_chunk *chunk; int slot, nr_to_pop, ret; @@ -2068,7 +2054,7 @@ retry_pop: pcpu_atomic_alloc_failed = false; } else { nr_to_pop = clamp(PCPU_EMPTY_POP_PAGES_HIGH - - pcpu_nr_empty_pop_pages[type], + pcpu_nr_empty_pop_pages, 0, PCPU_EMPTY_POP_PAGES_HIGH); } @@ -2079,7 +2065,7 @@ retry_pop: break; spin_lock_irq(&pcpu_lock); - list_for_each_entry(chunk, &pcpu_slot[slot], list) { + list_for_each_entry(chunk, &pcpu_chunk_lists[slot], list) { nr_unpop = chunk->nr_pages - chunk->nr_populated; if (nr_unpop) break; @@ -2111,7 +2097,7 @@ retry_pop: if (nr_to_pop) { /* ran out of chunks to populate, create a new one and retry */ - chunk = pcpu_create_chunk(type, gfp); + chunk = pcpu_create_chunk(gfp); if (chunk) { spin_lock_irq(&pcpu_lock); pcpu_chunk_relocate(chunk, -1); @@ -2123,7 +2109,6 @@ retry_pop: /** * pcpu_reclaim_populated - scan over to_depopulate chunks and free empty pages - * @type: chunk type * * Scan over chunks in the depopulate list and try to release unused populated * pages back to the system. Depopulated chunks are sidelined to prevent @@ -2133,9 +2118,8 @@ retry_pop: * Each chunk is scanned in the reverse order to keep populated pages close to * the beginning of the chunk. */ -static void pcpu_reclaim_populated(enum pcpu_chunk_type type) +static void pcpu_reclaim_populated(void) { - struct list_head *pcpu_slot = pcpu_chunk_list(type); struct pcpu_chunk *chunk; struct pcpu_block_md *block; int i, end; @@ -2149,8 +2133,8 @@ restart: * other accessor is the free path which only returns area back to the * allocator not touching the populated bitmap. */ - while (!list_empty(&pcpu_slot[pcpu_to_depopulate_slot])) { - chunk = list_first_entry(&pcpu_slot[pcpu_to_depopulate_slot], + while (!list_empty(&pcpu_chunk_lists[pcpu_to_depopulate_slot])) { + chunk = list_first_entry(&pcpu_chunk_lists[pcpu_to_depopulate_slot], struct pcpu_chunk, list); WARN_ON(chunk->immutable); @@ -2164,8 +2148,7 @@ restart: break; /* reintegrate chunk to prevent atomic alloc failures */ - if (pcpu_nr_empty_pop_pages[type] < - PCPU_EMPTY_POP_PAGES_HIGH) { + if (pcpu_nr_empty_pop_pages < PCPU_EMPTY_POP_PAGES_HIGH) { pcpu_reintegrate_chunk(chunk); goto restart; } @@ -2205,7 +2188,7 @@ restart: pcpu_reintegrate_chunk(chunk); else list_move(&chunk->list, - &pcpu_slot[pcpu_sidelined_slot]); + &pcpu_chunk_lists[pcpu_sidelined_slot]); } spin_unlock_irq(&pcpu_lock); @@ -2221,8 +2204,6 @@ restart: */ static void pcpu_balance_workfn(struct work_struct *work) { - enum pcpu_chunk_type type; - /* * pcpu_balance_free() is called twice because the first time we may * trim pages in the active pcpu_nr_empty_pop_pages which may cause us @@ -2230,14 +2211,12 @@ static void pcpu_balance_workfn(struct work_struct *work) * to move fully free chunks to the active list to be freed if * appropriate. */ - for (type = 0; type < PCPU_NR_CHUNK_TYPES; type++) { - mutex_lock(&pcpu_alloc_mutex); - pcpu_balance_free(type, false); - pcpu_reclaim_populated(type); - pcpu_balance_populated(type); - pcpu_balance_free(type, true); - mutex_unlock(&pcpu_alloc_mutex); - } + mutex_lock(&pcpu_alloc_mutex); + pcpu_balance_free(false); + pcpu_reclaim_populated(); + pcpu_balance_populated(); + pcpu_balance_free(true); + mutex_unlock(&pcpu_alloc_mutex); } /** @@ -2256,7 +2235,6 @@ void free_percpu(void __percpu *ptr) unsigned long flags; int size, off; bool need_balance = false; - struct list_head *pcpu_slot; if (!ptr) return; @@ -2272,8 +2250,6 @@ void free_percpu(void __percpu *ptr) size = pcpu_free_area(chunk, off); - pcpu_slot = pcpu_chunk_list(pcpu_chunk_type(chunk)); - pcpu_memcg_free_hook(chunk, off, size); /* @@ -2284,7 +2260,7 @@ void free_percpu(void __percpu *ptr) if (!chunk->isolated && chunk->free_bytes == pcpu_unit_size) { struct pcpu_chunk *pos; - list_for_each_entry(pos, &pcpu_slot[pcpu_free_slot], list) + list_for_each_entry(pos, &pcpu_chunk_lists[pcpu_free_slot], list) if (pos != chunk) { need_balance = true; break; @@ -2592,7 +2568,6 @@ void __init pcpu_setup_first_chunk(const struct pcpu_alloc_info *ai, int map_size; unsigned long tmp_addr; size_t alloc_size; - enum pcpu_chunk_type type; #define PCPU_SETUP_BUG_ON(cond) do { \ if (unlikely(cond)) { \ @@ -2716,17 +2691,14 @@ void __init pcpu_setup_first_chunk(const struct pcpu_alloc_info *ai, pcpu_to_depopulate_slot = pcpu_free_slot + 1; pcpu_nr_slots = pcpu_to_depopulate_slot + 1; pcpu_chunk_lists = memblock_alloc(pcpu_nr_slots * - sizeof(pcpu_chunk_lists[0]) * - PCPU_NR_CHUNK_TYPES, + sizeof(pcpu_chunk_lists[0]), SMP_CACHE_BYTES); if (!pcpu_chunk_lists) panic("%s: Failed to allocate %zu bytes\n", __func__, - pcpu_nr_slots * sizeof(pcpu_chunk_lists[0]) * - PCPU_NR_CHUNK_TYPES); + pcpu_nr_slots * sizeof(pcpu_chunk_lists[0])); - for (type = 0; type < PCPU_NR_CHUNK_TYPES; type++) - for (i = 0; i < pcpu_nr_slots; i++) - INIT_LIST_HEAD(&pcpu_chunk_list(type)[i]); + for (i = 0; i < pcpu_nr_slots; i++) + INIT_LIST_HEAD(&pcpu_chunk_lists[i]); /* * The end of the static region needs to be aligned with the @@ -2763,7 +2735,7 @@ void __init pcpu_setup_first_chunk(const struct pcpu_alloc_info *ai, /* link the first chunk in */ pcpu_first_chunk = chunk; - pcpu_nr_empty_pop_pages[PCPU_CHUNK_ROOT] = pcpu_first_chunk->nr_empty_pop_pages; + pcpu_nr_empty_pop_pages = pcpu_first_chunk->nr_empty_pop_pages; pcpu_chunk_relocate(pcpu_first_chunk, -1); /* include all regions of the first chunk */ -- cgit v1.2.3-70-g09d2