diff options
author | 2012-07-31 19:25:39 -0700 | |
---|---|---|
committer | 2012-07-31 19:25:39 -0700 | |
commit | ac694dbdbc403c00e2c14d10bc7b8412cc378259 (patch) | |
tree | e37328cfbeaf43716dd5914cad9179e57e84df76 /mm | |
parent | Merge tag 'vfio-for-v3.6' of git://github.com/awilliam/linux-vfio (diff) | |
parent | rtc/rtc-88pm80x: remove unneed devm_kfree (diff) | |
download | linux-ac694dbdbc403c00e2c14d10bc7b8412cc378259.tar.gz linux-ac694dbdbc403c00e2c14d10bc7b8412cc378259.tar.bz2 linux-ac694dbdbc403c00e2c14d10bc7b8412cc378259.zip |
Merge branch 'akpm' (Andrew's patch-bomb)
Merge Andrew's second set of patches:
- MM
- a few random fixes
- a couple of RTC leftovers
* emailed patches from Andrew Morton <akpm@linux-foundation.org>: (120 commits)
rtc/rtc-88pm80x: remove unneed devm_kfree
rtc/rtc-88pm80x: assign ret only when rtc_register_driver fails
mm: hugetlbfs: close race during teardown of hugetlbfs shared page tables
tmpfs: distribute interleave better across nodes
mm: remove redundant initialization
mm: warn if pg_data_t isn't initialized with zero
mips: zero out pg_data_t when it's allocated
memcg: gix memory accounting scalability in shrink_page_list
mm/sparse: remove index_init_lock
mm/sparse: more checks on mem_section number
mm/sparse: optimize sparse_index_alloc
memcg: add mem_cgroup_from_css() helper
memcg: further prevent OOM with too many dirty pages
memcg: prevent OOM with too many dirty pages
mm: mmu_notifier: fix freed page still mapped in secondary MMU
mm: memcg: only check anon swapin page charges for swap cache
mm: memcg: only check swap cache pages for repeated charging
mm: memcg: split swapin charge function into private and public part
mm: memcg: remove needless !mm fixup to init_mm when charging
mm: memcg: remove unneeded shmem charge type
...
Diffstat (limited to 'mm')
-rw-r--r-- | mm/Kconfig | 5 | ||||
-rw-r--r-- | mm/Makefile | 8 | ||||
-rw-r--r-- | mm/backing-dev.c | 20 | ||||
-rw-r--r-- | mm/compaction.c | 63 | ||||
-rw-r--r-- | mm/fadvise.c | 18 | ||||
-rw-r--r-- | mm/highmem.c | 12 | ||||
-rw-r--r-- | mm/hugetlb.c | 195 | ||||
-rw-r--r-- | mm/hugetlb_cgroup.c | 418 | ||||
-rw-r--r-- | mm/hwpoison-inject.c | 2 | ||||
-rw-r--r-- | mm/internal.h | 8 | ||||
-rw-r--r-- | mm/memblock.c | 35 | ||||
-rw-r--r-- | mm/memcontrol.c | 390 | ||||
-rw-r--r-- | mm/memory-failure.c | 17 | ||||
-rw-r--r-- | mm/memory.c | 9 | ||||
-rw-r--r-- | mm/memory_hotplug.c | 20 | ||||
-rw-r--r-- | mm/migrate.c | 81 | ||||
-rw-r--r-- | mm/mmap.c | 5 | ||||
-rw-r--r-- | mm/mmu_notifier.c | 45 | ||||
-rw-r--r-- | mm/mmzone.c | 2 | ||||
-rw-r--r-- | mm/mremap.c | 2 | ||||
-rw-r--r-- | mm/oom_kill.c | 223 | ||||
-rw-r--r-- | mm/page_alloc.c | 318 | ||||
-rw-r--r-- | mm/page_cgroup.c | 2 | ||||
-rw-r--r-- | mm/page_io.c | 145 | ||||
-rw-r--r-- | mm/page_isolation.c | 93 | ||||
-rw-r--r-- | mm/shmem.c | 6 | ||||
-rw-r--r-- | mm/slab.c | 216 | ||||
-rw-r--r-- | mm/slub.c | 30 | ||||
-rw-r--r-- | mm/sparse.c | 29 | ||||
-rw-r--r-- | mm/swap.c | 52 | ||||
-rw-r--r-- | mm/swap_state.c | 7 | ||||
-rw-r--r-- | mm/swapfile.c | 145 | ||||
-rw-r--r-- | mm/vmalloc.c | 16 | ||||
-rw-r--r-- | mm/vmscan.c | 175 | ||||
-rw-r--r-- | mm/vmstat.c | 1 |
35 files changed, 2043 insertions, 770 deletions
diff --git a/mm/Kconfig b/mm/Kconfig index 82fed4eb2b6f..d5c8019c6627 100644 --- a/mm/Kconfig +++ b/mm/Kconfig @@ -140,9 +140,13 @@ config ARCH_DISCARD_MEMBLOCK config NO_BOOTMEM boolean +config MEMORY_ISOLATION + boolean + # eventually, we can have this option just 'select SPARSEMEM' config MEMORY_HOTPLUG bool "Allow for memory hot-add" + select MEMORY_ISOLATION depends on SPARSEMEM || X86_64_ACPI_NUMA depends on HOTPLUG && ARCH_ENABLE_MEMORY_HOTPLUG depends on (IA64 || X86 || PPC_BOOK3S_64 || SUPERH || S390) @@ -272,6 +276,7 @@ config MEMORY_FAILURE depends on MMU depends on ARCH_SUPPORTS_MEMORY_FAILURE bool "Enable recovery from hardware memory errors" + select MEMORY_ISOLATION help Enables code to recover from some memory failures on systems with MCA recovery. This allows a system to continue running diff --git a/mm/Makefile b/mm/Makefile index 8e81fe263c94..92753e2d82da 100644 --- a/mm/Makefile +++ b/mm/Makefile @@ -15,8 +15,8 @@ obj-y := filemap.o mempool.o oom_kill.o fadvise.o \ maccess.o page_alloc.o page-writeback.o \ readahead.o swap.o truncate.o vmscan.o shmem.o \ prio_tree.o util.o mmzone.o vmstat.o backing-dev.o \ - page_isolation.o mm_init.o mmu_context.o percpu.o \ - compaction.o slab_common.o $(mmu-y) + mm_init.o mmu_context.o percpu.o slab_common.o \ + compaction.o $(mmu-y) obj-y += init-mm.o @@ -49,9 +49,11 @@ obj-$(CONFIG_FS_XIP) += filemap_xip.o obj-$(CONFIG_MIGRATION) += migrate.o obj-$(CONFIG_QUICKLIST) += quicklist.o obj-$(CONFIG_TRANSPARENT_HUGEPAGE) += huge_memory.o -obj-$(CONFIG_CGROUP_MEM_RES_CTLR) += memcontrol.o page_cgroup.o +obj-$(CONFIG_MEMCG) += memcontrol.o page_cgroup.o +obj-$(CONFIG_CGROUP_HUGETLB) += hugetlb_cgroup.o obj-$(CONFIG_MEMORY_FAILURE) += memory-failure.o obj-$(CONFIG_HWPOISON_INJECT) += hwpoison-inject.o obj-$(CONFIG_DEBUG_KMEMLEAK) += kmemleak.o obj-$(CONFIG_DEBUG_KMEMLEAK_TEST) += kmemleak-test.o obj-$(CONFIG_CLEANCACHE) += cleancache.o +obj-$(CONFIG_MEMORY_ISOLATION) += page_isolation.o diff --git a/mm/backing-dev.c b/mm/backing-dev.c index 3387aea11209..6b4718e2ee34 100644 --- a/mm/backing-dev.c +++ b/mm/backing-dev.c @@ -886,3 +886,23 @@ out: return ret; } EXPORT_SYMBOL(wait_iff_congested); + +int pdflush_proc_obsolete(struct ctl_table *table, int write, + void __user *buffer, size_t *lenp, loff_t *ppos) +{ + char kbuf[] = "0\n"; + + if (*ppos) { + *lenp = 0; + return 0; + } + + if (copy_to_user(buffer, kbuf, sizeof(kbuf))) + return -EFAULT; + printk_once(KERN_WARNING "%s exported in /proc is scheduled for removal\n", + table->procname); + + *lenp = 2; + *ppos += *lenp; + return 2; +} diff --git a/mm/compaction.c b/mm/compaction.c index 2f42d9528539..e78cb9688421 100644 --- a/mm/compaction.c +++ b/mm/compaction.c @@ -422,6 +422,17 @@ static void isolate_freepages(struct zone *zone, pfn -= pageblock_nr_pages) { unsigned long isolated; + /* + * Skip ahead if another thread is compacting in the area + * simultaneously. If we wrapped around, we can only skip + * ahead if zone->compact_cached_free_pfn also wrapped to + * above our starting point. + */ + if (cc->order > 0 && (!cc->wrapped || + zone->compact_cached_free_pfn > + cc->start_free_pfn)) + pfn = min(pfn, zone->compact_cached_free_pfn); + if (!pfn_valid(pfn)) continue; @@ -461,8 +472,11 @@ static void isolate_freepages(struct zone *zone, * looking for free pages, the search will restart here as * page migration may have returned some pages to the allocator */ - if (isolated) + if (isolated) { high_pfn = max(high_pfn, pfn); + if (cc->order > 0) + zone->compact_cached_free_pfn = high_pfn; + } } /* split_free_page does not map the pages */ @@ -556,6 +570,20 @@ static isolate_migrate_t isolate_migratepages(struct zone *zone, return ISOLATE_SUCCESS; } +/* + * Returns the start pfn of the last page block in a zone. This is the starting + * point for full compaction of a zone. Compaction searches for free pages from + * the end of each zone, while isolate_freepages_block scans forward inside each + * page block. + */ +static unsigned long start_free_pfn(struct zone *zone) +{ + unsigned long free_pfn; + free_pfn = zone->zone_start_pfn + zone->spanned_pages; + free_pfn &= ~(pageblock_nr_pages-1); + return free_pfn; +} + static int compact_finished(struct zone *zone, struct compact_control *cc) { @@ -565,8 +593,26 @@ static int compact_finished(struct zone *zone, if (fatal_signal_pending(current)) return COMPACT_PARTIAL; - /* Compaction run completes if the migrate and free scanner meet */ - if (cc->free_pfn <= cc->migrate_pfn) + /* + * A full (order == -1) compaction run starts at the beginning and + * end of a zone; it completes when the migrate and free scanner meet. + * A partial (order > 0) compaction can start with the free scanner + * at a random point in the zone, and may have to restart. + */ + if (cc->free_pfn <= cc->migrate_pfn) { + if (cc->order > 0 && !cc->wrapped) { + /* We started partway through; restart at the end. */ + unsigned long free_pfn = start_free_pfn(zone); + zone->compact_cached_free_pfn = free_pfn; + cc->free_pfn = free_pfn; + cc->wrapped = 1; + return COMPACT_CONTINUE; + } + return COMPACT_COMPLETE; + } + + /* We wrapped around and ended up where we started. */ + if (cc->wrapped && cc->free_pfn <= cc->start_free_pfn) return COMPACT_COMPLETE; /* @@ -664,8 +710,15 @@ static int compact_zone(struct zone *zone, struct compact_control *cc) /* Setup to move all movable pages to the end of the zone */ cc->migrate_pfn = zone->zone_start_pfn; - cc->free_pfn = cc->migrate_pfn + zone->spanned_pages; - cc->free_pfn &= ~(pageblock_nr_pages-1); + + if (cc->order > 0) { + /* Incremental compaction. Start where the last one stopped. */ + cc->free_pfn = zone->compact_cached_free_pfn; + cc->start_free_pfn = cc->free_pfn; + } else { + /* Order == -1 starts at the end of the zone. */ + cc->free_pfn = start_free_pfn(zone); + } migrate_prep_local(); diff --git a/mm/fadvise.c b/mm/fadvise.c index 469491e0af79..9b75a045dbf4 100644 --- a/mm/fadvise.c +++ b/mm/fadvise.c @@ -93,11 +93,6 @@ SYSCALL_DEFINE(fadvise64_64)(int fd, loff_t offset, loff_t len, int advice) spin_unlock(&file->f_lock); break; case POSIX_FADV_WILLNEED: - if (!mapping->a_ops->readpage) { - ret = -EINVAL; - break; - } - /* First and last PARTIAL page! */ start_index = offset >> PAGE_CACHE_SHIFT; end_index = endbyte >> PAGE_CACHE_SHIFT; @@ -106,12 +101,13 @@ SYSCALL_DEFINE(fadvise64_64)(int fd, loff_t offset, loff_t len, int advice) nrpages = end_index - start_index + 1; if (!nrpages) nrpages = ~0UL; - - ret = force_page_cache_readahead(mapping, file, - start_index, - nrpages); - if (ret > 0) - ret = 0; + + /* + * Ignore return value because fadvise() shall return + * success even if filesystem can't retrieve a hint, + */ + force_page_cache_readahead(mapping, file, start_index, + nrpages); break; case POSIX_FADV_NOREUSE: break; diff --git a/mm/highmem.c b/mm/highmem.c index 57d82c6250c3..d517cd16a6eb 100644 --- a/mm/highmem.c +++ b/mm/highmem.c @@ -94,6 +94,18 @@ static DECLARE_WAIT_QUEUE_HEAD(pkmap_map_wait); do { spin_unlock(&kmap_lock); (void)(flags); } while (0) #endif +struct page *kmap_to_page(void *vaddr) +{ + unsigned long addr = (unsigned long)vaddr; + + if (addr >= PKMAP_ADDR(0) && addr <= PKMAP_ADDR(LAST_PKMAP)) { + int i = (addr - PKMAP_ADDR(0)) >> PAGE_SHIFT; + return pte_page(pkmap_page_table[i]); + } + + return virt_to_page(addr); +} + static void flush_all_zero_pkmaps(void) { int i; diff --git a/mm/hugetlb.c b/mm/hugetlb.c index e198831276a3..bc727122dd44 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -24,17 +24,20 @@ #include <asm/page.h> #include <asm/pgtable.h> -#include <linux/io.h> +#include <asm/tlb.h> +#include <linux/io.h> #include <linux/hugetlb.h> +#include <linux/hugetlb_cgroup.h> #include <linux/node.h> +#include <linux/hugetlb_cgroup.h> #include "internal.h" const unsigned long hugetlb_zero = 0, hugetlb_infinity = ~0UL; static gfp_t htlb_alloc_mask = GFP_HIGHUSER; unsigned long hugepages_treat_as_movable; -static int max_hstate; +int hugetlb_max_hstate __read_mostly; unsigned int default_hstate_idx; struct hstate hstates[HUGE_MAX_HSTATE]; @@ -45,13 +48,10 @@ static struct hstate * __initdata parsed_hstate; static unsigned long __initdata default_hstate_max_huge_pages; static unsigned long __initdata default_hstate_size; -#define for_each_hstate(h) \ - for ((h) = hstates; (h) < &hstates[max_hstate]; (h)++) - /* * Protects updates to hugepage_freelists, nr_huge_pages, and free_huge_pages */ -static DEFINE_SPINLOCK(hugetlb_lock); +DEFINE_SPINLOCK(hugetlb_lock); static inline void unlock_or_release_subpool(struct hugepage_subpool *spool) { @@ -509,7 +509,7 @@ void copy_huge_page(struct page *dst, struct page *src) static void enqueue_huge_page(struct hstate *h, struct page *page) { int nid = page_to_nid(page); - list_add(&page->lru, &h->hugepage_freelists[nid]); + list_move(&page->lru, &h->hugepage_freelists[nid]); h->free_huge_pages++; h->free_huge_pages_node[nid]++; } @@ -521,7 +521,7 @@ static struct page *dequeue_huge_page_node(struct hstate *h, int nid) if (list_empty(&h->hugepage_freelists[nid])) return NULL; page = list_entry(h->hugepage_freelists[nid].next, struct page, lru); - list_del(&page->lru); + list_move(&page->lru, &h->hugepage_activelist); set_page_refcounted(page); h->free_huge_pages--; h->free_huge_pages_node[nid]--; @@ -593,6 +593,7 @@ static void update_and_free_page(struct hstate *h, struct page *page) 1 << PG_active | 1 << PG_reserved | 1 << PG_private | 1 << PG_writeback); } + VM_BUG_ON(hugetlb_cgroup_from_page(page)); set_compound_page_dtor(page, NULL); set_page_refcounted(page); arch_release_hugepage(page); @@ -625,10 +626,13 @@ static void free_huge_page(struct page *page) page->mapping = NULL; BUG_ON(page_count(page)); BUG_ON(page_mapcount(page)); - INIT_LIST_HEAD(&page->lru); spin_lock(&hugetlb_lock); + hugetlb_cgroup_uncharge_page(hstate_index(h), + pages_per_huge_page(h), page); if (h->surplus_huge_pages_node[nid] && huge_page_order(h) < MAX_ORDER) { + /* remove the page from active list */ + list_del(&page->lru); update_and_free_page(h, page); h->surplus_huge_pages--; h->surplus_huge_pages_node[nid]--; @@ -641,8 +645,10 @@ static void free_huge_page(struct page *page) static void prep_new_huge_page(struct hstate *h, struct page *page, int nid) { + INIT_LIST_HEAD(&page->lru); set_compound_page_dtor(page, free_huge_page); spin_lock(&hugetlb_lock); + set_hugetlb_cgroup(page, NULL); h->nr_huge_pages++; h->nr_huge_pages_node[nid]++; spin_unlock(&hugetlb_lock); @@ -889,8 +895,10 @@ static struct page *alloc_buddy_huge_page(struct hstate *h, int nid) spin_lock(&hugetlb_lock); if (page) { + INIT_LIST_HEAD(&page->lru); r_nid = page_to_nid(page); set_compound_page_dtor(page, free_huge_page); + set_hugetlb_cgroup(page, NULL); /* * We incremented the global counters already */ @@ -993,7 +1001,6 @@ retry: list_for_each_entry_safe(page, tmp, &surplus_list, lru) { if ((--needed) < 0) break; - list_del(&page->lru); /* * This page is now managed by the hugetlb allocator and has * no users -- drop the buddy allocator's reference. @@ -1008,7 +1015,6 @@ free: /* Free unnecessary surplus pages to the buddy allocator */ if (!list_empty(&surplus_list)) { list_for_each_entry_safe(page, tmp, &surplus_list, lru) { - list_del(&page->lru); put_page(page); } } @@ -1112,7 +1118,10 @@ static struct page *alloc_huge_page(struct vm_area_struct *vma, struct hstate *h = hstate_vma(vma); struct page *page; long chg; + int ret, idx; + struct hugetlb_cgroup *h_cg; + idx = hstate_index(h); /* * Processes that did not create the mapping will have no * reserves and will not have accounted against subpool @@ -1123,27 +1132,43 @@ static struct page *alloc_huge_page(struct vm_area_struct *vma, */ chg = vma_needs_reservation(h, vma, addr); if (chg < 0) - return ERR_PTR(-VM_FAULT_OOM); + return ERR_PTR(-ENOMEM); if (chg) if (hugepage_subpool_get_pages(spool, chg)) - return ERR_PTR(-VM_FAULT_SIGBUS); + return ERR_PTR(-ENOSPC); + ret = hugetlb_cgroup_charge_cgroup(idx, pages_per_huge_page(h), &h_cg); + if (ret) { + hugepage_subpool_put_pages(spool, chg); + return ERR_PTR(-ENOSPC); + } spin_lock(&hugetlb_lock); page = dequeue_huge_page_vma(h, vma, addr, avoid_reserve); - spin_unlock(&hugetlb_lock); - - if (!page) { + if (page) { + /* update page cgroup details */ + hugetlb_cgroup_commit_charge(idx, pages_per_huge_page(h), + h_cg, page); + spin_unlock(&hugetlb_lock); + } else { + spin_unlock(&hugetlb_lock); page = alloc_buddy_huge_page(h, NUMA_NO_NODE); if (!page) { + hugetlb_cgroup_uncharge_cgroup(idx, + pages_per_huge_page(h), + h_cg); hugepage_subpool_put_pages(spool, chg); - return ERR_PTR(-VM_FAULT_SIGBUS); + return ERR_PTR(-ENOSPC); } + spin_lock(&hugetlb_lock); + hugetlb_cgroup_commit_charge(idx, pages_per_huge_page(h), + h_cg, page); + list_move(&page->lru, &h->hugepage_activelist); + spin_unlock(&hugetlb_lock); } set_page_private(page, (unsigned long)spool); vma_commit_reservation(h, vma, addr); - return page; } @@ -1646,7 +1671,7 @@ static int hugetlb_sysfs_add_hstate(struct hstate *h, struct kobject *parent, struct attribute_group *hstate_attr_group) { int retval; - int hi = h - hstates; + int hi = hstate_index(h); hstate_kobjs[hi] = kobject_create_and_add(h->name, parent); if (!hstate_kobjs[hi]) @@ -1741,11 +1766,13 @@ void hugetlb_unregister_node(struct node *node) if (!nhs->hugepages_kobj) return; /* no hstate attributes */ - for_each_hstate(h) - if (nhs->hstate_kobjs[h - hstates]) { - kobject_put(nhs->hstate_kobjs[h - hstates]); - nhs->hstate_kobjs[h - hstates] = NULL; + for_each_hstate(h) { + int idx = hstate_index(h); + if (nhs->hstate_kobjs[idx]) { + kobject_put(nhs->hstate_kobjs[idx]); + nhs->hstate_kobjs[idx] = NULL; } + } kobject_put(nhs->hugepages_kobj); nhs->hugepages_kobj = NULL; @@ -1848,7 +1875,7 @@ static void __exit hugetlb_exit(void) hugetlb_unregister_all_nodes(); for_each_hstate(h) { - kobject_put(hstate_kobjs[h - hstates]); + kobject_put(hstate_kobjs[hstate_index(h)]); } kobject_put(hugepages_kobj); @@ -1869,7 +1896,7 @@ static int __init hugetlb_init(void) if (!size_to_hstate(default_hstate_size)) hugetlb_add_hstate(HUGETLB_PAGE_ORDER); } - default_hstate_idx = size_to_hstate(default_hstate_size) - hstates; + default_hstate_idx = hstate_index(size_to_hstate(default_hstate_size)); if (default_hstate_max_huge_pages) default_hstate.max_huge_pages = default_hstate_max_huge_pages; @@ -1897,19 +1924,27 @@ void __init hugetlb_add_hstate(unsigned order) printk(KERN_WARNING "hugepagesz= specified twice, ignoring\n"); return; } - BUG_ON(max_hstate >= HUGE_MAX_HSTATE); + BUG_ON(hugetlb_max_hstate >= HUGE_MAX_HSTATE); BUG_ON(order == 0); - h = &hstates[max_hstate++]; + h = &hstates[hugetlb_max_hstate++]; h->order = order; h->mask = ~((1ULL << (order + PAGE_SHIFT)) - 1); h->nr_huge_pages = 0; h->free_huge_pages = 0; for (i = 0; i < MAX_NUMNODES; ++i) INIT_LIST_HEAD(&h->hugepage_freelists[i]); + INIT_LIST_HEAD(&h->hugepage_activelist); h->next_nid_to_alloc = first_node(node_states[N_HIGH_MEMORY]); h->next_nid_to_free = first_node(node_states[N_HIGH_MEMORY]); snprintf(h->name, HSTATE_NAME_LEN, "hugepages-%lukB", huge_page_size(h)/1024); + /* + * Add cgroup control files only if the huge page consists + * of more than two normal pages. This is because we use + * page[2].lru.next for storing cgoup details. + */ + if (order >= HUGETLB_CGROUP_MIN_ORDER) + hugetlb_cgroup_file_init(hugetlb_max_hstate - 1); parsed_hstate = h; } @@ -1920,10 +1955,10 @@ static int __init hugetlb_nrpages_setup(char *s) static unsigned long *last_mhp; /* - * !max_hstate means we haven't parsed a hugepagesz= parameter yet, + * !hugetlb_max_hstate means we haven't parsed a hugepagesz= parameter yet, * so this hugepages= parameter goes to the "default hstate". */ - if (!max_hstate) + if (!hugetlb_max_hstate) mhp = &default_hstate_max_huge_pages; else mhp = &parsed_hstate->max_huge_pages; @@ -1942,7 +1977,7 @@ static int __init hugetlb_nrpages_setup(char *s) * But we need to allocate >= MAX_ORDER hstates here early to still * use the bootmem allocator. */ - if (max_hstate && parsed_hstate->order >= MAX_ORDER) + if (hugetlb_max_hstate && parsed_hstate->order >= MAX_ORDER) hugetlb_hstate_alloc_pages(parsed_hstate); last_mhp = mhp; @@ -2308,30 +2343,26 @@ static int is_hugetlb_entry_hwpoisoned(pte_t pte) return 0; } -void __unmap_hugepage_range(struct vm_area_struct *vma, unsigned long start, - unsigned long end, struct page *ref_page) +void __unmap_hugepage_range(struct mmu_gather *tlb, struct vm_area_struct *vma, + unsigned long start, unsigned long end, + struct page *ref_page) { + int force_flush = 0; struct mm_struct *mm = vma->vm_mm; unsigned long address; pte_t *ptep; pte_t pte; struct page *page; - struct page *tmp; struct hstate *h = hstate_vma(vma); unsigned long sz = huge_page_size(h); - /* - * A page gathering list, protected by per file i_mmap_mutex. The - * lock is used to avoid list corruption from multiple unmapping - * of the same page since we are using page->lru. - */ - LIST_HEAD(page_list); - WARN_ON(!is_vm_hugetlb_page(vma)); BUG_ON(start & ~huge_page_mask(h)); BUG_ON(end & ~huge_page_mask(h)); + tlb_start_vma(tlb, vma); mmu_notifier_invalidate_range_start(mm, start, end); +again: spin_lock(&mm->page_table_lock); for (address = start; address < end; address += sz) { ptep = huge_pte_offset(mm, address); @@ -2370,30 +2401,64 @@ void __unmap_hugepage_range(struct vm_area_struct *vma, unsigned long start, } pte = huge_ptep_get_and_clear(mm, address, ptep); + tlb_remove_tlb_entry(tlb, ptep, address); if (pte_dirty(pte)) set_page_dirty(page); - list_add(&page->lru, &page_list); + page_remove_rmap(page); + force_flush = !__tlb_remove_page(tlb, page); + if (force_flush) + break; /* Bail out after unmapping reference page if supplied */ if (ref_page) break; } - flush_tlb_range(vma, start, end); spin_unlock(&mm->page_table_lock); - mmu_notifier_invalidate_range_end(mm, start, end); - list_for_each_entry_safe(page, tmp, &page_list, lru) { - page_remove_rmap(page); - list_del(&page->lru); - put_page(page); + /* + * mmu_gather ran out of room to batch pages, we break out of + * the PTE lock to avoid doing the potential expensive TLB invalidate + * and page-free while holding it. + */ + if (force_flush) { + force_flush = 0; + tlb_flush_mmu(tlb); + if (address < end && !ref_page) + goto again; } + mmu_notifier_invalidate_range_end(mm, start, end); + tlb_end_vma(tlb, vma); +} + +void __unmap_hugepage_range_final(struct mmu_gather *tlb, + struct vm_area_struct *vma, unsigned long start, + unsigned long end, struct page *ref_page) +{ + __unmap_hugepage_range(tlb, vma, start, end, ref_page); + + /* + * Clear this flag so that x86's huge_pmd_share page_table_shareable + * test will fail on a vma being torn down, and not grab a page table + * on its way out. We're lucky that the flag has such an appropriate + * name, and can in fact be safely cleared here. We could clear it + * before the __unmap_hugepage_range above, but all that's necessary + * is to clear it before releasing the i_mmap_mutex. This works + * because in the context this is called, the VMA is about to be + * destroyed and the i_mmap_mutex is held. + */ + vma->vm_flags &= ~VM_MAYSHARE; } void unmap_hugepage_range(struct vm_area_struct *vma, unsigned long start, unsigned long end, struct page *ref_page) { - mutex_lock(&vma->vm_file->f_mapping->i_mmap_mutex); - __unmap_hugepage_range(vma, start, end, ref_page); - mutex_unlock(&vma->vm_file->f_mapping->i_mmap_mutex); + struct mm_struct *mm; + struct mmu_gather tlb; + + mm = vma->vm_mm; + + tlb_gather_mmu(&tlb, mm, 0); + __unmap_hugepage_range(&tlb, vma, start, end, ref_page); + tlb_finish_mmu(&tlb, start, end); } /* @@ -2438,9 +2503,8 @@ static int unmap_ref_private(struct mm_struct *mm, struct vm_area_struct *vma, * from the time of fork. This would look like data corruption */ if (!is_vma_resv_set(iter_vma, HPAGE_RESV_OWNER)) - __unmap_hugepage_range(iter_vma, - address, address + huge_page_size(h), - page); + unmap_hugepage_range(iter_vma, address, + address + huge_page_size(h), page); } mutex_unlock(&mapping->i_mmap_mutex); @@ -2496,6 +2560,7 @@ retry_avoidcopy: new_page = alloc_huge_page(vma, address, outside_reserve); if (IS_ERR(new_page)) { + long err = PTR_ERR(new_page); page_cache_release(old_page); /* @@ -2524,7 +2589,10 @@ retry_avoidcopy: /* Caller expects lock to be held */ spin_lock(&mm->page_table_lock); - return -PTR_ERR(new_page); + if (err == -ENOMEM) + return VM_FAULT_OOM; + else + return VM_FAULT_SIGBUS; } /* @@ -2642,7 +2710,11 @@ retry: goto out; page = alloc_huge_page(vma, address, 0); if (IS_ERR(page)) { - ret = -PTR_ERR(page); + ret = PTR_ERR(page); + if (ret == -ENOMEM) + ret = VM_FAULT_OOM; + else + ret = VM_FAULT_SIGBUS; goto out; } clear_huge_page(page, address, pages_per_huge_page(h)); @@ -2679,7 +2751,7 @@ retry: */ if (unlikely(PageHWPoison(page))) { ret = VM_FAULT_HWPOISON | - VM_FAULT_SET_HINDEX(h - hstates); + VM_FAULT_SET_HINDEX(hstate_index(h)); goto backout_unlocked; } } @@ -2752,7 +2824,7 @@ int hugetlb_fault(struct mm_struct *mm, struct vm_area_struct *vma, return 0; } else if (unlikely(is_hugetlb_entry_hwpoisoned(entry))) return VM_FAULT_HWPOISON_LARGE | - VM_FAULT_SET_HINDEX(h - hstates); + VM_FAULT_SET_HINDEX(hstate_index(h)); } ptep = huge_pte_alloc(mm, address, huge_page_size(h)); @@ -2959,9 +3031,14 @@ void hugetlb_change_protection(struct vm_area_struct *vma, } } spin_unlock(&mm->page_table_lock); - mutex_unlock(&vma->vm_file->f_mapping->i_mmap_mutex); - + /* + * Must flush TLB before releasing i_mmap_mutex: x86's huge_pmd_unshare + * may have cleared our pud entry and done put_page on the page table: + * once we release i_mmap_mutex, another task can do the final put_page + * and that page table be reused and filled with junk. + */ flush_tlb_range(vma, start, end); + mutex_unlock(&vma->vm_file->f_mapping->i_mmap_mutex); } int hugetlb_reserve_pages(struct inode *inode, diff --git a/mm/hugetlb_cgroup.c b/mm/hugetlb_cgroup.c new file mode 100644 index 000000000000..a3f358fb8a0c --- /dev/null +++ b/mm/hugetlb_cgroup.c @@ -0,0 +1,418 @@ +/* + * + * Copyright IBM Corporation, 2012 + * Author Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com> + * + * This program is free software; you can redistribute it and/or modify it + * under the terms of version 2.1 of the GNU Lesser General Public License + * as published by the Free Software Foundation. + * + * This program is distributed in the hope that it would be useful, but + * WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. + * + */ + +#include <linux/cgroup.h> +#include <linux/slab.h> +#include <linux/hugetlb.h> +#include <linux/hugetlb_cgroup.h> + +struct hugetlb_cgroup { + struct cgroup_subsys_state css; + /* + * the counter to account for hugepages from hugetlb. + */ + struct res_counter hugepage[HUGE_MAX_HSTATE]; +}; + +#define MEMFILE_PRIVATE(x, val) (((x) << 16) | (val)) +#define MEMFILE_IDX(val) (((val) >> 16) & 0xffff) +#define MEMFILE_ATTR(val) ((val) & 0xffff) + +struct cgroup_subsys hugetlb_subsys __read_mostly; +static struct hugetlb_cgroup *root_h_cgroup __read_mostly; + +static inline +struct hugetlb_cgroup *hugetlb_cgroup_from_css(struct cgroup_subsys_state *s) +{ + return container_of(s, struct hugetlb_cgroup, css); +} + +static inline +struct hugetlb_cgroup *hugetlb_cgroup_from_cgroup(struct cgroup *cgroup) +{ + return hugetlb_cgroup_from_css(cgroup_subsys_state(cgroup, + hugetlb_subsys_id)); +} + +static inline +struct hugetlb_cgroup *hugetlb_cgroup_from_task(struct task_struct *task) +{ + return hugetlb_cgroup_from_css(task_subsys_state(task, + hugetlb_subsys_id)); +} + +static inline bool hugetlb_cgroup_is_root(struct hugetlb_cgroup *h_cg) +{ + return (h_cg == root_h_cgroup); +} + +static inline struct hugetlb_cgroup *parent_hugetlb_cgroup(struct cgroup *cg) +{ + if (!cg->parent) + return NULL; + return hugetlb_cgroup_from_cgroup(cg->parent); +} + +static inline bool hugetlb_cgroup_have_usage(struct cgroup *cg) +{ + int idx; + struct hugetlb_cgroup *h_cg = hugetlb_cgroup_from_cgroup(cg); + + for (idx = 0; idx < hugetlb_max_hstate; idx++) { + if ((res_counter_read_u64(&h_cg->hugepage[idx], RES_USAGE)) > 0) + return true; + } + return false; +} + +static struct cgroup_subsys_state *hugetlb_cgroup_create(struct cgroup *cgroup) +{ + int idx; + struct cgroup *parent_cgroup; + struct hugetlb_cgroup *h_cgroup, *parent_h_cgroup; + + h_cgroup = kzalloc(sizeof(*h_cgroup), GFP_KERNEL); + if (!h_cgroup) + return ERR_PTR(-ENOMEM); + + parent_cgroup = cgroup->parent; + if (parent_cgroup) { + parent_h_cgroup = hugetlb_cgroup_from_cgroup(parent_cgroup); + for (idx = 0; idx < HUGE_MAX_HSTATE; idx++) + res_counter_init(&h_cgroup->hugepage[idx], + &parent_h_cgroup->hugepage[idx]); + } else { + root_h_cgroup = h_cgroup; + for (idx = 0; idx < HUGE_MAX_HSTATE; idx++) + res_counter_init(&h_cgroup->hugepage[idx], NULL); + } + return &h_cgroup->css; +} + +static void hugetlb_cgroup_destroy(struct cgroup *cgroup) +{ + struct hugetlb_cgroup *h_cgroup; + + h_cgroup = hugetlb_cgroup_from_cgroup(cgroup); + kfree(h_cgroup); +} + + +/* + * Should be called with hugetlb_lock held. + * Since we are holding hugetlb_lock, pages cannot get moved from + * active list or uncharged from the cgroup, So no need to get + * page reference and test for page active here. This function + * cannot fail. + */ +static void hugetlb_cgroup_move_parent(int idx, struct cgroup *cgroup, + struct page *page) +{ + int csize; + struct res_counter *counter; + struct res_counter *fail_res; + struct hugetlb_cgroup *page_hcg; + struct hugetlb_cgroup *h_cg = hugetlb_cgroup_from_cgroup(cgroup); + struct hugetlb_cgroup *parent = parent_hugetlb_cgroup(cgroup); + + page_hcg = hugetlb_cgroup_from_page(page); + /* + * We can have pages in active list without any cgroup + * ie, hugepage with less than 3 pages. We can safely + * ignore those pages. + */ + if (!page_hcg || page_hcg != h_cg) + goto out; + + csize = PAGE_SIZE << compound_order(page); + if (!parent) { + parent = root_h_cgroup; + /* root has no limit */ + res_counter_charge_nofail(&parent->hugepage[idx], + csize, &fail_res); + } + counter = &h_cg->hugepage[idx]; + res_counter_uncharge_until(counter, counter->parent, csize); + + set_hugetlb_cgroup(page, parent); +out: + return; +} + +/* + * Force the hugetlb cgroup to empty the hugetlb resources by moving them to + * the parent cgroup. + */ +static int hugetlb_cgroup_pre_destroy(struct cgroup *cgroup) +{ + struct hstate *h; + struct page *page; + int ret = 0, idx = 0; + + do { + if (cgroup_task_count(cgroup) || + !list_empty(&cgroup->children)) { + ret = -EBUSY; + goto out; + } + for_each_hstate(h) { + spin_lock(&hugetlb_lock); + list_for_each_entry(page, &h->hugepage_activelist, lru) + hugetlb_cgroup_move_parent(idx, cgroup, page); + + spin_unlock(&hugetlb_lock); + idx++; + } + cond_resched(); + } while (hugetlb_cgroup_have_usage(cgroup)); +out: + return ret; +} + +int hugetlb_cgroup_charge_cgroup(int idx, unsigned long nr_pages, + struct hugetlb_cgroup **ptr) +{ + int ret = 0; + struct res_counter *fail_res; + struct hugetlb_cgroup *h_cg = NULL; + unsigned long csize = nr_pages * PAGE_SIZE; + + if (hugetlb_cgroup_disabled()) + goto done; + /* + * We don't charge any cgroup if the compound page have less + * than 3 pages. + */ + if (huge_page_order(&hstates[idx]) < HUGETLB_CGROUP_MIN_ORDER) + goto done; +again: + rcu_read_lock(); + h_cg = hugetlb_cgroup_from_task(current); + if (!css_tryget(&h_cg->css)) { + rcu_read_unlock(); + goto again; + } + rcu_read_unlock(); + + ret = res_counter_charge(&h_cg->hugepage[idx], csize, &fail_res); + css_put(&h_cg->css); +done: + *ptr = h_cg; + return ret; +} + +/* Should be called with hugetlb_lock held */ +void hugetlb_cgroup_commit_charge(int idx, unsigned long nr_pages, + struct hugetlb_cgroup *h_cg, + struct page *page) +{ + if (hugetlb_cgroup_disabled() || !h_cg) + return; + + set_hugetlb_cgroup(page, h_cg); + return; +} + +/* + * Should be called with hugetlb_lock held + */ +void hugetlb_cgroup_uncharge_page(int idx, unsigned long nr_pages, + struct page *page) +{ + struct hugetlb_cgroup *h_cg; + unsigned long csize = nr_pages * PAGE_SIZE; + + if (hugetlb_cgroup_disabled()) + return; + VM_BUG_ON(!spin_is_locked(&hugetlb_lock)); + h_cg = hugetlb_cgroup_from_page(page); + if (unlikely(!h_cg)) + return; + set_hugetlb_cgroup(page, NULL); + res_counter_uncharge(&h_cg->hugepage[idx], csize); + return; +} + +void hugetlb_cgroup_uncharge_cgroup(int idx, unsigned long nr_pages, + struct hugetlb_cgroup *h_cg) +{ + unsigned long csize = nr_pages * PAGE_SIZE; + + if (hugetlb_cgroup_disabled() || !h_cg) + return; + + if (huge_page_order(&hstates[idx]) < HUGETLB_CGROUP_MIN_ORDER) + return; + + res_counter_uncharge(&h_cg->hugepage[idx], csize); + return; +} + +static ssize_t hugetlb_cgroup_read(struct cgroup *cgroup, struct cftype *cft, + struct file *file, char __user *buf, + size_t nbytes, loff_t *ppos) +{ + u64 val; + char str[64]; + int idx, name, len; + struct hugetlb_cgroup *h_cg = hugetlb_cgroup_from_cgroup(cgroup); + + idx = MEMFILE_IDX(cft->private); + name = MEMFILE_ATTR(cft->private); + + val = res_counter_read_u64(&h_cg->hugepage[idx], name); + len = scnprintf(str, sizeof(str), "%llu\n", (unsigned long long)val); + return simple_read_from_buffer(buf, nbytes, ppos, str, len); +} + +static int hugetlb_cgroup_write(struct cgroup *cgroup, struct cftype *cft, + const char *buffer) +{ + int idx, name, ret; + unsigned long long val; + struct hugetlb_cgroup *h_cg = hugetlb_cgroup_from_cgroup(cgroup); + + idx = MEMFILE_IDX(cft->private); + name = MEMFILE_ATTR(cft->private); + + switch (name) { + case RES_LIMIT: + if (hugetlb_cgroup_is_root(h_cg)) { + /* Can't set limit on root */ + ret = -EINVAL; + break; + } + /* This function does all necessary parse...reuse it */ + ret = res_counter_memparse_write_strategy(buffer, &val); + if (ret) + break; + ret = res_counter_set_limit(&h_cg->hugepage[idx], val); + break; + default: + ret = -EINVAL; + break; + } + return ret; +} + +static int hugetlb_cgroup_reset(struct cgroup *cgroup, unsigned int event) +{ + int idx, name, ret = 0; + struct hugetlb_cgroup *h_cg = hugetlb_cgroup_from_cgroup(cgroup); + + idx = MEMFILE_IDX(event); + name = MEMFILE_ATTR(event); + + switch (name) { + case RES_MAX_USAGE: + res_counter_reset_max(&h_cg->hugepage[idx]); + break; + case RES_FAILCNT: + res_counter_reset_failcnt(&h_cg->hugepage[idx]); + break; + default: + ret = -EINVAL; + break; + } + return ret; +} + +static char *mem_fmt(char *buf, int size, unsigned long hsize) +{ + if (hsize >= (1UL << 30)) + snprintf(buf, size, "%luGB", hsize >> 30); + else if (hsize >= (1UL << 20)) + snprintf(buf, size, "%luMB", hsize >> 20); + else + snprintf(buf, size, "%luKB", hsize >> 10); + return buf; +} + +int __init hugetlb_cgroup_file_init(int idx) +{ + char buf[32]; + struct cftype *cft; + struct hstate *h = &hstates[idx]; + + /* format the size */ + mem_fmt(buf, 32, huge_page_size(h)); + + /* Add the limit file */ + cft = &h->cgroup_files[0]; + snprintf(cft->name, MAX_CFTYPE_NAME, "%s.limit_in_bytes", buf); + cft->private = MEMFILE_PRIVATE(idx, RES_LIMIT); + cft->read = hugetlb_cgroup_read; + cft->write_string = hugetlb_cgroup_write; + + /* Add the usage file */ + cft = &h->cgroup_files[1]; + snprintf(cft->name, MAX_CFTYPE_NAME, "%s.usage_in_bytes", buf); + cft->private = MEMFILE_PRIVATE(idx, RES_USAGE); + cft->read = hugetlb_cgroup_read; + + /* Add the MAX usage file */ + cft = &h->cgroup_files[2]; + snprintf(cft->name, MAX_CFTYPE_NAME, "%s.max_usage_in_bytes", buf); + cft->private = MEMFILE_PRIVATE(idx, RES_MAX_USAGE); + cft->trigger = hugetlb_cgroup_reset; + cft->read = hugetlb_cgroup_read; + + /* Add the failcntfile */ + cft = &h->cgroup_files[3]; + snprintf(cft->name, MAX_CFTYPE_NAME, "%s.failcnt", buf); + cft->private = MEMFILE_PRIVATE(idx, RES_FAILCNT); + cft->trigger = hugetlb_cgroup_reset; + cft->read = hugetlb_cgroup_read; + + /* NULL terminate the last cft */ + cft = &h->cgroup_files[4]; + memset(cft, 0, sizeof(*cft)); + + WARN_ON(cgroup_add_cftypes(&hugetlb_subsys, h->cgroup_files)); + + return 0; +} + +/* + * hugetlb_lock will make sure a parallel cgroup rmdir won't happen + * when we migrate hugepages + */ +void hugetlb_cgroup_migrate(struct page *oldhpage, struct page *newhpage) +{ + struct hugetlb_cgroup *h_cg; + struct hstate *h = page_hstate(oldhpage); + + if (hugetlb_cgroup_disabled()) + return; + + VM_BUG_ON(!PageHuge(oldhpage)); + spin_lock(&hugetlb_lock); + h_cg = hugetlb_cgroup_from_page(oldhpage); + set_hugetlb_cgroup(oldhpage, NULL); + + /* move the h_cg details to new cgroup */ + set_hugetlb_cgroup(newhpage, h_cg); + list_move(&newhpage->lru, &h->hugepage_activelist); + spin_unlock(&hugetlb_lock); + return; +} + +struct cgroup_subsys hugetlb_subsys = { + .name = "hugetlb", + .create = hugetlb_cgroup_create, + .pre_destroy = hugetlb_cgroup_pre_destroy, + .destroy = hugetlb_cgroup_destroy, + .subsys_id = hugetlb_subsys_id, +}; diff --git a/mm/hwpoison-inject.c b/mm/hwpoison-inject.c index cc448bb983ba..3a61efc518d5 100644 --- a/mm/hwpoison-inject.c +++ b/mm/hwpoison-inject.c @@ -123,7 +123,7 @@ static int pfn_inject_init(void) if (!dentry) goto fail; -#ifdef CONFIG_CGROUP_MEM_RES_CTLR_SWAP +#ifdef CONFIG_MEMCG_SWAP dentry = debugfs_create_u64("corrupt-filter-memcg", 0600, hwpoison_dir, &hwpoison_filter_memcg); if (!dentry) diff --git a/mm/internal.h b/mm/internal.h index 2ba87fbfb75b..3314f79d775a 100644 --- a/mm/internal.h +++ b/mm/internal.h @@ -118,8 +118,14 @@ struct compact_control { unsigned long nr_freepages; /* Number of isolated free pages */ unsigned long nr_migratepages; /* Number of pages to migrate */ unsigned long free_pfn; /* isolate_freepages search base */ + unsigned long start_free_pfn; /* where we started the search */ unsigned long migrate_pfn; /* isolate_migratepages search base */ bool sync; /* Synchronous migration */ + bool wrapped; /* Order > 0 compactions are + incremental, once free_pfn + and migrate_pfn meet, we restart + from the top of the zone; + remember we wrapped around. */ int order; /* order a direct compactor needs */ int migratetype; /* MOVABLE, RECLAIMABLE etc */ @@ -347,3 +353,5 @@ extern u32 hwpoison_filter_enable; extern unsigned long vm_mmap_pgoff(struct file *, unsigned long, unsigned long, unsigned long, unsigned long, unsigned long); + +extern void set_pageblock_order(void); diff --git a/mm/memblock.c b/mm/memblock.c index 5cc6731b00cc..4d9393c7edc9 100644 --- a/mm/memblock.c +++ b/mm/memblock.c @@ -222,13 +222,13 @@ static int __init_memblock memblock_double_array(struct memblock_type *type, /* Try to find some space for it. * * WARNING: We assume that either slab_is_available() and we use it or - * we use MEMBLOCK for allocations. That means that this is unsafe to use - * when bootmem is currently active (unless bootmem itself is implemented - * on top of MEMBLOCK which isn't the case yet) + * we use MEMBLOCK for allocations. That means that this is unsafe to + * use when bootmem is currently active (unless bootmem itself is + * implemented on top of MEMBLOCK which isn't the case yet) * * This should however not be an issue for now, as we currently only - * call into MEMBLOCK while it's still active, or much later when slab is - * active for memory hotplug operations + * call into MEMBLOCK while it's still active, or much later when slab + * is active for memory hotplug operations */ if (use_slab) { new_array = kmalloc(new_size, GFP_KERNEL); @@ -243,8 +243,8 @@ static int __init_memblock memblock_double_array(struct memblock_type *type, new_alloc_size, PAGE_SIZE); if (!addr && new_area_size) addr = memblock_find_in_range(0, - min(new_area_start, memblock.current_limit), - new_alloc_size, PAGE_SIZE); + min(new_area_start, memblock.current_limit), + new_alloc_size, PAGE_SIZE); new_array = addr ? __va(addr) : 0; } @@ -254,12 +254,14 @@ static int __init_memblock memblock_double_array(struct memblock_type *type, return -1; } - memblock_dbg("memblock: %s array is doubled to %ld at [%#010llx-%#010llx]", - memblock_type_name(type), type->max * 2, (u64)addr, (u64)addr + new_size - 1); + memblock_dbg("memblock: %s is doubled to %ld at [%#010llx-%#010llx]", + memblock_type_name(type), type->max * 2, (u64)addr, + (u64)addr + new_size - 1); - /* Found space, we now need to move the array over before - * we add the reserved region since it may be our reserved - * array itself that is full. + /* + * Found space, we now need to move the array over before we add the + * reserved region since it may be our reserved array itself that is + * full. */ memcpy(new_array, type->regions, old_size); memset(new_array + type->max, 0, old_size); @@ -267,17 +269,16 @@ static int __init_memblock memblock_double_array(struct memblock_type *type, type->regions = new_array; type->max <<= 1; - /* Free old array. We needn't free it if the array is the - * static one - */ + /* Free old array. We needn't free it if the array is the static one */ if (*in_slab) kfree(old_array); else if (old_array != memblock_memory_init_regions && old_array != memblock_reserved_init_regions) memblock_free(__pa(old_array), old_alloc_size); - /* Reserve the new array if that comes from the memblock. - * Otherwise, we needn't do it + /* + * Reserve the new array if that comes from the memblock. Otherwise, we + * needn't do it */ if (!use_slab) BUG_ON(memblock_reserve(addr, new_alloc_size)); diff --git a/mm/memcontrol.c b/mm/memcontrol.c index f72b5e52451a..795e525afaba 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -61,12 +61,12 @@ struct cgroup_subsys mem_cgroup_subsys __read_mostly; #define MEM_CGROUP_RECLAIM_RETRIES 5 static struct mem_cgroup *root_mem_cgroup __read_mostly; -#ifdef CONFIG_CGROUP_MEM_RES_CTLR_SWAP +#ifdef CONFIG_MEMCG_SWAP /* Turned on only when memory cgroup is enabled && really_do_swap_account = 1 */ int do_swap_account __read_mostly; /* for remember boot option*/ -#ifdef CONFIG_CGROUP_MEM_RES_CTLR_SWAP_ENABLED +#ifdef CONFIG_MEMCG_SWAP_ENABLED static int really_do_swap_account __initdata = 1; #else static int really_do_swap_account __initdata = 0; @@ -87,7 +87,7 @@ enum mem_cgroup_stat_index { MEM_CGROUP_STAT_CACHE, /* # of pages charged as cache */ MEM_CGROUP_STAT_RSS, /* # of pages charged as anon rss */ MEM_CGROUP_STAT_FILE_MAPPED, /* # of pages charged as file rss */ - MEM_CGROUP_STAT_SWAPOUT, /* # of pages, swapped out */ + MEM_CGROUP_STAT_SWAP, /* # of pages, swapped out */ MEM_CGROUP_STAT_NSTATS, }; @@ -378,9 +378,7 @@ static bool move_file(void) enum charge_type { MEM_CGROUP_CHARGE_TYPE_CACHE = 0, - MEM_CGROUP_CHARGE_TYPE_MAPPED, - MEM_CGROUP_CHARGE_TYPE_SHMEM, /* used by page migration of shmem */ - MEM_CGROUP_CHARGE_TYPE_FORCE, /* used by force_empty */ + MEM_CGROUP_CHARGE_TYPE_ANON, MEM_CGROUP_CHARGE_TYPE_SWAPOUT, /* for accounting swapcache */ MEM_CGROUP_CHARGE_TYPE_DROP, /* a page was unused swap cache */ NR_CHARGE_TYPE, @@ -407,8 +405,14 @@ enum charge_type { static void mem_cgroup_get(struct mem_cgroup *memcg); static void mem_cgroup_put(struct mem_cgroup *memcg); +static inline +struct mem_cgroup *mem_cgroup_from_css(struct cgroup_subsys_state *s) +{ + return container_of(s, struct mem_cgroup, css); +} + /* Writing them here to avoid exposing memcg's inner layout */ -#ifdef CONFIG_CGROUP_MEM_RES_CTLR_KMEM +#ifdef CONFIG_MEMCG_KMEM #include <net/sock.h> #include <net/ip.h> @@ -467,9 +471,9 @@ struct cg_proto *tcp_proto_cgroup(struct mem_cgroup *memcg) } EXPORT_SYMBOL(tcp_proto_cgroup); #endif /* CONFIG_INET */ -#endif /* CONFIG_CGROUP_MEM_RES_CTLR_KMEM */ +#endif /* CONFIG_MEMCG_KMEM */ -#if defined(CONFIG_INET) && defined(CONFIG_CGROUP_MEM_RES_CTLR_KMEM) +#if defined(CONFIG_INET) && defined(CONFIG_MEMCG_KMEM) static void disarm_sock_keys(struct mem_cgroup *memcg) { if (!memcg_proto_activated(&memcg->tcp_mem.cg_proto)) @@ -703,7 +707,7 @@ static void mem_cgroup_swap_statistics(struct mem_cgroup *memcg, bool charge) { int val = (charge) ? 1 : -1; - this_cpu_add(memcg->stat->count[MEM_CGROUP_STAT_SWAPOUT], val); + this_cpu_add(memcg->stat->count[MEM_CGROUP_STAT_SWAP], val); } static unsigned long mem_cgroup_read_events(struct mem_cgroup *memcg, @@ -864,9 +868,8 @@ static void memcg_check_events(struct mem_cgroup *memcg, struct page *page) struct mem_cgroup *mem_cgroup_from_cont(struct cgroup *cont) { - return container_of(cgroup_subsys_state(cont, - mem_cgroup_subsys_id), struct mem_cgroup, - css); + return mem_cgroup_from_css( + cgroup_subsys_state(cont, mem_cgroup_subsys_id)); } struct mem_cgroup *mem_cgroup_from_task(struct task_struct *p) @@ -879,8 +882,7 @@ struct mem_cgroup *mem_cgroup_from_task(struct task_struct *p) if (unlikely(!p)) return NULL; - return container_of(task_subsys_state(p, mem_cgroup_subsys_id), - struct mem_cgroup, css); + return mem_cgroup_from_css(task_subsys_state(p, mem_cgroup_subsys_id)); } struct mem_cgroup *try_get_mem_cgroup_from_mm(struct mm_struct *mm) @@ -966,8 +968,7 @@ struct mem_cgroup *mem_cgroup_iter(struct mem_cgroup *root, css = css_get_next(&mem_cgroup_subsys, id + 1, &root->css, &id); if (css) { if (css == &root->css || css_tryget(css)) - memcg = container_of(css, - struct mem_cgroup, css); + memcg = mem_cgroup_from_css(css); } else id = 0; rcu_read_unlock(); @@ -1454,7 +1455,7 @@ static int mem_cgroup_count_children(struct mem_cgroup *memcg) /* * Return the memory (and swap, if configured) limit for a memcg. */ -u64 mem_cgroup_get_limit(struct mem_cgroup *memcg) +static u64 mem_cgroup_get_limit(struct mem_cgroup *memcg) { u64 limit; u64 memsw; @@ -1470,6 +1471,73 @@ u64 mem_cgroup_get_limit(struct mem_cgroup *memcg) return min(limit, memsw); } +void mem_cgroup_out_of_memory(struct mem_cgroup *memcg, gfp_t gfp_mask, + int order) +{ + struct mem_cgroup *iter; + unsigned long chosen_points = 0; + unsigned long totalpages; + unsigned int points = 0; + struct task_struct *chosen = NULL; + + /* + * If current has a pending SIGKILL, then automatically select it. The + * goal is to allow it to allocate so that it may quickly exit and free + * its memory. + */ + if (fatal_signal_pending(current)) { + set_thread_flag(TIF_MEMDIE); + return; + } + + check_panic_on_oom(CONSTRAINT_MEMCG, gfp_mask, order, NULL); + totalpages = mem_cgroup_get_limit(memcg) >> PAGE_SHIFT ? : 1; + for_each_mem_cgroup_tree(iter, memcg) { + struct cgroup *cgroup = iter->css.cgroup; + struct cgroup_iter it; + struct task_struct *task; + + cgroup_iter_start(cgroup, &it); + while ((task = cgroup_iter_next(cgroup, &it))) { + switch (oom_scan_process_thread(task, totalpages, NULL, + false)) { + case OOM_SCAN_SELECT: + if (chosen) + put_task_struct(chosen); + chosen = task; + chosen_points = ULONG_MAX; + get_task_struct(chosen); + /* fall through */ + case OOM_SCAN_CONTINUE: + continue; + case OOM_SCAN_ABORT: + cgroup_iter_end(cgroup, &it); + mem_cgroup_iter_break(memcg, iter); + if (chosen) + put_task_struct(chosen); + return; + case OOM_SCAN_OK: + break; + }; + points = oom_badness(task, memcg, NULL, totalpages); + if (points > chosen_points) { + if (chosen) + put_task_struct(chosen); + chosen = task; + chosen_points = points; + get_task_struct(chosen); + } + } + cgroup_iter_end(cgroup, &it); + } + + if (!chosen) + return; + points = chosen_points * 1000 / totalpages; + oom_kill_process(chosen, gfp_mask, order, points, totalpages, memcg, + NULL, "Memory cgroup out of memory"); +} + static unsigned long mem_cgroup_reclaim(struct mem_cgroup *memcg, gfp_t gfp_mask, unsigned long flags) @@ -1899,7 +1967,7 @@ again: return; /* * If this memory cgroup is not under account moving, we don't - * need to take move_lock_page_cgroup(). Because we already hold + * need to take move_lock_mem_cgroup(). Because we already hold * rcu_read_lock(), any calls to move_account will be delayed until * rcu_read_unlock() if mem_cgroup_stolen() == true. */ @@ -1921,7 +1989,7 @@ void __mem_cgroup_end_update_page_stat(struct page *page, unsigned long *flags) /* * It's guaranteed that pc->mem_cgroup never changes while * lock is held because a routine modifies pc->mem_cgroup - * should take move_lock_page_cgroup(). + * should take move_lock_mem_cgroup(). */ move_unlock_mem_cgroup(pc->mem_cgroup, flags); } @@ -2268,7 +2336,7 @@ static int __mem_cgroup_try_charge(struct mm_struct *mm, * We always charge the cgroup the mm_struct belongs to. * The mm_struct's mem_cgroup changes on task migration if the * thread group leader migrates. It's possible that mm is not - * set, if so charge the init_mm (happens for pagecache usage). + * set, if so charge the root memcg (happens for pagecache usage). */ if (!*ptr && !mm) *ptr = root_mem_cgroup; @@ -2429,7 +2497,7 @@ static struct mem_cgroup *mem_cgroup_lookup(unsigned short id) css = css_lookup(&mem_cgroup_subsys, id); if (!css) return NULL; - return container_of(css, struct mem_cgroup, css); + return mem_cgroup_from_css(css); } struct mem_cgroup *try_get_mem_cgroup_from_page(struct page *page) @@ -2473,11 +2541,7 @@ static void __mem_cgroup_commit_charge(struct mem_cgroup *memcg, bool anon; lock_page_cgroup(pc); - if (unlikely(PageCgroupUsed(pc))) { - unlock_page_cgroup(pc); - __mem_cgroup_cancel_charge(memcg, nr_pages); - return; - } + VM_BUG_ON(PageCgroupUsed(pc)); /* * we don't need page_cgroup_lock about tail pages, becase they are not * accessed by any other context at this point. @@ -2519,7 +2583,7 @@ static void __mem_cgroup_commit_charge(struct mem_cgroup *memcg, spin_unlock_irq(&zone->lru_lock); } - if (ctype == MEM_CGROUP_CHARGE_TYPE_MAPPED) + if (ctype == MEM_CGROUP_CHARGE_TYPE_ANON) anon = true; else anon = false; @@ -2644,8 +2708,7 @@ out: static int mem_cgroup_move_parent(struct page *page, struct page_cgroup *pc, - struct mem_cgroup *child, - gfp_t gfp_mask) + struct mem_cgroup *child) { struct mem_cgroup *parent; unsigned int nr_pages; @@ -2728,38 +2791,7 @@ int mem_cgroup_newpage_charge(struct page *page, VM_BUG_ON(page->mapping && !PageAnon(page)); VM_BUG_ON(!mm); return mem_cgroup_charge_common(page, mm, gfp_mask, - MEM_CGROUP_CHARGE_TYPE_MAPPED); -} - -static void -__mem_cgroup_commit_charge_swapin(struct page *page, struct mem_cgroup *ptr, - enum charge_type ctype); - -int mem_cgroup_cache_charge(struct page *page, struct mm_struct *mm, - gfp_t gfp_mask) -{ - struct mem_cgroup *memcg = NULL; - enum charge_type type = MEM_CGROUP_CHARGE_TYPE_CACHE; - int ret; - - if (mem_cgroup_disabled()) - return 0; - if (PageCompound(page)) - return 0; - - if (unlikely(!mm)) - mm = &init_mm; - if (!page_is_file_cache(page)) - type = MEM_CGROUP_CHARGE_TYPE_SHMEM; - - if (!PageSwapCache(page)) - ret = mem_cgroup_charge_common(page, mm, gfp_mask, type); - else { /* page is swapcache/shmem */ - ret = mem_cgroup_try_charge_swapin(mm, page, gfp_mask, &memcg); - if (!ret) - __mem_cgroup_commit_charge_swapin(page, memcg, type); - } - return ret; + MEM_CGROUP_CHARGE_TYPE_ANON); } /* @@ -2768,27 +2800,26 @@ int mem_cgroup_cache_charge(struct page *page, struct mm_struct *mm, * struct page_cgroup is acquired. This refcnt will be consumed by * "commit()" or removed by "cancel()" */ -int mem_cgroup_try_charge_swapin(struct mm_struct *mm, - struct page *page, - gfp_t mask, struct mem_cgroup **memcgp) +static int __mem_cgroup_try_charge_swapin(struct mm_struct *mm, + struct page *page, + gfp_t mask, + struct mem_cgroup **memcgp) { struct mem_cgroup *memcg; + struct page_cgroup *pc; int ret; - *memcgp = NULL; - - if (mem_cgroup_disabled()) - return 0; - - if (!do_swap_account) - goto charge_cur_mm; + pc = lookup_page_cgroup(page); /* - * A racing thread's fault, or swapoff, may have already updated - * the pte, and even removed page from swap cache: in those cases - * do_swap_page()'s pte_same() test will fail; but there's also a - * KSM case which does need to charge the page. + * Every swap fault against a single page tries to charge the + * page, bail as early as possible. shmem_unuse() encounters + * already charged pages, too. The USED bit is protected by + * the page lock, which serializes swap cache removal, which + * in turn serializes uncharging. */ - if (!PageSwapCache(page)) + if (PageCgroupUsed(pc)) + return 0; + if (!do_swap_account) goto charge_cur_mm; memcg = try_get_mem_cgroup_from_page(page); if (!memcg) @@ -2800,14 +2831,44 @@ int mem_cgroup_try_charge_swapin(struct mm_struct *mm, ret = 0; return ret; charge_cur_mm: - if (unlikely(!mm)) - mm = &init_mm; ret = __mem_cgroup_try_charge(mm, mask, 1, memcgp, true); if (ret == -EINTR) ret = 0; return ret; } +int mem_cgroup_try_charge_swapin(struct mm_struct *mm, struct page *page, + gfp_t gfp_mask, struct mem_cgroup **memcgp) +{ + *memcgp = NULL; + if (mem_cgroup_disabled()) + return 0; + /* + * A racing thread's fault, or swapoff, may have already + * updated the pte, and even removed page from swap cache: in + * those cases unuse_pte()'s pte_same() test will fail; but + * there's also a KSM case which does need to charge the page. + */ + if (!PageSwapCache(page)) { + int ret; + + ret = __mem_cgroup_try_charge(mm, gfp_mask, 1, memcgp, true); + if (ret == -EINTR) + ret = 0; + return ret; + } + return __mem_cgroup_try_charge_swapin(mm, page, gfp_mask, memcgp); +} + +void mem_cgroup_cancel_charge_swapin(struct mem_cgroup *memcg) +{ + if (mem_cgroup_disabled()) + return; + if (!memcg) + return; + __mem_cgroup_cancel_charge(memcg, 1); +} + static void __mem_cgroup_commit_charge_swapin(struct page *page, struct mem_cgroup *memcg, enum charge_type ctype) @@ -2842,16 +2903,30 @@ void mem_cgroup_commit_charge_swapin(struct page *page, struct mem_cgroup *memcg) { __mem_cgroup_commit_charge_swapin(page, memcg, - MEM_CGROUP_CHARGE_TYPE_MAPPED); + MEM_CGROUP_CHARGE_TYPE_ANON); } -void mem_cgroup_cancel_charge_swapin(struct mem_cgroup *memcg) +int mem_cgroup_cache_charge(struct page *page, struct mm_struct *mm, + gfp_t gfp_mask) { + struct mem_cgroup *memcg = NULL; + enum charge_type type = MEM_CGROUP_CHARGE_TYPE_CACHE; + int ret; + if (mem_cgroup_disabled()) - return; - if (!memcg) - return; - __mem_cgroup_cancel_charge(memcg, 1); + return 0; + if (PageCompound(page)) + return 0; + + if (!PageSwapCache(page)) + ret = mem_cgroup_charge_common(page, mm, gfp_mask, type); + else { /* page is swapcache/shmem */ + ret = __mem_cgroup_try_charge_swapin(mm, page, + gfp_mask, &memcg); + if (!ret) + __mem_cgroup_commit_charge_swapin(page, memcg, type); + } + return ret; } static void mem_cgroup_do_uncharge(struct mem_cgroup *memcg, @@ -2911,7 +2986,8 @@ direct_uncharge: * uncharge if !page_mapped(page) */ static struct mem_cgroup * -__mem_cgroup_uncharge_common(struct page *page, enum charge_type ctype) +__mem_cgroup_uncharge_common(struct page *page, enum charge_type ctype, + bool end_migration) { struct mem_cgroup *memcg = NULL; unsigned int nr_pages = 1; @@ -2921,8 +2997,7 @@ __mem_cgroup_uncharge_common(struct page *page, enum charge_type ctype) if (mem_cgroup_disabled()) return NULL; - if (PageSwapCache(page)) - return NULL; + VM_BUG_ON(PageSwapCache(page)); if (PageTransHuge(page)) { nr_pages <<= compound_order(page); @@ -2945,7 +3020,7 @@ __mem_cgroup_uncharge_common(struct page *page, enum charge_type ctype) anon = PageAnon(page); switch (ctype) { - case MEM_CGROUP_CHARGE_TYPE_MAPPED: + case MEM_CGROUP_CHARGE_TYPE_ANON: /* * Generally PageAnon tells if it's the anon statistics to be * updated; but sometimes e.g. mem_cgroup_uncharge_page() is @@ -2955,7 +3030,16 @@ __mem_cgroup_uncharge_common(struct page *page, enum charge_type ctype) /* fallthrough */ case MEM_CGROUP_CHARGE_TYPE_DROP: /* See mem_cgroup_prepare_migration() */ - if (page_mapped(page) || PageCgroupMigration(pc)) + if (page_mapped(page)) + goto unlock_out; + /* + * Pages under migration may not be uncharged. But + * end_migration() /must/ be the one uncharging the + * unused post-migration page and so it has to call + * here with the migration bit still set. See the + * res_counter handling below. + */ + if (!end_migration && PageCgroupMigration(pc)) goto unlock_out; break; case MEM_CGROUP_CHARGE_TYPE_SWAPOUT: @@ -2989,7 +3073,12 @@ __mem_cgroup_uncharge_common(struct page *page, enum charge_type ctype) mem_cgroup_swap_statistics(memcg, true); mem_cgroup_get(memcg); } - if (!mem_cgroup_is_root(memcg)) + /* + * Migration does not charge the res_counter for the + * replacement page, so leave it alone when phasing out the + * page that is unused after the migration. + */ + if (!end_migration && !mem_cgroup_is_root(memcg)) mem_cgroup_do_uncharge(memcg, nr_pages, ctype); return memcg; @@ -3005,14 +3094,16 @@ void mem_cgroup_uncharge_page(struct page *page) if (page_mapped(page)) return; VM_BUG_ON(page->mapping && !PageAnon(page)); - __mem_cgroup_uncharge_common(page, MEM_CGROUP_CHARGE_TYPE_MAPPED); + if (PageSwapCache(page)) + return; + __mem_cgroup_uncharge_common(page, MEM_CGROUP_CHARGE_TYPE_ANON, false); } void mem_cgroup_uncharge_cache_page(struct page *page) { VM_BUG_ON(page_mapped(page)); VM_BUG_ON(page->mapping); - __mem_cgroup_uncharge_common(page, MEM_CGROUP_CHARGE_TYPE_CACHE); + __mem_cgroup_uncharge_common(page, MEM_CGROUP_CHARGE_TYPE_CACHE, false); } /* @@ -3076,7 +3167,7 @@ mem_cgroup_uncharge_swapcache(struct page *page, swp_entry_t ent, bool swapout) if (!swapout) /* this was a swap cache but the swap is unused ! */ ctype = MEM_CGROUP_CHARGE_TYPE_DROP; - memcg = __mem_cgroup_uncharge_common(page, ctype); + memcg = __mem_cgroup_uncharge_common(page, ctype, false); /* * record memcg information, if swapout && memcg != NULL, @@ -3087,7 +3178,7 @@ mem_cgroup_uncharge_swapcache(struct page *page, swp_entry_t ent, bool swapout) } #endif -#ifdef CONFIG_CGROUP_MEM_RES_CTLR_SWAP +#ifdef CONFIG_MEMCG_SWAP /* * called from swap_entry_free(). remove record in swap_cgroup and * uncharge "memsw" account. @@ -3166,19 +3257,18 @@ static inline int mem_cgroup_move_swap_account(swp_entry_t entry, * Before starting migration, account PAGE_SIZE to mem_cgroup that the old * page belongs to. */ -int mem_cgroup_prepare_migration(struct page *page, - struct page *newpage, struct mem_cgroup **memcgp, gfp_t gfp_mask) +void mem_cgroup_prepare_migration(struct page *page, struct page *newpage, + struct mem_cgroup **memcgp) { struct mem_cgroup *memcg = NULL; struct page_cgroup *pc; enum charge_type ctype; - int ret = 0; *memcgp = NULL; VM_BUG_ON(PageTransHuge(page)); if (mem_cgroup_disabled()) - return 0; + return; pc = lookup_page_cgroup(page); lock_page_cgroup(pc); @@ -3223,24 +3313,9 @@ int mem_cgroup_prepare_migration(struct page *page, * we return here. */ if (!memcg) - return 0; + return; *memcgp = memcg; - ret = __mem_cgroup_try_charge(NULL, gfp_mask, 1, memcgp, false); - css_put(&memcg->css);/* drop extra refcnt */ - if (ret) { - if (PageAnon(page)) { - lock_page_cgroup(pc); - ClearPageCgroupMigration(pc); - unlock_page_cgroup(pc); - /* - * The old page may be fully unmapped while we kept it. - */ - mem_cgroup_uncharge_page(page); - } - /* we'll need to revisit this error code (we have -EINTR) */ - return -ENOMEM; - } /* * We charge new page before it's used/mapped. So, even if unlock_page() * is called before end_migration, we can catch all events on this new @@ -3248,13 +3323,15 @@ int mem_cgroup_prepare_migration(struct page *page, * mapcount will be finally 0 and we call uncharge in end_migration(). */ if (PageAnon(page)) - ctype = MEM_CGROUP_CHARGE_TYPE_MAPPED; - else if (page_is_file_cache(page)) - ctype = MEM_CGROUP_CHARGE_TYPE_CACHE; + ctype = MEM_CGROUP_CHARGE_TYPE_ANON; else - ctype = MEM_CGROUP_CHARGE_TYPE_SHMEM; + ctype = MEM_CGROUP_CHARGE_TYPE_CACHE; + /* + * The page is committed to the memcg, but it's not actually + * charged to the res_counter since we plan on replacing the + * old one and only one page is going to be left afterwards. + */ __mem_cgroup_commit_charge(memcg, newpage, 1, ctype, false); - return ret; } /* remove redundant charge if migration failed*/ @@ -3276,6 +3353,12 @@ void mem_cgroup_end_migration(struct mem_cgroup *memcg, used = newpage; unused = oldpage; } + anon = PageAnon(used); + __mem_cgroup_uncharge_common(unused, + anon ? MEM_CGROUP_CHARGE_TYPE_ANON + : MEM_CGROUP_CHARGE_TYPE_CACHE, + true); + css_put(&memcg->css); /* * We disallowed uncharge of pages under migration because mapcount * of the page goes down to zero, temporarly. @@ -3285,10 +3368,6 @@ void mem_cgroup_end_migration(struct mem_cgroup *memcg, lock_page_cgroup(pc); ClearPageCgroupMigration(pc); unlock_page_cgroup(pc); - anon = PageAnon(used); - __mem_cgroup_uncharge_common(unused, - anon ? MEM_CGROUP_CHARGE_TYPE_MAPPED - : MEM_CGROUP_CHARGE_TYPE_CACHE); /* * If a page is a file cache, radix-tree replacement is very atomic @@ -3340,10 +3419,6 @@ void mem_cgroup_replace_page_cache(struct page *oldpage, */ if (!memcg) return; - - if (PageSwapBacked(oldpage)) - type = MEM_CGROUP_CHARGE_TYPE_SHMEM; - /* * Even if newpage->mapping was NULL before starting replacement, * the newpage may be on LRU(or pagevec for LRU) already. We lock @@ -3418,7 +3493,7 @@ static int mem_cgroup_resize_limit(struct mem_cgroup *memcg, /* * Rather than hide all in some function, I do this in * open coded manner. You see what this really does. - * We have to guarantee memcg->res.limit < memcg->memsw.limit. + * We have to guarantee memcg->res.limit <= memcg->memsw.limit. */ mutex_lock(&set_limit_mutex); memswlimit = res_counter_read_u64(&memcg->memsw, RES_LIMIT); @@ -3479,7 +3554,7 @@ static int mem_cgroup_resize_memsw_limit(struct mem_cgroup *memcg, /* * Rather than hide all in some function, I do this in * open coded manner. You see what this really does. - * We have to guarantee memcg->res.limit < memcg->memsw.limit. + * We have to guarantee memcg->res.limit <= memcg->memsw.limit. */ mutex_lock(&set_limit_mutex); memlimit = res_counter_read_u64(&memcg->res, RES_LIMIT); @@ -3611,10 +3686,12 @@ unsigned long mem_cgroup_soft_limit_reclaim(struct zone *zone, int order, } /* - * This routine traverse page_cgroup in given list and drop them all. - * *And* this routine doesn't reclaim page itself, just removes page_cgroup. + * Traverse a specified page_cgroup list and try to drop them all. This doesn't + * reclaim the pages page themselves - it just removes the page_cgroups. + * Returns true if some page_cgroups were not freed, indicating that the caller + * must retry this operation. */ -static int mem_cgroup_force_empty_list(struct mem_cgroup *memcg, +static bool mem_cgroup_force_empty_list(struct mem_cgroup *memcg, int node, int zid, enum lru_list lru) { struct mem_cgroup_per_zone *mz; @@ -3622,7 +3699,6 @@ static int mem_cgroup_force_empty_list(struct mem_cgroup *memcg, struct list_head *list; struct page *busy; struct zone *zone; - int ret = 0; zone = &NODE_DATA(node)->node_zones[zid]; mz = mem_cgroup_zoneinfo(memcg, node, zid); @@ -3636,7 +3712,6 @@ static int mem_cgroup_force_empty_list(struct mem_cgroup *memcg, struct page_cgroup *pc; struct page *page; - ret = 0; spin_lock_irqsave(&zone->lru_lock, flags); if (list_empty(list)) { spin_unlock_irqrestore(&zone->lru_lock, flags); @@ -3653,21 +3728,14 @@ static int mem_cgroup_force_empty_list(struct mem_cgroup *memcg, pc = lookup_page_cgroup(page); - ret = mem_cgroup_move_parent(page, pc, memcg, GFP_KERNEL); - if (ret == -ENOMEM || ret == -EINTR) - break; - - if (ret == -EBUSY || ret == -EINVAL) { + if (mem_cgroup_move_parent(page, pc, memcg)) { /* found lock contention or "pc" is obsolete. */ busy = page; cond_resched(); } else busy = NULL; } - - if (!ret && !list_empty(list)) - return -EBUSY; - return ret; + return !list_empty(list); } /* @@ -3692,9 +3760,6 @@ move_account: ret = -EBUSY; if (cgroup_task_count(cgrp) || !list_empty(&cgrp->children)) goto out; - ret = -EINTR; - if (signal_pending(current)) - goto out; /* This is for making all *used* pages to be on LRU. */ lru_add_drain_all(); drain_all_stock_sync(memcg); @@ -3715,9 +3780,6 @@ move_account: } mem_cgroup_end_move(memcg); memcg_oom_recover(memcg); - /* it seems parent cgroup doesn't have enough mem */ - if (ret == -ENOMEM) - goto try_to_free; cond_resched(); /* "ret" should also be checked to ensure all lists are empty. */ } while (res_counter_read_u64(&memcg->res, RES_USAGE) > 0 || ret); @@ -3779,6 +3841,10 @@ static int mem_cgroup_hierarchy_write(struct cgroup *cont, struct cftype *cft, parent_memcg = mem_cgroup_from_cont(parent); cgroup_lock(); + + if (memcg->use_hierarchy == val) + goto out; + /* * If parent's use_hierarchy is set, we can't make any modifications * in the child subtrees. If it is unset, then the change can @@ -3795,6 +3861,8 @@ static int mem_cgroup_hierarchy_write(struct cgroup *cont, struct cftype *cft, retval = -EBUSY; } else retval = -EINVAL; + +out: cgroup_unlock(); return retval; @@ -3831,7 +3899,7 @@ static inline u64 mem_cgroup_usage(struct mem_cgroup *memcg, bool swap) val += mem_cgroup_recursive_stat(memcg, MEM_CGROUP_STAT_RSS); if (swap) - val += mem_cgroup_recursive_stat(memcg, MEM_CGROUP_STAT_SWAPOUT); + val += mem_cgroup_recursive_stat(memcg, MEM_CGROUP_STAT_SWAP); return val << PAGE_SHIFT; } @@ -4015,7 +4083,7 @@ static int mem_cgroup_move_charge_write(struct cgroup *cgrp, #endif #ifdef CONFIG_NUMA -static int mem_control_numa_stat_show(struct cgroup *cont, struct cftype *cft, +static int memcg_numa_stat_show(struct cgroup *cont, struct cftype *cft, struct seq_file *m) { int nid; @@ -4074,7 +4142,7 @@ static inline void mem_cgroup_lru_names_not_uptodate(void) BUILD_BUG_ON(ARRAY_SIZE(mem_cgroup_lru_names) != NR_LRU_LISTS); } -static int mem_control_stat_show(struct cgroup *cont, struct cftype *cft, +static int memcg_stat_show(struct cgroup *cont, struct cftype *cft, struct seq_file *m) { struct mem_cgroup *memcg = mem_cgroup_from_cont(cont); @@ -4082,7 +4150,7 @@ static int mem_control_stat_show(struct cgroup *cont, struct cftype *cft, unsigned int i; for (i = 0; i < MEM_CGROUP_STAT_NSTATS; i++) { - if (i == MEM_CGROUP_STAT_SWAPOUT && !do_swap_account) + if (i == MEM_CGROUP_STAT_SWAP && !do_swap_account) continue; seq_printf(m, "%s %ld\n", mem_cgroup_stat_names[i], mem_cgroup_read_stat(memcg, i) * PAGE_SIZE); @@ -4109,7 +4177,7 @@ static int mem_control_stat_show(struct cgroup *cont, struct cftype *cft, for (i = 0; i < MEM_CGROUP_STAT_NSTATS; i++) { long long val = 0; - if (i == MEM_CGROUP_STAT_SWAPOUT && !do_swap_account) + if (i == MEM_CGROUP_STAT_SWAP && !do_swap_account) continue; for_each_mem_cgroup_tree(mi, memcg) val += mem_cgroup_read_stat(mi, i) * PAGE_SIZE; @@ -4533,7 +4601,7 @@ static int mem_cgroup_oom_control_write(struct cgroup *cgrp, return 0; } -#ifdef CONFIG_CGROUP_MEM_RES_CTLR_KMEM +#ifdef CONFIG_MEMCG_KMEM static int memcg_init_kmem(struct mem_cgroup *memcg, struct cgroup_subsys *ss) { return mem_cgroup_sockets_init(memcg, ss); @@ -4588,7 +4656,7 @@ static struct cftype mem_cgroup_files[] = { }, { .name = "stat", - .read_seq_string = mem_control_stat_show, + .read_seq_string = memcg_stat_show, }, { .name = "force_empty", @@ -4620,10 +4688,10 @@ static struct cftype mem_cgroup_files[] = { #ifdef CONFIG_NUMA { .name = "numa_stat", - .read_seq_string = mem_control_numa_stat_show, + .read_seq_string = memcg_numa_stat_show, }, #endif -#ifdef CONFIG_CGROUP_MEM_RES_CTLR_SWAP +#ifdef CONFIG_MEMCG_SWAP { .name = "memsw.usage_in_bytes", .private = MEMFILE_PRIVATE(_MEMSWAP, RES_USAGE), @@ -4810,7 +4878,7 @@ struct mem_cgroup *parent_mem_cgroup(struct mem_cgroup *memcg) } EXPORT_SYMBOL(parent_mem_cgroup); -#ifdef CONFIG_CGROUP_MEM_RES_CTLR_SWAP +#ifdef CONFIG_MEMCG_SWAP static void __init enable_swap_cgroup(void) { if (!mem_cgroup_disabled() && really_do_swap_account) @@ -5541,7 +5609,7 @@ struct cgroup_subsys mem_cgroup_subsys = { .__DEPRECATED_clear_css_refs = true, }; -#ifdef CONFIG_CGROUP_MEM_RES_CTLR_SWAP +#ifdef CONFIG_MEMCG_SWAP static int __init enable_swap_account(char *s) { /* consider enabled if no parameter or 1 is given */ diff --git a/mm/memory-failure.c b/mm/memory-failure.c index 6de0d613bbe6..a6e2141a6610 100644 --- a/mm/memory-failure.c +++ b/mm/memory-failure.c @@ -128,7 +128,7 @@ static int hwpoison_filter_flags(struct page *p) * can only guarantee that the page either belongs to the memcg tasks, or is * a freed page. */ -#ifdef CONFIG_CGROUP_MEM_RES_CTLR_SWAP +#ifdef CONFIG_MEMCG_SWAP u64 hwpoison_filter_memcg; EXPORT_SYMBOL_GPL(hwpoison_filter_memcg); static int hwpoison_filter_task(struct page *p) @@ -1416,7 +1416,6 @@ static int soft_offline_huge_page(struct page *page, int flags) int ret; unsigned long pfn = page_to_pfn(page); struct page *hpage = compound_head(page); - LIST_HEAD(pagelist); ret = get_any_page(page, pfn, flags); if (ret < 0) @@ -1431,24 +1430,18 @@ static int soft_offline_huge_page(struct page *page, int flags) } /* Keep page count to indicate a given hugepage is isolated. */ - - list_add(&hpage->lru, &pagelist); - ret = migrate_huge_pages(&pagelist, new_page, MPOL_MF_MOVE_ALL, false, + ret = migrate_huge_page(hpage, new_page, MPOL_MF_MOVE_ALL, false, MIGRATE_SYNC); + put_page(hpage); if (ret) { - struct page *page1, *page2; - list_for_each_entry_safe(page1, page2, &pagelist, lru) - put_page(page1); - pr_info("soft offline: %#lx: migration failed %d, type %lx\n", pfn, ret, page->flags); - if (ret > 0) - ret = -EIO; return ret; } done: if (!PageHWPoison(hpage)) - atomic_long_add(1 << compound_trans_order(hpage), &mce_bad_pages); + atomic_long_add(1 << compound_trans_order(hpage), + &mce_bad_pages); set_page_hwpoison_huge_page(hpage); dequeue_hwpoisoned_huge_page(hpage); /* keep elevated page count for bad page */ diff --git a/mm/memory.c b/mm/memory.c index 91f69459d3e8..482f089765ff 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -1343,8 +1343,11 @@ static void unmap_single_vma(struct mmu_gather *tlb, * Since no pte has actually been setup, it is * safe to do nothing in this case. */ - if (vma->vm_file) - unmap_hugepage_range(vma, start, end, NULL); + if (vma->vm_file) { + mutex_lock(&vma->vm_file->f_mapping->i_mmap_mutex); + __unmap_hugepage_range_final(tlb, vma, start, end, NULL); + mutex_unlock(&vma->vm_file->f_mapping->i_mmap_mutex); + } } else unmap_page_range(tlb, vma, start, end, details); } @@ -3938,7 +3941,7 @@ void print_vma_addr(char *prefix, unsigned long ip) free_page((unsigned long)buf); } } - up_read(¤t->mm->mmap_sem); + up_read(&mm->mmap_sem); } #ifdef CONFIG_PROVE_LOCKING diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c index 427bb291dd0f..3ad25f9d1fc1 100644 --- a/mm/memory_hotplug.c +++ b/mm/memory_hotplug.c @@ -512,19 +512,20 @@ int __ref online_pages(unsigned long pfn, unsigned long nr_pages) zone->present_pages += onlined_pages; zone->zone_pgdat->node_present_pages += onlined_pages; - if (need_zonelists_rebuild) - build_all_zonelists(zone); - else - zone_pcp_update(zone); + if (onlined_pages) { + node_set_state(zone_to_nid(zone), N_HIGH_MEMORY); + if (need_zonelists_rebuild) + build_all_zonelists(NULL, zone); + else + zone_pcp_update(zone); + } mutex_unlock(&zonelists_mutex); init_per_zone_wmark_min(); - if (onlined_pages) { + if (onlined_pages) kswapd_run(zone_to_nid(zone)); - node_set_state(zone_to_nid(zone), N_HIGH_MEMORY); - } vm_total_pages = nr_free_pagecache_pages(); @@ -562,7 +563,7 @@ static pg_data_t __ref *hotadd_new_pgdat(int nid, u64 start) * to access not-initialized zonelist, build here. */ mutex_lock(&zonelists_mutex); - build_all_zonelists(NULL); + build_all_zonelists(pgdat, NULL); mutex_unlock(&zonelists_mutex); return pgdat; @@ -965,6 +966,9 @@ repeat: init_per_zone_wmark_min(); + if (!populated_zone(zone)) + zone_pcp_reset(zone); + if (!node_present_pages(node)) { node_clear_state(node, N_HIGH_MEMORY); kswapd_stop(node); diff --git a/mm/migrate.c b/mm/migrate.c index be26d5cbe56b..77ed2d773705 100644 --- a/mm/migrate.c +++ b/mm/migrate.c @@ -33,6 +33,7 @@ #include <linux/memcontrol.h> #include <linux/syscalls.h> #include <linux/hugetlb.h> +#include <linux/hugetlb_cgroup.h> #include <linux/gfp.h> #include <asm/tlbflush.h> @@ -682,7 +683,6 @@ static int __unmap_and_move(struct page *page, struct page *newpage, { int rc = -EAGAIN; int remap_swapcache = 1; - int charge = 0; struct mem_cgroup *mem; struct anon_vma *anon_vma = NULL; @@ -724,12 +724,7 @@ static int __unmap_and_move(struct page *page, struct page *newpage, } /* charge against new page */ - charge = mem_cgroup_prepare_migration(page, newpage, &mem, GFP_KERNEL); - if (charge == -ENOMEM) { - rc = -ENOMEM; - goto unlock; - } - BUG_ON(charge); + mem_cgroup_prepare_migration(page, newpage, &mem); if (PageWriteback(page)) { /* @@ -819,8 +814,7 @@ skip_unmap: put_anon_vma(anon_vma); uncharge: - if (!charge) - mem_cgroup_end_migration(mem, page, newpage, rc == 0); + mem_cgroup_end_migration(mem, page, newpage, rc == 0); unlock: unlock_page(page); out: @@ -931,16 +925,13 @@ static int unmap_and_move_huge_page(new_page_t get_new_page, if (anon_vma) put_anon_vma(anon_vma); - unlock_page(hpage); -out: - if (rc != -EAGAIN) { - list_del(&hpage->lru); - put_page(hpage); - } + if (!rc) + hugetlb_cgroup_migrate(hpage, new_hpage); + unlock_page(hpage); +out: put_page(new_hpage); - if (result) { if (rc) *result = rc; @@ -1016,48 +1007,32 @@ out: return nr_failed + retry; } -int migrate_huge_pages(struct list_head *from, - new_page_t get_new_page, unsigned long private, bool offlining, - enum migrate_mode mode) +int migrate_huge_page(struct page *hpage, new_page_t get_new_page, + unsigned long private, bool offlining, + enum migrate_mode mode) { - int retry = 1; - int nr_failed = 0; - int pass = 0; - struct page *page; - struct page *page2; - int rc; - - for (pass = 0; pass < 10 && retry; pass++) { - retry = 0; - - list_for_each_entry_safe(page, page2, from, lru) { + int pass, rc; + + for (pass = 0; pass < 10; pass++) { + rc = unmap_and_move_huge_page(get_new_page, + private, hpage, pass > 2, offlining, + mode); + switch (rc) { + case -ENOMEM: + goto out; + case -EAGAIN: + /* try again */ cond_resched(); - - rc = unmap_and_move_huge_page(get_new_page, - private, page, pass > 2, offlining, - mode); - - switch(rc) { - case -ENOMEM: - goto out; - case -EAGAIN: - retry++; - break; - case 0: - break; - default: - /* Permanent failure */ - nr_failed++; - break; - } + break; + case 0: + goto out; + default: + rc = -EIO; + goto out; } } - rc = 0; out: - if (rc) - return rc; - - return nr_failed + retry; + return rc; } #ifdef CONFIG_NUMA diff --git a/mm/mmap.c b/mm/mmap.c index 4fe2697339ed..e3e86914f11a 100644 --- a/mm/mmap.c +++ b/mm/mmap.c @@ -943,6 +943,8 @@ void vm_stat_account(struct mm_struct *mm, unsigned long flags, const unsigned long stack_flags = VM_STACK_FLAGS & (VM_GROWSUP|VM_GROWSDOWN); + mm->total_vm += pages; + if (file) { mm->shared_vm += pages; if ((flags & (VM_EXEC|VM_WRITE)) == VM_EXEC) @@ -1347,7 +1349,6 @@ munmap_back: out: perf_event_mmap(vma); - mm->total_vm += len >> PAGE_SHIFT; vm_stat_account(mm, vm_flags, file, len >> PAGE_SHIFT); if (vm_flags & VM_LOCKED) { if (!mlock_vma_pages_range(vma, addr, addr + len)) @@ -1707,7 +1708,6 @@ static int acct_stack_growth(struct vm_area_struct *vma, unsigned long size, uns return -ENOMEM; /* Ok, everything looks good - let it rip */ - mm->total_vm += grow; if (vma->vm_flags & VM_LOCKED) mm->locked_vm += grow; vm_stat_account(mm, vma->vm_flags, vma->vm_file, grow); @@ -1889,7 +1889,6 @@ static void remove_vma_list(struct mm_struct *mm, struct vm_area_struct *vma) if (vma->vm_flags & VM_ACCOUNT) nr_accounted += nrpages; - mm->total_vm -= nrpages; vm_stat_account(mm, vma->vm_flags, vma->vm_file, -nrpages); vma = remove_vma(vma); } while (vma); diff --git a/mm/mmu_notifier.c b/mm/mmu_notifier.c index 9a611d3a1848..862b60822d9f 100644 --- a/mm/mmu_notifier.c +++ b/mm/mmu_notifier.c @@ -33,6 +33,24 @@ void __mmu_notifier_release(struct mm_struct *mm) { struct mmu_notifier *mn; + struct hlist_node *n; + + /* + * RCU here will block mmu_notifier_unregister until + * ->release returns. + */ + rcu_read_lock(); + hlist_for_each_entry_rcu(mn, n, &mm->mmu_notifier_mm->list, hlist) + /* + * if ->release runs before mmu_notifier_unregister it + * must be handled as it's the only way for the driver + * to flush all existing sptes and stop the driver + * from establishing any more sptes before all the + * pages in the mm are freed. + */ + if (mn->ops->release) + mn->ops->release(mn, mm); + rcu_read_unlock(); spin_lock(&mm->mmu_notifier_mm->lock); while (unlikely(!hlist_empty(&mm->mmu_notifier_mm->list))) { @@ -46,23 +64,6 @@ void __mmu_notifier_release(struct mm_struct *mm) * mmu_notifier_unregister to return. */ hlist_del_init_rcu(&mn->hlist); - /* - * RCU here will block mmu_notifier_unregister until - * ->release returns. - */ - rcu_read_lock(); - spin_unlock(&mm->mmu_notifier_mm->lock); - /* - * if ->release runs before mmu_notifier_unregister it - * must be handled as it's the only way for the driver - * to flush all existing sptes and stop the driver - * from establishing any more sptes before all the - * pages in the mm are freed. - */ - if (mn->ops->release) - mn->ops->release(mn, mm); - rcu_read_unlock(); - spin_lock(&mm->mmu_notifier_mm->lock); } spin_unlock(&mm->mmu_notifier_mm->lock); @@ -284,16 +285,13 @@ void mmu_notifier_unregister(struct mmu_notifier *mn, struct mm_struct *mm) { BUG_ON(atomic_read(&mm->mm_count) <= 0); - spin_lock(&mm->mmu_notifier_mm->lock); if (!hlist_unhashed(&mn->hlist)) { - hlist_del_rcu(&mn->hlist); - /* * RCU here will force exit_mmap to wait ->release to finish * before freeing the pages. */ rcu_read_lock(); - spin_unlock(&mm->mmu_notifier_mm->lock); + /* * exit_mmap will block in mmu_notifier_release to * guarantee ->release is called before freeing the @@ -302,8 +300,11 @@ void mmu_notifier_unregister(struct mmu_notifier *mn, struct mm_struct *mm) if (mn->ops->release) mn->ops->release(mn, mm); rcu_read_unlock(); - } else + + spin_lock(&mm->mmu_notifier_mm->lock); + hlist_del_rcu(&mn->hlist); spin_unlock(&mm->mmu_notifier_mm->lock); + } /* * Wait any running method to finish, of course including diff --git a/mm/mmzone.c b/mm/mmzone.c index 6830eab5bf09..3cef80f6ac79 100644 --- a/mm/mmzone.c +++ b/mm/mmzone.c @@ -96,7 +96,7 @@ void lruvec_init(struct lruvec *lruvec, struct zone *zone) for_each_lru(lru) INIT_LIST_HEAD(&lruvec->lists[lru]); -#ifdef CONFIG_CGROUP_MEM_RES_CTLR +#ifdef CONFIG_MEMCG lruvec->zone = zone; #endif } diff --git a/mm/mremap.c b/mm/mremap.c index 21fed202ddad..cc06d0e48d05 100644 --- a/mm/mremap.c +++ b/mm/mremap.c @@ -260,7 +260,6 @@ static unsigned long move_vma(struct vm_area_struct *vma, * If this were a serious issue, we'd add a flag to do_munmap(). */ hiwater_vm = mm->hiwater_vm; - mm->total_vm += new_len >> PAGE_SHIFT; vm_stat_account(mm, vma->vm_flags, vma->vm_file, new_len>>PAGE_SHIFT); if (do_munmap(mm, old_addr, old_len) < 0) { @@ -497,7 +496,6 @@ SYSCALL_DEFINE5(mremap, unsigned long, addr, unsigned long, old_len, goto out; } - mm->total_vm += pages; vm_stat_account(mm, vma->vm_flags, vma->vm_file, pages); if (vma->vm_flags & VM_LOCKED) { mm->locked_vm += pages; diff --git a/mm/oom_kill.c b/mm/oom_kill.c index ac300c99baf6..198600861638 100644 --- a/mm/oom_kill.c +++ b/mm/oom_kill.c @@ -288,76 +288,93 @@ static enum oom_constraint constrained_alloc(struct zonelist *zonelist, } #endif +enum oom_scan_t oom_scan_process_thread(struct task_struct *task, + unsigned long totalpages, const nodemask_t *nodemask, + bool force_kill) +{ + if (task->exit_state) + return OOM_SCAN_CONTINUE; + if (oom_unkillable_task(task, NULL, nodemask)) + return OOM_SCAN_CONTINUE; + + /* + * This task already has access to memory reserves and is being killed. + * Don't allow any other task to have access to the reserves. + */ + if (test_tsk_thread_flag(task, TIF_MEMDIE)) { + if (unlikely(frozen(task))) + __thaw_task(task); + if (!force_kill) + return OOM_SCAN_ABORT; + } + if (!task->mm) + return OOM_SCAN_CONTINUE; + + if (task->flags & PF_EXITING) { + /* + * If task is current and is in the process of releasing memory, + * allow the "kill" to set TIF_MEMDIE, which will allow it to + * access memory reserves. Otherwise, it may stall forever. + * + * The iteration isn't broken here, however, in case other + * threads are found to have already been oom killed. + */ + if (task == current) + return OOM_SCAN_SELECT; + else if (!force_kill) { + /* + * If this task is not being ptraced on exit, then wait + * for it to finish before killing some other task + * unnecessarily. + */ + if (!(task->group_leader->ptrace & PT_TRACE_EXIT)) + return OOM_SCAN_ABORT; + } + } + return OOM_SCAN_OK; +} + /* * Simple selection loop. We chose the process with the highest - * number of 'points'. We expect the caller will lock the tasklist. + * number of 'points'. * * (not docbooked, we don't want this one cluttering up the manual) */ static struct task_struct *select_bad_process(unsigned int *ppoints, - unsigned long totalpages, struct mem_cgroup *memcg, - const nodemask_t *nodemask, bool force_kill) + unsigned long totalpages, const nodemask_t *nodemask, + bool force_kill) { struct task_struct *g, *p; struct task_struct *chosen = NULL; unsigned long chosen_points = 0; + rcu_read_lock(); do_each_thread(g, p) { unsigned int points; - if (p->exit_state) - continue; - if (oom_unkillable_task(p, memcg, nodemask)) - continue; - - /* - * This task already has access to memory reserves and is - * being killed. Don't allow any other task access to the - * memory reserve. - * - * Note: this may have a chance of deadlock if it gets - * blocked waiting for another task which itself is waiting - * for memory. Is there a better alternative? - */ - if (test_tsk_thread_flag(p, TIF_MEMDIE)) { - if (unlikely(frozen(p))) - __thaw_task(p); - if (!force_kill) - return ERR_PTR(-1UL); - } - if (!p->mm) + switch (oom_scan_process_thread(p, totalpages, nodemask, + force_kill)) { + case OOM_SCAN_SELECT: + chosen = p; + chosen_points = ULONG_MAX; + /* fall through */ + case OOM_SCAN_CONTINUE: continue; - - if (p->flags & PF_EXITING) { - /* - * If p is the current task and is in the process of - * releasing memory, we allow the "kill" to set - * TIF_MEMDIE, which will allow it to gain access to - * memory reserves. Otherwise, it may stall forever. - * - * The loop isn't broken here, however, in case other - * threads are found to have already been oom killed. - */ - if (p == current) { - chosen = p; - chosen_points = ULONG_MAX; - } else if (!force_kill) { - /* - * If this task is not being ptraced on exit, - * then wait for it to finish before killing - * some other task unnecessarily. - */ - if (!(p->group_leader->ptrace & PT_TRACE_EXIT)) - return ERR_PTR(-1UL); - } - } - - points = oom_badness(p, memcg, nodemask, totalpages); + case OOM_SCAN_ABORT: + rcu_read_unlock(); + return ERR_PTR(-1UL); + case OOM_SCAN_OK: + break; + }; + points = oom_badness(p, NULL, nodemask, totalpages); if (points > chosen_points) { chosen = p; chosen_points = points; } } while_each_thread(g, p); + if (chosen) + get_task_struct(chosen); + rcu_read_unlock(); *ppoints = chosen_points * 1000 / totalpages; return chosen; @@ -371,17 +388,16 @@ static struct task_struct *select_bad_process(unsigned int *ppoints, * Dumps the current memory state of all eligible tasks. Tasks not in the same * memcg, not in the same cpuset, or bound to a disjoint set of mempolicy nodes * are not shown. - * State information includes task's pid, uid, tgid, vm size, rss, cpu, oom_adj - * value, oom_score_adj value, and name. - * - * Call with tasklist_lock read-locked. + * State information includes task's pid, uid, tgid, vm size, rss, nr_ptes, + * swapents, oom_score_adj value, and name. */ static void dump_tasks(const struct mem_cgroup *memcg, const nodemask_t *nodemask) { struct task_struct *p; struct task_struct *task; - pr_info("[ pid ] uid tgid total_vm rss cpu oom_adj oom_score_adj name\n"); + pr_info("[ pid ] uid tgid total_vm rss nr_ptes swapents oom_score_adj name\n"); + rcu_read_lock(); for_each_process(p) { if (oom_unkillable_task(p, memcg, nodemask)) continue; @@ -396,13 +412,15 @@ static void dump_tasks(const struct mem_cgroup *memcg, const nodemask_t *nodemas continue; } - pr_info("[%5d] %5d %5d %8lu %8lu %3u %3d %5d %s\n", + pr_info("[%5d] %5d %5d %8lu %8lu %7lu %8lu %5d %s\n", task->pid, from_kuid(&init_user_ns, task_uid(task)), task->tgid, task->mm->total_vm, get_mm_rss(task->mm), - task_cpu(task), task->signal->oom_adj, + task->mm->nr_ptes, + get_mm_counter(task->mm, MM_SWAPENTS), task->signal->oom_score_adj, task->comm); task_unlock(task); } + rcu_read_unlock(); } static void dump_header(struct task_struct *p, gfp_t gfp_mask, int order, @@ -423,10 +441,14 @@ static void dump_header(struct task_struct *p, gfp_t gfp_mask, int order, } #define K(x) ((x) << (PAGE_SHIFT-10)) -static void oom_kill_process(struct task_struct *p, gfp_t gfp_mask, int order, - unsigned int points, unsigned long totalpages, - struct mem_cgroup *memcg, nodemask_t *nodemask, - const char *message) +/* + * Must be called while holding a reference to p, which will be released upon + * returning. + */ +void oom_kill_process(struct task_struct *p, gfp_t gfp_mask, int order, + unsigned int points, unsigned long totalpages, + struct mem_cgroup *memcg, nodemask_t *nodemask, + const char *message) { struct task_struct *victim = p; struct task_struct *child; @@ -442,6 +464,7 @@ static void oom_kill_process(struct task_struct *p, gfp_t gfp_mask, int order, */ if (p->flags & PF_EXITING) { set_tsk_thread_flag(p, TIF_MEMDIE); + put_task_struct(p); return; } @@ -459,6 +482,7 @@ static void oom_kill_process(struct task_struct *p, gfp_t gfp_mask, int order, * parent. This attempts to lose the minimal amount of work done while * still freeing memory. */ + read_lock(&tasklist_lock); do { list_for_each_entry(child, &t->children, sibling) { unsigned int child_points; @@ -471,15 +495,26 @@ static void oom_kill_process(struct task_struct *p, gfp_t gfp_mask, int order, child_points = oom_badness(child, memcg, nodemask, totalpages); if (child_points > victim_points) { + put_task_struct(victim); victim = child; victim_points = child_points; + get_task_struct(victim); } } } while_each_thread(p, t); + read_unlock(&tasklist_lock); - victim = find_lock_task_mm(victim); - if (!victim) + rcu_read_lock(); + p = find_lock_task_mm(victim); + if (!p) { + rcu_read_unlock(); + put_task_struct(victim); return; + } else if (victim != p) { + get_task_struct(p); + put_task_struct(victim); + victim = p; + } /* mm cannot safely be dereferenced after task_unlock(victim) */ mm = victim->mm; @@ -510,17 +545,19 @@ static void oom_kill_process(struct task_struct *p, gfp_t gfp_mask, int order, task_unlock(p); do_send_sig_info(SIGKILL, SEND_SIG_FORCED, p, true); } + rcu_read_unlock(); set_tsk_thread_flag(victim, TIF_MEMDIE); do_send_sig_info(SIGKILL, SEND_SIG_FORCED, victim, true); + put_task_struct(victim); } #undef K /* * Determines whether the kernel must panic because of the panic_on_oom sysctl. */ -static void check_panic_on_oom(enum oom_constraint constraint, gfp_t gfp_mask, - int order, const nodemask_t *nodemask) +void check_panic_on_oom(enum oom_constraint constraint, gfp_t gfp_mask, + int order, const nodemask_t *nodemask) { if (likely(!sysctl_panic_on_oom)) return; @@ -533,42 +570,11 @@ static void check_panic_on_oom(enum oom_constraint constraint, gfp_t gfp_mask, if (constraint != CONSTRAINT_NONE) return; } - read_lock(&tasklist_lock); dump_header(NULL, gfp_mask, order, NULL, nodemask); - read_unlock(&tasklist_lock); panic("Out of memory: %s panic_on_oom is enabled\n", sysctl_panic_on_oom == 2 ? "compulsory" : "system-wide"); } -#ifdef CONFIG_CGROUP_MEM_RES_CTLR -void mem_cgroup_out_of_memory(struct mem_cgroup *memcg, gfp_t gfp_mask, - int order) -{ - unsigned long limit; - unsigned int points = 0; - struct task_struct *p; - - /* - * If current has a pending SIGKILL, then automatically select it. The - * goal is to allow it to allocate so that it may quickly exit and free - * its memory. - */ - if (fatal_signal_pending(current)) { - set_thread_flag(TIF_MEMDIE); - return; - } - - check_panic_on_oom(CONSTRAINT_MEMCG, gfp_mask, order, NULL); - limit = mem_cgroup_get_limit(memcg) >> PAGE_SHIFT ? : 1; - read_lock(&tasklist_lock); - p = select_bad_process(&points, limit, memcg, NULL, false); - if (p && PTR_ERR(p) != -1UL) - oom_kill_process(p, gfp_mask, order, points, limit, memcg, NULL, - "Memory cgroup out of memory"); - read_unlock(&tasklist_lock); -} -#endif - static BLOCKING_NOTIFIER_HEAD(oom_notify_list); int register_oom_notifier(struct notifier_block *nb) @@ -690,7 +696,7 @@ void out_of_memory(struct zonelist *zonelist, gfp_t gfp_mask, struct task_struct *p; unsigned long totalpages; unsigned long freed = 0; - unsigned int points; + unsigned int uninitialized_var(points); enum oom_constraint constraint = CONSTRAINT_NONE; int killed = 0; @@ -718,22 +724,20 @@ void out_of_memory(struct zonelist *zonelist, gfp_t gfp_mask, mpol_mask = (constraint == CONSTRAINT_MEMORY_POLICY) ? nodemask : NULL; check_panic_on_oom(constraint, gfp_mask, order, mpol_mask); - read_lock(&tasklist_lock); - if (sysctl_oom_kill_allocating_task && + if (sysctl_oom_kill_allocating_task && current->mm && !oom_unkillable_task(current, NULL, nodemask) && - current->mm) { + current->signal->oom_score_adj != OOM_SCORE_ADJ_MIN) { + get_task_struct(current); oom_kill_process(current, gfp_mask, order, 0, totalpages, NULL, nodemask, "Out of memory (oom_kill_allocating_task)"); goto out; } - p = select_bad_process(&points, totalpages, NULL, mpol_mask, - force_kill); + p = select_bad_process(&points, totalpages, mpol_mask, force_kill); /* Found nothing?!?! Either we hang forever, or we panic. */ if (!p) { dump_header(NULL, gfp_mask, order, NULL, mpol_mask); - read_unlock(&tasklist_lock); panic("Out of memory and no killable processes...\n"); } if (PTR_ERR(p) != -1UL) { @@ -742,14 +746,12 @@ void out_of_memory(struct zonelist *zonelist, gfp_t gfp_mask, killed = 1; } out: - read_unlock(&tasklist_lock); - /* - * Give "p" a good chance of killing itself before we - * retry to allocate memory unless "p" is current + * Give the killed threads a good chance of exiting before trying to + * allocate memory again. */ - if (killed && !test_thread_flag(TIF_MEMDIE)) - schedule_timeout_uninterruptible(1); + if (killed) + schedule_timeout_killable(1); } /* @@ -764,6 +766,5 @@ void pagefault_out_of_memory(void) out_of_memory(NULL, 0, 0, NULL, false); clear_system_oom(); } - if (!test_thread_flag(TIF_MEMDIE)) - schedule_timeout_uninterruptible(1); + schedule_timeout_killable(1); } diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 4a4f9219683f..889532b8e6c1 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -51,7 +51,6 @@ #include <linux/page_cgroup.h> #include <linux/debugobjects.h> #include <linux/kmemleak.h> -#include <linux/memory.h> #include <linux/compaction.h> #include <trace/events/kmem.h> #include <linux/ftrace_event.h> @@ -219,7 +218,12 @@ EXPORT_SYMBOL(nr_online_nodes); int page_group_by_mobility_disabled __read_mostly; -static void set_pageblock_migratetype(struct page *page, int migratetype) +/* + * NOTE: + * Don't use set_pageblock_migratetype(page, MIGRATE_ISOLATE) directly. + * Instead, use {un}set_pageblock_isolate. + */ +void set_pageblock_migratetype(struct page *page, int migratetype) { if (unlikely(page_group_by_mobility_disabled)) @@ -954,7 +958,7 @@ static int move_freepages(struct zone *zone, return pages_moved; } -static int move_freepages_block(struct zone *zone, struct page *page, +int move_freepages_block(struct zone *zone, struct page *page, int migratetype) { unsigned long start_pfn, end_pfn; @@ -1158,8 +1162,10 @@ void drain_zone_pages(struct zone *zone, struct per_cpu_pages *pcp) to_drain = pcp->batch; else to_drain = pcp->count; - free_pcppages_bulk(zone, to_drain, pcp); - pcp->count -= to_drain; + if (to_drain > 0) { + free_pcppages_bulk(zone, to_drain, pcp); + pcp->count -= to_drain; + } local_irq_restore(flags); } #endif @@ -1529,16 +1535,16 @@ static int __init setup_fail_page_alloc(char *str) } __setup("fail_page_alloc=", setup_fail_page_alloc); -static int should_fail_alloc_page(gfp_t gfp_mask, unsigned int order) +static bool should_fail_alloc_page(gfp_t gfp_mask, unsigned int order) { if (order < fail_page_alloc.min_order) - return 0; + return false; if (gfp_mask & __GFP_NOFAIL) - return 0; + return false; if (fail_page_alloc.ignore_gfp_highmem && (gfp_mask & __GFP_HIGHMEM)) - return 0; + return false; if (fail_page_alloc.ignore_gfp_wait && (gfp_mask & __GFP_WAIT)) - return 0; + return false; return should_fail(&fail_page_alloc.attr, 1 << order); } @@ -1578,9 +1584,9 @@ late_initcall(fail_page_alloc_debugfs); #else /* CONFIG_FAIL_PAGE_ALLOC */ -static inline int should_fail_alloc_page(gfp_t gfp_mask, unsigned int order) +static inline bool should_fail_alloc_page(gfp_t gfp_mask, unsigned int order) { - return 0; + return false; } #endif /* CONFIG_FAIL_PAGE_ALLOC */ @@ -1594,6 +1600,7 @@ static bool __zone_watermark_ok(struct zone *z, int order, unsigned long mark, { /* free_pages my go negative - that's OK */ long min = mark; + long lowmem_reserve = z->lowmem_reserve[classzone_idx]; int o; free_pages -= (1 << order) - 1; @@ -1602,7 +1609,7 @@ static bool __zone_watermark_ok(struct zone *z, int order, unsigned long mark, if (alloc_flags & ALLOC_HARDER) min -= min / 4; - if (free_pages <= min + z->lowmem_reserve[classzone_idx]) + if (free_pages <= min + lowmem_reserve) return false; for (o = 0; o < order; o++) { /* At the next order, this order's pages become unavailable */ @@ -1617,6 +1624,20 @@ static bool __zone_watermark_ok(struct zone *z, int order, unsigned long mark, return true; } +#ifdef CONFIG_MEMORY_ISOLATION +static inline unsigned long nr_zone_isolate_freepages(struct zone *zone) +{ + if (unlikely(zone->nr_pageblock_isolate)) + return zone->nr_pageblock_isolate * pageblock_nr_pages; + return 0; +} +#else +static inline unsigned long nr_zone_isolate_freepages(struct zone *zone) +{ + return 0; +} +#endif + bool zone_watermark_ok(struct zone *z, int order, unsigned long mark, int classzone_idx, int alloc_flags) { @@ -1632,6 +1653,14 @@ bool zone_watermark_ok_safe(struct zone *z, int order, unsigned long mark, if (z->percpu_drift_mark && free_pages < z->percpu_drift_mark) free_pages = zone_page_state_snapshot(z, NR_FREE_PAGES); + /* + * If the zone has MIGRATE_ISOLATE type free pages, we should consider + * it. nr_zone_isolate_freepages is never accurate so kswapd might not + * sleep although it could do so. But this is more desirable for memory + * hotplug than sleeping which can cause a livelock in the direct + * reclaim path. + */ + free_pages -= nr_zone_isolate_freepages(z); return __zone_watermark_ok(z, order, mark, classzone_idx, alloc_flags, free_pages); } @@ -2087,8 +2116,8 @@ __alloc_pages_direct_compact(gfp_t gfp_mask, unsigned int order, page = get_page_from_freelist(gfp_mask, nodemask, order, zonelist, high_zoneidx, - alloc_flags, preferred_zone, - migratetype); + alloc_flags & ~ALLOC_NO_WATERMARKS, + preferred_zone, migratetype); if (page) { preferred_zone->compact_considered = 0; preferred_zone->compact_defer_shift = 0; @@ -2180,8 +2209,8 @@ __alloc_pages_direct_reclaim(gfp_t gfp_mask, unsigned int order, retry: page = get_page_from_freelist(gfp_mask, nodemask, order, zonelist, high_zoneidx, - alloc_flags, preferred_zone, - migratetype); + alloc_flags & ~ALLOC_NO_WATERMARKS, + preferred_zone, migratetype); /* * If an allocation failed after direct reclaim, it could be because @@ -2265,15 +2294,24 @@ gfp_to_alloc_flags(gfp_t gfp_mask) alloc_flags |= ALLOC_HARDER; if (likely(!(gfp_mask & __GFP_NOMEMALLOC))) { - if (!in_interrupt() && - ((current->flags & PF_MEMALLOC) || - unlikely(test_thread_flag(TIF_MEMDIE)))) + if (gfp_mask & __GFP_MEMALLOC) + alloc_flags |= ALLOC_NO_WATERMARKS; + else if (in_serving_softirq() && (current->flags & PF_MEMALLOC)) + alloc_flags |= ALLOC_NO_WATERMARKS; + else if (!in_interrupt() && + ((current->flags & PF_MEMALLOC) || + unlikely(test_thread_flag(TIF_MEMDIE)))) alloc_flags |= ALLOC_NO_WATERMARKS; } return alloc_flags; } +bool gfp_pfmemalloc_allowed(gfp_t gfp_mask) +{ + return !!(gfp_to_alloc_flags(gfp_mask) & ALLOC_NO_WATERMARKS); +} + static inline struct page * __alloc_pages_slowpath(gfp_t gfp_mask, unsigned int order, struct zonelist *zonelist, enum zone_type high_zoneidx, @@ -2340,11 +2378,27 @@ rebalance: /* Allocate without watermarks if the context allows */ if (alloc_flags & ALLOC_NO_WATERMARKS) { + /* + * Ignore mempolicies if ALLOC_NO_WATERMARKS on the grounds + * the allocation is high priority and these type of + * allocations are system rather than user orientated + */ + zonelist = node_zonelist(numa_node_id(), gfp_mask); + page = __alloc_pages_high_priority(gfp_mask, order, zonelist, high_zoneidx, nodemask, preferred_zone, migratetype); - if (page) + if (page) { + /* + * page->pfmemalloc is set when ALLOC_NO_WATERMARKS was + * necessary to allocate the page. The expectation is + * that the caller is taking steps that will free more + * memory. The caller should avoid the page being used + * for !PFMEMALLOC purposes. + */ + page->pfmemalloc = true; goto got_pg; + } } /* Atomic allocations - we can't balance anything */ @@ -2463,8 +2517,8 @@ nopage: got_pg: if (kmemcheck_enabled) kmemcheck_pagealloc_alloc(page, order, gfp_mask); - return page; + return page; } /* @@ -2515,6 +2569,8 @@ retry_cpuset: page = __alloc_pages_slowpath(gfp_mask, order, zonelist, high_zoneidx, nodemask, preferred_zone, migratetype); + else + page->pfmemalloc = false; trace_mm_page_alloc(page, order, gfp_mask, migratetype); @@ -3030,7 +3086,7 @@ int numa_zonelist_order_handler(ctl_table *table, int write, user_zonelist_order = oldval; } else if (oldval != user_zonelist_order) { mutex_lock(&zonelists_mutex); - build_all_zonelists(NULL); + build_all_zonelists(NULL, NULL); mutex_unlock(&zonelists_mutex); } } @@ -3409,14 +3465,21 @@ static void setup_zone_pageset(struct zone *zone); DEFINE_MUTEX(zonelists_mutex); /* return values int ....just for stop_machine() */ -static __init_refok int __build_all_zonelists(void *data) +static int __build_all_zonelists(void *data) { int nid; int cpu; + pg_data_t *self = data; #ifdef CONFIG_NUMA memset(node_load, 0, sizeof(node_load)); #endif + + if (self && !node_online(self->node_id)) { + build_zonelists(self); + build_zonelist_cache(self); + } + for_each_online_node(nid) { pg_data_t *pgdat = NODE_DATA(nid); @@ -3461,7 +3524,7 @@ static __init_refok int __build_all_zonelists(void *data) * Called with zonelists_mutex held always * unless system_state == SYSTEM_BOOTING. */ -void __ref build_all_zonelists(void *data) +void __ref build_all_zonelists(pg_data_t *pgdat, struct zone *zone) { set_zonelist_order(); @@ -3473,10 +3536,10 @@ void __ref build_all_zonelists(void *data) /* we have to stop all cpus to guarantee there is no user of zonelist */ #ifdef CONFIG_MEMORY_HOTPLUG - if (data) - setup_zone_pageset((struct zone *)data); + if (zone) + setup_zone_pageset(zone); #endif - stop_machine(__build_all_zonelists, NULL, NULL); + stop_machine(__build_all_zonelists, pgdat, NULL); /* cpuset refresh routine should be here */ } vm_total_pages = nr_free_pagecache_pages(); @@ -3746,7 +3809,7 @@ static void __meminit zone_init_free_lists(struct zone *zone) memmap_init_zone((size), (nid), (zone), (start_pfn), MEMMAP_EARLY) #endif -static int zone_batchsize(struct zone *zone) +static int __meminit zone_batchsize(struct zone *zone) { #ifdef CONFIG_MMU int batch; @@ -3828,7 +3891,7 @@ static void setup_pagelist_highmark(struct per_cpu_pageset *p, pcp->batch = PAGE_SHIFT * 8; } -static void setup_zone_pageset(struct zone *zone) +static void __meminit setup_zone_pageset(struct zone *zone) { int cpu; @@ -3901,32 +3964,6 @@ int zone_wait_table_init(struct zone *zone, unsigned long zone_size_pages) return 0; } -static int __zone_pcp_update(void *data) -{ - struct zone *zone = data; - int cpu; - unsigned long batch = zone_batchsize(zone), flags; - - for_each_possible_cpu(cpu) { - struct per_cpu_pageset *pset; - struct per_cpu_pages *pcp; - - pset = per_cpu_ptr(zone->pageset, cpu); - pcp = &pset->pcp; - - local_irq_save(flags); - free_pcppages_bulk(zone, pcp->count, pcp); - setup_pageset(pset, batch); - local_irq_restore(flags); - } - return 0; -} - -void zone_pcp_update(struct zone *zone) -{ - stop_machine(__zone_pcp_update, zone, NULL); -} - static __meminit void zone_pcp_init(struct zone *zone) { /* @@ -3942,7 +3979,7 @@ static __meminit void zone_pcp_init(struct zone *zone) zone_batchsize(zone)); } -__meminit int init_currently_empty_zone(struct zone *zone, +int __meminit init_currently_empty_zone(struct zone *zone, unsigned long zone_start_pfn, unsigned long size, enum memmap_context context) @@ -4301,7 +4338,7 @@ static inline void setup_usemap(struct pglist_data *pgdat, #ifdef CONFIG_HUGETLB_PAGE_SIZE_VARIABLE /* Initialise the number of pages represented by NR_PAGEBLOCK_BITS */ -static inline void __init set_pageblock_order(void) +void __init set_pageblock_order(void) { unsigned int order; @@ -4329,7 +4366,7 @@ static inline void __init set_pageblock_order(void) * include/linux/pageblock-flags.h for the values of pageblock_order based on * the kernel config */ -static inline void set_pageblock_order(void) +void __init set_pageblock_order(void) { } @@ -4340,6 +4377,8 @@ static inline void set_pageblock_order(void) * - mark all pages reserved * - mark all memory queues empty * - clear the memory bitmaps + * + * NOTE: pgdat should get zeroed by caller. */ static void __paginginit free_area_init_core(struct pglist_data *pgdat, unsigned long *zones_size, unsigned long *zholes_size) @@ -4350,9 +4389,8 @@ static void __paginginit free_area_init_core(struct pglist_data *pgdat, int ret; pgdat_resize_init(pgdat); - pgdat->nr_zones = 0; init_waitqueue_head(&pgdat->kswapd_wait); - pgdat->kswapd_max_order = 0; + init_waitqueue_head(&pgdat->pfmemalloc_wait); pgdat_page_cgroup_init(pgdat); for (j = 0; j < MAX_NR_ZONES; j++) { @@ -4394,6 +4432,11 @@ static void __paginginit free_area_init_core(struct pglist_data *pgdat, zone->spanned_pages = size; zone->present_pages = realsize; +#if defined CONFIG_COMPACTION || defined CONFIG_CMA + zone->compact_cached_free_pfn = zone->zone_start_pfn + + zone->spanned_pages; + zone->compact_cached_free_pfn &= ~(pageblock_nr_pages-1); +#endif #ifdef CONFIG_NUMA zone->node = nid; zone->min_unmapped_pages = (realsize*sysctl_min_unmapped_ratio) @@ -4408,8 +4451,6 @@ static void __paginginit free_area_init_core(struct pglist_data *pgdat, zone_pcp_init(zone); lruvec_init(&zone->lruvec, zone); - zap_zone_vm_stats(zone); - zone->flags = 0; if (!size) continue; @@ -4469,6 +4510,9 @@ void __paginginit free_area_init_node(int nid, unsigned long *zones_size, { pg_data_t *pgdat = NODE_DATA(nid); + /* pg_data_t should be reset to zero when it's allocated */ + WARN_ON(pgdat->nr_zones || pgdat->node_start_pfn || pgdat->classzone_idx); + pgdat->node_id = nid; pgdat->node_start_pfn = node_start_pfn; calculate_node_totalpages(pgdat, zones_size, zholes_size); @@ -4750,7 +4794,7 @@ out: } /* Any regular memory on that node ? */ -static void check_for_regular_memory(pg_data_t *pgdat) +static void __init check_for_regular_memory(pg_data_t *pgdat) { #ifdef CONFIG_HIGHMEM enum zone_type zone_type; @@ -5468,26 +5512,27 @@ void set_pageblock_flags_group(struct page *page, unsigned long flags, } /* - * This is designed as sub function...plz see page_isolation.c also. - * set/clear page block's type to be ISOLATE. - * page allocater never alloc memory from ISOLATE block. + * This function checks whether pageblock includes unmovable pages or not. + * If @count is not zero, it is okay to include less @count unmovable pages + * + * PageLRU check wihtout isolation or lru_lock could race so that + * MIGRATE_MOVABLE block might include unmovable pages. It means you can't + * expect this function should be exact. */ - -static int -__count_immobile_pages(struct zone *zone, struct page *page, int count) +bool has_unmovable_pages(struct zone *zone, struct page *page, int count) { unsigned long pfn, iter, found; int mt; /* * For avoiding noise data, lru_add_drain_all() should be called - * If ZONE_MOVABLE, the zone never contains immobile pages + * If ZONE_MOVABLE, the zone never contains unmovable pages */ if (zone_idx(zone) == ZONE_MOVABLE) - return true; + return false; mt = get_pageblock_migratetype(page); if (mt == MIGRATE_MOVABLE || is_migrate_cma(mt)) - return true; + return false; pfn = page_to_pfn(page); for (found = 0, iter = 0; iter < pageblock_nr_pages; iter++) { @@ -5497,11 +5542,18 @@ __count_immobile_pages(struct zone *zone, struct page *page, int count) continue; page = pfn_to_page(check); - if (!page_count(page)) { + /* + * We can't use page_count without pin a page + * because another CPU can free compound page. + * This check already skips compound tails of THP + * because their page->_count is zero at all time. + */ + if (!atomic_read(&page->_count)) { if (PageBuddy(page)) iter += (1 << page_order(page)) - 1; continue; } + if (!PageLRU(page)) found++; /* @@ -5518,9 +5570,9 @@ __count_immobile_pages(struct zone *zone, struct page *page, int count) * page at boot. */ if (found > count) - return false; + return true; } - return true; + return false; } bool is_pageblock_removable_nolock(struct page *page) @@ -5544,77 +5596,7 @@ bool is_pageblock_removable_nolock(struct page *page) zone->zone_start_pfn + zone->spanned_pages <= pfn) return false; - return __count_immobile_pages(zone, page, 0); -} - -int set_migratetype_isolate(struct page *page) -{ - struct zone *zone; - unsigned long flags, pfn; - struct memory_isolate_notify arg; - int notifier_ret; - int ret = -EBUSY; - - zone = page_zone(page); - - spin_lock_irqsave(&zone->lock, flags); - - pfn = page_to_pfn(page); - arg.start_pfn = pfn; - arg.nr_pages = pageblock_nr_pages; - arg.pages_found = 0; - - /* - * It may be possible to isolate a pageblock even if the - * migratetype is not MIGRATE_MOVABLE. The memory isolation - * notifier chain is used by balloon drivers to return the - * number of pages in a range that are held by the balloon - * driver to shrink memory. If all the pages are accounted for - * by balloons, are free, or on the LRU, isolation can continue. - * Later, for example, when memory hotplug notifier runs, these - * pages reported as "can be isolated" should be isolated(freed) - * by the balloon driver through the memory notifier chain. - */ - notifier_ret = memory_isolate_notify(MEM_ISOLATE_COUNT, &arg); - notifier_ret = notifier_to_errno(notifier_ret); - if (notifier_ret) - goto out; - /* - * FIXME: Now, memory hotplug doesn't call shrink_slab() by itself. - * We just check MOVABLE pages. - */ - if (__count_immobile_pages(zone, page, arg.pages_found)) - ret = 0; - - /* - * immobile means "not-on-lru" paes. If immobile is larger than - * removable-by-driver pages reported by notifier, we'll fail. - */ - -out: - if (!ret) { - set_pageblock_migratetype(page, MIGRATE_ISOLATE); - move_freepages_block(zone, page, MIGRATE_ISOLATE); - } - - spin_unlock_irqrestore(&zone->lock, flags); - if (!ret) - drain_all_pages(); - return ret; -} - -void unset_migratetype_isolate(struct page *page, unsigned migratetype) -{ - struct zone *zone; - unsigned long flags; - zone = page_zone(page); - spin_lock_irqsave(&zone->lock, flags); - if (get_pageblock_migratetype(page) != MIGRATE_ISOLATE) - goto out; - set_pageblock_migratetype(page, migratetype); - move_freepages_block(zone, page, migratetype); -out: - spin_unlock_irqrestore(&zone->lock, flags); + return !has_unmovable_pages(zone, page, 0); } #ifdef CONFIG_CMA @@ -5869,7 +5851,49 @@ void free_contig_range(unsigned long pfn, unsigned nr_pages) } #endif +#ifdef CONFIG_MEMORY_HOTPLUG +static int __meminit __zone_pcp_update(void *data) +{ + struct zone *zone = data; + int cpu; + unsigned long batch = zone_batchsize(zone), flags; + + for_each_possible_cpu(cpu) { + struct per_cpu_pageset *pset; + struct per_cpu_pages *pcp; + + pset = per_cpu_ptr(zone->pageset, cpu); + pcp = &pset->pcp; + + local_irq_save(flags); + if (pcp->count > 0) + free_pcppages_bulk(zone, pcp->count, pcp); + setup_pageset(pset, batch); + local_irq_restore(flags); + } + return 0; +} + +void __meminit zone_pcp_update(struct zone *zone) +{ + stop_machine(__zone_pcp_update, zone, NULL); +} +#endif + #ifdef CONFIG_MEMORY_HOTREMOVE +void zone_pcp_reset(struct zone *zone) +{ + unsigned long flags; + + /* avoid races with drain_pages() */ + local_irq_save(flags); + if (zone->pageset != &boot_pageset) { + free_percpu(zone->pageset); + zone->pageset = &boot_pageset; + } + local_irq_restore(flags); +} + /* * All pages in the range must be isolated before calling this. */ diff --git a/mm/page_cgroup.c b/mm/page_cgroup.c index eb750f851395..5ddad0c6daa6 100644 --- a/mm/page_cgroup.c +++ b/mm/page_cgroup.c @@ -317,7 +317,7 @@ void __meminit pgdat_page_cgroup_init(struct pglist_data *pgdat) #endif -#ifdef CONFIG_CGROUP_MEM_RES_CTLR_SWAP +#ifdef CONFIG_MEMCG_SWAP static DEFINE_MUTEX(swap_cgroup_mutex); struct swap_cgroup_ctrl { diff --git a/mm/page_io.c b/mm/page_io.c index 34f02923744c..78eee32ee486 100644 --- a/mm/page_io.c +++ b/mm/page_io.c @@ -17,6 +17,7 @@ #include <linux/swap.h> #include <linux/bio.h> #include <linux/swapops.h> +#include <linux/buffer_head.h> #include <linux/writeback.h> #include <linux/frontswap.h> #include <asm/pgtable.h> @@ -86,6 +87,98 @@ void end_swap_bio_read(struct bio *bio, int err) bio_put(bio); } +int generic_swapfile_activate(struct swap_info_struct *sis, + struct file *swap_file, + sector_t *span) +{ + struct address_space *mapping = swap_file->f_mapping; + struct inode *inode = mapping->host; + unsigned blocks_per_page; + unsigned long page_no; + unsigned blkbits; + sector_t probe_block; + sector_t last_block; + sector_t lowest_block = -1; + sector_t highest_block = 0; + int nr_extents = 0; + int ret; + + blkbits = inode->i_blkbits; + blocks_per_page = PAGE_SIZE >> blkbits; + + /* + * Map all the blocks into the extent list. This code doesn't try + * to be very smart. + */ + probe_block = 0; + page_no = 0; + last_block = i_size_read(inode) >> blkbits; + while ((probe_block + blocks_per_page) <= last_block && + page_no < sis->max) { + unsigned block_in_page; + sector_t first_block; + + first_block = bmap(inode, probe_block); + if (first_block == 0) + goto bad_bmap; + + /* + * It must be PAGE_SIZE aligned on-disk + */ + if (first_block & (blocks_per_page - 1)) { + probe_block++; + goto reprobe; + } + + for (block_in_page = 1; block_in_page < blocks_per_page; + block_in_page++) { + sector_t block; + + block = bmap(inode, probe_block + block_in_page); + if (block == 0) + goto bad_bmap; + if (block != first_block + block_in_page) { + /* Discontiguity */ + probe_block++; + goto reprobe; + } + } + + first_block >>= (PAGE_SHIFT - blkbits); + if (page_no) { /* exclude the header page */ + if (first_block < lowest_block) + lowest_block = first_block; + if (first_block > highest_block) + highest_block = first_block; + } + + /* + * We found a PAGE_SIZE-length, PAGE_SIZE-aligned run of blocks + */ + ret = add_swap_extent(sis, page_no, 1, first_block); + if (ret < 0) + goto out; + nr_extents += ret; + page_no++; + probe_block += blocks_per_page; +reprobe: + continue; + } + ret = nr_extents; + *span = 1 + highest_block - lowest_block; + if (page_no == 0) + page_no = 1; /* force Empty message */ + sis->max = page_no; + sis->pages = page_no - 1; + sis->highest_bit = page_no - 1; +out: + return ret; +bad_bmap: + printk(KERN_ERR "swapon: swapfile has holes\n"); + ret = -EINVAL; + goto out; +} + /* * We may have stale swap cache pages in memory: notice * them here and get rid of the unnecessary final write. @@ -94,6 +187,7 @@ int swap_writepage(struct page *page, struct writeback_control *wbc) { struct bio *bio; int ret = 0, rw = WRITE; + struct swap_info_struct *sis = page_swap_info(page); if (try_to_free_swap(page)) { unlock_page(page); @@ -105,6 +199,33 @@ int swap_writepage(struct page *page, struct writeback_control *wbc) end_page_writeback(page); goto out; } + + if (sis->flags & SWP_FILE) { + struct kiocb kiocb; + struct file *swap_file = sis->swap_file; + struct address_space *mapping = swap_file->f_mapping; + struct iovec iov = { + .iov_base = kmap(page), + .iov_len = PAGE_SIZE, + }; + + init_sync_kiocb(&kiocb, swap_file); + kiocb.ki_pos = page_file_offset(page); + kiocb.ki_left = PAGE_SIZE; + kiocb.ki_nbytes = PAGE_SIZE; + + unlock_page(page); + ret = mapping->a_ops->direct_IO(KERNEL_WRITE, + &kiocb, &iov, + kiocb.ki_pos, 1); + kunmap(page); + if (ret == PAGE_SIZE) { + count_vm_event(PSWPOUT); + ret = 0; + } + return ret; + } + bio = get_swap_bio(GFP_NOIO, page, end_swap_bio_write); if (bio == NULL) { set_page_dirty(page); @@ -126,6 +247,7 @@ int swap_readpage(struct page *page) { struct bio *bio; int ret = 0; + struct swap_info_struct *sis = page_swap_info(page); VM_BUG_ON(!PageLocked(page)); VM_BUG_ON(PageUptodate(page)); @@ -134,6 +256,17 @@ int swap_readpage(struct page *page) unlock_page(page); goto out; } + + if (sis->flags & SWP_FILE) { + struct file *swap_file = sis->swap_file; + struct address_space *mapping = swap_file->f_mapping; + + ret = mapping->a_ops->readpage(swap_file, page); + if (!ret) + count_vm_event(PSWPIN); + return ret; + } + bio = get_swap_bio(GFP_KERNEL, page, end_swap_bio_read); if (bio == NULL) { unlock_page(page); @@ -145,3 +278,15 @@ int swap_readpage(struct page *page) out: return ret; } + +int swap_set_page_dirty(struct page *page) +{ + struct swap_info_struct *sis = page_swap_info(page); + + if (sis->flags & SWP_FILE) { + struct address_space *mapping = sis->swap_file->f_mapping; + return mapping->a_ops->set_page_dirty(page); + } else { + return __set_page_dirty_no_writeback(page); + } +} diff --git a/mm/page_isolation.c b/mm/page_isolation.c index c9f04774f2b8..247d1f175739 100644 --- a/mm/page_isolation.c +++ b/mm/page_isolation.c @@ -5,8 +5,101 @@ #include <linux/mm.h> #include <linux/page-isolation.h> #include <linux/pageblock-flags.h> +#include <linux/memory.h> #include "internal.h" +/* called while holding zone->lock */ +static void set_pageblock_isolate(struct page *page) +{ + if (get_pageblock_migratetype(page) == MIGRATE_ISOLATE) + return; + + set_pageblock_migratetype(page, MIGRATE_ISOLATE); + page_zone(page)->nr_pageblock_isolate++; +} + +/* called while holding zone->lock */ +static void restore_pageblock_isolate(struct page *page, int migratetype) +{ + struct zone *zone = page_zone(page); + if (WARN_ON(get_pageblock_migratetype(page) != MIGRATE_ISOLATE)) + return; + + BUG_ON(zone->nr_pageblock_isolate <= 0); + set_pageblock_migratetype(page, migratetype); + zone->nr_pageblock_isolate--; +} + +int set_migratetype_isolate(struct page *page) +{ + struct zone *zone; + unsigned long flags, pfn; + struct memory_isolate_notify arg; + int notifier_ret; + int ret = -EBUSY; + + zone = page_zone(page); + + spin_lock_irqsave(&zone->lock, flags); + + pfn = page_to_pfn(page); + arg.start_pfn = pfn; + arg.nr_pages = pageblock_nr_pages; + arg.pages_found = 0; + + /* + * It may be possible to isolate a pageblock even if the + * migratetype is not MIGRATE_MOVABLE. The memory isolation + * notifier chain is used by balloon drivers to return the + * number of pages in a range that are held by the balloon + * driver to shrink memory. If all the pages are accounted for + * by balloons, are free, or on the LRU, isolation can continue. + * Later, for example, when memory hotplug notifier runs, these + * pages reported as "can be isolated" should be isolated(freed) + * by the balloon driver through the memory notifier chain. + */ + notifier_ret = memory_isolate_notify(MEM_ISOLATE_COUNT, &arg); + notifier_ret = notifier_to_errno(notifier_ret); + if (notifier_ret) + goto out; + /* + * FIXME: Now, memory hotplug doesn't call shrink_slab() by itself. + * We just check MOVABLE pages. + */ + if (!has_unmovable_pages(zone, page, arg.pages_found)) + ret = 0; + + /* + * immobile means "not-on-lru" paes. If immobile is larger than + * removable-by-driver pages reported by notifier, we'll fail. + */ + +out: + if (!ret) { + set_pageblock_isolate(page); + move_freepages_block(zone, page, MIGRATE_ISOLATE); + } + + spin_unlock_irqrestore(&zone->lock, flags); + if (!ret) + drain_all_pages(); + return ret; +} + +void unset_migratetype_isolate(struct page *page, unsigned migratetype) +{ + struct zone *zone; + unsigned long flags; + zone = page_zone(page); + spin_lock_irqsave(&zone->lock, flags); + if (get_pageblock_migratetype(page) != MIGRATE_ISOLATE) + goto out; + move_freepages_block(zone, page, migratetype); + restore_pageblock_isolate(page, migratetype); +out: + spin_unlock_irqrestore(&zone->lock, flags); +} + static inline struct page * __first_valid_page(unsigned long pfn, unsigned long nr_pages) { diff --git a/mm/shmem.c b/mm/shmem.c index c15b998e5a86..d4e184e2a38e 100644 --- a/mm/shmem.c +++ b/mm/shmem.c @@ -929,7 +929,8 @@ static struct page *shmem_swapin(swp_entry_t swap, gfp_t gfp, /* Create a pseudo vma that just contains the policy */ pvma.vm_start = 0; - pvma.vm_pgoff = index; + /* Bias interleave by inode number to distribute better across nodes */ + pvma.vm_pgoff = index + info->vfs_inode.i_ino; pvma.vm_ops = NULL; pvma.vm_policy = spol; return swapin_readahead(swap, gfp, &pvma, 0); @@ -942,7 +943,8 @@ static struct page *shmem_alloc_page(gfp_t gfp, /* Create a pseudo vma that just contains the policy */ pvma.vm_start = 0; - pvma.vm_pgoff = index; + /* Bias interleave by inode number to distribute better across nodes */ + pvma.vm_pgoff = index + info->vfs_inode.i_ino; pvma.vm_ops = NULL; pvma.vm_policy = mpol_shared_policy_lookup(&info->policy, index); diff --git a/mm/slab.c b/mm/slab.c index 1fcf3ac94b6c..f8b0d539b482 100644 --- a/mm/slab.c +++ b/mm/slab.c @@ -118,12 +118,16 @@ #include <linux/memory.h> #include <linux/prefetch.h> +#include <net/sock.h> + #include <asm/cacheflush.h> #include <asm/tlbflush.h> #include <asm/page.h> #include <trace/events/kmem.h> +#include "internal.h" + /* * DEBUG - 1 for kmem_cache_create() to honour; SLAB_RED_ZONE & SLAB_POISON. * 0 for faster, smaller code (especially in the critical paths). @@ -152,6 +156,12 @@ #define ARCH_KMALLOC_FLAGS SLAB_HWCACHE_ALIGN #endif +/* + * true if a page was allocated from pfmemalloc reserves for network-based + * swap + */ +static bool pfmemalloc_active __read_mostly; + /* Legal flag mask for kmem_cache_create(). */ #if DEBUG # define CREATE_MASK (SLAB_RED_ZONE | \ @@ -257,9 +267,30 @@ struct array_cache { * Must have this definition in here for the proper * alignment of array_cache. Also simplifies accessing * the entries. + * + * Entries should not be directly dereferenced as + * entries belonging to slabs marked pfmemalloc will + * have the lower bits set SLAB_OBJ_PFMEMALLOC */ }; +#define SLAB_OBJ_PFMEMALLOC 1 +static inline bool is_obj_pfmemalloc(void *objp) +{ + return (unsigned long)objp & SLAB_OBJ_PFMEMALLOC; +} + +static inline void set_obj_pfmemalloc(void **objp) +{ + *objp = (void *)((unsigned long)*objp | SLAB_OBJ_PFMEMALLOC); + return; +} + +static inline void clear_obj_pfmemalloc(void **objp) +{ + *objp = (void *)((unsigned long)*objp & ~SLAB_OBJ_PFMEMALLOC); +} + /* * bootstrap: The caches do not work without cpuarrays anymore, but the * cpuarrays are allocated from the generic caches... @@ -900,6 +931,124 @@ static struct array_cache *alloc_arraycache(int node, int entries, return nc; } +static inline bool is_slab_pfmemalloc(struct slab *slabp) +{ + struct page *page = virt_to_page(slabp->s_mem); + + return PageSlabPfmemalloc(page); +} + +/* Clears pfmemalloc_active if no slabs have pfmalloc set */ +static void recheck_pfmemalloc_active(struct kmem_cache *cachep, + struct array_cache *ac) +{ + struct kmem_list3 *l3 = cachep->nodelists[numa_mem_id()]; + struct slab *slabp; + unsigned long flags; + + if (!pfmemalloc_active) + return; + + spin_lock_irqsave(&l3->list_lock, flags); + list_for_each_entry(slabp, &l3->slabs_full, list) + if (is_slab_pfmemalloc(slabp)) + goto out; + + list_for_each_entry(slabp, &l3->slabs_partial, list) + if (is_slab_pfmemalloc(slabp)) + goto out; + + list_for_each_entry(slabp, &l3->slabs_free, list) + if (is_slab_pfmemalloc(slabp)) + goto out; + + pfmemalloc_active = false; +out: + spin_unlock_irqrestore(&l3->list_lock, flags); +} + +static void *__ac_get_obj(struct kmem_cache *cachep, struct array_cache *ac, + gfp_t flags, bool force_refill) +{ + int i; + void *objp = ac->entry[--ac->avail]; + + /* Ensure the caller is allowed to use objects from PFMEMALLOC slab */ + if (unlikely(is_obj_pfmemalloc(objp))) { + struct kmem_list3 *l3; + + if (gfp_pfmemalloc_allowed(flags)) { + clear_obj_pfmemalloc(&objp); + return objp; + } + + /* The caller cannot use PFMEMALLOC objects, find another one */ + for (i = 1; i < ac->avail; i++) { + /* If a !PFMEMALLOC object is found, swap them */ + if (!is_obj_pfmemalloc(ac->entry[i])) { + objp = ac->entry[i]; + ac->entry[i] = ac->entry[ac->avail]; + ac->entry[ac->avail] = objp; + return objp; + } + } + + /* + * If there are empty slabs on the slabs_free list and we are + * being forced to refill the cache, mark this one !pfmemalloc. + */ + l3 = cachep->nodelists[numa_mem_id()]; + if (!list_empty(&l3->slabs_free) && force_refill) { + struct slab *slabp = virt_to_slab(objp); + ClearPageSlabPfmemalloc(virt_to_page(slabp->s_mem)); + clear_obj_pfmemalloc(&objp); + recheck_pfmemalloc_active(cachep, ac); + return objp; + } + + /* No !PFMEMALLOC objects available */ + ac->avail++; + objp = NULL; + } + + return objp; +} + +static inline void *ac_get_obj(struct kmem_cache *cachep, + struct array_cache *ac, gfp_t flags, bool force_refill) +{ + void *objp; + + if (unlikely(sk_memalloc_socks())) + objp = __ac_get_obj(cachep, ac, flags, force_refill); + else + objp = ac->entry[--ac->avail]; + + return objp; +} + +static void *__ac_put_obj(struct kmem_cache *cachep, struct array_cache *ac, + void *objp) +{ + if (unlikely(pfmemalloc_active)) { + /* Some pfmemalloc slabs exist, check if this is one */ + struct page *page = virt_to_page(objp); + if (PageSlabPfmemalloc(page)) + set_obj_pfmemalloc(&objp); + } + + return objp; +} + +static inline void ac_put_obj(struct kmem_cache *cachep, struct array_cache *ac, + void *objp) +{ + if (unlikely(sk_memalloc_socks())) + objp = __ac_put_obj(cachep, ac, objp); + + ac->entry[ac->avail++] = objp; +} + /* * Transfer objects in one arraycache to another. * Locking must be handled by the caller. @@ -1076,7 +1225,7 @@ static inline int cache_free_alien(struct kmem_cache *cachep, void *objp) STATS_INC_ACOVERFLOW(cachep); __drain_alien_cache(cachep, alien, nodeid); } - alien->entry[alien->avail++] = objp; + ac_put_obj(cachep, alien, objp); spin_unlock(&alien->lock); } else { spin_lock(&(cachep->nodelists[nodeid])->list_lock); @@ -1759,6 +1908,10 @@ static void *kmem_getpages(struct kmem_cache *cachep, gfp_t flags, int nodeid) return NULL; } + /* Record if ALLOC_NO_WATERMARKS was set when allocating the slab */ + if (unlikely(page->pfmemalloc)) + pfmemalloc_active = true; + nr_pages = (1 << cachep->gfporder); if (cachep->flags & SLAB_RECLAIM_ACCOUNT) add_zone_page_state(page_zone(page), @@ -1766,9 +1919,13 @@ static void *kmem_getpages(struct kmem_cache *cachep, gfp_t flags, int nodeid) else add_zone_page_state(page_zone(page), NR_SLAB_UNRECLAIMABLE, nr_pages); - for (i = 0; i < nr_pages; i++) + for (i = 0; i < nr_pages; i++) { __SetPageSlab(page + i); + if (page->pfmemalloc) + SetPageSlabPfmemalloc(page + i); + } + if (kmemcheck_enabled && !(cachep->flags & SLAB_NOTRACK)) { kmemcheck_alloc_shadow(page, cachep->gfporder, flags, nodeid); @@ -1800,6 +1957,7 @@ static void kmem_freepages(struct kmem_cache *cachep, void *addr) NR_SLAB_UNRECLAIMABLE, nr_freed); while (i--) { BUG_ON(!PageSlab(page)); + __ClearPageSlabPfmemalloc(page); __ClearPageSlab(page); page++; } @@ -3015,16 +3173,19 @@ bad: #define check_slabp(x,y) do { } while(0) #endif -static void *cache_alloc_refill(struct kmem_cache *cachep, gfp_t flags) +static void *cache_alloc_refill(struct kmem_cache *cachep, gfp_t flags, + bool force_refill) { int batchcount; struct kmem_list3 *l3; struct array_cache *ac; int node; -retry: check_irq_off(); node = numa_mem_id(); + if (unlikely(force_refill)) + goto force_grow; +retry: ac = cpu_cache_get(cachep); batchcount = ac->batchcount; if (!ac->touched && batchcount > BATCHREFILL_LIMIT) { @@ -3074,8 +3235,8 @@ retry: STATS_INC_ACTIVE(cachep); STATS_SET_HIGH(cachep); - ac->entry[ac->avail++] = slab_get_obj(cachep, slabp, - node); + ac_put_obj(cachep, ac, slab_get_obj(cachep, slabp, + node)); } check_slabp(cachep, slabp); @@ -3094,18 +3255,22 @@ alloc_done: if (unlikely(!ac->avail)) { int x; +force_grow: x = cache_grow(cachep, flags | GFP_THISNODE, node, NULL); /* cache_grow can reenable interrupts, then ac could change. */ ac = cpu_cache_get(cachep); - if (!x && ac->avail == 0) /* no objects in sight? abort */ + + /* no objects in sight? abort */ + if (!x && (ac->avail == 0 || force_refill)) return NULL; if (!ac->avail) /* objects refilled by interrupt? */ goto retry; } ac->touched = 1; - return ac->entry[--ac->avail]; + + return ac_get_obj(cachep, ac, flags, force_refill); } static inline void cache_alloc_debugcheck_before(struct kmem_cache *cachep, @@ -3187,23 +3352,35 @@ static inline void *____cache_alloc(struct kmem_cache *cachep, gfp_t flags) { void *objp; struct array_cache *ac; + bool force_refill = false; check_irq_off(); ac = cpu_cache_get(cachep); if (likely(ac->avail)) { - STATS_INC_ALLOCHIT(cachep); ac->touched = 1; - objp = ac->entry[--ac->avail]; - } else { - STATS_INC_ALLOCMISS(cachep); - objp = cache_alloc_refill(cachep, flags); + objp = ac_get_obj(cachep, ac, flags, false); + /* - * the 'ac' may be updated by cache_alloc_refill(), - * and kmemleak_erase() requires its correct value. + * Allow for the possibility all avail objects are not allowed + * by the current flags */ - ac = cpu_cache_get(cachep); + if (objp) { + STATS_INC_ALLOCHIT(cachep); + goto out; + } + force_refill = true; } + + STATS_INC_ALLOCMISS(cachep); + objp = cache_alloc_refill(cachep, flags, force_refill); + /* + * the 'ac' may be updated by cache_alloc_refill(), + * and kmemleak_erase() requires its correct value. + */ + ac = cpu_cache_get(cachep); + +out: /* * To avoid a false negative, if an object that is in one of the * per-CPU caches is leaked, we need to make sure kmemleak doesn't @@ -3525,9 +3702,12 @@ static void free_block(struct kmem_cache *cachep, void **objpp, int nr_objects, struct kmem_list3 *l3; for (i = 0; i < nr_objects; i++) { - void *objp = objpp[i]; + void *objp; struct slab *slabp; + clear_obj_pfmemalloc(&objpp[i]); + objp = objpp[i]; + slabp = virt_to_slab(objp); l3 = cachep->nodelists[node]; list_del(&slabp->list); @@ -3645,7 +3825,7 @@ static inline void __cache_free(struct kmem_cache *cachep, void *objp, cache_flusharray(cachep, ac); } - ac->entry[ac->avail++] = objp; + ac_put_obj(cachep, ac, objp); } /** diff --git a/mm/slub.c b/mm/slub.c index e517d435e5dc..8f78e2577031 100644 --- a/mm/slub.c +++ b/mm/slub.c @@ -34,6 +34,8 @@ #include <trace/events/kmem.h> +#include "internal.h" + /* * Lock order: * 1. slab_mutex (Global Mutex) @@ -1354,6 +1356,8 @@ static struct page *new_slab(struct kmem_cache *s, gfp_t flags, int node) inc_slabs_node(s, page_to_nid(page), page->objects); page->slab = s; __SetPageSlab(page); + if (page->pfmemalloc) + SetPageSlabPfmemalloc(page); start = page_address(page); @@ -1397,6 +1401,7 @@ static void __free_slab(struct kmem_cache *s, struct page *page) NR_SLAB_RECLAIMABLE : NR_SLAB_UNRECLAIMABLE, -pages); + __ClearPageSlabPfmemalloc(page); __ClearPageSlab(page); reset_page_mapcount(page); if (current->reclaim_state) @@ -2126,6 +2131,14 @@ static inline void *new_slab_objects(struct kmem_cache *s, gfp_t flags, return freelist; } +static inline bool pfmemalloc_match(struct page *page, gfp_t gfpflags) +{ + if (unlikely(PageSlabPfmemalloc(page))) + return gfp_pfmemalloc_allowed(gfpflags); + + return true; +} + /* * Check the page->freelist of a page and either transfer the freelist to the per cpu freelist * or deactivate the page. @@ -2206,6 +2219,18 @@ redo: goto new_slab; } + /* + * By rights, we should be searching for a slab page that was + * PFMEMALLOC but right now, we are losing the pfmemalloc + * information when the page leaves the per-cpu allocator + */ + if (unlikely(!pfmemalloc_match(page, gfpflags))) { + deactivate_slab(s, page, c->freelist); + c->page = NULL; + c->freelist = NULL; + goto new_slab; + } + /* must check again c->freelist in case of cpu migration or IRQ */ freelist = c->freelist; if (freelist) @@ -2256,11 +2281,11 @@ new_slab: } page = c->page; - if (likely(!kmem_cache_debug(s))) + if (likely(!kmem_cache_debug(s) && pfmemalloc_match(page, gfpflags))) goto load_freelist; /* Only entered in the debug case */ - if (!alloc_debug_processing(s, page, freelist, addr)) + if (kmem_cache_debug(s) && !alloc_debug_processing(s, page, freelist, addr)) goto new_slab; /* Slab failed checks. Next slab needed */ deactivate_slab(s, page, get_freepointer(s, freelist)); @@ -2313,7 +2338,6 @@ redo: object = c->freelist; page = c->page; if (unlikely(!object || !node_match(page, node))) - object = __slab_alloc(s, gfpflags, node, addr, c); else { diff --git a/mm/sparse.c b/mm/sparse.c index c7bb952400c8..fac95f2888f2 100644 --- a/mm/sparse.c +++ b/mm/sparse.c @@ -65,21 +65,18 @@ static struct mem_section noinline __init_refok *sparse_index_alloc(int nid) if (slab_is_available()) { if (node_state(nid, N_HIGH_MEMORY)) - section = kmalloc_node(array_size, GFP_KERNEL, nid); + section = kzalloc_node(array_size, GFP_KERNEL, nid); else - section = kmalloc(array_size, GFP_KERNEL); - } else + section = kzalloc(array_size, GFP_KERNEL); + } else { section = alloc_bootmem_node(NODE_DATA(nid), array_size); - - if (section) - memset(section, 0, array_size); + } return section; } static int __meminit sparse_index_init(unsigned long section_nr, int nid) { - static DEFINE_SPINLOCK(index_init_lock); unsigned long root = SECTION_NR_TO_ROOT(section_nr); struct mem_section *section; int ret = 0; @@ -90,20 +87,9 @@ static int __meminit sparse_index_init(unsigned long section_nr, int nid) section = sparse_index_alloc(nid); if (!section) return -ENOMEM; - /* - * This lock keeps two different sections from - * reallocating for the same index - */ - spin_lock(&index_init_lock); - - if (mem_section[root]) { - ret = -EEXIST; - goto out; - } mem_section[root] = section; -out: - spin_unlock(&index_init_lock); + return ret; } #else /* !SPARSEMEM_EXTREME */ @@ -132,6 +118,8 @@ int __section_nr(struct mem_section* ms) break; } + VM_BUG_ON(root_nr == NR_SECTION_ROOTS); + return (root_nr * SECTIONS_PER_ROOT) + (ms - root); } @@ -493,6 +481,9 @@ void __init sparse_init(void) struct page **map_map; #endif + /* Setup pageblock_order for HUGETLB_PAGE_SIZE_VARIABLE */ + set_pageblock_order(); + /* * map is using big page (aka 2M in x86 64 bit) * usemap is less one page (aka 24 bytes) diff --git a/mm/swap.c b/mm/swap.c index 4e7e2ec67078..77825883298f 100644 --- a/mm/swap.c +++ b/mm/swap.c @@ -236,6 +236,58 @@ void put_pages_list(struct list_head *pages) } EXPORT_SYMBOL(put_pages_list); +/* + * get_kernel_pages() - pin kernel pages in memory + * @kiov: An array of struct kvec structures + * @nr_segs: number of segments to pin + * @write: pinning for read/write, currently ignored + * @pages: array that receives pointers to the pages pinned. + * Should be at least nr_segs long. + * + * Returns number of pages pinned. This may be fewer than the number + * requested. If nr_pages is 0 or negative, returns 0. If no pages + * were pinned, returns -errno. Each page returned must be released + * with a put_page() call when it is finished with. + */ +int get_kernel_pages(const struct kvec *kiov, int nr_segs, int write, + struct page **pages) +{ + int seg; + + for (seg = 0; seg < nr_segs; seg++) { + if (WARN_ON(kiov[seg].iov_len != PAGE_SIZE)) + return seg; + + pages[seg] = kmap_to_page(kiov[seg].iov_base); + page_cache_get(pages[seg]); + } + + return seg; +} +EXPORT_SYMBOL_GPL(get_kernel_pages); + +/* + * get_kernel_page() - pin a kernel page in memory + * @start: starting kernel address + * @write: pinning for read/write, currently ignored + * @pages: array that receives pointer to the page pinned. + * Must be at least nr_segs long. + * + * Returns 1 if page is pinned. If the page was not pinned, returns + * -errno. The page returned must be released with a put_page() call + * when it is finished with. + */ +int get_kernel_page(unsigned long start, int write, struct page **pages) +{ + const struct kvec kiov = { + .iov_base = (void *)start, + .iov_len = PAGE_SIZE + }; + + return get_kernel_pages(&kiov, 1, write, pages); +} +EXPORT_SYMBOL_GPL(get_kernel_page); + static void pagevec_lru_move_fn(struct pagevec *pvec, void (*move_fn)(struct page *page, struct lruvec *lruvec, void *arg), void *arg) diff --git a/mm/swap_state.c b/mm/swap_state.c index 4c5ff7f284d9..0cb36fb1f61c 100644 --- a/mm/swap_state.c +++ b/mm/swap_state.c @@ -14,6 +14,7 @@ #include <linux/init.h> #include <linux/pagemap.h> #include <linux/backing-dev.h> +#include <linux/blkdev.h> #include <linux/pagevec.h> #include <linux/migrate.h> #include <linux/page_cgroup.h> @@ -26,7 +27,7 @@ */ static const struct address_space_operations swap_aops = { .writepage = swap_writepage, - .set_page_dirty = __set_page_dirty_no_writeback, + .set_page_dirty = swap_set_page_dirty, .migratepage = migrate_page, }; @@ -376,6 +377,7 @@ struct page *swapin_readahead(swp_entry_t entry, gfp_t gfp_mask, unsigned long offset = swp_offset(entry); unsigned long start_offset, end_offset; unsigned long mask = (1UL << page_cluster) - 1; + struct blk_plug plug; /* Read a page_cluster sized and aligned cluster around offset. */ start_offset = offset & ~mask; @@ -383,6 +385,7 @@ struct page *swapin_readahead(swp_entry_t entry, gfp_t gfp_mask, if (!start_offset) /* First page is swap header. */ start_offset++; + blk_start_plug(&plug); for (offset = start_offset; offset <= end_offset ; offset++) { /* Ok, do the async read-ahead now */ page = read_swap_cache_async(swp_entry(swp_type(entry), offset), @@ -391,6 +394,8 @@ struct page *swapin_readahead(swp_entry_t entry, gfp_t gfp_mask, continue; page_cache_release(page); } + blk_finish_plug(&plug); + lru_add_drain(); /* Push any new pages onto the LRU now */ return read_swap_cache_async(entry, gfp_mask, vma, addr); } diff --git a/mm/swapfile.c b/mm/swapfile.c index 71373d03fcee..14e254c768fc 100644 --- a/mm/swapfile.c +++ b/mm/swapfile.c @@ -33,6 +33,7 @@ #include <linux/oom.h> #include <linux/frontswap.h> #include <linux/swapfile.h> +#include <linux/export.h> #include <asm/pgtable.h> #include <asm/tlbflush.h> @@ -548,7 +549,6 @@ static unsigned char swap_entry_free(struct swap_info_struct *p, /* free if no reference */ if (!usage) { - struct gendisk *disk = p->bdev->bd_disk; if (offset < p->lowest_bit) p->lowest_bit = offset; if (offset > p->highest_bit) @@ -559,9 +559,12 @@ static unsigned char swap_entry_free(struct swap_info_struct *p, nr_swap_pages++; p->inuse_pages--; frontswap_invalidate_page(p->type, offset); - if ((p->flags & SWP_BLKDEV) && - disk->fops->swap_slot_free_notify) - disk->fops->swap_slot_free_notify(p->bdev, offset); + if (p->flags & SWP_BLKDEV) { + struct gendisk *disk = p->bdev->bd_disk; + if (disk->fops->swap_slot_free_notify) + disk->fops->swap_slot_free_notify(p->bdev, + offset); + } } return usage; @@ -832,8 +835,7 @@ static int unuse_pte(struct vm_area_struct *vma, pmd_t *pmd, pte = pte_offset_map_lock(vma->vm_mm, pmd, addr, &ptl); if (unlikely(!pte_same(*pte, swp_entry_to_pte(entry)))) { - if (ret > 0) - mem_cgroup_cancel_charge_swapin(memcg); + mem_cgroup_cancel_charge_swapin(memcg); ret = 0; goto out; } @@ -1328,6 +1330,14 @@ static void destroy_swap_extents(struct swap_info_struct *sis) list_del(&se->list); kfree(se); } + + if (sis->flags & SWP_FILE) { + struct file *swap_file = sis->swap_file; + struct address_space *mapping = swap_file->f_mapping; + + sis->flags &= ~SWP_FILE; + mapping->a_ops->swap_deactivate(swap_file); + } } /* @@ -1336,7 +1346,7 @@ static void destroy_swap_extents(struct swap_info_struct *sis) * * This function rather assumes that it is called in ascending page order. */ -static int +int add_swap_extent(struct swap_info_struct *sis, unsigned long start_page, unsigned long nr_pages, sector_t start_block) { @@ -1409,98 +1419,28 @@ add_swap_extent(struct swap_info_struct *sis, unsigned long start_page, */ static int setup_swap_extents(struct swap_info_struct *sis, sector_t *span) { - struct inode *inode; - unsigned blocks_per_page; - unsigned long page_no; - unsigned blkbits; - sector_t probe_block; - sector_t last_block; - sector_t lowest_block = -1; - sector_t highest_block = 0; - int nr_extents = 0; + struct file *swap_file = sis->swap_file; + struct address_space *mapping = swap_file->f_mapping; + struct inode *inode = mapping->host; int ret; - inode = sis->swap_file->f_mapping->host; if (S_ISBLK(inode->i_mode)) { ret = add_swap_extent(sis, 0, sis->max, 0); *span = sis->pages; - goto out; + return ret; } - blkbits = inode->i_blkbits; - blocks_per_page = PAGE_SIZE >> blkbits; - - /* - * Map all the blocks into the extent list. This code doesn't try - * to be very smart. - */ - probe_block = 0; - page_no = 0; - last_block = i_size_read(inode) >> blkbits; - while ((probe_block + blocks_per_page) <= last_block && - page_no < sis->max) { - unsigned block_in_page; - sector_t first_block; - - first_block = bmap(inode, probe_block); - if (first_block == 0) - goto bad_bmap; - - /* - * It must be PAGE_SIZE aligned on-disk - */ - if (first_block & (blocks_per_page - 1)) { - probe_block++; - goto reprobe; - } - - for (block_in_page = 1; block_in_page < blocks_per_page; - block_in_page++) { - sector_t block; - - block = bmap(inode, probe_block + block_in_page); - if (block == 0) - goto bad_bmap; - if (block != first_block + block_in_page) { - /* Discontiguity */ - probe_block++; - goto reprobe; - } - } - - first_block >>= (PAGE_SHIFT - blkbits); - if (page_no) { /* exclude the header page */ - if (first_block < lowest_block) - lowest_block = first_block; - if (first_block > highest_block) - highest_block = first_block; + if (mapping->a_ops->swap_activate) { + ret = mapping->a_ops->swap_activate(sis, swap_file, span); + if (!ret) { + sis->flags |= SWP_FILE; + ret = add_swap_extent(sis, 0, sis->max, 0); + *span = sis->pages; } + return ret; + } - /* - * We found a PAGE_SIZE-length, PAGE_SIZE-aligned run of blocks - */ - ret = add_swap_extent(sis, page_no, 1, first_block); - if (ret < 0) - goto out; - nr_extents += ret; - page_no++; - probe_block += blocks_per_page; -reprobe: - continue; - } - ret = nr_extents; - *span = 1 + highest_block - lowest_block; - if (page_no == 0) - page_no = 1; /* force Empty message */ - sis->max = page_no; - sis->pages = page_no - 1; - sis->highest_bit = page_no - 1; -out: - return ret; -bad_bmap: - printk(KERN_ERR "swapon: swapfile has holes\n"); - ret = -EINVAL; - goto out; + return generic_swapfile_activate(sis, swap_file, span); } static void enable_swap_info(struct swap_info_struct *p, int prio, @@ -2285,6 +2225,31 @@ int swapcache_prepare(swp_entry_t entry) return __swap_duplicate(entry, SWAP_HAS_CACHE); } +struct swap_info_struct *page_swap_info(struct page *page) +{ + swp_entry_t swap = { .val = page_private(page) }; + BUG_ON(!PageSwapCache(page)); + return swap_info[swp_type(swap)]; +} + +/* + * out-of-line __page_file_ methods to avoid include hell. + */ +struct address_space *__page_file_mapping(struct page *page) +{ + VM_BUG_ON(!PageSwapCache(page)); + return page_swap_info(page)->swap_file->f_mapping; +} +EXPORT_SYMBOL_GPL(__page_file_mapping); + +pgoff_t __page_file_index(struct page *page) +{ + swp_entry_t swap = { .val = page_private(page) }; + VM_BUG_ON(!PageSwapCache(page)); + return swp_offset(swap); +} +EXPORT_SYMBOL_GPL(__page_file_index); + /* * add_swap_count_continuation - called when a swap count is duplicated * beyond SWAP_MAP_MAX, it allocates a new page and links that to the entry's diff --git a/mm/vmalloc.c b/mm/vmalloc.c index e03f4c7307a5..2bb90b1d241c 100644 --- a/mm/vmalloc.c +++ b/mm/vmalloc.c @@ -413,11 +413,11 @@ nocache: if (addr + size - 1 < addr) goto overflow; - n = rb_next(&first->rb_node); - if (n) - first = rb_entry(n, struct vmap_area, rb_node); - else + if (list_is_last(&first->list, &vmap_area_list)) goto found; + + first = list_entry(first->list.next, + struct vmap_area, list); } found: @@ -904,6 +904,14 @@ static void *vb_alloc(unsigned long size, gfp_t gfp_mask) BUG_ON(size & ~PAGE_MASK); BUG_ON(size > PAGE_SIZE*VMAP_MAX_ALLOC); + if (WARN_ON(size == 0)) { + /* + * Allocating 0 bytes isn't what caller wants since + * get_order(0) returns funny result. Just warn and terminate + * early. + */ + return NULL; + } order = get_order(size); again: diff --git a/mm/vmscan.c b/mm/vmscan.c index 347b3ff2a478..8d01243d9560 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -133,7 +133,7 @@ long vm_total_pages; /* The total number of pages which the VM controls */ static LIST_HEAD(shrinker_list); static DECLARE_RWSEM(shrinker_rwsem); -#ifdef CONFIG_CGROUP_MEM_RES_CTLR +#ifdef CONFIG_MEMCG static bool global_reclaim(struct scan_control *sc) { return !sc->target_mem_cgroup; @@ -687,6 +687,7 @@ static unsigned long shrink_page_list(struct list_head *page_list, cond_resched(); + mem_cgroup_uncharge_start(); while (!list_empty(page_list)) { enum page_references references; struct address_space *mapping; @@ -720,9 +721,41 @@ static unsigned long shrink_page_list(struct list_head *page_list, (PageSwapCache(page) && (sc->gfp_mask & __GFP_IO)); if (PageWriteback(page)) { - nr_writeback++; - unlock_page(page); - goto keep; + /* + * memcg doesn't have any dirty pages throttling so we + * could easily OOM just because too many pages are in + * writeback and there is nothing else to reclaim. + * + * Check __GFP_IO, certainly because a loop driver + * thread might enter reclaim, and deadlock if it waits + * on a page for which it is needed to do the write + * (loop masks off __GFP_IO|__GFP_FS for this reason); + * but more thought would probably show more reasons. + * + * Don't require __GFP_FS, since we're not going into + * the FS, just waiting on its writeback completion. + * Worryingly, ext4 gfs2 and xfs allocate pages with + * grab_cache_page_write_begin(,,AOP_FLAG_NOFS), so + * testing may_enter_fs here is liable to OOM on them. + */ + if (global_reclaim(sc) || + !PageReclaim(page) || !(sc->gfp_mask & __GFP_IO)) { + /* + * This is slightly racy - end_page_writeback() + * might have just cleared PageReclaim, then + * setting PageReclaim here end up interpreted + * as PageReadahead - but that does not matter + * enough to care. What we do want is for this + * page to have PageReclaim set next time memcg + * reclaim reaches the tests above, so it will + * then wait_on_page_writeback() to avoid OOM; + * and it's also appropriate in global reclaim. + */ + SetPageReclaim(page); + nr_writeback++; + goto keep_locked; + } + wait_on_page_writeback(page); } references = page_check_references(page, sc); @@ -921,6 +954,7 @@ keep: list_splice(&ret_pages, page_list); count_vm_events(PGACTIVATE, pgactivate); + mem_cgroup_uncharge_end(); *ret_nr_dirty += nr_dirty; *ret_nr_writeback += nr_writeback; return nr_reclaimed; @@ -2112,6 +2146,83 @@ out: return 0; } +static bool pfmemalloc_watermark_ok(pg_data_t *pgdat) +{ + struct zone *zone; + unsigned long pfmemalloc_reserve = 0; + unsigned long free_pages = 0; + int i; + bool wmark_ok; + + for (i = 0; i <= ZONE_NORMAL; i++) { + zone = &pgdat->node_zones[i]; + pfmemalloc_reserve += min_wmark_pages(zone); + free_pages += zone_page_state(zone, NR_FREE_PAGES); + } + + wmark_ok = free_pages > pfmemalloc_reserve / 2; + + /* kswapd must be awake if processes are being throttled */ + if (!wmark_ok && waitqueue_active(&pgdat->kswapd_wait)) { + pgdat->classzone_idx = min(pgdat->classzone_idx, + (enum zone_type)ZONE_NORMAL); + wake_up_interruptible(&pgdat->kswapd_wait); + } + + return wmark_ok; +} + +/* + * Throttle direct reclaimers if backing storage is backed by the network + * and the PFMEMALLOC reserve for the preferred node is getting dangerously + * depleted. kswapd will continue to make progress and wake the processes + * when the low watermark is reached + */ +static void throttle_direct_reclaim(gfp_t gfp_mask, struct zonelist *zonelist, + nodemask_t *nodemask) +{ + struct zone *zone; + int high_zoneidx = gfp_zone(gfp_mask); + pg_data_t *pgdat; + + /* + * Kernel threads should not be throttled as they may be indirectly + * responsible for cleaning pages necessary for reclaim to make forward + * progress. kjournald for example may enter direct reclaim while + * committing a transaction where throttling it could forcing other + * processes to block on log_wait_commit(). + */ + if (current->flags & PF_KTHREAD) + return; + + /* Check if the pfmemalloc reserves are ok */ + first_zones_zonelist(zonelist, high_zoneidx, NULL, &zone); + pgdat = zone->zone_pgdat; + if (pfmemalloc_watermark_ok(pgdat)) + return; + + /* Account for the throttling */ + count_vm_event(PGSCAN_DIRECT_THROTTLE); + + /* + * If the caller cannot enter the filesystem, it's possible that it + * is due to the caller holding an FS lock or performing a journal + * transaction in the case of a filesystem like ext[3|4]. In this case, + * it is not safe to block on pfmemalloc_wait as kswapd could be + * blocked waiting on the same lock. Instead, throttle for up to a + * second before continuing. + */ + if (!(gfp_mask & __GFP_FS)) { + wait_event_interruptible_timeout(pgdat->pfmemalloc_wait, + pfmemalloc_watermark_ok(pgdat), HZ); + return; + } + + /* Throttle until kswapd wakes the process */ + wait_event_killable(zone->zone_pgdat->pfmemalloc_wait, + pfmemalloc_watermark_ok(pgdat)); +} + unsigned long try_to_free_pages(struct zonelist *zonelist, int order, gfp_t gfp_mask, nodemask_t *nodemask) { @@ -2131,6 +2242,15 @@ unsigned long try_to_free_pages(struct zonelist *zonelist, int order, .gfp_mask = sc.gfp_mask, }; + throttle_direct_reclaim(gfp_mask, zonelist, nodemask); + + /* + * Do not enter reclaim if fatal signal is pending. 1 is returned so + * that the page allocator does not consider triggering OOM + */ + if (fatal_signal_pending(current)) + return 1; + trace_mm_vmscan_direct_reclaim_begin(order, sc.may_writepage, gfp_mask); @@ -2142,7 +2262,7 @@ unsigned long try_to_free_pages(struct zonelist *zonelist, int order, return nr_reclaimed; } -#ifdef CONFIG_CGROUP_MEM_RES_CTLR +#ifdef CONFIG_MEMCG unsigned long mem_cgroup_shrink_node_zone(struct mem_cgroup *memcg, gfp_t gfp_mask, bool noswap, @@ -2275,8 +2395,13 @@ static bool pgdat_balanced(pg_data_t *pgdat, unsigned long balanced_pages, return balanced_pages >= (present_pages >> 2); } -/* is kswapd sleeping prematurely? */ -static bool sleeping_prematurely(pg_data_t *pgdat, int order, long remaining, +/* + * Prepare kswapd for sleeping. This verifies that there are no processes + * waiting in throttle_direct_reclaim() and that watermarks have been met. + * + * Returns true if kswapd is ready to sleep + */ +static bool prepare_kswapd_sleep(pg_data_t *pgdat, int order, long remaining, int classzone_idx) { int i; @@ -2285,7 +2410,21 @@ static bool sleeping_prematurely(pg_data_t *pgdat, int order, long remaining, /* If a direct reclaimer woke kswapd within HZ/10, it's premature */ if (remaining) - return true; + return false; + + /* + * There is a potential race between when kswapd checks its watermarks + * and a process gets throttled. There is also a potential race if + * processes get throttled, kswapd wakes, a large process exits therby + * balancing the zones that causes kswapd to miss a wakeup. If kswapd + * is going to sleep, no process should be sleeping on pfmemalloc_wait + * so wake them now if necessary. If necessary, processes will wake + * kswapd and get throttled again + */ + if (waitqueue_active(&pgdat->pfmemalloc_wait)) { + wake_up(&pgdat->pfmemalloc_wait); + return false; + } /* Check the watermark levels */ for (i = 0; i <= classzone_idx; i++) { @@ -2318,9 +2457,9 @@ static bool sleeping_prematurely(pg_data_t *pgdat, int order, long remaining, * must be balanced */ if (order) - return !pgdat_balanced(pgdat, balanced, classzone_idx); + return pgdat_balanced(pgdat, balanced, classzone_idx); else - return !all_zones_ok; + return all_zones_ok; } /* @@ -2546,6 +2685,16 @@ loop_again: } } + + /* + * If the low watermark is met there is no need for processes + * to be throttled on pfmemalloc_wait as they should not be + * able to safely make forward progress. Wake them + */ + if (waitqueue_active(&pgdat->pfmemalloc_wait) && + pfmemalloc_watermark_ok(pgdat)) + wake_up(&pgdat->pfmemalloc_wait); + if (all_zones_ok || (order && pgdat_balanced(pgdat, balanced, *classzone_idx))) break; /* kswapd: all done */ /* @@ -2647,7 +2796,7 @@ out: } /* - * Return the order we were reclaiming at so sleeping_prematurely() + * Return the order we were reclaiming at so prepare_kswapd_sleep() * makes a decision on the order we were last reclaiming at. However, * if another caller entered the allocator slow path while kswapd * was awake, order will remain at the higher level @@ -2667,7 +2816,7 @@ static void kswapd_try_to_sleep(pg_data_t *pgdat, int order, int classzone_idx) prepare_to_wait(&pgdat->kswapd_wait, &wait, TASK_INTERRUPTIBLE); /* Try to sleep for a short interval */ - if (!sleeping_prematurely(pgdat, order, remaining, classzone_idx)) { + if (prepare_kswapd_sleep(pgdat, order, remaining, classzone_idx)) { remaining = schedule_timeout(HZ/10); finish_wait(&pgdat->kswapd_wait, &wait); prepare_to_wait(&pgdat->kswapd_wait, &wait, TASK_INTERRUPTIBLE); @@ -2677,7 +2826,7 @@ static void kswapd_try_to_sleep(pg_data_t *pgdat, int order, int classzone_idx) * After a short sleep, check if it was a premature sleep. If not, then * go fully to sleep until explicitly woken up. */ - if (!sleeping_prematurely(pgdat, order, remaining, classzone_idx)) { + if (prepare_kswapd_sleep(pgdat, order, remaining, classzone_idx)) { trace_mm_vmscan_kswapd_sleep(pgdat->node_id); /* diff --git a/mm/vmstat.c b/mm/vmstat.c index 1bbbbd9776ad..df7a6748231d 100644 --- a/mm/vmstat.c +++ b/mm/vmstat.c @@ -745,6 +745,7 @@ const char * const vmstat_text[] = { TEXTS_FOR_ZONES("pgsteal_direct") TEXTS_FOR_ZONES("pgscan_kswapd") TEXTS_FOR_ZONES("pgscan_direct") + "pgscan_direct_throttle", #ifdef CONFIG_NUMA "zone_reclaim_failed", |