diff options
Diffstat (limited to 'mm')
| -rw-r--r-- | mm/Kconfig | 27 | ||||
| -rw-r--r-- | mm/Makefile | 2 | ||||
| -rw-r--r-- | mm/backing-dev.c | 2 | ||||
| -rw-r--r-- | mm/bootmem.c | 8 | ||||
| -rw-r--r-- | mm/bounce.c | 2 | ||||
| -rw-r--r-- | mm/compaction.c | 17 | ||||
| -rw-r--r-- | mm/filemap.c | 60 | ||||
| -rw-r--r-- | mm/filemap_xip.c | 2 | ||||
| -rw-r--r-- | mm/huge_memory.c | 556 | ||||
| -rw-r--r-- | mm/hugetlb.c | 572 | ||||
| -rw-r--r-- | mm/hwpoison-inject.c | 9 | ||||
| -rw-r--r-- | mm/internal.h | 2 | ||||
| -rw-r--r-- | mm/kmemleak.c | 6 | ||||
| -rw-r--r-- | mm/ksm.c | 10 | ||||
| -rw-r--r-- | mm/list_lru.c | 140 | ||||
| -rw-r--r-- | mm/madvise.c | 38 | ||||
| -rw-r--r-- | mm/memblock.c | 142 | ||||
| -rw-r--r-- | mm/memcontrol.c | 515 | ||||
| -rw-r--r-- | mm/memory-failure.c | 206 | ||||
| -rw-r--r-- | mm/memory.c | 305 | ||||
| -rw-r--r-- | mm/memory_hotplug.c | 181 | ||||
| -rw-r--r-- | mm/mempolicy.c | 261 | ||||
| -rw-r--r-- | mm/mempool.c | 2 | ||||
| -rw-r--r-- | mm/migrate.c | 132 | ||||
| -rw-r--r-- | mm/mlock.c | 321 | ||||
| -rw-r--r-- | mm/mm_init.c | 18 | ||||
| -rw-r--r-- | mm/mmap.c | 82 | ||||
| -rw-r--r-- | mm/mmzone.c | 14 | ||||
| -rw-r--r-- | mm/mprotect.c | 76 | ||||
| -rw-r--r-- | mm/nobootmem.c | 25 | ||||
| -rw-r--r-- | mm/nommu.c | 5 | ||||
| -rw-r--r-- | mm/oom_kill.c | 13 | ||||
| -rw-r--r-- | mm/page-writeback.c | 294 | ||||
| -rw-r--r-- | mm/page_alloc.c | 326 | ||||
| -rw-r--r-- | mm/page_io.c | 1 | ||||
| -rw-r--r-- | mm/page_isolation.c | 14 | ||||
| -rw-r--r-- | mm/pagewalk.c | 2 | ||||
| -rw-r--r-- | mm/percpu.c | 5 | ||||
| -rw-r--r-- | mm/pgtable-generic.c | 40 | ||||
| -rw-r--r-- | mm/readahead.c | 16 | ||||
| -rw-r--r-- | mm/rmap.c | 37 | ||||
| -rw-r--r-- | mm/shmem.c | 6 | ||||
| -rw-r--r-- | mm/slab.c | 2 | ||||
| -rw-r--r-- | mm/slab.h | 6 | ||||
| -rw-r--r-- | mm/slab_common.c | 16 | ||||
| -rw-r--r-- | mm/slob.c | 28 | ||||
| -rw-r--r-- | mm/slub.c | 152 | ||||
| -rw-r--r-- | mm/sparse.c | 186 | ||||
| -rw-r--r-- | mm/swap.c | 124 | ||||
| -rw-r--r-- | mm/swap_state.c | 4 | ||||
| -rw-r--r-- | mm/swapfile.c | 616 | ||||
| -rw-r--r-- | mm/truncate.c | 9 | ||||
| -rw-r--r-- | mm/util.c | 18 | ||||
| -rw-r--r-- | mm/vmalloc.c | 77 | ||||
| -rw-r--r-- | mm/vmscan.c | 326 | ||||
| -rw-r--r-- | mm/vmstat.c | 117 | ||||
| -rw-r--r-- | mm/zbud.c | 4 | ||||
| -rw-r--r-- | mm/zswap.c | 215 |
58 files changed, 4079 insertions, 2313 deletions
diff --git a/mm/Kconfig b/mm/Kconfig index 79ac9915d504..eb69f352401d 100644 --- a/mm/Kconfig +++ b/mm/Kconfig @@ -153,11 +153,18 @@ config MOVABLE_NODE help Allow a node to have only movable memory. Pages used by the kernel, such as direct mapping pages cannot be migrated. So the corresponding - memory device cannot be hotplugged. This option allows users to - online all the memory of a node as movable memory so that the whole - node can be hotplugged. Users who don't use the memory hotplug - feature are fine with this option on since they don't online memory - as movable. + memory device cannot be hotplugged. This option allows the following + two things: + - When the system is booting, node full of hotpluggable memory can + be arranged to have only movable memory so that the whole node can + be hot-removed. (need movable_node boot option specified). + - After the system is up, the option allows users to online all the + memory of a node as movable memory so that the whole node can be + hot-removed. + + Users who don't use the memory hotplug feature are fine with this + option on since they don't specify movable_node boot option or they + don't online memory as movable. Say Y here if you want to hotplug a whole node. Say N here if you want kernel to use memory on all nodes evenly. @@ -183,7 +190,7 @@ config MEMORY_HOTPLUG_SPARSE config MEMORY_HOTREMOVE bool "Allow for memory hot remove" select MEMORY_ISOLATION - select HAVE_BOOTMEM_INFO_NODE if X86_64 + select HAVE_BOOTMEM_INFO_NODE if (X86_64 || PPC64) depends on MEMORY_HOTPLUG && ARCH_ENABLE_MEMORY_HOTREMOVE depends on MIGRATION @@ -211,9 +218,11 @@ config SPLIT_PTLOCK_CPUS int default "999999" if ARM && !CPU_CACHE_VIPT default "999999" if PARISC && !PA20 - default "999999" if DEBUG_SPINLOCK || DEBUG_LOCK_ALLOC default "4" +config ARCH_ENABLE_SPLIT_PMD_PTLOCK + boolean + # # support for memory balloon compaction config BALLOON_COMPACTION @@ -245,7 +254,7 @@ config COMPACTION config MIGRATION bool "Page migration" def_bool y - depends on NUMA || ARCH_ENABLE_MEMORY_HOTREMOVE || COMPACTION || CMA + depends on (NUMA || ARCH_ENABLE_MEMORY_HOTREMOVE || COMPACTION || CMA) && MMU help Allows the migration of the physical location of pages of processes while the virtual addresses are not changed. This is useful in @@ -480,7 +489,7 @@ config FRONTSWAP config CMA bool "Contiguous Memory Allocator" - depends on HAVE_MEMBLOCK + depends on HAVE_MEMBLOCK && MMU select MIGRATION select MEMORY_ISOLATION help diff --git a/mm/Makefile b/mm/Makefile index f00803386a67..305d10acd081 100644 --- a/mm/Makefile +++ b/mm/Makefile @@ -17,7 +17,7 @@ obj-y := filemap.o mempool.o oom_kill.o fadvise.o \ util.o mmzone.o vmstat.o backing-dev.o \ mm_init.o mmu_context.o percpu.o slab_common.o \ compaction.o balloon_compaction.o \ - interval_tree.o $(mmu-y) + interval_tree.o list_lru.o $(mmu-y) obj-y += init-mm.o diff --git a/mm/backing-dev.c b/mm/backing-dev.c index 37d9edcd14cf..ce682f7a4f29 100644 --- a/mm/backing-dev.c +++ b/mm/backing-dev.c @@ -652,7 +652,7 @@ int pdflush_proc_obsolete(struct ctl_table *table, int write, { char kbuf[] = "0\n"; - if (*ppos) { + if (*ppos || *lenp < sizeof(kbuf)) { *lenp = 0; return 0; } diff --git a/mm/bootmem.c b/mm/bootmem.c index 6ab7744e692e..90bd3507b413 100644 --- a/mm/bootmem.c +++ b/mm/bootmem.c @@ -172,11 +172,12 @@ void __init free_bootmem_late(unsigned long physaddr, unsigned long size) static unsigned long __init free_all_bootmem_core(bootmem_data_t *bdata) { struct page *page; - unsigned long start, end, pages, count = 0; + unsigned long *map, start, end, pages, count = 0; if (!bdata->node_bootmem_map) return 0; + map = bdata->node_bootmem_map; start = bdata->node_min_pfn; end = bdata->node_low_pfn; @@ -184,10 +185,9 @@ static unsigned long __init free_all_bootmem_core(bootmem_data_t *bdata) bdata - bootmem_node_data, start, end); while (start < end) { - unsigned long *map, idx, vec; + unsigned long idx, vec; unsigned shift; - map = bdata->node_bootmem_map; idx = start - bdata->node_min_pfn; shift = idx & (BITS_PER_LONG - 1); /* @@ -784,7 +784,7 @@ void * __init __alloc_bootmem_node_high(pg_data_t *pgdat, unsigned long size, return kzalloc_node(size, GFP_NOWAIT, pgdat->node_id); /* update goal according ...MAX_DMA32_PFN */ - end_pfn = pgdat->node_start_pfn + pgdat->node_spanned_pages; + end_pfn = pgdat_end_pfn(pgdat); if (end_pfn > MAX_DMA32_PFN + (128 >> (20 - PAGE_SHIFT)) && (goal >> PAGE_SHIFT) < MAX_DMA32_PFN) { diff --git a/mm/bounce.c b/mm/bounce.c index c9f0a4339a7d..5a7d58fb883b 100644 --- a/mm/bounce.c +++ b/mm/bounce.c @@ -204,6 +204,8 @@ static void __blk_queue_bounce(struct request_queue *q, struct bio **bio_orig, struct bio_vec *to, *from; unsigned i; + if (force) + goto bounce; bio_for_each_segment(from, *bio_orig, i) if (page_to_pfn(from->bv_page) > queue_bounce_pfn(q)) goto bounce; diff --git a/mm/compaction.c b/mm/compaction.c index 05ccb4cc0bdb..805165bcd3dd 100644 --- a/mm/compaction.c +++ b/mm/compaction.c @@ -235,10 +235,9 @@ static bool suitable_migration_target(struct page *page) } /* - * Isolate free pages onto a private freelist. Caller must hold zone->lock. - * If @strict is true, will abort returning 0 on any invalid PFNs or non-free - * pages inside of the pageblock (even though it may still end up isolating - * some pages). + * Isolate free pages onto a private freelist. If @strict is true, will abort + * returning 0 on any invalid PFNs or non-free pages inside of the pageblock + * (even though it may still end up isolating some pages). */ static unsigned long isolate_freepages_block(struct compact_control *cc, unsigned long blockpfn, @@ -677,6 +676,13 @@ static void isolate_freepages(struct zone *zone, pfn -= pageblock_nr_pages) { unsigned long isolated; + /* + * This can iterate a massively long zone without finding any + * suitable migration targets, so periodically check if we need + * to schedule. + */ + cond_resched(); + if (!pfn_valid(pfn)) continue; @@ -1131,6 +1137,9 @@ void compact_pgdat(pg_data_t *pgdat, int order) .sync = false, }; + if (!order) + return; + __compact_pgdat(pgdat, &cc); } diff --git a/mm/filemap.c b/mm/filemap.c index 731a2c24532d..b7749a92021c 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -467,32 +467,34 @@ int add_to_page_cache_locked(struct page *page, struct address_space *mapping, error = mem_cgroup_cache_charge(page, current->mm, gfp_mask & GFP_RECLAIM_MASK); if (error) - goto out; - - error = radix_tree_preload(gfp_mask & ~__GFP_HIGHMEM); - if (error == 0) { - page_cache_get(page); - page->mapping = mapping; - page->index = offset; + return error; - spin_lock_irq(&mapping->tree_lock); - error = radix_tree_insert(&mapping->page_tree, offset, page); - if (likely(!error)) { - mapping->nrpages++; - __inc_zone_page_state(page, NR_FILE_PAGES); - spin_unlock_irq(&mapping->tree_lock); - trace_mm_filemap_add_to_page_cache(page); - } else { - page->mapping = NULL; - /* Leave page->index set: truncation relies upon it */ - spin_unlock_irq(&mapping->tree_lock); - mem_cgroup_uncharge_cache_page(page); - page_cache_release(page); - } - radix_tree_preload_end(); - } else + error = radix_tree_maybe_preload(gfp_mask & ~__GFP_HIGHMEM); + if (error) { mem_cgroup_uncharge_cache_page(page); -out: + return error; + } + + page_cache_get(page); + page->mapping = mapping; + page->index = offset; + + spin_lock_irq(&mapping->tree_lock); + error = radix_tree_insert(&mapping->page_tree, offset, page); + radix_tree_preload_end(); + if (unlikely(error)) + goto err_insert; + mapping->nrpages++; + __inc_zone_page_state(page, NR_FILE_PAGES); + spin_unlock_irq(&mapping->tree_lock); + trace_mm_filemap_add_to_page_cache(page); + return 0; +err_insert: + page->mapping = NULL; + /* Leave page->index set: truncation relies upon it */ + spin_unlock_irq(&mapping->tree_lock); + mem_cgroup_uncharge_cache_page(page); + page_cache_release(page); return error; } EXPORT_SYMBOL(add_to_page_cache_locked); @@ -1088,7 +1090,6 @@ static void shrink_readahead_size_eio(struct file *filp, * @filp: the file to read * @ppos: current file position * @desc: read_descriptor - * @actor: read method * * This is a generic file read routine, and uses the * mapping->a_ops->readpage() function for the actual low-level stuff. @@ -1097,7 +1098,7 @@ static void shrink_readahead_size_eio(struct file *filp, * of the logic when it comes to error handling etc. */ static void do_generic_file_read(struct file *filp, loff_t *ppos, - read_descriptor_t *desc, read_actor_t actor) + read_descriptor_t *desc) { struct address_space *mapping = filp->f_mapping; struct inode *inode = mapping->host; @@ -1198,13 +1199,14 @@ page_ok: * Ok, we have the page, and it's up-to-date, so * now we can copy it to user space... * - * The actor routine returns how many bytes were actually used.. + * The file_read_actor routine returns how many bytes were + * actually used.. * NOTE! This may not be the same as how much of a user buffer * we filled up (we may be padding etc), so we can only update * "pos" here (the actor routine has to update the user buffer * pointers and the remaining count). */ - ret = actor(desc, page, offset, nr); + ret = file_read_actor(desc, page, offset, nr); offset += ret; index += offset >> PAGE_CACHE_SHIFT; offset &= ~PAGE_CACHE_MASK; @@ -1477,7 +1479,7 @@ generic_file_aio_read(struct kiocb *iocb, const struct iovec *iov, if (desc.count == 0) continue; desc.error = 0; - do_generic_file_read(filp, ppos, &desc, file_read_actor); + do_generic_file_read(filp, ppos, &desc); retval += desc.written; if (desc.error) { retval = retval ?: desc.error; diff --git a/mm/filemap_xip.c b/mm/filemap_xip.c index 28fe26b64f8a..d8d9fe3f685c 100644 --- a/mm/filemap_xip.c +++ b/mm/filemap_xip.c @@ -26,7 +26,7 @@ * of ZERO_PAGE(), such as /dev/zero */ static DEFINE_MUTEX(xip_sparse_mutex); -static seqcount_t xip_sparse_seq = SEQCNT_ZERO; +static seqcount_t xip_sparse_seq = SEQCNT_ZERO(xip_sparse_seq); static struct page *__xip_sparse_page; /* called under xip_sparse_mutex */ diff --git a/mm/huge_memory.c b/mm/huge_memory.c index a92012a71702..bccd5a628ea6 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -27,11 +27,12 @@ #include "internal.h" /* - * By default transparent hugepage support is enabled for all mappings - * and khugepaged scans all mappings. Defrag is only invoked by - * khugepaged hugepage allocations and by page faults inside - * MADV_HUGEPAGE regions to avoid the risk of slowing down short lived - * allocations. + * By default transparent hugepage support is disabled in order that avoid + * to risk increase the memory footprint of applications without a guaranteed + * benefit. When transparent hugepage support is enabled, is for all mappings, + * and khugepaged scans all mappings. + * Defrag is invoked by khugepaged hugepage allocations and by page faults + * for all hugepage allocations. */ unsigned long transparent_hugepage_flags __read_mostly = #ifdef CONFIG_TRANSPARENT_HUGEPAGE_ALWAYS @@ -211,24 +212,29 @@ static void put_huge_zero_page(void) BUG_ON(atomic_dec_and_test(&huge_zero_refcount)); } -static int shrink_huge_zero_page(struct shrinker *shrink, - struct shrink_control *sc) +static unsigned long shrink_huge_zero_page_count(struct shrinker *shrink, + struct shrink_control *sc) { - if (!sc->nr_to_scan) - /* we can free zero page only if last reference remains */ - return atomic_read(&huge_zero_refcount) == 1 ? HPAGE_PMD_NR : 0; + /* we can free zero page only if last reference remains */ + return atomic_read(&huge_zero_refcount) == 1 ? HPAGE_PMD_NR : 0; +} +static unsigned long shrink_huge_zero_page_scan(struct shrinker *shrink, + struct shrink_control *sc) +{ if (atomic_cmpxchg(&huge_zero_refcount, 1, 0) == 1) { struct page *zero_page = xchg(&huge_zero_page, NULL); BUG_ON(zero_page == NULL); __free_page(zero_page); + return HPAGE_PMD_NR; } return 0; } static struct shrinker huge_zero_page_shrinker = { - .shrink = shrink_huge_zero_page, + .count_objects = shrink_huge_zero_page_count, + .scan_objects = shrink_huge_zero_page_scan, .seeks = DEFAULT_SEEKS, }; @@ -417,7 +423,7 @@ static ssize_t scan_sleep_millisecs_store(struct kobject *kobj, unsigned long msecs; int err; - err = strict_strtoul(buf, 10, &msecs); + err = kstrtoul(buf, 10, &msecs); if (err || msecs > UINT_MAX) return -EINVAL; @@ -444,7 +450,7 @@ static ssize_t alloc_sleep_millisecs_store(struct kobject *kobj, unsigned long msecs; int err; - err = strict_strtoul(buf, 10, &msecs); + err = kstrtoul(buf, 10, &msecs); if (err || msecs > UINT_MAX) return -EINVAL; @@ -470,7 +476,7 @@ static ssize_t pages_to_scan_store(struct kobject *kobj, int err; unsigned long pages; - err = strict_strtoul(buf, 10, &pages); + err = kstrtoul(buf, 10, &pages); if (err || !pages || pages > UINT_MAX) return -EINVAL; @@ -538,7 +544,7 @@ static ssize_t khugepaged_max_ptes_none_store(struct kobject *kobj, int err; unsigned long max_ptes_none; - err = strict_strtoul(buf, 10, &max_ptes_none); + err = kstrtoul(buf, 10, &max_ptes_none); if (err || max_ptes_none > HPAGE_PMD_NR-1) return -EINVAL; @@ -690,11 +696,10 @@ pmd_t maybe_pmd_mkwrite(pmd_t pmd, struct vm_area_struct *vma) return pmd; } -static inline pmd_t mk_huge_pmd(struct page *page, struct vm_area_struct *vma) +static inline pmd_t mk_huge_pmd(struct page *page, pgprot_t prot) { pmd_t entry; - entry = mk_pmd(page, vma->vm_page_prot); - entry = maybe_pmd_mkwrite(pmd_mkdirty(entry), vma); + entry = mk_pmd(page, prot); entry = pmd_mkhuge(entry); return entry; } @@ -705,6 +710,7 @@ static int __do_huge_pmd_anonymous_page(struct mm_struct *mm, struct page *page) { pgtable_t pgtable; + spinlock_t *ptl; VM_BUG_ON(!PageCompound(page)); pgtable = pte_alloc_one(mm, haddr); @@ -719,21 +725,22 @@ static int __do_huge_pmd_anonymous_page(struct mm_struct *mm, */ __SetPageUptodate(page); - spin_lock(&mm->page_table_lock); + ptl = pmd_lock(mm, pmd); if (unlikely(!pmd_none(*pmd))) { - spin_unlock(&mm->page_table_lock); + spin_unlock(ptl); mem_cgroup_uncharge_page(page); put_page(page); pte_free(mm, pgtable); } else { pmd_t entry; - entry = mk_huge_pmd(page, vma); + entry = mk_huge_pmd(page, vma->vm_page_prot); + entry = maybe_pmd_mkwrite(pmd_mkdirty(entry), vma); page_add_new_anon_rmap(page, vma, haddr); pgtable_trans_huge_deposit(mm, pmd, pgtable); set_pmd_at(mm, haddr, pmd, entry); add_mm_counter(mm, MM_ANONPAGES, HPAGE_PMD_NR); - mm->nr_ptes++; - spin_unlock(&mm->page_table_lock); + atomic_long_inc(&mm->nr_ptes); + spin_unlock(ptl); } return 0; @@ -753,14 +760,7 @@ static inline struct page *alloc_hugepage_vma(int defrag, HPAGE_PMD_ORDER, vma, haddr, nd); } -#ifndef CONFIG_NUMA -static inline struct page *alloc_hugepage(int defrag) -{ - return alloc_pages(alloc_hugepage_gfpmask(defrag, 0), - HPAGE_PMD_ORDER); -} -#endif - +/* Caller must hold page table lock. */ static bool set_huge_zero_page(pgtable_t pgtable, struct mm_struct *mm, struct vm_area_struct *vma, unsigned long haddr, pmd_t *pmd, struct page *zero_page) @@ -773,7 +773,7 @@ static bool set_huge_zero_page(pgtable_t pgtable, struct mm_struct *mm, entry = pmd_mkhuge(entry); pgtable_trans_huge_deposit(mm, pmd, pgtable); set_pmd_at(mm, haddr, pmd, entry); - mm->nr_ptes++; + atomic_long_inc(&mm->nr_ptes); return true; } @@ -783,83 +783,65 @@ int do_huge_pmd_anonymous_page(struct mm_struct *mm, struct vm_area_struct *vma, { struct page *page; unsigned long haddr = address & HPAGE_PMD_MASK; - pte_t *pte; - if (haddr >= vma->vm_start && haddr + HPAGE_PMD_SIZE <= vma->vm_end) { - if (unlikely(anon_vma_prepare(vma))) - return VM_FAULT_OOM; - if (unlikely(khugepaged_enter(vma))) + if (haddr < vma->vm_start || haddr + HPAGE_PMD_SIZE > vma->vm_end) + return VM_FAULT_FALLBACK; + if (unlikely(anon_vma_prepare(vma))) + return VM_FAULT_OOM; + if (unlikely(khugepaged_enter(vma))) + return VM_FAULT_OOM; + if (!(flags & FAULT_FLAG_WRITE) && + transparent_hugepage_use_zero_page()) { + spinlock_t *ptl; + pgtable_t pgtable; + struct page *zero_page; + bool set; + pgtable = pte_alloc_one(mm, haddr); + if (unlikely(!pgtable)) return VM_FAULT_OOM; - if (!(flags & FAULT_FLAG_WRITE) && - transparent_hugepage_use_zero_page()) { - pgtable_t pgtable; - struct page *zero_page; - bool set; - pgtable = pte_alloc_one(mm, haddr); - if (unlikely(!pgtable)) - return VM_FAULT_OOM; - zero_page = get_huge_zero_page(); - if (unlikely(!zero_page)) { - pte_free(mm, pgtable); - count_vm_event(THP_FAULT_FALLBACK); - goto out; - } - spin_lock(&mm->page_table_lock); - set = set_huge_zero_page(pgtable, mm, vma, haddr, pmd, - zero_page); - spin_unlock(&mm->page_table_lock); - if (!set) { - pte_free(mm, pgtable); - put_huge_zero_page(); - } - return 0; - } - page = alloc_hugepage_vma(transparent_hugepage_defrag(vma), - vma, haddr, numa_node_id(), 0); - if (unlikely(!page)) { + zero_page = get_huge_zero_page(); + if (unlikely(!zero_page)) { + pte_free(mm, pgtable); count_vm_event(THP_FAULT_FALLBACK); - goto out; - } - count_vm_event(THP_FAULT_ALLOC); - if (unlikely(mem_cgroup_newpage_charge(page, mm, GFP_KERNEL))) { - put_page(page); - goto out; + return VM_FAULT_FALLBACK; } - if (unlikely(__do_huge_pmd_anonymous_page(mm, vma, haddr, pmd, - page))) { - mem_cgroup_uncharge_page(page); - put_page(page); - goto out; + ptl = pmd_lock(mm, pmd); + set = set_huge_zero_page(pgtable, mm, vma, haddr, pmd, + zero_page); + spin_unlock(ptl); + if (!set) { + pte_free(mm, pgtable); + put_huge_zero_page(); } - return 0; } -out: - /* - * Use __pte_alloc instead of pte_alloc_map, because we can't - * run pte_offset_map on the pmd, if an huge pmd could - * materialize from under us from a different thread. - */ - if (unlikely(pmd_none(*pmd)) && - unlikely(__pte_alloc(mm, vma, pmd, address))) - return VM_FAULT_OOM; - /* if an huge pmd materialized from under us just retry later */ - if (unlikely(pmd_trans_huge(*pmd))) - return 0; - /* - * A regular pmd is established and it can't morph into a huge pmd - * from under us anymore at this point because we hold the mmap_sem - * read mode and khugepaged takes it in write mode. So now it's - * safe to run pte_offset_map(). - */ - pte = pte_offset_map(pmd, address); - return handle_pte_fault(mm, vma, address, pte, pmd, flags); + page = alloc_hugepage_vma(transparent_hugepage_defrag(vma), + vma, haddr, numa_node_id(), 0); + if (unlikely(!page)) { + count_vm_event(THP_FAULT_FALLBACK); + return VM_FAULT_FALLBACK; + } + if (unlikely(mem_cgroup_newpage_charge(page, mm, GFP_KERNEL))) { + put_page(page); + count_vm_event(THP_FAULT_FALLBACK); + return VM_FAULT_FALLBACK; + } + if (unlikely(__do_huge_pmd_anonymous_page(mm, vma, haddr, pmd, page))) { + mem_cgroup_uncharge_page(page); + put_page(page); + count_vm_event(THP_FAULT_FALLBACK); + return VM_FAULT_FALLBACK; + } + + count_vm_event(THP_FAULT_ALLOC); + return 0; } int copy_huge_pmd(struct mm_struct *dst_mm, struct mm_struct *src_mm, pmd_t *dst_pmd, pmd_t *src_pmd, unsigned long addr, struct vm_area_struct *vma) { + spinlock_t *dst_ptl, *src_ptl; struct page *src_page; pmd_t pmd; pgtable_t pgtable; @@ -870,8 +852,9 @@ int copy_huge_pmd(struct mm_struct *dst_mm, struct mm_struct *src_mm, if (unlikely(!pgtable)) goto out; - spin_lock(&dst_mm->page_table_lock); - spin_lock_nested(&src_mm->page_table_lock, SINGLE_DEPTH_NESTING); + dst_ptl = pmd_lock(dst_mm, dst_pmd); + src_ptl = pmd_lockptr(src_mm, src_pmd); + spin_lock_nested(src_ptl, SINGLE_DEPTH_NESTING); ret = -EAGAIN; pmd = *src_pmd; @@ -880,7 +863,7 @@ int copy_huge_pmd(struct mm_struct *dst_mm, struct mm_struct *src_mm, goto out_unlock; } /* - * mm->page_table_lock is enough to be sure that huge zero pmd is not + * When page table lock is held, the huge zero pmd should not be * under splitting since we don't split the page itself, only pmd to * a page table. */ @@ -901,8 +884,8 @@ int copy_huge_pmd(struct mm_struct *dst_mm, struct mm_struct *src_mm, } if (unlikely(pmd_trans_splitting(pmd))) { /* split huge page running from under us */ - spin_unlock(&src_mm->page_table_lock); - spin_unlock(&dst_mm->page_table_lock); + spin_unlock(src_ptl); + spin_unlock(dst_ptl); pte_free(dst_mm, pgtable); wait_split_huge_page(vma->anon_vma, src_pmd); /* src_vma */ @@ -918,12 +901,12 @@ int copy_huge_pmd(struct mm_struct *dst_mm, struct mm_struct *src_mm, pmd = pmd_mkold(pmd_wrprotect(pmd)); pgtable_trans_huge_deposit(dst_mm, dst_pmd, pgtable); set_pmd_at(dst_mm, addr, dst_pmd, pmd); - dst_mm->nr_ptes++; + atomic_long_inc(&dst_mm->nr_ptes); ret = 0; out_unlock: - spin_unlock(&src_mm->page_table_lock); - spin_unlock(&dst_mm->page_table_lock); + spin_unlock(src_ptl); + spin_unlock(dst_ptl); out: return ret; } @@ -934,10 +917,11 @@ void huge_pmd_set_accessed(struct mm_struct *mm, pmd_t *pmd, pmd_t orig_pmd, int dirty) { + spinlock_t *ptl; pmd_t entry; unsigned long haddr; - spin_lock(&mm->page_table_lock); + ptl = pmd_lock(mm, pmd); if (unlikely(!pmd_same(*pmd, orig_pmd))) goto unlock; @@ -947,13 +931,14 @@ void huge_pmd_set_accessed(struct mm_struct *mm, update_mmu_cache_pmd(vma, address, pmd); unlock: - spin_unlock(&mm->page_table_lock); + spin_unlock(ptl); } static int do_huge_pmd_wp_zero_page_fallback(struct mm_struct *mm, struct vm_area_struct *vma, unsigned long address, pmd_t *pmd, pmd_t orig_pmd, unsigned long haddr) { + spinlock_t *ptl; pgtable_t pgtable; pmd_t _pmd; struct page *page; @@ -980,7 +965,7 @@ static int do_huge_pmd_wp_zero_page_fallback(struct mm_struct *mm, mmun_end = haddr + HPAGE_PMD_SIZE; mmu_notifier_invalidate_range_start(mm, mmun_start, mmun_end); - spin_lock(&mm->page_table_lock); + ptl = pmd_lock(mm, pmd); if (unlikely(!pmd_same(*pmd, orig_pmd))) goto out_free_page; @@ -1007,7 +992,7 @@ static int do_huge_pmd_wp_zero_page_fallback(struct mm_struct *mm, } smp_wmb(); /* make pte visible before pmd */ pmd_populate(mm, pmd, pgtable); - spin_unlock(&mm->page_table_lock); + spin_unlock(ptl); put_huge_zero_page(); inc_mm_counter(mm, MM_ANONPAGES); @@ -1017,7 +1002,7 @@ static int do_huge_pmd_wp_zero_page_fallback(struct mm_struct *mm, out: return ret; out_free_page: - spin_unlock(&mm->page_table_lock); + spin_unlock(ptl); mmu_notifier_invalidate_range_end(mm, mmun_start, mmun_end); mem_cgroup_uncharge_page(page); put_page(page); @@ -1031,6 +1016,7 @@ static int do_huge_pmd_wp_page_fallback(struct mm_struct *mm, struct page *page, unsigned long haddr) { + spinlock_t *ptl; pgtable_t pgtable; pmd_t _pmd; int ret = 0, i; @@ -1077,7 +1063,7 @@ static int do_huge_pmd_wp_page_fallback(struct mm_struct *mm, mmun_end = haddr + HPAGE_PMD_SIZE; mmu_notifier_invalidate_range_start(mm, mmun_start, mmun_end); - spin_lock(&mm->page_table_lock); + ptl = pmd_lock(mm, pmd); if (unlikely(!pmd_same(*pmd, orig_pmd))) goto out_free_pages; VM_BUG_ON(!PageHead(page)); @@ -1103,7 +1089,7 @@ static int do_huge_pmd_wp_page_fallback(struct mm_struct *mm, smp_wmb(); /* make pte visible before pmd */ pmd_populate(mm, pmd, pgtable); page_remove_rmap(page); - spin_unlock(&mm->page_table_lock); + spin_unlock(ptl); mmu_notifier_invalidate_range_end(mm, mmun_start, mmun_end); @@ -1114,7 +1100,7 @@ out: return ret; out_free_pages: - spin_unlock(&mm->page_table_lock); + spin_unlock(ptl); mmu_notifier_invalidate_range_end(mm, mmun_start, mmun_end); mem_cgroup_uncharge_start(); for (i = 0; i < HPAGE_PMD_NR; i++) { @@ -1129,17 +1115,19 @@ out_free_pages: int do_huge_pmd_wp_page(struct mm_struct *mm, struct vm_area_struct *vma, unsigned long address, pmd_t *pmd, pmd_t orig_pmd) { + spinlock_t *ptl; int ret = 0; struct page *page = NULL, *new_page; unsigned long haddr; unsigned long mmun_start; /* For mmu_notifiers */ unsigned long mmun_end; /* For mmu_notifiers */ + ptl = pmd_lockptr(mm, pmd); VM_BUG_ON(!vma->anon_vma); haddr = address & HPAGE_PMD_MASK; if (is_huge_zero_pmd(orig_pmd)) goto alloc; - spin_lock(&mm->page_table_lock); + spin_lock(ptl); if (unlikely(!pmd_same(*pmd, orig_pmd))) goto out_unlock; @@ -1155,7 +1143,7 @@ int do_huge_pmd_wp_page(struct mm_struct *mm, struct vm_area_struct *vma, goto out_unlock; } get_page(page); - spin_unlock(&mm->page_table_lock); + spin_unlock(ptl); alloc: if (transparent_hugepage_enabled(vma) && !transparent_hugepage_debug_cow()) @@ -1165,7 +1153,6 @@ alloc: new_page = NULL; if (unlikely(!new_page)) { - count_vm_event(THP_FAULT_FALLBACK); if (is_huge_zero_pmd(orig_pmd)) { ret = do_huge_pmd_wp_zero_page_fallback(mm, vma, address, pmd, orig_pmd, haddr); @@ -1176,9 +1163,9 @@ alloc: split_huge_page(page); put_page(page); } + count_vm_event(THP_FAULT_FALLBACK); goto out; } - count_vm_event(THP_FAULT_ALLOC); if (unlikely(mem_cgroup_newpage_charge(new_page, mm, GFP_KERNEL))) { put_page(new_page); @@ -1186,10 +1173,13 @@ alloc: split_huge_page(page); put_page(page); } + count_vm_event(THP_FAULT_FALLBACK); ret |= VM_FAULT_OOM; goto out; } + count_vm_event(THP_FAULT_ALLOC); + if (is_huge_zero_pmd(orig_pmd)) clear_huge_page(new_page, haddr, HPAGE_PMD_NR); else @@ -1200,17 +1190,18 @@ alloc: mmun_end = haddr + HPAGE_PMD_SIZE; mmu_notifier_invalidate_range_start(mm, mmun_start, mmun_end); - spin_lock(&mm->page_table_lock); + spin_lock(ptl); if (page) put_page(page); if (unlikely(!pmd_same(*pmd, orig_pmd))) { - spin_unlock(&mm->page_table_lock); + spin_unlock(ptl); mem_cgroup_uncharge_page(new_page); put_page(new_page); goto out_mn; } else { pmd_t entry; - entry = mk_huge_pmd(new_page, vma); + entry = mk_huge_pmd(new_page, vma->vm_page_prot); + entry = maybe_pmd_mkwrite(pmd_mkdirty(entry), vma); pmdp_clear_flush(vma, haddr, pmd); page_add_new_anon_rmap(new_page, vma, haddr); set_pmd_at(mm, haddr, pmd, entry); @@ -1225,13 +1216,13 @@ alloc: } ret |= VM_FAULT_WRITE; } - spin_unlock(&mm->page_table_lock); + spin_unlock(ptl); out_mn: mmu_notifier_invalidate_range_end(mm, mmun_start, mmun_end); out: return ret; out_unlock: - spin_unlock(&mm->page_table_lock); + spin_unlock(ptl); return ret; } @@ -1243,7 +1234,7 @@ struct page *follow_trans_huge_pmd(struct vm_area_struct *vma, struct mm_struct *mm = vma->vm_mm; struct page *page = NULL; - assert_spin_locked(&mm->page_table_lock); + assert_spin_locked(pmd_lockptr(mm, pmd)); if (flags & FOLL_WRITE && !pmd_write(*pmd)) goto out; @@ -1290,73 +1281,116 @@ out: int do_huge_pmd_numa_page(struct mm_struct *mm, struct vm_area_struct *vma, unsigned long addr, pmd_t pmd, pmd_t *pmdp) { + spinlock_t *ptl; + struct anon_vma *anon_vma = NULL; struct page *page; unsigned long haddr = addr & HPAGE_PMD_MASK; - int target_nid; - int current_nid = -1; - bool migrated; + int page_nid = -1, this_nid = numa_node_id(); + int target_nid, last_cpupid = -1; + bool page_locked; + bool migrated = false; + int flags = 0; - spin_lock(&mm->page_table_lock); + ptl = pmd_lock(mm, pmdp); if (unlikely(!pmd_same(pmd, *pmdp))) goto out_unlock; page = pmd_page(pmd); - get_page(page); - current_nid = page_to_nid(page); + BUG_ON(is_huge_zero_page(page)); + page_nid = page_to_nid(page); + last_cpupid = page_cpupid_last(page); count_vm_numa_event(NUMA_HINT_FAULTS); - if (current_nid == numa_node_id()) + if (page_nid == this_nid) { count_vm_numa_event(NUMA_HINT_FAULTS_LOCAL); + flags |= TNF_FAULT_LOCAL; + } + + /* + * Avoid grouping on DSO/COW pages in specific and RO pages + * in general, RO pages shouldn't hurt as much anyway since + * they can be in shared cache state. + */ + if (!pmd_write(pmd)) + flags |= TNF_NO_GROUP; + /* + * Acquire the page lock to serialise THP migrations but avoid dropping + * page_table_lock if at all possible + */ + page_locked = trylock_page(page); target_nid = mpol_misplaced(page, vma, haddr); if (target_nid == -1) { - put_page(page); - goto clear_pmdnuma; + /* If the page was locked, there are no parallel migrations */ + if (page_locked) + goto clear_pmdnuma; + + /* + * Otherwise wait for potential migrations and retry. We do + * relock and check_same as the page may no longer be mapped. + * As the fault is being retried, do not account for it. + */ + spin_unlock(ptl); + wait_on_page_locked(page); + page_nid = -1; + goto out; } - /* Acquire the page lock to serialise THP migrations */ - spin_unlock(&mm->page_table_lock); - lock_page(page); + /* Page is misplaced, serialise migrations and parallel THP splits */ + get_page(page); + spin_unlock(ptl); + if (!page_locked) + lock_page(page); + anon_vma = page_lock_anon_vma_read(page); - /* Confirm the PTE did not while locked */ - spin_lock(&mm->page_table_lock); + /* Confirm the PMD did not change while page_table_lock was released */ + spin_lock(ptl); if (unlikely(!pmd_same(pmd, *pmdp))) { unlock_page(page); put_page(page); + page_nid = -1; goto out_unlock; } - spin_unlock(&mm->page_table_lock); - /* Migrate the THP to the requested node */ + /* + * Migrate the THP to the requested node, returns with page unlocked + * and pmd_numa cleared. + */ + spin_unlock(ptl); migrated = migrate_misplaced_transhuge_page(mm, vma, pmdp, pmd, addr, page, target_nid); - if (!migrated) - goto check_same; - - task_numa_fault(target_nid, HPAGE_PMD_NR, true); - return 0; + if (migrated) { + flags |= TNF_MIGRATED; + page_nid = target_nid; + } -check_same: - spin_lock(&mm->page_table_lock); - if (unlikely(!pmd_same(pmd, *pmdp))) - goto out_unlock; + goto out; clear_pmdnuma: + BUG_ON(!PageLocked(page)); pmd = pmd_mknonnuma(pmd); set_pmd_at(mm, haddr, pmdp, pmd); VM_BUG_ON(pmd_numa(*pmdp)); update_mmu_cache_pmd(vma, addr, pmdp); + unlock_page(page); out_unlock: - spin_unlock(&mm->page_table_lock); - if (current_nid != -1) - task_numa_fault(current_nid, HPAGE_PMD_NR, false); + spin_unlock(ptl); + +out: + if (anon_vma) + page_unlock_anon_vma_read(anon_vma); + + if (page_nid != -1) + task_numa_fault(last_cpupid, page_nid, HPAGE_PMD_NR, flags); + return 0; } int zap_huge_pmd(struct mmu_gather *tlb, struct vm_area_struct *vma, pmd_t *pmd, unsigned long addr) { + spinlock_t *ptl; int ret = 0; - if (__pmd_trans_huge_lock(pmd, vma) == 1) { + if (__pmd_trans_huge_lock(pmd, vma, &ptl) == 1) { struct page *page; pgtable_t pgtable; pmd_t orig_pmd; @@ -1370,8 +1404,8 @@ int zap_huge_pmd(struct mmu_gather *tlb, struct vm_area_struct *vma, tlb_remove_pmd_tlb_entry(tlb, pmd, addr); pgtable = pgtable_trans_huge_withdraw(tlb->mm, pmd); if (is_huge_zero_pmd(orig_pmd)) { - tlb->mm->nr_ptes--; - spin_unlock(&tlb->mm->page_table_lock); + atomic_long_dec(&tlb->mm->nr_ptes); + spin_unlock(ptl); put_huge_zero_page(); } else { page = pmd_page(orig_pmd); @@ -1379,8 +1413,8 @@ int zap_huge_pmd(struct mmu_gather *tlb, struct vm_area_struct *vma, VM_BUG_ON(page_mapcount(page) < 0); add_mm_counter(tlb->mm, MM_ANONPAGES, -HPAGE_PMD_NR); VM_BUG_ON(!PageHead(page)); - tlb->mm->nr_ptes--; - spin_unlock(&tlb->mm->page_table_lock); + atomic_long_dec(&tlb->mm->nr_ptes); + spin_unlock(ptl); tlb_remove_page(tlb, page); } pte_free(tlb->mm, pgtable); @@ -1393,14 +1427,15 @@ int mincore_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd, unsigned long addr, unsigned long end, unsigned char *vec) { + spinlock_t *ptl; int ret = 0; - if (__pmd_trans_huge_lock(pmd, vma) == 1) { + if (__pmd_trans_huge_lock(pmd, vma, &ptl) == 1) { /* * All logical pages in the range are present * if backed by a huge page. */ - spin_unlock(&vma->vm_mm->page_table_lock); + spin_unlock(ptl); memset(vec, 1, (end - addr) >> PAGE_SHIFT); ret = 1; } @@ -1413,6 +1448,7 @@ int move_huge_pmd(struct vm_area_struct *vma, struct vm_area_struct *new_vma, unsigned long new_addr, unsigned long old_end, pmd_t *old_pmd, pmd_t *new_pmd) { + spinlock_t *old_ptl, *new_ptl; int ret = 0; pmd_t pmd; @@ -1433,41 +1469,69 @@ int move_huge_pmd(struct vm_area_struct *vma, struct vm_area_struct *new_vma, goto out; } - ret = __pmd_trans_huge_lock(old_pmd, vma); + /* + * We don't have to worry about the ordering of src and dst + * ptlocks because exclusive mmap_sem prevents deadlock. + */ + ret = __pmd_trans_huge_lock(old_pmd, vma, &old_ptl); if (ret == 1) { + new_ptl = pmd_lockptr(mm, new_pmd); + if (new_ptl != old_ptl) + spin_lock_nested(new_ptl, SINGLE_DEPTH_NESTING); pmd = pmdp_get_and_clear(mm, old_addr, old_pmd); VM_BUG_ON(!pmd_none(*new_pmd)); set_pmd_at(mm, new_addr, new_pmd, pmd_mksoft_dirty(pmd)); - spin_unlock(&mm->page_table_lock); + if (new_ptl != old_ptl) + spin_unlock(new_ptl); + spin_unlock(old_ptl); } out: return ret; } +/* + * Returns + * - 0 if PMD could not be locked + * - 1 if PMD was locked but protections unchange and TLB flush unnecessary + * - HPAGE_PMD_NR is protections changed and TLB flush necessary + */ int change_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd, unsigned long addr, pgprot_t newprot, int prot_numa) { struct mm_struct *mm = vma->vm_mm; + spinlock_t *ptl; int ret = 0; - if (__pmd_trans_huge_lock(pmd, vma) == 1) { + if (__pmd_trans_huge_lock(pmd, vma, &ptl) == 1) { pmd_t entry; - entry = pmdp_get_and_clear(mm, addr, pmd); + ret = 1; if (!prot_numa) { + entry = pmdp_get_and_clear(mm, addr, pmd); entry = pmd_modify(entry, newprot); + ret = HPAGE_PMD_NR; BUG_ON(pmd_write(entry)); } else { struct page *page = pmd_page(*pmd); - /* only check non-shared pages */ - if (page_mapcount(page) == 1 && + /* + * Do not trap faults against the zero page. The + * read-only data is likely to be read-cached on the + * local CPU cache and it is less useful to know about + * local vs remote hits on the zero page. + */ + if (!is_huge_zero_page(page) && !pmd_numa(*pmd)) { + entry = pmdp_get_and_clear(mm, addr, pmd); entry = pmd_mknuma(entry); + ret = HPAGE_PMD_NR; } } - set_pmd_at(mm, addr, pmd, entry); - spin_unlock(&vma->vm_mm->page_table_lock); - ret = 1; + + /* Set PMD if cleared earlier */ + if (ret == HPAGE_PMD_NR) + set_pmd_at(mm, addr, pmd, entry); + + spin_unlock(ptl); } return ret; @@ -1480,12 +1544,13 @@ int change_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd, * Note that if it returns 1, this routine returns without unlocking page * table locks. So callers must unlock them. */ -int __pmd_trans_huge_lock(pmd_t *pmd, struct vm_area_struct *vma) +int __pmd_trans_huge_lock(pmd_t *pmd, struct vm_area_struct *vma, + spinlock_t **ptl) { - spin_lock(&vma->vm_mm->page_table_lock); + *ptl = pmd_lock(vma->vm_mm, pmd); if (likely(pmd_trans_huge(*pmd))) { if (unlikely(pmd_trans_splitting(*pmd))) { - spin_unlock(&vma->vm_mm->page_table_lock); + spin_unlock(*ptl); wait_split_huge_page(vma->anon_vma, pmd); return -1; } else { @@ -1494,27 +1559,37 @@ int __pmd_trans_huge_lock(pmd_t *pmd, struct vm_area_struct *vma) return 1; } } - spin_unlock(&vma->vm_mm->page_table_lock); + spin_unlock(*ptl); return 0; } +/* + * This function returns whether a given @page is mapped onto the @address + * in the virtual space of @mm. + * + * When it's true, this function returns *pmd with holding the page table lock + * and passing it back to the caller via @ptl. + * If it's false, returns NULL without holding the page table lock. + */ pmd_t *page_check_address_pmd(struct page *page, struct mm_struct *mm, unsigned long address, - enum page_check_address_pmd_flag flag) + enum page_check_address_pmd_flag flag, + spinlock_t **ptl) { - pmd_t *pmd, *ret = NULL; + pmd_t *pmd; if (address & ~HPAGE_PMD_MASK) - goto out; + return NULL; pmd = mm_find_pmd(mm, address); if (!pmd) - goto out; + return NULL; + *ptl = pmd_lock(mm, pmd); if (pmd_none(*pmd)) - goto out; + goto unlock; if (pmd_page(*pmd) != page) - goto out; + goto unlock; /* * split_vma() may create temporary aliased mappings. There is * no risk as long as all huge pmd are found and have their @@ -1524,14 +1599,15 @@ pmd_t *page_check_address_pmd(struct page *page, */ if (flag == PAGE_CHECK_ADDRESS_PMD_NOTSPLITTING_FLAG && pmd_trans_splitting(*pmd)) - goto out; + goto unlock; if (pmd_trans_huge(*pmd)) { VM_BUG_ON(flag == PAGE_CHECK_ADDRESS_PMD_SPLITTING_FLAG && !pmd_trans_splitting(*pmd)); - ret = pmd; + return pmd; } -out: - return ret; +unlock: + spin_unlock(*ptl); + return NULL; } static int __split_huge_page_splitting(struct page *page, @@ -1539,6 +1615,7 @@ static int __split_huge_page_splitting(struct page *page, unsigned long address) { struct mm_struct *mm = vma->vm_mm; + spinlock_t *ptl; pmd_t *pmd; int ret = 0; /* For mmu_notifiers */ @@ -1546,9 +1623,8 @@ static int __split_huge_page_splitting(struct page *page, const unsigned long mmun_end = address + HPAGE_PMD_SIZE; mmu_notifier_invalidate_range_start(mm, mmun_start, mmun_end); - spin_lock(&mm->page_table_lock); pmd = page_check_address_pmd(page, mm, address, - PAGE_CHECK_ADDRESS_PMD_NOTSPLITTING_FLAG); + PAGE_CHECK_ADDRESS_PMD_NOTSPLITTING_FLAG, &ptl); if (pmd) { /* * We can't temporarily set the pmd to null in order @@ -1559,8 +1635,8 @@ static int __split_huge_page_splitting(struct page *page, */ pmdp_splitting_flush(vma, address, pmd); ret = 1; + spin_unlock(ptl); } - spin_unlock(&mm->page_table_lock); mmu_notifier_invalidate_range_end(mm, mmun_start, mmun_end); return ret; @@ -1648,7 +1724,7 @@ static void __split_huge_page_refcount(struct page *page, page_tail->mapping = page->mapping; page_tail->index = page->index + i; - page_nid_xchg_last(page_tail, page_nid_last(page)); + page_cpupid_xchg_last(page_tail, page_cpupid_last(page)); BUG_ON(!PageAnon(page_tail)); BUG_ON(!PageUptodate(page_tail)); @@ -1661,7 +1737,6 @@ static void __split_huge_page_refcount(struct page *page, BUG_ON(atomic_read(&page->_count) <= 0); __mod_zone_page_state(zone, NR_ANON_TRANSPARENT_HUGEPAGES, -1); - __mod_zone_page_state(zone, NR_ANON_PAGES, HPAGE_PMD_NR); ClearPageCompound(page); compound_unlock(page); @@ -1692,14 +1767,14 @@ static int __split_huge_page_map(struct page *page, unsigned long address) { struct mm_struct *mm = vma->vm_mm; + spinlock_t *ptl; pmd_t *pmd, _pmd; int ret = 0, i; pgtable_t pgtable; unsigned long haddr; - spin_lock(&mm->page_table_lock); pmd = page_check_address_pmd(page, mm, address, - PAGE_CHECK_ADDRESS_PMD_SPLITTING_FLAG); + PAGE_CHECK_ADDRESS_PMD_SPLITTING_FLAG, &ptl); if (pmd) { pgtable = pgtable_trans_huge_withdraw(mm, pmd); pmd_populate(mm, &_pmd, pgtable); @@ -1754,8 +1829,8 @@ static int __split_huge_page_map(struct page *page, pmdp_invalidate(vma, address, pmd); pmd_populate(mm, pmd, pgtable); ret = 1; + spin_unlock(ptl); } - spin_unlock(&mm->page_table_lock); return ret; } @@ -2152,7 +2227,34 @@ static void khugepaged_alloc_sleep(void) msecs_to_jiffies(khugepaged_alloc_sleep_millisecs)); } +static int khugepaged_node_load[MAX_NUMNODES]; + #ifdef CONFIG_NUMA +static int khugepaged_find_target_node(void) +{ + static int last_khugepaged_target_node = NUMA_NO_NODE; + int nid, target_node = 0, max_value = 0; + + /* find first node with max normal pages hit */ + for (nid = 0; nid < MAX_NUMNODES; nid++) + if (khugepaged_node_load[nid] > max_value) { + max_value = khugepaged_node_load[nid]; + target_node = nid; + } + + /* do some balance if several nodes have the same hit record */ + if (target_node <= last_khugepaged_target_node) + for (nid = last_khugepaged_target_node + 1; nid < MAX_NUMNODES; + nid++) + if (max_value == khugepaged_node_load[nid]) { + target_node = nid; + break; + } + + last_khugepaged_target_node = target_node; + return target_node; +} + static bool khugepaged_prealloc_page(struct page **hpage, bool *wait) { if (IS_ERR(*hpage)) { @@ -2186,9 +2288,8 @@ static struct page * mmap_sem in read mode is good idea also to allow greater * scalability. */ - *hpage = alloc_hugepage_vma(khugepaged_defrag(), vma, address, - node, __GFP_OTHER_NODE); - + *hpage = alloc_pages_exact_node(node, alloc_hugepage_gfpmask( + khugepaged_defrag(), __GFP_OTHER_NODE), HPAGE_PMD_ORDER); /* * After allocating the hugepage, release the mmap_sem read lock in * preparation for taking it in write mode. @@ -2204,6 +2305,17 @@ static struct page return *hpage; } #else +static int khugepaged_find_target_node(void) +{ + return 0; +} + +static inline struct page *alloc_hugepage(int defrag) +{ + return alloc_pages(alloc_hugepage_gfpmask(defrag, 0), + HPAGE_PMD_ORDER); +} + static struct page *khugepaged_alloc_hugepage(bool *wait) { struct page *hpage; @@ -2270,7 +2382,7 @@ static void collapse_huge_page(struct mm_struct *mm, pte_t *pte; pgtable_t pgtable; struct page *new_page; - spinlock_t *ptl; + spinlock_t *pmd_ptl, *pte_ptl; int isolated; unsigned long hstart, hend; unsigned long mmun_start; /* For mmu_notifiers */ @@ -2296,6 +2408,8 @@ static void collapse_huge_page(struct mm_struct *mm, goto out; vma = find_vma(mm, address); + if (!vma) + goto out; hstart = (vma->vm_start + ~HPAGE_PMD_MASK) & HPAGE_PMD_MASK; hend = vma->vm_end & HPAGE_PMD_MASK; if (address < hstart || address + HPAGE_PMD_SIZE > hend) @@ -2311,12 +2425,12 @@ static void collapse_huge_page(struct mm_struct *mm, anon_vma_lock_write(vma->anon_vma); pte = pte_offset_map(pmd, address); - ptl = pte_lockptr(mm, pmd); + pte_ptl = pte_lockptr(mm, pmd); mmun_start = address; mmun_end = address + HPAGE_PMD_SIZE; mmu_notifier_invalidate_range_start(mm, mmun_start, mmun_end); - spin_lock(&mm->page_table_lock); /* probably unnecessary */ + pmd_ptl = pmd_lock(mm, pmd); /* probably unnecessary */ /* * After this gup_fast can't run anymore. This also removes * any huge TLB entry from the CPU so we won't allow @@ -2324,16 +2438,16 @@ static void collapse_huge_page(struct mm_struct *mm, * to avoid the risk of CPU bugs in that area. */ _pmd = pmdp_clear_flush(vma, address, pmd); - spin_unlock(&mm->page_table_lock); + spin_unlock(pmd_ptl); mmu_notifier_invalidate_range_end(mm, mmun_start, mmun_end); - spin_lock(ptl); + spin_lock(pte_ptl); isolated = __collapse_huge_page_isolate(vma, address, pte); - spin_unlock(ptl); + spin_unlock(pte_ptl); if (unlikely(!isolated)) { pte_unmap(pte); - spin_lock(&mm->page_table_lock); + spin_lock(pmd_ptl); BUG_ON(!pmd_none(*pmd)); /* * We can only use set_pmd_at when establishing @@ -2341,7 +2455,7 @@ static void collapse_huge_page(struct mm_struct *mm, * points to regular pagetables. Use pmd_populate for that */ pmd_populate(mm, pmd, pmd_pgtable(_pmd)); - spin_unlock(&mm->page_table_lock); + spin_unlock(pmd_ptl); anon_vma_unlock_write(vma->anon_vma); goto out; } @@ -2352,12 +2466,13 @@ static void collapse_huge_page(struct mm_struct *mm, */ anon_vma_unlock_write(vma->anon_vma); - __collapse_huge_page_copy(pte, new_page, vma, address, ptl); + __collapse_huge_page_copy(pte, new_page, vma, address, pte_ptl); pte_unmap(pte); __SetPageUptodate(new_page); pgtable = pmd_pgtable(_pmd); - _pmd = mk_huge_pmd(new_page, vma); + _pmd = mk_huge_pmd(new_page, vma->vm_page_prot); + _pmd = maybe_pmd_mkwrite(pmd_mkdirty(_pmd), vma); /* * spin_lock() below is not the equivalent of smp_wmb(), so @@ -2366,13 +2481,13 @@ static void collapse_huge_page(struct mm_struct *mm, */ smp_wmb(); - spin_lock(&mm->page_table_lock); + spin_lock(pmd_ptl); BUG_ON(!pmd_none(*pmd)); page_add_new_anon_rmap(new_page, vma, address); pgtable_trans_huge_deposit(mm, pmd, pgtable); set_pmd_at(mm, address, pmd, _pmd); update_mmu_cache_pmd(vma, address, pmd); - spin_unlock(&mm->page_table_lock); + spin_unlock(pmd_ptl); *hpage = NULL; @@ -2407,6 +2522,7 @@ static int khugepaged_scan_pmd(struct mm_struct *mm, if (pmd_trans_huge(*pmd)) goto out; + memset(khugepaged_node_load, 0, sizeof(khugepaged_node_load)); pte = pte_offset_map_lock(mm, pmd, address, &ptl); for (_address = address, _pte = pte; _pte < pte+HPAGE_PMD_NR; _pte++, _address += PAGE_SIZE) { @@ -2423,12 +2539,13 @@ static int khugepaged_scan_pmd(struct mm_struct *mm, if (unlikely(!page)) goto out_unmap; /* - * Chose the node of the first page. This could - * be more sophisticated and look at more pages, - * but isn't for now. + * Record which node the original page is from and save this + * information to khugepaged_node_load[]. + * Khupaged will allocate hugepage from the node has the max + * hit record. */ - if (node == NUMA_NO_NODE) - node = page_to_nid(page); + node = page_to_nid(page); + khugepaged_node_load[node]++; VM_BUG_ON(PageCompound(page)); if (!PageLRU(page) || PageLocked(page) || !PageAnon(page)) goto out_unmap; @@ -2443,9 +2560,11 @@ static int khugepaged_scan_pmd(struct mm_struct *mm, ret = 1; out_unmap: pte_unmap_unlock(pte, ptl); - if (ret) + if (ret) { + node = khugepaged_find_target_node(); /* collapse_huge_page will return with the mmap_sem released */ collapse_huge_page(mm, address, hpage, vma, node); + } out: return ret; } @@ -2697,6 +2816,7 @@ static void __split_huge_zero_page_pmd(struct vm_area_struct *vma, void __split_huge_page_pmd(struct vm_area_struct *vma, unsigned long address, pmd_t *pmd) { + spinlock_t *ptl; struct page *page; struct mm_struct *mm = vma->vm_mm; unsigned long haddr = address & HPAGE_PMD_MASK; @@ -2707,29 +2827,37 @@ void __split_huge_page_pmd(struct vm_area_struct *vma, unsigned long address, mmun_start = haddr; mmun_end = haddr + HPAGE_PMD_SIZE; +again: mmu_notifier_invalidate_range_start(mm, mmun_start, mmun_end); - spin_lock(&mm->page_table_lock); + ptl = pmd_lock(mm, pmd); if (unlikely(!pmd_trans_huge(*pmd))) { - spin_unlock(&mm->page_table_lock); + spin_unlock(ptl); mmu_notifier_invalidate_range_end(mm, mmun_start, mmun_end); return; } if (is_huge_zero_pmd(*pmd)) { __split_huge_zero_page_pmd(vma, haddr, pmd); - spin_unlock(&mm->page_table_lock); + spin_unlock(ptl); mmu_notifier_invalidate_range_end(mm, mmun_start, mmun_end); return; } page = pmd_page(*pmd); VM_BUG_ON(!page_count(page)); get_page(page); - spin_unlock(&mm->page_table_lock); + spin_unlock(ptl); mmu_notifier_invalidate_range_end(mm, mmun_start, mmun_end); split_huge_page(page); put_page(page); - BUG_ON(pmd_trans_huge(*pmd)); + + /* + * We don't always have down_write of mmap_sem here: a racing + * do_huge_pmd_wp_page() might have copied-on-write to another + * huge page before our split_huge_page() got the anon_vma lock. + */ + if (unlikely(pmd_trans_huge(*pmd))) + goto again; } void split_huge_page_pmd_mm(struct mm_struct *mm, unsigned long address, diff --git a/mm/hugetlb.c b/mm/hugetlb.c index b60f33080a28..7d57af21f49e 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -21,6 +21,7 @@ #include <linux/rmap.h> #include <linux/swap.h> #include <linux/swapops.h> +#include <linux/page-isolation.h> #include <asm/page.h> #include <asm/pgtable.h> @@ -33,7 +34,6 @@ #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; int hugetlb_max_hstate __read_mostly; @@ -48,7 +48,8 @@ static unsigned long __initdata default_hstate_max_huge_pages; static unsigned long __initdata default_hstate_size; /* - * Protects updates to hugepage_freelists, nr_huge_pages, and free_huge_pages + * Protects updates to hugepage_freelists, hugepage_activelist, nr_huge_pages, + * free_huge_pages, and surplus_huge_pages. */ DEFINE_SPINLOCK(hugetlb_lock); @@ -135,9 +136,9 @@ static inline struct hugepage_subpool *subpool_vma(struct vm_area_struct *vma) * across the pages in a mapping. * * The region data structures are protected by a combination of the mmap_sem - * and the hugetlb_instantion_mutex. To access or modify a region the caller + * and the hugetlb_instantiation_mutex. To access or modify a region the caller * must either hold the mmap_sem for write, or the mmap_sem for read and - * the hugetlb_instantiation mutex: + * the hugetlb_instantiation_mutex: * * down_write(&mm->mmap_sem); * or @@ -434,25 +435,6 @@ static int is_vma_resv_set(struct vm_area_struct *vma, unsigned long flag) return (get_vma_private_data(vma) & flag) != 0; } -/* Decrement the reserved pages in the hugepage pool by one */ -static void decrement_hugepage_resv_vma(struct hstate *h, - struct vm_area_struct *vma) -{ - if (vma->vm_flags & VM_NORESERVE) - return; - - if (vma->vm_flags & VM_MAYSHARE) { - /* Shared mappings always use reserves */ - h->resv_huge_pages--; - } else if (is_vma_resv_set(vma, HPAGE_RESV_OWNER)) { - /* - * Only the process that called mmap() has reserves for - * private mappings. - */ - h->resv_huge_pages--; - } -} - /* Reset counters to 0 and clear all HPAGE_RESV_* flags */ void reset_vma_resv_huge_pages(struct vm_area_struct *vma) { @@ -462,12 +444,35 @@ void reset_vma_resv_huge_pages(struct vm_area_struct *vma) } /* Returns true if the VMA has associated reserve pages */ -static int vma_has_reserves(struct vm_area_struct *vma) +static int vma_has_reserves(struct vm_area_struct *vma, long chg) { + if (vma->vm_flags & VM_NORESERVE) { + /* + * This address is already reserved by other process(chg == 0), + * so, we should decrement reserved count. Without decrementing, + * reserve count remains after releasing inode, because this + * allocated page will go into page cache and is regarded as + * coming from reserved pool in releasing step. Currently, we + * don't have any other solution to deal with this situation + * properly, so add work-around here. + */ + if (vma->vm_flags & VM_MAYSHARE && chg == 0) + return 1; + else + return 0; + } + + /* Shared mappings always use reserves */ if (vma->vm_flags & VM_MAYSHARE) return 1; + + /* + * Only the process that called mmap() has reserves for + * private mappings. + */ if (is_vma_resv_set(vma, HPAGE_RESV_OWNER)) return 1; + return 0; } @@ -517,9 +522,15 @@ static struct page *dequeue_huge_page_node(struct hstate *h, int nid) { struct page *page; - if (list_empty(&h->hugepage_freelists[nid])) + list_for_each_entry(page, &h->hugepage_freelists[nid], lru) + if (!is_migrate_isolate_page(page)) + break; + /* + * if 'non-isolated free hugepage' not found on the list, + * the allocation fails. + */ + if (&h->hugepage_freelists[nid] == &page->lru) return NULL; - page = list_entry(h->hugepage_freelists[nid].next, struct page, lru); list_move(&page->lru, &h->hugepage_activelist); set_page_refcounted(page); h->free_huge_pages--; @@ -527,9 +538,19 @@ static struct page *dequeue_huge_page_node(struct hstate *h, int nid) return page; } +/* Movability of hugepages depends on migration support. */ +static inline gfp_t htlb_alloc_mask(struct hstate *h) +{ + if (hugepages_treat_as_movable || hugepage_migration_support(h)) + return GFP_HIGHUSER_MOVABLE; + else + return GFP_HIGHUSER; +} + static struct page *dequeue_huge_page_vma(struct hstate *h, struct vm_area_struct *vma, - unsigned long address, int avoid_reserve) + unsigned long address, int avoid_reserve, + long chg) { struct page *page = NULL; struct mempolicy *mpol; @@ -539,16 +560,12 @@ static struct page *dequeue_huge_page_vma(struct hstate *h, struct zoneref *z; unsigned int cpuset_mems_cookie; -retry_cpuset: - cpuset_mems_cookie = get_mems_allowed(); - zonelist = huge_zonelist(vma, address, - htlb_alloc_mask, &mpol, &nodemask); /* * A child process with MAP_PRIVATE mappings created by their parent * have no page reserves. This check ensures that reservations are * not "stolen". The child may still get SIGKILLed */ - if (!vma_has_reserves(vma) && + if (!vma_has_reserves(vma, chg) && h->free_huge_pages - h->resv_huge_pages == 0) goto err; @@ -556,13 +573,23 @@ retry_cpuset: if (avoid_reserve && h->free_huge_pages - h->resv_huge_pages == 0) goto err; +retry_cpuset: + cpuset_mems_cookie = get_mems_allowed(); + zonelist = huge_zonelist(vma, address, + htlb_alloc_mask(h), &mpol, &nodemask); + for_each_zone_zonelist_nodemask(zone, z, zonelist, MAX_NR_ZONES - 1, nodemask) { - if (cpuset_zone_allowed_softwall(zone, htlb_alloc_mask)) { + if (cpuset_zone_allowed_softwall(zone, htlb_alloc_mask(h))) { page = dequeue_huge_page_node(h, zone_to_nid(zone)); if (page) { - if (!avoid_reserve) - decrement_hugepage_resv_vma(h, vma); + if (avoid_reserve) + break; + if (!vma_has_reserves(vma, chg)) + break; + + SetPagePrivate(page); + h->resv_huge_pages--; break; } } @@ -574,7 +601,6 @@ retry_cpuset: return page; err: - mpol_cond_put(mpol); return NULL; } @@ -620,15 +646,21 @@ static void free_huge_page(struct page *page) int nid = page_to_nid(page); struct hugepage_subpool *spool = (struct hugepage_subpool *)page_private(page); + bool restore_reserve; set_page_private(page, 0); page->mapping = NULL; BUG_ON(page_count(page)); BUG_ON(page_mapcount(page)); + restore_reserve = PagePrivate(page); + ClearPagePrivate(page); spin_lock(&hugetlb_lock); hugetlb_cgroup_uncharge_page(hstate_index(h), pages_per_huge_page(h), page); + if (restore_reserve) + h->resv_huge_pages++; + if (h->surplus_huge_pages_node[nid] && huge_page_order(h) < MAX_ORDER) { /* remove the page from active list */ list_del(&page->lru); @@ -664,8 +696,22 @@ static void prep_compound_gigantic_page(struct page *page, unsigned long order) /* we rely on prep_new_huge_page to set the destructor */ set_compound_order(page, order); __SetPageHead(page); + __ClearPageReserved(page); for (i = 1; i < nr_pages; i++, p = mem_map_next(p, page, i)) { __SetPageTail(p); + /* + * For gigantic hugepages allocated through bootmem at + * boot, it's safer to be consistent with the not-gigantic + * hugepages and clear the PG_reserved bit from all tail pages + * too. Otherwse drivers using get_user_pages() to access tail + * pages may get the reference counting wrong if they see + * PG_reserved set on a tail page (despite the head page not + * having PG_reserved set). Enforcing this consistency between + * head and tail pages allows drivers to optimize away a check + * on the head page when they need know if put_page() is needed + * after get_user_pages(). + */ + __ClearPageReserved(p); set_page_count(p, 0); p->first_page = page; } @@ -715,7 +761,7 @@ static struct page *alloc_fresh_huge_page_node(struct hstate *h, int nid) return NULL; page = alloc_pages_exact_node(nid, - htlb_alloc_mask|__GFP_COMP|__GFP_THISNODE| + htlb_alloc_mask(h)|__GFP_COMP|__GFP_THISNODE| __GFP_REPEAT|__GFP_NOWARN, huge_page_order(h)); if (page) { @@ -772,33 +818,6 @@ static int hstate_next_node_to_alloc(struct hstate *h, return nid; } -static int alloc_fresh_huge_page(struct hstate *h, nodemask_t *nodes_allowed) -{ - struct page *page; - int start_nid; - int next_nid; - int ret = 0; - - start_nid = hstate_next_node_to_alloc(h, nodes_allowed); - next_nid = start_nid; - - do { - page = alloc_fresh_huge_page_node(h, next_nid); - if (page) { - ret = 1; - break; - } - next_nid = hstate_next_node_to_alloc(h, nodes_allowed); - } while (next_nid != start_nid); - - if (ret) - count_vm_event(HTLB_BUDDY_PGALLOC); - else - count_vm_event(HTLB_BUDDY_PGALLOC_FAIL); - - return ret; -} - /* * helper for free_pool_huge_page() - return the previously saved * node ["this node"] from which to free a huge page. Advance the @@ -817,6 +836,40 @@ static int hstate_next_node_to_free(struct hstate *h, nodemask_t *nodes_allowed) return nid; } +#define for_each_node_mask_to_alloc(hs, nr_nodes, node, mask) \ + for (nr_nodes = nodes_weight(*mask); \ + nr_nodes > 0 && \ + ((node = hstate_next_node_to_alloc(hs, mask)) || 1); \ + nr_nodes--) + +#define for_each_node_mask_to_free(hs, nr_nodes, node, mask) \ + for (nr_nodes = nodes_weight(*mask); \ + nr_nodes > 0 && \ + ((node = hstate_next_node_to_free(hs, mask)) || 1); \ + nr_nodes--) + +static int alloc_fresh_huge_page(struct hstate *h, nodemask_t *nodes_allowed) +{ + struct page *page; + int nr_nodes, node; + int ret = 0; + + for_each_node_mask_to_alloc(h, nr_nodes, node, nodes_allowed) { + page = alloc_fresh_huge_page_node(h, node); + if (page) { + ret = 1; + break; + } + } + + if (ret) + count_vm_event(HTLB_BUDDY_PGALLOC); + else + count_vm_event(HTLB_BUDDY_PGALLOC_FAIL); + + return ret; +} + /* * Free huge page from pool from next node to free. * Attempt to keep persistent huge pages more or less @@ -826,40 +879,73 @@ static int hstate_next_node_to_free(struct hstate *h, nodemask_t *nodes_allowed) static int free_pool_huge_page(struct hstate *h, nodemask_t *nodes_allowed, bool acct_surplus) { - int start_nid; - int next_nid; + int nr_nodes, node; int ret = 0; - start_nid = hstate_next_node_to_free(h, nodes_allowed); - next_nid = start_nid; - - do { + for_each_node_mask_to_free(h, nr_nodes, node, nodes_allowed) { /* * If we're returning unused surplus pages, only examine * nodes with surplus pages. */ - if ((!acct_surplus || h->surplus_huge_pages_node[next_nid]) && - !list_empty(&h->hugepage_freelists[next_nid])) { + if ((!acct_surplus || h->surplus_huge_pages_node[node]) && + !list_empty(&h->hugepage_freelists[node])) { struct page *page = - list_entry(h->hugepage_freelists[next_nid].next, + list_entry(h->hugepage_freelists[node].next, struct page, lru); list_del(&page->lru); h->free_huge_pages--; - h->free_huge_pages_node[next_nid]--; + h->free_huge_pages_node[node]--; if (acct_surplus) { h->surplus_huge_pages--; - h->surplus_huge_pages_node[next_nid]--; + h->surplus_huge_pages_node[node]--; } update_and_free_page(h, page); ret = 1; break; } - next_nid = hstate_next_node_to_free(h, nodes_allowed); - } while (next_nid != start_nid); + } return ret; } +/* + * Dissolve a given free hugepage into free buddy pages. This function does + * nothing for in-use (including surplus) hugepages. + */ +static void dissolve_free_huge_page(struct page *page) +{ + spin_lock(&hugetlb_lock); + if (PageHuge(page) && !page_count(page)) { + struct hstate *h = page_hstate(page); + int nid = page_to_nid(page); + list_del(&page->lru); + h->free_huge_pages--; + h->free_huge_pages_node[nid]--; + update_and_free_page(h, page); + } + spin_unlock(&hugetlb_lock); +} + +/* + * Dissolve free hugepages in a given pfn range. Used by memory hotplug to + * make specified memory blocks removable from the system. + * Note that start_pfn should aligned with (minimum) hugepage size. + */ +void dissolve_free_huge_pages(unsigned long start_pfn, unsigned long end_pfn) +{ + unsigned int order = 8 * sizeof(void *); + unsigned long pfn; + struct hstate *h; + + /* Set scan step to minimum hugepage size */ + for_each_hstate(h) + if (order > huge_page_order(h)) + order = huge_page_order(h); + VM_BUG_ON(!IS_ALIGNED(start_pfn, 1 << order)); + for (pfn = start_pfn; pfn < end_pfn; pfn += 1 << order) + dissolve_free_huge_page(pfn_to_page(pfn)); +} + static struct page *alloc_buddy_huge_page(struct hstate *h, int nid) { struct page *page; @@ -902,12 +988,12 @@ static struct page *alloc_buddy_huge_page(struct hstate *h, int nid) spin_unlock(&hugetlb_lock); if (nid == NUMA_NO_NODE) - page = alloc_pages(htlb_alloc_mask|__GFP_COMP| + page = alloc_pages(htlb_alloc_mask(h)|__GFP_COMP| __GFP_REPEAT|__GFP_NOWARN, huge_page_order(h)); else page = alloc_pages_exact_node(nid, - htlb_alloc_mask|__GFP_COMP|__GFP_THISNODE| + htlb_alloc_mask(h)|__GFP_COMP|__GFP_THISNODE| __GFP_REPEAT|__GFP_NOWARN, huge_page_order(h)); if (page && arch_prepare_hugepage(page)) { @@ -944,10 +1030,11 @@ static struct page *alloc_buddy_huge_page(struct hstate *h, int nid) */ struct page *alloc_huge_page_node(struct hstate *h, int nid) { - struct page *page; + struct page *page = NULL; spin_lock(&hugetlb_lock); - page = dequeue_huge_page_node(h, nid); + if (h->free_huge_pages - h->resv_huge_pages > 0) + page = dequeue_huge_page_node(h, nid); spin_unlock(&hugetlb_lock); if (!page) @@ -1035,11 +1122,8 @@ free: spin_unlock(&hugetlb_lock); /* Free unnecessary surplus pages to the buddy allocator */ - if (!list_empty(&surplus_list)) { - list_for_each_entry_safe(page, tmp, &surplus_list, lru) { - put_page(page); - } - } + list_for_each_entry_safe(page, tmp, &surplus_list, lru) + put_page(page); spin_lock(&hugetlb_lock); return ret; @@ -1106,9 +1190,9 @@ static long vma_needs_reservation(struct hstate *h, } else { long err; pgoff_t idx = vma_hugecache_offset(h, vma, addr); - struct resv_map *reservations = vma_resv_map(vma); + struct resv_map *resv = vma_resv_map(vma); - err = region_chg(&reservations->regions, idx, idx + 1); + err = region_chg(&resv->regions, idx, idx + 1); if (err < 0) return err; return 0; @@ -1126,10 +1210,10 @@ static void vma_commit_reservation(struct hstate *h, } else if (is_vma_resv_set(vma, HPAGE_RESV_OWNER)) { pgoff_t idx = vma_hugecache_offset(h, vma, addr); - struct resv_map *reservations = vma_resv_map(vma); + struct resv_map *resv = vma_resv_map(vma); /* Mark this page used in the map. */ - region_add(&reservations->regions, idx, idx + 1); + region_add(&resv->regions, idx, idx + 1); } } @@ -1155,38 +1239,35 @@ static struct page *alloc_huge_page(struct vm_area_struct *vma, chg = vma_needs_reservation(h, vma, addr); if (chg < 0) return ERR_PTR(-ENOMEM); - if (chg) - if (hugepage_subpool_get_pages(spool, chg)) + if (chg || avoid_reserve) + if (hugepage_subpool_get_pages(spool, 1)) 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); + if (chg || avoid_reserve) + hugepage_subpool_put_pages(spool, 1); return ERR_PTR(-ENOSPC); } spin_lock(&hugetlb_lock); - page = dequeue_huge_page_vma(h, vma, addr, avoid_reserve); - if (page) { - /* update page cgroup details */ - hugetlb_cgroup_commit_charge(idx, pages_per_huge_page(h), - h_cg, page); - spin_unlock(&hugetlb_lock); - } else { + page = dequeue_huge_page_vma(h, vma, addr, avoid_reserve, chg); + if (!page) { 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); + if (chg || avoid_reserve) + hugepage_subpool_put_pages(spool, 1); 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); + /* Fall through */ } + hugetlb_cgroup_commit_charge(idx, pages_per_huge_page(h), h_cg, page); + spin_unlock(&hugetlb_lock); set_page_private(page, (unsigned long)spool); @@ -1194,17 +1275,29 @@ static struct page *alloc_huge_page(struct vm_area_struct *vma, return page; } +/* + * alloc_huge_page()'s wrapper which simply returns the page if allocation + * succeeds, otherwise NULL. This function is called from new_vma_page(), + * where no ERR_VALUE is expected to be returned. + */ +struct page *alloc_huge_page_noerr(struct vm_area_struct *vma, + unsigned long addr, int avoid_reserve) +{ + struct page *page = alloc_huge_page(vma, addr, avoid_reserve); + if (IS_ERR(page)) + page = NULL; + return page; +} + int __weak alloc_bootmem_huge_page(struct hstate *h) { struct huge_bootmem_page *m; - int nr_nodes = nodes_weight(node_states[N_MEMORY]); + int nr_nodes, node; - while (nr_nodes) { + for_each_node_mask_to_alloc(h, nr_nodes, node, &node_states[N_MEMORY]) { void *addr; - addr = __alloc_bootmem_node_nopanic( - NODE_DATA(hstate_next_node_to_alloc(h, - &node_states[N_MEMORY])), + addr = __alloc_bootmem_node_nopanic(NODE_DATA(node), huge_page_size(h), huge_page_size(h), 0); if (addr) { @@ -1216,7 +1309,6 @@ int __weak alloc_bootmem_huge_page(struct hstate *h) m = addr; goto found; } - nr_nodes--; } return 0; @@ -1252,9 +1344,9 @@ static void __init gather_bootmem_prealloc(void) #else page = virt_to_page(m); #endif - __ClearPageReserved(page); WARN_ON(page_count(page) != 1); prep_compound_huge_page(page, h->order); + WARN_ON(PageReserved(page)); prep_new_huge_page(h, page, page_to_nid(page)); /* * If we had gigantic hugepages allocated at boot time, we need @@ -1355,48 +1447,28 @@ static inline void try_to_free_low(struct hstate *h, unsigned long count, static int adjust_pool_surplus(struct hstate *h, nodemask_t *nodes_allowed, int delta) { - int start_nid, next_nid; - int ret = 0; + int nr_nodes, node; VM_BUG_ON(delta != -1 && delta != 1); - if (delta < 0) - start_nid = hstate_next_node_to_alloc(h, nodes_allowed); - else - start_nid = hstate_next_node_to_free(h, nodes_allowed); - next_nid = start_nid; - - do { - int nid = next_nid; - if (delta < 0) { - /* - * To shrink on this node, there must be a surplus page - */ - if (!h->surplus_huge_pages_node[nid]) { - next_nid = hstate_next_node_to_alloc(h, - nodes_allowed); - continue; - } + if (delta < 0) { + for_each_node_mask_to_alloc(h, nr_nodes, node, nodes_allowed) { + if (h->surplus_huge_pages_node[node]) + goto found; } - if (delta > 0) { - /* - * Surplus cannot exceed the total number of pages - */ - if (h->surplus_huge_pages_node[nid] >= - h->nr_huge_pages_node[nid]) { - next_nid = hstate_next_node_to_free(h, - nodes_allowed); - continue; - } + } else { + for_each_node_mask_to_free(h, nr_nodes, node, nodes_allowed) { + if (h->surplus_huge_pages_node[node] < + h->nr_huge_pages_node[node]) + goto found; } + } + return 0; - h->surplus_huge_pages += delta; - h->surplus_huge_pages_node[nid] += delta; - ret = 1; - break; - } while (next_nid != start_nid); - - return ret; +found: + h->surplus_huge_pages += delta; + h->surplus_huge_pages_node[node] += delta; + return 1; } #define persistent_huge_pages(h) (h->nr_huge_pages - h->surplus_huge_pages) @@ -1526,7 +1598,7 @@ static ssize_t nr_hugepages_store_common(bool obey_mempolicy, struct hstate *h; NODEMASK_ALLOC(nodemask_t, nodes_allowed, GFP_KERNEL | __GFP_NORETRY); - err = strict_strtoul(buf, 10, &count); + err = kstrtoul(buf, 10, &count); if (err) goto out; @@ -1617,7 +1689,7 @@ static ssize_t nr_overcommit_hugepages_store(struct kobject *kobj, if (h->order >= MAX_ORDER) return -EINVAL; - err = strict_strtoul(buf, 10, &input); + err = kstrtoul(buf, 10, &input); if (err) return err; @@ -2068,18 +2140,6 @@ int hugetlb_mempolicy_sysctl_handler(struct ctl_table *table, int write, } #endif /* CONFIG_NUMA */ -int hugetlb_treat_movable_handler(struct ctl_table *table, int write, - void __user *buffer, - size_t *length, loff_t *ppos) -{ - proc_dointvec(table, write, buffer, length, ppos); - if (hugepages_treat_as_movable) - htlb_alloc_mask = GFP_HIGHUSER_MOVABLE; - else - htlb_alloc_mask = GFP_HIGHUSER; - return 0; -} - int hugetlb_overcommit_handler(struct ctl_table *table, int write, void __user *buffer, size_t *length, loff_t *ppos) @@ -2207,7 +2267,7 @@ out: static void hugetlb_vm_op_open(struct vm_area_struct *vma) { - struct resv_map *reservations = vma_resv_map(vma); + struct resv_map *resv = vma_resv_map(vma); /* * This new VMA should share its siblings reservation map if present. @@ -2217,34 +2277,34 @@ static void hugetlb_vm_op_open(struct vm_area_struct *vma) * after this open call completes. It is therefore safe to take a * new reference here without additional locking. */ - if (reservations) - kref_get(&reservations->refs); + if (resv) + kref_get(&resv->refs); } static void resv_map_put(struct vm_area_struct *vma) { - struct resv_map *reservations = vma_resv_map(vma); + struct resv_map *resv = vma_resv_map(vma); - if (!reservations) + if (!resv) return; - kref_put(&reservations->refs, resv_map_release); + kref_put(&resv->refs, resv_map_release); } static void hugetlb_vm_op_close(struct vm_area_struct *vma) { struct hstate *h = hstate_vma(vma); - struct resv_map *reservations = vma_resv_map(vma); + struct resv_map *resv = vma_resv_map(vma); struct hugepage_subpool *spool = subpool_vma(vma); unsigned long reserve; unsigned long start; unsigned long end; - if (reservations) { + if (resv) { start = vma_hugecache_offset(h, vma, vma->vm_start); end = vma_hugecache_offset(h, vma, vma->vm_end); reserve = (end - start) - - region_count(&reservations->regions, start, end); + region_count(&resv->regions, start, end); resv_map_put(vma); @@ -2316,6 +2376,7 @@ int copy_hugetlb_page_range(struct mm_struct *dst, struct mm_struct *src, cow = (vma->vm_flags & (VM_SHARED | VM_MAYWRITE)) == VM_MAYWRITE; for (addr = vma->vm_start; addr < vma->vm_end; addr += sz) { + spinlock_t *src_ptl, *dst_ptl; src_pte = huge_pte_offset(src, addr); if (!src_pte) continue; @@ -2327,8 +2388,9 @@ int copy_hugetlb_page_range(struct mm_struct *dst, struct mm_struct *src, if (dst_pte == src_pte) continue; - spin_lock(&dst->page_table_lock); - spin_lock_nested(&src->page_table_lock, SINGLE_DEPTH_NESTING); + dst_ptl = huge_pte_lock(h, dst, dst_pte); + src_ptl = huge_pte_lockptr(h, src, src_pte); + spin_lock_nested(src_ptl, SINGLE_DEPTH_NESTING); if (!huge_pte_none(huge_ptep_get(src_pte))) { if (cow) huge_ptep_set_wrprotect(src, addr, src_pte); @@ -2338,8 +2400,8 @@ int copy_hugetlb_page_range(struct mm_struct *dst, struct mm_struct *src, page_dup_rmap(ptepage); set_huge_pte_at(dst, addr, dst_pte, entry); } - spin_unlock(&src->page_table_lock); - spin_unlock(&dst->page_table_lock); + spin_unlock(src_ptl); + spin_unlock(dst_ptl); } return 0; @@ -2382,6 +2444,7 @@ void __unmap_hugepage_range(struct mmu_gather *tlb, struct vm_area_struct *vma, unsigned long address; pte_t *ptep; pte_t pte; + spinlock_t *ptl; struct page *page; struct hstate *h = hstate_vma(vma); unsigned long sz = huge_page_size(h); @@ -2395,25 +2458,25 @@ void __unmap_hugepage_range(struct mmu_gather *tlb, struct vm_area_struct *vma, tlb_start_vma(tlb, vma); mmu_notifier_invalidate_range_start(mm, mmun_start, mmun_end); again: - spin_lock(&mm->page_table_lock); for (address = start; address < end; address += sz) { ptep = huge_pte_offset(mm, address); if (!ptep) continue; + ptl = huge_pte_lock(h, mm, ptep); if (huge_pmd_unshare(mm, &address, ptep)) - continue; + goto unlock; pte = huge_ptep_get(ptep); if (huge_pte_none(pte)) - continue; + goto unlock; /* * HWPoisoned hugepage is already unmapped and dropped reference */ if (unlikely(is_hugetlb_entry_hwpoisoned(pte))) { huge_pte_clear(mm, address, ptep); - continue; + goto unlock; } page = pte_page(pte); @@ -2424,7 +2487,7 @@ again: */ if (ref_page) { if (page != ref_page) - continue; + goto unlock; /* * Mark the VMA as having unmapped its page so that @@ -2441,13 +2504,18 @@ again: page_remove_rmap(page); force_flush = !__tlb_remove_page(tlb, page); - if (force_flush) + if (force_flush) { + spin_unlock(ptl); break; + } /* Bail out after unmapping reference page if supplied */ - if (ref_page) + if (ref_page) { + spin_unlock(ptl); break; + } +unlock: + spin_unlock(ptl); } - spin_unlock(&mm->page_table_lock); /* * mmu_gather ran out of room to batch pages, we break out of * the PTE lock to avoid doing the potential expensive TLB invalidate @@ -2553,11 +2621,10 @@ static int unmap_ref_private(struct mm_struct *mm, struct vm_area_struct *vma, */ static int hugetlb_cow(struct mm_struct *mm, struct vm_area_struct *vma, unsigned long address, pte_t *ptep, pte_t pte, - struct page *pagecache_page) + struct page *pagecache_page, spinlock_t *ptl) { struct hstate *h = hstate_vma(vma); struct page *old_page, *new_page; - int avoidcopy; int outside_reserve = 0; unsigned long mmun_start; /* For mmu_notifiers */ unsigned long mmun_end; /* For mmu_notifiers */ @@ -2567,10 +2634,8 @@ static int hugetlb_cow(struct mm_struct *mm, struct vm_area_struct *vma, retry_avoidcopy: /* If no-one else is actually using this page, avoid the copy * and just make the page writable */ - avoidcopy = (page_mapcount(old_page) == 1); - if (avoidcopy) { - if (PageAnon(old_page)) - page_move_anon_rmap(old_page, vma, address); + if (page_mapcount(old_page) == 1 && PageAnon(old_page)) { + page_move_anon_rmap(old_page, vma, address); set_huge_ptep_writable(vma, address, ptep); return 0; } @@ -2584,15 +2649,14 @@ retry_avoidcopy: * at the time of fork() could consume its reserves on COW instead * of the full address range. */ - if (!(vma->vm_flags & VM_MAYSHARE) && - is_vma_resv_set(vma, HPAGE_RESV_OWNER) && + if (is_vma_resv_set(vma, HPAGE_RESV_OWNER) && old_page != pagecache_page) outside_reserve = 1; page_cache_get(old_page); - /* Drop page_table_lock as buddy allocator may be called */ - spin_unlock(&mm->page_table_lock); + /* Drop page table lock as buddy allocator may be called */ + spin_unlock(ptl); new_page = alloc_huge_page(vma, address, outside_reserve); if (IS_ERR(new_page)) { @@ -2610,13 +2674,13 @@ retry_avoidcopy: BUG_ON(huge_pte_none(pte)); if (unmap_ref_private(mm, vma, old_page, address)) { BUG_ON(huge_pte_none(pte)); - spin_lock(&mm->page_table_lock); + spin_lock(ptl); ptep = huge_pte_offset(mm, address & huge_page_mask(h)); if (likely(pte_same(huge_ptep_get(ptep), pte))) goto retry_avoidcopy; /* - * race occurs while re-acquiring page_table_lock, and - * our job is done. + * race occurs while re-acquiring page table + * lock, and our job is done. */ return 0; } @@ -2624,7 +2688,7 @@ retry_avoidcopy: } /* Caller expects lock to be held */ - spin_lock(&mm->page_table_lock); + spin_lock(ptl); if (err == -ENOMEM) return VM_FAULT_OOM; else @@ -2639,7 +2703,7 @@ retry_avoidcopy: page_cache_release(new_page); page_cache_release(old_page); /* Caller expects lock to be held */ - spin_lock(&mm->page_table_lock); + spin_lock(ptl); return VM_FAULT_OOM; } @@ -2651,12 +2715,14 @@ retry_avoidcopy: mmun_end = mmun_start + huge_page_size(h); mmu_notifier_invalidate_range_start(mm, mmun_start, mmun_end); /* - * Retake the page_table_lock to check for racing updates + * Retake the page table lock to check for racing updates * before the page tables are altered */ - spin_lock(&mm->page_table_lock); + spin_lock(ptl); ptep = huge_pte_offset(mm, address & huge_page_mask(h)); if (likely(pte_same(huge_ptep_get(ptep), pte))) { + ClearPagePrivate(new_page); + /* Break COW */ huge_ptep_clear_flush(vma, address, ptep); set_huge_pte_at(mm, address, ptep, @@ -2666,12 +2732,13 @@ retry_avoidcopy: /* Make the old page be freed below */ new_page = old_page; } - spin_unlock(&mm->page_table_lock); + spin_unlock(ptl); mmu_notifier_invalidate_range_end(mm, mmun_start, mmun_end); - /* Caller expects lock to be held */ - spin_lock(&mm->page_table_lock); page_cache_release(new_page); page_cache_release(old_page); + + /* Caller expects lock to be held */ + spin_lock(ptl); return 0; } @@ -2719,6 +2786,7 @@ static int hugetlb_no_page(struct mm_struct *mm, struct vm_area_struct *vma, struct page *page; struct address_space *mapping; pte_t new_pte; + spinlock_t *ptl; /* * Currently, we are forced to kill the process in the event the @@ -2767,6 +2835,7 @@ retry: goto retry; goto out; } + ClearPagePrivate(page); spin_lock(&inode->i_lock); inode->i_blocks += blocks_per_huge_page(h); @@ -2804,7 +2873,8 @@ retry: goto backout_unlocked; } - spin_lock(&mm->page_table_lock); + ptl = huge_pte_lockptr(h, mm, ptep); + spin_lock(ptl); size = i_size_read(mapping->host) >> huge_page_shift(h); if (idx >= size) goto backout; @@ -2813,8 +2883,10 @@ retry: if (!huge_pte_none(huge_ptep_get(ptep))) goto backout; - if (anon_rmap) + if (anon_rmap) { + ClearPagePrivate(page); hugepage_add_new_anon_rmap(page, vma, address); + } else page_dup_rmap(page); new_pte = make_huge_pte(vma, page, ((vma->vm_flags & VM_WRITE) @@ -2823,16 +2895,16 @@ retry: if ((flags & FAULT_FLAG_WRITE) && !(vma->vm_flags & VM_SHARED)) { /* Optimization, do the COW without a second fault */ - ret = hugetlb_cow(mm, vma, address, ptep, new_pte, page); + ret = hugetlb_cow(mm, vma, address, ptep, new_pte, page, ptl); } - spin_unlock(&mm->page_table_lock); + spin_unlock(ptl); unlock_page(page); out: return ret; backout: - spin_unlock(&mm->page_table_lock); + spin_unlock(ptl); backout_unlocked: unlock_page(page); put_page(page); @@ -2844,6 +2916,7 @@ int hugetlb_fault(struct mm_struct *mm, struct vm_area_struct *vma, { pte_t *ptep; pte_t entry; + spinlock_t *ptl; int ret; struct page *page = NULL; struct page *pagecache_page = NULL; @@ -2856,7 +2929,7 @@ int hugetlb_fault(struct mm_struct *mm, struct vm_area_struct *vma, if (ptep) { entry = huge_ptep_get(ptep); if (unlikely(is_hugetlb_entry_migration(entry))) { - migration_entry_wait_huge(mm, ptep); + migration_entry_wait_huge(vma, mm, ptep); return 0; } else if (unlikely(is_hugetlb_entry_hwpoisoned(entry))) return VM_FAULT_HWPOISON_LARGE | @@ -2912,17 +2985,18 @@ int hugetlb_fault(struct mm_struct *mm, struct vm_area_struct *vma, if (page != pagecache_page) lock_page(page); - spin_lock(&mm->page_table_lock); + ptl = huge_pte_lockptr(h, mm, ptep); + spin_lock(ptl); /* Check for a racing update before calling hugetlb_cow */ if (unlikely(!pte_same(entry, huge_ptep_get(ptep)))) - goto out_page_table_lock; + goto out_ptl; if (flags & FAULT_FLAG_WRITE) { if (!huge_pte_write(entry)) { ret = hugetlb_cow(mm, vma, address, ptep, entry, - pagecache_page); - goto out_page_table_lock; + pagecache_page, ptl); + goto out_ptl; } entry = huge_pte_mkdirty(entry); } @@ -2931,8 +3005,8 @@ int hugetlb_fault(struct mm_struct *mm, struct vm_area_struct *vma, flags & FAULT_FLAG_WRITE)) update_mmu_cache(vma, address, ptep); -out_page_table_lock: - spin_unlock(&mm->page_table_lock); +out_ptl: + spin_unlock(ptl); if (pagecache_page) { unlock_page(pagecache_page); @@ -2958,9 +3032,9 @@ long follow_hugetlb_page(struct mm_struct *mm, struct vm_area_struct *vma, unsigned long remainder = *nr_pages; struct hstate *h = hstate_vma(vma); - spin_lock(&mm->page_table_lock); while (vaddr < vma->vm_end && remainder) { pte_t *pte; + spinlock_t *ptl = NULL; int absent; struct page *page; @@ -2968,8 +3042,12 @@ long follow_hugetlb_page(struct mm_struct *mm, struct vm_area_struct *vma, * Some archs (sparc64, sh*) have multiple pte_ts to * each hugepage. We have to make sure we get the * first, for the page indexing below to work. + * + * Note that page table lock is not held when pte is null. */ pte = huge_pte_offset(mm, vaddr & huge_page_mask(h)); + if (pte) + ptl = huge_pte_lock(h, mm, pte); absent = !pte || huge_pte_none(huge_ptep_get(pte)); /* @@ -2981,6 +3059,8 @@ long follow_hugetlb_page(struct mm_struct *mm, struct vm_area_struct *vma, */ if (absent && (flags & FOLL_DUMP) && !hugetlbfs_pagecache_present(h, vma, vaddr)) { + if (pte) + spin_unlock(ptl); remainder = 0; break; } @@ -3000,10 +3080,10 @@ long follow_hugetlb_page(struct mm_struct *mm, struct vm_area_struct *vma, !huge_pte_write(huge_ptep_get(pte)))) { int ret; - spin_unlock(&mm->page_table_lock); + if (pte) + spin_unlock(ptl); ret = hugetlb_fault(mm, vma, vaddr, (flags & FOLL_WRITE) ? FAULT_FLAG_WRITE : 0); - spin_lock(&mm->page_table_lock); if (!(ret & VM_FAULT_ERROR)) continue; @@ -3034,8 +3114,8 @@ same_page: */ goto same_page; } + spin_unlock(ptl); } - spin_unlock(&mm->page_table_lock); *nr_pages = remainder; *position = vaddr; @@ -3056,13 +3136,15 @@ unsigned long hugetlb_change_protection(struct vm_area_struct *vma, flush_cache_range(vma, address, end); mutex_lock(&vma->vm_file->f_mapping->i_mmap_mutex); - spin_lock(&mm->page_table_lock); for (; address < end; address += huge_page_size(h)) { + spinlock_t *ptl; ptep = huge_pte_offset(mm, address); if (!ptep) continue; + ptl = huge_pte_lock(h, mm, ptep); if (huge_pmd_unshare(mm, &address, ptep)) { pages++; + spin_unlock(ptl); continue; } if (!huge_pte_none(huge_ptep_get(ptep))) { @@ -3072,8 +3154,8 @@ unsigned long hugetlb_change_protection(struct vm_area_struct *vma, set_huge_pte_at(mm, address, ptep, pte); pages++; } + spin_unlock(ptl); } - spin_unlock(&mm->page_table_lock); /* * 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: @@ -3236,6 +3318,7 @@ pte_t *huge_pmd_share(struct mm_struct *mm, unsigned long addr, pud_t *pud) unsigned long saddr; pte_t *spte = NULL; pte_t *pte; + spinlock_t *ptl; if (!vma_shareable(vma, addr)) return (pte_t *)pmd_alloc(mm, pud, addr); @@ -3258,13 +3341,14 @@ pte_t *huge_pmd_share(struct mm_struct *mm, unsigned long addr, pud_t *pud) if (!spte) goto out; - spin_lock(&mm->page_table_lock); + ptl = huge_pte_lockptr(hstate_vma(vma), mm, spte); + spin_lock(ptl); if (pud_none(*pud)) pud_populate(mm, pud, (pmd_t *)((unsigned long)spte & PAGE_MASK)); else put_page(virt_to_page(spte)); - spin_unlock(&mm->page_table_lock); + spin_unlock(ptl); out: pte = (pte_t *)pmd_alloc(mm, pud, addr); mutex_unlock(&mapping->i_mmap_mutex); @@ -3278,7 +3362,7 @@ out: * indicated by page_count > 1, unmap is achieved by clearing pud and * decrementing the ref count. If count == 1, the pte page is not shared. * - * called with vma->vm_mm->page_table_lock held. + * called with page table lock held. * * returns: 1 successfully unmapped a shared pte page * 0 the underlying pte page is not shared, or it is the last user @@ -3431,3 +3515,45 @@ int dequeue_hwpoisoned_huge_page(struct page *hpage) return ret; } #endif + +bool isolate_huge_page(struct page *page, struct list_head *list) +{ + VM_BUG_ON(!PageHead(page)); + if (!get_page_unless_zero(page)) + return false; + spin_lock(&hugetlb_lock); + list_move_tail(&page->lru, list); + spin_unlock(&hugetlb_lock); + return true; +} + +void putback_active_hugepage(struct page *page) +{ + VM_BUG_ON(!PageHead(page)); + spin_lock(&hugetlb_lock); + list_move_tail(&page->lru, &(page_hstate(page))->hugepage_activelist); + spin_unlock(&hugetlb_lock); + put_page(page); +} + +bool is_hugepage_active(struct page *page) +{ + VM_BUG_ON(!PageHuge(page)); + /* + * This function can be called for a tail page because the caller, + * scan_movable_pages, scans through a given pfn-range which typically + * covers one memory block. In systems using gigantic hugepage (1GB + * for x86_64,) a hugepage is larger than a memory block, and we don't + * support migrating such large hugepages for now, so return false + * when called for tail pages. + */ + if (PageTail(page)) + return false; + /* + * Refcount of a hwpoisoned hugepages is 1, but they are not active, + * so we should return false for them. + */ + if (unlikely(PageHWPoison(page))) + return false; + return page_count(page) > 0; +} diff --git a/mm/hwpoison-inject.c b/mm/hwpoison-inject.c index 3a61efc518d5..4c84678371eb 100644 --- a/mm/hwpoison-inject.c +++ b/mm/hwpoison-inject.c @@ -20,8 +20,6 @@ static int hwpoison_inject(void *data, u64 val) if (!capable(CAP_SYS_ADMIN)) return -EPERM; - if (!hwpoison_filter_enable) - goto inject; if (!pfn_valid(pfn)) return -ENXIO; @@ -33,6 +31,9 @@ static int hwpoison_inject(void *data, u64 val) if (!get_page_unless_zero(hpage)) return 0; + if (!hwpoison_filter_enable) + goto inject; + if (!PageLRU(p) && !PageHuge(p)) shake_page(p, 0); /* @@ -88,12 +89,12 @@ static int pfn_inject_init(void) * hardware status change, hence do not require hardware support. * They are mainly for testing hwpoison in software level. */ - dentry = debugfs_create_file("corrupt-pfn", 0600, hwpoison_dir, + dentry = debugfs_create_file("corrupt-pfn", 0200, hwpoison_dir, NULL, &hwpoison_fops); if (!dentry) goto fail; - dentry = debugfs_create_file("unpoison-pfn", 0600, hwpoison_dir, + dentry = debugfs_create_file("unpoison-pfn", 0200, hwpoison_dir, NULL, &unpoison_fops); if (!dentry) goto fail; diff --git a/mm/internal.h b/mm/internal.h index 4390ac6c106e..684f7aa9692a 100644 --- a/mm/internal.h +++ b/mm/internal.h @@ -85,6 +85,8 @@ extern unsigned long highest_memmap_pfn; */ extern int isolate_lru_page(struct page *page); extern void putback_lru_page(struct page *page); +extern unsigned long zone_reclaimable_pages(struct zone *zone); +extern bool zone_reclaimable(struct zone *zone); /* * in mm/rmap.c: diff --git a/mm/kmemleak.c b/mm/kmemleak.c index c8d7f3110fd0..31f01c5011e5 100644 --- a/mm/kmemleak.c +++ b/mm/kmemleak.c @@ -753,7 +753,9 @@ static void add_scan_area(unsigned long ptr, size_t size, gfp_t gfp) } spin_lock_irqsave(&object->lock, flags); - if (ptr + size > object->pointer + object->size) { + if (size == SIZE_MAX) { + size = object->pointer + object->size - ptr; + } else if (ptr + size > object->pointer + object->size) { kmemleak_warn("Scan area larger than object 0x%08lx\n", ptr); dump_object_info(object); kmem_cache_free(scan_area_cache, area); @@ -1639,7 +1641,7 @@ static ssize_t kmemleak_write(struct file *file, const char __user *user_buf, else if (strncmp(buf, "scan=", 5) == 0) { unsigned long secs; - ret = strict_strtoul(buf + 5, 0, &secs); + ret = kstrtoul(buf + 5, 0, &secs); if (ret < 0) goto out; stop_scan_thread(); @@ -2194,7 +2194,7 @@ static ssize_t sleep_millisecs_store(struct kobject *kobj, unsigned long msecs; int err; - err = strict_strtoul(buf, 10, &msecs); + err = kstrtoul(buf, 10, &msecs); if (err || msecs > UINT_MAX) return -EINVAL; @@ -2217,7 +2217,7 @@ static ssize_t pages_to_scan_store(struct kobject *kobj, int err; unsigned long nr_pages; - err = strict_strtoul(buf, 10, &nr_pages); + err = kstrtoul(buf, 10, &nr_pages); if (err || nr_pages > UINT_MAX) return -EINVAL; @@ -2239,7 +2239,7 @@ static ssize_t run_store(struct kobject *kobj, struct kobj_attribute *attr, int err; unsigned long flags; - err = strict_strtoul(buf, 10, &flags); + err = kstrtoul(buf, 10, &flags); if (err || flags > UINT_MAX) return -EINVAL; if (flags > KSM_RUN_UNMERGE) @@ -2309,8 +2309,8 @@ static ssize_t merge_across_nodes_store(struct kobject *kobj, * Allocate stable and unstable together: * MAXSMP NODES_SHIFT 10 will use 16kB. */ - buf = kcalloc(nr_node_ids + nr_node_ids, - sizeof(*buf), GFP_KERNEL | __GFP_ZERO); + buf = kcalloc(nr_node_ids + nr_node_ids, sizeof(*buf), + GFP_KERNEL); /* Let us assume that RB_ROOT is NULL is zero */ if (!buf) err = -ENOMEM; diff --git a/mm/list_lru.c b/mm/list_lru.c new file mode 100644 index 000000000000..72f9decb0104 --- /dev/null +++ b/mm/list_lru.c @@ -0,0 +1,140 @@ +/* + * Copyright (c) 2013 Red Hat, Inc. and Parallels Inc. All rights reserved. + * Authors: David Chinner and Glauber Costa + * + * Generic LRU infrastructure + */ +#include <linux/kernel.h> +#include <linux/module.h> +#include <linux/mm.h> +#include <linux/list_lru.h> +#include <linux/slab.h> + +bool list_lru_add(struct list_lru *lru, struct list_head *item) +{ + int nid = page_to_nid(virt_to_page(item)); + struct list_lru_node *nlru = &lru->node[nid]; + + spin_lock(&nlru->lock); + WARN_ON_ONCE(nlru->nr_items < 0); + if (list_empty(item)) { + list_add_tail(item, &nlru->list); + if (nlru->nr_items++ == 0) + node_set(nid, lru->active_nodes); + spin_unlock(&nlru->lock); + return true; + } + spin_unlock(&nlru->lock); + return false; +} +EXPORT_SYMBOL_GPL(list_lru_add); + +bool list_lru_del(struct list_lru *lru, struct list_head *item) +{ + int nid = page_to_nid(virt_to_page(item)); + struct list_lru_node *nlru = &lru->node[nid]; + + spin_lock(&nlru->lock); + if (!list_empty(item)) { + list_del_init(item); + if (--nlru->nr_items == 0) + node_clear(nid, lru->active_nodes); + WARN_ON_ONCE(nlru->nr_items < 0); + spin_unlock(&nlru->lock); + return true; + } + spin_unlock(&nlru->lock); + return false; +} +EXPORT_SYMBOL_GPL(list_lru_del); + +unsigned long +list_lru_count_node(struct list_lru *lru, int nid) +{ + unsigned long count = 0; + struct list_lru_node *nlru = &lru->node[nid]; + + spin_lock(&nlru->lock); + WARN_ON_ONCE(nlru->nr_items < 0); + count += nlru->nr_items; + spin_unlock(&nlru->lock); + + return count; +} +EXPORT_SYMBOL_GPL(list_lru_count_node); + +unsigned long +list_lru_walk_node(struct list_lru *lru, int nid, list_lru_walk_cb isolate, + void *cb_arg, unsigned long *nr_to_walk) +{ + + struct list_lru_node *nlru = &lru->node[nid]; + struct list_head *item, *n; + unsigned long isolated = 0; + + spin_lock(&nlru->lock); +restart: + list_for_each_safe(item, n, &nlru->list) { + enum lru_status ret; + + /* + * decrement nr_to_walk first so that we don't livelock if we + * get stuck on large numbesr of LRU_RETRY items + */ + if (!*nr_to_walk) + break; + --*nr_to_walk; + + ret = isolate(item, &nlru->lock, cb_arg); + switch (ret) { + case LRU_REMOVED: + if (--nlru->nr_items == 0) + node_clear(nid, lru->active_nodes); + WARN_ON_ONCE(nlru->nr_items < 0); + isolated++; + break; + case LRU_ROTATE: + list_move_tail(item, &nlru->list); + break; + case LRU_SKIP: + break; + case LRU_RETRY: + /* + * The lru lock has been dropped, our list traversal is + * now invalid and so we have to restart from scratch. + */ + goto restart; + default: + BUG(); + } + } + + spin_unlock(&nlru->lock); + return isolated; +} +EXPORT_SYMBOL_GPL(list_lru_walk_node); + +int list_lru_init(struct list_lru *lru) +{ + int i; + size_t size = sizeof(*lru->node) * nr_node_ids; + + lru->node = kzalloc(size, GFP_KERNEL); + if (!lru->node) + return -ENOMEM; + + nodes_clear(lru->active_nodes); + for (i = 0; i < nr_node_ids; i++) { + spin_lock_init(&lru->node[i].lock); + INIT_LIST_HEAD(&lru->node[i].list); + lru->node[i].nr_items = 0; + } + return 0; +} +EXPORT_SYMBOL_GPL(list_lru_init); + +void list_lru_destroy(struct list_lru *lru) +{ + kfree(lru->node); +} +EXPORT_SYMBOL_GPL(list_lru_destroy); diff --git a/mm/madvise.c b/mm/madvise.c index 7055883e6e25..539eeb96b323 100644 --- a/mm/madvise.c +++ b/mm/madvise.c @@ -42,11 +42,11 @@ static int madvise_need_mmap_write(int behavior) * We can potentially split a vm area into separate * areas, each area with its own behavior. */ -static long madvise_behavior(struct vm_area_struct * vma, +static long madvise_behavior(struct vm_area_struct *vma, struct vm_area_struct **prev, unsigned long start, unsigned long end, int behavior) { - struct mm_struct * mm = vma->vm_mm; + struct mm_struct *mm = vma->vm_mm; int error = 0; pgoff_t pgoff; unsigned long new_flags = vma->vm_flags; @@ -215,8 +215,8 @@ static void force_shm_swapin_readahead(struct vm_area_struct *vma, /* * Schedule all required I/O operations. Do not wait for completion. */ -static long madvise_willneed(struct vm_area_struct * vma, - struct vm_area_struct ** prev, +static long madvise_willneed(struct vm_area_struct *vma, + struct vm_area_struct **prev, unsigned long start, unsigned long end) { struct file *file = vma->vm_file; @@ -270,8 +270,8 @@ static long madvise_willneed(struct vm_area_struct * vma, * An interface that causes the system to free clean pages and flush * dirty pages is already available as msync(MS_INVALIDATE). */ -static long madvise_dontneed(struct vm_area_struct * vma, - struct vm_area_struct ** prev, +static long madvise_dontneed(struct vm_area_struct *vma, + struct vm_area_struct **prev, unsigned long start, unsigned long end) { *prev = vma; @@ -343,29 +343,35 @@ static long madvise_remove(struct vm_area_struct *vma, */ static int madvise_hwpoison(int bhv, unsigned long start, unsigned long end) { - int ret = 0; - + struct page *p; if (!capable(CAP_SYS_ADMIN)) return -EPERM; - for (; start < end; start += PAGE_SIZE) { - struct page *p; - int ret = get_user_pages_fast(start, 1, 0, &p); + for (; start < end; start += PAGE_SIZE << + compound_order(compound_head(p))) { + int ret; + + ret = get_user_pages_fast(start, 1, 0, &p); if (ret != 1) return ret; + + if (PageHWPoison(p)) { + put_page(p); + continue; + } if (bhv == MADV_SOFT_OFFLINE) { - printk(KERN_INFO "Soft offlining page %lx at %lx\n", + pr_info("Soft offlining page %#lx at %#lx\n", page_to_pfn(p), start); ret = soft_offline_page(p, MF_COUNT_INCREASED); if (ret) - break; + return ret; continue; } - printk(KERN_INFO "Injecting memory failure for page %lx at %lx\n", + pr_info("Injecting memory failure for page %#lx at %#lx\n", page_to_pfn(p), start); /* Ignore return value for now */ memory_failure(page_to_pfn(p), 0, MF_COUNT_INCREASED); } - return ret; + return 0; } #endif @@ -459,7 +465,7 @@ madvise_behavior_valid(int behavior) SYSCALL_DEFINE3(madvise, unsigned long, start, size_t, len_in, int, behavior) { unsigned long end, tmp; - struct vm_area_struct * vma, *prev; + struct vm_area_struct *vma, *prev; int unmapped_error = 0; int error = -EINVAL; int write; diff --git a/mm/memblock.c b/mm/memblock.c index a847bfe6f3ba..53e477bb5558 100644 --- a/mm/memblock.c +++ b/mm/memblock.c @@ -20,6 +20,8 @@ #include <linux/seq_file.h> #include <linux/memblock.h> +#include <asm-generic/sections.h> + static struct memblock_region memblock_memory_init_regions[INIT_MEMBLOCK_REGIONS] __initdata_memblock; static struct memblock_region memblock_reserved_init_regions[INIT_MEMBLOCK_REGIONS] __initdata_memblock; @@ -32,6 +34,7 @@ struct memblock memblock __initdata_memblock = { .reserved.cnt = 1, /* empty dummy entry */ .reserved.max = INIT_MEMBLOCK_REGIONS, + .bottom_up = false, .current_limit = MEMBLOCK_ALLOC_ANYWHERE, }; @@ -82,6 +85,73 @@ static long __init_memblock memblock_overlaps_region(struct memblock_type *type, return (i < type->cnt) ? i : -1; } +/* + * __memblock_find_range_bottom_up - find free area utility in bottom-up + * @start: start of candidate range + * @end: end of candidate range, can be %MEMBLOCK_ALLOC_{ANYWHERE|ACCESSIBLE} + * @size: size of free area to find + * @align: alignment of free area to find + * @nid: nid of the free area to find, %MAX_NUMNODES for any node + * + * Utility called from memblock_find_in_range_node(), find free area bottom-up. + * + * RETURNS: + * Found address on success, 0 on failure. + */ +static phys_addr_t __init_memblock +__memblock_find_range_bottom_up(phys_addr_t start, phys_addr_t end, + phys_addr_t size, phys_addr_t align, int nid) +{ + phys_addr_t this_start, this_end, cand; + u64 i; + + for_each_free_mem_range(i, nid, &this_start, &this_end, NULL) { + this_start = clamp(this_start, start, end); + this_end = clamp(this_end, start, end); + + cand = round_up(this_start, align); + if (cand < this_end && this_end - cand >= size) + return cand; + } + + return 0; +} + +/** + * __memblock_find_range_top_down - find free area utility, in top-down + * @start: start of candidate range + * @end: end of candidate range, can be %MEMBLOCK_ALLOC_{ANYWHERE|ACCESSIBLE} + * @size: size of free area to find + * @align: alignment of free area to find + * @nid: nid of the free area to find, %MAX_NUMNODES for any node + * + * Utility called from memblock_find_in_range_node(), find free area top-down. + * + * RETURNS: + * Found address on success, 0 on failure. + */ +static phys_addr_t __init_memblock +__memblock_find_range_top_down(phys_addr_t start, phys_addr_t end, + phys_addr_t size, phys_addr_t align, int nid) +{ + phys_addr_t this_start, this_end, cand; + u64 i; + + for_each_free_mem_range_reverse(i, nid, &this_start, &this_end, NULL) { + this_start = clamp(this_start, start, end); + this_end = clamp(this_end, start, end); + + if (this_end < size) + continue; + + cand = round_down(this_end - size, align); + if (cand >= this_start) + return cand; + } + + return 0; +} + /** * memblock_find_in_range_node - find free area in given range and node * @start: start of candidate range @@ -92,15 +162,23 @@ static long __init_memblock memblock_overlaps_region(struct memblock_type *type, * * Find @size free area aligned to @align in the specified range and node. * + * When allocation direction is bottom-up, the @start should be greater + * than the end of the kernel image. Otherwise, it will be trimmed. The + * reason is that we want the bottom-up allocation just near the kernel + * image so it is highly likely that the allocated memory and the kernel + * will reside in the same node. + * + * If bottom-up allocation failed, will try to allocate memory top-down. + * * RETURNS: - * Found address on success, %0 on failure. + * Found address on success, 0 on failure. */ phys_addr_t __init_memblock memblock_find_in_range_node(phys_addr_t start, phys_addr_t end, phys_addr_t size, phys_addr_t align, int nid) { - phys_addr_t this_start, this_end, cand; - u64 i; + int ret; + phys_addr_t kernel_end; /* pump up @end */ if (end == MEMBLOCK_ALLOC_ACCESSIBLE) @@ -109,19 +187,39 @@ phys_addr_t __init_memblock memblock_find_in_range_node(phys_addr_t start, /* avoid allocating the first page */ start = max_t(phys_addr_t, start, PAGE_SIZE); end = max(start, end); + kernel_end = __pa_symbol(_end); - for_each_free_mem_range_reverse(i, nid, &this_start, &this_end, NULL) { - this_start = clamp(this_start, start, end); - this_end = clamp(this_end, start, end); + /* + * try bottom-up allocation only when bottom-up mode + * is set and @end is above the kernel image. + */ + if (memblock_bottom_up() && end > kernel_end) { + phys_addr_t bottom_up_start; - if (this_end < size) - continue; + /* make sure we will allocate above the kernel */ + bottom_up_start = max(start, kernel_end); - cand = round_down(this_end - size, align); - if (cand >= this_start) - return cand; + /* ok, try bottom-up allocation first */ + ret = __memblock_find_range_bottom_up(bottom_up_start, end, + size, align, nid); + if (ret) + return ret; + + /* + * we always limit bottom-up allocation above the kernel, + * but top-down allocation doesn't have the limit, so + * retrying top-down allocation may succeed when bottom-up + * allocation failed. + * + * bottom-up allocation is expected to be fail very rarely, + * so we use WARN_ONCE() here to see the stack trace if + * fail happens. + */ + WARN_ONCE(1, "memblock: bottom-up allocation failed, " + "memory hotunplug may be affected\n"); } - return 0; + + return __memblock_find_range_top_down(start, end, size, align, nid); } /** @@ -134,7 +232,7 @@ phys_addr_t __init_memblock memblock_find_in_range_node(phys_addr_t start, * Find @size free area aligned to @align in the specified range. * * RETURNS: - * Found address on success, %0 on failure. + * Found address on success, 0 on failure. */ phys_addr_t __init_memblock memblock_find_in_range(phys_addr_t start, phys_addr_t end, phys_addr_t size, @@ -914,6 +1012,24 @@ int __init_memblock memblock_is_memory(phys_addr_t addr) return memblock_search(&memblock.memory, addr) != -1; } +#ifdef CONFIG_HAVE_MEMBLOCK_NODE_MAP +int __init_memblock memblock_search_pfn_nid(unsigned long pfn, + unsigned long *start_pfn, unsigned long *end_pfn) +{ + struct memblock_type *type = &memblock.memory; + int mid = memblock_search(type, (phys_addr_t)pfn << PAGE_SHIFT); + + if (mid == -1) + return -1; + + *start_pfn = type->regions[mid].base >> PAGE_SHIFT; + *end_pfn = (type->regions[mid].base + type->regions[mid].size) + >> PAGE_SHIFT; + + return type->regions[mid].nid; +} +#endif + /** * memblock_is_region_memory - check if a region is a subset of memory * @base: base of region to check diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 3b83957b6439..f1a0ae6e11b8 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -54,10 +54,12 @@ #include <linux/page_cgroup.h> #include <linux/cpu.h> #include <linux/oom.h> +#include <linux/lockdep.h> #include "internal.h" #include <net/sock.h> #include <net/ip.h> #include <net/tcp_memcontrol.h> +#include "slab.h" #include <asm/uaccess.h> @@ -85,26 +87,12 @@ static int really_do_swap_account __initdata = 0; #endif -/* - * Statistics for memory cgroup. - */ -enum mem_cgroup_stat_index { - /* - * For MEM_CONTAINER_TYPE_ALL, usage = pagecache + rss. - */ - MEM_CGROUP_STAT_CACHE, /* # of pages charged as cache */ - MEM_CGROUP_STAT_RSS, /* # of pages charged as anon rss */ - MEM_CGROUP_STAT_RSS_HUGE, /* # of pages charged as anon huge */ - MEM_CGROUP_STAT_FILE_MAPPED, /* # of pages charged as file rss */ - MEM_CGROUP_STAT_SWAP, /* # of pages, swapped out */ - MEM_CGROUP_STAT_NSTATS, -}; - static const char * const mem_cgroup_stat_names[] = { "cache", "rss", "rss_huge", "mapped_file", + "writeback", "swap", }; @@ -280,6 +268,7 @@ struct mem_cgroup { bool oom_lock; atomic_t under_oom; + atomic_t oom_wakeups; int swappiness; /* OOM-Killer disable */ @@ -304,7 +293,7 @@ struct mem_cgroup { * Should we move charges of a task when a task is moved into this * mem_cgroup ? And what type of charges should we move ? */ - unsigned long move_charge_at_immigrate; + unsigned long move_charge_at_immigrate; /* * set > 0 if pages under this cgroup are moving to other cgroup. */ @@ -324,7 +313,7 @@ struct mem_cgroup { atomic_t dead_count; #if defined(CONFIG_MEMCG_KMEM) && defined(CONFIG_INET) - struct tcp_memcontrol tcp_mem; + struct cg_proto tcp_mem; #endif #if defined(CONFIG_MEMCG_KMEM) /* analogous to slab_common's slab_caches list. per-memcg */ @@ -511,6 +500,29 @@ static inline bool mem_cgroup_is_root(struct mem_cgroup *memcg) return (memcg == root_mem_cgroup); } +/* + * We restrict the id in the range of [1, 65535], so it can fit into + * an unsigned short. + */ +#define MEM_CGROUP_ID_MAX USHRT_MAX + +static inline unsigned short mem_cgroup_id(struct mem_cgroup *memcg) +{ + /* + * The ID of the root cgroup is 0, but memcg treat 0 as an + * invalid ID, so we return (cgroup_id + 1). + */ + return memcg->css.cgroup->id + 1; +} + +static inline struct mem_cgroup *mem_cgroup_from_id(unsigned short id) +{ + struct cgroup_subsys_state *css; + + css = css_from_id(id - 1, &mem_cgroup_subsys); + return mem_cgroup_from_css(css); +} + /* Writing them here to avoid exposing memcg's inner layout */ #if defined(CONFIG_INET) && defined(CONFIG_MEMCG_KMEM) @@ -563,13 +575,13 @@ struct cg_proto *tcp_proto_cgroup(struct mem_cgroup *memcg) if (!memcg || mem_cgroup_is_root(memcg)) return NULL; - return &memcg->tcp_mem.cg_proto; + return &memcg->tcp_mem; } EXPORT_SYMBOL(tcp_proto_cgroup); static void disarm_sock_keys(struct mem_cgroup *memcg) { - if (!memcg_proto_activated(&memcg->tcp_mem.cg_proto)) + if (!memcg_proto_activated(&memcg->tcp_mem)) return; static_key_slow_dec(&memcg_socket_limit_enabled); } @@ -582,16 +594,11 @@ static void disarm_sock_keys(struct mem_cgroup *memcg) #ifdef CONFIG_MEMCG_KMEM /* * This will be the memcg's index in each cache's ->memcg_params->memcg_caches. - * There are two main reasons for not using the css_id for this: - * 1) this works better in sparse environments, where we have a lot of memcgs, - * but only a few kmem-limited. Or also, if we have, for instance, 200 - * memcgs, and none but the 200th is kmem-limited, we'd have to have a - * 200 entry array for that. - * - * 2) In order not to violate the cgroup API, we would like to do all memory - * allocation in ->create(). At that point, we haven't yet allocated the - * css_id. Having a separate index prevents us from messing with the cgroup - * core for this + * The main reason for not using cgroup id for this: + * this works better in sparse environments, where we have a lot of memcgs, + * but only a few kmem-limited. Or also, if we have, for instance, 200 + * memcgs, and none but the 200th is kmem-limited, we'd have to have a + * 200 entry array for that. * * The current size of the caches array is stored in * memcg_limited_groups_array_size. It will double each time we have to @@ -606,14 +613,14 @@ int memcg_limited_groups_array_size; * cgroups is a reasonable guess. In the future, it could be a parameter or * tunable, but that is strictly not necessary. * - * MAX_SIZE should be as large as the number of css_ids. Ideally, we could get + * MAX_SIZE should be as large as the number of cgrp_ids. Ideally, we could get * this constant directly from cgroup, but it is understandable that this is * better kept as an internal representation in cgroup.c. In any case, the - * css_id space is not getting any smaller, and we don't have to necessarily + * cgrp_id space is not getting any smaller, and we don't have to necessarily * increase ours as well if it increases. */ #define MEMCG_CACHES_MIN_SIZE 4 -#define MEMCG_CACHES_MAX_SIZE 65535 +#define MEMCG_CACHES_MAX_SIZE MEM_CGROUP_ID_MAX /* * A lot of the calls to the cache allocation functions are expected to be @@ -879,6 +886,7 @@ static unsigned long mem_cgroup_read_events(struct mem_cgroup *memcg, unsigned long val = 0; int cpu; + get_online_cpus(); for_each_online_cpu(cpu) val += per_cpu(memcg->stat->events[idx], cpu); #ifdef CONFIG_HOTPLUG_CPU @@ -886,6 +894,7 @@ static unsigned long mem_cgroup_read_events(struct mem_cgroup *memcg, val += memcg->nocpu_base.events[idx]; spin_unlock(&memcg->pcp_counter_lock); #endif + put_online_cpus(); return val; } @@ -1418,7 +1427,7 @@ bool __mem_cgroup_same_or_subtree(const struct mem_cgroup *root_memcg, return true; if (!root_memcg->use_hierarchy || !memcg) return false; - return css_is_ancestor(&memcg->css, &root_memcg->css); + return cgroup_is_descendant(memcg->css.cgroup, root_memcg->css.cgroup); } static bool mem_cgroup_same_or_subtree(const struct mem_cgroup *root_memcg, @@ -2057,15 +2066,24 @@ static int mem_cgroup_soft_reclaim(struct mem_cgroup *root_memcg, return total; } +#ifdef CONFIG_LOCKDEP +static struct lockdep_map memcg_oom_lock_dep_map = { + .name = "memcg_oom_lock", +}; +#endif + +static DEFINE_SPINLOCK(memcg_oom_lock); + /* * Check OOM-Killer is already running under our hierarchy. * If someone is running, return false. - * Has to be called with memcg_oom_lock */ -static bool mem_cgroup_oom_lock(struct mem_cgroup *memcg) +static bool mem_cgroup_oom_trylock(struct mem_cgroup *memcg) { struct mem_cgroup *iter, *failed = NULL; + spin_lock(&memcg_oom_lock); + for_each_mem_cgroup_tree(iter, memcg) { if (iter->oom_lock) { /* @@ -2079,33 +2097,35 @@ static bool mem_cgroup_oom_lock(struct mem_cgroup *memcg) iter->oom_lock = true; } - if (!failed) - return true; - - /* - * OK, we failed to lock the whole subtree so we have to clean up - * what we set up to the failing subtree - */ - for_each_mem_cgroup_tree(iter, memcg) { - if (iter == failed) { - mem_cgroup_iter_break(memcg, iter); - break; + if (failed) { + /* + * OK, we failed to lock the whole subtree so we have + * to clean up what we set up to the failing subtree + */ + for_each_mem_cgroup_tree(iter, memcg) { + if (iter == failed) { + mem_cgroup_iter_break(memcg, iter); + break; + } + iter->oom_lock = false; } - iter->oom_lock = false; - } - return false; + } else + mutex_acquire(&memcg_oom_lock_dep_map, 0, 1, _RET_IP_); + + spin_unlock(&memcg_oom_lock); + + return !failed; } -/* - * Has to be called with memcg_oom_lock - */ -static int mem_cgroup_oom_unlock(struct mem_cgroup *memcg) +static void mem_cgroup_oom_unlock(struct mem_cgroup *memcg) { struct mem_cgroup *iter; + spin_lock(&memcg_oom_lock); + mutex_release(&memcg_oom_lock_dep_map, 1, _RET_IP_); for_each_mem_cgroup_tree(iter, memcg) iter->oom_lock = false; - return 0; + spin_unlock(&memcg_oom_lock); } static void mem_cgroup_mark_under_oom(struct mem_cgroup *memcg) @@ -2129,7 +2149,6 @@ static void mem_cgroup_unmark_under_oom(struct mem_cgroup *memcg) atomic_add_unless(&iter->under_oom, -1, 0); } -static DEFINE_SPINLOCK(memcg_oom_lock); static DECLARE_WAIT_QUEUE_HEAD(memcg_oom_waitq); struct oom_wait_info { @@ -2159,6 +2178,7 @@ static int memcg_oom_wake_function(wait_queue_t *wait, static void memcg_wakeup_oom(struct mem_cgroup *memcg) { + atomic_inc(&memcg->oom_wakeups); /* for filtering, pass "memcg" as argument. */ __wake_up(&memcg_oom_waitq, TASK_NORMAL, 0, memcg); } @@ -2169,57 +2189,97 @@ static void memcg_oom_recover(struct mem_cgroup *memcg) memcg_wakeup_oom(memcg); } -/* - * try to call OOM killer. returns false if we should exit memory-reclaim loop. +static void mem_cgroup_oom(struct mem_cgroup *memcg, gfp_t mask, int order) +{ + if (!current->memcg_oom.may_oom) + return; + /* + * We are in the middle of the charge context here, so we + * don't want to block when potentially sitting on a callstack + * that holds all kinds of filesystem and mm locks. + * + * Also, the caller may handle a failed allocation gracefully + * (like optional page cache readahead) and so an OOM killer + * invocation might not even be necessary. + * + * That's why we don't do anything here except remember the + * OOM context and then deal with it at the end of the page + * fault when the stack is unwound, the locks are released, + * and when we know whether the fault was overall successful. + */ + css_get(&memcg->css); + current->memcg_oom.memcg = memcg; + current->memcg_oom.gfp_mask = mask; + current->memcg_oom.order = order; +} + +/** + * mem_cgroup_oom_synchronize - complete memcg OOM handling + * @handle: actually kill/wait or just clean up the OOM state + * + * This has to be called at the end of a page fault if the memcg OOM + * handler was enabled. + * + * Memcg supports userspace OOM handling where failed allocations must + * sleep on a waitqueue until the userspace task resolves the + * situation. Sleeping directly in the charge context with all kinds + * of locks held is not a good idea, instead we remember an OOM state + * in the task and mem_cgroup_oom_synchronize() has to be called at + * the end of the page fault to complete the OOM handling. + * + * Returns %true if an ongoing memcg OOM situation was detected and + * completed, %false otherwise. */ -static bool mem_cgroup_handle_oom(struct mem_cgroup *memcg, gfp_t mask, - int order) +bool mem_cgroup_oom_synchronize(bool handle) { + struct mem_cgroup *memcg = current->memcg_oom.memcg; struct oom_wait_info owait; - bool locked, need_to_kill; + bool locked; + + /* OOM is global, do not handle */ + if (!memcg) + return false; + + if (!handle) + goto cleanup; owait.memcg = memcg; owait.wait.flags = 0; owait.wait.func = memcg_oom_wake_function; owait.wait.private = current; INIT_LIST_HEAD(&owait.wait.task_list); - need_to_kill = true; - mem_cgroup_mark_under_oom(memcg); - /* At first, try to OOM lock hierarchy under memcg.*/ - spin_lock(&memcg_oom_lock); - locked = mem_cgroup_oom_lock(memcg); - /* - * Even if signal_pending(), we can't quit charge() loop without - * accounting. So, UNINTERRUPTIBLE is appropriate. But SIGKILL - * under OOM is always welcomed, use TASK_KILLABLE here. - */ prepare_to_wait(&memcg_oom_waitq, &owait.wait, TASK_KILLABLE); - if (!locked || memcg->oom_kill_disable) - need_to_kill = false; + mem_cgroup_mark_under_oom(memcg); + + locked = mem_cgroup_oom_trylock(memcg); + if (locked) mem_cgroup_oom_notify(memcg); - spin_unlock(&memcg_oom_lock); - if (need_to_kill) { + if (locked && !memcg->oom_kill_disable) { + mem_cgroup_unmark_under_oom(memcg); finish_wait(&memcg_oom_waitq, &owait.wait); - mem_cgroup_out_of_memory(memcg, mask, order); + mem_cgroup_out_of_memory(memcg, current->memcg_oom.gfp_mask, + current->memcg_oom.order); } else { schedule(); + mem_cgroup_unmark_under_oom(memcg); finish_wait(&memcg_oom_waitq, &owait.wait); } - spin_lock(&memcg_oom_lock); - if (locked) - mem_cgroup_oom_unlock(memcg); - memcg_wakeup_oom(memcg); - spin_unlock(&memcg_oom_lock); - - mem_cgroup_unmark_under_oom(memcg); - if (test_thread_flag(TIF_MEMDIE) || fatal_signal_pending(current)) - return false; - /* Give chance to dying process */ - schedule_timeout_uninterruptible(1); + if (locked) { + mem_cgroup_oom_unlock(memcg); + /* + * There is no guarantee that an OOM-lock contender + * sees the wakeups triggered by the OOM kill + * uncharges. Wake any sleepers explicitely. + */ + memcg_oom_recover(memcg); + } +cleanup: + current->memcg_oom.memcg = NULL; + css_put(&memcg->css); return true; } @@ -2288,7 +2348,7 @@ void __mem_cgroup_end_update_page_stat(struct page *page, unsigned long *flags) } void mem_cgroup_update_page_stat(struct page *page, - enum mem_cgroup_page_stat_item idx, int val) + enum mem_cgroup_stat_index idx, int val) { struct mem_cgroup *memcg; struct page_cgroup *pc = lookup_page_cgroup(page); @@ -2297,18 +2357,11 @@ void mem_cgroup_update_page_stat(struct page *page, if (mem_cgroup_disabled()) return; + VM_BUG_ON(!rcu_read_lock_held()); memcg = pc->mem_cgroup; if (unlikely(!memcg || !PageCgroupUsed(pc))) return; - switch (idx) { - case MEMCG_NR_FILE_MAPPED: - idx = MEM_CGROUP_STAT_FILE_MAPPED; - break; - default: - BUG(); - } - this_cpu_add(memcg->stat->count[idx], val); } @@ -2450,7 +2503,7 @@ static void drain_all_stock(struct mem_cgroup *root_memcg, bool sync) flush_work(&stock->work); } out: - put_online_cpus(); + put_online_cpus(); } /* @@ -2532,12 +2585,11 @@ enum { CHARGE_RETRY, /* need to retry but retry is not bad */ CHARGE_NOMEM, /* we can't do more. return -ENOMEM */ CHARGE_WOULDBLOCK, /* GFP_WAIT wasn't set and no enough res. */ - CHARGE_OOM_DIE, /* the current is killed because of OOM */ }; static int mem_cgroup_do_charge(struct mem_cgroup *memcg, gfp_t gfp_mask, unsigned int nr_pages, unsigned int min_pages, - bool oom_check) + bool invoke_oom) { unsigned long csize = nr_pages * PAGE_SIZE; struct mem_cgroup *mem_over_limit; @@ -2594,14 +2646,10 @@ static int mem_cgroup_do_charge(struct mem_cgroup *memcg, gfp_t gfp_mask, if (mem_cgroup_wait_acct_move(mem_over_limit)) return CHARGE_RETRY; - /* If we don't need to call oom-killer at el, return immediately */ - if (!oom_check) - return CHARGE_NOMEM; - /* check OOM */ - if (!mem_cgroup_handle_oom(mem_over_limit, gfp_mask, get_order(csize))) - return CHARGE_OOM_DIE; + if (invoke_oom) + mem_cgroup_oom(mem_over_limit, gfp_mask, get_order(csize)); - return CHARGE_RETRY; + return CHARGE_NOMEM; } /* @@ -2645,6 +2693,9 @@ static int __mem_cgroup_try_charge(struct mm_struct *mm, || fatal_signal_pending(current))) goto bypass; + if (unlikely(task_in_memcg_oom(current))) + goto bypass; + /* * We always charge the cgroup the mm_struct belongs to. * The mm_struct's mem_cgroup changes on task migration if the @@ -2704,7 +2755,7 @@ again: } do { - bool oom_check; + bool invoke_oom = oom && !nr_oom_retries; /* If killed, bypass charge */ if (fatal_signal_pending(current)) { @@ -2712,14 +2763,8 @@ again: goto bypass; } - oom_check = false; - if (oom && !nr_oom_retries) { - oom_check = true; - nr_oom_retries = MEM_CGROUP_RECLAIM_RETRIES; - } - - ret = mem_cgroup_do_charge(memcg, gfp_mask, batch, nr_pages, - oom_check); + ret = mem_cgroup_do_charge(memcg, gfp_mask, batch, + nr_pages, invoke_oom); switch (ret) { case CHARGE_OK: break; @@ -2732,16 +2777,12 @@ again: css_put(&memcg->css); goto nomem; case CHARGE_NOMEM: /* OOM routine works */ - if (!oom) { + if (!oom || invoke_oom) { css_put(&memcg->css); goto nomem; } - /* If oom, we never return -ENOMEM */ nr_oom_retries--; break; - case CHARGE_OOM_DIE: /* Killed by OOM Killer */ - css_put(&memcg->css); - goto bypass; } } while (ret != CHARGE_OK); @@ -2752,8 +2793,10 @@ done: *ptr = memcg; return 0; nomem: - *ptr = NULL; - return -ENOMEM; + if (!(gfp_mask & __GFP_NOFAIL)) { + *ptr = NULL; + return -ENOMEM; + } bypass: *ptr = root_mem_cgroup; return -EINTR; @@ -2802,15 +2845,10 @@ static void __mem_cgroup_cancel_local_charge(struct mem_cgroup *memcg, */ static struct mem_cgroup *mem_cgroup_lookup(unsigned short id) { - struct cgroup_subsys_state *css; - /* ID 0 is unused ID */ if (!id) return NULL; - css = css_lookup(&mem_cgroup_subsys, id); - if (!css) - return NULL; - return mem_cgroup_from_css(css); + return mem_cgroup_from_id(id); } struct mem_cgroup *try_get_mem_cgroup_from_page(struct page *page) @@ -2882,7 +2920,7 @@ static void __mem_cgroup_commit_charge(struct mem_cgroup *memcg, * is accessed after testing USED bit. To make pc->mem_cgroup visible * before USED bit, we need memory barrier here. * See mem_cgroup_add_lru_list(), etc. - */ + */ smp_wmb(); SetPageCgroupUsed(pc); @@ -2931,7 +2969,7 @@ static struct kmem_cache *memcg_params_to_cache(struct memcg_cache_params *p) VM_BUG_ON(p->is_root_cache); cachep = p->root_cache; - return cachep->memcg_params->memcg_caches[memcg_cache_id(p->memcg)]; + return cache_from_memcg_idx(cachep, memcg_cache_id(p->memcg)); } #ifdef CONFIG_SLABINFO @@ -2960,21 +2998,14 @@ static int memcg_charge_kmem(struct mem_cgroup *memcg, gfp_t gfp, u64 size) struct res_counter *fail_res; struct mem_cgroup *_memcg; int ret = 0; - bool may_oom; ret = res_counter_charge(&memcg->kmem, size, &fail_res); if (ret) return ret; - /* - * Conditions under which we can wait for the oom_killer. Those are - * the same conditions tested by the core page allocator - */ - may_oom = (gfp & __GFP_FS) && !(gfp & __GFP_NORETRY); - _memcg = memcg; ret = __mem_cgroup_try_charge(NULL, gfp, size >> PAGE_SHIFT, - &_memcg, may_oom); + &_memcg, oom_gfp_allowed(gfp)); if (ret == -EINTR) { /* @@ -3114,14 +3145,14 @@ int memcg_update_cache_size(struct kmem_cache *s, int num_groups) { struct memcg_cache_params *cur_params = s->memcg_params; - VM_BUG_ON(s->memcg_params && !s->memcg_params->is_root_cache); + VM_BUG_ON(!is_root_cache(s)); if (num_groups > memcg_limited_groups_array_size) { int i; ssize_t size = memcg_caches_array_size(num_groups); size *= sizeof(void *); - size += sizeof(struct memcg_cache_params); + size += offsetof(struct memcg_cache_params, memcg_caches); s->memcg_params = kzalloc(size, GFP_KERNEL); if (!s->memcg_params) { @@ -3164,13 +3195,16 @@ int memcg_update_cache_size(struct kmem_cache *s, int num_groups) int memcg_register_cache(struct mem_cgroup *memcg, struct kmem_cache *s, struct kmem_cache *root_cache) { - size_t size = sizeof(struct memcg_cache_params); + size_t size; if (!memcg_kmem_enabled()) return 0; - if (!memcg) + if (!memcg) { + size = offsetof(struct memcg_cache_params, memcg_caches); size += memcg_limited_groups_array_size * sizeof(void *); + } else + size = sizeof(struct memcg_cache_params); s->memcg_params = kzalloc(size, GFP_KERNEL); if (!s->memcg_params) @@ -3372,7 +3406,7 @@ static struct kmem_cache *memcg_create_kmem_cache(struct mem_cgroup *memcg, idx = memcg_cache_id(memcg); mutex_lock(&memcg_cache_mutex); - new_cachep = cachep->memcg_params->memcg_caches[idx]; + new_cachep = cache_from_memcg_idx(cachep, idx); if (new_cachep) { css_put(&memcg->css); goto out; @@ -3418,8 +3452,8 @@ void kmem_cache_destroy_memcg_children(struct kmem_cache *s) * we'll take the set_limit_mutex to protect ourselves against this. */ mutex_lock(&set_limit_mutex); - for (i = 0; i < memcg_limited_groups_array_size; i++) { - c = s->memcg_params->memcg_caches[i]; + for_each_memcg_cache_index(i) { + c = cache_from_memcg_idx(s, i); if (!c) continue; @@ -3552,8 +3586,8 @@ struct kmem_cache *__memcg_kmem_get_cache(struct kmem_cache *cachep, * code updating memcg_caches will issue a write barrier to match this. */ read_barrier_depends(); - if (likely(cachep->memcg_params->memcg_caches[idx])) { - cachep = cachep->memcg_params->memcg_caches[idx]; + if (likely(cache_from_memcg_idx(cachep, idx))) { + cachep = cache_from_memcg_idx(cachep, idx); goto out; } @@ -3623,9 +3657,9 @@ __memcg_kmem_newpage_charge(gfp_t gfp, struct mem_cgroup **_memcg, int order) * the page allocator. Therefore, the following sequence when backed by * the SLUB allocator: * - * memcg_stop_kmem_account(); - * kmalloc(<large_number>) - * memcg_resume_kmem_account(); + * memcg_stop_kmem_account(); + * kmalloc(<large_number>) + * memcg_resume_kmem_account(); * * would effectively ignore the fact that we should skip accounting, * since it will drive us directly to this function without passing @@ -3747,6 +3781,19 @@ void mem_cgroup_split_huge_fixup(struct page *head) } #endif /* CONFIG_TRANSPARENT_HUGEPAGE */ +static inline +void mem_cgroup_move_account_page_stat(struct mem_cgroup *from, + struct mem_cgroup *to, + unsigned int nr_pages, + enum mem_cgroup_stat_index idx) +{ + /* Update stat data for mem_cgroup */ + preempt_disable(); + __this_cpu_sub(from->stat->count[idx], nr_pages); + __this_cpu_add(to->stat->count[idx], nr_pages); + preempt_enable(); +} + /** * mem_cgroup_move_account - move account of the page * @page: the page @@ -3792,13 +3839,14 @@ static int mem_cgroup_move_account(struct page *page, move_lock_mem_cgroup(from, &flags); - if (!anon && page_mapped(page)) { - /* Update mapped_file data for mem_cgroup */ - preempt_disable(); - __this_cpu_dec(from->stat->count[MEM_CGROUP_STAT_FILE_MAPPED]); - __this_cpu_inc(to->stat->count[MEM_CGROUP_STAT_FILE_MAPPED]); - preempt_enable(); - } + if (!anon && page_mapped(page)) + mem_cgroup_move_account_page_stat(from, to, nr_pages, + MEM_CGROUP_STAT_FILE_MAPPED); + + if (PageWriteback(page)) + mem_cgroup_move_account_page_stat(from, to, nr_pages, + MEM_CGROUP_STAT_WRITEBACK); + mem_cgroup_charge_statistics(from, page, anon, -nr_pages); /* caller should have done css_get */ @@ -4309,7 +4357,7 @@ mem_cgroup_uncharge_swapcache(struct page *page, swp_entry_t ent, bool swapout) * css_get() was called in uncharge(). */ if (do_swap_account && swapout && memcg) - swap_cgroup_record(ent, css_id(&memcg->css)); + swap_cgroup_record(ent, mem_cgroup_id(memcg)); } #endif @@ -4361,8 +4409,8 @@ static int mem_cgroup_move_swap_account(swp_entry_t entry, { unsigned short old_id, new_id; - old_id = css_id(&from->css); - new_id = css_id(&to->css); + old_id = mem_cgroup_id(from); + new_id = mem_cgroup_id(to); if (swap_cgroup_cmpxchg(entry, old_id, new_id) == old_id) { mem_cgroup_swap_statistics(from, false); @@ -4654,7 +4702,7 @@ static int mem_cgroup_resize_limit(struct mem_cgroup *memcg, MEM_CGROUP_RECLAIM_SHRINK); curusage = res_counter_read_u64(&memcg->res, RES_USAGE); /* Usage is reduced ? */ - if (curusage >= oldusage) + if (curusage >= oldusage) retry_count--; else oldusage = curusage; @@ -4675,7 +4723,7 @@ static int mem_cgroup_resize_memsw_limit(struct mem_cgroup *memcg, int enlarge = 0; /* see mem_cgroup_resize_res_limit */ - retry_count = children * MEM_CGROUP_RECLAIM_RETRIES; + retry_count = children * MEM_CGROUP_RECLAIM_RETRIES; oldusage = res_counter_read_u64(&memcg->memsw, RES_USAGE); while (retry_count) { if (signal_pending(current)) { @@ -4917,31 +4965,18 @@ static void mem_cgroup_reparent_charges(struct mem_cgroup *memcg) } while (usage > 0); } -/* - * This mainly exists for tests during the setting of set of use_hierarchy. - * Since this is the very setting we are changing, the current hierarchy value - * is meaningless - */ -static inline bool __memcg_has_children(struct mem_cgroup *memcg) -{ - struct cgroup_subsys_state *pos; - - /* bounce at first found */ - css_for_each_child(pos, &memcg->css) - return true; - return false; -} - -/* - * Must be called with memcg_create_mutex held, unless the cgroup is guaranteed - * to be already dead (as in mem_cgroup_force_empty, for instance). This is - * from mem_cgroup_count_children(), in the sense that we don't really care how - * many children we have; we only need to know if we have any. It also counts - * any memcg without hierarchy as infertile. - */ static inline bool memcg_has_children(struct mem_cgroup *memcg) { - return memcg->use_hierarchy && __memcg_has_children(memcg); + lockdep_assert_held(&memcg_create_mutex); + /* + * The lock does not prevent addition or deletion to the list + * of children, but it prevents a new child from being + * initialized based on this parent in css_online(), so it's + * enough to decide whether hierarchically inherited + * attributes can still be changed or not. + */ + return memcg->use_hierarchy && + !list_empty(&memcg->css.cgroup->children); } /* @@ -4987,18 +5022,12 @@ static int mem_cgroup_force_empty_write(struct cgroup_subsys_state *css, unsigned int event) { struct mem_cgroup *memcg = mem_cgroup_from_css(css); - int ret; if (mem_cgroup_is_root(memcg)) return -EINVAL; - css_get(&memcg->css); - ret = mem_cgroup_force_empty(memcg); - css_put(&memcg->css); - - return ret; + return mem_cgroup_force_empty(memcg); } - static u64 mem_cgroup_hierarchy_read(struct cgroup_subsys_state *css, struct cftype *cft) { @@ -5027,7 +5056,7 @@ static int mem_cgroup_hierarchy_write(struct cgroup_subsys_state *css, */ if ((!parent_memcg || !parent_memcg->use_hierarchy) && (val == 1 || val == 0)) { - if (!__memcg_has_children(memcg)) + if (list_empty(&memcg->css.cgroup->children)) memcg->use_hierarchy = val; else retval = -EBUSY; @@ -5136,7 +5165,7 @@ static int memcg_update_kmem_limit(struct cgroup_subsys_state *css, u64 val) */ mutex_lock(&memcg_create_mutex); mutex_lock(&set_limit_mutex); - if (!memcg->kmem_account_flags && val != RESOURCE_MAX) { + if (!memcg->kmem_account_flags && val != RES_COUNTER_MAX) { if (cgroup_task_count(css->cgroup) || memcg_has_children(memcg)) { ret = -EBUSY; goto out; @@ -5146,7 +5175,7 @@ static int memcg_update_kmem_limit(struct cgroup_subsys_state *css, u64 val) ret = memcg_update_cache_sizes(memcg); if (ret) { - res_counter_set_limit(&memcg->kmem, RESOURCE_MAX); + res_counter_set_limit(&memcg->kmem, RES_COUNTER_MAX); goto out; } static_key_slow_inc(&memcg_kmem_enabled_key); @@ -5354,45 +5383,50 @@ static int mem_cgroup_move_charge_write(struct cgroup_subsys_state *css, static int memcg_numa_stat_show(struct cgroup_subsys_state *css, struct cftype *cft, struct seq_file *m) { + struct numa_stat { + const char *name; + unsigned int lru_mask; + }; + + static const struct numa_stat stats[] = { + { "total", LRU_ALL }, + { "file", LRU_ALL_FILE }, + { "anon", LRU_ALL_ANON }, + { "unevictable", BIT(LRU_UNEVICTABLE) }, + }; + const struct numa_stat *stat; int nid; - unsigned long total_nr, file_nr, anon_nr, unevictable_nr; - unsigned long node_nr; + unsigned long nr; struct mem_cgroup *memcg = mem_cgroup_from_css(css); - total_nr = mem_cgroup_nr_lru_pages(memcg, LRU_ALL); - seq_printf(m, "total=%lu", total_nr); - for_each_node_state(nid, N_MEMORY) { - node_nr = mem_cgroup_node_nr_lru_pages(memcg, nid, LRU_ALL); - seq_printf(m, " N%d=%lu", nid, node_nr); - } - seq_putc(m, '\n'); - - file_nr = mem_cgroup_nr_lru_pages(memcg, LRU_ALL_FILE); - seq_printf(m, "file=%lu", file_nr); - for_each_node_state(nid, N_MEMORY) { - node_nr = mem_cgroup_node_nr_lru_pages(memcg, nid, - LRU_ALL_FILE); - seq_printf(m, " N%d=%lu", nid, node_nr); - } - seq_putc(m, '\n'); - - anon_nr = mem_cgroup_nr_lru_pages(memcg, LRU_ALL_ANON); - seq_printf(m, "anon=%lu", anon_nr); - for_each_node_state(nid, N_MEMORY) { - node_nr = mem_cgroup_node_nr_lru_pages(memcg, nid, - LRU_ALL_ANON); - seq_printf(m, " N%d=%lu", nid, node_nr); + for (stat = stats; stat < stats + ARRAY_SIZE(stats); stat++) { + nr = mem_cgroup_nr_lru_pages(memcg, stat->lru_mask); + seq_printf(m, "%s=%lu", stat->name, nr); + for_each_node_state(nid, N_MEMORY) { + nr = mem_cgroup_node_nr_lru_pages(memcg, nid, + stat->lru_mask); + seq_printf(m, " N%d=%lu", nid, nr); + } + seq_putc(m, '\n'); + } + + for (stat = stats; stat < stats + ARRAY_SIZE(stats); stat++) { + struct mem_cgroup *iter; + + nr = 0; + for_each_mem_cgroup_tree(iter, memcg) + nr += mem_cgroup_nr_lru_pages(iter, stat->lru_mask); + seq_printf(m, "hierarchical_%s=%lu", stat->name, nr); + for_each_node_state(nid, N_MEMORY) { + nr = 0; + for_each_mem_cgroup_tree(iter, memcg) + nr += mem_cgroup_node_nr_lru_pages( + iter, nid, stat->lru_mask); + seq_printf(m, " N%d=%lu", nid, nr); + } + seq_putc(m, '\n'); } - seq_putc(m, '\n'); - unevictable_nr = mem_cgroup_nr_lru_pages(memcg, BIT(LRU_UNEVICTABLE)); - seq_printf(m, "unevictable=%lu", unevictable_nr); - for_each_node_state(nid, N_MEMORY) { - node_nr = mem_cgroup_node_nr_lru_pages(memcg, nid, - BIT(LRU_UNEVICTABLE)); - seq_printf(m, " N%d=%lu", nid, node_nr); - } - seq_putc(m, '\n'); return 0; } #endif /* CONFIG_NUMA */ @@ -5588,7 +5622,13 @@ static int compare_thresholds(const void *a, const void *b) const struct mem_cgroup_threshold *_a = a; const struct mem_cgroup_threshold *_b = b; - return _a->threshold - _b->threshold; + if (_a->threshold > _b->threshold) + return 1; + + if (_a->threshold < _b->threshold) + return -1; + + return 0; } static int mem_cgroup_oom_notify_cb(struct mem_cgroup *memcg) @@ -6138,7 +6178,6 @@ static void __mem_cgroup_free(struct mem_cgroup *memcg) size_t size = memcg_size(); mem_cgroup_remove_from_trees(memcg); - free_css_id(&mem_cgroup_subsys, &memcg->css); for_each_node(node) free_mem_cgroup_per_zone_info(memcg, node); @@ -6241,6 +6280,9 @@ mem_cgroup_css_online(struct cgroup_subsys_state *css) struct mem_cgroup *parent = mem_cgroup_from_css(css_parent(css)); int error = 0; + if (css->cgroup->id > MEM_CGROUP_ID_MAX) + return -ENOSPC; + if (!parent) return 0; @@ -6512,7 +6554,7 @@ static enum mc_target_type get_mctgt_type(struct vm_area_struct *vma, } /* There is a swap entry and a page doesn't exist or isn't charged */ if (ent.val && !ret && - css_id(&mc.from->css) == lookup_swap_cgroup_id(ent)) { + mem_cgroup_id(mc.from) == lookup_swap_cgroup_id(ent)) { ret = MC_TARGET_SWAP; if (target) target->ent = ent; @@ -6563,10 +6605,10 @@ static int mem_cgroup_count_precharge_pte_range(pmd_t *pmd, pte_t *pte; spinlock_t *ptl; - if (pmd_trans_huge_lock(pmd, vma) == 1) { + if (pmd_trans_huge_lock(pmd, vma, &ptl) == 1) { if (get_mctgt_type_thp(vma, addr, *pmd, NULL) == MC_TARGET_PAGE) mc.precharge += HPAGE_PMD_NR; - spin_unlock(&vma->vm_mm->page_table_lock); + spin_unlock(ptl); return 0; } @@ -6755,9 +6797,9 @@ static int mem_cgroup_move_charge_pte_range(pmd_t *pmd, * to be unlocked in __split_huge_page_splitting(), where the main * part of thp split is not executed yet. */ - if (pmd_trans_huge_lock(pmd, vma) == 1) { + if (pmd_trans_huge_lock(pmd, vma, &ptl) == 1) { if (mc.precharge < HPAGE_PMD_NR) { - spin_unlock(&vma->vm_mm->page_table_lock); + spin_unlock(ptl); return 0; } target_type = get_mctgt_type_thp(vma, addr, *pmd, &target); @@ -6774,7 +6816,7 @@ static int mem_cgroup_move_charge_pte_range(pmd_t *pmd, } put_page(page); } - spin_unlock(&vma->vm_mm->page_table_lock); + spin_unlock(ptl); return 0; } @@ -6932,7 +6974,6 @@ struct cgroup_subsys mem_cgroup_subsys = { .bind = mem_cgroup_bind, .base_cftypes = mem_cgroup_files, .early_init = 0, - .use_id = 1, }; #ifdef CONFIG_MEMCG_SWAP diff --git a/mm/memory-failure.c b/mm/memory-failure.c index d84c5e5331bb..b7c171602ba1 100644 --- a/mm/memory-failure.c +++ b/mm/memory-failure.c @@ -206,7 +206,7 @@ static int kill_proc(struct task_struct *t, unsigned long addr, int trapno, #ifdef __ARCH_SI_TRAPNO si.si_trapno = trapno; #endif - si.si_addr_lsb = compound_trans_order(compound_head(page)) + PAGE_SHIFT; + si.si_addr_lsb = compound_order(compound_head(page)) + PAGE_SHIFT; if ((flags & MF_ACTION_REQUIRED) && t == current) { si.si_code = BUS_MCEERR_AR; @@ -248,10 +248,12 @@ void shake_page(struct page *p, int access) */ if (access) { int nr; + int nid = page_to_nid(p); do { struct shrink_control shrink = { .gfp_mask = GFP_KERNEL, }; + node_set(nid, shrink.nodes_to_scan); nr = shrink_slab(&shrink, 1000, 1000); if (page_count(p) == 1) @@ -983,7 +985,7 @@ static int hwpoison_user_mappings(struct page *p, unsigned long pfn, static void set_page_hwpoison_huge_page(struct page *hpage) { int i; - int nr_pages = 1 << compound_trans_order(hpage); + int nr_pages = 1 << compound_order(hpage); for (i = 0; i < nr_pages; i++) SetPageHWPoison(hpage + i); } @@ -991,7 +993,7 @@ static void set_page_hwpoison_huge_page(struct page *hpage) static void clear_page_hwpoison_huge_page(struct page *hpage) { int i; - int nr_pages = 1 << compound_trans_order(hpage); + int nr_pages = 1 << compound_order(hpage); for (i = 0; i < nr_pages; i++) ClearPageHWPoison(hpage + i); } @@ -1112,8 +1114,10 @@ int memory_failure(unsigned long pfn, int trapno, int flags) * shake_page could have turned it free. */ if (is_free_buddy_page(p)) { - action_result(pfn, "free buddy, 2nd try", - DELAYED); + if (flags & MF_COUNT_INCREASED) + action_result(pfn, "free buddy", DELAYED); + else + action_result(pfn, "free buddy, 2nd try", DELAYED); return 0; } action_result(pfn, "non LRU", IGNORED); @@ -1204,6 +1208,9 @@ int memory_failure(unsigned long pfn, int trapno, int flags) for (ps = error_states;; ps++) if ((p->flags & ps->mask) == ps->res) break; + + page_flags |= (p->flags & (1UL << PG_dirty)); + if (!ps->mask) for (ps = error_states;; ps++) if ((page_flags & ps->mask) == ps->res) @@ -1262,7 +1269,7 @@ void memory_failure_queue(unsigned long pfn, int trapno, int flags) mf_cpu = &get_cpu_var(memory_failure_cpu); spin_lock_irqsave(&mf_cpu->lock, proc_flags); - if (kfifo_put(&mf_cpu->fifo, &entry)) + if (kfifo_put(&mf_cpu->fifo, entry)) schedule_work_on(smp_processor_id(), &mf_cpu->work); else pr_err("Memory failure: buffer overflow when queuing memory failure at %#lx\n", @@ -1339,7 +1346,17 @@ int unpoison_memory(unsigned long pfn) return 0; } - nr_pages = 1 << compound_trans_order(page); + /* + * unpoison_memory() can encounter thp only when the thp is being + * worked by memory_failure() and the page lock is not held yet. + * In such case, we yield to memory_failure() and make unpoison fail. + */ + if (!PageHuge(page) && PageTransHuge(page)) { + pr_info("MCE: Memory failure is now running on %#lx\n", pfn); + return 0; + } + + nr_pages = 1 << compound_order(page); if (!get_page_unless_zero(page)) { /* @@ -1353,7 +1370,7 @@ int unpoison_memory(unsigned long pfn) return 0; } if (TestClearPageHWPoison(p)) - atomic_long_sub(nr_pages, &num_poisoned_pages); + atomic_long_dec(&num_poisoned_pages); pr_info("MCE: Software-unpoisoned free page %#lx\n", pfn); return 0; } @@ -1375,7 +1392,7 @@ int unpoison_memory(unsigned long pfn) unlock_page(page); put_page(page); - if (freeit) + if (freeit && !(pfn == my_zero_pfn(0) && page_count(p) == 1)) put_page(page); return 0; @@ -1406,18 +1423,6 @@ static int __get_any_page(struct page *p, unsigned long pfn, int flags) return 1; /* - * The lock_memory_hotplug prevents a race with memory hotplug. - * This is a big hammer, a better would be nicer. - */ - lock_memory_hotplug(); - - /* - * Isolate the page, so that it doesn't get reallocated if it - * was free. This flag should be kept set until the source page - * is freed and PG_hwpoison on it is set. - */ - set_migratetype_isolate(p, true); - /* * When the target page is a free hugepage, just remove it * from free hugepage list. */ @@ -1437,7 +1442,6 @@ static int __get_any_page(struct page *p, unsigned long pfn, int flags) /* Not a free page */ ret = 1; } - unlock_memory_hotplug(); return ret; } @@ -1470,6 +1474,7 @@ 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); /* * This double-check of PageHWPoison is to avoid the race with @@ -1485,86 +1490,29 @@ static int soft_offline_huge_page(struct page *page, int flags) unlock_page(hpage); /* Keep page count to indicate a given hugepage is isolated. */ - ret = migrate_huge_page(hpage, new_page, MPOL_MF_MOVE_ALL, - MIGRATE_SYNC); - put_page(hpage); + list_move(&hpage->lru, &pagelist); + ret = migrate_pages(&pagelist, new_page, MPOL_MF_MOVE_ALL, + MIGRATE_SYNC, MR_MEMORY_FAILURE); if (ret) { pr_info("soft offline: %#lx: migration failed %d, type %lx\n", pfn, ret, page->flags); + /* + * We know that soft_offline_huge_page() tries to migrate + * only one hugepage pointed to by hpage, so we need not + * run through the pagelist here. + */ + putback_active_hugepage(hpage); + if (ret > 0) + ret = -EIO; } else { set_page_hwpoison_huge_page(hpage); dequeue_hwpoisoned_huge_page(hpage); - atomic_long_add(1 << compound_trans_order(hpage), + atomic_long_add(1 << compound_order(hpage), &num_poisoned_pages); } return ret; } -static int __soft_offline_page(struct page *page, int flags); - -/** - * soft_offline_page - Soft offline a page. - * @page: page to offline - * @flags: flags. Same as memory_failure(). - * - * Returns 0 on success, otherwise negated errno. - * - * Soft offline a page, by migration or invalidation, - * without killing anything. This is for the case when - * a page is not corrupted yet (so it's still valid to access), - * but has had a number of corrected errors and is better taken - * out. - * - * The actual policy on when to do that is maintained by - * user space. - * - * This should never impact any application or cause data loss, - * however it might take some time. - * - * This is not a 100% solution for all memory, but tries to be - * ``good enough'' for the majority of memory. - */ -int soft_offline_page(struct page *page, int flags) -{ - int ret; - unsigned long pfn = page_to_pfn(page); - struct page *hpage = compound_trans_head(page); - - if (PageHWPoison(page)) { - pr_info("soft offline: %#lx page already poisoned\n", pfn); - return -EBUSY; - } - if (!PageHuge(page) && PageTransHuge(hpage)) { - if (PageAnon(hpage) && unlikely(split_huge_page(hpage))) { - pr_info("soft offline: %#lx: failed to split THP\n", - pfn); - return -EBUSY; - } - } - - ret = get_any_page(page, pfn, flags); - if (ret < 0) - return ret; - if (ret) { /* for in-use pages */ - if (PageHuge(page)) - ret = soft_offline_huge_page(page, flags); - else - ret = __soft_offline_page(page, flags); - } else { /* for free pages */ - if (PageHuge(page)) { - set_page_hwpoison_huge_page(hpage); - dequeue_hwpoisoned_huge_page(hpage); - atomic_long_add(1 << compound_trans_order(hpage), - &num_poisoned_pages); - } else { - SetPageHWPoison(page); - atomic_long_inc(&num_poisoned_pages); - } - } - unset_migratetype_isolate(page, MIGRATE_MOVABLE); - return ret; -} - static int __soft_offline_page(struct page *page, int flags) { int ret; @@ -1651,3 +1599,79 @@ static int __soft_offline_page(struct page *page, int flags) } return ret; } + +/** + * soft_offline_page - Soft offline a page. + * @page: page to offline + * @flags: flags. Same as memory_failure(). + * + * Returns 0 on success, otherwise negated errno. + * + * Soft offline a page, by migration or invalidation, + * without killing anything. This is for the case when + * a page is not corrupted yet (so it's still valid to access), + * but has had a number of corrected errors and is better taken + * out. + * + * The actual policy on when to do that is maintained by + * user space. + * + * This should never impact any application or cause data loss, + * however it might take some time. + * + * This is not a 100% solution for all memory, but tries to be + * ``good enough'' for the majority of memory. + */ +int soft_offline_page(struct page *page, int flags) +{ + int ret; + unsigned long pfn = page_to_pfn(page); + struct page *hpage = compound_trans_head(page); + + if (PageHWPoison(page)) { + pr_info("soft offline: %#lx page already poisoned\n", pfn); + return -EBUSY; + } + if (!PageHuge(page) && PageTransHuge(hpage)) { + if (PageAnon(hpage) && unlikely(split_huge_page(hpage))) { + pr_info("soft offline: %#lx: failed to split THP\n", + pfn); + return -EBUSY; + } + } + + /* + * The lock_memory_hotplug prevents a race with memory hotplug. + * This is a big hammer, a better would be nicer. + */ + lock_memory_hotplug(); + + /* + * Isolate the page, so that it doesn't get reallocated if it + * was free. This flag should be kept set until the source page + * is freed and PG_hwpoison on it is set. + */ + if (get_pageblock_migratetype(page) != MIGRATE_ISOLATE) + set_migratetype_isolate(page, true); + + ret = get_any_page(page, pfn, flags); + unlock_memory_hotplug(); + if (ret > 0) { /* for in-use pages */ + if (PageHuge(page)) + ret = soft_offline_huge_page(page, flags); + else + ret = __soft_offline_page(page, flags); + } else if (ret == 0) { /* for free pages */ + if (PageHuge(page)) { + set_page_hwpoison_huge_page(hpage); + dequeue_hwpoisoned_huge_page(hpage); + atomic_long_add(1 << compound_order(hpage), + &num_poisoned_pages); + } else { + SetPageHWPoison(page); + atomic_long_inc(&num_poisoned_pages); + } + } + unset_migratetype_isolate(page, MIGRATE_MOVABLE); + return ret; +} diff --git a/mm/memory.c b/mm/memory.c index b3c6bf9a398e..0409e8f43fa0 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -69,8 +69,8 @@ #include "internal.h" -#ifdef LAST_NID_NOT_IN_PAGE_FLAGS -#warning Unfortunate NUMA and NUMA Balancing config, growing page-frame for last_nid. +#ifdef LAST_CPUPID_NOT_IN_PAGE_FLAGS +#warning Unfortunate NUMA and NUMA Balancing config, growing page-frame for last_cpupid. #endif #ifndef CONFIG_NEED_MULTIPLE_NODES @@ -373,30 +373,6 @@ void tlb_remove_table(struct mmu_gather *tlb, void *table) #endif /* CONFIG_HAVE_RCU_TABLE_FREE */ /* - * If a p?d_bad entry is found while walking page tables, report - * the error, before resetting entry to p?d_none. Usually (but - * very seldom) called out from the p?d_none_or_clear_bad macros. - */ - -void pgd_clear_bad(pgd_t *pgd) -{ - pgd_ERROR(*pgd); - pgd_clear(pgd); -} - -void pud_clear_bad(pud_t *pud) -{ - pud_ERROR(*pud); - pud_clear(pud); -} - -void pmd_clear_bad(pmd_t *pmd) -{ - pmd_ERROR(*pmd); - pmd_clear(pmd); -} - -/* * Note: this doesn't free the actual pages themselves. That * has been handled earlier when unmapping all the memory regions. */ @@ -406,7 +382,7 @@ static void free_pte_range(struct mmu_gather *tlb, pmd_t *pmd, pgtable_t token = pmd_pgtable(*pmd); pmd_clear(pmd); pte_free_tlb(tlb, token, addr); - tlb->mm->nr_ptes--; + atomic_long_dec(&tlb->mm->nr_ptes); } static inline void free_pmd_range(struct mmu_gather *tlb, pud_t *pud, @@ -477,8 +453,6 @@ static inline void free_pud_range(struct mmu_gather *tlb, pgd_t *pgd, /* * This function frees user-level page tables of a process. - * - * Must be called with pagetable lock held. */ void free_pgd_range(struct mmu_gather *tlb, unsigned long addr, unsigned long end, @@ -576,6 +550,7 @@ void free_pgtables(struct mmu_gather *tlb, struct vm_area_struct *vma, int __pte_alloc(struct mm_struct *mm, struct vm_area_struct *vma, pmd_t *pmd, unsigned long address) { + spinlock_t *ptl; pgtable_t new = pte_alloc_one(mm, address); int wait_split_huge_page; if (!new) @@ -596,15 +571,15 @@ int __pte_alloc(struct mm_struct *mm, struct vm_area_struct *vma, */ smp_wmb(); /* Could be smp_wmb__xxx(before|after)_spin_lock */ - spin_lock(&mm->page_table_lock); + ptl = pmd_lock(mm, pmd); wait_split_huge_page = 0; if (likely(pmd_none(*pmd))) { /* Has another populated it ? */ - mm->nr_ptes++; + atomic_long_inc(&mm->nr_ptes); pmd_populate(mm, pmd, new); new = NULL; } else if (unlikely(pmd_trans_splitting(*pmd))) wait_split_huge_page = 1; - spin_unlock(&mm->page_table_lock); + spin_unlock(ptl); if (new) pte_free(mm, new); if (wait_split_huge_page) @@ -705,7 +680,7 @@ static void print_bad_pte(struct vm_area_struct *vma, unsigned long addr, if (vma->vm_ops) printk(KERN_ALERT "vma->vm_ops->fault: %pSR\n", vma->vm_ops->fault); - if (vma->vm_file && vma->vm_file->f_op) + if (vma->vm_file) printk(KERN_ALERT "vma->vm_file->f_op->mmap: %pSR\n", vma->vm_file->f_op->mmap); dump_stack(); @@ -861,6 +836,8 @@ copy_one_pte(struct mm_struct *dst_mm, struct mm_struct *src_mm, */ make_migration_entry_read(&entry); pte = swp_entry_to_pte(entry); + if (pte_swp_soft_dirty(*src_pte)) + pte = pte_swp_mksoft_dirty(pte); set_pte_at(src_mm, addr, src_pte, pte); } } @@ -1505,7 +1482,8 @@ struct page *follow_page_mask(struct vm_area_struct *vma, if (pud_none(*pud)) goto no_page_table; if (pud_huge(*pud) && vma->vm_flags & VM_HUGETLB) { - BUG_ON(flags & FOLL_GET); + if (flags & FOLL_GET) + goto out; page = follow_huge_pud(mm, address, pud, flags & FOLL_WRITE); goto out; } @@ -1516,8 +1494,20 @@ struct page *follow_page_mask(struct vm_area_struct *vma, if (pmd_none(*pmd)) goto no_page_table; if (pmd_huge(*pmd) && vma->vm_flags & VM_HUGETLB) { - BUG_ON(flags & FOLL_GET); page = follow_huge_pmd(mm, address, pmd, flags & FOLL_WRITE); + if (flags & FOLL_GET) { + /* + * Refcount on tail pages are not well-defined and + * shouldn't be taken. The caller should handle a NULL + * return when trying to follow tail pages. + */ + if (PageHead(page)) + get_page(page); + else { + page = NULL; + goto out; + } + } goto out; } if ((flags & FOLL_NUMA) && pmd_numa(*pmd)) @@ -1527,20 +1517,20 @@ struct page *follow_page_mask(struct vm_area_struct *vma, split_huge_page_pmd(vma, address, pmd); goto split_fallthrough; } - spin_lock(&mm->page_table_lock); + ptl = pmd_lock(mm, pmd); if (likely(pmd_trans_huge(*pmd))) { if (unlikely(pmd_trans_splitting(*pmd))) { - spin_unlock(&mm->page_table_lock); + spin_unlock(ptl); wait_split_huge_page(vma->anon_vma, pmd); } else { page = follow_trans_huge_pmd(vma, address, pmd, flags); - spin_unlock(&mm->page_table_lock); + spin_unlock(ptl); *page_mask = HPAGE_PMD_NR - 1; goto out; } } else - spin_unlock(&mm->page_table_lock); + spin_unlock(ptl); /* fall through */ } split_fallthrough: @@ -2730,6 +2720,14 @@ static int do_wp_page(struct mm_struct *mm, struct vm_area_struct *vma, get_page(dirty_page); reuse: + /* + * Clear the pages cpupid information as the existing + * information potentially belongs to a now completely + * unrelated process. + */ + if (old_page) + page_cpupid_xchg_last(old_page, (1 << LAST_CPUPID_SHIFT) - 1); + flush_cache_page(vma, address, pte_pfn(orig_pte)); entry = pte_mkyoung(orig_pte); entry = maybe_mkwrite(pte_mkdirty(entry), vma); @@ -3530,13 +3528,16 @@ static int do_nonlinear_fault(struct mm_struct *mm, struct vm_area_struct *vma, } int numa_migrate_prep(struct page *page, struct vm_area_struct *vma, - unsigned long addr, int current_nid) + unsigned long addr, int page_nid, + int *flags) { get_page(page); count_vm_numa_event(NUMA_HINT_FAULTS); - if (current_nid == numa_node_id()) + if (page_nid == numa_node_id()) { count_vm_numa_event(NUMA_HINT_FAULTS_LOCAL); + *flags |= TNF_FAULT_LOCAL; + } return mpol_misplaced(page, vma, addr); } @@ -3546,9 +3547,11 @@ int do_numa_page(struct mm_struct *mm, struct vm_area_struct *vma, { struct page *page = NULL; spinlock_t *ptl; - int current_nid = -1; + int page_nid = -1; + int last_cpupid; int target_nid; bool migrated = false; + int flags = 0; /* * The "pte" at this point cannot be used safely without @@ -3575,123 +3578,44 @@ int do_numa_page(struct mm_struct *mm, struct vm_area_struct *vma, pte_unmap_unlock(ptep, ptl); return 0; } + BUG_ON(is_zero_pfn(page_to_pfn(page))); - current_nid = page_to_nid(page); - target_nid = numa_migrate_prep(page, vma, addr, current_nid); + /* + * Avoid grouping on DSO/COW pages in specific and RO pages + * in general, RO pages shouldn't hurt as much anyway since + * they can be in shared cache state. + */ + if (!pte_write(pte)) + flags |= TNF_NO_GROUP; + + /* + * Flag if the page is shared between multiple address spaces. This + * is later used when determining whether to group tasks together + */ + if (page_mapcount(page) > 1 && (vma->vm_flags & VM_SHARED)) + flags |= TNF_SHARED; + + last_cpupid = page_cpupid_last(page); + page_nid = page_to_nid(page); + target_nid = numa_migrate_prep(page, vma, addr, page_nid, &flags); pte_unmap_unlock(ptep, ptl); if (target_nid == -1) { - /* - * Account for the fault against the current node if it not - * being replaced regardless of where the page is located. - */ - current_nid = numa_node_id(); put_page(page); goto out; } /* Migrate to the requested node */ - migrated = migrate_misplaced_page(page, target_nid); - if (migrated) - current_nid = target_nid; - -out: - if (current_nid != -1) - task_numa_fault(current_nid, 1, migrated); - return 0; -} - -/* NUMA hinting page fault entry point for regular pmds */ -#ifdef CONFIG_NUMA_BALANCING -static int do_pmd_numa_page(struct mm_struct *mm, struct vm_area_struct *vma, - unsigned long addr, pmd_t *pmdp) -{ - pmd_t pmd; - pte_t *pte, *orig_pte; - unsigned long _addr = addr & PMD_MASK; - unsigned long offset; - spinlock_t *ptl; - bool numa = false; - int local_nid = numa_node_id(); - - spin_lock(&mm->page_table_lock); - pmd = *pmdp; - if (pmd_numa(pmd)) { - set_pmd_at(mm, _addr, pmdp, pmd_mknonnuma(pmd)); - numa = true; + migrated = migrate_misplaced_page(page, vma, target_nid); + if (migrated) { + page_nid = target_nid; + flags |= TNF_MIGRATED; } - spin_unlock(&mm->page_table_lock); - if (!numa) - return 0; - - /* we're in a page fault so some vma must be in the range */ - BUG_ON(!vma); - BUG_ON(vma->vm_start >= _addr + PMD_SIZE); - offset = max(_addr, vma->vm_start) & ~PMD_MASK; - VM_BUG_ON(offset >= PMD_SIZE); - orig_pte = pte = pte_offset_map_lock(mm, pmdp, _addr, &ptl); - pte += offset >> PAGE_SHIFT; - for (addr = _addr + offset; addr < _addr + PMD_SIZE; pte++, addr += PAGE_SIZE) { - pte_t pteval = *pte; - struct page *page; - int curr_nid = local_nid; - int target_nid; - bool migrated; - if (!pte_present(pteval)) - continue; - if (!pte_numa(pteval)) - continue; - if (addr >= vma->vm_end) { - vma = find_vma(mm, addr); - /* there's a pte present so there must be a vma */ - BUG_ON(!vma); - BUG_ON(addr < vma->vm_start); - } - if (pte_numa(pteval)) { - pteval = pte_mknonnuma(pteval); - set_pte_at(mm, addr, pte, pteval); - } - page = vm_normal_page(vma, addr, pteval); - if (unlikely(!page)) - continue; - /* only check non-shared pages */ - if (unlikely(page_mapcount(page) != 1)) - continue; - - /* - * Note that the NUMA fault is later accounted to either - * the node that is currently running or where the page is - * migrated to. - */ - curr_nid = local_nid; - target_nid = numa_migrate_prep(page, vma, addr, - page_to_nid(page)); - if (target_nid == -1) { - put_page(page); - continue; - } - - /* Migrate to the requested node */ - pte_unmap_unlock(pte, ptl); - migrated = migrate_misplaced_page(page, target_nid); - if (migrated) - curr_nid = target_nid; - task_numa_fault(curr_nid, 1, migrated); - - pte = pte_offset_map_lock(mm, pmdp, addr, &ptl); - } - pte_unmap_unlock(orig_pte, ptl); - - return 0; -} -#else -static int do_pmd_numa_page(struct mm_struct *mm, struct vm_area_struct *vma, - unsigned long addr, pmd_t *pmdp) -{ - BUG(); +out: + if (page_nid != -1) + task_numa_fault(last_cpupid, page_nid, 1, flags); return 0; } -#endif /* CONFIG_NUMA_BALANCING */ /* * These routines also need to handle stuff like marking pages dirty @@ -3706,7 +3630,7 @@ static int do_pmd_numa_page(struct mm_struct *mm, struct vm_area_struct *vma, * but allow concurrent faults), and pte mapped but not yet locked. * We return with mmap_sem still held, but pte unmapped and unlocked. */ -int handle_pte_fault(struct mm_struct *mm, +static int handle_pte_fault(struct mm_struct *mm, struct vm_area_struct *vma, unsigned long address, pte_t *pte, pmd_t *pmd, unsigned int flags) { @@ -3765,22 +3689,14 @@ unlock: /* * By the time we get here, we already hold the mm semaphore */ -int handle_mm_fault(struct mm_struct *mm, struct vm_area_struct *vma, - unsigned long address, unsigned int flags) +static int __handle_mm_fault(struct mm_struct *mm, struct vm_area_struct *vma, + unsigned long address, unsigned int flags) { pgd_t *pgd; pud_t *pud; pmd_t *pmd; pte_t *pte; - __set_current_state(TASK_RUNNING); - - count_vm_event(PGFAULT); - mem_cgroup_count_vm_event(mm, PGFAULT); - - /* do counter updates before entering really critical section. */ - check_sync_rss_stat(current); - if (unlikely(is_vm_hugetlb_page(vma))) return hugetlb_fault(mm, vma, address, flags); @@ -3793,9 +3709,12 @@ retry: if (!pmd) return VM_FAULT_OOM; if (pmd_none(*pmd) && transparent_hugepage_enabled(vma)) { + int ret = VM_FAULT_FALLBACK; if (!vma->vm_ops) - return do_huge_pmd_anonymous_page(mm, vma, address, - pmd, flags); + ret = do_huge_pmd_anonymous_page(mm, vma, address, + pmd, flags); + if (!(ret & VM_FAULT_FALLBACK)) + return ret; } else { pmd_t orig_pmd = *pmd; int ret; @@ -3836,8 +3755,8 @@ retry: } } - if (pmd_numa(*pmd)) - return do_pmd_numa_page(mm, vma, address, pmd); + /* THP should already have been handled */ + BUG_ON(pmd_numa(*pmd)); /* * Use __pte_alloc instead of pte_alloc_map, because we can't @@ -3861,6 +3780,43 @@ retry: return handle_pte_fault(mm, vma, address, pte, pmd, flags); } +int handle_mm_fault(struct mm_struct *mm, struct vm_area_struct *vma, + unsigned long address, unsigned int flags) +{ + int ret; + + __set_current_state(TASK_RUNNING); + + count_vm_event(PGFAULT); + mem_cgroup_count_vm_event(mm, PGFAULT); + + /* do counter updates before entering really critical section. */ + check_sync_rss_stat(current); + + /* + * Enable the memcg OOM handling for faults triggered in user + * space. Kernel faults are handled more gracefully. + */ + if (flags & FAULT_FLAG_USER) + mem_cgroup_oom_enable(); + + ret = __handle_mm_fault(mm, vma, address, flags); + + if (flags & FAULT_FLAG_USER) { + mem_cgroup_oom_disable(); + /* + * The task may have entered a memcg OOM situation but + * if the allocation error was handled gracefully (no + * VM_FAULT_OOM), there is no need to kill anything. + * Just clean up the OOM state peacefully. + */ + if (task_in_memcg_oom(current) && !(ret & VM_FAULT_OOM)) + mem_cgroup_oom_synchronize(false); + } + + return ret; +} + #ifndef __PAGETABLE_PUD_FOLDED /* * Allocate page upper directory. @@ -4314,3 +4270,28 @@ void copy_user_huge_page(struct page *dst, struct page *src, } } #endif /* CONFIG_TRANSPARENT_HUGEPAGE || CONFIG_HUGETLBFS */ + +#if USE_SPLIT_PTE_PTLOCKS && BLOATED_SPINLOCKS +static struct kmem_cache *page_ptl_cachep; +void __init ptlock_cache_init(void) +{ + page_ptl_cachep = kmem_cache_create("page->ptl", sizeof(spinlock_t), 0, + SLAB_PANIC, NULL); +} + +bool ptlock_alloc(struct page *page) +{ + spinlock_t *ptl; + + ptl = kmalloc(sizeof(spinlock_t), GFP_KERNEL); + if (!ptl) + return false; + page->ptl = ptl; + return true; +} + +void ptlock_free(struct page *page) +{ + kfree(page->ptl); +} +#endif diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c index ca1dd3aa5eee..489f235502db 100644 --- a/mm/memory_hotplug.c +++ b/mm/memory_hotplug.c @@ -30,6 +30,8 @@ #include <linux/mm_inline.h> #include <linux/firmware-map.h> #include <linux/stop_machine.h> +#include <linux/hugetlb.h> +#include <linux/memblock.h> #include <asm/tlbflush.h> @@ -51,14 +53,10 @@ DEFINE_MUTEX(mem_hotplug_mutex); void lock_memory_hotplug(void) { mutex_lock(&mem_hotplug_mutex); - - /* for exclusive hibernation if CONFIG_HIBERNATION=y */ - lock_system_sleep(); } void unlock_memory_hotplug(void) { - unlock_system_sleep(); mutex_unlock(&mem_hotplug_mutex); } @@ -194,7 +192,7 @@ void register_page_bootmem_info_node(struct pglist_data *pgdat) zone = &pgdat->node_zones[0]; for (; zone < pgdat->node_zones + MAX_NR_ZONES - 1; zone++) { - if (zone->wait_table) { + if (zone_is_initialized(zone)) { nr_pages = zone->wait_table_hash_nr_entries * sizeof(wait_queue_head_t); nr_pages = PAGE_ALIGN(nr_pages) >> PAGE_SHIFT; @@ -229,8 +227,8 @@ static void grow_zone_span(struct zone *zone, unsigned long start_pfn, zone_span_writelock(zone); - old_zone_end_pfn = zone->zone_start_pfn + zone->spanned_pages; - if (!zone->spanned_pages || start_pfn < zone->zone_start_pfn) + old_zone_end_pfn = zone_end_pfn(zone); + if (zone_is_empty(zone) || start_pfn < zone->zone_start_pfn) zone->zone_start_pfn = start_pfn; zone->spanned_pages = max(old_zone_end_pfn, end_pfn) - @@ -305,7 +303,7 @@ static int __meminit move_pfn_range_left(struct zone *z1, struct zone *z2, goto out_fail; /* use start_pfn for z1's start_pfn if z1 is empty */ - if (z1->spanned_pages) + if (!zone_is_empty(z1)) z1_start_pfn = z1->zone_start_pfn; else z1_start_pfn = start_pfn; @@ -347,7 +345,7 @@ static int __meminit move_pfn_range_right(struct zone *z1, struct zone *z2, goto out_fail; /* use end_pfn for z2's end_pfn if z2 is empty */ - if (z2->spanned_pages) + if (!zone_is_empty(z2)) z2_end_pfn = zone_end_pfn(z2); else z2_end_pfn = end_pfn; @@ -368,8 +366,7 @@ out_fail: static void grow_pgdat_span(struct pglist_data *pgdat, unsigned long start_pfn, unsigned long end_pfn) { - unsigned long old_pgdat_end_pfn = - pgdat->node_start_pfn + pgdat->node_spanned_pages; + unsigned long old_pgdat_end_pfn = pgdat_end_pfn(pgdat); if (!pgdat->node_spanned_pages || start_pfn < pgdat->node_start_pfn) pgdat->node_start_pfn = start_pfn; @@ -405,13 +402,12 @@ static int __meminit __add_zone(struct zone *zone, unsigned long phys_start_pfn) static int __meminit __add_section(int nid, struct zone *zone, unsigned long phys_start_pfn) { - int nr_pages = PAGES_PER_SECTION; int ret; if (pfn_valid(phys_start_pfn)) return -EEXIST; - ret = sparse_add_one_section(zone, phys_start_pfn, nr_pages); + ret = sparse_add_one_section(zone, phys_start_pfn); if (ret < 0) return ret; @@ -514,8 +510,9 @@ static int find_biggest_section_pfn(int nid, struct zone *zone, static void shrink_zone_span(struct zone *zone, unsigned long start_pfn, unsigned long end_pfn) { - unsigned long zone_start_pfn = zone->zone_start_pfn; - unsigned long zone_end_pfn = zone->zone_start_pfn + zone->spanned_pages; + unsigned long zone_start_pfn = zone->zone_start_pfn; + unsigned long z = zone_end_pfn(zone); /* zone_end_pfn namespace clash */ + unsigned long zone_end_pfn = z; unsigned long pfn; struct mem_section *ms; int nid = zone_to_nid(zone); @@ -581,9 +578,9 @@ static void shrink_zone_span(struct zone *zone, unsigned long start_pfn, static void shrink_pgdat_span(struct pglist_data *pgdat, unsigned long start_pfn, unsigned long end_pfn) { - unsigned long pgdat_start_pfn = pgdat->node_start_pfn; - unsigned long pgdat_end_pfn = - pgdat->node_start_pfn + pgdat->node_spanned_pages; + unsigned long pgdat_start_pfn = pgdat->node_start_pfn; + unsigned long p = pgdat_end_pfn(pgdat); /* pgdat_end_pfn namespace clash */ + unsigned long pgdat_end_pfn = p; unsigned long pfn; struct mem_section *ms; int nid = pgdat->node_id; @@ -937,7 +934,7 @@ int __ref online_pages(unsigned long pfn, unsigned long nr_pages, int online_typ arg.nr_pages = nr_pages; node_states_check_changes_online(nr_pages, zone, &arg); - nid = page_to_nid(pfn_to_page(pfn)); + nid = pfn_to_nid(pfn); ret = memory_notify(MEM_GOING_ONLINE, &arg); ret = notifier_to_errno(ret); @@ -1046,17 +1043,23 @@ static void rollback_node_hotadd(int nid, pg_data_t *pgdat) } -/* +/** + * try_online_node - online a node if offlined + * * called by cpu_up() to online a node without onlined memory. */ -int mem_online_node(int nid) +int try_online_node(int nid) { pg_data_t *pgdat; int ret; + if (node_online(nid)) + return 0; + lock_memory_hotplug(); pgdat = hotadd_new_pgdat(nid, 0); if (!pgdat) { + pr_err("Cannot online node %d due to NULL pgdat\n", nid); ret = -ENOMEM; goto out; } @@ -1064,11 +1067,34 @@ int mem_online_node(int nid) ret = register_one_node(nid); BUG_ON(ret); + if (pgdat->node_zonelists->_zonerefs->zone == NULL) { + mutex_lock(&zonelists_mutex); + build_all_zonelists(NULL, NULL); + mutex_unlock(&zonelists_mutex); + } + out: unlock_memory_hotplug(); return ret; } +static int check_hotplug_memory_range(u64 start, u64 size) +{ + u64 start_pfn = start >> PAGE_SHIFT; + u64 nr_pages = size >> PAGE_SHIFT; + + /* Memory range must be aligned with section */ + if ((start_pfn & ~PAGE_SECTION_MASK) || + (nr_pages % PAGES_PER_SECTION) || (!nr_pages)) { + pr_err("Section-unaligned hotplug range: start 0x%llx, size 0x%llx\n", + (unsigned long long)start, + (unsigned long long)size); + return -EINVAL; + } + + return 0; +} + /* we are OK calling __meminit stuff here - we have CONFIG_MEMORY_HOTPLUG */ int __ref add_memory(int nid, u64 start, u64 size) { @@ -1078,6 +1104,10 @@ int __ref add_memory(int nid, u64 start, u64 size) struct resource *res; int ret; + ret = check_hotplug_memory_range(start, size); + if (ret) + return ret; + lock_memory_hotplug(); res = register_memory_resource(start, size); @@ -1208,10 +1238,12 @@ static int test_pages_in_a_zone(unsigned long start_pfn, unsigned long end_pfn) } /* - * Scanning pfn is much easier than scanning lru list. - * Scan pfn from start to end and Find LRU page. + * Scan pfn range [start,end) to find movable/migratable pages (LRU pages + * and hugepages). We scan pfn because it's much easier than scanning over + * linked list. This function returns the pfn of the first found movable + * page if it's found, otherwise 0. */ -static unsigned long scan_lru_pages(unsigned long start, unsigned long end) +static unsigned long scan_movable_pages(unsigned long start, unsigned long end) { unsigned long pfn; struct page *page; @@ -1220,6 +1252,13 @@ static unsigned long scan_lru_pages(unsigned long start, unsigned long end) page = pfn_to_page(pfn); if (PageLRU(page)) return pfn; + if (PageHuge(page)) { + if (is_hugepage_active(page)) + return pfn; + else + pfn = round_up(pfn + 1, + 1 << compound_order(page)) - 1; + } } } return 0; @@ -1240,6 +1279,19 @@ do_migrate_range(unsigned long start_pfn, unsigned long end_pfn) if (!pfn_valid(pfn)) continue; page = pfn_to_page(pfn); + + if (PageHuge(page)) { + struct page *head = compound_head(page); + pfn = page_to_pfn(head) + (1<<compound_order(head)) - 1; + if (compound_order(head) > PFN_SECTION_SHIFT) { + ret = -EBUSY; + break; + } + if (isolate_huge_page(page, &source)) + move_pages -= 1 << compound_order(head); + continue; + } + if (!get_page_unless_zero(page)) continue; /* @@ -1272,7 +1324,7 @@ do_migrate_range(unsigned long start_pfn, unsigned long end_pfn) } if (!list_empty(&source)) { if (not_managed) { - putback_lru_pages(&source); + putback_movable_pages(&source); goto out; } @@ -1283,7 +1335,7 @@ do_migrate_range(unsigned long start_pfn, unsigned long end_pfn) ret = migrate_pages(&source, alloc_migrate_target, 0, MIGRATE_SYNC, MR_MEMORY_HOTPLUG); if (ret) - putback_lru_pages(&source); + putback_movable_pages(&source); } out: return ret; @@ -1371,6 +1423,36 @@ static bool can_offline_normal(struct zone *zone, unsigned long nr_pages) } #endif /* CONFIG_MOVABLE_NODE */ +static int __init cmdline_parse_movable_node(char *p) +{ +#ifdef CONFIG_MOVABLE_NODE + /* + * Memory used by the kernel cannot be hot-removed because Linux + * cannot migrate the kernel pages. When memory hotplug is + * enabled, we should prevent memblock from allocating memory + * for the kernel. + * + * ACPI SRAT records all hotpluggable memory ranges. But before + * SRAT is parsed, we don't know about it. + * + * The kernel image is loaded into memory at very early time. We + * cannot prevent this anyway. So on NUMA system, we set any + * node the kernel resides in as un-hotpluggable. + * + * Since on modern servers, one node could have double-digit + * gigabytes memory, we can assume the memory around the kernel + * image is also un-hotpluggable. So before SRAT is parsed, just + * allocate memory near the kernel image to try the best to keep + * the kernel away from hotpluggable memory. + */ + memblock_set_bottom_up(true); +#else + pr_warn("movable_node option not supported\n"); +#endif + return 0; +} +early_param("movable_node", cmdline_parse_movable_node); + /* check which state of node_states will be changed when offline memory */ static void node_states_check_changes_offline(unsigned long nr_pages, struct zone *zone, struct memory_notify *arg) @@ -1472,7 +1554,6 @@ static int __ref __offline_pages(unsigned long start_pfn, struct zone *zone; struct memory_notify arg; - BUG_ON(start_pfn >= end_pfn); /* at least, alignment against pageblock is necessary */ if (!IS_ALIGNED(start_pfn, pageblock_nr_pages)) return -EINVAL; @@ -1527,8 +1608,8 @@ repeat: drain_all_pages(); } - pfn = scan_lru_pages(start_pfn, end_pfn); - if (pfn) { /* We have page on LRU */ + pfn = scan_movable_pages(start_pfn, end_pfn); + if (pfn) { /* We have movable pages */ ret = do_migrate_range(pfn, end_pfn); if (!ret) { drain = 1; @@ -1547,6 +1628,11 @@ repeat: yield(); /* drain pcp pages, this is synchronous. */ drain_all_pages(); + /* + * dissolve free hugepages in the memory block before doing offlining + * actually in order to make hugetlbfs's object counting consistent. + */ + dissolve_free_huge_pages(start_pfn, end_pfn); /* check again */ offlined_pages = check_pages_isolated(start_pfn, end_pfn); if (offlined_pages < 0) { @@ -1657,7 +1743,7 @@ int walk_memory_range(unsigned long start_pfn, unsigned long end_pfn, } #ifdef CONFIG_MEMORY_HOTREMOVE -static int is_memblock_offlined_cb(struct memory_block *mem, void *arg) +static int check_memblock_offlined_cb(struct memory_block *mem, void *arg) { int ret = !is_memblock_offlined(mem); @@ -1674,9 +1760,8 @@ static int is_memblock_offlined_cb(struct memory_block *mem, void *arg) return ret; } -static int check_cpu_on_node(void *data) +static int check_cpu_on_node(pg_data_t *pgdat) { - struct pglist_data *pgdat = data; int cpu; for_each_present_cpu(cpu) { @@ -1691,10 +1776,9 @@ static int check_cpu_on_node(void *data) return 0; } -static void unmap_cpu_on_node(void *data) +static void unmap_cpu_on_node(pg_data_t *pgdat) { #ifdef CONFIG_ACPI_NUMA - struct pglist_data *pgdat = data; int cpu; for_each_possible_cpu(cpu) @@ -1703,10 +1787,11 @@ static void unmap_cpu_on_node(void *data) #endif } -static int check_and_unmap_cpu_on_node(void *data) +static int check_and_unmap_cpu_on_node(pg_data_t *pgdat) { - int ret = check_cpu_on_node(data); + int ret; + ret = check_cpu_on_node(pgdat); if (ret) return ret; @@ -1715,11 +1800,18 @@ static int check_and_unmap_cpu_on_node(void *data) * the cpu_to_node() now. */ - unmap_cpu_on_node(data); + unmap_cpu_on_node(pgdat); return 0; } -/* offline the node if all memory sections of this node are removed */ +/** + * try_offline_node + * + * Offline a node if all memory sections and cpus of the node are removed. + * + * NOTE: The caller must call lock_device_hotplug() to serialize hotplug + * and online/offline operations before this call. + */ void try_offline_node(int nid) { pg_data_t *pgdat = NODE_DATA(nid); @@ -1745,7 +1837,7 @@ void try_offline_node(int nid) return; } - if (stop_machine(check_and_unmap_cpu_on_node, pgdat, NULL)) + if (check_and_unmap_cpu_on_node(pgdat)) return; /* @@ -1782,10 +1874,19 @@ void try_offline_node(int nid) } EXPORT_SYMBOL(try_offline_node); +/** + * remove_memory + * + * NOTE: The caller must call lock_device_hotplug() to serialize hotplug + * and online/offline operations before this call, as required by + * try_offline_node(). + */ void __ref remove_memory(int nid, u64 start, u64 size) { int ret; + BUG_ON(check_hotplug_memory_range(start, size)); + lock_memory_hotplug(); /* @@ -1794,7 +1895,7 @@ void __ref remove_memory(int nid, u64 start, u64 size) * if this is not the case. */ ret = walk_memory_range(PFN_DOWN(start), PFN_UP(start + size - 1), NULL, - is_memblock_offlined_cb); + check_memblock_offlined_cb); if (ret) { unlock_memory_hotplug(); BUG(); diff --git a/mm/mempolicy.c b/mm/mempolicy.c index 4baf12e534d1..c4403cdf3433 100644 --- a/mm/mempolicy.c +++ b/mm/mempolicy.c @@ -123,16 +123,19 @@ static struct mempolicy preferred_node_policy[MAX_NUMNODES]; static struct mempolicy *get_task_policy(struct task_struct *p) { struct mempolicy *pol = p->mempolicy; - int node; if (!pol) { - node = numa_node_id(); - if (node != NUMA_NO_NODE) - pol = &preferred_node_policy[node]; + int node = numa_node_id(); - /* preferred_node_policy is not initialised early in boot */ - if (!pol->mode) - pol = NULL; + if (node != NUMA_NO_NODE) { + pol = &preferred_node_policy[node]; + /* + * preferred_node_policy is not initialised early in + * boot + */ + if (!pol->mode) + pol = NULL; + } } return pol; @@ -473,8 +476,11 @@ static const struct mempolicy_operations mpol_ops[MPOL_MAX] = { static void migrate_page_add(struct page *page, struct list_head *pagelist, unsigned long flags); -/* Scan through pages checking if pages follow certain conditions. */ -static int check_pte_range(struct vm_area_struct *vma, pmd_t *pmd, +/* + * Scan through pages checking if pages follow certain conditions, + * and move them to the pagelist if they do. + */ +static int queue_pages_pte_range(struct vm_area_struct *vma, pmd_t *pmd, unsigned long addr, unsigned long end, const nodemask_t *nodes, unsigned long flags, void *private) @@ -512,7 +518,32 @@ static int check_pte_range(struct vm_area_struct *vma, pmd_t *pmd, return addr != end; } -static inline int check_pmd_range(struct vm_area_struct *vma, pud_t *pud, +static void queue_pages_hugetlb_pmd_range(struct vm_area_struct *vma, + pmd_t *pmd, const nodemask_t *nodes, unsigned long flags, + void *private) +{ +#ifdef CONFIG_HUGETLB_PAGE + int nid; + struct page *page; + spinlock_t *ptl; + + ptl = huge_pte_lock(hstate_vma(vma), vma->vm_mm, (pte_t *)pmd); + page = pte_page(huge_ptep_get((pte_t *)pmd)); + nid = page_to_nid(page); + if (node_isset(nid, *nodes) == !!(flags & MPOL_MF_INVERT)) + goto unlock; + /* With MPOL_MF_MOVE, we migrate only unshared hugepage. */ + if (flags & (MPOL_MF_MOVE_ALL) || + (flags & MPOL_MF_MOVE && page_mapcount(page) == 1)) + isolate_huge_page(page, private); +unlock: + spin_unlock(ptl); +#else + BUG(); +#endif +} + +static inline int queue_pages_pmd_range(struct vm_area_struct *vma, pud_t *pud, unsigned long addr, unsigned long end, const nodemask_t *nodes, unsigned long flags, void *private) @@ -523,17 +554,24 @@ static inline int check_pmd_range(struct vm_area_struct *vma, pud_t *pud, pmd = pmd_offset(pud, addr); do { next = pmd_addr_end(addr, end); + if (!pmd_present(*pmd)) + continue; + if (pmd_huge(*pmd) && is_vm_hugetlb_page(vma)) { + queue_pages_hugetlb_pmd_range(vma, pmd, nodes, + flags, private); + continue; + } split_huge_page_pmd(vma, addr, pmd); if (pmd_none_or_trans_huge_or_clear_bad(pmd)) continue; - if (check_pte_range(vma, pmd, addr, next, nodes, + if (queue_pages_pte_range(vma, pmd, addr, next, nodes, flags, private)) return -EIO; } while (pmd++, addr = next, addr != end); return 0; } -static inline int check_pud_range(struct vm_area_struct *vma, pgd_t *pgd, +static inline int queue_pages_pud_range(struct vm_area_struct *vma, pgd_t *pgd, unsigned long addr, unsigned long end, const nodemask_t *nodes, unsigned long flags, void *private) @@ -544,16 +582,18 @@ static inline int check_pud_range(struct vm_area_struct *vma, pgd_t *pgd, pud = pud_offset(pgd, addr); do { next = pud_addr_end(addr, end); + if (pud_huge(*pud) && is_vm_hugetlb_page(vma)) + continue; if (pud_none_or_clear_bad(pud)) continue; - if (check_pmd_range(vma, pud, addr, next, nodes, + if (queue_pages_pmd_range(vma, pud, addr, next, nodes, flags, private)) return -EIO; } while (pud++, addr = next, addr != end); return 0; } -static inline int check_pgd_range(struct vm_area_struct *vma, +static inline int queue_pages_pgd_range(struct vm_area_struct *vma, unsigned long addr, unsigned long end, const nodemask_t *nodes, unsigned long flags, void *private) @@ -566,7 +606,7 @@ static inline int check_pgd_range(struct vm_area_struct *vma, next = pgd_addr_end(addr, end); if (pgd_none_or_clear_bad(pgd)) continue; - if (check_pud_range(vma, pgd, addr, next, nodes, + if (queue_pages_pud_range(vma, pgd, addr, next, nodes, flags, private)) return -EIO; } while (pgd++, addr = next, addr != end); @@ -604,12 +644,14 @@ static unsigned long change_prot_numa(struct vm_area_struct *vma, #endif /* CONFIG_ARCH_USES_NUMA_PROT_NONE */ /* - * Check if all pages in a range are on a set of nodes. - * If pagelist != NULL then isolate pages from the LRU and - * put them on the pagelist. + * Walk through page tables and collect pages to be migrated. + * + * If pages found in a given range are on a set of nodes (determined by + * @nodes and @flags,) it's isolated and queued to the pagelist which is + * passed via @private.) */ static struct vm_area_struct * -check_range(struct mm_struct *mm, unsigned long start, unsigned long end, +queue_pages_range(struct mm_struct *mm, unsigned long start, unsigned long end, const nodemask_t *nodes, unsigned long flags, void *private) { int err; @@ -635,9 +677,6 @@ check_range(struct mm_struct *mm, unsigned long start, unsigned long end, return ERR_PTR(-EFAULT); } - if (is_vm_hugetlb_page(vma)) - goto next; - if (flags & MPOL_MF_LAZY) { change_prot_numa(vma, start, endvma); goto next; @@ -647,7 +686,7 @@ check_range(struct mm_struct *mm, unsigned long start, unsigned long end, ((flags & (MPOL_MF_MOVE | MPOL_MF_MOVE_ALL)) && vma_migratable(vma))) { - err = check_pgd_range(vma, start, endvma, nodes, + err = queue_pages_pgd_range(vma, start, endvma, nodes, flags, private); if (err) { first = ERR_PTR(err); @@ -990,7 +1029,11 @@ static void migrate_page_add(struct page *page, struct list_head *pagelist, static struct page *new_node_page(struct page *page, unsigned long node, int **x) { - return alloc_pages_exact_node(node, GFP_HIGHUSER_MOVABLE, 0); + if (PageHuge(page)) + return alloc_huge_page_node(page_hstate(compound_head(page)), + node); + else + return alloc_pages_exact_node(node, GFP_HIGHUSER_MOVABLE, 0); } /* @@ -1013,14 +1056,14 @@ static int migrate_to_node(struct mm_struct *mm, int source, int dest, * space range and MPOL_MF_DISCONTIG_OK, this call can not fail. */ VM_BUG_ON(!(flags & (MPOL_MF_MOVE | MPOL_MF_MOVE_ALL))); - check_range(mm, mm->mmap->vm_start, mm->task_size, &nmask, + queue_pages_range(mm, mm->mmap->vm_start, mm->task_size, &nmask, flags | MPOL_MF_DISCONTIG_OK, &pagelist); if (!list_empty(&pagelist)) { err = migrate_pages(&pagelist, new_node_page, dest, MIGRATE_SYNC, MR_SYSCALL); if (err) - putback_lru_pages(&pagelist); + putback_movable_pages(&pagelist); } return err; @@ -1083,7 +1126,7 @@ int do_migrate_pages(struct mm_struct *mm, const nodemask_t *from, tmp = *from; while (!nodes_empty(tmp)) { int s,d; - int source = -1; + int source = NUMA_NO_NODE; int dest = 0; for_each_node_mask(s, tmp) { @@ -1118,7 +1161,7 @@ int do_migrate_pages(struct mm_struct *mm, const nodemask_t *from, if (!node_isset(dest, tmp)) break; } - if (source == -1) + if (source == NUMA_NO_NODE) break; node_clear(source, tmp); @@ -1154,10 +1197,14 @@ static struct page *new_vma_page(struct page *page, unsigned long private, int * break; vma = vma->vm_next; } - /* - * if !vma, alloc_page_vma() will use task or system default policy + * queue_pages_range() confirms that @page belongs to some vma, + * so vma shouldn't be NULL. */ + BUG_ON(!vma); + + if (PageHuge(page)) + return alloc_huge_page_noerr(vma, address, 1); return alloc_page_vma(GFP_HIGHUSER_MOVABLE, vma, address); } #else @@ -1249,7 +1296,7 @@ static long do_mbind(unsigned long start, unsigned long len, if (err) goto mpol_out; - vma = check_range(mm, start, end, nmask, + vma = queue_pages_range(mm, start, end, nmask, flags | MPOL_MF_INVERT, &pagelist); err = PTR_ERR(vma); /* maybe ... */ @@ -1265,7 +1312,7 @@ static long do_mbind(unsigned long start, unsigned long len, (unsigned long)vma, MIGRATE_SYNC, MR_MEMPOLICY_MBIND); if (nr_failed) - putback_lru_pages(&pagelist); + putback_movable_pages(&pagelist); } if (nr_failed && (flags & MPOL_MF_STRICT)) @@ -1633,6 +1680,30 @@ struct mempolicy *get_vma_policy(struct task_struct *task, return pol; } +bool vma_policy_mof(struct task_struct *task, struct vm_area_struct *vma) +{ + struct mempolicy *pol = get_task_policy(task); + if (vma) { + if (vma->vm_ops && vma->vm_ops->get_policy) { + bool ret = false; + + pol = vma->vm_ops->get_policy(vma, vma->vm_start); + if (pol && (pol->flags & MPOL_F_MOF)) + ret = true; + mpol_cond_put(pol); + + return ret; + } else if (vma->vm_policy) { + pol = vma->vm_policy; + } + } + + if (!pol) + return default_policy.flags & MPOL_F_MOF; + + return pol->flags & MPOL_F_MOF; +} + static int apply_policy_zone(struct mempolicy *policy, enum zone_type zone) { enum zone_type dynamic_policy_zone = policy_zone; @@ -1765,7 +1836,7 @@ static unsigned offset_il_node(struct mempolicy *pol, unsigned nnodes = nodes_weight(pol->v.nodes); unsigned target; int c; - int nid = -1; + int nid = NUMA_NO_NODE; if (!nnodes) return numa_node_id(); @@ -1802,11 +1873,11 @@ static inline unsigned interleave_nid(struct mempolicy *pol, /* * Return the bit number of a random bit set in the nodemask. - * (returns -1 if nodemask is empty) + * (returns NUMA_NO_NODE if nodemask is empty) */ int node_random(const nodemask_t *maskp) { - int w, bit = -1; + int w, bit = NUMA_NO_NODE; w = nodes_weight(*maskp); if (w) @@ -2065,6 +2136,16 @@ retry_cpuset: } EXPORT_SYMBOL(alloc_pages_current); +int vma_dup_policy(struct vm_area_struct *src, struct vm_area_struct *dst) +{ + struct mempolicy *pol = mpol_dup(vma_policy(src)); + + if (IS_ERR(pol)) + return PTR_ERR(pol); + dst->vm_policy = pol; + return 0; +} + /* * If mpol_dup() sees current->cpuset == cpuset_being_rebound, then it * rebinds the mempolicy its copying by calling mpol_rebind_policy() @@ -2221,6 +2302,35 @@ static void sp_free(struct sp_node *n) kmem_cache_free(sn_cache, n); } +#ifdef CONFIG_NUMA_BALANCING +static bool numa_migrate_deferred(struct task_struct *p, int last_cpupid) +{ + /* Never defer a private fault */ + if (cpupid_match_pid(p, last_cpupid)) + return false; + + if (p->numa_migrate_deferred) { + p->numa_migrate_deferred--; + return true; + } + return false; +} + +static inline void defer_numa_migrate(struct task_struct *p) +{ + p->numa_migrate_deferred = sysctl_numa_balancing_migrate_deferred; +} +#else +static inline bool numa_migrate_deferred(struct task_struct *p, int last_cpupid) +{ + return false; +} + +static inline void defer_numa_migrate(struct task_struct *p) +{ +} +#endif /* CONFIG_NUMA_BALANCING */ + /** * mpol_misplaced - check whether current page node is valid in policy * @@ -2244,6 +2354,8 @@ int mpol_misplaced(struct page *page, struct vm_area_struct *vma, unsigned long struct zone *zone; int curnid = page_to_nid(page); unsigned long pgoff; + int thiscpu = raw_smp_processor_id(); + int thisnid = cpu_to_node(thiscpu); int polnid = -1; int ret = -1; @@ -2292,9 +2404,11 @@ int mpol_misplaced(struct page *page, struct vm_area_struct *vma, unsigned long /* Migrate the page towards the node whose CPU is referencing it */ if (pol->flags & MPOL_F_MORON) { - int last_nid; + int last_cpupid; + int this_cpupid; - polnid = numa_node_id(); + polnid = thisnid; + this_cpupid = cpu_pid_to_cpupid(thiscpu, current->pid); /* * Multi-stage node selection is used in conjunction @@ -2317,8 +2431,25 @@ int mpol_misplaced(struct page *page, struct vm_area_struct *vma, unsigned long * it less likely we act on an unlikely task<->page * relation. */ - last_nid = page_nid_xchg_last(page, polnid); - if (last_nid != polnid) + last_cpupid = page_cpupid_xchg_last(page, this_cpupid); + if (!cpupid_pid_unset(last_cpupid) && cpupid_to_nid(last_cpupid) != thisnid) { + + /* See sysctl_numa_balancing_migrate_deferred comment */ + if (!cpupid_match_pid(current, last_cpupid)) + defer_numa_migrate(current); + + goto out; + } + + /* + * The quadratic filter above reduces extraneous migration + * of shared pages somewhat. This code reduces it even more, + * reducing the overhead of page migrations of shared pages. + * This makes workloads with shared pages rely more on + * "move task near its memory", and less on "move memory + * towards its task", which is exactly what we want. + */ + if (numa_migrate_deferred(current, last_cpupid)) goto out; } @@ -2784,62 +2915,45 @@ out: * @maxlen: length of @buffer * @pol: pointer to mempolicy to be formatted * - * Convert a mempolicy into a string. - * Returns the number of characters in buffer (if positive) - * or an error (negative) + * Convert @pol into a string. If @buffer is too short, truncate the string. + * Recommend a @maxlen of at least 32 for the longest mode, "interleave", the + * longest flag, "relative", and to display at least a few node ids. */ -int mpol_to_str(char *buffer, int maxlen, struct mempolicy *pol) +void mpol_to_str(char *buffer, int maxlen, struct mempolicy *pol) { char *p = buffer; - int l; - nodemask_t nodes; - unsigned short mode; - unsigned short flags = pol ? pol->flags : 0; - - /* - * Sanity check: room for longest mode, flag and some nodes - */ - VM_BUG_ON(maxlen < strlen("interleave") + strlen("relative") + 16); + nodemask_t nodes = NODE_MASK_NONE; + unsigned short mode = MPOL_DEFAULT; + unsigned short flags = 0; - if (!pol || pol == &default_policy) - mode = MPOL_DEFAULT; - else + if (pol && pol != &default_policy) { mode = pol->mode; + flags = pol->flags; + } switch (mode) { case MPOL_DEFAULT: - nodes_clear(nodes); break; - case MPOL_PREFERRED: - nodes_clear(nodes); if (flags & MPOL_F_LOCAL) mode = MPOL_LOCAL; else node_set(pol->v.preferred_node, nodes); break; - case MPOL_BIND: - /* Fall through */ case MPOL_INTERLEAVE: nodes = pol->v.nodes; break; - default: - return -EINVAL; + WARN_ON_ONCE(1); + snprintf(p, maxlen, "unknown"); + return; } - l = strlen(policy_modes[mode]); - if (buffer + maxlen < p + l + 1) - return -ENOSPC; - - strcpy(p, policy_modes[mode]); - p += l; + p += snprintf(p, maxlen, policy_modes[mode]); if (flags & MPOL_MODE_FLAGS) { - if (buffer + maxlen < p + 2) - return -ENOSPC; - *p++ = '='; + p += snprintf(p, buffer + maxlen - p, "="); /* * Currently, the only defined flags are mutually exclusive @@ -2851,10 +2965,7 @@ int mpol_to_str(char *buffer, int maxlen, struct mempolicy *pol) } if (!nodes_empty(nodes)) { - if (buffer + maxlen < p + 2) - return -ENOSPC; - *p++ = ':'; + p += snprintf(p, buffer + maxlen - p, ":"); p += nodelist_scnprintf(p, buffer + maxlen - p, nodes); } - return p - buffer; } diff --git a/mm/mempool.c b/mm/mempool.c index 54990476c049..659aa42bad16 100644 --- a/mm/mempool.c +++ b/mm/mempool.c @@ -73,7 +73,7 @@ mempool_t *mempool_create_node(int min_nr, mempool_alloc_t *alloc_fn, gfp_t gfp_mask, int node_id) { mempool_t *pool; - pool = kmalloc_node(sizeof(*pool), gfp_mask | __GFP_ZERO, node_id); + pool = kzalloc_node(sizeof(*pool), gfp_mask, node_id); if (!pool) return NULL; pool->elements = kmalloc_node(min_nr * sizeof(void *), diff --git a/mm/migrate.c b/mm/migrate.c index 6f0c24438bba..316e720a2023 100644 --- a/mm/migrate.c +++ b/mm/migrate.c @@ -100,10 +100,14 @@ void putback_movable_pages(struct list_head *l) struct page *page2; list_for_each_entry_safe(page, page2, l, lru) { + if (unlikely(PageHuge(page))) { + putback_active_hugepage(page); + continue; + } list_del(&page->lru); dec_zone_page_state(page, NR_ISOLATED_ANON + page_is_file_cache(page)); - if (unlikely(balloon_page_movable(page))) + if (unlikely(isolated_balloon_page(page))) balloon_page_putback(page); else putback_lru_page(page); @@ -126,7 +130,7 @@ static int remove_migration_pte(struct page *new, struct vm_area_struct *vma, ptep = huge_pte_offset(mm, addr); if (!ptep) goto out; - ptl = &mm->page_table_lock; + ptl = huge_pte_lockptr(hstate_vma(vma), mm, ptep); } else { pmd = mm_find_pmd(mm, addr); if (!pmd) @@ -157,6 +161,8 @@ static int remove_migration_pte(struct page *new, struct vm_area_struct *vma, get_page(new); pte = pte_mkold(mk_pte(new, vma->vm_page_prot)); + if (pte_swp_soft_dirty(*ptep)) + pte = pte_mksoft_dirty(pte); if (is_write_migration_entry(entry)) pte = pte_mkwrite(pte); #ifdef CONFIG_HUGETLB_PAGE @@ -243,9 +249,10 @@ void migration_entry_wait(struct mm_struct *mm, pmd_t *pmd, __migration_entry_wait(mm, ptep, ptl); } -void migration_entry_wait_huge(struct mm_struct *mm, pte_t *pte) +void migration_entry_wait_huge(struct vm_area_struct *vma, + struct mm_struct *mm, pte_t *pte) { - spinlock_t *ptl = &(mm)->page_table_lock; + spinlock_t *ptl = huge_pte_lockptr(hstate_vma(vma), mm, pte); __migration_entry_wait(mm, pte, ptl); } @@ -307,7 +314,7 @@ static inline bool buffer_migrate_lock_buffers(struct buffer_head *head, * 2 for pages with a mapping * 3 for pages with a mapping and PagePrivate/PagePrivate2 set. */ -static int migrate_page_move_mapping(struct address_space *mapping, +int migrate_page_move_mapping(struct address_space *mapping, struct page *newpage, struct page *page, struct buffer_head *head, enum migrate_mode mode) { @@ -439,6 +446,8 @@ int migrate_huge_page_move_mapping(struct address_space *mapping, */ void migrate_page_copy(struct page *newpage, struct page *page) { + int cpupid; + if (PageHuge(page) || PageTransHuge(page)) copy_huge_page(newpage, page); else @@ -475,6 +484,13 @@ void migrate_page_copy(struct page *newpage, struct page *page) __set_page_dirty_nobuffers(newpage); } + /* + * Copy NUMA information to the new page, to prevent over-eager + * future migrations of this same page. + */ + cpupid = page_cpupid_xchg_last(page, -1); + page_cpupid_xchg_last(newpage, cpupid); + mlock_migrate_page(newpage, page); ksm_migrate_page(newpage, page); /* @@ -945,6 +961,16 @@ static int unmap_and_move_huge_page(new_page_t get_new_page, struct page *new_hpage = get_new_page(hpage, private, &result); struct anon_vma *anon_vma = NULL; + /* + * Movability of hugepages depends on architectures and hugepage size. + * This check is necessary because some callers of hugepage migration + * like soft offline and memory hotremove don't walk through page + * tables or check whether the hugepage is pmd-based or not before + * kicking migration. + */ + if (!hugepage_migration_support(page_hstate(hpage))) + return -ENOSYS; + if (!new_hpage) return -ENOMEM; @@ -975,6 +1001,8 @@ static int unmap_and_move_huge_page(new_page_t get_new_page, unlock_page(hpage); out: + if (rc != -EAGAIN) + putback_active_hugepage(hpage); put_page(new_hpage); if (result) { if (rc) @@ -1025,7 +1053,11 @@ int migrate_pages(struct list_head *from, new_page_t get_new_page, list_for_each_entry_safe(page, page2, from, lru) { cond_resched(); - rc = unmap_and_move(get_new_page, private, + if (PageHuge(page)) + rc = unmap_and_move_huge_page(get_new_page, + private, page, pass > 2, mode); + else + rc = unmap_and_move(get_new_page, private, page, pass > 2, mode); switch(rc) { @@ -1058,32 +1090,6 @@ out: return rc; } -int migrate_huge_page(struct page *hpage, new_page_t get_new_page, - unsigned long private, enum migrate_mode mode) -{ - int pass, rc; - - for (pass = 0; pass < 10; pass++) { - rc = unmap_and_move_huge_page(get_new_page, private, - hpage, pass > 2, mode); - switch (rc) { - case -ENOMEM: - goto out; - case -EAGAIN: - /* try again */ - cond_resched(); - break; - case MIGRATEPAGE_SUCCESS: - goto out; - default: - rc = -EIO; - goto out; - } - } -out: - return rc; -} - #ifdef CONFIG_NUMA /* * Move a list of individual pages @@ -1108,7 +1114,11 @@ static struct page *new_page_node(struct page *p, unsigned long private, *result = &pm->status; - return alloc_pages_exact_node(pm->node, + if (PageHuge(p)) + return alloc_huge_page_node(page_hstate(compound_head(p)), + pm->node); + else + return alloc_pages_exact_node(pm->node, GFP_HIGHUSER_MOVABLE | GFP_THISNODE, 0); } @@ -1168,6 +1178,11 @@ static int do_move_page_to_node_array(struct mm_struct *mm, !migrate_all) goto put_and_set; + if (PageHuge(page)) { + isolate_huge_page(page, &pagelist); + goto put_and_set; + } + err = isolate_lru_page(page); if (!err) { list_add_tail(&page->lru, &pagelist); @@ -1190,7 +1205,7 @@ set_status: err = migrate_pages(&pagelist, new_page_node, (unsigned long)pm, MIGRATE_SYNC, MR_SYSCALL); if (err) - putback_lru_pages(&pagelist); + putback_movable_pages(&pagelist); } up_read(&mm->mmap_sem); @@ -1468,7 +1483,7 @@ static bool migrate_balanced_pgdat(struct pglist_data *pgdat, if (!populated_zone(zone)) continue; - if (zone->all_unreclaimable) + if (!zone_reclaimable(zone)) continue; /* Avoid waking kswapd by allocating pages_to_migrate pages. */ @@ -1495,7 +1510,7 @@ static struct page *alloc_misplaced_dst_page(struct page *page, __GFP_NOWARN) & ~GFP_IOFS, 0); if (newpage) - page_nid_xchg_last(newpage, page_nid_last(page)); + page_cpupid_xchg_last(newpage, page_cpupid_last(page)); return newpage; } @@ -1596,7 +1611,8 @@ int numamigrate_isolate_page(pg_data_t *pgdat, struct page *page) * node. Caller is expected to have an elevated reference count on * the page that will be dropped by this function before returning. */ -int migrate_misplaced_page(struct page *page, int node) +int migrate_misplaced_page(struct page *page, struct vm_area_struct *vma, + int node) { pg_data_t *pgdat = NODE_DATA(node); int isolated; @@ -1604,10 +1620,11 @@ int migrate_misplaced_page(struct page *page, int node) LIST_HEAD(migratepages); /* - * Don't migrate pages that are mapped in multiple processes. - * TODO: Handle false sharing detection instead of this hammer + * Don't migrate file pages that are mapped in multiple processes + * with execute permissions as they are probably shared libraries. */ - if (page_mapcount(page) != 1) + if (page_mapcount(page) != 1 && page_is_file_cache(page) && + (vma->vm_flags & VM_EXEC)) goto out; /* @@ -1650,6 +1667,7 @@ int migrate_misplaced_transhuge_page(struct mm_struct *mm, unsigned long address, struct page *page, int node) { + spinlock_t *ptl; unsigned long haddr = address & HPAGE_PMD_MASK; pg_data_t *pgdat = NODE_DATA(node); int isolated = 0; @@ -1658,13 +1676,6 @@ int migrate_misplaced_transhuge_page(struct mm_struct *mm, int page_lru = page_is_file_cache(page); /* - * Don't migrate pages that are mapped in multiple processes. - * TODO: Handle false sharing detection instead of this hammer - */ - if (page_mapcount(page) != 1) - goto out_dropref; - - /* * Rate-limit the amount of data that is being migrated to a node. * Optimal placement is no good if the memory bus is saturated and * all the time is being spent migrating! @@ -1677,7 +1688,7 @@ int migrate_misplaced_transhuge_page(struct mm_struct *mm, if (!new_page) goto out_fail; - page_nid_xchg_last(new_page, page_nid_last(page)); + page_cpupid_xchg_last(new_page, page_cpupid_last(page)); isolated = numamigrate_isolate_page(pgdat, page); if (!isolated) { @@ -1696,9 +1707,9 @@ int migrate_misplaced_transhuge_page(struct mm_struct *mm, WARN_ON(PageLRU(new_page)); /* Recheck the target PMD */ - spin_lock(&mm->page_table_lock); + ptl = pmd_lock(mm, pmd); if (unlikely(!pmd_same(*pmd, entry))) { - spin_unlock(&mm->page_table_lock); + spin_unlock(ptl); /* Reverse changes made by migrate_page_copy() */ if (TestClearPageActive(new_page)) @@ -1710,12 +1721,12 @@ int migrate_misplaced_transhuge_page(struct mm_struct *mm, unlock_page(new_page); put_page(new_page); /* Free it */ - unlock_page(page); + /* Retake the callers reference and putback on LRU */ + get_page(page); putback_lru_page(page); - - count_vm_events(PGMIGRATE_FAIL, HPAGE_PMD_NR); - isolated = 0; - goto out; + mod_zone_page_state(page_zone(page), + NR_ISOLATED_ANON + page_lru, -HPAGE_PMD_NR); + goto out_fail; } /* @@ -1732,9 +1743,9 @@ int migrate_misplaced_transhuge_page(struct mm_struct *mm, entry = maybe_pmd_mkwrite(pmd_mkdirty(entry), vma); entry = pmd_mkhuge(entry); - page_add_new_anon_rmap(new_page, vma, haddr); - + pmdp_clear_flush(vma, haddr, pmd); set_pmd_at(mm, haddr, pmd, entry); + page_add_new_anon_rmap(new_page, vma, haddr); update_mmu_cache_pmd(vma, address, &entry); page_remove_rmap(page); /* @@ -1743,7 +1754,7 @@ int migrate_misplaced_transhuge_page(struct mm_struct *mm, * before it's fully transferred to the new page. */ mem_cgroup_end_migration(memcg, page, new_page, true); - spin_unlock(&mm->page_table_lock); + spin_unlock(ptl); unlock_page(new_page); unlock_page(page); @@ -1753,7 +1764,6 @@ int migrate_misplaced_transhuge_page(struct mm_struct *mm, count_vm_events(PGMIGRATE_SUCCESS, HPAGE_PMD_NR); count_vm_numa_events(NUMA_PAGE_MIGRATE, HPAGE_PMD_NR); -out: mod_zone_page_state(page_zone(page), NR_ISOLATED_ANON + page_lru, -HPAGE_PMD_NR); @@ -1762,6 +1772,10 @@ out: out_fail: count_vm_events(PGMIGRATE_FAIL, HPAGE_PMD_NR); out_dropref: + entry = pmd_mknonnuma(entry); + set_pmd_at(mm, haddr, pmd, entry); + update_mmu_cache_pmd(vma, address, &entry); + unlock_page(page); put_page(page); return 0; diff --git a/mm/mlock.c b/mm/mlock.c index 79b7cf7d1bca..d480cd6fc475 100644 --- a/mm/mlock.c +++ b/mm/mlock.c @@ -11,6 +11,7 @@ #include <linux/swap.h> #include <linux/swapops.h> #include <linux/pagemap.h> +#include <linux/pagevec.h> #include <linux/mempolicy.h> #include <linux/syscalls.h> #include <linux/sched.h> @@ -18,6 +19,8 @@ #include <linux/rmap.h> #include <linux/mmzone.h> #include <linux/hugetlb.h> +#include <linux/memcontrol.h> +#include <linux/mm_inline.h> #include "internal.h" @@ -87,6 +90,47 @@ void mlock_vma_page(struct page *page) } } +/* + * Finish munlock after successful page isolation + * + * Page must be locked. This is a wrapper for try_to_munlock() + * and putback_lru_page() with munlock accounting. + */ +static void __munlock_isolated_page(struct page *page) +{ + int ret = SWAP_AGAIN; + + /* + * Optimization: if the page was mapped just once, that's our mapping + * and we don't need to check all the other vmas. + */ + if (page_mapcount(page) > 1) + ret = try_to_munlock(page); + + /* Did try_to_unlock() succeed or punt? */ + if (ret != SWAP_MLOCK) + count_vm_event(UNEVICTABLE_PGMUNLOCKED); + + putback_lru_page(page); +} + +/* + * Accounting for page isolation fail during munlock + * + * Performs accounting when page isolation fails in munlock. There is nothing + * else to do because it means some other task has already removed the page + * from the LRU. putback_lru_page() will take care of removing the page from + * the unevictable list, if necessary. vmscan [page_referenced()] will move + * the page back to the unevictable list if some other vma has it mlocked. + */ +static void __munlock_isolation_failed(struct page *page) +{ + if (PageUnevictable(page)) + count_vm_event(UNEVICTABLE_PGSTRANDED); + else + count_vm_event(UNEVICTABLE_PGMUNLOCKED); +} + /** * munlock_vma_page - munlock a vma page * @page - page to be unlocked @@ -112,37 +156,10 @@ unsigned int munlock_vma_page(struct page *page) unsigned int nr_pages = hpage_nr_pages(page); mod_zone_page_state(page_zone(page), NR_MLOCK, -nr_pages); page_mask = nr_pages - 1; - if (!isolate_lru_page(page)) { - int ret = SWAP_AGAIN; - - /* - * Optimization: if the page was mapped just once, - * that's our mapping and we don't need to check all the - * other vmas. - */ - if (page_mapcount(page) > 1) - ret = try_to_munlock(page); - /* - * did try_to_unlock() succeed or punt? - */ - if (ret != SWAP_MLOCK) - count_vm_event(UNEVICTABLE_PGMUNLOCKED); - - putback_lru_page(page); - } else { - /* - * Some other task has removed the page from the LRU. - * putback_lru_page() will take care of removing the - * page from the unevictable list, if necessary. - * vmscan [page_referenced()] will move the page back - * to the unevictable list if some other vma has it - * mlocked. - */ - if (PageUnevictable(page)) - count_vm_event(UNEVICTABLE_PGSTRANDED); - else - count_vm_event(UNEVICTABLE_PGMUNLOCKED); - } + if (!isolate_lru_page(page)) + __munlock_isolated_page(page); + else + __munlock_isolation_failed(page); } return page_mask; @@ -210,6 +227,195 @@ static int __mlock_posix_error_return(long retval) } /* + * Prepare page for fast batched LRU putback via putback_lru_evictable_pagevec() + * + * The fast path is available only for evictable pages with single mapping. + * Then we can bypass the per-cpu pvec and get better performance. + * when mapcount > 1 we need try_to_munlock() which can fail. + * when !page_evictable(), we need the full redo logic of putback_lru_page to + * avoid leaving evictable page in unevictable list. + * + * In case of success, @page is added to @pvec and @pgrescued is incremented + * in case that the page was previously unevictable. @page is also unlocked. + */ +static bool __putback_lru_fast_prepare(struct page *page, struct pagevec *pvec, + int *pgrescued) +{ + VM_BUG_ON(PageLRU(page)); + VM_BUG_ON(!PageLocked(page)); + + if (page_mapcount(page) <= 1 && page_evictable(page)) { + pagevec_add(pvec, page); + if (TestClearPageUnevictable(page)) + (*pgrescued)++; + unlock_page(page); + return true; + } + + return false; +} + +/* + * Putback multiple evictable pages to the LRU + * + * Batched putback of evictable pages that bypasses the per-cpu pvec. Some of + * the pages might have meanwhile become unevictable but that is OK. + */ +static void __putback_lru_fast(struct pagevec *pvec, int pgrescued) +{ + count_vm_events(UNEVICTABLE_PGMUNLOCKED, pagevec_count(pvec)); + /* + *__pagevec_lru_add() calls release_pages() so we don't call + * put_page() explicitly + */ + __pagevec_lru_add(pvec); + count_vm_events(UNEVICTABLE_PGRESCUED, pgrescued); +} + +/* + * Munlock a batch of pages from the same zone + * + * The work is split to two main phases. First phase clears the Mlocked flag + * and attempts to isolate the pages, all under a single zone lru lock. + * The second phase finishes the munlock only for pages where isolation + * succeeded. + * + * Note that the pagevec may be modified during the process. + */ +static void __munlock_pagevec(struct pagevec *pvec, struct zone *zone) +{ + int i; + int nr = pagevec_count(pvec); + int delta_munlocked = -nr; + struct pagevec pvec_putback; + int pgrescued = 0; + + /* Phase 1: page isolation */ + spin_lock_irq(&zone->lru_lock); + for (i = 0; i < nr; i++) { + struct page *page = pvec->pages[i]; + + if (TestClearPageMlocked(page)) { + struct lruvec *lruvec; + int lru; + + if (PageLRU(page)) { + lruvec = mem_cgroup_page_lruvec(page, zone); + lru = page_lru(page); + /* + * We already have pin from follow_page_mask() + * so we can spare the get_page() here. + */ + ClearPageLRU(page); + del_page_from_lru_list(page, lruvec, lru); + } else { + __munlock_isolation_failed(page); + goto skip_munlock; + } + + } else { +skip_munlock: + /* + * We won't be munlocking this page in the next phase + * but we still need to release the follow_page_mask() + * pin. + */ + pvec->pages[i] = NULL; + put_page(page); + delta_munlocked++; + } + } + __mod_zone_page_state(zone, NR_MLOCK, delta_munlocked); + spin_unlock_irq(&zone->lru_lock); + + /* Phase 2: page munlock */ + pagevec_init(&pvec_putback, 0); + for (i = 0; i < nr; i++) { + struct page *page = pvec->pages[i]; + + if (page) { + lock_page(page); + if (!__putback_lru_fast_prepare(page, &pvec_putback, + &pgrescued)) { + /* + * Slow path. We don't want to lose the last + * pin before unlock_page() + */ + get_page(page); /* for putback_lru_page() */ + __munlock_isolated_page(page); + unlock_page(page); + put_page(page); /* from follow_page_mask() */ + } + } + } + + /* + * Phase 3: page putback for pages that qualified for the fast path + * This will also call put_page() to return pin from follow_page_mask() + */ + if (pagevec_count(&pvec_putback)) + __putback_lru_fast(&pvec_putback, pgrescued); +} + +/* + * Fill up pagevec for __munlock_pagevec using pte walk + * + * The function expects that the struct page corresponding to @start address is + * a non-TPH page already pinned and in the @pvec, and that it belongs to @zone. + * + * The rest of @pvec is filled by subsequent pages within the same pmd and same + * zone, as long as the pte's are present and vm_normal_page() succeeds. These + * pages also get pinned. + * + * Returns the address of the next page that should be scanned. This equals + * @start + PAGE_SIZE when no page could be added by the pte walk. + */ +static unsigned long __munlock_pagevec_fill(struct pagevec *pvec, + struct vm_area_struct *vma, int zoneid, unsigned long start, + unsigned long end) +{ + pte_t *pte; + spinlock_t *ptl; + + /* + * Initialize pte walk starting at the already pinned page where we + * are sure that there is a pte, as it was pinned under the same + * mmap_sem write op. + */ + pte = get_locked_pte(vma->vm_mm, start, &ptl); + /* Make sure we do not cross the page table boundary */ + end = pgd_addr_end(start, end); + end = pud_addr_end(start, end); + end = pmd_addr_end(start, end); + + /* The page next to the pinned page is the first we will try to get */ + start += PAGE_SIZE; + while (start < end) { + struct page *page = NULL; + pte++; + if (pte_present(*pte)) + page = vm_normal_page(vma, start, *pte); + /* + * Break if page could not be obtained or the page's node+zone does not + * match + */ + if (!page || page_zone_id(page) != zoneid) + break; + + get_page(page); + /* + * Increase the address that will be returned *before* the + * eventual break due to pvec becoming full by adding the page + */ + start += PAGE_SIZE; + if (pagevec_add(pvec, page) == 0) + break; + } + pte_unmap_unlock(pte, ptl); + return start; +} + +/* * munlock_vma_pages_range() - munlock all pages in the vma range.' * @vma - vma containing range to be munlock()ed. * @start - start address in @vma of the range @@ -233,9 +439,13 @@ void munlock_vma_pages_range(struct vm_area_struct *vma, vma->vm_flags &= ~VM_LOCKED; while (start < end) { - struct page *page; + struct page *page = NULL; unsigned int page_mask, page_increm; + struct pagevec pvec; + struct zone *zone; + int zoneid; + pagevec_init(&pvec, 0); /* * Although FOLL_DUMP is intended for get_dump_page(), * it just so happens that its special treatment of the @@ -244,21 +454,45 @@ void munlock_vma_pages_range(struct vm_area_struct *vma, * has sneaked into the range, we won't oops here: great). */ page = follow_page_mask(vma, start, FOLL_GET | FOLL_DUMP, - &page_mask); + &page_mask); + if (page && !IS_ERR(page)) { - lock_page(page); - lru_add_drain(); - /* - * Any THP page found by follow_page_mask() may have - * gotten split before reaching munlock_vma_page(), - * so we need to recompute the page_mask here. - */ - page_mask = munlock_vma_page(page); - unlock_page(page); - put_page(page); + if (PageTransHuge(page)) { + lock_page(page); + /* + * Any THP page found by follow_page_mask() may + * have gotten split before reaching + * munlock_vma_page(), so we need to recompute + * the page_mask here. + */ + page_mask = munlock_vma_page(page); + unlock_page(page); + put_page(page); /* follow_page_mask() */ + } else { + /* + * Non-huge pages are handled in batches via + * pagevec. The pin from follow_page_mask() + * prevents them from collapsing by THP. + */ + pagevec_add(&pvec, page); + zone = page_zone(page); + zoneid = page_zone_id(page); + + /* + * Try to fill the rest of pagevec using fast + * pte walk. This will also update start to + * the next page to process. Then munlock the + * pagevec. + */ + start = __munlock_pagevec_fill(&pvec, vma, + zoneid, start, end); + __munlock_pagevec(&pvec, zone); + goto next; + } } page_increm = 1 + (~(start >> PAGE_SHIFT) & page_mask); start += page_increm * PAGE_SIZE; +next: cond_resched(); } } @@ -506,6 +740,7 @@ static int do_mlockall(int flags) /* Ignore errors */ mlock_fixup(vma, &prev, vma->vm_start, vma->vm_end, newflags); + cond_resched(); } out: return 0; diff --git a/mm/mm_init.c b/mm/mm_init.c index 633c08863fd8..68562e92d50c 100644 --- a/mm/mm_init.c +++ b/mm/mm_init.c @@ -71,26 +71,26 @@ void __init mminit_verify_pageflags_layout(void) unsigned long or_mask, add_mask; shift = 8 * sizeof(unsigned long); - width = shift - SECTIONS_WIDTH - NODES_WIDTH - ZONES_WIDTH - LAST_NID_SHIFT; + width = shift - SECTIONS_WIDTH - NODES_WIDTH - ZONES_WIDTH - LAST_CPUPID_SHIFT; mminit_dprintk(MMINIT_TRACE, "pageflags_layout_widths", - "Section %d Node %d Zone %d Lastnid %d Flags %d\n", + "Section %d Node %d Zone %d Lastcpupid %d Flags %d\n", SECTIONS_WIDTH, NODES_WIDTH, ZONES_WIDTH, - LAST_NID_WIDTH, + LAST_CPUPID_WIDTH, NR_PAGEFLAGS); mminit_dprintk(MMINIT_TRACE, "pageflags_layout_shifts", - "Section %d Node %d Zone %d Lastnid %d\n", + "Section %d Node %d Zone %d Lastcpupid %d\n", SECTIONS_SHIFT, NODES_SHIFT, ZONES_SHIFT, - LAST_NID_SHIFT); + LAST_CPUPID_SHIFT); mminit_dprintk(MMINIT_TRACE, "pageflags_layout_pgshifts", - "Section %lu Node %lu Zone %lu Lastnid %lu\n", + "Section %lu Node %lu Zone %lu Lastcpupid %lu\n", (unsigned long)SECTIONS_PGSHIFT, (unsigned long)NODES_PGSHIFT, (unsigned long)ZONES_PGSHIFT, - (unsigned long)LAST_NID_PGSHIFT); + (unsigned long)LAST_CPUPID_PGSHIFT); mminit_dprintk(MMINIT_TRACE, "pageflags_layout_nodezoneid", "Node/Zone ID: %lu -> %lu\n", (unsigned long)(ZONEID_PGOFF + ZONEID_SHIFT), @@ -102,9 +102,9 @@ void __init mminit_verify_pageflags_layout(void) mminit_dprintk(MMINIT_TRACE, "pageflags_layout_nodeflags", "Node not in page flags"); #endif -#ifdef LAST_NID_NOT_IN_PAGE_FLAGS +#ifdef LAST_CPUPID_NOT_IN_PAGE_FLAGS mminit_dprintk(MMINIT_TRACE, "pageflags_layout_nodeflags", - "Last nid not in page flags"); + "Last cpupid not in page flags"); #endif if (SECTIONS_WIDTH) { diff --git a/mm/mmap.c b/mm/mmap.c index f9c97d10b873..834b2d785f1e 100644 --- a/mm/mmap.c +++ b/mm/mmap.c @@ -179,14 +179,12 @@ int __vm_enough_memory(struct mm_struct *mm, long pages, int cap_sys_admin) goto error; } - allowed = (totalram_pages - hugetlb_total_pages()) - * sysctl_overcommit_ratio / 100; + allowed = vm_commit_limit(); /* * Reserve some for root */ if (!cap_sys_admin) allowed -= sysctl_admin_reserve_kbytes >> (PAGE_SHIFT - 10); - allowed += total_swap_pages; /* * Don't let a single process grow so big a user can't recover @@ -1202,7 +1200,6 @@ unsigned long do_mmap_pgoff(struct file *file, unsigned long addr, unsigned long *populate) { struct mm_struct * mm = current->mm; - struct inode *inode; vm_flags_t vm_flags; *populate = 0; @@ -1265,9 +1262,9 @@ unsigned long do_mmap_pgoff(struct file *file, unsigned long addr, return -EAGAIN; } - inode = file ? file_inode(file) : NULL; - if (file) { + struct inode *inode = file_inode(file); + switch (flags & MAP_TYPE) { case MAP_SHARED: if ((prot&PROT_WRITE) && !(file->f_mode&FMODE_WRITE)) @@ -1300,8 +1297,10 @@ unsigned long do_mmap_pgoff(struct file *file, unsigned long addr, vm_flags &= ~VM_MAYEXEC; } - if (!file->f_op || !file->f_op->mmap) + if (!file->f_op->mmap) return -ENODEV; + if (vm_flags & (VM_GROWSDOWN|VM_GROWSUP)) + return -EINVAL; break; default: @@ -1310,6 +1309,8 @@ unsigned long do_mmap_pgoff(struct file *file, unsigned long addr, } else { switch (flags & MAP_TYPE) { case MAP_SHARED: + if (vm_flags & (VM_GROWSDOWN|VM_GROWSUP)) + return -EINVAL; /* * Ignore pgoff. */ @@ -1476,11 +1477,9 @@ unsigned long mmap_region(struct file *file, unsigned long addr, { struct mm_struct *mm = current->mm; struct vm_area_struct *vma, *prev; - int correct_wcount = 0; int error; struct rb_node **rb_link, *rb_parent; unsigned long charged = 0; - struct inode *inode = file ? file_inode(file) : NULL; /* Check against address space limit. */ if (!may_expand_vm(mm, len >> PAGE_SHIFT)) { @@ -1544,16 +1543,11 @@ munmap_back: vma->vm_pgoff = pgoff; INIT_LIST_HEAD(&vma->anon_vma_chain); - error = -EINVAL; /* when rejecting VM_GROWSDOWN|VM_GROWSUP */ - if (file) { - if (vm_flags & (VM_GROWSDOWN|VM_GROWSUP)) - goto free_vma; if (vm_flags & VM_DENYWRITE) { error = deny_write_access(file); if (error) goto free_vma; - correct_wcount = 1; } vma->vm_file = get_file(file); error = file->f_op->mmap(file, vma); @@ -1570,11 +1564,8 @@ munmap_back: WARN_ON_ONCE(addr != vma->vm_start); addr = vma->vm_start; - pgoff = vma->vm_pgoff; vm_flags = vma->vm_flags; } else if (vm_flags & VM_SHARED) { - if (unlikely(vm_flags & (VM_GROWSDOWN|VM_GROWSUP))) - goto free_vma; error = shmem_zero_setup(vma); if (error) goto free_vma; @@ -1596,11 +1587,10 @@ munmap_back: } vma_link(mm, vma, prev, rb_link, rb_parent); - file = vma->vm_file; - /* Once vma denies write, undo our temporary denial count */ - if (correct_wcount) - atomic_inc(&inode->i_writecount); + if (vm_flags & VM_DENYWRITE) + allow_write_access(file); + file = vma->vm_file; out: perf_event_mmap(vma); @@ -1616,11 +1606,20 @@ out: if (file) uprobe_mmap(vma); + /* + * New (or expanded) vma always get soft dirty status. + * Otherwise user-space soft-dirty page tracker won't + * be able to distinguish situation when vma area unmapped, + * then new mapped in-place (which must be aimed as + * a completely new data area). + */ + vma->vm_flags |= VM_SOFTDIRTY; + return addr; unmap_and_free_vma: - if (correct_wcount) - atomic_inc(&inode->i_writecount); + if (vm_flags & VM_DENYWRITE) + allow_write_access(file); vma->vm_file = NULL; fput(file); @@ -1855,7 +1854,7 @@ arch_get_unmapped_area(struct file *filp, unsigned long addr, struct vm_area_struct *vma; struct vm_unmapped_area_info info; - if (len > TASK_SIZE) + if (len > TASK_SIZE - mmap_min_addr) return -ENOMEM; if (flags & MAP_FIXED) @@ -1864,14 +1863,14 @@ arch_get_unmapped_area(struct file *filp, unsigned long addr, if (addr) { addr = PAGE_ALIGN(addr); vma = find_vma(mm, addr); - if (TASK_SIZE - len >= addr && + if (TASK_SIZE - len >= addr && addr >= mmap_min_addr && (!vma || addr + len <= vma->vm_start)) return addr; } info.flags = 0; info.length = len; - info.low_limit = TASK_UNMAPPED_BASE; + info.low_limit = mm->mmap_base; info.high_limit = TASK_SIZE; info.align_mask = 0; return vm_unmapped_area(&info); @@ -1894,7 +1893,7 @@ arch_get_unmapped_area_topdown(struct file *filp, const unsigned long addr0, struct vm_unmapped_area_info info; /* requested length too big for entire address space */ - if (len > TASK_SIZE) + if (len > TASK_SIZE - mmap_min_addr) return -ENOMEM; if (flags & MAP_FIXED) @@ -1904,14 +1903,14 @@ arch_get_unmapped_area_topdown(struct file *filp, const unsigned long addr0, if (addr) { addr = PAGE_ALIGN(addr); vma = find_vma(mm, addr); - if (TASK_SIZE - len >= addr && + if (TASK_SIZE - len >= addr && addr >= mmap_min_addr && (!vma || addr + len <= vma->vm_start)) return addr; } info.flags = VM_UNMAPPED_AREA_TOPDOWN; info.length = len; - info.low_limit = PAGE_SIZE; + info.low_limit = max(PAGE_SIZE, mmap_min_addr); info.high_limit = mm->mmap_base; info.align_mask = 0; addr = vm_unmapped_area(&info); @@ -1950,7 +1949,7 @@ get_unmapped_area(struct file *file, unsigned long addr, unsigned long len, return -ENOMEM; get_area = current->mm->get_unmapped_area; - if (file && file->f_op && file->f_op->get_unmapped_area) + if (file && file->f_op->get_unmapped_area) get_area = file->f_op->get_unmapped_area; addr = get_area(file, addr, len, pgoff, flags); if (IS_ERR_VALUE(addr)) @@ -2380,7 +2379,6 @@ detach_vmas_to_be_unmapped(struct mm_struct *mm, struct vm_area_struct *vma, static int __split_vma(struct mm_struct * mm, struct vm_area_struct * vma, unsigned long addr, int new_below) { - struct mempolicy *pol; struct vm_area_struct *new; int err = -ENOMEM; @@ -2404,12 +2402,9 @@ static int __split_vma(struct mm_struct * mm, struct vm_area_struct * vma, new->vm_pgoff += ((addr - vma->vm_start) >> PAGE_SHIFT); } - pol = mpol_dup(vma_policy(vma)); - if (IS_ERR(pol)) { - err = PTR_ERR(pol); + err = vma_dup_policy(vma, new); + if (err) goto out_free_vma; - } - vma_set_policy(new, pol); if (anon_vma_clone(new, vma)) goto out_free_mpol; @@ -2437,7 +2432,7 @@ static int __split_vma(struct mm_struct * mm, struct vm_area_struct * vma, fput(new->vm_file); unlink_anon_vmas(new); out_free_mpol: - mpol_put(pol); + mpol_put(vma_policy(new)); out_free_vma: kmem_cache_free(vm_area_cachep, new); out_err: @@ -2663,6 +2658,7 @@ out: mm->total_vm += len >> PAGE_SHIFT; if (flags & VM_LOCKED) mm->locked_vm += (len >> PAGE_SHIFT); + vma->vm_flags |= VM_SOFTDIRTY; return addr; } @@ -2728,7 +2724,8 @@ void exit_mmap(struct mm_struct *mm) } vm_unacct_memory(nr_accounted); - WARN_ON(mm->nr_ptes > (FIRST_USER_ADDRESS+PMD_SIZE-1)>>PMD_SHIFT); + WARN_ON(atomic_long_read(&mm->nr_ptes) > + (FIRST_USER_ADDRESS+PMD_SIZE-1)>>PMD_SHIFT); } /* Insert vm structure into process list sorted by address @@ -2780,7 +2777,6 @@ struct vm_area_struct *copy_vma(struct vm_area_struct **vmap, struct mm_struct *mm = vma->vm_mm; struct vm_area_struct *new_vma, *prev; struct rb_node **rb_link, *rb_parent; - struct mempolicy *pol; bool faulted_in_anon_vma = true; /* @@ -2825,10 +2821,8 @@ struct vm_area_struct *copy_vma(struct vm_area_struct **vmap, new_vma->vm_start = addr; new_vma->vm_end = addr + len; new_vma->vm_pgoff = pgoff; - pol = mpol_dup(vma_policy(vma)); - if (IS_ERR(pol)) + if (vma_dup_policy(vma, new_vma)) goto out_free_vma; - vma_set_policy(new_vma, pol); INIT_LIST_HEAD(&new_vma->anon_vma_chain); if (anon_vma_clone(new_vma, vma)) goto out_free_mempol; @@ -2843,7 +2837,7 @@ struct vm_area_struct *copy_vma(struct vm_area_struct **vmap, return new_vma; out_free_mempol: - mpol_put(pol); + mpol_put(vma_policy(new_vma)); out_free_vma: kmem_cache_free(vm_area_cachep, new_vma); return NULL; @@ -2930,7 +2924,7 @@ int install_special_mapping(struct mm_struct *mm, vma->vm_start = addr; vma->vm_end = addr + len; - vma->vm_flags = vm_flags | mm->def_flags | VM_DONTEXPAND; + vma->vm_flags = vm_flags | mm->def_flags | VM_DONTEXPAND | VM_SOFTDIRTY; vma->vm_page_prot = vm_get_page_prot(vma->vm_flags); vma->vm_ops = &special_mapping_vmops; diff --git a/mm/mmzone.c b/mm/mmzone.c index 2ac0afbd68f3..bf34fb8556db 100644 --- a/mm/mmzone.c +++ b/mm/mmzone.c @@ -97,20 +97,20 @@ void lruvec_init(struct lruvec *lruvec) INIT_LIST_HEAD(&lruvec->lists[lru]); } -#if defined(CONFIG_NUMA_BALANCING) && !defined(LAST_NID_NOT_IN_PAGE_FLAGS) -int page_nid_xchg_last(struct page *page, int nid) +#if defined(CONFIG_NUMA_BALANCING) && !defined(LAST_CPUPID_NOT_IN_PAGE_FLAGS) +int page_cpupid_xchg_last(struct page *page, int cpupid) { unsigned long old_flags, flags; - int last_nid; + int last_cpupid; do { old_flags = flags = page->flags; - last_nid = page_nid_last(page); + last_cpupid = page_cpupid_last(page); - flags &= ~(LAST_NID_MASK << LAST_NID_PGSHIFT); - flags |= (nid & LAST_NID_MASK) << LAST_NID_PGSHIFT; + flags &= ~(LAST_CPUPID_MASK << LAST_CPUPID_PGSHIFT); + flags |= (cpupid & LAST_CPUPID_MASK) << LAST_CPUPID_PGSHIFT; } while (unlikely(cmpxchg(&page->flags, old_flags, flags) != old_flags)); - return last_nid; + return last_cpupid; } #endif diff --git a/mm/mprotect.c b/mm/mprotect.c index 94722a4d6b43..26667971c824 100644 --- a/mm/mprotect.c +++ b/mm/mprotect.c @@ -37,14 +37,12 @@ static inline pgprot_t pgprot_modify(pgprot_t oldprot, pgprot_t newprot) static unsigned long change_pte_range(struct vm_area_struct *vma, pmd_t *pmd, unsigned long addr, unsigned long end, pgprot_t newprot, - int dirty_accountable, int prot_numa, bool *ret_all_same_node) + int dirty_accountable, int prot_numa) { struct mm_struct *mm = vma->vm_mm; pte_t *pte, oldpte; spinlock_t *ptl; unsigned long pages = 0; - bool all_same_node = true; - int last_nid = -1; pte = pte_offset_map_lock(mm, pmd, addr, &ptl); arch_enter_lazy_mmu_mode(); @@ -63,15 +61,7 @@ static unsigned long change_pte_range(struct vm_area_struct *vma, pmd_t *pmd, page = vm_normal_page(vma, addr, oldpte); if (page) { - int this_nid = page_to_nid(page); - if (last_nid == -1) - last_nid = this_nid; - if (last_nid != this_nid) - all_same_node = false; - - /* only check non-shared pages */ - if (!pte_numa(oldpte) && - page_mapcount(page) == 1) { + if (!pte_numa(oldpte)) { ptent = pte_mknuma(ptent); updated = true; } @@ -94,40 +84,27 @@ static unsigned long change_pte_range(struct vm_area_struct *vma, pmd_t *pmd, swp_entry_t entry = pte_to_swp_entry(oldpte); if (is_write_migration_entry(entry)) { + pte_t newpte; /* * A protection check is difficult so * just be safe and disable write */ make_migration_entry_read(&entry); - set_pte_at(mm, addr, pte, - swp_entry_to_pte(entry)); + newpte = swp_entry_to_pte(entry); + if (pte_swp_soft_dirty(oldpte)) + newpte = pte_swp_mksoft_dirty(newpte); + set_pte_at(mm, addr, pte, newpte); + + pages++; } - pages++; } } while (pte++, addr += PAGE_SIZE, addr != end); arch_leave_lazy_mmu_mode(); pte_unmap_unlock(pte - 1, ptl); - *ret_all_same_node = all_same_node; return pages; } -#ifdef CONFIG_NUMA_BALANCING -static inline void change_pmd_protnuma(struct mm_struct *mm, unsigned long addr, - pmd_t *pmd) -{ - spin_lock(&mm->page_table_lock); - set_pmd_at(mm, addr & PMD_MASK, pmd, pmd_mknuma(*pmd)); - spin_unlock(&mm->page_table_lock); -} -#else -static inline void change_pmd_protnuma(struct mm_struct *mm, unsigned long addr, - pmd_t *pmd) -{ - BUG(); -} -#endif /* CONFIG_NUMA_BALANCING */ - static inline unsigned long change_pmd_range(struct vm_area_struct *vma, pud_t *pud, unsigned long addr, unsigned long end, pgprot_t newprot, int dirty_accountable, int prot_numa) @@ -135,36 +112,39 @@ static inline unsigned long change_pmd_range(struct vm_area_struct *vma, pmd_t *pmd; unsigned long next; unsigned long pages = 0; - bool all_same_node; + unsigned long nr_huge_updates = 0; pmd = pmd_offset(pud, addr); do { + unsigned long this_pages; + next = pmd_addr_end(addr, end); if (pmd_trans_huge(*pmd)) { if (next - addr != HPAGE_PMD_SIZE) split_huge_page_pmd(vma, addr, pmd); - else if (change_huge_pmd(vma, pmd, addr, newprot, - prot_numa)) { - pages += HPAGE_PMD_NR; - continue; + else { + int nr_ptes = change_huge_pmd(vma, pmd, addr, + newprot, prot_numa); + + if (nr_ptes) { + if (nr_ptes == HPAGE_PMD_NR) { + pages += HPAGE_PMD_NR; + nr_huge_updates++; + } + continue; + } } /* fall through */ } if (pmd_none_or_clear_bad(pmd)) continue; - pages += change_pte_range(vma, pmd, addr, next, newprot, - dirty_accountable, prot_numa, &all_same_node); - - /* - * If we are changing protections for NUMA hinting faults then - * set pmd_numa if the examined pages were all on the same - * node. This allows a regular PMD to be handled as one fault - * and effectively batches the taking of the PTL - */ - if (prot_numa && all_same_node) - change_pmd_protnuma(vma->vm_mm, addr, pmd); + this_pages = change_pte_range(vma, pmd, addr, next, newprot, + dirty_accountable, prot_numa); + pages += this_pages; } while (pmd++, addr = next, addr != end); + if (nr_huge_updates) + count_vm_numa_events(NUMA_HUGE_PTE_UPDATES, nr_huge_updates); return pages; } diff --git a/mm/nobootmem.c b/mm/nobootmem.c index 61107cf55bb3..2c254d374655 100644 --- a/mm/nobootmem.c +++ b/mm/nobootmem.c @@ -82,27 +82,18 @@ void __init free_bootmem_late(unsigned long addr, unsigned long size) static void __init __free_pages_memory(unsigned long start, unsigned long end) { - unsigned long i, start_aligned, end_aligned; - int order = ilog2(BITS_PER_LONG); + int order; - start_aligned = (start + (BITS_PER_LONG - 1)) & ~(BITS_PER_LONG - 1); - end_aligned = end & ~(BITS_PER_LONG - 1); + while (start < end) { + order = min(MAX_ORDER - 1UL, __ffs(start)); - if (end_aligned <= start_aligned) { - for (i = start; i < end; i++) - __free_pages_bootmem(pfn_to_page(i), 0); + while (start + (1UL << order) > end) + order--; - return; - } - - for (i = start; i < start_aligned; i++) - __free_pages_bootmem(pfn_to_page(i), 0); + __free_pages_bootmem(pfn_to_page(start), order); - for (i = start_aligned; i < end_aligned; i += BITS_PER_LONG) - __free_pages_bootmem(pfn_to_page(i), order); - - for (i = end_aligned; i < end; i++) - __free_pages_bootmem(pfn_to_page(i), 0); + start += (1UL << order); + } } static unsigned long __init __free_memory_core(phys_addr_t start, diff --git a/mm/nommu.c b/mm/nommu.c index ecd1f158548e..fec093adad9c 100644 --- a/mm/nommu.c +++ b/mm/nommu.c @@ -937,7 +937,7 @@ static int validate_mmap_request(struct file *file, struct address_space *mapping; /* files must support mmap */ - if (!file->f_op || !file->f_op->mmap) + if (!file->f_op->mmap) return -ENODEV; /* work out if what we've got could possibly be shared @@ -1948,13 +1948,12 @@ int __vm_enough_memory(struct mm_struct *mm, long pages, int cap_sys_admin) goto error; } - allowed = totalram_pages * sysctl_overcommit_ratio / 100; + allowed = vm_commit_limit(); /* * Reserve some 3% for root */ if (!cap_sys_admin) allowed -= sysctl_admin_reserve_kbytes >> (PAGE_SHIFT - 10); - allowed += total_swap_pages; /* * Don't let a single process grow so big a user can't recover diff --git a/mm/oom_kill.c b/mm/oom_kill.c index 98e75f2ac7bc..1e4a600a6163 100644 --- a/mm/oom_kill.c +++ b/mm/oom_kill.c @@ -161,7 +161,7 @@ unsigned long oom_badness(struct task_struct *p, struct mem_cgroup *memcg, * The baseline for the badness score is the proportion of RAM that each * task's rss, pagetable and swap space use. */ - points = get_mm_rss(p->mm) + p->mm->nr_ptes + + points = get_mm_rss(p->mm) + atomic_long_read(&p->mm->nr_ptes) + get_mm_counter(p->mm, MM_SWAPENTS); task_unlock(p); @@ -364,10 +364,10 @@ static void dump_tasks(const struct mem_cgroup *memcg, const nodemask_t *nodemas continue; } - pr_info("[%5d] %5d %5d %8lu %8lu %7lu %8lu %5hd %s\n", + pr_info("[%5d] %5d %5d %8lu %8lu %7ld %8lu %5hd %s\n", task->pid, from_kuid(&init_user_ns, task_uid(task)), task->tgid, task->mm->total_vm, get_mm_rss(task->mm), - task->mm->nr_ptes, + atomic_long_read(&task->mm->nr_ptes), get_mm_counter(task->mm, MM_SWAPENTS), task->signal->oom_score_adj, task->comm); task_unlock(task); @@ -678,9 +678,12 @@ out: */ void pagefault_out_of_memory(void) { - struct zonelist *zonelist = node_zonelist(first_online_node, - GFP_KERNEL); + struct zonelist *zonelist; + if (mem_cgroup_oom_synchronize(true)) + return; + + zonelist = node_zonelist(first_online_node, GFP_KERNEL); if (try_set_zonelist_oom(zonelist, GFP_KERNEL)) { out_of_memory(NULL, 0, 0, NULL, false); clear_zonelist_oom(zonelist, GFP_KERNEL); diff --git a/mm/page-writeback.c b/mm/page-writeback.c index 3f0c895c71fe..63807583d8e8 100644 --- a/mm/page-writeback.c +++ b/mm/page-writeback.c @@ -36,8 +36,11 @@ #include <linux/pagevec.h> #include <linux/timer.h> #include <linux/sched/rt.h> +#include <linux/mm_inline.h> #include <trace/events/writeback.h> +#include "internal.h" + /* * Sleep at most 200ms at a time in balance_dirty_pages(). */ @@ -241,9 +244,6 @@ static unsigned long global_dirtyable_memory(void) if (!vm_highmem_is_dirtyable) x -= highmem_dirtyable_memory(x); - /* Subtract min_free_kbytes */ - x -= min_t(unsigned long, x, min_free_kbytes >> (PAGE_SHIFT - 10)); - return x + 1; /* Ensure that we never return 0 */ } @@ -585,6 +585,37 @@ unsigned long bdi_dirty_limit(struct backing_dev_info *bdi, unsigned long dirty) } /* + * setpoint - dirty 3 + * f(dirty) := 1.0 + (----------------) + * limit - setpoint + * + * it's a 3rd order polynomial that subjects to + * + * (1) f(freerun) = 2.0 => rampup dirty_ratelimit reasonably fast + * (2) f(setpoint) = 1.0 => the balance point + * (3) f(limit) = 0 => the hard limit + * (4) df/dx <= 0 => negative feedback control + * (5) the closer to setpoint, the smaller |df/dx| (and the reverse) + * => fast response on large errors; small oscillation near setpoint + */ +static inline long long pos_ratio_polynom(unsigned long setpoint, + unsigned long dirty, + unsigned long limit) +{ + long long pos_ratio; + long x; + + x = div_s64(((s64)setpoint - (s64)dirty) << RATELIMIT_CALC_SHIFT, + limit - setpoint + 1); + pos_ratio = x; + pos_ratio = pos_ratio * x >> RATELIMIT_CALC_SHIFT; + pos_ratio = pos_ratio * x >> RATELIMIT_CALC_SHIFT; + pos_ratio += 1 << RATELIMIT_CALC_SHIFT; + + return clamp(pos_ratio, 0LL, 2LL << RATELIMIT_CALC_SHIFT); +} + +/* * Dirty position control. * * (o) global/bdi setpoints @@ -682,26 +713,80 @@ static unsigned long bdi_position_ratio(struct backing_dev_info *bdi, /* * global setpoint * - * setpoint - dirty 3 - * f(dirty) := 1.0 + (----------------) - * limit - setpoint + * See comment for pos_ratio_polynom(). + */ + setpoint = (freerun + limit) / 2; + pos_ratio = pos_ratio_polynom(setpoint, dirty, limit); + + /* + * The strictlimit feature is a tool preventing mistrusted filesystems + * from growing a large number of dirty pages before throttling. For + * such filesystems balance_dirty_pages always checks bdi counters + * against bdi limits. Even if global "nr_dirty" is under "freerun". + * This is especially important for fuse which sets bdi->max_ratio to + * 1% by default. Without strictlimit feature, fuse writeback may + * consume arbitrary amount of RAM because it is accounted in + * NR_WRITEBACK_TEMP which is not involved in calculating "nr_dirty". * - * it's a 3rd order polynomial that subjects to + * Here, in bdi_position_ratio(), we calculate pos_ratio based on + * two values: bdi_dirty and bdi_thresh. Let's consider an example: + * total amount of RAM is 16GB, bdi->max_ratio is equal to 1%, global + * limits are set by default to 10% and 20% (background and throttle). + * Then bdi_thresh is 1% of 20% of 16GB. This amounts to ~8K pages. + * bdi_dirty_limit(bdi, bg_thresh) is about ~4K pages. bdi_setpoint is + * about ~6K pages (as the average of background and throttle bdi + * limits). The 3rd order polynomial will provide positive feedback if + * bdi_dirty is under bdi_setpoint and vice versa. * - * (1) f(freerun) = 2.0 => rampup dirty_ratelimit reasonably fast - * (2) f(setpoint) = 1.0 => the balance point - * (3) f(limit) = 0 => the hard limit - * (4) df/dx <= 0 => negative feedback control - * (5) the closer to setpoint, the smaller |df/dx| (and the reverse) - * => fast response on large errors; small oscillation near setpoint + * Note, that we cannot use global counters in these calculations + * because we want to throttle process writing to a strictlimit BDI + * much earlier than global "freerun" is reached (~23MB vs. ~2.3GB + * in the example above). */ - setpoint = (freerun + limit) / 2; - x = div_s64(((s64)setpoint - (s64)dirty) << RATELIMIT_CALC_SHIFT, - limit - setpoint + 1); - pos_ratio = x; - pos_ratio = pos_ratio * x >> RATELIMIT_CALC_SHIFT; - pos_ratio = pos_ratio * x >> RATELIMIT_CALC_SHIFT; - pos_ratio += 1 << RATELIMIT_CALC_SHIFT; + if (unlikely(bdi->capabilities & BDI_CAP_STRICTLIMIT)) { + long long bdi_pos_ratio; + unsigned long bdi_bg_thresh; + + if (bdi_dirty < 8) + return min_t(long long, pos_ratio * 2, + 2 << RATELIMIT_CALC_SHIFT); + + if (bdi_dirty >= bdi_thresh) + return 0; + + bdi_bg_thresh = div_u64((u64)bdi_thresh * bg_thresh, thresh); + bdi_setpoint = dirty_freerun_ceiling(bdi_thresh, + bdi_bg_thresh); + + if (bdi_setpoint == 0 || bdi_setpoint == bdi_thresh) + return 0; + + bdi_pos_ratio = pos_ratio_polynom(bdi_setpoint, bdi_dirty, + bdi_thresh); + + /* + * Typically, for strictlimit case, bdi_setpoint << setpoint + * and pos_ratio >> bdi_pos_ratio. In the other words global + * state ("dirty") is not limiting factor and we have to + * make decision based on bdi counters. But there is an + * important case when global pos_ratio should get precedence: + * global limits are exceeded (e.g. due to activities on other + * BDIs) while given strictlimit BDI is below limit. + * + * "pos_ratio * bdi_pos_ratio" would work for the case above, + * but it would look too non-natural for the case of all + * activity in the system coming from a single strictlimit BDI + * with bdi->max_ratio == 100%. + * + * Note that min() below somewhat changes the dynamics of the + * control system. Normally, pos_ratio value can be well over 3 + * (when globally we are at freerun and bdi is well below bdi + * setpoint). Now the maximum pos_ratio in the same situation + * is 2. We might want to tweak this if we observe the control + * system is too slow to adapt. + */ + return min(pos_ratio, bdi_pos_ratio); + } /* * We have computed basic pos_ratio above based on global situation. If @@ -994,6 +1079,27 @@ static void bdi_update_dirty_ratelimit(struct backing_dev_info *bdi, * keep that period small to reduce time lags). */ step = 0; + + /* + * For strictlimit case, calculations above were based on bdi counters + * and limits (starting from pos_ratio = bdi_position_ratio() and up to + * balanced_dirty_ratelimit = task_ratelimit * write_bw / dirty_rate). + * Hence, to calculate "step" properly, we have to use bdi_dirty as + * "dirty" and bdi_setpoint as "setpoint". + * + * We rampup dirty_ratelimit forcibly if bdi_dirty is low because + * it's possible that bdi_thresh is close to zero due to inactivity + * of backing device (see the implementation of bdi_dirty_limit()). + */ + if (unlikely(bdi->capabilities & BDI_CAP_STRICTLIMIT)) { + dirty = bdi_dirty; + if (bdi_dirty < 8) + setpoint = bdi_dirty + 1; + else + setpoint = (bdi_thresh + + bdi_dirty_limit(bdi, bg_thresh)) / 2; + } + if (dirty < setpoint) { x = min(bdi->balanced_dirty_ratelimit, min(balanced_dirty_ratelimit, task_ratelimit)); @@ -1104,11 +1210,11 @@ static unsigned long dirty_poll_interval(unsigned long dirty, return 1; } -static long bdi_max_pause(struct backing_dev_info *bdi, - unsigned long bdi_dirty) +static unsigned long bdi_max_pause(struct backing_dev_info *bdi, + unsigned long bdi_dirty) { - long bw = bdi->avg_write_bandwidth; - long t; + unsigned long bw = bdi->avg_write_bandwidth; + unsigned long t; /* * Limit pause time for small memory systems. If sleeping for too long @@ -1120,7 +1226,7 @@ static long bdi_max_pause(struct backing_dev_info *bdi, t = bdi_dirty / (1 + bw / roundup_pow_of_two(1 + HZ / 8)); t++; - return min_t(long, t, MAX_PAUSE); + return min_t(unsigned long, t, MAX_PAUSE); } static long bdi_min_pause(struct backing_dev_info *bdi, @@ -1198,6 +1304,56 @@ static long bdi_min_pause(struct backing_dev_info *bdi, return pages >= DIRTY_POLL_THRESH ? 1 + t / 2 : t; } +static inline void bdi_dirty_limits(struct backing_dev_info *bdi, + unsigned long dirty_thresh, + unsigned long background_thresh, + unsigned long *bdi_dirty, + unsigned long *bdi_thresh, + unsigned long *bdi_bg_thresh) +{ + unsigned long bdi_reclaimable; + + /* + * bdi_thresh is not treated as some limiting factor as + * dirty_thresh, due to reasons + * - in JBOD setup, bdi_thresh can fluctuate a lot + * - in a system with HDD and USB key, the USB key may somehow + * go into state (bdi_dirty >> bdi_thresh) either because + * bdi_dirty starts high, or because bdi_thresh drops low. + * In this case we don't want to hard throttle the USB key + * dirtiers for 100 seconds until bdi_dirty drops under + * bdi_thresh. Instead the auxiliary bdi control line in + * bdi_position_ratio() will let the dirtier task progress + * at some rate <= (write_bw / 2) for bringing down bdi_dirty. + */ + *bdi_thresh = bdi_dirty_limit(bdi, dirty_thresh); + + if (bdi_bg_thresh) + *bdi_bg_thresh = div_u64((u64)*bdi_thresh * + background_thresh, + dirty_thresh); + + /* + * In order to avoid the stacked BDI deadlock we need + * to ensure we accurately count the 'dirty' pages when + * the threshold is low. + * + * Otherwise it would be possible to get thresh+n pages + * reported dirty, even though there are thresh-m pages + * actually dirty; with m+n sitting in the percpu + * deltas. + */ + if (*bdi_thresh < 2 * bdi_stat_error(bdi)) { + bdi_reclaimable = bdi_stat_sum(bdi, BDI_RECLAIMABLE); + *bdi_dirty = bdi_reclaimable + + bdi_stat_sum(bdi, BDI_WRITEBACK); + } else { + bdi_reclaimable = bdi_stat(bdi, BDI_RECLAIMABLE); + *bdi_dirty = bdi_reclaimable + + bdi_stat(bdi, BDI_WRITEBACK); + } +} + /* * balance_dirty_pages() must be called by processes which are generating dirty * data. It looks at the number of dirty pages in the machine and will force @@ -1209,13 +1365,9 @@ static void balance_dirty_pages(struct address_space *mapping, unsigned long pages_dirtied) { unsigned long nr_reclaimable; /* = file_dirty + unstable_nfs */ - unsigned long bdi_reclaimable; unsigned long nr_dirty; /* = file_dirty + writeback + unstable_nfs */ - unsigned long bdi_dirty; - unsigned long freerun; unsigned long background_thresh; unsigned long dirty_thresh; - unsigned long bdi_thresh; long period; long pause; long max_pause; @@ -1226,10 +1378,16 @@ static void balance_dirty_pages(struct address_space *mapping, unsigned long dirty_ratelimit; unsigned long pos_ratio; struct backing_dev_info *bdi = mapping->backing_dev_info; + bool strictlimit = bdi->capabilities & BDI_CAP_STRICTLIMIT; unsigned long start_time = jiffies; for (;;) { unsigned long now = jiffies; + unsigned long uninitialized_var(bdi_thresh); + unsigned long thresh; + unsigned long uninitialized_var(bdi_dirty); + unsigned long dirty; + unsigned long bg_thresh; /* * Unstable writes are a feature of certain networked @@ -1243,61 +1401,44 @@ static void balance_dirty_pages(struct address_space *mapping, global_dirty_limits(&background_thresh, &dirty_thresh); + if (unlikely(strictlimit)) { + bdi_dirty_limits(bdi, dirty_thresh, background_thresh, + &bdi_dirty, &bdi_thresh, &bg_thresh); + + dirty = bdi_dirty; + thresh = bdi_thresh; + } else { + dirty = nr_dirty; + thresh = dirty_thresh; + bg_thresh = background_thresh; + } + /* * Throttle it only when the background writeback cannot * catch-up. This avoids (excessively) small writeouts - * when the bdi limits are ramping up. + * when the bdi limits are ramping up in case of !strictlimit. + * + * In strictlimit case make decision based on the bdi counters + * and limits. Small writeouts when the bdi limits are ramping + * up are the price we consciously pay for strictlimit-ing. */ - freerun = dirty_freerun_ceiling(dirty_thresh, - background_thresh); - if (nr_dirty <= freerun) { + if (dirty <= dirty_freerun_ceiling(thresh, bg_thresh)) { current->dirty_paused_when = now; current->nr_dirtied = 0; current->nr_dirtied_pause = - dirty_poll_interval(nr_dirty, dirty_thresh); + dirty_poll_interval(dirty, thresh); break; } if (unlikely(!writeback_in_progress(bdi))) bdi_start_background_writeback(bdi); - /* - * bdi_thresh is not treated as some limiting factor as - * dirty_thresh, due to reasons - * - in JBOD setup, bdi_thresh can fluctuate a lot - * - in a system with HDD and USB key, the USB key may somehow - * go into state (bdi_dirty >> bdi_thresh) either because - * bdi_dirty starts high, or because bdi_thresh drops low. - * In this case we don't want to hard throttle the USB key - * dirtiers for 100 seconds until bdi_dirty drops under - * bdi_thresh. Instead the auxiliary bdi control line in - * bdi_position_ratio() will let the dirtier task progress - * at some rate <= (write_bw / 2) for bringing down bdi_dirty. - */ - bdi_thresh = bdi_dirty_limit(bdi, dirty_thresh); - - /* - * In order to avoid the stacked BDI deadlock we need - * to ensure we accurately count the 'dirty' pages when - * the threshold is low. - * - * Otherwise it would be possible to get thresh+n pages - * reported dirty, even though there are thresh-m pages - * actually dirty; with m+n sitting in the percpu - * deltas. - */ - if (bdi_thresh < 2 * bdi_stat_error(bdi)) { - bdi_reclaimable = bdi_stat_sum(bdi, BDI_RECLAIMABLE); - bdi_dirty = bdi_reclaimable + - bdi_stat_sum(bdi, BDI_WRITEBACK); - } else { - bdi_reclaimable = bdi_stat(bdi, BDI_RECLAIMABLE); - bdi_dirty = bdi_reclaimable + - bdi_stat(bdi, BDI_WRITEBACK); - } + if (!strictlimit) + bdi_dirty_limits(bdi, dirty_thresh, background_thresh, + &bdi_dirty, &bdi_thresh, NULL); dirty_exceeded = (bdi_dirty > bdi_thresh) && - (nr_dirty > dirty_thresh); + ((nr_dirty > dirty_thresh) || strictlimit); if (dirty_exceeded && !bdi->dirty_exceeded) bdi->dirty_exceeded = 1; @@ -2002,11 +2143,17 @@ EXPORT_SYMBOL(account_page_dirtied); /* * Helper function for set_page_writeback family. + * + * The caller must hold mem_cgroup_begin/end_update_page_stat() lock + * while calling this function. + * See test_set_page_writeback for example. + * * NOTE: Unlike account_page_dirtied this does not rely on being atomic * wrt interrupts. */ void account_page_writeback(struct page *page) { + mem_cgroup_inc_page_stat(page, MEM_CGROUP_STAT_WRITEBACK); inc_zone_page_state(page, NR_WRITEBACK); } EXPORT_SYMBOL(account_page_writeback); @@ -2223,7 +2370,10 @@ int test_clear_page_writeback(struct page *page) { struct address_space *mapping = page_mapping(page); int ret; + bool locked; + unsigned long memcg_flags; + mem_cgroup_begin_update_page_stat(page, &locked, &memcg_flags); if (mapping) { struct backing_dev_info *bdi = mapping->backing_dev_info; unsigned long flags; @@ -2244,9 +2394,11 @@ int test_clear_page_writeback(struct page *page) ret = TestClearPageWriteback(page); } if (ret) { + mem_cgroup_dec_page_stat(page, MEM_CGROUP_STAT_WRITEBACK); dec_zone_page_state(page, NR_WRITEBACK); inc_zone_page_state(page, NR_WRITTEN); } + mem_cgroup_end_update_page_stat(page, &locked, &memcg_flags); return ret; } @@ -2254,7 +2406,10 @@ int test_set_page_writeback(struct page *page) { struct address_space *mapping = page_mapping(page); int ret; + bool locked; + unsigned long memcg_flags; + mem_cgroup_begin_update_page_stat(page, &locked, &memcg_flags); if (mapping) { struct backing_dev_info *bdi = mapping->backing_dev_info; unsigned long flags; @@ -2281,6 +2436,7 @@ int test_set_page_writeback(struct page *page) } if (!ret) account_page_writeback(page); + mem_cgroup_end_update_page_stat(page, &locked, &memcg_flags); return ret; } diff --git a/mm/page_alloc.c b/mm/page_alloc.c index c2b59dbda196..580a5f075ed0 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -56,6 +56,7 @@ #include <linux/ftrace_event.h> #include <linux/memcontrol.h> #include <linux/prefetch.h> +#include <linux/mm_inline.h> #include <linux/migrate.h> #include <linux/page-debug-flags.h> #include <linux/hugetlb.h> @@ -233,8 +234,8 @@ int page_group_by_mobility_disabled __read_mostly; void set_pageblock_migratetype(struct page *page, int migratetype) { - - if (unlikely(page_group_by_mobility_disabled)) + if (unlikely(page_group_by_mobility_disabled && + migratetype < MIGRATE_PCPTYPES)) migratetype = MIGRATE_UNMOVABLE; set_pageblock_flags_group(page, (unsigned long)migratetype, @@ -488,8 +489,10 @@ __find_buddy_index(unsigned long page_idx, unsigned int order) * (c) a page and its buddy have the same order && * (d) a page and its buddy are in the same zone. * - * For recording whether a page is in the buddy system, we set ->_mapcount -2. - * Setting, clearing, and testing _mapcount -2 is serialized by zone->lock. + * For recording whether a page is in the buddy system, we set ->_mapcount + * PAGE_BUDDY_MAPCOUNT_VALUE. + * Setting, clearing, and testing _mapcount PAGE_BUDDY_MAPCOUNT_VALUE is + * serialized by zone->lock. * * For recording page's order, we use page_private(page). */ @@ -527,8 +530,9 @@ static inline int page_is_buddy(struct page *page, struct page *buddy, * as necessary, plus some accounting needed to play nicely with other * parts of the VM system. * At each level, we keep a list of pages, which are heads of continuous - * free pages of length of (1 << order) and marked with _mapcount -2. Page's - * order is recorded in page_private(page) field. + * free pages of length of (1 << order) and marked with _mapcount + * PAGE_BUDDY_MAPCOUNT_VALUE. Page's order is recorded in page_private(page) + * field. * So when we are allocating or freeing one, we can derive the state of the * other. That is, if we allocate a small block, and both were * free, the remainder of the region must be split into blocks. @@ -622,7 +626,7 @@ static inline int free_pages_check(struct page *page) bad_page(page); return 1; } - page_nid_reset_last(page); + page_cpupid_reset_last(page); if (page->flags & PAGE_FLAGS_CHECK_AT_PREP) page->flags &= ~PAGE_FLAGS_CHECK_AT_PREP; return 0; @@ -647,7 +651,6 @@ static void free_pcppages_bulk(struct zone *zone, int count, int to_free = count; spin_lock(&zone->lock); - zone->all_unreclaimable = 0; zone->pages_scanned = 0; while (to_free) { @@ -696,7 +699,6 @@ static void free_one_page(struct zone *zone, struct page *page, int order, int migratetype) { spin_lock(&zone->lock); - zone->all_unreclaimable = 0; zone->pages_scanned = 0; __free_one_page(page, zone, order, migratetype); @@ -721,7 +723,8 @@ static bool free_pages_prepare(struct page *page, unsigned int order) return false; if (!PageHighMem(page)) { - debug_check_no_locks_freed(page_address(page),PAGE_SIZE<<order); + debug_check_no_locks_freed(page_address(page), + PAGE_SIZE << order); debug_check_no_obj_freed(page_address(page), PAGE_SIZE << order); } @@ -750,19 +753,19 @@ static void __free_pages_ok(struct page *page, unsigned int order) void __init __free_pages_bootmem(struct page *page, unsigned int order) { unsigned int nr_pages = 1 << order; + struct page *p = page; unsigned int loop; - prefetchw(page); - for (loop = 0; loop < nr_pages; loop++) { - struct page *p = &page[loop]; - - if (loop + 1 < nr_pages) - prefetchw(p + 1); + prefetchw(p); + for (loop = 0; loop < (nr_pages - 1); loop++, p++) { + prefetchw(p + 1); __ClearPageReserved(p); set_page_count(p, 0); } + __ClearPageReserved(p); + set_page_count(p, 0); - page_zone(page)->managed_pages += 1 << order; + page_zone(page)->managed_pages += nr_pages; set_page_refcounted(page); __free_pages(page, order); } @@ -885,7 +888,7 @@ struct page *__rmqueue_smallest(struct zone *zone, unsigned int order, int migratetype) { unsigned int current_order; - struct free_area * area; + struct free_area *area; struct page *page; /* Find a page of the appropriate size in the preferred list */ @@ -1007,14 +1010,64 @@ static void change_pageblock_range(struct page *pageblock_page, } } +/* + * If breaking a large block of pages, move all free pages to the preferred + * allocation list. If falling back for a reclaimable kernel allocation, be + * more aggressive about taking ownership of free pages. + * + * On the other hand, never change migration type of MIGRATE_CMA pageblocks + * nor move CMA pages to different free lists. We don't want unmovable pages + * to be allocated from MIGRATE_CMA areas. + * + * Returns the new migratetype of the pageblock (or the same old migratetype + * if it was unchanged). + */ +static int try_to_steal_freepages(struct zone *zone, struct page *page, + int start_type, int fallback_type) +{ + int current_order = page_order(page); + + /* + * When borrowing from MIGRATE_CMA, we need to release the excess + * buddy pages to CMA itself. + */ + if (is_migrate_cma(fallback_type)) + return fallback_type; + + /* Take ownership for orders >= pageblock_order */ + if (current_order >= pageblock_order) { + change_pageblock_range(page, current_order, start_type); + return start_type; + } + + if (current_order >= pageblock_order / 2 || + start_type == MIGRATE_RECLAIMABLE || + page_group_by_mobility_disabled) { + int pages; + + pages = move_freepages_block(zone, page, start_type); + + /* Claim the whole block if over half of it is free */ + if (pages >= (1 << (pageblock_order-1)) || + page_group_by_mobility_disabled) { + + set_pageblock_migratetype(page, start_type); + return start_type; + } + + } + + return fallback_type; +} + /* Remove an element from the buddy allocator from the fallback list */ static inline struct page * __rmqueue_fallback(struct zone *zone, int order, int start_migratetype) { - struct free_area * area; + struct free_area *area; int current_order; struct page *page; - int migratetype, i; + int migratetype, new_type, i; /* Find the largest possible block of pages in the other list */ for (current_order = MAX_ORDER-1; current_order >= order; @@ -1034,51 +1087,19 @@ __rmqueue_fallback(struct zone *zone, int order, int start_migratetype) struct page, lru); area->nr_free--; - /* - * If breaking a large block of pages, move all free - * pages to the preferred allocation list. If falling - * back for a reclaimable kernel allocation, be more - * aggressive about taking ownership of free pages - * - * On the other hand, never change migration - * type of MIGRATE_CMA pageblocks nor move CMA - * pages on different free lists. We don't - * want unmovable pages to be allocated from - * MIGRATE_CMA areas. - */ - if (!is_migrate_cma(migratetype) && - (current_order >= pageblock_order / 2 || - start_migratetype == MIGRATE_RECLAIMABLE || - page_group_by_mobility_disabled)) { - int pages; - pages = move_freepages_block(zone, page, - start_migratetype); - - /* Claim the whole block if over half of it is free */ - if (pages >= (1 << (pageblock_order-1)) || - page_group_by_mobility_disabled) - set_pageblock_migratetype(page, - start_migratetype); - - migratetype = start_migratetype; - } + new_type = try_to_steal_freepages(zone, page, + start_migratetype, + migratetype); /* Remove the page from the freelists */ list_del(&page->lru); rmv_page_order(page); - /* Take ownership for orders >= pageblock_order */ - if (current_order >= pageblock_order && - !is_migrate_cma(migratetype)) - change_pageblock_range(page, current_order, - start_migratetype); - expand(zone, page, order, current_order, area, - is_migrate_cma(migratetype) - ? migratetype : start_migratetype); + new_type); trace_mm_page_alloc_extfrag(page, order, current_order, - start_migratetype, migratetype); + start_migratetype, migratetype, new_type); return page; } @@ -1281,7 +1302,7 @@ void mark_free_pages(struct zone *zone) int order, t; struct list_head *curr; - if (!zone->spanned_pages) + if (zone_is_empty(zone)) return; spin_lock_irqsave(&zone->lock, flags); @@ -1526,6 +1547,7 @@ again: get_pageblock_migratetype(page)); } + __mod_zone_page_state(zone, NR_ALLOC_BATCH, -(1 << order)); __count_zone_vm_events(PGALLOC, zone, 1 << order); zone_statistics(preferred_zone, zone, gfp_flags); local_irq_restore(flags); @@ -1683,7 +1705,7 @@ bool zone_watermark_ok_safe(struct zone *z, int order, unsigned long mark, * comments in mmzone.h. Reduces cache footprint of zonelist scans * that have to skip over a lot of full or unallowed zones. * - * If the zonelist cache is present in the passed in zonelist, then + * If the zonelist cache is present in the passed zonelist, then * returns a pointer to the allowed node mask (either the current * tasks mems_allowed, or node_states[N_MEMORY].) * @@ -1792,6 +1814,11 @@ static void zlc_clear_zones_full(struct zonelist *zonelist) bitmap_zero(zlc->fullzones, MAX_ZONES_PER_ZONELIST); } +static bool zone_local(struct zone *local_zone, struct zone *zone) +{ + return node_distance(local_zone->node, zone->node) == LOCAL_DISTANCE; +} + static bool zone_allows_reclaim(struct zone *local_zone, struct zone *zone) { return node_isset(local_zone->node, zone->zone_pgdat->reclaim_nodes); @@ -1829,6 +1856,11 @@ static void zlc_clear_zones_full(struct zonelist *zonelist) { } +static bool zone_local(struct zone *local_zone, struct zone *zone) +{ + return true; +} + static bool zone_allows_reclaim(struct zone *local_zone, struct zone *zone) { return true; @@ -1860,16 +1892,41 @@ get_page_from_freelist(gfp_t gfp_mask, nodemask_t *nodemask, unsigned int order, zonelist_scan: /* * Scan zonelist, looking for a zone with enough free. - * See also cpuset_zone_allowed() comment in kernel/cpuset.c. + * See also __cpuset_node_allowed_softwall() comment in kernel/cpuset.c. */ for_each_zone_zonelist_nodemask(zone, z, zonelist, high_zoneidx, nodemask) { + unsigned long mark; + if (IS_ENABLED(CONFIG_NUMA) && zlc_active && !zlc_zone_worth_trying(zonelist, z, allowednodes)) continue; if ((alloc_flags & ALLOC_CPUSET) && !cpuset_zone_allowed_softwall(zone, gfp_mask)) continue; + BUILD_BUG_ON(ALLOC_NO_WATERMARKS < NR_WMARK); + if (unlikely(alloc_flags & ALLOC_NO_WATERMARKS)) + goto try_this_zone; + /* + * Distribute pages in proportion to the individual + * zone size to ensure fair page aging. The zone a + * page was allocated in should have no effect on the + * time the page has in memory before being reclaimed. + * + * When zone_reclaim_mode is enabled, try to stay in + * local zones in the fastpath. If that fails, the + * slowpath is entered, which will do another pass + * starting with the local zones, but ultimately fall + * back to remote zones that do not partake in the + * fairness round-robin cycle of this zonelist. + */ + if (alloc_flags & ALLOC_WMARK_LOW) { + if (zone_page_state(zone, NR_ALLOC_BATCH) <= 0) + continue; + if (zone_reclaim_mode && + !zone_local(preferred_zone, zone)) + continue; + } /* * When allocating a page cache page for writing, we * want to get it from a zone that is within its dirty @@ -1900,16 +1957,11 @@ zonelist_scan: (gfp_mask & __GFP_WRITE) && !zone_dirty_ok(zone)) goto this_zone_full; - BUILD_BUG_ON(ALLOC_NO_WATERMARKS < NR_WMARK); - if (!(alloc_flags & ALLOC_NO_WATERMARKS)) { - unsigned long mark; + mark = zone->watermark[alloc_flags & ALLOC_WMARK_MASK]; + if (!zone_watermark_ok(zone, order, mark, + classzone_idx, alloc_flags)) { int ret; - mark = zone->watermark[alloc_flags & ALLOC_WMARK_MASK]; - if (zone_watermark_ok(zone, order, mark, - classzone_idx, alloc_flags)) - goto try_this_zone; - if (IS_ENABLED(CONFIG_NUMA) && !did_zlc_setup && nr_online_nodes > 1) { /* @@ -2321,16 +2373,30 @@ __alloc_pages_high_priority(gfp_t gfp_mask, unsigned int order, return page; } -static inline -void wake_all_kswapd(unsigned int order, struct zonelist *zonelist, - enum zone_type high_zoneidx, - enum zone_type classzone_idx) +static void prepare_slowpath(gfp_t gfp_mask, unsigned int order, + struct zonelist *zonelist, + enum zone_type high_zoneidx, + struct zone *preferred_zone) { struct zoneref *z; struct zone *zone; - for_each_zone_zonelist(zone, z, zonelist, high_zoneidx) - wakeup_kswapd(zone, order, classzone_idx); + for_each_zone_zonelist(zone, z, zonelist, high_zoneidx) { + if (!(gfp_mask & __GFP_NO_KSWAPD)) + wakeup_kswapd(zone, order, zone_idx(preferred_zone)); + /* + * Only reset the batches of zones that were actually + * considered in the fast path, we don't want to + * thrash fairness information for zones that are not + * actually part of this zonelist's round-robin cycle. + */ + if (zone_reclaim_mode && !zone_local(preferred_zone, zone)) + continue; + mod_zone_page_state(zone, NR_ALLOC_BATCH, + high_wmark_pages(zone) - + low_wmark_pages(zone) - + zone_page_state(zone, NR_ALLOC_BATCH)); + } } static inline int @@ -2426,9 +2492,8 @@ __alloc_pages_slowpath(gfp_t gfp_mask, unsigned int order, goto nopage; restart: - if (!(gfp_mask & __GFP_NO_KSWAPD)) - wake_all_kswapd(order, zonelist, high_zoneidx, - zone_idx(preferred_zone)); + prepare_slowpath(gfp_mask, order, zonelist, + high_zoneidx, preferred_zone); /* * OK, we're below the kswapd watermark and have kicked background @@ -2522,7 +2587,7 @@ rebalance: * running out of options and have to consider going OOM */ if (!did_some_progress) { - if ((gfp_mask & __GFP_FS) && !(gfp_mask & __GFP_NORETRY)) { + if (oom_gfp_allowed(gfp_mask)) { if (oom_killer_disabled) goto nopage; /* Coredumps can quickly deplete all memory reserves */ @@ -3095,7 +3160,7 @@ void show_free_areas(unsigned int filter) K(zone_page_state(zone, NR_FREE_CMA_PAGES)), K(zone_page_state(zone, NR_WRITEBACK_TEMP)), zone->pages_scanned, - (zone->all_unreclaimable ? "yes" : "no") + (!zone_reclaimable(zone) ? "yes" : "no") ); printk("lowmem_reserve[]:"); for (i = 0; i < MAX_NR_ZONES; i++) @@ -3104,7 +3169,7 @@ void show_free_areas(unsigned int filter) } for_each_populated_zone(zone) { - unsigned long nr[MAX_ORDER], flags, order, total = 0; + unsigned long nr[MAX_ORDER], flags, order, total = 0; unsigned char types[MAX_ORDER]; if (skip_free_areas_node(filter, zone_to_nid(zone))) @@ -3416,11 +3481,11 @@ static void build_zonelists_in_zone_order(pg_data_t *pgdat, int nr_nodes) static int default_zonelist_order(void) { int nid, zone_type; - unsigned long low_kmem_size,total_size; + unsigned long low_kmem_size, total_size; struct zone *z; int average_size; /* - * ZONE_DMA and ZONE_DMA32 can be very small area in the system. + * ZONE_DMA and ZONE_DMA32 can be very small area in the system. * If they are really small and used heavily, the system can fall * into OOM very easily. * This function detect ZONE_DMA/DMA32 size and configures zone order. @@ -3452,9 +3517,9 @@ static int default_zonelist_order(void) return ZONELIST_ORDER_NODE; /* * look into each node's config. - * If there is a node whose DMA/DMA32 memory is very big area on - * local memory, NODE_ORDER may be suitable. - */ + * If there is a node whose DMA/DMA32 memory is very big area on + * local memory, NODE_ORDER may be suitable. + */ average_size = total_size / (nodes_weight(node_states[N_MEMORY]) + 1); for_each_online_node(nid) { @@ -3810,8 +3875,6 @@ static inline unsigned long wait_table_bits(unsigned long size) return ffz(~size); } -#define LONG_ALIGN(x) (((x)+(sizeof(long))-1)&~((sizeof(long))-1)) - /* * Check if a pageblock contains reserved pages */ @@ -3944,7 +4007,7 @@ void __meminit memmap_init_zone(unsigned long size, int nid, unsigned long zone, mminit_verify_page_links(page, zone, nid, pfn); init_page_count(page); page_mapcount_reset(page); - page_nid_reset_last(page); + page_cpupid_reset_last(page); SetPageReserved(page); /* * Mark the block movable so that blocks are reserved for @@ -4180,7 +4243,7 @@ int zone_wait_table_init(struct zone *zone, unsigned long zone_size_pages) if (!zone->wait_table) return -ENOMEM; - for(i = 0; i < zone->wait_table_hash_nr_entries; ++i) + for (i = 0; i < zone->wait_table_hash_nr_entries; ++i) init_waitqueue_head(zone->wait_table + i); return 0; @@ -4195,7 +4258,7 @@ static __meminit void zone_pcp_init(struct zone *zone) */ zone->pageset = &boot_pageset; - if (zone->present_pages) + if (populated_zone(zone)) printk(KERN_DEBUG " %s zone: %lu pages, LIFO batch:%u\n", zone->name, zone->present_pages, zone_batchsize(zone)); @@ -4237,7 +4300,7 @@ int __meminit init_currently_empty_zone(struct zone *zone, int __meminit __early_pfn_to_nid(unsigned long pfn) { unsigned long start_pfn, end_pfn; - int i, nid; + int nid; /* * NOTE: The following SMP-unsafe globals are only used early in boot * when the kernel is running single-threaded. @@ -4248,15 +4311,14 @@ int __meminit __early_pfn_to_nid(unsigned long pfn) if (last_start_pfn <= pfn && pfn < last_end_pfn) return last_nid; - for_each_mem_pfn_range(i, MAX_NUMNODES, &start_pfn, &end_pfn, &nid) - if (start_pfn <= pfn && pfn < end_pfn) { - last_start_pfn = start_pfn; - last_end_pfn = end_pfn; - last_nid = nid; - return nid; - } - /* This is a memory hole */ - return -1; + nid = memblock_search_pfn_nid(pfn, &start_pfn, &end_pfn); + if (nid != -1) { + last_start_pfn = start_pfn; + last_end_pfn = end_pfn; + last_nid = nid; + } + + return nid; } #endif /* CONFIG_HAVE_ARCH_EARLY_PFN_TO_NID */ @@ -4586,7 +4648,7 @@ static inline void setup_usemap(struct pglist_data *pgdat, struct zone *zone, #ifdef CONFIG_HUGETLB_PAGE_SIZE_VARIABLE /* Initialise the number of pages represented by NR_PAGEBLOCK_BITS */ -void __init set_pageblock_order(void) +void __paginginit set_pageblock_order(void) { unsigned int order; @@ -4614,7 +4676,7 @@ void __init set_pageblock_order(void) * include/linux/pageblock-flags.h for the values of pageblock_order based on * the kernel config */ -void __init set_pageblock_order(void) +void __paginginit set_pageblock_order(void) { } @@ -4728,8 +4790,11 @@ static void __paginginit free_area_init_core(struct pglist_data *pgdat, spin_lock_init(&zone->lru_lock); zone_seqlock_init(zone); zone->zone_pgdat = pgdat; - zone_pcp_init(zone); + + /* For bootup, initialized properly in watermark setup */ + mod_zone_page_state(zone, NR_ALLOC_BATCH, zone->managed_pages); + lruvec_init(&zone->lruvec); if (!size) continue; @@ -4930,7 +4995,7 @@ static unsigned long __init early_calculate_totalpages(void) if (pages) node_set_state(nid, N_MEMORY); } - return totalpages; + return totalpages; } /* @@ -5047,7 +5112,7 @@ restart: /* * Some kernelcore has been met, update counts and * break if the kernelcore for this node has been - * satisified + * satisfied */ required_kernelcore -= min(required_kernelcore, size_pages); @@ -5061,7 +5126,7 @@ restart: * If there is still required_kernelcore, we do another pass with one * less node in the count. This will push zone_movable_pfn[nid] further * along on the nodes that still have memory until kernelcore is - * satisified + * satisfied */ usable_nodes--; if (usable_nodes && required_kernelcore > usable_nodes) @@ -5087,7 +5152,7 @@ static void check_for_memory(pg_data_t *pgdat, int nid) for (zone_type = 0; zone_type <= ZONE_MOVABLE - 1; zone_type++) { struct zone *zone = &pgdat->node_zones[zone_type]; - if (zone->present_pages) { + if (populated_zone(zone)) { node_set_state(nid, N_HIGH_MEMORY); if (N_NORMAL_MEMORY != N_HIGH_MEMORY && zone_type <= ZONE_NORMAL) @@ -5286,8 +5351,10 @@ void __init mem_init_print_info(const char *str) * 3) .rodata.* may be embedded into .text or .data sections. */ #define adj_init_size(start, end, size, pos, adj) \ - if (start <= pos && pos < end && size > adj) \ - size -= adj; + do { \ + if (start <= pos && pos < end && size > adj) \ + size -= adj; \ + } while (0) adj_init_size(__init_begin, __init_end, init_data_size, _sinittext, init_code_size); @@ -5361,7 +5428,7 @@ static int page_alloc_cpu_notify(struct notifier_block *self, * This is only okay since the processor is dead and cannot * race with what we are doing. */ - refresh_cpu_vm_stats(cpu); + cpu_vm_stats_fold(cpu); } return NOTIFY_OK; } @@ -5498,6 +5565,11 @@ static void __setup_per_zone_wmarks(void) zone->watermark[WMARK_LOW] = min_wmark_pages(zone) + (tmp >> 2); zone->watermark[WMARK_HIGH] = min_wmark_pages(zone) + (tmp >> 1); + __mod_zone_page_state(zone, NR_ALLOC_BATCH, + high_wmark_pages(zone) - + low_wmark_pages(zone) - + zone_page_state(zone, NR_ALLOC_BATCH)); + setup_zone_migrate_reserve(zone); spin_unlock_irqrestore(&zone->lock, flags); } @@ -5570,7 +5642,7 @@ static void __meminit setup_per_zone_inactive_ratio(void) * we want it large (64MB max). But it is not linear, because network * bandwidth does not increase linearly with machine size. We use * - * min_free_kbytes = 4 * sqrt(lowmem_kbytes), for better accuracy: + * min_free_kbytes = 4 * sqrt(lowmem_kbytes), for better accuracy: * min_free_kbytes = sqrt(lowmem_kbytes * 16) * * which yields @@ -5614,11 +5686,11 @@ int __meminit init_per_zone_wmark_min(void) module_init(init_per_zone_wmark_min) /* - * min_free_kbytes_sysctl_handler - just a wrapper around proc_dointvec() so + * min_free_kbytes_sysctl_handler - just a wrapper around proc_dointvec() so * that we can call two helper functions whenever min_free_kbytes * changes. */ -int min_free_kbytes_sysctl_handler(ctl_table *table, int write, +int min_free_kbytes_sysctl_handler(ctl_table *table, int write, void __user *buffer, size_t *length, loff_t *ppos) { proc_dointvec(table, write, buffer, length, ppos); @@ -5682,8 +5754,8 @@ int lowmem_reserve_ratio_sysctl_handler(ctl_table *table, int write, /* * percpu_pagelist_fraction - changes the pcp->high for each zone on each - * cpu. It is the fraction of total pages in each zone that a hot per cpu pagelist - * can have before it gets flushed back to buddy allocator. + * cpu. It is the fraction of total pages in each zone that a hot per cpu + * pagelist can have before it gets flushed back to buddy allocator. */ int percpu_pagelist_fraction_sysctl_handler(ctl_table *table, int write, void __user *buffer, size_t *length, loff_t *ppos) @@ -5745,9 +5817,10 @@ void *__init alloc_large_system_hash(const char *tablename, if (!numentries) { /* round applicable memory size up to nearest megabyte */ numentries = nr_kernel_pages; - numentries += (1UL << (20 - PAGE_SHIFT)) - 1; - numentries >>= 20 - PAGE_SHIFT; - numentries <<= 20 - PAGE_SHIFT; + + /* It isn't necessary when PAGE_SIZE >= 1MB */ + if (PAGE_SHIFT < 20) + numentries = round_up(numentries, (1<<20)/PAGE_SIZE); /* limit to 1 bucket per 2^scale bytes of low memory */ if (scale > PAGE_SHIFT) @@ -5900,7 +5973,7 @@ void set_pageblock_flags_group(struct page *page, unsigned long flags, * 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 + * PageLRU check without 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. */ @@ -5928,6 +6001,17 @@ bool has_unmovable_pages(struct zone *zone, struct page *page, int count, continue; page = pfn_to_page(check); + + /* + * Hugepages are not in LRU lists, but they're movable. + * We need not scan over tail pages bacause we don't + * handle each tail page individually in migration. + */ + if (PageHuge(page)) { + iter = round_up(iter + 1, 1<<compound_order(page)) - 1; + continue; + } + /* * We can't use page_count without pin a page * because another CPU can free compound page. @@ -6274,10 +6358,6 @@ __offline_isolated_pages(unsigned long start_pfn, unsigned long end_pfn) list_del(&page->lru); rmv_page_order(page); zone->free_area[order].nr_free--; -#ifdef CONFIG_HIGHMEM - if (PageHighMem(page)) - totalhigh_pages -= 1 << order; -#endif for (i = 0; i < (1 << order); i++) SetPageReserved((page+i)); pfn += (1 << order); diff --git a/mm/page_io.c b/mm/page_io.c index ba05b64e5d8d..8c79a4764be0 100644 --- a/mm/page_io.c +++ b/mm/page_io.c @@ -266,7 +266,6 @@ int __swap_writepage(struct page *page, struct writeback_control *wbc, init_sync_kiocb(&kiocb, swap_file); kiocb.ki_pos = page_file_offset(page); - kiocb.ki_left = PAGE_SIZE; kiocb.ki_nbytes = PAGE_SIZE; set_page_writeback(page); diff --git a/mm/page_isolation.c b/mm/page_isolation.c index 0cee10ffb98d..d1473b2e9481 100644 --- a/mm/page_isolation.c +++ b/mm/page_isolation.c @@ -6,6 +6,7 @@ #include <linux/page-isolation.h> #include <linux/pageblock-flags.h> #include <linux/memory.h> +#include <linux/hugetlb.h> #include "internal.h" int set_migratetype_isolate(struct page *page, bool skip_hwpoisoned_pages) @@ -252,6 +253,19 @@ struct page *alloc_migrate_target(struct page *page, unsigned long private, { gfp_t gfp_mask = GFP_USER | __GFP_MOVABLE; + /* + * TODO: allocate a destination hugepage from a nearest neighbor node, + * accordance with memory policy of the user process if possible. For + * now as a simple work-around, we use the next node for destination. + */ + if (PageHuge(page)) { + nodemask_t src = nodemask_of_node(page_to_nid(page)); + nodemask_t dst; + nodes_complement(dst, src); + return alloc_huge_page_node(page_hstate(compound_head(page)), + next_node(page_to_nid(page), dst)); + } + if (PageHighMem(page)) gfp_mask |= __GFP_HIGHMEM; diff --git a/mm/pagewalk.c b/mm/pagewalk.c index 5da2cbcfdbb5..2beeabf502c5 100644 --- a/mm/pagewalk.c +++ b/mm/pagewalk.c @@ -242,7 +242,7 @@ int walk_page_range(unsigned long addr, unsigned long end, if (err) break; pgd++; - } while (addr = next, addr != end); + } while (addr = next, addr < end); return err; } diff --git a/mm/percpu.c b/mm/percpu.c index 8c8e08f3a692..0d10defe951e 100644 --- a/mm/percpu.c +++ b/mm/percpu.c @@ -1706,8 +1706,9 @@ int __init pcpu_embed_first_chunk(size_t reserved_size, size_t dyn_size, out_free_areas: for (group = 0; group < ai->nr_groups; group++) - free_fn(areas[group], - ai->groups[group].nr_units * ai->unit_size); + if (areas[group]) + free_fn(areas[group], + ai->groups[group].nr_units * ai->unit_size); out_free: pcpu_free_alloc_info(ai); if (areas) diff --git a/mm/pgtable-generic.c b/mm/pgtable-generic.c index e1a6e4fab016..cbb38545d9d6 100644 --- a/mm/pgtable-generic.c +++ b/mm/pgtable-generic.c @@ -10,6 +10,30 @@ #include <asm/tlb.h> #include <asm-generic/pgtable.h> +/* + * If a p?d_bad entry is found while walking page tables, report + * the error, before resetting entry to p?d_none. Usually (but + * very seldom) called out from the p?d_none_or_clear_bad macros. + */ + +void pgd_clear_bad(pgd_t *pgd) +{ + pgd_ERROR(*pgd); + pgd_clear(pgd); +} + +void pud_clear_bad(pud_t *pud) +{ + pud_ERROR(*pud); + pud_clear(pud); +} + +void pmd_clear_bad(pmd_t *pmd) +{ + pmd_ERROR(*pmd); + pmd_clear(pmd); +} + #ifndef __HAVE_ARCH_PTEP_SET_ACCESS_FLAGS /* * Only sets the access flags (dirty, accessed), as well as write @@ -127,14 +151,14 @@ void pmdp_splitting_flush(struct vm_area_struct *vma, unsigned long address, void pgtable_trans_huge_deposit(struct mm_struct *mm, pmd_t *pmdp, pgtable_t pgtable) { - assert_spin_locked(&mm->page_table_lock); + assert_spin_locked(pmd_lockptr(mm, pmdp)); /* FIFO */ - if (!mm->pmd_huge_pte) + if (!pmd_huge_pte(mm, pmdp)) INIT_LIST_HEAD(&pgtable->lru); else - list_add(&pgtable->lru, &mm->pmd_huge_pte->lru); - mm->pmd_huge_pte = pgtable; + list_add(&pgtable->lru, &pmd_huge_pte(mm, pmdp)->lru); + pmd_huge_pte(mm, pmdp) = pgtable; } #endif /* CONFIG_TRANSPARENT_HUGEPAGE */ #endif @@ -146,14 +170,14 @@ pgtable_t pgtable_trans_huge_withdraw(struct mm_struct *mm, pmd_t *pmdp) { pgtable_t pgtable; - assert_spin_locked(&mm->page_table_lock); + assert_spin_locked(pmd_lockptr(mm, pmdp)); /* FIFO */ - pgtable = mm->pmd_huge_pte; + pgtable = pmd_huge_pte(mm, pmdp); if (list_empty(&pgtable->lru)) - mm->pmd_huge_pte = NULL; + pmd_huge_pte(mm, pmdp) = NULL; else { - mm->pmd_huge_pte = list_entry(pgtable->lru.next, + pmd_huge_pte(mm, pmdp) = list_entry(pgtable->lru.next, struct page, lru); list_del(&pgtable->lru); } diff --git a/mm/readahead.c b/mm/readahead.c index 829a77c62834..7cdbb44aa90b 100644 --- a/mm/readahead.c +++ b/mm/readahead.c @@ -371,10 +371,10 @@ static int try_context_readahead(struct address_space *mapping, size = count_history_pages(mapping, ra, offset, max); /* - * no history pages: + * not enough history pages: * it could be a random read */ - if (!size) + if (size <= req_size) return 0; /* @@ -385,8 +385,8 @@ static int try_context_readahead(struct address_space *mapping, size *= 2; ra->start = offset; - ra->size = get_init_ra_size(size + req_size, max); - ra->async_size = ra->size; + ra->size = min(size + req_size, max); + ra->async_size = 1; return 1; } @@ -401,6 +401,7 @@ ondemand_readahead(struct address_space *mapping, unsigned long req_size) { unsigned long max = max_sane_readahead(ra->ra_pages); + pgoff_t prev_offset; /* * start of file @@ -452,8 +453,11 @@ ondemand_readahead(struct address_space *mapping, /* * sequential cache miss + * trivial case: (offset - prev_offset) == 1 + * unaligned reads: (offset - prev_offset) == 0 */ - if (offset - (ra->prev_pos >> PAGE_CACHE_SHIFT) <= 1UL) + prev_offset = (unsigned long long)ra->prev_pos >> PAGE_CACHE_SHIFT; + if (offset - prev_offset <= 1UL) goto initial_readahead; /* @@ -569,7 +573,7 @@ static ssize_t do_readahead(struct address_space *mapping, struct file *filp, pgoff_t index, unsigned long nr) { - if (!mapping || !mapping->a_ops || !mapping->a_ops->readpage) + if (!mapping || !mapping->a_ops) return -EINVAL; force_page_cache_readahead(mapping, filp, index, nr); diff --git a/mm/rmap.c b/mm/rmap.c index 07748e68b729..55c8b8dc9ffb 100644 --- a/mm/rmap.c +++ b/mm/rmap.c @@ -601,7 +601,7 @@ pte_t *__page_check_address(struct page *page, struct mm_struct *mm, if (unlikely(PageHuge(page))) { pte = huge_pte_offset(mm, address); - ptl = &mm->page_table_lock; + ptl = huge_pte_lockptr(page_hstate(page), mm, pte); goto check; } @@ -665,25 +665,23 @@ int page_referenced_one(struct page *page, struct vm_area_struct *vma, unsigned long *vm_flags) { struct mm_struct *mm = vma->vm_mm; + spinlock_t *ptl; int referenced = 0; if (unlikely(PageTransHuge(page))) { pmd_t *pmd; - spin_lock(&mm->page_table_lock); /* * rmap might return false positives; we must filter * these out using page_check_address_pmd(). */ pmd = page_check_address_pmd(page, mm, address, - PAGE_CHECK_ADDRESS_PMD_FLAG); - if (!pmd) { - spin_unlock(&mm->page_table_lock); + PAGE_CHECK_ADDRESS_PMD_FLAG, &ptl); + if (!pmd) goto out; - } if (vma->vm_flags & VM_LOCKED) { - spin_unlock(&mm->page_table_lock); + spin_unlock(ptl); *mapcount = 0; /* break early from loop */ *vm_flags |= VM_LOCKED; goto out; @@ -692,10 +690,9 @@ int page_referenced_one(struct page *page, struct vm_area_struct *vma, /* go ahead even if the pmd is pmd_trans_splitting() */ if (pmdp_clear_flush_young_notify(vma, address, pmd)) referenced++; - spin_unlock(&mm->page_table_lock); + spin_unlock(ptl); } else { pte_t *pte; - spinlock_t *ptl; /* * rmap might return false positives; we must filter @@ -1052,11 +1049,11 @@ void do_page_add_anon_rmap(struct page *page, { int first = atomic_inc_and_test(&page->_mapcount); if (first) { - if (!PageTransHuge(page)) - __inc_zone_page_state(page, NR_ANON_PAGES); - else + if (PageTransHuge(page)) __inc_zone_page_state(page, NR_ANON_TRANSPARENT_HUGEPAGES); + __mod_zone_page_state(page_zone(page), NR_ANON_PAGES, + hpage_nr_pages(page)); } if (unlikely(PageKsm(page))) return; @@ -1085,10 +1082,10 @@ void page_add_new_anon_rmap(struct page *page, VM_BUG_ON(address < vma->vm_start || address >= vma->vm_end); SetPageSwapBacked(page); atomic_set(&page->_mapcount, 0); /* increment count (starts at -1) */ - if (!PageTransHuge(page)) - __inc_zone_page_state(page, NR_ANON_PAGES); - else + if (PageTransHuge(page)) __inc_zone_page_state(page, NR_ANON_TRANSPARENT_HUGEPAGES); + __mod_zone_page_state(page_zone(page), NR_ANON_PAGES, + hpage_nr_pages(page)); __page_set_anon_rmap(page, vma, address, 1); if (!mlocked_vma_newpage(vma, page)) { SetPageActive(page); @@ -1111,7 +1108,7 @@ void page_add_file_rmap(struct page *page) mem_cgroup_begin_update_page_stat(page, &locked, &flags); if (atomic_inc_and_test(&page->_mapcount)) { __inc_zone_page_state(page, NR_FILE_MAPPED); - mem_cgroup_inc_page_stat(page, MEMCG_NR_FILE_MAPPED); + mem_cgroup_inc_page_stat(page, MEM_CGROUP_STAT_FILE_MAPPED); } mem_cgroup_end_update_page_stat(page, &locked, &flags); } @@ -1148,14 +1145,14 @@ void page_remove_rmap(struct page *page) goto out; if (anon) { mem_cgroup_uncharge_page(page); - if (!PageTransHuge(page)) - __dec_zone_page_state(page, NR_ANON_PAGES); - else + if (PageTransHuge(page)) __dec_zone_page_state(page, NR_ANON_TRANSPARENT_HUGEPAGES); + __mod_zone_page_state(page_zone(page), NR_ANON_PAGES, + -hpage_nr_pages(page)); } else { __dec_zone_page_state(page, NR_FILE_MAPPED); - mem_cgroup_dec_page_stat(page, MEMCG_NR_FILE_MAPPED); + mem_cgroup_dec_page_stat(page, MEM_CGROUP_STAT_FILE_MAPPED); mem_cgroup_end_update_page_stat(page, &locked, &flags); } if (unlikely(PageMlocked(page))) diff --git a/mm/shmem.c b/mm/shmem.c index 526149846d0a..8297623fcaed 100644 --- a/mm/shmem.c +++ b/mm/shmem.c @@ -1205,7 +1205,7 @@ repeat: gfp & GFP_RECLAIM_MASK); if (error) goto decused; - error = radix_tree_preload(gfp & GFP_RECLAIM_MASK); + error = radix_tree_maybe_preload(gfp & GFP_RECLAIM_MASK); if (!error) { error = shmem_add_to_page_cache(page, mapping, index, gfp, NULL); @@ -2819,6 +2819,10 @@ int __init shmem_init(void) { int error; + /* If rootfs called this, don't re-init */ + if (shmem_inode_cachep) + return 0; + error = bdi_init(&shmem_backing_dev_info); if (error) goto out4; diff --git a/mm/slab.c b/mm/slab.c index 2580db062df9..0c8967bb2018 100644 --- a/mm/slab.c +++ b/mm/slab.c @@ -3982,7 +3982,7 @@ static int do_tune_cpucache(struct kmem_cache *cachep, int limit, VM_BUG_ON(!mutex_is_locked(&slab_mutex)); for_each_memcg_cache_index(i) { - c = cache_from_memcg(cachep, i); + c = cache_from_memcg_idx(cachep, i); if (c) /* return value determined by the parent cache only */ __do_tune_cpucache(c, limit, batchcount, shared, gfp); diff --git a/mm/slab.h b/mm/slab.h index a535033f7e9a..0859c4241ba1 100644 --- a/mm/slab.h +++ b/mm/slab.h @@ -160,7 +160,8 @@ static inline const char *cache_name(struct kmem_cache *s) return s->name; } -static inline struct kmem_cache *cache_from_memcg(struct kmem_cache *s, int idx) +static inline struct kmem_cache * +cache_from_memcg_idx(struct kmem_cache *s, int idx) { if (!s->memcg_params) return NULL; @@ -204,7 +205,8 @@ static inline const char *cache_name(struct kmem_cache *s) return s->name; } -static inline struct kmem_cache *cache_from_memcg(struct kmem_cache *s, int idx) +static inline struct kmem_cache * +cache_from_memcg_idx(struct kmem_cache *s, int idx) { return NULL; } diff --git a/mm/slab_common.c b/mm/slab_common.c index 538bade6df7d..0b7bb399b0e4 100644 --- a/mm/slab_common.c +++ b/mm/slab_common.c @@ -19,6 +19,7 @@ #include <asm/tlbflush.h> #include <asm/page.h> #include <linux/memcontrol.h> +#include <trace/events/kmem.h> #include "slab.h" @@ -55,6 +56,7 @@ static int kmem_cache_sanity_check(struct mem_cgroup *memcg, const char *name, continue; } +#if !defined(CONFIG_SLUB) || !defined(CONFIG_SLUB_DEBUG_ON) /* * For simplicity, we won't check this in the list of memcg * caches. We have control over memcg naming, and if there @@ -68,6 +70,7 @@ static int kmem_cache_sanity_check(struct mem_cgroup *memcg, const char *name, s = NULL; return -EINVAL; } +#endif } WARN_ON(strchr(name, ' ')); /* It confuses parsers */ @@ -373,7 +376,7 @@ struct kmem_cache *kmalloc_slab(size_t size, gfp_t flags) { int index; - if (size > KMALLOC_MAX_SIZE) { + if (unlikely(size > KMALLOC_MAX_SIZE)) { WARN_ON_ONCE(!(flags & __GFP_NOWARN)); return NULL; } @@ -495,6 +498,15 @@ void __init create_kmalloc_caches(unsigned long flags) } #endif /* !CONFIG_SLOB */ +#ifdef CONFIG_TRACING +void *kmalloc_order_trace(size_t size, gfp_t flags, unsigned int order) +{ + void *ret = kmalloc_order(size, flags, order); + trace_kmalloc(_RET_IP_, ret, size, PAGE_SIZE << order, flags); + return ret; +} +EXPORT_SYMBOL(kmalloc_order_trace); +#endif #ifdef CONFIG_SLABINFO @@ -559,7 +571,7 @@ memcg_accumulate_slabinfo(struct kmem_cache *s, struct slabinfo *info) return; for_each_memcg_cache_index(i) { - c = cache_from_memcg(s, i); + c = cache_from_memcg_idx(s, i); if (!c) continue; diff --git a/mm/slob.c b/mm/slob.c index 91bd3f2dd2f0..4bf8809dfcce 100644 --- a/mm/slob.c +++ b/mm/slob.c @@ -462,11 +462,11 @@ __do_kmalloc_node(size_t size, gfp_t gfp, int node, unsigned long caller) return ret; } -void *__kmalloc_node(size_t size, gfp_t gfp, int node) +void *__kmalloc(size_t size, gfp_t gfp) { - return __do_kmalloc_node(size, gfp, node, _RET_IP_); + return __do_kmalloc_node(size, gfp, NUMA_NO_NODE, _RET_IP_); } -EXPORT_SYMBOL(__kmalloc_node); +EXPORT_SYMBOL(__kmalloc); #ifdef CONFIG_TRACING void *__kmalloc_track_caller(size_t size, gfp_t gfp, unsigned long caller) @@ -534,7 +534,7 @@ int __kmem_cache_create(struct kmem_cache *c, unsigned long flags) return 0; } -void *kmem_cache_alloc_node(struct kmem_cache *c, gfp_t flags, int node) +void *slob_alloc_node(struct kmem_cache *c, gfp_t flags, int node) { void *b; @@ -560,7 +560,27 @@ void *kmem_cache_alloc_node(struct kmem_cache *c, gfp_t flags, int node) kmemleak_alloc_recursive(b, c->size, 1, c->flags, flags); return b; } +EXPORT_SYMBOL(slob_alloc_node); + +void *kmem_cache_alloc(struct kmem_cache *cachep, gfp_t flags) +{ + return slob_alloc_node(cachep, flags, NUMA_NO_NODE); +} +EXPORT_SYMBOL(kmem_cache_alloc); + +#ifdef CONFIG_NUMA +void *__kmalloc_node(size_t size, gfp_t gfp, int node) +{ + return __do_kmalloc_node(size, gfp, node, _RET_IP_); +} +EXPORT_SYMBOL(__kmalloc_node); + +void *kmem_cache_alloc_node(struct kmem_cache *cachep, gfp_t gfp, int node) +{ + return slob_alloc_node(cachep, gfp, node); +} EXPORT_SYMBOL(kmem_cache_alloc_node); +#endif static void __kmem_cache_free(void *b, int size) { diff --git a/mm/slub.c b/mm/slub.c index 6a2fa986e7a7..7e8bd8d828bc 100644 --- a/mm/slub.c +++ b/mm/slub.c @@ -373,7 +373,8 @@ static inline bool __cmpxchg_double_slab(struct kmem_cache *s, struct page *page #endif { slab_lock(page); - if (page->freelist == freelist_old && page->counters == counters_old) { + if (page->freelist == freelist_old && + page->counters == counters_old) { page->freelist = freelist_new; page->counters = counters_new; slab_unlock(page); @@ -411,7 +412,8 @@ static inline bool cmpxchg_double_slab(struct kmem_cache *s, struct page *page, local_irq_save(flags); slab_lock(page); - if (page->freelist == freelist_old && page->counters == counters_old) { + if (page->freelist == freelist_old && + page->counters == counters_old) { page->freelist = freelist_new; page->counters = counters_new; slab_unlock(page); @@ -553,8 +555,9 @@ static void print_tracking(struct kmem_cache *s, void *object) static void print_page_info(struct page *page) { - printk(KERN_ERR "INFO: Slab 0x%p objects=%u used=%u fp=0x%p flags=0x%04lx\n", - page, page->objects, page->inuse, page->freelist, page->flags); + printk(KERN_ERR + "INFO: Slab 0x%p objects=%u used=%u fp=0x%p flags=0x%04lx\n", + page, page->objects, page->inuse, page->freelist, page->flags); } @@ -629,7 +632,8 @@ static void object_err(struct kmem_cache *s, struct page *page, print_trailer(s, page, object); } -static void slab_err(struct kmem_cache *s, struct page *page, const char *fmt, ...) +static void slab_err(struct kmem_cache *s, struct page *page, + const char *fmt, ...) { va_list args; char buf[100]; @@ -788,7 +792,8 @@ static int check_object(struct kmem_cache *s, struct page *page, } else { if ((s->flags & SLAB_POISON) && s->object_size < s->inuse) { check_bytes_and_report(s, page, p, "Alignment padding", - endobject, POISON_INUSE, s->inuse - s->object_size); + endobject, POISON_INUSE, + s->inuse - s->object_size); } } @@ -873,7 +878,6 @@ static int on_freelist(struct kmem_cache *s, struct page *page, void *search) object_err(s, page, object, "Freechain corrupt"); set_freepointer(s, object, NULL); - break; } else { slab_err(s, page, "Freepointer corrupt"); page->freelist = NULL; @@ -918,7 +922,8 @@ static void trace(struct kmem_cache *s, struct page *page, void *object, page->freelist); if (!alloc) - print_section("Object ", (void *)object, s->object_size); + print_section("Object ", (void *)object, + s->object_size); dump_stack(); } @@ -937,7 +942,8 @@ static inline int slab_pre_alloc_hook(struct kmem_cache *s, gfp_t flags) return should_failslab(s->object_size, flags, s->flags); } -static inline void slab_post_alloc_hook(struct kmem_cache *s, gfp_t flags, void *object) +static inline void slab_post_alloc_hook(struct kmem_cache *s, + gfp_t flags, void *object) { flags &= gfp_allowed_mask; kmemcheck_slab_alloc(s, flags, object, slab_ksize(s)); @@ -1039,7 +1045,8 @@ static void setup_object_debug(struct kmem_cache *s, struct page *page, init_tracking(s, object); } -static noinline int alloc_debug_processing(struct kmem_cache *s, struct page *page, +static noinline int alloc_debug_processing(struct kmem_cache *s, + struct page *page, void *object, unsigned long addr) { if (!check_slab(s, page)) @@ -1743,7 +1750,8 @@ static void init_kmem_cache_cpus(struct kmem_cache *s) /* * Remove the cpu slab */ -static void deactivate_slab(struct kmem_cache *s, struct page *page, void *freelist) +static void deactivate_slab(struct kmem_cache *s, struct page *page, + void *freelist) { enum slab_modes { M_NONE, M_PARTIAL, M_FULL, M_FREE }; struct kmem_cache_node *n = get_node(s, page_to_nid(page)); @@ -1999,7 +2007,8 @@ static void put_cpu_partial(struct kmem_cache *s, struct page *page, int drain) page->pobjects = pobjects; page->next = oldpage; - } while (this_cpu_cmpxchg(s->cpu_slab->partial, oldpage, page) != oldpage); + } while (this_cpu_cmpxchg(s->cpu_slab->partial, oldpage, page) + != oldpage); #endif } @@ -2169,8 +2178,8 @@ static inline bool pfmemalloc_match(struct page *page, gfp_t gfpflags) } /* - * Check the page->freelist of a page and either transfer the freelist to the per cpu freelist - * or deactivate the page. + * Check the page->freelist of a page and either transfer the freelist to the + * per cpu freelist or deactivate the page. * * The page is still frozen if the return value is not NULL. * @@ -2314,7 +2323,8 @@ new_slab: goto load_freelist; /* Only entered in the debug case */ - if (kmem_cache_debug(s) && !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)); @@ -2372,7 +2382,7 @@ redo: object = c->freelist; page = c->page; - if (unlikely(!object || !page || !node_match(page, node))) + if (unlikely(!object || !node_match(page, node))) object = __slab_alloc(s, gfpflags, node, addr, c); else { @@ -2382,13 +2392,15 @@ redo: * The cmpxchg will only match if there was no additional * operation and if we are on the right processor. * - * The cmpxchg does the following atomically (without lock semantics!) + * The cmpxchg does the following atomically (without lock + * semantics!) * 1. Relocate first pointer to the current per cpu area. * 2. Verify that tid and freelist have not been changed * 3. If they were not changed replace tid and freelist * - * Since this is without lock semantics the protection is only against - * code executing on this cpu *not* from access by other cpus. + * Since this is without lock semantics the protection is only + * against code executing on this cpu *not* from access by + * other cpus. */ if (unlikely(!this_cpu_cmpxchg_double( s->cpu_slab->freelist, s->cpu_slab->tid, @@ -2420,7 +2432,8 @@ void *kmem_cache_alloc(struct kmem_cache *s, gfp_t gfpflags) { void *ret = slab_alloc(s, gfpflags, _RET_IP_); - trace_kmem_cache_alloc(_RET_IP_, ret, s->object_size, s->size, gfpflags); + trace_kmem_cache_alloc(_RET_IP_, ret, s->object_size, + s->size, gfpflags); return ret; } @@ -2434,14 +2447,6 @@ void *kmem_cache_alloc_trace(struct kmem_cache *s, gfp_t gfpflags, size_t size) return ret; } EXPORT_SYMBOL(kmem_cache_alloc_trace); - -void *kmalloc_order_trace(size_t size, gfp_t flags, unsigned int order) -{ - void *ret = kmalloc_order(size, flags, order); - trace_kmalloc(_RET_IP_, ret, size, PAGE_SIZE << order, flags); - return ret; -} -EXPORT_SYMBOL(kmalloc_order_trace); #endif #ifdef CONFIG_NUMA @@ -2512,8 +2517,10 @@ static void __slab_free(struct kmem_cache *s, struct page *page, if (kmem_cache_has_cpu_partial(s) && !prior) /* - * Slab was on no list before and will be partially empty - * We can defer the list move and instead freeze it. + * Slab was on no list before and will be + * partially empty + * We can defer the list move and instead + * freeze it. */ new.frozen = 1; @@ -3071,8 +3078,8 @@ static int kmem_cache_open(struct kmem_cache *s, unsigned long flags) * A) The number of objects from per cpu partial slabs dumped to the * per node list when we reach the limit. * B) The number of objects in cpu partial slabs to extract from the - * per node list when we run out of per cpu objects. We only fetch 50% - * to keep some capacity around for frees. + * per node list when we run out of per cpu objects. We only fetch + * 50% to keep some capacity around for frees. */ if (!kmem_cache_has_cpu_partial(s)) s->cpu_partial = 0; @@ -3099,8 +3106,8 @@ error: if (flags & SLAB_PANIC) panic("Cannot create slab %s size=%lu realsize=%u " "order=%u offset=%u flags=%lx\n", - s->name, (unsigned long)s->size, s->size, oo_order(s->oo), - s->offset, flags); + s->name, (unsigned long)s->size, s->size, + oo_order(s->oo), s->offset, flags); return -EINVAL; } @@ -3316,42 +3323,6 @@ size_t ksize(const void *object) } EXPORT_SYMBOL(ksize); -#ifdef CONFIG_SLUB_DEBUG -bool verify_mem_not_deleted(const void *x) -{ - struct page *page; - void *object = (void *)x; - unsigned long flags; - bool rv; - - if (unlikely(ZERO_OR_NULL_PTR(x))) - return false; - - local_irq_save(flags); - - page = virt_to_head_page(x); - if (unlikely(!PageSlab(page))) { - /* maybe it was from stack? */ - rv = true; - goto out_unlock; - } - - slab_lock(page); - if (on_freelist(page->slab_cache, page, object)) { - object_err(page->slab_cache, page, object, "Object is on free-list"); - rv = false; - } else { - rv = true; - } - slab_unlock(page); - -out_unlock: - local_irq_restore(flags); - return rv; -} -EXPORT_SYMBOL(verify_mem_not_deleted); -#endif - void kfree(const void *x) { struct page *page; @@ -4162,15 +4133,17 @@ static int list_locations(struct kmem_cache *s, char *buf, !cpumask_empty(to_cpumask(l->cpus)) && len < PAGE_SIZE - 60) { len += sprintf(buf + len, " cpus="); - len += cpulist_scnprintf(buf + len, PAGE_SIZE - len - 50, + len += cpulist_scnprintf(buf + len, + PAGE_SIZE - len - 50, to_cpumask(l->cpus)); } if (nr_online_nodes > 1 && !nodes_empty(l->nodes) && len < PAGE_SIZE - 60) { len += sprintf(buf + len, " nodes="); - len += nodelist_scnprintf(buf + len, PAGE_SIZE - len - 50, - l->nodes); + len += nodelist_scnprintf(buf + len, + PAGE_SIZE - len - 50, + l->nodes); } len += sprintf(buf + len, "\n"); @@ -4268,18 +4241,17 @@ static ssize_t show_slab_objects(struct kmem_cache *s, int node; int x; unsigned long *nodes; - unsigned long *per_cpu; - nodes = kzalloc(2 * sizeof(unsigned long) * nr_node_ids, GFP_KERNEL); + nodes = kzalloc(sizeof(unsigned long) * nr_node_ids, GFP_KERNEL); if (!nodes) return -ENOMEM; - per_cpu = nodes + nr_node_ids; if (flags & SO_CPU) { int cpu; for_each_possible_cpu(cpu) { - struct kmem_cache_cpu *c = per_cpu_ptr(s->cpu_slab, cpu); + struct kmem_cache_cpu *c = per_cpu_ptr(s->cpu_slab, + cpu); int node; struct page *page; @@ -4304,8 +4276,6 @@ static ssize_t show_slab_objects(struct kmem_cache *s, total += x; nodes[node] += x; } - - per_cpu[node]++; } } @@ -4315,12 +4285,11 @@ static ssize_t show_slab_objects(struct kmem_cache *s, for_each_node_state(node, N_NORMAL_MEMORY) { struct kmem_cache_node *n = get_node(s, node); - if (flags & SO_TOTAL) - x = atomic_long_read(&n->total_objects); - else if (flags & SO_OBJECTS) - x = atomic_long_read(&n->total_objects) - - count_partial(n, count_free); - + if (flags & SO_TOTAL) + x = atomic_long_read(&n->total_objects); + else if (flags & SO_OBJECTS) + x = atomic_long_read(&n->total_objects) - + count_partial(n, count_free); else x = atomic_long_read(&n->nr_slabs); total += x; @@ -4420,7 +4389,7 @@ static ssize_t order_store(struct kmem_cache *s, unsigned long order; int err; - err = strict_strtoul(buf, 10, &order); + err = kstrtoul(buf, 10, &order); if (err) return err; @@ -4448,7 +4417,7 @@ static ssize_t min_partial_store(struct kmem_cache *s, const char *buf, unsigned long min; int err; - err = strict_strtoul(buf, 10, &min); + err = kstrtoul(buf, 10, &min); if (err) return err; @@ -4468,7 +4437,7 @@ static ssize_t cpu_partial_store(struct kmem_cache *s, const char *buf, unsigned long objects; int err; - err = strict_strtoul(buf, 10, &objects); + err = kstrtoul(buf, 10, &objects); if (err) return err; if (objects && !kmem_cache_has_cpu_partial(s)) @@ -4784,7 +4753,7 @@ static ssize_t remote_node_defrag_ratio_store(struct kmem_cache *s, unsigned long ratio; int err; - err = strict_strtoul(buf, 10, &ratio); + err = kstrtoul(buf, 10, &ratio); if (err) return err; @@ -5014,7 +4983,7 @@ static ssize_t slab_attr_store(struct kobject *kobj, * through the descendants with best-effort propagation. */ for_each_memcg_cache_index(i) { - struct kmem_cache *c = cache_from_memcg(s, i); + struct kmem_cache *c = cache_from_memcg_idx(s, i); if (c) attribute->store(c, buf, len); } @@ -5136,7 +5105,8 @@ static char *create_unique_id(struct kmem_cache *s) #ifdef CONFIG_MEMCG_KMEM if (!is_root_cache(s)) - p += sprintf(p, "-%08d", memcg_cache_id(s->memcg_params->memcg)); + p += sprintf(p, "-%08d", + memcg_cache_id(s->memcg_params->memcg)); #endif BUG_ON(p > name + ID_STR_LENGTH - 1); diff --git a/mm/sparse.c b/mm/sparse.c index 308d50331bc3..8cc7be0e9590 100644 --- a/mm/sparse.c +++ b/mm/sparse.c @@ -339,13 +339,14 @@ static void __init check_usemap_section_nr(int nid, unsigned long *usemap) } #endif /* CONFIG_MEMORY_HOTREMOVE */ -static void __init sparse_early_usemaps_alloc_node(unsigned long**usemap_map, +static void __init sparse_early_usemaps_alloc_node(void *data, unsigned long pnum_begin, unsigned long pnum_end, unsigned long usemap_count, int nodeid) { void *usemap; unsigned long pnum; + unsigned long **usemap_map = (unsigned long **)data; int size = usemap_size(); usemap = sparse_early_usemaps_alloc_pgdat_section(NODE_DATA(nodeid), @@ -430,11 +431,12 @@ void __init sparse_mem_maps_populate_node(struct page **map_map, #endif /* !CONFIG_SPARSEMEM_VMEMMAP */ #ifdef CONFIG_SPARSEMEM_ALLOC_MEM_MAP_TOGETHER -static void __init sparse_early_mem_maps_alloc_node(struct page **map_map, +static void __init sparse_early_mem_maps_alloc_node(void *data, unsigned long pnum_begin, unsigned long pnum_end, unsigned long map_count, int nodeid) { + struct page **map_map = (struct page **)data; sparse_mem_maps_populate_node(map_map, pnum_begin, pnum_end, map_count, nodeid); } @@ -460,6 +462,55 @@ void __attribute__((weak)) __meminit vmemmap_populate_print_last(void) { } +/** + * alloc_usemap_and_memmap - memory alloction for pageblock flags and vmemmap + * @map: usemap_map for pageblock flags or mmap_map for vmemmap + */ +static void __init alloc_usemap_and_memmap(void (*alloc_func) + (void *, unsigned long, unsigned long, + unsigned long, int), void *data) +{ + unsigned long pnum; + unsigned long map_count; + int nodeid_begin = 0; + unsigned long pnum_begin = 0; + + for (pnum = 0; pnum < NR_MEM_SECTIONS; pnum++) { + struct mem_section *ms; + + if (!present_section_nr(pnum)) + continue; + ms = __nr_to_section(pnum); + nodeid_begin = sparse_early_nid(ms); + pnum_begin = pnum; + break; + } + map_count = 1; + for (pnum = pnum_begin + 1; pnum < NR_MEM_SECTIONS; pnum++) { + struct mem_section *ms; + int nodeid; + + if (!present_section_nr(pnum)) + continue; + ms = __nr_to_section(pnum); + nodeid = sparse_early_nid(ms); + if (nodeid == nodeid_begin) { + map_count++; + continue; + } + /* ok, we need to take cake of from pnum_begin to pnum - 1*/ + alloc_func(data, pnum_begin, pnum, + map_count, nodeid_begin); + /* new start, update count etc*/ + nodeid_begin = nodeid; + pnum_begin = pnum; + map_count = 1; + } + /* ok, last chunk */ + alloc_func(data, pnum_begin, NR_MEM_SECTIONS, + map_count, nodeid_begin); +} + /* * Allocate the accumulated non-linear sections, allocate a mem_map * for each and record the physical to section mapping. @@ -471,11 +522,7 @@ void __init sparse_init(void) unsigned long *usemap; unsigned long **usemap_map; int size; - int nodeid_begin = 0; - unsigned long pnum_begin = 0; - unsigned long usemap_count; #ifdef CONFIG_SPARSEMEM_ALLOC_MEM_MAP_TOGETHER - unsigned long map_count; int size2; struct page **map_map; #endif @@ -501,82 +548,16 @@ void __init sparse_init(void) usemap_map = alloc_bootmem(size); if (!usemap_map) panic("can not allocate usemap_map\n"); - - for (pnum = 0; pnum < NR_MEM_SECTIONS; pnum++) { - struct mem_section *ms; - - if (!present_section_nr(pnum)) - continue; - ms = __nr_to_section(pnum); - nodeid_begin = sparse_early_nid(ms); - pnum_begin = pnum; - break; - } - usemap_count = 1; - for (pnum = pnum_begin + 1; pnum < NR_MEM_SECTIONS; pnum++) { - struct mem_section *ms; - int nodeid; - - if (!present_section_nr(pnum)) - continue; - ms = __nr_to_section(pnum); - nodeid = sparse_early_nid(ms); - if (nodeid == nodeid_begin) { - usemap_count++; - continue; - } - /* ok, we need to take cake of from pnum_begin to pnum - 1*/ - sparse_early_usemaps_alloc_node(usemap_map, pnum_begin, pnum, - usemap_count, nodeid_begin); - /* new start, update count etc*/ - nodeid_begin = nodeid; - pnum_begin = pnum; - usemap_count = 1; - } - /* ok, last chunk */ - sparse_early_usemaps_alloc_node(usemap_map, pnum_begin, NR_MEM_SECTIONS, - usemap_count, nodeid_begin); + alloc_usemap_and_memmap(sparse_early_usemaps_alloc_node, + (void *)usemap_map); #ifdef CONFIG_SPARSEMEM_ALLOC_MEM_MAP_TOGETHER size2 = sizeof(struct page *) * NR_MEM_SECTIONS; map_map = alloc_bootmem(size2); if (!map_map) panic("can not allocate map_map\n"); - - for (pnum = 0; pnum < NR_MEM_SECTIONS; pnum++) { - struct mem_section *ms; - - if (!present_section_nr(pnum)) - continue; - ms = __nr_to_section(pnum); - nodeid_begin = sparse_early_nid(ms); - pnum_begin = pnum; - break; - } - map_count = 1; - for (pnum = pnum_begin + 1; pnum < NR_MEM_SECTIONS; pnum++) { - struct mem_section *ms; - int nodeid; - - if (!present_section_nr(pnum)) - continue; - ms = __nr_to_section(pnum); - nodeid = sparse_early_nid(ms); - if (nodeid == nodeid_begin) { - map_count++; - continue; - } - /* ok, we need to take cake of from pnum_begin to pnum - 1*/ - sparse_early_mem_maps_alloc_node(map_map, pnum_begin, pnum, - map_count, nodeid_begin); - /* new start, update count etc*/ - nodeid_begin = nodeid; - pnum_begin = pnum; - map_count = 1; - } - /* ok, last chunk */ - sparse_early_mem_maps_alloc_node(map_map, pnum_begin, NR_MEM_SECTIONS, - map_count, nodeid_begin); + alloc_usemap_and_memmap(sparse_early_mem_maps_alloc_node, + (void *)map_map); #endif for (pnum = 0; pnum < NR_MEM_SECTIONS; pnum++) { @@ -609,33 +590,32 @@ void __init sparse_init(void) #ifdef CONFIG_MEMORY_HOTPLUG #ifdef CONFIG_SPARSEMEM_VMEMMAP -static inline struct page *kmalloc_section_memmap(unsigned long pnum, int nid, - unsigned long nr_pages) +static inline struct page *kmalloc_section_memmap(unsigned long pnum, int nid) { /* This will make the necessary allocations eventually. */ return sparse_mem_map_populate(pnum, nid); } -static void __kfree_section_memmap(struct page *memmap, unsigned long nr_pages) +static void __kfree_section_memmap(struct page *memmap) { unsigned long start = (unsigned long)memmap; - unsigned long end = (unsigned long)(memmap + nr_pages); + unsigned long end = (unsigned long)(memmap + PAGES_PER_SECTION); vmemmap_free(start, end); } #ifdef CONFIG_MEMORY_HOTREMOVE -static void free_map_bootmem(struct page *memmap, unsigned long nr_pages) +static void free_map_bootmem(struct page *memmap) { unsigned long start = (unsigned long)memmap; - unsigned long end = (unsigned long)(memmap + nr_pages); + unsigned long end = (unsigned long)(memmap + PAGES_PER_SECTION); vmemmap_free(start, end); } #endif /* CONFIG_MEMORY_HOTREMOVE */ #else -static struct page *__kmalloc_section_memmap(unsigned long nr_pages) +static struct page *__kmalloc_section_memmap(void) { struct page *page, *ret; - unsigned long memmap_size = sizeof(struct page) * nr_pages; + unsigned long memmap_size = sizeof(struct page) * PAGES_PER_SECTION; page = alloc_pages(GFP_KERNEL|__GFP_NOWARN, get_order(memmap_size)); if (page) @@ -653,28 +633,30 @@ got_map_ptr: return ret; } -static inline struct page *kmalloc_section_memmap(unsigned long pnum, int nid, - unsigned long nr_pages) +static inline struct page *kmalloc_section_memmap(unsigned long pnum, int nid) { - return __kmalloc_section_memmap(nr_pages); + return __kmalloc_section_memmap(); } -static void __kfree_section_memmap(struct page *memmap, unsigned long nr_pages) +static void __kfree_section_memmap(struct page *memmap) { if (is_vmalloc_addr(memmap)) vfree(memmap); else free_pages((unsigned long)memmap, - get_order(sizeof(struct page) * nr_pages)); + get_order(sizeof(struct page) * PAGES_PER_SECTION)); } #ifdef CONFIG_MEMORY_HOTREMOVE -static void free_map_bootmem(struct page *memmap, unsigned long nr_pages) +static void free_map_bootmem(struct page *memmap) { unsigned long maps_section_nr, removing_section_nr, i; - unsigned long magic; + unsigned long magic, nr_pages; struct page *page = virt_to_page(memmap); + nr_pages = PAGE_ALIGN(PAGES_PER_SECTION * sizeof(struct page)) + >> PAGE_SHIFT; + for (i = 0; i < nr_pages; i++, page++) { magic = (unsigned long) page->lru.next; @@ -703,8 +685,7 @@ static void free_map_bootmem(struct page *memmap, unsigned long nr_pages) * set. If this is <=0, then that means that the passed-in * map was not consumed and must be freed. */ -int __meminit sparse_add_one_section(struct zone *zone, unsigned long start_pfn, - int nr_pages) +int __meminit sparse_add_one_section(struct zone *zone, unsigned long start_pfn) { unsigned long section_nr = pfn_to_section_nr(start_pfn); struct pglist_data *pgdat = zone->zone_pgdat; @@ -721,12 +702,12 @@ int __meminit sparse_add_one_section(struct zone *zone, unsigned long start_pfn, ret = sparse_index_init(section_nr, pgdat->node_id); if (ret < 0 && ret != -EEXIST) return ret; - memmap = kmalloc_section_memmap(section_nr, pgdat->node_id, nr_pages); + memmap = kmalloc_section_memmap(section_nr, pgdat->node_id); if (!memmap) return -ENOMEM; usemap = __kmalloc_section_usemap(); if (!usemap) { - __kfree_section_memmap(memmap, nr_pages); + __kfree_section_memmap(memmap); return -ENOMEM; } @@ -738,7 +719,7 @@ int __meminit sparse_add_one_section(struct zone *zone, unsigned long start_pfn, goto out; } - memset(memmap, 0, sizeof(struct page) * nr_pages); + memset(memmap, 0, sizeof(struct page) * PAGES_PER_SECTION); ms->section_mem_map |= SECTION_MARKED_PRESENT; @@ -748,7 +729,7 @@ out: pgdat_resize_unlock(pgdat, &flags); if (ret <= 0) { kfree(usemap); - __kfree_section_memmap(memmap, nr_pages); + __kfree_section_memmap(memmap); } return ret; } @@ -778,7 +759,6 @@ static inline void clear_hwpoisoned_pages(struct page *memmap, int nr_pages) static void free_section_usemap(struct page *memmap, unsigned long *usemap) { struct page *usemap_page; - unsigned long nr_pages; if (!usemap) return; @@ -790,7 +770,7 @@ static void free_section_usemap(struct page *memmap, unsigned long *usemap) if (PageSlab(usemap_page) || PageCompound(usemap_page)) { kfree(usemap); if (memmap) - __kfree_section_memmap(memmap, PAGES_PER_SECTION); + __kfree_section_memmap(memmap); return; } @@ -799,12 +779,8 @@ static void free_section_usemap(struct page *memmap, unsigned long *usemap) * on the section which has pgdat at boot time. Just keep it as is now. */ - if (memmap) { - nr_pages = PAGE_ALIGN(PAGES_PER_SECTION * sizeof(struct page)) - >> PAGE_SHIFT; - - free_map_bootmem(memmap, nr_pages); - } + if (memmap) + free_map_bootmem(memmap); } void sparse_remove_one_section(struct zone *zone, struct mem_section *ms) diff --git a/mm/swap.c b/mm/swap.c index 62b78a6e224f..7a9f80d451f5 100644 --- a/mm/swap.c +++ b/mm/swap.c @@ -31,6 +31,7 @@ #include <linux/memcontrol.h> #include <linux/gfp.h> #include <linux/uio.h> +#include <linux/hugetlb.h> #include "internal.h" @@ -81,6 +82,19 @@ static void __put_compound_page(struct page *page) static void put_compound_page(struct page *page) { + /* + * hugetlbfs pages cannot be split from under us. If this is a + * hugetlbfs page, check refcount on head page and release the page if + * the refcount becomes zero. + */ + if (PageHuge(page)) { + page = compound_head(page); + if (put_page_testzero(page)) + __put_compound_page(page); + + return; + } + if (unlikely(PageTail(page))) { /* __split_huge_page_refcount can run under us */ struct page *page_head = compound_trans_head(page); @@ -184,38 +198,51 @@ bool __get_page_tail(struct page *page) * proper PT lock that already serializes against * split_huge_page(). */ - unsigned long flags; bool got = false; - struct page *page_head = compound_trans_head(page); + struct page *page_head; - if (likely(page != page_head && get_page_unless_zero(page_head))) { + /* + * If this is a hugetlbfs page it cannot be split under us. Simply + * increment refcount for the head page. + */ + if (PageHuge(page)) { + page_head = compound_head(page); + atomic_inc(&page_head->_count); + got = true; + } else { + unsigned long flags; - /* Ref to put_compound_page() comment. */ - if (PageSlab(page_head)) { + page_head = compound_trans_head(page); + if (likely(page != page_head && + get_page_unless_zero(page_head))) { + + /* Ref to put_compound_page() comment. */ + if (PageSlab(page_head)) { + if (likely(PageTail(page))) { + __get_page_tail_foll(page, false); + return true; + } else { + put_page(page_head); + return false; + } + } + + /* + * page_head wasn't a dangling pointer but it + * may not be a head page anymore by the time + * we obtain the lock. That is ok as long as it + * can't be freed from under us. + */ + flags = compound_lock_irqsave(page_head); + /* here __split_huge_page_refcount won't run anymore */ if (likely(PageTail(page))) { __get_page_tail_foll(page, false); - return true; - } else { - put_page(page_head); - return false; + got = true; } + compound_unlock_irqrestore(page_head, flags); + if (unlikely(!got)) + put_page(page_head); } - - /* - * page_head wasn't a dangling pointer but it - * may not be a head page anymore by the time - * we obtain the lock. That is ok as long as it - * can't be freed from under us. - */ - flags = compound_lock_irqsave(page_head); - /* here __split_huge_page_refcount won't run anymore */ - if (likely(PageTail(page))) { - __get_page_tail_foll(page, false); - got = true; - } - compound_unlock_irqrestore(page_head, flags); - if (unlikely(!got)) - put_page(page_head); } return got; } @@ -405,6 +432,11 @@ static void activate_page_drain(int cpu) pagevec_lru_move_fn(pvec, __activate_page, NULL); } +static bool need_activate_page_drain(int cpu) +{ + return pagevec_count(&per_cpu(activate_page_pvecs, cpu)) != 0; +} + void activate_page(struct page *page) { if (PageLRU(page) && !PageActive(page) && !PageUnevictable(page)) { @@ -422,6 +454,11 @@ static inline void activate_page_drain(int cpu) { } +static bool need_activate_page_drain(int cpu) +{ + return false; +} + void activate_page(struct page *page) { struct zone *zone = page_zone(page); @@ -674,12 +711,36 @@ static void lru_add_drain_per_cpu(struct work_struct *dummy) lru_add_drain(); } -/* - * Returns 0 for success - */ -int lru_add_drain_all(void) +static DEFINE_PER_CPU(struct work_struct, lru_add_drain_work); + +void lru_add_drain_all(void) { - return schedule_on_each_cpu(lru_add_drain_per_cpu); + static DEFINE_MUTEX(lock); + static struct cpumask has_work; + int cpu; + + mutex_lock(&lock); + get_online_cpus(); + cpumask_clear(&has_work); + + for_each_online_cpu(cpu) { + struct work_struct *work = &per_cpu(lru_add_drain_work, cpu); + + if (pagevec_count(&per_cpu(lru_add_pvec, cpu)) || + pagevec_count(&per_cpu(lru_rotate_pvecs, cpu)) || + pagevec_count(&per_cpu(lru_deactivate_pvecs, cpu)) || + need_activate_page_drain(cpu)) { + INIT_WORK(work, lru_add_drain_per_cpu); + schedule_work_on(cpu, work); + cpumask_set_cpu(cpu, &has_work); + } + } + + for_each_cpu(cpu, &has_work) + flush_work(&per_cpu(lru_add_drain_work, cpu)); + + put_online_cpus(); + mutex_unlock(&lock); } /* @@ -873,7 +934,8 @@ void __init swap_setup(void) #ifdef CONFIG_SWAP int i; - bdi_init(swapper_spaces[0].backing_dev_info); + if (bdi_init(swapper_spaces[0].backing_dev_info)) + panic("Failed to init swap bdi"); for (i = 0; i < MAX_SWAPFILES; i++) { spin_lock_init(&swapper_spaces[i].tree_lock); INIT_LIST_HEAD(&swapper_spaces[i].i_mmap_nonlinear); diff --git a/mm/swap_state.c b/mm/swap_state.c index f24ab0dff554..e6f15f8ca2af 100644 --- a/mm/swap_state.c +++ b/mm/swap_state.c @@ -122,7 +122,7 @@ int add_to_swap_cache(struct page *page, swp_entry_t entry, gfp_t gfp_mask) { int error; - error = radix_tree_preload(gfp_mask); + error = radix_tree_maybe_preload(gfp_mask); if (!error) { error = __add_to_swap_cache(page, entry); radix_tree_preload_end(); @@ -328,7 +328,7 @@ struct page *read_swap_cache_async(swp_entry_t entry, gfp_t gfp_mask, /* * call radix_tree_preload() while we can wait. */ - err = radix_tree_preload(gfp_mask & GFP_KERNEL); + err = radix_tree_maybe_preload(gfp_mask & GFP_KERNEL); if (err) break; diff --git a/mm/swapfile.c b/mm/swapfile.c index 6cf2e60983b7..612a7c9795f6 100644 --- a/mm/swapfile.c +++ b/mm/swapfile.c @@ -175,14 +175,296 @@ static void discard_swap_cluster(struct swap_info_struct *si, } } -static int wait_for_discard(void *word) +#define SWAPFILE_CLUSTER 256 +#define LATENCY_LIMIT 256 + +static inline void cluster_set_flag(struct swap_cluster_info *info, + unsigned int flag) { - schedule(); - return 0; + info->flags = flag; } -#define SWAPFILE_CLUSTER 256 -#define LATENCY_LIMIT 256 +static inline unsigned int cluster_count(struct swap_cluster_info *info) +{ + return info->data; +} + +static inline void cluster_set_count(struct swap_cluster_info *info, + unsigned int c) +{ + info->data = c; +} + +static inline void cluster_set_count_flag(struct swap_cluster_info *info, + unsigned int c, unsigned int f) +{ + info->flags = f; + info->data = c; +} + +static inline unsigned int cluster_next(struct swap_cluster_info *info) +{ + return info->data; +} + +static inline void cluster_set_next(struct swap_cluster_info *info, + unsigned int n) +{ + info->data = n; +} + +static inline void cluster_set_next_flag(struct swap_cluster_info *info, + unsigned int n, unsigned int f) +{ + info->flags = f; + info->data = n; +} + +static inline bool cluster_is_free(struct swap_cluster_info *info) +{ + return info->flags & CLUSTER_FLAG_FREE; +} + +static inline bool cluster_is_null(struct swap_cluster_info *info) +{ + return info->flags & CLUSTER_FLAG_NEXT_NULL; +} + +static inline void cluster_set_null(struct swap_cluster_info *info) +{ + info->flags = CLUSTER_FLAG_NEXT_NULL; + info->data = 0; +} + +/* Add a cluster to discard list and schedule it to do discard */ +static void swap_cluster_schedule_discard(struct swap_info_struct *si, + unsigned int idx) +{ + /* + * If scan_swap_map() can't find a free cluster, it will check + * si->swap_map directly. To make sure the discarding cluster isn't + * taken by scan_swap_map(), mark the swap entries bad (occupied). It + * will be cleared after discard + */ + memset(si->swap_map + idx * SWAPFILE_CLUSTER, + SWAP_MAP_BAD, SWAPFILE_CLUSTER); + + if (cluster_is_null(&si->discard_cluster_head)) { + cluster_set_next_flag(&si->discard_cluster_head, + idx, 0); + cluster_set_next_flag(&si->discard_cluster_tail, + idx, 0); + } else { + unsigned int tail = cluster_next(&si->discard_cluster_tail); + cluster_set_next(&si->cluster_info[tail], idx); + cluster_set_next_flag(&si->discard_cluster_tail, + idx, 0); + } + + schedule_work(&si->discard_work); +} + +/* + * Doing discard actually. After a cluster discard is finished, the cluster + * will be added to free cluster list. caller should hold si->lock. +*/ +static void swap_do_scheduled_discard(struct swap_info_struct *si) +{ + struct swap_cluster_info *info; + unsigned int idx; + + info = si->cluster_info; + + while (!cluster_is_null(&si->discard_cluster_head)) { + idx = cluster_next(&si->discard_cluster_head); + + cluster_set_next_flag(&si->discard_cluster_head, + cluster_next(&info[idx]), 0); + if (cluster_next(&si->discard_cluster_tail) == idx) { + cluster_set_null(&si->discard_cluster_head); + cluster_set_null(&si->discard_cluster_tail); + } + spin_unlock(&si->lock); + + discard_swap_cluster(si, idx * SWAPFILE_CLUSTER, + SWAPFILE_CLUSTER); + + spin_lock(&si->lock); + cluster_set_flag(&info[idx], CLUSTER_FLAG_FREE); + if (cluster_is_null(&si->free_cluster_head)) { + cluster_set_next_flag(&si->free_cluster_head, + idx, 0); + cluster_set_next_flag(&si->free_cluster_tail, + idx, 0); + } else { + unsigned int tail; + + tail = cluster_next(&si->free_cluster_tail); + cluster_set_next(&info[tail], idx); + cluster_set_next_flag(&si->free_cluster_tail, + idx, 0); + } + memset(si->swap_map + idx * SWAPFILE_CLUSTER, + 0, SWAPFILE_CLUSTER); + } +} + +static void swap_discard_work(struct work_struct *work) +{ + struct swap_info_struct *si; + + si = container_of(work, struct swap_info_struct, discard_work); + + spin_lock(&si->lock); + swap_do_scheduled_discard(si); + spin_unlock(&si->lock); +} + +/* + * The cluster corresponding to page_nr will be used. The cluster will be + * removed from free cluster list and its usage counter will be increased. + */ +static void inc_cluster_info_page(struct swap_info_struct *p, + struct swap_cluster_info *cluster_info, unsigned long page_nr) +{ + unsigned long idx = page_nr / SWAPFILE_CLUSTER; + + if (!cluster_info) + return; + if (cluster_is_free(&cluster_info[idx])) { + VM_BUG_ON(cluster_next(&p->free_cluster_head) != idx); + cluster_set_next_flag(&p->free_cluster_head, + cluster_next(&cluster_info[idx]), 0); + if (cluster_next(&p->free_cluster_tail) == idx) { + cluster_set_null(&p->free_cluster_tail); + cluster_set_null(&p->free_cluster_head); + } + cluster_set_count_flag(&cluster_info[idx], 0, 0); + } + + VM_BUG_ON(cluster_count(&cluster_info[idx]) >= SWAPFILE_CLUSTER); + cluster_set_count(&cluster_info[idx], + cluster_count(&cluster_info[idx]) + 1); +} + +/* + * The cluster corresponding to page_nr decreases one usage. If the usage + * counter becomes 0, which means no page in the cluster is in using, we can + * optionally discard the cluster and add it to free cluster list. + */ +static void dec_cluster_info_page(struct swap_info_struct *p, + struct swap_cluster_info *cluster_info, unsigned long page_nr) +{ + unsigned long idx = page_nr / SWAPFILE_CLUSTER; + + if (!cluster_info) + return; + + VM_BUG_ON(cluster_count(&cluster_info[idx]) == 0); + cluster_set_count(&cluster_info[idx], + cluster_count(&cluster_info[idx]) - 1); + + if (cluster_count(&cluster_info[idx]) == 0) { + /* + * If the swap is discardable, prepare discard the cluster + * instead of free it immediately. The cluster will be freed + * after discard. + */ + if ((p->flags & (SWP_WRITEOK | SWP_PAGE_DISCARD)) == + (SWP_WRITEOK | SWP_PAGE_DISCARD)) { + swap_cluster_schedule_discard(p, idx); + return; + } + + cluster_set_flag(&cluster_info[idx], CLUSTER_FLAG_FREE); + if (cluster_is_null(&p->free_cluster_head)) { + cluster_set_next_flag(&p->free_cluster_head, idx, 0); + cluster_set_next_flag(&p->free_cluster_tail, idx, 0); + } else { + unsigned int tail = cluster_next(&p->free_cluster_tail); + cluster_set_next(&cluster_info[tail], idx); + cluster_set_next_flag(&p->free_cluster_tail, idx, 0); + } + } +} + +/* + * It's possible scan_swap_map() uses a free cluster in the middle of free + * cluster list. Avoiding such abuse to avoid list corruption. + */ +static bool +scan_swap_map_ssd_cluster_conflict(struct swap_info_struct *si, + unsigned long offset) +{ + struct percpu_cluster *percpu_cluster; + bool conflict; + + offset /= SWAPFILE_CLUSTER; + conflict = !cluster_is_null(&si->free_cluster_head) && + offset != cluster_next(&si->free_cluster_head) && + cluster_is_free(&si->cluster_info[offset]); + + if (!conflict) + return false; + + percpu_cluster = this_cpu_ptr(si->percpu_cluster); + cluster_set_null(&percpu_cluster->index); + return true; +} + +/* + * Try to get a swap entry from current cpu's swap entry pool (a cluster). This + * might involve allocating a new cluster for current CPU too. + */ +static void scan_swap_map_try_ssd_cluster(struct swap_info_struct *si, + unsigned long *offset, unsigned long *scan_base) +{ + struct percpu_cluster *cluster; + bool found_free; + unsigned long tmp; + +new_cluster: + cluster = this_cpu_ptr(si->percpu_cluster); + if (cluster_is_null(&cluster->index)) { + if (!cluster_is_null(&si->free_cluster_head)) { + cluster->index = si->free_cluster_head; + cluster->next = cluster_next(&cluster->index) * + SWAPFILE_CLUSTER; + } else if (!cluster_is_null(&si->discard_cluster_head)) { + /* + * we don't have free cluster but have some clusters in + * discarding, do discard now and reclaim them + */ + swap_do_scheduled_discard(si); + *scan_base = *offset = si->cluster_next; + goto new_cluster; + } else + return; + } + + found_free = false; + + /* + * Other CPUs can use our cluster if they can't find a free cluster, + * check if there is still free entry in the cluster + */ + tmp = cluster->next; + while (tmp < si->max && tmp < (cluster_next(&cluster->index) + 1) * + SWAPFILE_CLUSTER) { + if (!si->swap_map[tmp]) { + found_free = true; + break; + } + tmp++; + } + if (!found_free) { + cluster_set_null(&cluster->index); + goto new_cluster; + } + cluster->next = tmp + 1; + *offset = tmp; + *scan_base = tmp; +} static unsigned long scan_swap_map(struct swap_info_struct *si, unsigned char usage) @@ -191,7 +473,6 @@ static unsigned long scan_swap_map(struct swap_info_struct *si, unsigned long scan_base; unsigned long last_in_cluster = 0; int latency_ration = LATENCY_LIMIT; - int found_free_cluster = 0; /* * We try to cluster swap pages by allocating them sequentially @@ -207,24 +488,18 @@ static unsigned long scan_swap_map(struct swap_info_struct *si, si->flags += SWP_SCANNING; scan_base = offset = si->cluster_next; + /* SSD algorithm */ + if (si->cluster_info) { + scan_swap_map_try_ssd_cluster(si, &offset, &scan_base); + goto checks; + } + if (unlikely(!si->cluster_nr--)) { if (si->pages - si->inuse_pages < SWAPFILE_CLUSTER) { si->cluster_nr = SWAPFILE_CLUSTER - 1; goto checks; } - if (si->flags & SWP_PAGE_DISCARD) { - /* - * Start range check on racing allocations, in case - * they overlap the cluster we eventually decide on - * (we scan without swap_lock to allow preemption). - * It's hardly conceivable that cluster_nr could be - * wrapped during our scan, but don't depend on it. - */ - if (si->lowest_alloc) - goto checks; - si->lowest_alloc = si->max; - si->highest_alloc = 0; - } + spin_unlock(&si->lock); /* @@ -248,7 +523,6 @@ static unsigned long scan_swap_map(struct swap_info_struct *si, offset -= SWAPFILE_CLUSTER - 1; si->cluster_next = offset; si->cluster_nr = SWAPFILE_CLUSTER - 1; - found_free_cluster = 1; goto checks; } if (unlikely(--latency_ration < 0)) { @@ -269,7 +543,6 @@ static unsigned long scan_swap_map(struct swap_info_struct *si, offset -= SWAPFILE_CLUSTER - 1; si->cluster_next = offset; si->cluster_nr = SWAPFILE_CLUSTER - 1; - found_free_cluster = 1; goto checks; } if (unlikely(--latency_ration < 0)) { @@ -281,10 +554,13 @@ static unsigned long scan_swap_map(struct swap_info_struct *si, offset = scan_base; spin_lock(&si->lock); si->cluster_nr = SWAPFILE_CLUSTER - 1; - si->lowest_alloc = 0; } checks: + if (si->cluster_info) { + while (scan_swap_map_ssd_cluster_conflict(si, offset)) + scan_swap_map_try_ssd_cluster(si, &offset, &scan_base); + } if (!(si->flags & SWP_WRITEOK)) goto no_page; if (!si->highest_bit) @@ -317,62 +593,10 @@ checks: si->highest_bit = 0; } si->swap_map[offset] = usage; + inc_cluster_info_page(si, si->cluster_info, offset); si->cluster_next = offset + 1; si->flags -= SWP_SCANNING; - if (si->lowest_alloc) { - /* - * Only set when SWP_PAGE_DISCARD, and there's a scan - * for a free cluster in progress or just completed. - */ - if (found_free_cluster) { - /* - * To optimize wear-levelling, discard the - * old data of the cluster, taking care not to - * discard any of its pages that have already - * been allocated by racing tasks (offset has - * already stepped over any at the beginning). - */ - if (offset < si->highest_alloc && - si->lowest_alloc <= last_in_cluster) - last_in_cluster = si->lowest_alloc - 1; - si->flags |= SWP_DISCARDING; - spin_unlock(&si->lock); - - if (offset < last_in_cluster) - discard_swap_cluster(si, offset, - last_in_cluster - offset + 1); - - spin_lock(&si->lock); - si->lowest_alloc = 0; - si->flags &= ~SWP_DISCARDING; - - smp_mb(); /* wake_up_bit advises this */ - wake_up_bit(&si->flags, ilog2(SWP_DISCARDING)); - - } else if (si->flags & SWP_DISCARDING) { - /* - * Delay using pages allocated by racing tasks - * until the whole discard has been issued. We - * could defer that delay until swap_writepage, - * but it's easier to keep this self-contained. - */ - spin_unlock(&si->lock); - wait_on_bit(&si->flags, ilog2(SWP_DISCARDING), - wait_for_discard, TASK_UNINTERRUPTIBLE); - spin_lock(&si->lock); - } else { - /* - * Note pages allocated by racing tasks while - * scan for a free cluster is in progress, so - * that its final discard can exclude them. - */ - if (offset < si->lowest_alloc) - si->lowest_alloc = offset; - if (offset > si->highest_alloc) - si->highest_alloc = offset; - } - } return offset; scan: @@ -483,7 +707,7 @@ noswap: return (swp_entry_t) {0}; } -/* The only caller of this function is now susupend routine */ +/* The only caller of this function is now suspend routine */ swp_entry_t get_swap_page_of_type(int type) { struct swap_info_struct *si; @@ -527,16 +751,16 @@ static struct swap_info_struct *swap_info_get(swp_entry_t entry) return p; bad_free: - printk(KERN_ERR "swap_free: %s%08lx\n", Unused_offset, entry.val); + pr_err("swap_free: %s%08lx\n", Unused_offset, entry.val); goto out; bad_offset: - printk(KERN_ERR "swap_free: %s%08lx\n", Bad_offset, entry.val); + pr_err("swap_free: %s%08lx\n", Bad_offset, entry.val); goto out; bad_device: - printk(KERN_ERR "swap_free: %s%08lx\n", Unused_file, entry.val); + pr_err("swap_free: %s%08lx\n", Unused_file, entry.val); goto out; bad_nofile: - printk(KERN_ERR "swap_free: %s%08lx\n", Bad_file, entry.val); + pr_err("swap_free: %s%08lx\n", Bad_file, entry.val); out: return NULL; } @@ -600,6 +824,7 @@ static unsigned char swap_entry_free(struct swap_info_struct *p, /* free if no reference */ if (!usage) { + dec_cluster_info_page(p, p->cluster_info, offset); if (offset < p->lowest_bit) p->lowest_bit = offset; if (offset > p->highest_bit) @@ -620,7 +845,7 @@ static unsigned char swap_entry_free(struct swap_info_struct *p, } /* - * Caller has made sure that the swapdevice corresponding to entry + * Caller has made sure that the swap device corresponding to entry * is still around or has not been recycled. */ void swap_free(swp_entry_t entry) @@ -722,7 +947,7 @@ int try_to_free_swap(struct page *page) * original page might be freed under memory pressure, then * later read back in from swap, now with the wrong data. * - * Hibration suspends storage while it is writing the image + * Hibernation suspends storage while it is writing the image * to disk so check that here. */ if (pm_suspended_storage()) @@ -954,7 +1179,7 @@ static int unuse_pte_range(struct vm_area_struct *vma, pmd_t *pmd, * some architectures (e.g. x86_32 with PAE) we might catch a glimpse * of unmatched parts which look like swp_pte, so unuse_pte must * recheck under pte lock. Scanning without pte lock lets it be - * preemptible whenever CONFIG_PREEMPT but not CONFIG_HIGHPTE. + * preemptable whenever CONFIG_PREEMPT but not CONFIG_HIGHPTE. */ pte = pte_offset_map(pmd, addr); do { @@ -1107,7 +1332,7 @@ static unsigned int find_next_to_unuse(struct swap_info_struct *si, else continue; } - count = si->swap_map[i]; + count = ACCESS_ONCE(si->swap_map[i]); if (count && swap_count(count) != SWAP_MAP_BAD) break; } @@ -1127,7 +1352,11 @@ int try_to_unuse(unsigned int type, bool frontswap, { struct swap_info_struct *si = swap_info[type]; struct mm_struct *start_mm; - unsigned char *swap_map; + volatile unsigned char *swap_map; /* swap_map is accessed without + * locking. Mark it as volatile + * to prevent compiler doing + * something odd. + */ unsigned char swcount; struct page *page; swp_entry_t entry; @@ -1178,7 +1407,15 @@ int try_to_unuse(unsigned int type, bool frontswap, * reused since sys_swapoff() already disabled * allocation from here, or alloc_page() failed. */ - if (!*swap_map) + swcount = *swap_map; + /* + * We don't hold lock here, so the swap entry could be + * SWAP_MAP_BAD (when the cluster is discarding). + * Instead of fail out, We can just skip the swap + * entry because swapoff will wait for discarding + * finish anyway. + */ + if (!swcount || swcount == SWAP_MAP_BAD) continue; retval = -ENOMEM; break; @@ -1524,7 +1761,8 @@ static int setup_swap_extents(struct swap_info_struct *sis, sector_t *span) } static void _enable_swap_info(struct swap_info_struct *p, int prio, - unsigned char *swap_map) + unsigned char *swap_map, + struct swap_cluster_info *cluster_info) { int i, prev; @@ -1533,6 +1771,7 @@ static void _enable_swap_info(struct swap_info_struct *p, int prio, else p->prio = --least_priority; p->swap_map = swap_map; + p->cluster_info = cluster_info; p->flags |= SWP_WRITEOK; atomic_long_add(p->pages, &nr_swap_pages); total_swap_pages += p->pages; @@ -1553,12 +1792,13 @@ static void _enable_swap_info(struct swap_info_struct *p, int prio, static void enable_swap_info(struct swap_info_struct *p, int prio, unsigned char *swap_map, + struct swap_cluster_info *cluster_info, unsigned long *frontswap_map) { frontswap_init(p->type, frontswap_map); spin_lock(&swap_lock); spin_lock(&p->lock); - _enable_swap_info(p, prio, swap_map); + _enable_swap_info(p, prio, swap_map, cluster_info); spin_unlock(&p->lock); spin_unlock(&swap_lock); } @@ -1567,7 +1807,7 @@ static void reinsert_swap_info(struct swap_info_struct *p) { spin_lock(&swap_lock); spin_lock(&p->lock); - _enable_swap_info(p, p->prio, p->swap_map); + _enable_swap_info(p, p->prio, p->swap_map, p->cluster_info); spin_unlock(&p->lock); spin_unlock(&swap_lock); } @@ -1576,6 +1816,7 @@ SYSCALL_DEFINE1(swapoff, const char __user *, specialfile) { struct swap_info_struct *p = NULL; unsigned char *swap_map; + struct swap_cluster_info *cluster_info; unsigned long *frontswap_map; struct file *swap_file, *victim; struct address_space *mapping; @@ -1583,6 +1824,7 @@ SYSCALL_DEFINE1(swapoff, const char __user *, specialfile) struct filename *pathname; int i, type, prev; int err; + unsigned int old_block_size; if (!capable(CAP_SYS_ADMIN)) return -EPERM; @@ -1651,6 +1893,8 @@ SYSCALL_DEFINE1(swapoff, const char __user *, specialfile) goto out_dput; } + flush_work(&p->discard_work); + destroy_swap_extents(p); if (p->flags & SWP_CONTINUED) free_swap_count_continuations(p); @@ -1671,26 +1915,32 @@ SYSCALL_DEFINE1(swapoff, const char __user *, specialfile) } swap_file = p->swap_file; + old_block_size = p->old_block_size; p->swap_file = NULL; p->max = 0; swap_map = p->swap_map; p->swap_map = NULL; + cluster_info = p->cluster_info; + p->cluster_info = NULL; p->flags = 0; frontswap_map = frontswap_map_get(p); - frontswap_map_set(p, NULL); spin_unlock(&p->lock); spin_unlock(&swap_lock); frontswap_invalidate_area(type); + frontswap_map_set(p, NULL); mutex_unlock(&swapon_mutex); + free_percpu(p->percpu_cluster); + p->percpu_cluster = NULL; vfree(swap_map); + vfree(cluster_info); vfree(frontswap_map); - /* Destroy swap account informatin */ + /* Destroy swap account information */ swap_cgroup_swapoff(type); inode = mapping->host; if (S_ISBLK(inode->i_mode)) { struct block_device *bdev = I_BDEV(inode); - set_blocksize(bdev, p->old_block_size); + set_blocksize(bdev, old_block_size); blkdev_put(bdev, FMODE_READ | FMODE_WRITE | FMODE_EXCL); } else { mutex_lock(&inode->i_mutex); @@ -1926,9 +2176,10 @@ static unsigned long read_swap_header(struct swap_info_struct *p, int i; unsigned long maxpages; unsigned long swapfilepages; + unsigned long last_page; if (memcmp("SWAPSPACE2", swap_header->magic.magic, 10)) { - printk(KERN_ERR "Unable to find swap-space signature\n"); + pr_err("Unable to find swap-space signature\n"); return 0; } @@ -1942,9 +2193,8 @@ static unsigned long read_swap_header(struct swap_info_struct *p, } /* Check the swap header's sub-version */ if (swap_header->info.version != 1) { - printk(KERN_WARNING - "Unable to handle swap header version %d\n", - swap_header->info.version); + pr_warn("Unable to handle swap header version %d\n", + swap_header->info.version); return 0; } @@ -1968,8 +2218,14 @@ static unsigned long read_swap_header(struct swap_info_struct *p, */ maxpages = swp_offset(pte_to_swp_entry( swp_entry_to_pte(swp_entry(0, ~0UL)))) + 1; - if (maxpages > swap_header->info.last_page) { - maxpages = swap_header->info.last_page + 1; + last_page = swap_header->info.last_page; + if (last_page > maxpages) { + pr_warn("Truncating oversized swap area, only using %luk out of %luk\n", + maxpages << (PAGE_SHIFT - 10), + last_page << (PAGE_SHIFT - 10)); + } + if (maxpages > last_page) { + maxpages = last_page + 1; /* p->max is an unsigned int: don't overflow it */ if ((unsigned int)maxpages == 0) maxpages = UINT_MAX; @@ -1980,8 +2236,7 @@ static unsigned long read_swap_header(struct swap_info_struct *p, return 0; swapfilepages = i_size_read(inode) >> PAGE_SHIFT; if (swapfilepages && maxpages > swapfilepages) { - printk(KERN_WARNING - "Swap area shorter than signature indicates\n"); + pr_warn("Swap area shorter than signature indicates\n"); return 0; } if (swap_header->info.nr_badpages && S_ISREG(inode->i_mode)) @@ -1995,15 +2250,23 @@ static unsigned long read_swap_header(struct swap_info_struct *p, static int setup_swap_map_and_extents(struct swap_info_struct *p, union swap_header *swap_header, unsigned char *swap_map, + struct swap_cluster_info *cluster_info, unsigned long maxpages, sector_t *span) { int i; unsigned int nr_good_pages; int nr_extents; + unsigned long nr_clusters = DIV_ROUND_UP(maxpages, SWAPFILE_CLUSTER); + unsigned long idx = p->cluster_next / SWAPFILE_CLUSTER; nr_good_pages = maxpages - 1; /* omit header page */ + cluster_set_null(&p->free_cluster_head); + cluster_set_null(&p->free_cluster_tail); + cluster_set_null(&p->discard_cluster_head); + cluster_set_null(&p->discard_cluster_tail); + for (i = 0; i < swap_header->info.nr_badpages; i++) { unsigned int page_nr = swap_header->info.badpages[i]; if (page_nr == 0 || page_nr > swap_header->info.last_page) @@ -2011,11 +2274,25 @@ static int setup_swap_map_and_extents(struct swap_info_struct *p, if (page_nr < maxpages) { swap_map[page_nr] = SWAP_MAP_BAD; nr_good_pages--; + /* + * Haven't marked the cluster free yet, no list + * operation involved + */ + inc_cluster_info_page(p, cluster_info, page_nr); } } + /* Haven't marked the cluster free yet, no list operation involved */ + for (i = maxpages; i < round_up(maxpages, SWAPFILE_CLUSTER); i++) + inc_cluster_info_page(p, cluster_info, i); + if (nr_good_pages) { swap_map[0] = SWAP_MAP_BAD; + /* + * Not mark the cluster free yet, no list + * operation involved + */ + inc_cluster_info_page(p, cluster_info, 0); p->max = maxpages; p->pages = nr_good_pages; nr_extents = setup_swap_extents(p, span); @@ -2024,10 +2301,34 @@ static int setup_swap_map_and_extents(struct swap_info_struct *p, nr_good_pages = p->pages; } if (!nr_good_pages) { - printk(KERN_WARNING "Empty swap-file\n"); + pr_warn("Empty swap-file\n"); return -EINVAL; } + if (!cluster_info) + return nr_extents; + + for (i = 0; i < nr_clusters; i++) { + if (!cluster_count(&cluster_info[idx])) { + cluster_set_flag(&cluster_info[idx], CLUSTER_FLAG_FREE); + if (cluster_is_null(&p->free_cluster_head)) { + cluster_set_next_flag(&p->free_cluster_head, + idx, 0); + cluster_set_next_flag(&p->free_cluster_tail, + idx, 0); + } else { + unsigned int tail; + + tail = cluster_next(&p->free_cluster_tail); + cluster_set_next(&cluster_info[tail], idx); + cluster_set_next_flag(&p->free_cluster_tail, + idx, 0); + } + } + idx++; + if (idx == nr_clusters) + idx = 0; + } return nr_extents; } @@ -2059,6 +2360,7 @@ SYSCALL_DEFINE2(swapon, const char __user *, specialfile, int, swap_flags) sector_t span; unsigned long maxpages; unsigned char *swap_map = NULL; + struct swap_cluster_info *cluster_info = NULL; unsigned long *frontswap_map = NULL; struct page *page = NULL; struct inode *inode = NULL; @@ -2073,6 +2375,8 @@ SYSCALL_DEFINE2(swapon, const char __user *, specialfile, int, swap_flags) if (IS_ERR(p)) return PTR_ERR(p); + INIT_WORK(&p->discard_work, swap_discard_work); + name = getname(specialfile); if (IS_ERR(name)) { error = PTR_ERR(name); @@ -2132,13 +2436,38 @@ SYSCALL_DEFINE2(swapon, const char __user *, specialfile, int, swap_flags) error = -ENOMEM; goto bad_swap; } + if (p->bdev && blk_queue_nonrot(bdev_get_queue(p->bdev))) { + p->flags |= SWP_SOLIDSTATE; + /* + * select a random position to start with to help wear leveling + * SSD + */ + p->cluster_next = 1 + (prandom_u32() % p->highest_bit); + + cluster_info = vzalloc(DIV_ROUND_UP(maxpages, + SWAPFILE_CLUSTER) * sizeof(*cluster_info)); + if (!cluster_info) { + error = -ENOMEM; + goto bad_swap; + } + p->percpu_cluster = alloc_percpu(struct percpu_cluster); + if (!p->percpu_cluster) { + error = -ENOMEM; + goto bad_swap; + } + for_each_possible_cpu(i) { + struct percpu_cluster *cluster; + cluster = per_cpu_ptr(p->percpu_cluster, i); + cluster_set_null(&cluster->index); + } + } error = swap_cgroup_swapon(p->type, maxpages); if (error) goto bad_swap; nr_extents = setup_swap_map_and_extents(p, swap_header, swap_map, - maxpages, &span); + cluster_info, maxpages, &span); if (unlikely(nr_extents < 0)) { error = nr_extents; goto bad_swap; @@ -2147,41 +2476,33 @@ SYSCALL_DEFINE2(swapon, const char __user *, specialfile, int, swap_flags) if (frontswap_enabled) frontswap_map = vzalloc(BITS_TO_LONGS(maxpages) * sizeof(long)); - if (p->bdev) { - if (blk_queue_nonrot(bdev_get_queue(p->bdev))) { - p->flags |= SWP_SOLIDSTATE; - p->cluster_next = 1 + (prandom_u32() % p->highest_bit); - } - - if ((swap_flags & SWAP_FLAG_DISCARD) && swap_discardable(p)) { - /* - * When discard is enabled for swap with no particular - * policy flagged, we set all swap discard flags here in - * order to sustain backward compatibility with older - * swapon(8) releases. - */ - p->flags |= (SWP_DISCARDABLE | SWP_AREA_DISCARD | - SWP_PAGE_DISCARD); + if (p->bdev &&(swap_flags & SWAP_FLAG_DISCARD) && swap_discardable(p)) { + /* + * When discard is enabled for swap with no particular + * policy flagged, we set all swap discard flags here in + * order to sustain backward compatibility with older + * swapon(8) releases. + */ + p->flags |= (SWP_DISCARDABLE | SWP_AREA_DISCARD | + SWP_PAGE_DISCARD); - /* - * By flagging sys_swapon, a sysadmin can tell us to - * either do single-time area discards only, or to just - * perform discards for released swap page-clusters. - * Now it's time to adjust the p->flags accordingly. - */ - if (swap_flags & SWAP_FLAG_DISCARD_ONCE) - p->flags &= ~SWP_PAGE_DISCARD; - else if (swap_flags & SWAP_FLAG_DISCARD_PAGES) - p->flags &= ~SWP_AREA_DISCARD; - - /* issue a swapon-time discard if it's still required */ - if (p->flags & SWP_AREA_DISCARD) { - int err = discard_swap(p); - if (unlikely(err)) - printk(KERN_ERR - "swapon: discard_swap(%p): %d\n", - p, err); - } + /* + * By flagging sys_swapon, a sysadmin can tell us to + * either do single-time area discards only, or to just + * perform discards for released swap page-clusters. + * Now it's time to adjust the p->flags accordingly. + */ + if (swap_flags & SWAP_FLAG_DISCARD_ONCE) + p->flags &= ~SWP_PAGE_DISCARD; + else if (swap_flags & SWAP_FLAG_DISCARD_PAGES) + p->flags &= ~SWP_AREA_DISCARD; + + /* issue a swapon-time discard if it's still required */ + if (p->flags & SWP_AREA_DISCARD) { + int err = discard_swap(p); + if (unlikely(err)) + pr_err("swapon: discard_swap(%p): %d\n", + p, err); } } @@ -2190,9 +2511,9 @@ SYSCALL_DEFINE2(swapon, const char __user *, specialfile, int, swap_flags) if (swap_flags & SWAP_FLAG_PREFER) prio = (swap_flags & SWAP_FLAG_PRIO_MASK) >> SWAP_FLAG_PRIO_SHIFT; - enable_swap_info(p, prio, swap_map, frontswap_map); + enable_swap_info(p, prio, swap_map, cluster_info, frontswap_map); - printk(KERN_INFO "Adding %uk swap on %s. " + pr_info("Adding %uk swap on %s. " "Priority:%d extents:%d across:%lluk %s%s%s%s%s\n", p->pages<<(PAGE_SHIFT-10), name->name, p->prio, nr_extents, (unsigned long long)span<<(PAGE_SHIFT-10), @@ -2211,6 +2532,8 @@ SYSCALL_DEFINE2(swapon, const char __user *, specialfile, int, swap_flags) error = 0; goto out; bad_swap: + free_percpu(p->percpu_cluster); + p->percpu_cluster = NULL; if (inode && S_ISBLK(inode->i_mode) && p->bdev) { set_blocksize(p->bdev, p->old_block_size); blkdev_put(p->bdev, FMODE_READ | FMODE_WRITE | FMODE_EXCL); @@ -2222,6 +2545,7 @@ bad_swap: p->flags = 0; spin_unlock(&swap_lock); vfree(swap_map); + vfree(cluster_info); if (swap_file) { if (inode && S_ISREG(inode->i_mode)) { mutex_unlock(&inode->i_mutex); @@ -2291,6 +2615,16 @@ static int __swap_duplicate(swp_entry_t entry, unsigned char usage) goto unlock_out; count = p->swap_map[offset]; + + /* + * swapin_readahead() doesn't check if a swap entry is valid, so the + * swap entry could be SWAP_MAP_BAD. Check here with lock held. + */ + if (unlikely(swap_count(count) == SWAP_MAP_BAD)) { + err = -ENOENT; + goto unlock_out; + } + has_cache = count & SWAP_HAS_CACHE; count &= ~SWAP_HAS_CACHE; err = 0; @@ -2326,7 +2660,7 @@ out: return err; bad_file: - printk(KERN_ERR "swap_dup: %s%08lx\n", Bad_file, entry.val); + pr_err("swap_dup: %s%08lx\n", Bad_file, entry.val); goto out; } @@ -2452,8 +2786,8 @@ int add_swap_count_continuation(swp_entry_t entry, gfp_t gfp_mask) /* * We are fortunate that although vmalloc_to_page uses pte_offset_map, - * no architecture is using highmem pages for kernel pagetables: so it - * will not corrupt the GFP_ATOMIC caller's atomic pagetable kmaps. + * no architecture is using highmem pages for kernel page tables: so it + * will not corrupt the GFP_ATOMIC caller's atomic page table kmaps. */ head = vmalloc_to_page(si->swap_map + offset); offset &= ~PAGE_MASK; diff --git a/mm/truncate.c b/mm/truncate.c index e2e8a8a7eb9d..353b683afd6e 100644 --- a/mm/truncate.c +++ b/mm/truncate.c @@ -567,7 +567,6 @@ EXPORT_SYMBOL_GPL(invalidate_inode_pages2); /** * truncate_pagecache - unmap and remove pagecache that has been truncated * @inode: inode - * @oldsize: old file size * @newsize: new file size * * inode's new i_size must already be written before truncate_pagecache @@ -580,7 +579,7 @@ EXPORT_SYMBOL_GPL(invalidate_inode_pages2); * situations such as writepage being called for a page that has already * had its underlying blocks deallocated. */ -void truncate_pagecache(struct inode *inode, loff_t oldsize, loff_t newsize) +void truncate_pagecache(struct inode *inode, loff_t newsize) { struct address_space *mapping = inode->i_mapping; loff_t holebegin = round_up(newsize, PAGE_SIZE); @@ -614,12 +613,8 @@ EXPORT_SYMBOL(truncate_pagecache); */ void truncate_setsize(struct inode *inode, loff_t newsize) { - loff_t oldsize; - - oldsize = inode->i_size; i_size_write(inode, newsize); - - truncate_pagecache(inode, oldsize, newsize); + truncate_pagecache(inode, newsize); } EXPORT_SYMBOL(truncate_setsize); diff --git a/mm/util.c b/mm/util.c index 7441c41d00f6..f7bc2096071c 100644 --- a/mm/util.c +++ b/mm/util.c @@ -7,6 +7,9 @@ #include <linux/security.h> #include <linux/swap.h> #include <linux/swapops.h> +#include <linux/mman.h> +#include <linux/hugetlb.h> + #include <asm/uaccess.h> #include "internal.h" @@ -388,19 +391,26 @@ struct address_space *page_mapping(struct page *page) struct address_space *mapping = page->mapping; VM_BUG_ON(PageSlab(page)); -#ifdef CONFIG_SWAP if (unlikely(PageSwapCache(page))) { swp_entry_t entry; entry.val = page_private(page); mapping = swap_address_space(entry); - } else -#endif - if ((unsigned long)mapping & PAGE_MAPPING_ANON) + } else if ((unsigned long)mapping & PAGE_MAPPING_ANON) mapping = NULL; return mapping; } +/* + * Committed memory limit enforced when OVERCOMMIT_NEVER policy is used + */ +unsigned long vm_commit_limit(void) +{ + return ((totalram_pages - hugetlb_total_pages()) + * sysctl_overcommit_ratio / 100) + total_swap_pages; +} + + /* Tracepoints definitions. */ EXPORT_TRACEPOINT_SYMBOL(kmalloc); EXPORT_TRACEPOINT_SYMBOL(kmem_cache_alloc); diff --git a/mm/vmalloc.c b/mm/vmalloc.c index 13a54953a273..0fdf96803c5b 100644 --- a/mm/vmalloc.c +++ b/mm/vmalloc.c @@ -359,6 +359,12 @@ static struct vmap_area *alloc_vmap_area(unsigned long size, if (unlikely(!va)) return ERR_PTR(-ENOMEM); + /* + * Only scan the relevant parts containing pointers to other objects + * to avoid false negatives. + */ + kmemleak_scan_area(&va->rb_node, SIZE_MAX, gfp_mask & GFP_RECLAIM_MASK); + retry: spin_lock(&vmap_area_lock); /* @@ -752,7 +758,6 @@ struct vmap_block_queue { struct vmap_block { spinlock_t lock; struct vmap_area *va; - struct vmap_block_queue *vbq; unsigned long free, dirty; DECLARE_BITMAP(dirty_map, VMAP_BBMAP_BITS); struct list_head free_list; @@ -830,7 +835,6 @@ static struct vmap_block *new_vmap_block(gfp_t gfp_mask) radix_tree_preload_end(); vbq = &get_cpu_var(vmap_block_queue); - vb->vbq = vbq; spin_lock(&vbq->lock); list_add_rcu(&vb->free_list, &vbq->free); spin_unlock(&vbq->lock); @@ -1018,15 +1022,16 @@ void vm_unmap_aliases(void) rcu_read_lock(); list_for_each_entry_rcu(vb, &vbq->free, free_list) { - int i; + int i, j; spin_lock(&vb->lock); i = find_first_bit(vb->dirty_map, VMAP_BBMAP_BITS); - while (i < VMAP_BBMAP_BITS) { + if (i < VMAP_BBMAP_BITS) { unsigned long s, e; - int j; - j = find_next_zero_bit(vb->dirty_map, - VMAP_BBMAP_BITS, i); + + j = find_last_bit(vb->dirty_map, + VMAP_BBMAP_BITS); + j = j + 1; /* need exclusive index */ s = vb->va->va_start + (i << PAGE_SHIFT); e = vb->va->va_start + (j << PAGE_SHIFT); @@ -1036,10 +1041,6 @@ void vm_unmap_aliases(void) start = s; if (e > end) end = e; - - i = j; - i = find_next_bit(vb->dirty_map, - VMAP_BBMAP_BITS, i); } spin_unlock(&vb->lock); } @@ -1263,7 +1264,7 @@ void unmap_kernel_range(unsigned long addr, unsigned long size) int map_vm_area(struct vm_struct *area, pgprot_t prot, struct page ***pages) { unsigned long addr = (unsigned long)area->addr; - unsigned long end = addr + area->size - PAGE_SIZE; + unsigned long end = addr + get_vm_area_size(area); int err; err = vmap_page_range(addr, end, prot, *pages); @@ -1551,27 +1552,26 @@ static void *__vmalloc_node(unsigned long size, unsigned long align, gfp_t gfp_mask, pgprot_t prot, int node, const void *caller); static void *__vmalloc_area_node(struct vm_struct *area, gfp_t gfp_mask, - pgprot_t prot, int node, const void *caller) + pgprot_t prot, int node) { const int order = 0; struct page **pages; unsigned int nr_pages, array_size, i; gfp_t nested_gfp = (gfp_mask & GFP_RECLAIM_MASK) | __GFP_ZERO; - nr_pages = (area->size - PAGE_SIZE) >> PAGE_SHIFT; + nr_pages = get_vm_area_size(area) >> PAGE_SHIFT; array_size = (nr_pages * sizeof(struct page *)); area->nr_pages = nr_pages; /* Please note that the recursion is strictly bounded. */ if (array_size > PAGE_SIZE) { pages = __vmalloc_node(array_size, 1, nested_gfp|__GFP_HIGHMEM, - PAGE_KERNEL, node, caller); + PAGE_KERNEL, node, area->caller); area->flags |= VM_VPAGES; } else { pages = kmalloc_node(array_size, nested_gfp, node); } area->pages = pages; - area->caller = caller; if (!area->pages) { remove_vm_area(area->addr); kfree(area); @@ -1582,7 +1582,7 @@ static void *__vmalloc_area_node(struct vm_struct *area, gfp_t gfp_mask, struct page *page; gfp_t tmp_mask = gfp_mask | __GFP_NOWARN; - if (node < 0) + if (node == NUMA_NO_NODE) page = alloc_page(tmp_mask); else page = alloc_pages_node(node, tmp_mask, order); @@ -1639,9 +1639,9 @@ void *__vmalloc_node_range(unsigned long size, unsigned long align, if (!area) goto fail; - addr = __vmalloc_area_node(area, gfp_mask, prot, node, caller); + addr = __vmalloc_area_node(area, gfp_mask, prot, node); if (!addr) - goto fail; + return NULL; /* * In this function, newly allocated vm_struct has VM_UNINITIALIZED @@ -1651,11 +1651,11 @@ void *__vmalloc_node_range(unsigned long size, unsigned long align, clear_vm_uninitialized_flag(area); /* - * A ref_count = 3 is needed because the vm_struct and vmap_area - * structures allocated in the __get_vm_area_node() function contain - * references to the virtual address of the vmalloc'ed block. + * A ref_count = 2 is needed because vm_struct allocated in + * __get_vm_area_node() contains a reference to the virtual address of + * the vmalloc'ed block. */ - kmemleak_alloc(addr, real_size, 3, gfp_mask); + kmemleak_alloc(addr, real_size, 2, gfp_mask); return addr; @@ -1990,7 +1990,7 @@ long vread(char *buf, char *addr, unsigned long count) vm = va->vm; vaddr = (char *) vm->addr; - if (addr >= vaddr + vm->size - PAGE_SIZE) + if (addr >= vaddr + get_vm_area_size(vm)) continue; while (addr < vaddr) { if (count == 0) @@ -2000,7 +2000,7 @@ long vread(char *buf, char *addr, unsigned long count) addr++; count--; } - n = vaddr + vm->size - PAGE_SIZE - addr; + n = vaddr + get_vm_area_size(vm) - addr; if (n > count) n = count; if (!(vm->flags & VM_IOREMAP)) @@ -2072,7 +2072,7 @@ long vwrite(char *buf, char *addr, unsigned long count) vm = va->vm; vaddr = (char *) vm->addr; - if (addr >= vaddr + vm->size - PAGE_SIZE) + if (addr >= vaddr + get_vm_area_size(vm)) continue; while (addr < vaddr) { if (count == 0) @@ -2081,7 +2081,7 @@ long vwrite(char *buf, char *addr, unsigned long count) addr++; count--; } - n = vaddr + vm->size - PAGE_SIZE - addr; + n = vaddr + get_vm_area_size(vm) - addr; if (n > count) n = count; if (!(vm->flags & VM_IOREMAP)) { @@ -2568,6 +2568,11 @@ static void show_numa_info(struct seq_file *m, struct vm_struct *v) if (!counters) return; + /* Pair with smp_wmb() in clear_vm_uninitialized_flag() */ + smp_rmb(); + if (v->flags & VM_UNINITIALIZED) + return; + memset(counters, 0, nr_node_ids * sizeof(unsigned int)); for (nr = 0; nr < v->nr_pages; nr++) @@ -2584,23 +2589,15 @@ static int s_show(struct seq_file *m, void *p) struct vmap_area *va = p; struct vm_struct *v; - if (va->flags & (VM_LAZY_FREE | VM_LAZY_FREEING)) - return 0; - - if (!(va->flags & VM_VM_AREA)) { - seq_printf(m, "0x%pK-0x%pK %7ld vm_map_ram\n", - (void *)va->va_start, (void *)va->va_end, - va->va_end - va->va_start); + /* + * s_show can encounter race with remove_vm_area, !VM_VM_AREA on + * behalf of vmap area is being tear down or vm_map_ram allocation. + */ + if (!(va->flags & VM_VM_AREA)) return 0; - } v = va->vm; - /* Pair with smp_wmb() in clear_vm_uninitialized_flag() */ - smp_rmb(); - if (v->flags & VM_UNINITIALIZED) - return 0; - seq_printf(m, "0x%pK-0x%pK %7ld", v->addr, v->addr + v->size, v->size); diff --git a/mm/vmscan.c b/mm/vmscan.c index 2cff0d491c6d..eea668d9cff6 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -48,6 +48,7 @@ #include <asm/div64.h> #include <linux/swapops.h> +#include <linux/balloon_compaction.h> #include "internal.h" @@ -146,6 +147,25 @@ static bool global_reclaim(struct scan_control *sc) } #endif +unsigned long zone_reclaimable_pages(struct zone *zone) +{ + int nr; + + nr = zone_page_state(zone, NR_ACTIVE_FILE) + + zone_page_state(zone, NR_INACTIVE_FILE); + + if (get_nr_swap_pages() > 0) + nr += zone_page_state(zone, NR_ACTIVE_ANON) + + zone_page_state(zone, NR_INACTIVE_ANON); + + return nr; +} + +bool zone_reclaimable(struct zone *zone) +{ + return zone->pages_scanned < zone_reclaimable_pages(zone) * 6; +} + static unsigned long get_lru_size(struct lruvec *lruvec, enum lru_list lru) { if (!mem_cgroup_disabled()) @@ -155,14 +175,31 @@ static unsigned long get_lru_size(struct lruvec *lruvec, enum lru_list lru) } /* - * Add a shrinker callback to be called from the vm + * Add a shrinker callback to be called from the vm. */ -void register_shrinker(struct shrinker *shrinker) +int register_shrinker(struct shrinker *shrinker) { - atomic_long_set(&shrinker->nr_in_batch, 0); + size_t size = sizeof(*shrinker->nr_deferred); + + /* + * If we only have one possible node in the system anyway, save + * ourselves the trouble and disable NUMA aware behavior. This way we + * will save memory and some small loop time later. + */ + if (nr_node_ids == 1) + shrinker->flags &= ~SHRINKER_NUMA_AWARE; + + if (shrinker->flags & SHRINKER_NUMA_AWARE) + size *= nr_node_ids; + + shrinker->nr_deferred = kzalloc(size, GFP_KERNEL); + if (!shrinker->nr_deferred) + return -ENOMEM; + down_write(&shrinker_rwsem); list_add_tail(&shrinker->list, &shrinker_list); up_write(&shrinker_rwsem); + return 0; } EXPORT_SYMBOL(register_shrinker); @@ -174,18 +211,106 @@ void unregister_shrinker(struct shrinker *shrinker) down_write(&shrinker_rwsem); list_del(&shrinker->list); up_write(&shrinker_rwsem); + kfree(shrinker->nr_deferred); } EXPORT_SYMBOL(unregister_shrinker); -static inline int do_shrinker_shrink(struct shrinker *shrinker, - struct shrink_control *sc, - unsigned long nr_to_scan) -{ - sc->nr_to_scan = nr_to_scan; - return (*shrinker->shrink)(shrinker, sc); +#define SHRINK_BATCH 128 + +static unsigned long +shrink_slab_node(struct shrink_control *shrinkctl, struct shrinker *shrinker, + unsigned long nr_pages_scanned, unsigned long lru_pages) +{ + unsigned long freed = 0; + unsigned long long delta; + long total_scan; + long max_pass; + long nr; + long new_nr; + int nid = shrinkctl->nid; + long batch_size = shrinker->batch ? shrinker->batch + : SHRINK_BATCH; + + max_pass = shrinker->count_objects(shrinker, shrinkctl); + if (max_pass == 0) + return 0; + + /* + * copy the current shrinker scan count into a local variable + * and zero it so that other concurrent shrinker invocations + * don't also do this scanning work. + */ + nr = atomic_long_xchg(&shrinker->nr_deferred[nid], 0); + + total_scan = nr; + delta = (4 * nr_pages_scanned) / shrinker->seeks; + delta *= max_pass; + do_div(delta, lru_pages + 1); + total_scan += delta; + if (total_scan < 0) { + printk(KERN_ERR + "shrink_slab: %pF negative objects to delete nr=%ld\n", + shrinker->scan_objects, total_scan); + total_scan = max_pass; + } + + /* + * We need to avoid excessive windup on filesystem shrinkers + * due to large numbers of GFP_NOFS allocations causing the + * shrinkers to return -1 all the time. This results in a large + * nr being built up so when a shrink that can do some work + * comes along it empties the entire cache due to nr >>> + * max_pass. This is bad for sustaining a working set in + * memory. + * + * Hence only allow the shrinker to scan the entire cache when + * a large delta change is calculated directly. + */ + if (delta < max_pass / 4) + total_scan = min(total_scan, max_pass / 2); + + /* + * Avoid risking looping forever due to too large nr value: + * never try to free more than twice the estimate number of + * freeable entries. + */ + if (total_scan > max_pass * 2) + total_scan = max_pass * 2; + + trace_mm_shrink_slab_start(shrinker, shrinkctl, nr, + nr_pages_scanned, lru_pages, + max_pass, delta, total_scan); + + while (total_scan >= batch_size) { + unsigned long ret; + + shrinkctl->nr_to_scan = batch_size; + ret = shrinker->scan_objects(shrinker, shrinkctl); + if (ret == SHRINK_STOP) + break; + freed += ret; + + count_vm_events(SLABS_SCANNED, batch_size); + total_scan -= batch_size; + + cond_resched(); + } + + /* + * move the unused scan count back into the shrinker in a + * manner that handles concurrent updates. If we exhausted the + * scan, there is no need to do an update. + */ + if (total_scan > 0) + new_nr = atomic_long_add_return(total_scan, + &shrinker->nr_deferred[nid]); + else + new_nr = atomic_long_read(&shrinker->nr_deferred[nid]); + + trace_mm_shrink_slab_end(shrinker, freed, nr, new_nr); + return freed; } -#define SHRINK_BATCH 128 /* * Call the shrink functions to age shrinkable caches * @@ -205,115 +330,45 @@ static inline int do_shrinker_shrink(struct shrinker *shrinker, * * Returns the number of slab objects which we shrunk. */ -unsigned long shrink_slab(struct shrink_control *shrink, +unsigned long shrink_slab(struct shrink_control *shrinkctl, unsigned long nr_pages_scanned, unsigned long lru_pages) { struct shrinker *shrinker; - unsigned long ret = 0; + unsigned long freed = 0; if (nr_pages_scanned == 0) nr_pages_scanned = SWAP_CLUSTER_MAX; if (!down_read_trylock(&shrinker_rwsem)) { - /* Assume we'll be able to shrink next time */ - ret = 1; + /* + * If we would return 0, our callers would understand that we + * have nothing else to shrink and give up trying. By returning + * 1 we keep it going and assume we'll be able to shrink next + * time. + */ + freed = 1; goto out; } list_for_each_entry(shrinker, &shrinker_list, list) { - unsigned long long delta; - long total_scan; - long max_pass; - int shrink_ret = 0; - long nr; - long new_nr; - long batch_size = shrinker->batch ? shrinker->batch - : SHRINK_BATCH; - - max_pass = do_shrinker_shrink(shrinker, shrink, 0); - if (max_pass <= 0) - continue; - - /* - * copy the current shrinker scan count into a local variable - * and zero it so that other concurrent shrinker invocations - * don't also do this scanning work. - */ - nr = atomic_long_xchg(&shrinker->nr_in_batch, 0); - - total_scan = nr; - delta = (4 * nr_pages_scanned) / shrinker->seeks; - delta *= max_pass; - do_div(delta, lru_pages + 1); - total_scan += delta; - if (total_scan < 0) { - printk(KERN_ERR "shrink_slab: %pF negative objects to " - "delete nr=%ld\n", - shrinker->shrink, total_scan); - total_scan = max_pass; - } - - /* - * We need to avoid excessive windup on filesystem shrinkers - * due to large numbers of GFP_NOFS allocations causing the - * shrinkers to return -1 all the time. This results in a large - * nr being built up so when a shrink that can do some work - * comes along it empties the entire cache due to nr >>> - * max_pass. This is bad for sustaining a working set in - * memory. - * - * Hence only allow the shrinker to scan the entire cache when - * a large delta change is calculated directly. - */ - if (delta < max_pass / 4) - total_scan = min(total_scan, max_pass / 2); - - /* - * Avoid risking looping forever due to too large nr value: - * never try to free more than twice the estimate number of - * freeable entries. - */ - if (total_scan > max_pass * 2) - total_scan = max_pass * 2; - - trace_mm_shrink_slab_start(shrinker, shrink, nr, - nr_pages_scanned, lru_pages, - max_pass, delta, total_scan); - - while (total_scan >= batch_size) { - int nr_before; + for_each_node_mask(shrinkctl->nid, shrinkctl->nodes_to_scan) { + if (!node_online(shrinkctl->nid)) + continue; - nr_before = do_shrinker_shrink(shrinker, shrink, 0); - shrink_ret = do_shrinker_shrink(shrinker, shrink, - batch_size); - if (shrink_ret == -1) + if (!(shrinker->flags & SHRINKER_NUMA_AWARE) && + (shrinkctl->nid != 0)) break; - if (shrink_ret < nr_before) - ret += nr_before - shrink_ret; - count_vm_events(SLABS_SCANNED, batch_size); - total_scan -= batch_size; - cond_resched(); - } + freed += shrink_slab_node(shrinkctl, shrinker, + nr_pages_scanned, lru_pages); - /* - * move the unused scan count back into the shrinker in a - * manner that handles concurrent updates. If we exhausted the - * scan, there is no need to do an update. - */ - if (total_scan > 0) - new_nr = atomic_long_add_return(total_scan, - &shrinker->nr_in_batch); - else - new_nr = atomic_long_read(&shrinker->nr_in_batch); - - trace_mm_shrink_slab_end(shrinker, shrink_ret, nr, new_nr); + } } up_read(&shrinker_rwsem); out: cond_resched(); - return ret; + return freed; } static inline int is_page_cache_freeable(struct page *page) @@ -545,7 +600,7 @@ int remove_mapping(struct address_space *mapping, struct page *page) */ void putback_lru_page(struct page *page) { - int lru; + bool is_unevictable; int was_unevictable = PageUnevictable(page); VM_BUG_ON(PageLRU(page)); @@ -560,14 +615,14 @@ redo: * unevictable page on [in]active list. * We know how to handle that. */ - lru = page_lru_base_type(page); + is_unevictable = false; lru_cache_add(page); } else { /* * Put unevictable pages directly on zone's unevictable * list. */ - lru = LRU_UNEVICTABLE; + is_unevictable = true; add_page_to_unevictable_list(page); /* * When racing with an mlock or AS_UNEVICTABLE clearing @@ -587,7 +642,7 @@ redo: * page is on unevictable list, it never be freed. To avoid that, * check after we added it to the list, again. */ - if (lru == LRU_UNEVICTABLE && page_evictable(page)) { + if (is_unevictable && page_evictable(page)) { if (!isolate_lru_page(page)) { put_page(page); goto redo; @@ -598,9 +653,9 @@ redo: */ } - if (was_unevictable && lru != LRU_UNEVICTABLE) + if (was_unevictable && !is_unevictable) count_vm_event(UNEVICTABLE_PGRESCUED); - else if (!was_unevictable && lru == LRU_UNEVICTABLE) + else if (!was_unevictable && is_unevictable) count_vm_event(UNEVICTABLE_PGCULLED); put_page(page); /* drop ref from isolate */ @@ -1060,7 +1115,8 @@ unsigned long reclaim_clean_pages_from_list(struct zone *zone, LIST_HEAD(clean_pages); list_for_each_entry_safe(page, next, page_list, lru) { - if (page_is_file_cache(page) && !PageDirty(page)) { + if (page_is_file_cache(page) && !PageDirty(page) && + !isolated_balloon_page(page)) { ClearPageActive(page); list_move(&page->lru, &clean_pages); } @@ -1789,7 +1845,7 @@ static void get_scan_count(struct lruvec *lruvec, struct scan_control *sc, * latencies, so it's better to scan a minimum amount there as * well. */ - if (current_is_kswapd() && zone->all_unreclaimable) + if (current_is_kswapd() && !zone_reclaimable(zone)) force_scan = true; if (!global_reclaim(sc)) force_scan = true; @@ -2244,8 +2300,8 @@ static bool shrink_zones(struct zonelist *zonelist, struct scan_control *sc) if (global_reclaim(sc)) { if (!cpuset_zone_allowed_hardwall(zone, GFP_KERNEL)) continue; - if (zone->all_unreclaimable && - sc->priority != DEF_PRIORITY) + if (sc->priority != DEF_PRIORITY && + !zone_reclaimable(zone)) continue; /* Let kswapd poll it */ if (IS_ENABLED(CONFIG_COMPACTION)) { /* @@ -2283,11 +2339,6 @@ static bool shrink_zones(struct zonelist *zonelist, struct scan_control *sc) return aborted_reclaim; } -static bool zone_reclaimable(struct zone *zone) -{ - return zone->pages_scanned < zone_reclaimable_pages(zone) * 6; -} - /* All zones in zonelist are unreclaimable? */ static bool all_unreclaimable(struct zonelist *zonelist, struct scan_control *sc) @@ -2301,7 +2352,7 @@ static bool all_unreclaimable(struct zonelist *zonelist, continue; if (!cpuset_zone_allowed_hardwall(zone, GFP_KERNEL)) continue; - if (!zone->all_unreclaimable) + if (zone_reclaimable(zone)) return false; } @@ -2354,12 +2405,16 @@ static unsigned long do_try_to_free_pages(struct zonelist *zonelist, */ if (global_reclaim(sc)) { unsigned long lru_pages = 0; + + nodes_clear(shrink->nodes_to_scan); for_each_zone_zonelist(zone, z, zonelist, gfp_zone(sc->gfp_mask)) { if (!cpuset_zone_allowed_hardwall(zone, GFP_KERNEL)) continue; lru_pages += zone_reclaimable_pages(zone); + node_set(zone_to_nid(zone), + shrink->nodes_to_scan); } shrink_slab(shrink, sc->nr_scanned, lru_pages); @@ -2712,7 +2767,7 @@ static bool pgdat_balanced(pg_data_t *pgdat, int order, int classzone_idx) * DEF_PRIORITY. Effectively, it considers them balanced so * they must be considered balanced here as well! */ - if (zone->all_unreclaimable) { + if (!zone_reclaimable(zone)) { balanced_pages += zone->managed_pages; continue; } @@ -2773,7 +2828,6 @@ static bool kswapd_shrink_zone(struct zone *zone, unsigned long lru_pages, unsigned long *nr_attempted) { - unsigned long nr_slab; int testorder = sc->order; unsigned long balance_gap; struct reclaim_state *reclaim_state = current->reclaim_state; @@ -2816,17 +2870,16 @@ static bool kswapd_shrink_zone(struct zone *zone, return true; shrink_zone(zone, sc); + nodes_clear(shrink.nodes_to_scan); + node_set(zone_to_nid(zone), shrink.nodes_to_scan); reclaim_state->reclaimed_slab = 0; - nr_slab = shrink_slab(&shrink, sc->nr_scanned, lru_pages); + shrink_slab(&shrink, sc->nr_scanned, lru_pages); sc->nr_reclaimed += reclaim_state->reclaimed_slab; /* Account for the number of pages attempted to reclaim */ *nr_attempted += sc->nr_to_reclaim; - if (nr_slab == 0 && !zone_reclaimable(zone)) - zone->all_unreclaimable = 1; - zone_clear_flag(zone, ZONE_WRITEBACK); /* @@ -2835,7 +2888,7 @@ static bool kswapd_shrink_zone(struct zone *zone, * BDIs but as pressure is relieved, speculatively avoid congestion * waits. */ - if (!zone->all_unreclaimable && + if (zone_reclaimable(zone) && zone_balanced(zone, testorder, 0, classzone_idx)) { zone_clear_flag(zone, ZONE_CONGESTED); zone_clear_flag(zone, ZONE_TAIL_LRU_DIRTY); @@ -2901,8 +2954,8 @@ static unsigned long balance_pgdat(pg_data_t *pgdat, int order, if (!populated_zone(zone)) continue; - if (zone->all_unreclaimable && - sc.priority != DEF_PRIORITY) + if (sc.priority != DEF_PRIORITY && + !zone_reclaimable(zone)) continue; /* @@ -2980,8 +3033,8 @@ static unsigned long balance_pgdat(pg_data_t *pgdat, int order, if (!populated_zone(zone)) continue; - if (zone->all_unreclaimable && - sc.priority != DEF_PRIORITY) + if (sc.priority != DEF_PRIORITY && + !zone_reclaimable(zone)) continue; sc.nr_scanned = 0; @@ -3237,7 +3290,7 @@ void wakeup_kswapd(struct zone *zone, int order, enum zone_type classzone_idx) } if (!waitqueue_active(&pgdat->kswapd_wait)) return; - if (zone_watermark_ok_safe(zone, order, low_wmark_pages(zone), 0, 0)) + if (zone_balanced(zone, order, 0, 0)) return; trace_mm_vmscan_wakeup_kswapd(pgdat->node_id, zone_idx(zone), order); @@ -3265,20 +3318,6 @@ unsigned long global_reclaimable_pages(void) return nr; } -unsigned long zone_reclaimable_pages(struct zone *zone) -{ - int nr; - - nr = zone_page_state(zone, NR_ACTIVE_FILE) + - zone_page_state(zone, NR_INACTIVE_FILE); - - if (get_nr_swap_pages() > 0) - nr += zone_page_state(zone, NR_ACTIVE_ANON) + - zone_page_state(zone, NR_INACTIVE_ANON); - - return nr; -} - #ifdef CONFIG_HIBERNATION /* * Try to free `nr_to_reclaim' of memory, system-wide, and return the number of @@ -3524,10 +3563,9 @@ static int __zone_reclaim(struct zone *zone, gfp_t gfp_mask, unsigned int order) * number of slab pages and shake the slab until it is reduced * by the same nr_pages that we used for reclaiming unmapped * pages. - * - * Note that shrink_slab will free memory on all zones and may - * take a long time. */ + nodes_clear(shrink.nodes_to_scan); + node_set(zone_to_nid(zone), shrink.nodes_to_scan); for (;;) { unsigned long lru_pages = zone_reclaimable_pages(zone); @@ -3576,7 +3614,7 @@ int zone_reclaim(struct zone *zone, gfp_t gfp_mask, unsigned int order) zone_page_state(zone, NR_SLAB_RECLAIMABLE) <= zone->min_slab_pages) return ZONE_RECLAIM_FULL; - if (zone->all_unreclaimable) + if (!zone_reclaimable(zone)) return ZONE_RECLAIM_FULL; /* diff --git a/mm/vmstat.c b/mm/vmstat.c index 20c2ef4458fa..72496140ac08 100644 --- a/mm/vmstat.c +++ b/mm/vmstat.c @@ -19,6 +19,9 @@ #include <linux/math64.h> #include <linux/writeback.h> #include <linux/compaction.h> +#include <linux/mm_inline.h> + +#include "internal.h" #ifdef CONFIG_VM_EVENT_COUNTERS DEFINE_PER_CPU(struct vm_event_state, vm_event_states) = {{0}}; @@ -414,12 +417,17 @@ void dec_zone_page_state(struct page *page, enum zone_stat_item item) EXPORT_SYMBOL(dec_zone_page_state); #endif +static inline void fold_diff(int *diff) +{ + int i; + + for (i = 0; i < NR_VM_ZONE_STAT_ITEMS; i++) + if (diff[i]) + atomic_long_add(diff[i], &vm_stat[i]); +} + /* - * Update the zone counters for one cpu. - * - * The cpu specified must be either the current cpu or a processor that - * is not online. If it is the current cpu then the execution thread must - * be pinned to the current cpu. + * Update the zone counters for the current cpu. * * Note that refresh_cpu_vm_stats strives to only access * node local memory. The per cpu pagesets on remote zones are placed @@ -432,33 +440,29 @@ EXPORT_SYMBOL(dec_zone_page_state); * with the global counters. These could cause remote node cache line * bouncing and will have to be only done when necessary. */ -void refresh_cpu_vm_stats(int cpu) +static void refresh_cpu_vm_stats(void) { struct zone *zone; int i; int global_diff[NR_VM_ZONE_STAT_ITEMS] = { 0, }; for_each_populated_zone(zone) { - struct per_cpu_pageset *p; + struct per_cpu_pageset __percpu *p = zone->pageset; - p = per_cpu_ptr(zone->pageset, cpu); + for (i = 0; i < NR_VM_ZONE_STAT_ITEMS; i++) { + int v; - for (i = 0; i < NR_VM_ZONE_STAT_ITEMS; i++) - if (p->vm_stat_diff[i]) { - unsigned long flags; - int v; + v = this_cpu_xchg(p->vm_stat_diff[i], 0); + if (v) { - local_irq_save(flags); - v = p->vm_stat_diff[i]; - p->vm_stat_diff[i] = 0; - local_irq_restore(flags); atomic_long_add(v, &zone->vm_stat[i]); global_diff[i] += v; #ifdef CONFIG_NUMA /* 3 seconds idle till flush */ - p->expire = 3; + __this_cpu_write(p->expire, 3); #endif } + } cond_resched(); #ifdef CONFIG_NUMA /* @@ -468,29 +472,57 @@ void refresh_cpu_vm_stats(int cpu) * Check if there are pages remaining in this pageset * if not then there is nothing to expire. */ - if (!p->expire || !p->pcp.count) + if (!__this_cpu_read(p->expire) || + !__this_cpu_read(p->pcp.count)) continue; /* * We never drain zones local to this processor. */ if (zone_to_nid(zone) == numa_node_id()) { - p->expire = 0; + __this_cpu_write(p->expire, 0); continue; } - p->expire--; - if (p->expire) + + if (__this_cpu_dec_return(p->expire)) continue; - if (p->pcp.count) - drain_zone_pages(zone, &p->pcp); + if (__this_cpu_read(p->pcp.count)) + drain_zone_pages(zone, __this_cpu_ptr(&p->pcp)); #endif } + fold_diff(global_diff); +} - for (i = 0; i < NR_VM_ZONE_STAT_ITEMS; i++) - if (global_diff[i]) - atomic_long_add(global_diff[i], &vm_stat[i]); +/* + * Fold the data for an offline cpu into the global array. + * There cannot be any access by the offline cpu and therefore + * synchronization is simplified. + */ +void cpu_vm_stats_fold(int cpu) +{ + struct zone *zone; + int i; + int global_diff[NR_VM_ZONE_STAT_ITEMS] = { 0, }; + + for_each_populated_zone(zone) { + struct per_cpu_pageset *p; + + p = per_cpu_ptr(zone->pageset, cpu); + + for (i = 0; i < NR_VM_ZONE_STAT_ITEMS; i++) + if (p->vm_stat_diff[i]) { + int v; + + v = p->vm_stat_diff[i]; + p->vm_stat_diff[i] = 0; + atomic_long_add(v, &zone->vm_stat[i]); + global_diff[i] += v; + } + } + + fold_diff(global_diff); } /* @@ -703,6 +735,7 @@ static void walk_zones_in_node(struct seq_file *m, pg_data_t *pgdat, const char * const vmstat_text[] = { /* Zoned VM counters */ "nr_free_pages", + "nr_alloc_batch", "nr_inactive_anon", "nr_active_anon", "nr_inactive_file", @@ -779,6 +812,7 @@ const char * const vmstat_text[] = { #ifdef CONFIG_NUMA_BALANCING "numa_pte_updates", + "numa_huge_pte_updates", "numa_hint_faults", "numa_hint_faults_local", "numa_pages_migrated", @@ -817,6 +851,12 @@ const char * const vmstat_text[] = { "thp_zero_page_alloc", "thp_zero_page_alloc_failed", #endif +#ifdef CONFIG_SMP + "nr_tlb_remote_flush", + "nr_tlb_remote_flush_received", +#endif + "nr_tlb_local_flush_all", + "nr_tlb_local_flush_one", #endif /* CONFIG_VM_EVENTS_COUNTERS */ }; @@ -1052,7 +1092,7 @@ static void zoneinfo_show_print(struct seq_file *m, pg_data_t *pgdat, "\n all_unreclaimable: %u" "\n start_pfn: %lu" "\n inactive_ratio: %u", - zone->all_unreclaimable, + !zone_reclaimable(zone), zone->zone_start_pfn, zone->inactive_ratio); seq_putc(m, '\n'); @@ -1177,7 +1217,7 @@ int sysctl_stat_interval __read_mostly = HZ; static void vmstat_update(struct work_struct *w) { - refresh_cpu_vm_stats(smp_processor_id()); + refresh_cpu_vm_stats(); schedule_delayed_work(&__get_cpu_var(vmstat_work), round_jiffies_relative(sysctl_stat_interval)); } @@ -1190,6 +1230,20 @@ static void start_cpu_timer(int cpu) schedule_delayed_work_on(cpu, work, __round_jiffies_relative(HZ, cpu)); } +static void vmstat_cpu_dead(int node) +{ + int cpu; + + get_online_cpus(); + for_each_online_cpu(cpu) + if (cpu_to_node(cpu) == node) + goto end; + + node_clear_state(node, N_CPU); +end: + put_online_cpus(); +} + /* * Use the cpu notifier to insure that the thresholds are recalculated * when necessary. @@ -1219,6 +1273,7 @@ static int vmstat_cpuup_callback(struct notifier_block *nfb, case CPU_DEAD: case CPU_DEAD_FROZEN: refresh_zone_stat_thresholds(); + vmstat_cpu_dead(cpu_to_node(cpu)); break; default: break; @@ -1237,8 +1292,12 @@ static int __init setup_vmstat(void) register_cpu_notifier(&vmstat_notifier); - for_each_online_cpu(cpu) + get_online_cpus(); + for_each_online_cpu(cpu) { start_cpu_timer(cpu); + node_set_state(cpu_to_node(cpu), N_CPU); + } + put_online_cpus(); #endif #ifdef CONFIG_PROC_FS proc_create("buddyinfo", S_IRUGO, NULL, &fragmentation_file_operations); diff --git a/mm/zbud.c b/mm/zbud.c index ad1e781284fd..9451361e6aa7 100644 --- a/mm/zbud.c +++ b/mm/zbud.c @@ -16,7 +16,7 @@ * * zbud works by storing compressed pages, or "zpages", together in pairs in a * single memory page called a "zbud page". The first buddy is "left - * justifed" at the beginning of the zbud page, and the last buddy is "right + * justified" at the beginning of the zbud page, and the last buddy is "right * justified" at the end of the zbud page. The benefit is that if either * buddy is freed, the freed buddy space, coalesced with whatever slack space * that existed between the buddies, results in the largest possible free region @@ -243,7 +243,7 @@ void zbud_destroy_pool(struct zbud_pool *pool) * gfp should not set __GFP_HIGHMEM as highmem pages cannot be used * as zbud pool pages. * - * Return: 0 if success and handle is set, otherwise -EINVAL is the size or + * Return: 0 if success and handle is set, otherwise -EINVAL if the size or * gfp arguments are invalid or -ENOMEM if the pool was unable to allocate * a new page. */ diff --git a/mm/zswap.c b/mm/zswap.c index deda2b671e12..5a63f78a5601 100644 --- a/mm/zswap.c +++ b/mm/zswap.c @@ -217,6 +217,7 @@ static struct zswap_entry *zswap_entry_cache_alloc(gfp_t gfp) if (!entry) return NULL; entry->refcount = 1; + RB_CLEAR_NODE(&entry->rbnode); return entry; } @@ -225,19 +226,6 @@ static void zswap_entry_cache_free(struct zswap_entry *entry) kmem_cache_free(zswap_entry_cache, entry); } -/* caller must hold the tree lock */ -static void zswap_entry_get(struct zswap_entry *entry) -{ - entry->refcount++; -} - -/* caller must hold the tree lock */ -static int zswap_entry_put(struct zswap_entry *entry) -{ - entry->refcount--; - return entry->refcount; -} - /********************************* * rbtree functions **********************************/ @@ -285,6 +273,61 @@ static int zswap_rb_insert(struct rb_root *root, struct zswap_entry *entry, return 0; } +static void zswap_rb_erase(struct rb_root *root, struct zswap_entry *entry) +{ + if (!RB_EMPTY_NODE(&entry->rbnode)) { + rb_erase(&entry->rbnode, root); + RB_CLEAR_NODE(&entry->rbnode); + } +} + +/* + * Carries out the common pattern of freeing and entry's zsmalloc allocation, + * freeing the entry itself, and decrementing the number of stored pages. + */ +static void zswap_free_entry(struct zswap_tree *tree, + struct zswap_entry *entry) +{ + zbud_free(tree->pool, entry->handle); + zswap_entry_cache_free(entry); + atomic_dec(&zswap_stored_pages); + zswap_pool_pages = zbud_get_pool_size(tree->pool); +} + +/* caller must hold the tree lock */ +static void zswap_entry_get(struct zswap_entry *entry) +{ + entry->refcount++; +} + +/* caller must hold the tree lock +* remove from the tree and free it, if nobody reference the entry +*/ +static void zswap_entry_put(struct zswap_tree *tree, + struct zswap_entry *entry) +{ + int refcount = --entry->refcount; + + BUG_ON(refcount < 0); + if (refcount == 0) { + zswap_rb_erase(&tree->rbroot, entry); + zswap_free_entry(tree, entry); + } +} + +/* caller must hold the tree lock */ +static struct zswap_entry *zswap_entry_find_get(struct rb_root *root, + pgoff_t offset) +{ + struct zswap_entry *entry = NULL; + + entry = zswap_rb_search(root, offset); + if (entry) + zswap_entry_get(entry); + + return entry; +} + /********************************* * per-cpu code **********************************/ @@ -368,18 +411,6 @@ static bool zswap_is_full(void) zswap_pool_pages); } -/* - * Carries out the common pattern of freeing and entry's zsmalloc allocation, - * freeing the entry itself, and decrementing the number of stored pages. - */ -static void zswap_free_entry(struct zswap_tree *tree, struct zswap_entry *entry) -{ - zbud_free(tree->pool, entry->handle); - zswap_entry_cache_free(entry); - atomic_dec(&zswap_stored_pages); - zswap_pool_pages = zbud_get_pool_size(tree->pool); -} - /********************************* * writeback code **********************************/ @@ -387,7 +418,7 @@ static void zswap_free_entry(struct zswap_tree *tree, struct zswap_entry *entry) enum zswap_get_swap_ret { ZSWAP_SWAPCACHE_NEW, ZSWAP_SWAPCACHE_EXIST, - ZSWAP_SWAPCACHE_NOMEM + ZSWAP_SWAPCACHE_FAIL, }; /* @@ -401,15 +432,16 @@ enum zswap_get_swap_ret { * added to the swap cache, and returned in retpage. * * If success, the swap cache page is returned in retpage - * Returns 0 if page was already in the swap cache, page is not locked - * Returns 1 if the new page needs to be populated, page is locked - * Returns <0 on error + * Returns ZSWAP_SWAPCACHE_EXIST if page was already in the swap cache + * Returns ZSWAP_SWAPCACHE_NEW if the new page needs to be populated, + * the new page is added to swapcache and locked + * Returns ZSWAP_SWAPCACHE_FAIL on error */ static int zswap_get_swap_cache_page(swp_entry_t entry, struct page **retpage) { struct page *found_page, *new_page = NULL; - struct address_space *swapper_space = &swapper_spaces[swp_type(entry)]; + struct address_space *swapper_space = swap_address_space(entry); int err; *retpage = NULL; @@ -475,7 +507,7 @@ static int zswap_get_swap_cache_page(swp_entry_t entry, if (new_page) page_cache_release(new_page); if (!found_page) - return ZSWAP_SWAPCACHE_NOMEM; + return ZSWAP_SWAPCACHE_FAIL; *retpage = found_page; return ZSWAP_SWAPCACHE_EXIST; } @@ -502,7 +534,7 @@ static int zswap_writeback_entry(struct zbud_pool *pool, unsigned long handle) struct page *page; u8 *src, *dst; unsigned int dlen; - int ret, refcount; + int ret; struct writeback_control wbc = { .sync_mode = WB_SYNC_NONE, }; @@ -517,23 +549,22 @@ static int zswap_writeback_entry(struct zbud_pool *pool, unsigned long handle) /* find and ref zswap entry */ spin_lock(&tree->lock); - entry = zswap_rb_search(&tree->rbroot, offset); + entry = zswap_entry_find_get(&tree->rbroot, offset); if (!entry) { /* entry was invalidated */ spin_unlock(&tree->lock); return 0; } - zswap_entry_get(entry); spin_unlock(&tree->lock); BUG_ON(offset != entry->offset); /* try to allocate swap cache page */ switch (zswap_get_swap_cache_page(swpentry, &page)) { - case ZSWAP_SWAPCACHE_NOMEM: /* no memory */ + case ZSWAP_SWAPCACHE_FAIL: /* no memory or invalidate happened */ ret = -ENOMEM; goto fail; - case ZSWAP_SWAPCACHE_EXIST: /* page is unlocked */ + case ZSWAP_SWAPCACHE_EXIST: /* page is already in the swap cache, ignore for now */ page_cache_release(page); ret = -EEXIST; @@ -556,43 +587,44 @@ static int zswap_writeback_entry(struct zbud_pool *pool, unsigned long handle) SetPageUptodate(page); } + /* move it to the tail of the inactive list after end_writeback */ + SetPageReclaim(page); + /* start writeback */ __swap_writepage(page, &wbc, end_swap_bio_write); page_cache_release(page); zswap_written_back_pages++; spin_lock(&tree->lock); - /* drop local reference */ - zswap_entry_put(entry); - /* drop the initial reference from entry creation */ - refcount = zswap_entry_put(entry); + zswap_entry_put(tree, entry); /* - * There are three possible values for refcount here: - * (1) refcount is 1, load is in progress, unlink from rbtree, - * load will free - * (2) refcount is 0, (normal case) entry is valid, - * remove from rbtree and free entry - * (3) refcount is -1, invalidate happened during writeback, - * free entry - */ - if (refcount >= 0) { - /* no invalidate yet, remove from rbtree */ - rb_erase(&entry->rbnode, &tree->rbroot); - } + * There are two possible situations for entry here: + * (1) refcount is 1(normal case), entry is valid and on the tree + * (2) refcount is 0, entry is freed and not on the tree + * because invalidate happened during writeback + * search the tree and free the entry if find entry + */ + if (entry == zswap_rb_search(&tree->rbroot, offset)) + zswap_entry_put(tree, entry); spin_unlock(&tree->lock); - if (refcount <= 0) { - /* free the entry */ - zswap_free_entry(tree, entry); - return 0; - } - return -EAGAIN; + goto end; + + /* + * if we get here due to ZSWAP_SWAPCACHE_EXIST + * a load may happening concurrently + * it is safe and okay to not free the entry + * if we free the entry in the following put + * it it either okay to return !0 + */ fail: spin_lock(&tree->lock); - zswap_entry_put(entry); + zswap_entry_put(tree, entry); spin_unlock(&tree->lock); + +end: return ret; } @@ -676,11 +708,8 @@ static int zswap_frontswap_store(unsigned type, pgoff_t offset, if (ret == -EEXIST) { zswap_duplicate_entry++; /* remove from rbtree */ - rb_erase(&dupentry->rbnode, &tree->rbroot); - if (!zswap_entry_put(dupentry)) { - /* free */ - zswap_free_entry(tree, dupentry); - } + zswap_rb_erase(&tree->rbroot, dupentry); + zswap_entry_put(tree, dupentry); } } while (ret == -EEXIST); spin_unlock(&tree->lock); @@ -709,17 +738,16 @@ static int zswap_frontswap_load(unsigned type, pgoff_t offset, struct zswap_entry *entry; u8 *src, *dst; unsigned int dlen; - int refcount, ret; + int ret; /* find */ spin_lock(&tree->lock); - entry = zswap_rb_search(&tree->rbroot, offset); + entry = zswap_entry_find_get(&tree->rbroot, offset); if (!entry) { /* entry was written back */ spin_unlock(&tree->lock); return -1; } - zswap_entry_get(entry); spin_unlock(&tree->lock); /* decompress */ @@ -734,22 +762,9 @@ static int zswap_frontswap_load(unsigned type, pgoff_t offset, BUG_ON(ret); spin_lock(&tree->lock); - refcount = zswap_entry_put(entry); - if (likely(refcount)) { - spin_unlock(&tree->lock); - return 0; - } + zswap_entry_put(tree, entry); spin_unlock(&tree->lock); - /* - * We don't have to unlink from the rbtree because - * zswap_writeback_entry() or zswap_frontswap_invalidate page() - * has already done this for us if we are the last reference. - */ - /* free */ - - zswap_free_entry(tree, entry); - return 0; } @@ -758,7 +773,6 @@ static void zswap_frontswap_invalidate_page(unsigned type, pgoff_t offset) { struct zswap_tree *tree = zswap_trees[type]; struct zswap_entry *entry; - int refcount; /* find */ spin_lock(&tree->lock); @@ -770,52 +784,33 @@ static void zswap_frontswap_invalidate_page(unsigned type, pgoff_t offset) } /* remove from rbtree */ - rb_erase(&entry->rbnode, &tree->rbroot); + zswap_rb_erase(&tree->rbroot, entry); /* drop the initial reference from entry creation */ - refcount = zswap_entry_put(entry); + zswap_entry_put(tree, entry); spin_unlock(&tree->lock); - - if (refcount) { - /* writeback in progress, writeback will free */ - return; - } - - /* free */ - zswap_free_entry(tree, entry); } /* frees all zswap entries for the given swap type */ static void zswap_frontswap_invalidate_area(unsigned type) { struct zswap_tree *tree = zswap_trees[type]; - struct rb_node *node; - struct zswap_entry *entry; + struct zswap_entry *entry, *n; if (!tree) return; /* walk the tree and free everything */ spin_lock(&tree->lock); - /* - * TODO: Even though this code should not be executed because - * the try_to_unuse() in swapoff should have emptied the tree, - * it is very wasteful to rebalance the tree after every - * removal when we are freeing the whole tree. - * - * If post-order traversal code is ever added to the rbtree - * implementation, it should be used here. - */ - while ((node = rb_first(&tree->rbroot))) { - entry = rb_entry(node, struct zswap_entry, rbnode); - rb_erase(&entry->rbnode, &tree->rbroot); - zbud_free(tree->pool, entry->handle); - zswap_entry_cache_free(entry); - atomic_dec(&zswap_stored_pages); - } + rbtree_postorder_for_each_entry_safe(entry, n, &tree->rbroot, rbnode) + zswap_free_entry(tree, entry); tree->rbroot = RB_ROOT; spin_unlock(&tree->lock); + + zbud_destroy_pool(tree->pool); + kfree(tree); + zswap_trees[type] = NULL; } static struct zbud_ops zswap_zbud_ops = { |