diff options
Diffstat (limited to 'mm')
| -rw-r--r-- | mm/hugetlb.c | 9 | ||||
| -rw-r--r-- | mm/kmemleak.c | 158 | ||||
| -rw-r--r-- | mm/memcontrol.c | 6 | ||||
| -rw-r--r-- | mm/memory.c | 37 | ||||
| -rw-r--r-- | mm/page_alloc.c | 20 | ||||
| -rw-r--r-- | mm/percpu.c | 12 | ||||
| -rw-r--r-- | mm/shmem.c | 53 | ||||
| -rw-r--r-- | mm/vmscan.c | 124 |
8 files changed, 282 insertions, 137 deletions
diff --git a/mm/hugetlb.c b/mm/hugetlb.c index ea8c3a4cd2ae..5f34bd8dda34 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -2508,6 +2508,7 @@ static int hugetlb_no_page(struct mm_struct *mm, struct vm_area_struct *vma, { struct hstate *h = hstate_vma(vma); int ret = VM_FAULT_SIGBUS; + int anon_rmap = 0; pgoff_t idx; unsigned long size; struct page *page; @@ -2562,14 +2563,13 @@ retry: spin_lock(&inode->i_lock); inode->i_blocks += blocks_per_huge_page(h); spin_unlock(&inode->i_lock); - page_dup_rmap(page); } else { lock_page(page); if (unlikely(anon_vma_prepare(vma))) { ret = VM_FAULT_OOM; goto backout_unlocked; } - hugepage_add_new_anon_rmap(page, vma, address); + anon_rmap = 1; } } else { /* @@ -2582,7 +2582,6 @@ retry: VM_FAULT_SET_HINDEX(h - hstates); goto backout_unlocked; } - page_dup_rmap(page); } /* @@ -2606,6 +2605,10 @@ retry: if (!huge_pte_none(huge_ptep_get(ptep))) goto backout; + if (anon_rmap) + 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) && (vma->vm_flags & VM_SHARED))); set_huge_pte_at(mm, address, ptep, new_pte); diff --git a/mm/kmemleak.c b/mm/kmemleak.c index f3b2a00fe9c1..c833addd94d7 100644 --- a/mm/kmemleak.c +++ b/mm/kmemleak.c @@ -100,6 +100,7 @@ #include <linux/kmemcheck.h> #include <linux/kmemleak.h> +#include <linux/memory_hotplug.h> /* * Kmemleak configuration and common defines. @@ -196,7 +197,9 @@ static atomic_t kmemleak_enabled = ATOMIC_INIT(0); static atomic_t kmemleak_initialized = ATOMIC_INIT(0); /* enables or disables early logging of the memory operations */ static atomic_t kmemleak_early_log = ATOMIC_INIT(1); -/* set if a fata kmemleak error has occurred */ +/* set if a kmemleak warning was issued */ +static atomic_t kmemleak_warning = ATOMIC_INIT(0); +/* set if a fatal kmemleak error has occurred */ static atomic_t kmemleak_error = ATOMIC_INIT(0); /* minimum and maximum address that may be valid pointers */ @@ -228,8 +231,10 @@ static int kmemleak_skip_disable; /* kmemleak operation type for early logging */ enum { KMEMLEAK_ALLOC, + KMEMLEAK_ALLOC_PERCPU, KMEMLEAK_FREE, KMEMLEAK_FREE_PART, + KMEMLEAK_FREE_PERCPU, KMEMLEAK_NOT_LEAK, KMEMLEAK_IGNORE, KMEMLEAK_SCAN_AREA, @@ -259,9 +264,10 @@ static void kmemleak_disable(void); /* * Print a warning and dump the stack trace. */ -#define kmemleak_warn(x...) do { \ - pr_warning(x); \ - dump_stack(); \ +#define kmemleak_warn(x...) do { \ + pr_warning(x); \ + dump_stack(); \ + atomic_set(&kmemleak_warning, 1); \ } while (0) /* @@ -403,8 +409,8 @@ static struct kmemleak_object *lookup_object(unsigned long ptr, int alias) object = prio_tree_entry(node, struct kmemleak_object, tree_node); if (!alias && object->pointer != ptr) { - pr_warning("Found object by alias at 0x%08lx\n", ptr); - dump_stack(); + kmemleak_warn("Found object by alias at 0x%08lx\n", + ptr); dump_object_info(object); object = NULL; } @@ -794,9 +800,13 @@ static void __init log_early(int op_type, const void *ptr, size_t size, unsigned long flags; struct early_log *log; + if (atomic_read(&kmemleak_error)) { + /* kmemleak stopped recording, just count the requests */ + crt_early_log++; + return; + } + if (crt_early_log >= ARRAY_SIZE(early_log)) { - pr_warning("Early log buffer exceeded, " - "please increase DEBUG_KMEMLEAK_EARLY_LOG_SIZE\n"); kmemleak_disable(); return; } @@ -811,8 +821,7 @@ static void __init log_early(int op_type, const void *ptr, size_t size, log->ptr = ptr; log->size = size; log->min_count = min_count; - if (op_type == KMEMLEAK_ALLOC) - log->trace_len = __save_stack_trace(log->trace); + log->trace_len = __save_stack_trace(log->trace); crt_early_log++; local_irq_restore(flags); } @@ -846,6 +855,20 @@ out: rcu_read_unlock(); } +/* + * Log an early allocated block and populate the stack trace. + */ +static void early_alloc_percpu(struct early_log *log) +{ + unsigned int cpu; + const void __percpu *ptr = log->ptr; + + for_each_possible_cpu(cpu) { + log->ptr = per_cpu_ptr(ptr, cpu); + early_alloc(log); + } +} + /** * kmemleak_alloc - register a newly allocated object * @ptr: pointer to beginning of the object @@ -873,6 +896,34 @@ void __ref kmemleak_alloc(const void *ptr, size_t size, int min_count, EXPORT_SYMBOL_GPL(kmemleak_alloc); /** + * kmemleak_alloc_percpu - register a newly allocated __percpu object + * @ptr: __percpu pointer to beginning of the object + * @size: size of the object + * + * This function is called from the kernel percpu allocator when a new object + * (memory block) is allocated (alloc_percpu). It assumes GFP_KERNEL + * allocation. + */ +void __ref kmemleak_alloc_percpu(const void __percpu *ptr, size_t size) +{ + unsigned int cpu; + + pr_debug("%s(0x%p, %zu)\n", __func__, ptr, size); + + /* + * Percpu allocations are only scanned and not reported as leaks + * (min_count is set to 0). + */ + if (atomic_read(&kmemleak_enabled) && ptr && !IS_ERR(ptr)) + for_each_possible_cpu(cpu) + create_object((unsigned long)per_cpu_ptr(ptr, cpu), + size, 0, GFP_KERNEL); + else if (atomic_read(&kmemleak_early_log)) + log_early(KMEMLEAK_ALLOC_PERCPU, ptr, size, 0); +} +EXPORT_SYMBOL_GPL(kmemleak_alloc_percpu); + +/** * kmemleak_free - unregister a previously registered object * @ptr: pointer to beginning of the object * @@ -911,6 +962,28 @@ void __ref kmemleak_free_part(const void *ptr, size_t size) EXPORT_SYMBOL_GPL(kmemleak_free_part); /** + * kmemleak_free_percpu - unregister a previously registered __percpu object + * @ptr: __percpu pointer to beginning of the object + * + * This function is called from the kernel percpu allocator when an object + * (memory block) is freed (free_percpu). + */ +void __ref kmemleak_free_percpu(const void __percpu *ptr) +{ + unsigned int cpu; + + pr_debug("%s(0x%p)\n", __func__, ptr); + + if (atomic_read(&kmemleak_enabled) && ptr && !IS_ERR(ptr)) + for_each_possible_cpu(cpu) + delete_object_full((unsigned long)per_cpu_ptr(ptr, + cpu)); + else if (atomic_read(&kmemleak_early_log)) + log_early(KMEMLEAK_FREE_PERCPU, ptr, 0, 0); +} +EXPORT_SYMBOL_GPL(kmemleak_free_percpu); + +/** * kmemleak_not_leak - mark an allocated object as false positive * @ptr: pointer to beginning of the object * @@ -1220,9 +1293,9 @@ static void kmemleak_scan(void) #endif /* - * Struct page scanning for each node. The code below is not yet safe - * with MEMORY_HOTPLUG. + * Struct page scanning for each node. */ + lock_memory_hotplug(); for_each_online_node(i) { pg_data_t *pgdat = NODE_DATA(i); unsigned long start_pfn = pgdat->node_start_pfn; @@ -1241,6 +1314,7 @@ static void kmemleak_scan(void) scan_block(page, page + 1, NULL, 1); } } + unlock_memory_hotplug(); /* * Scanning the task stacks (may introduce false negatives). @@ -1467,9 +1541,6 @@ static const struct seq_operations kmemleak_seq_ops = { static int kmemleak_open(struct inode *inode, struct file *file) { - if (!atomic_read(&kmemleak_enabled)) - return -EBUSY; - return seq_open(file, &kmemleak_seq_ops); } @@ -1543,6 +1614,9 @@ static ssize_t kmemleak_write(struct file *file, const char __user *user_buf, int buf_size; int ret; + if (!atomic_read(&kmemleak_enabled)) + return -EBUSY; + buf_size = min(size, (sizeof(buf) - 1)); if (strncpy_from_user(buf, user_buf, buf_size) < 0) return -EFAULT; @@ -1602,20 +1676,24 @@ static const struct file_operations kmemleak_fops = { }; /* - * Perform the freeing of the kmemleak internal objects after waiting for any - * current memory scan to complete. + * Stop the memory scanning thread and free the kmemleak internal objects if + * no previous scan thread (otherwise, kmemleak may still have some useful + * information on memory leaks). */ static void kmemleak_do_cleanup(struct work_struct *work) { struct kmemleak_object *object; + bool cleanup = scan_thread == NULL; mutex_lock(&scan_mutex); stop_scan_thread(); - rcu_read_lock(); - list_for_each_entry_rcu(object, &object_list, object_list) - delete_object_full(object->pointer); - rcu_read_unlock(); + if (cleanup) { + rcu_read_lock(); + list_for_each_entry_rcu(object, &object_list, object_list) + delete_object_full(object->pointer); + rcu_read_unlock(); + } mutex_unlock(&scan_mutex); } @@ -1632,7 +1710,6 @@ static void kmemleak_disable(void) return; /* stop any memory operation tracing */ - atomic_set(&kmemleak_early_log, 0); atomic_set(&kmemleak_enabled, 0); /* check whether it is too early for a kernel thread */ @@ -1659,6 +1736,17 @@ static int kmemleak_boot_config(char *str) } early_param("kmemleak", kmemleak_boot_config); +static void __init print_log_trace(struct early_log *log) +{ + struct stack_trace trace; + + trace.nr_entries = log->trace_len; + trace.entries = log->trace; + + pr_notice("Early log backtrace:\n"); + print_stack_trace(&trace, 2); +} + /* * Kmemleak initialization. */ @@ -1681,12 +1769,18 @@ void __init kmemleak_init(void) scan_area_cache = KMEM_CACHE(kmemleak_scan_area, SLAB_NOLEAKTRACE); INIT_PRIO_TREE_ROOT(&object_tree_root); + if (crt_early_log >= ARRAY_SIZE(early_log)) + pr_warning("Early log buffer exceeded (%d), please increase " + "DEBUG_KMEMLEAK_EARLY_LOG_SIZE\n", crt_early_log); + /* the kernel is still in UP mode, so disabling the IRQs is enough */ local_irq_save(flags); - if (!atomic_read(&kmemleak_error)) { + atomic_set(&kmemleak_early_log, 0); + if (atomic_read(&kmemleak_error)) { + local_irq_restore(flags); + return; + } else atomic_set(&kmemleak_enabled, 1); - atomic_set(&kmemleak_early_log, 0); - } local_irq_restore(flags); /* @@ -1701,12 +1795,18 @@ void __init kmemleak_init(void) case KMEMLEAK_ALLOC: early_alloc(log); break; + case KMEMLEAK_ALLOC_PERCPU: + early_alloc_percpu(log); + break; case KMEMLEAK_FREE: kmemleak_free(log->ptr); break; case KMEMLEAK_FREE_PART: kmemleak_free_part(log->ptr, log->size); break; + case KMEMLEAK_FREE_PERCPU: + kmemleak_free_percpu(log->ptr); + break; case KMEMLEAK_NOT_LEAK: kmemleak_not_leak(log->ptr); break; @@ -1720,7 +1820,13 @@ void __init kmemleak_init(void) kmemleak_no_scan(log->ptr); break; default: - WARN_ON(1); + kmemleak_warn("Unknown early log operation: %d\n", + log->op_type); + } + + if (atomic_read(&kmemleak_warning)) { + print_log_trace(log); + atomic_set(&kmemleak_warning, 0); } } } diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 3dbff4dcde35..556859fec4ef 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -379,7 +379,7 @@ static void mem_cgroup_put(struct mem_cgroup *memcg); static bool mem_cgroup_is_root(struct mem_cgroup *memcg); void sock_update_memcg(struct sock *sk) { - if (static_branch(&memcg_socket_limit_enabled)) { + if (mem_cgroup_sockets_enabled) { struct mem_cgroup *memcg; BUG_ON(!sk->sk_prot->proto_cgroup); @@ -411,7 +411,7 @@ EXPORT_SYMBOL(sock_update_memcg); void sock_release_memcg(struct sock *sk) { - if (static_branch(&memcg_socket_limit_enabled) && sk->sk_cgrp) { + if (mem_cgroup_sockets_enabled && sk->sk_cgrp) { struct mem_cgroup *memcg; WARN_ON(!sk->sk_cgrp->memcg); memcg = sk->sk_cgrp->memcg; @@ -3247,7 +3247,7 @@ int mem_cgroup_prepare_migration(struct page *page, ctype = MEM_CGROUP_CHARGE_TYPE_CACHE; else ctype = MEM_CGROUP_CHARGE_TYPE_SHMEM; - __mem_cgroup_commit_charge(memcg, page, 1, pc, ctype); + __mem_cgroup_commit_charge(memcg, newpage, 1, pc, ctype); return ret; } diff --git a/mm/memory.c b/mm/memory.c index 5e30583c2605..fa2f04e0337c 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -878,15 +878,24 @@ copy_one_pte(struct mm_struct *dst_mm, struct mm_struct *src_mm, } if (likely(!non_swap_entry(entry))) rss[MM_SWAPENTS]++; - else if (is_write_migration_entry(entry) && - is_cow_mapping(vm_flags)) { - /* - * COW mappings require pages in both parent - * and child to be set to read. - */ - make_migration_entry_read(&entry); - pte = swp_entry_to_pte(entry); - set_pte_at(src_mm, addr, src_pte, pte); + else if (is_migration_entry(entry)) { + page = migration_entry_to_page(entry); + + if (PageAnon(page)) + rss[MM_ANONPAGES]++; + else + rss[MM_FILEPAGES]++; + + if (is_write_migration_entry(entry) && + is_cow_mapping(vm_flags)) { + /* + * COW mappings require pages in both + * parent and child to be set to read. + */ + make_migration_entry_read(&entry); + pte = swp_entry_to_pte(entry); + set_pte_at(src_mm, addr, src_pte, pte); + } } } goto out_set_pte; @@ -1191,6 +1200,16 @@ again: if (!non_swap_entry(entry)) rss[MM_SWAPENTS]--; + else if (is_migration_entry(entry)) { + struct page *page; + + page = migration_entry_to_page(entry); + + if (PageAnon(page)) + rss[MM_ANONPAGES]--; + else + rss[MM_FILEPAGES]--; + } if (unlikely(!free_swap_and_cache(entry))) print_bad_pte(vma, addr, ptent, NULL); } diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 0027d8f4a1bb..d2186ecb36f7 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -5413,7 +5413,25 @@ __count_immobile_pages(struct zone *zone, struct page *page, int count) bool is_pageblock_removable_nolock(struct page *page) { - struct zone *zone = page_zone(page); + struct zone *zone; + unsigned long pfn; + + /* + * We have to be careful here because we are iterating over memory + * sections which are not zone aware so we might end up outside of + * the zone but still within the section. + * We have to take care about the node as well. If the node is offline + * its NODE_DATA will be NULL - see page_zone. + */ + if (!node_online(page_to_nid(page))) + return false; + + zone = page_zone(page); + pfn = page_to_pfn(page); + if (zone->zone_start_pfn > pfn || + zone->zone_start_pfn + zone->spanned_pages <= pfn) + return false; + return __count_immobile_pages(zone, page, 0); } diff --git a/mm/percpu.c b/mm/percpu.c index 716eb4acf2fc..f47af9123af7 100644 --- a/mm/percpu.c +++ b/mm/percpu.c @@ -67,6 +67,7 @@ #include <linux/spinlock.h> #include <linux/vmalloc.h> #include <linux/workqueue.h> +#include <linux/kmemleak.h> #include <asm/cacheflush.h> #include <asm/sections.h> @@ -710,6 +711,7 @@ static void __percpu *pcpu_alloc(size_t size, size_t align, bool reserved) const char *err; int slot, off, new_alloc; unsigned long flags; + void __percpu *ptr; if (unlikely(!size || size > PCPU_MIN_UNIT_SIZE || align > PAGE_SIZE)) { WARN(true, "illegal size (%zu) or align (%zu) for " @@ -802,7 +804,9 @@ area_found: mutex_unlock(&pcpu_alloc_mutex); /* return address relative to base address */ - return __addr_to_pcpu_ptr(chunk->base_addr + off); + ptr = __addr_to_pcpu_ptr(chunk->base_addr + off); + kmemleak_alloc_percpu(ptr, size); + return ptr; fail_unlock: spin_unlock_irqrestore(&pcpu_lock, flags); @@ -916,6 +920,8 @@ void free_percpu(void __percpu *ptr) if (!ptr) return; + kmemleak_free_percpu(ptr); + addr = __pcpu_ptr_to_addr(ptr); spin_lock_irqsave(&pcpu_lock, flags); @@ -1639,6 +1645,8 @@ int __init pcpu_embed_first_chunk(size_t reserved_size, size_t dyn_size, rc = -ENOMEM; goto out_free_areas; } + /* kmemleak tracks the percpu allocations separately */ + kmemleak_free(ptr); areas[group] = ptr; base = min(ptr, base); @@ -1753,6 +1761,8 @@ int __init pcpu_page_first_chunk(size_t reserved_size, "for cpu%u\n", psize_str, cpu); goto enomem; } + /* kmemleak tracks the percpu allocations separately */ + kmemleak_free(ptr); pages[j++] = virt_to_page(ptr); } diff --git a/mm/shmem.c b/mm/shmem.c index feead1943d92..269d049294ab 100644 --- a/mm/shmem.c +++ b/mm/shmem.c @@ -379,7 +379,7 @@ static int shmem_free_swap(struct address_space *mapping, /* * Pagevec may contain swap entries, so shuffle up pages before releasing. */ -static void shmem_pagevec_release(struct pagevec *pvec) +static void shmem_deswap_pagevec(struct pagevec *pvec) { int i, j; @@ -389,7 +389,36 @@ static void shmem_pagevec_release(struct pagevec *pvec) pvec->pages[j++] = page; } pvec->nr = j; - pagevec_release(pvec); +} + +/* + * SysV IPC SHM_UNLOCK restore Unevictable pages to their evictable lists. + */ +void shmem_unlock_mapping(struct address_space *mapping) +{ + struct pagevec pvec; + pgoff_t indices[PAGEVEC_SIZE]; + pgoff_t index = 0; + + pagevec_init(&pvec, 0); + /* + * Minor point, but we might as well stop if someone else SHM_LOCKs it. + */ + while (!mapping_unevictable(mapping)) { + /* + * Avoid pagevec_lookup(): find_get_pages() returns 0 as if it + * has finished, if it hits a row of PAGEVEC_SIZE swap entries. + */ + pvec.nr = shmem_find_get_pages_and_swap(mapping, index, + PAGEVEC_SIZE, pvec.pages, indices); + if (!pvec.nr) + break; + index = indices[pvec.nr - 1] + 1; + shmem_deswap_pagevec(&pvec); + check_move_unevictable_pages(pvec.pages, pvec.nr); + pagevec_release(&pvec); + cond_resched(); + } } /* @@ -440,7 +469,8 @@ void shmem_truncate_range(struct inode *inode, loff_t lstart, loff_t lend) } unlock_page(page); } - shmem_pagevec_release(&pvec); + shmem_deswap_pagevec(&pvec); + pagevec_release(&pvec); mem_cgroup_uncharge_end(); cond_resched(); index++; @@ -470,7 +500,8 @@ void shmem_truncate_range(struct inode *inode, loff_t lstart, loff_t lend) continue; } if (index == start && indices[0] > end) { - shmem_pagevec_release(&pvec); + shmem_deswap_pagevec(&pvec); + pagevec_release(&pvec); break; } mem_cgroup_uncharge_start(); @@ -494,7 +525,8 @@ void shmem_truncate_range(struct inode *inode, loff_t lstart, loff_t lend) } unlock_page(page); } - shmem_pagevec_release(&pvec); + shmem_deswap_pagevec(&pvec); + pagevec_release(&pvec); mem_cgroup_uncharge_end(); index++; } @@ -1068,13 +1100,6 @@ int shmem_lock(struct file *file, int lock, struct user_struct *user) user_shm_unlock(inode->i_size, user); info->flags &= ~VM_LOCKED; mapping_clear_unevictable(file->f_mapping); - /* - * Ensure that a racing putback_lru_page() can see - * the pages of this mapping are evictable when we - * skip them due to !PageLRU during the scan. - */ - smp_mb__after_clear_bit(); - scan_mapping_unevictable_pages(file->f_mapping); } retval = 0; @@ -2445,6 +2470,10 @@ int shmem_lock(struct file *file, int lock, struct user_struct *user) return 0; } +void shmem_unlock_mapping(struct address_space *mapping) +{ +} + void shmem_truncate_range(struct inode *inode, loff_t lstart, loff_t lend) { truncate_inode_pages_range(inode->i_mapping, lstart, lend); diff --git a/mm/vmscan.c b/mm/vmscan.c index 2880396f7953..c52b23552659 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -26,7 +26,6 @@ #include <linux/buffer_head.h> /* for try_to_release_page(), buffer_heads_over_limit */ #include <linux/mm_inline.h> -#include <linux/pagevec.h> #include <linux/backing-dev.h> #include <linux/rmap.h> #include <linux/topology.h> @@ -661,7 +660,7 @@ redo: * When racing with an mlock or AS_UNEVICTABLE clearing * (page is unlocked) make sure that if the other thread * does not observe our setting of PG_lru and fails - * isolation/check_move_unevictable_page, + * isolation/check_move_unevictable_pages, * we see PG_mlocked/AS_UNEVICTABLE cleared below and move * the page back to the evictable list. * @@ -3499,100 +3498,61 @@ int page_evictable(struct page *page, struct vm_area_struct *vma) return 1; } +#ifdef CONFIG_SHMEM /** - * check_move_unevictable_page - check page for evictability and move to appropriate zone lru list - * @page: page to check evictability and move to appropriate lru list - * @zone: zone page is in + * check_move_unevictable_pages - check pages for evictability and move to appropriate zone lru list + * @pages: array of pages to check + * @nr_pages: number of pages to check * - * Checks a page for evictability and moves the page to the appropriate - * zone lru list. + * Checks pages for evictability and moves them to the appropriate lru list. * - * Restrictions: zone->lru_lock must be held, page must be on LRU and must - * have PageUnevictable set. + * This function is only used for SysV IPC SHM_UNLOCK. */ -static void check_move_unevictable_page(struct page *page, struct zone *zone) +void check_move_unevictable_pages(struct page **pages, int nr_pages) { struct lruvec *lruvec; + struct zone *zone = NULL; + int pgscanned = 0; + int pgrescued = 0; + int i; - VM_BUG_ON(PageActive(page)); -retry: - ClearPageUnevictable(page); - if (page_evictable(page, NULL)) { - enum lru_list l = page_lru_base_type(page); - - __dec_zone_state(zone, NR_UNEVICTABLE); - lruvec = mem_cgroup_lru_move_lists(zone, page, - LRU_UNEVICTABLE, l); - list_move(&page->lru, &lruvec->lists[l]); - __inc_zone_state(zone, NR_INACTIVE_ANON + l); - __count_vm_event(UNEVICTABLE_PGRESCUED); - } else { - /* - * rotate unevictable list - */ - SetPageUnevictable(page); - lruvec = mem_cgroup_lru_move_lists(zone, page, LRU_UNEVICTABLE, - LRU_UNEVICTABLE); - list_move(&page->lru, &lruvec->lists[LRU_UNEVICTABLE]); - if (page_evictable(page, NULL)) - goto retry; - } -} - -/** - * scan_mapping_unevictable_pages - scan an address space for evictable pages - * @mapping: struct address_space to scan for evictable pages - * - * Scan all pages in mapping. Check unevictable pages for - * evictability and move them to the appropriate zone lru list. - */ -void scan_mapping_unevictable_pages(struct address_space *mapping) -{ - pgoff_t next = 0; - pgoff_t end = (i_size_read(mapping->host) + PAGE_CACHE_SIZE - 1) >> - PAGE_CACHE_SHIFT; - struct zone *zone; - struct pagevec pvec; - - if (mapping->nrpages == 0) - return; - - pagevec_init(&pvec, 0); - while (next < end && - pagevec_lookup(&pvec, mapping, next, PAGEVEC_SIZE)) { - int i; - int pg_scanned = 0; - - zone = NULL; - - for (i = 0; i < pagevec_count(&pvec); i++) { - struct page *page = pvec.pages[i]; - pgoff_t page_index = page->index; - struct zone *pagezone = page_zone(page); + for (i = 0; i < nr_pages; i++) { + struct page *page = pages[i]; + struct zone *pagezone; - pg_scanned++; - if (page_index > next) - next = page_index; - next++; + pgscanned++; + pagezone = page_zone(page); + if (pagezone != zone) { + if (zone) + spin_unlock_irq(&zone->lru_lock); + zone = pagezone; + spin_lock_irq(&zone->lru_lock); + } - if (pagezone != zone) { - if (zone) - spin_unlock_irq(&zone->lru_lock); - zone = pagezone; - spin_lock_irq(&zone->lru_lock); - } + if (!PageLRU(page) || !PageUnevictable(page)) + continue; - if (PageLRU(page) && PageUnevictable(page)) - check_move_unevictable_page(page, zone); + if (page_evictable(page, NULL)) { + enum lru_list lru = page_lru_base_type(page); + + VM_BUG_ON(PageActive(page)); + ClearPageUnevictable(page); + __dec_zone_state(zone, NR_UNEVICTABLE); + lruvec = mem_cgroup_lru_move_lists(zone, page, + LRU_UNEVICTABLE, lru); + list_move(&page->lru, &lruvec->lists[lru]); + __inc_zone_state(zone, NR_INACTIVE_ANON + lru); + pgrescued++; } - if (zone) - spin_unlock_irq(&zone->lru_lock); - pagevec_release(&pvec); - - count_vm_events(UNEVICTABLE_PGSCANNED, pg_scanned); } + if (zone) { + __count_vm_events(UNEVICTABLE_PGRESCUED, pgrescued); + __count_vm_events(UNEVICTABLE_PGSCANNED, pgscanned); + spin_unlock_irq(&zone->lru_lock); + } } +#endif /* CONFIG_SHMEM */ static void warn_scan_unevictable_pages(void) { |