diff options
Diffstat (limited to 'mm')
-rw-r--r-- | mm/compaction.c | 1 | ||||
-rw-r--r-- | mm/filemap.c | 8 | ||||
-rw-r--r-- | mm/hugetlb.c | 3 | ||||
-rw-r--r-- | mm/ksm.c | 7 | ||||
-rw-r--r-- | mm/memcontrol.c | 19 | ||||
-rw-r--r-- | mm/memory-failure.c | 8 | ||||
-rw-r--r-- | mm/memory_hotplug.c | 31 | ||||
-rw-r--r-- | mm/mempolicy.c | 3 | ||||
-rw-r--r-- | mm/migrate.c | 2 | ||||
-rw-r--r-- | mm/mmap.c | 16 | ||||
-rw-r--r-- | mm/nommu.c | 28 | ||||
-rw-r--r-- | mm/page-writeback.c | 2 | ||||
-rw-r--r-- | mm/page_alloc.c | 19 | ||||
-rw-r--r-- | mm/percpu.c | 10 | ||||
-rw-r--r-- | mm/shmem.c | 9 | ||||
-rw-r--r-- | mm/slab.c | 40 | ||||
-rw-r--r-- | mm/slob.c | 5 | ||||
-rw-r--r-- | mm/slub.c | 44 | ||||
-rw-r--r-- | mm/truncate.c | 4 | ||||
-rw-r--r-- | mm/util.c | 21 | ||||
-rw-r--r-- | mm/vmalloc.c | 28 | ||||
-rw-r--r-- | mm/vmscan.c | 7 | ||||
-rw-r--r-- | mm/vmstat.c | 155 |
23 files changed, 269 insertions, 201 deletions
diff --git a/mm/compaction.c b/mm/compaction.c index 4d709ee59013..1a8894eadf72 100644 --- a/mm/compaction.c +++ b/mm/compaction.c @@ -279,7 +279,6 @@ static unsigned long isolate_migratepages(struct zone *zone, /* Successfully isolated */ del_page_from_lru_list(zone, page, page_lru(page)); list_add(&page->lru, migratelist); - mem_cgroup_del_lru(page); cc->nr_migratepages++; /* Avoid isolating too much */ diff --git a/mm/filemap.c b/mm/filemap.c index ea89840fc65f..ca389394fa2a 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -102,9 +102,6 @@ * ->inode_lock (zap_pte_range->set_page_dirty) * ->private_lock (zap_pte_range->__set_page_dirty_buffers) * - * ->task->proc_lock - * ->dcache_lock (proc_pid_lookup) - * * (code doesn't rely on that order, so you could switch it around) * ->tasklist_lock (memory_failure, collect_procs_ao) * ->i_mmap_lock @@ -143,13 +140,18 @@ void __remove_from_page_cache(struct page *page) void remove_from_page_cache(struct page *page) { struct address_space *mapping = page->mapping; + void (*freepage)(struct page *); BUG_ON(!PageLocked(page)); + freepage = mapping->a_ops->freepage; spin_lock_irq(&mapping->tree_lock); __remove_from_page_cache(page); spin_unlock_irq(&mapping->tree_lock); mem_cgroup_uncharge_cache_page(page); + + if (freepage) + freepage(page); } EXPORT_SYMBOL(remove_from_page_cache); diff --git a/mm/hugetlb.c b/mm/hugetlb.c index c4a3558589ab..85855240933d 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -2738,7 +2738,8 @@ out_page_table_lock: unlock_page(pagecache_page); put_page(pagecache_page); } - unlock_page(page); + if (page != pagecache_page) + unlock_page(page); out_mutex: mutex_unlock(&hugetlb_instantiation_mutex); @@ -1724,8 +1724,13 @@ static int ksm_memory_callback(struct notifier_block *self, /* * Keep it very simple for now: just lock out ksmd and * MADV_UNMERGEABLE while any memory is going offline. + * mutex_lock_nested() is necessary because lockdep was alarmed + * that here we take ksm_thread_mutex inside notifier chain + * mutex, and later take notifier chain mutex inside + * ksm_thread_mutex to unlock it. But that's safe because both + * are inside mem_hotplug_mutex. */ - mutex_lock(&ksm_thread_mutex); + mutex_lock_nested(&ksm_thread_mutex, SINGLE_DEPTH_NESTING); break; case MEM_OFFLINE: diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 7a22b4129211..00bb8a64d028 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -1925,19 +1925,18 @@ again: rcu_read_lock(); p = rcu_dereference(mm->owner); - VM_BUG_ON(!p); /* - * because we don't have task_lock(), "p" can exit while - * we're here. In that case, "mem" can point to root - * cgroup but never be NULL. (and task_struct itself is freed - * by RCU, cgroup itself is RCU safe.) Then, we have small - * risk here to get wrong cgroup. But such kind of mis-account - * by race always happens because we don't have cgroup_mutex(). - * It's overkill and we allow that small race, here. + * Because we don't have task_lock(), "p" can exit. + * In that case, "mem" can point to root or p can be NULL with + * race with swapoff. Then, we have small risk of mis-accouning. + * But such kind of mis-account by race always happens because + * we don't have cgroup_mutex(). It's overkill and we allo that + * small race, here. + * (*) swapoff at el will charge against mm-struct not against + * task-struct. So, mm->owner can be NULL. */ mem = mem_cgroup_from_task(p); - VM_BUG_ON(!mem); - if (mem_cgroup_is_root(mem)) { + if (!mem || mem_cgroup_is_root(mem)) { rcu_read_unlock(); goto done; } diff --git a/mm/memory-failure.c b/mm/memory-failure.c index 124324134ff6..46ab2c044b0e 100644 --- a/mm/memory-failure.c +++ b/mm/memory-failure.c @@ -51,6 +51,7 @@ #include <linux/slab.h> #include <linux/swapops.h> #include <linux/hugetlb.h> +#include <linux/memory_hotplug.h> #include "internal.h" int sysctl_memory_failure_early_kill __read_mostly = 0; @@ -1230,11 +1231,10 @@ static int get_any_page(struct page *p, unsigned long pfn, int flags) return 1; /* - * The lock_system_sleep prevents a race with memory hotplug, - * because the isolation assumes there's only a single user. + * The lock_memory_hotplug prevents a race with memory hotplug. * This is a big hammer, a better would be nicer. */ - lock_system_sleep(); + lock_memory_hotplug(); /* * Isolate the page, so that it doesn't get reallocated if it @@ -1264,7 +1264,7 @@ static int get_any_page(struct page *p, unsigned long pfn, int flags) ret = 1; } unset_migratetype_isolate(p); - unlock_system_sleep(); + unlock_memory_hotplug(); return ret; } diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c index 9260314a221e..2c6523af5473 100644 --- a/mm/memory_hotplug.c +++ b/mm/memory_hotplug.c @@ -34,6 +34,23 @@ #include "internal.h" +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); +} + + /* add this memory to iomem resource */ static struct resource *register_memory_resource(u64 start, u64 size) { @@ -493,7 +510,7 @@ int mem_online_node(int nid) pg_data_t *pgdat; int ret; - lock_system_sleep(); + lock_memory_hotplug(); pgdat = hotadd_new_pgdat(nid, 0); if (pgdat) { ret = -ENOMEM; @@ -504,7 +521,7 @@ int mem_online_node(int nid) BUG_ON(ret); out: - unlock_system_sleep(); + unlock_memory_hotplug(); return ret; } @@ -516,7 +533,7 @@ int __ref add_memory(int nid, u64 start, u64 size) struct resource *res; int ret; - lock_system_sleep(); + lock_memory_hotplug(); res = register_memory_resource(start, size); ret = -EEXIST; @@ -563,7 +580,7 @@ error: release_memory_resource(res); out: - unlock_system_sleep(); + unlock_memory_hotplug(); return ret; } EXPORT_SYMBOL_GPL(add_memory); @@ -791,7 +808,7 @@ static int offline_pages(unsigned long start_pfn, if (!test_pages_in_a_zone(start_pfn, end_pfn)) return -EINVAL; - lock_system_sleep(); + lock_memory_hotplug(); zone = page_zone(pfn_to_page(start_pfn)); node = zone_to_nid(zone); @@ -880,7 +897,7 @@ repeat: writeback_set_ratelimit(); memory_notify(MEM_OFFLINE, &arg); - unlock_system_sleep(); + unlock_memory_hotplug(); return 0; failed_removal: @@ -891,7 +908,7 @@ failed_removal: undo_isolate_page_range(start_pfn, end_pfn); out: - unlock_system_sleep(); + unlock_memory_hotplug(); return ret; } diff --git a/mm/mempolicy.c b/mm/mempolicy.c index 4a57f135b76e..11ff260fb282 100644 --- a/mm/mempolicy.c +++ b/mm/mempolicy.c @@ -1307,15 +1307,18 @@ SYSCALL_DEFINE4(migrate_pages, pid_t, pid, unsigned long, maxnode, goto out; /* Find the mm_struct */ + rcu_read_lock(); read_lock(&tasklist_lock); task = pid ? find_task_by_vpid(pid) : current; if (!task) { read_unlock(&tasklist_lock); + rcu_read_unlock(); err = -ESRCH; goto out; } mm = get_task_mm(task); read_unlock(&tasklist_lock); + rcu_read_unlock(); err = -EINVAL; if (!mm) diff --git a/mm/migrate.c b/mm/migrate.c index fe5a3c6a5426..6ae8a66a7045 100644 --- a/mm/migrate.c +++ b/mm/migrate.c @@ -35,6 +35,8 @@ #include <linux/hugetlb.h> #include <linux/gfp.h> +#include <asm/tlbflush.h> + #include "internal.h" #define lru_to_page(_head) (list_entry((_head)->prev, struct page, lru)) diff --git a/mm/mmap.c b/mm/mmap.c index b179abb1474a..50a4aa0255a0 100644 --- a/mm/mmap.c +++ b/mm/mmap.c @@ -2462,6 +2462,7 @@ int install_special_mapping(struct mm_struct *mm, unsigned long addr, unsigned long len, unsigned long vm_flags, struct page **pages) { + int ret; struct vm_area_struct *vma; vma = kmem_cache_zalloc(vm_area_cachep, GFP_KERNEL); @@ -2479,16 +2480,23 @@ int install_special_mapping(struct mm_struct *mm, vma->vm_ops = &special_mapping_vmops; vma->vm_private_data = pages; - if (unlikely(insert_vm_struct(mm, vma))) { - kmem_cache_free(vm_area_cachep, vma); - return -ENOMEM; - } + ret = security_file_mmap(NULL, 0, 0, 0, vma->vm_start, 1); + if (ret) + goto out; + + ret = insert_vm_struct(mm, vma); + if (ret) + goto out; mm->total_vm += len >> PAGE_SHIFT; perf_event_mmap(vma); return 0; + +out: + kmem_cache_free(vm_area_cachep, vma); + return ret; } static DEFINE_MUTEX(mm_all_locks_mutex); diff --git a/mm/nommu.c b/mm/nommu.c index 27a9ac588516..ef4045d010d5 100644 --- a/mm/nommu.c +++ b/mm/nommu.c @@ -10,7 +10,7 @@ * Copyright (c) 2000-2003 David McCullough <davidm@snapgear.com> * Copyright (c) 2000-2001 D Jeff Dionne <jeff@uClinux.org> * Copyright (c) 2002 Greg Ungerer <gerg@snapgear.com> - * Copyright (c) 2007-2009 Paul Mundt <lethal@linux-sh.org> + * Copyright (c) 2007-2010 Paul Mundt <lethal@linux-sh.org> */ #include <linux/module.h> @@ -328,6 +328,7 @@ void *vmalloc_node(unsigned long size, int node) { return vmalloc(size); } +EXPORT_SYMBOL(vmalloc_node); /** * vzalloc_node - allocate memory on a specific node with zero fill @@ -440,6 +441,31 @@ void __attribute__((weak)) vmalloc_sync_all(void) { } +/** + * alloc_vm_area - allocate a range of kernel address space + * @size: size of the area + * + * Returns: NULL on failure, vm_struct on success + * + * This function reserves a range of kernel address space, and + * allocates pagetables to map that range. No actual mappings + * are created. If the kernel address space is not shared + * between processes, it syncs the pagetable across all + * processes. + */ +struct vm_struct *alloc_vm_area(size_t size) +{ + BUG(); + return NULL; +} +EXPORT_SYMBOL_GPL(alloc_vm_area); + +void free_vm_area(struct vm_struct *area) +{ + BUG(); +} +EXPORT_SYMBOL_GPL(free_vm_area); + int vm_insert_page(struct vm_area_struct *vma, unsigned long addr, struct page *page) { diff --git a/mm/page-writeback.c b/mm/page-writeback.c index b840afa89761..b4edfe7ce06c 100644 --- a/mm/page-writeback.c +++ b/mm/page-writeback.c @@ -563,7 +563,7 @@ static void balance_dirty_pages(struct address_space *mapping, break; /* We've done our duty */ } trace_wbc_balance_dirty_wait(&wbc, bdi); - __set_current_state(TASK_INTERRUPTIBLE); + __set_current_state(TASK_UNINTERRUPTIBLE); io_schedule_timeout(pause); /* diff --git a/mm/page_alloc.c b/mm/page_alloc.c index e4092704c1a9..ff7e15872398 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -104,19 +104,24 @@ gfp_t gfp_allowed_mask __read_mostly = GFP_BOOT_MASK; * only be modified with pm_mutex held, unless the suspend/hibernate code is * guaranteed not to run in parallel with that modification). */ -void set_gfp_allowed_mask(gfp_t mask) + +static gfp_t saved_gfp_mask; + +void pm_restore_gfp_mask(void) { WARN_ON(!mutex_is_locked(&pm_mutex)); - gfp_allowed_mask = mask; + if (saved_gfp_mask) { + gfp_allowed_mask = saved_gfp_mask; + saved_gfp_mask = 0; + } } -gfp_t clear_gfp_allowed_mask(gfp_t mask) +void pm_restrict_gfp_mask(void) { - gfp_t ret = gfp_allowed_mask; - WARN_ON(!mutex_is_locked(&pm_mutex)); - gfp_allowed_mask &= ~mask; - return ret; + WARN_ON(saved_gfp_mask); + saved_gfp_mask = gfp_allowed_mask; + gfp_allowed_mask &= ~GFP_IOFS; } #endif /* CONFIG_PM_SLEEP */ diff --git a/mm/percpu.c b/mm/percpu.c index efe816856a9d..3dd4984bdef8 100644 --- a/mm/percpu.c +++ b/mm/percpu.c @@ -293,12 +293,8 @@ static void *pcpu_mem_alloc(size_t size) if (size <= PAGE_SIZE) return kzalloc(size, GFP_KERNEL); - else { - void *ptr = vmalloc(size); - if (ptr) - memset(ptr, 0, size); - return ptr; - } + else + return vzalloc(size); } /** @@ -1268,7 +1264,7 @@ int __init pcpu_setup_first_chunk(const struct pcpu_alloc_info *ai, /* we're done parsing the input, undefine BUG macro and dump config */ #undef PCPU_SETUP_BUG_ON - pcpu_dump_alloc_info(KERN_INFO, ai); + pcpu_dump_alloc_info(KERN_DEBUG, ai); pcpu_nr_groups = ai->nr_groups; pcpu_group_offsets = group_offsets; diff --git a/mm/shmem.c b/mm/shmem.c index 47fdeeb9d636..5ee67c990602 100644 --- a/mm/shmem.c +++ b/mm/shmem.c @@ -2415,13 +2415,20 @@ static struct inode *shmem_alloc_inode(struct super_block *sb) return &p->vfs_inode; } +static void shmem_i_callback(struct rcu_head *head) +{ + struct inode *inode = container_of(head, struct inode, i_rcu); + INIT_LIST_HEAD(&inode->i_dentry); + kmem_cache_free(shmem_inode_cachep, SHMEM_I(inode)); +} + static void shmem_destroy_inode(struct inode *inode) { if ((inode->i_mode & S_IFMT) == S_IFREG) { /* only struct inode is valid if it's an inline symlink */ mpol_free_shared_policy(&SHMEM_I(inode)->policy); } - kmem_cache_free(shmem_inode_cachep, SHMEM_I(inode)); + call_rcu(&inode->i_rcu, shmem_i_callback); } static void init_once(void *foo) diff --git a/mm/slab.c b/mm/slab.c index b1e40dafbab3..e9f92987954a 100644 --- a/mm/slab.c +++ b/mm/slab.c @@ -829,12 +829,12 @@ static void init_reap_node(int cpu) static void next_reap_node(void) { - int node = __get_cpu_var(slab_reap_node); + int node = __this_cpu_read(slab_reap_node); node = next_node(node, node_online_map); if (unlikely(node >= MAX_NUMNODES)) node = first_node(node_online_map); - __get_cpu_var(slab_reap_node) = node; + __this_cpu_write(slab_reap_node, node); } #else @@ -1012,7 +1012,7 @@ static void __drain_alien_cache(struct kmem_cache *cachep, */ static void reap_alien(struct kmem_cache *cachep, struct kmem_list3 *l3) { - int node = __get_cpu_var(slab_reap_node); + int node = __this_cpu_read(slab_reap_node); if (l3->alien) { struct array_cache *ac = l3->alien[node]; @@ -1293,7 +1293,7 @@ static int __cpuinit cpuup_callback(struct notifier_block *nfb, * anything expensive but will only modify reap_work * and reschedule the timer. */ - cancel_rearming_delayed_work(&per_cpu(slab_reap_work, cpu)); + cancel_delayed_work_sync(&per_cpu(slab_reap_work, cpu)); /* Now the cache_reaper is guaranteed to be not running. */ per_cpu(slab_reap_work, cpu).work.func = NULL; break; @@ -2781,7 +2781,7 @@ static void slab_put_obj(struct kmem_cache *cachep, struct slab *slabp, /* * Map pages beginning at addr to the given cache and slab. This is required * for the slab allocator to be able to lookup the cache and slab of a - * virtual address for kfree, ksize, kmem_ptr_validate, and slab debugging. + * virtual address for kfree, ksize, and slab debugging. */ static void slab_map_pages(struct kmem_cache *cache, struct slab *slab, void *addr) @@ -3660,36 +3660,6 @@ void *kmem_cache_alloc_notrace(struct kmem_cache *cachep, gfp_t flags) EXPORT_SYMBOL(kmem_cache_alloc_notrace); #endif -/** - * kmem_ptr_validate - check if an untrusted pointer might be a slab entry. - * @cachep: the cache we're checking against - * @ptr: pointer to validate - * - * This verifies that the untrusted pointer looks sane; - * it is _not_ a guarantee that the pointer is actually - * part of the slab cache in question, but it at least - * validates that the pointer can be dereferenced and - * looks half-way sane. - * - * Currently only used for dentry validation. - */ -int kmem_ptr_validate(struct kmem_cache *cachep, const void *ptr) -{ - unsigned long size = cachep->buffer_size; - struct page *page; - - if (unlikely(!kern_ptr_validate(ptr, size))) - goto out; - page = virt_to_page(ptr); - if (unlikely(!PageSlab(page))) - goto out; - if (unlikely(page_get_cache(page) != cachep)) - goto out; - return 1; -out: - return 0; -} - #ifdef CONFIG_NUMA void *kmem_cache_alloc_node(struct kmem_cache *cachep, gfp_t flags, int nodeid) { diff --git a/mm/slob.c b/mm/slob.c index 617b6d6c42c7..3588eaaef726 100644 --- a/mm/slob.c +++ b/mm/slob.c @@ -678,11 +678,6 @@ int kmem_cache_shrink(struct kmem_cache *d) } EXPORT_SYMBOL(kmem_cache_shrink); -int kmem_ptr_validate(struct kmem_cache *a, const void *b) -{ - return 0; -} - static unsigned int slob_ready __read_mostly; int slab_is_available(void) diff --git a/mm/slub.c b/mm/slub.c index 981fb730aa04..a2fe1727ed85 100644 --- a/mm/slub.c +++ b/mm/slub.c @@ -1917,17 +1917,6 @@ void kmem_cache_free(struct kmem_cache *s, void *x) } EXPORT_SYMBOL(kmem_cache_free); -/* Figure out on which slab page the object resides */ -static struct page *get_object_page(const void *x) -{ - struct page *page = virt_to_head_page(x); - - if (!PageSlab(page)) - return NULL; - - return page; -} - /* * Object placement in a slab is made very easy because we always start at * offset 0. If we tune the size of the object to the alignment then we can @@ -2386,35 +2375,6 @@ error: } /* - * Check if a given pointer is valid - */ -int kmem_ptr_validate(struct kmem_cache *s, const void *object) -{ - struct page *page; - - if (!kern_ptr_validate(object, s->size)) - return 0; - - page = get_object_page(object); - - if (!page || s != page->slab) - /* No slab or wrong slab */ - return 0; - - if (!check_valid_pointer(s, page, object)) - return 0; - - /* - * We could also check if the object is on the slabs freelist. - * But this would be too expensive and it seems that the main - * purpose of kmem_ptr_valid() is to check if the object belongs - * to a certain slab. - */ - return 1; -} -EXPORT_SYMBOL(kmem_ptr_validate); - -/* * Determine the size of a slab object */ unsigned int kmem_cache_size(struct kmem_cache *s) @@ -3401,13 +3361,13 @@ static int validate_slab(struct kmem_cache *s, struct page *page, for_each_free_object(p, s, page->freelist) { set_bit(slab_index(p, s, addr), map); - if (!check_object(s, page, p, 0)) + if (!check_object(s, page, p, SLUB_RED_INACTIVE)) return 0; } for_each_object(p, s, addr, page->objects) if (!test_bit(slab_index(p, s, addr), map)) - if (!check_object(s, page, p, 1)) + if (!check_object(s, page, p, SLUB_RED_ACTIVE)) return 0; return 1; } diff --git a/mm/truncate.c b/mm/truncate.c index ba887bff48c5..3c2d5ddfa0d4 100644 --- a/mm/truncate.c +++ b/mm/truncate.c @@ -390,6 +390,10 @@ invalidate_complete_page2(struct address_space *mapping, struct page *page) __remove_from_page_cache(page); spin_unlock_irq(&mapping->tree_lock); mem_cgroup_uncharge_cache_page(page); + + if (mapping->a_ops->freepage) + mapping->a_ops->freepage(page); + page_cache_release(page); /* pagecache ref */ return 1; failed: diff --git a/mm/util.c b/mm/util.c index 73dac81e9f78..f126975ef23e 100644 --- a/mm/util.c +++ b/mm/util.c @@ -186,27 +186,6 @@ void kzfree(const void *p) } EXPORT_SYMBOL(kzfree); -int kern_ptr_validate(const void *ptr, unsigned long size) -{ - unsigned long addr = (unsigned long)ptr; - unsigned long min_addr = PAGE_OFFSET; - unsigned long align_mask = sizeof(void *) - 1; - - if (unlikely(addr < min_addr)) - goto out; - if (unlikely(addr > (unsigned long)high_memory - size)) - goto out; - if (unlikely(addr & align_mask)) - goto out; - if (unlikely(!kern_addr_valid(addr))) - goto out; - if (unlikely(!kern_addr_valid(addr + size - 1))) - goto out; - return 1; -out: - return 0; -} - /* * strndup_user - duplicate an existing string from user space * @s: The string to duplicate diff --git a/mm/vmalloc.c b/mm/vmalloc.c index a3d66b3dc5cb..eb5cc7d00c5a 100644 --- a/mm/vmalloc.c +++ b/mm/vmalloc.c @@ -31,8 +31,6 @@ #include <asm/tlbflush.h> #include <asm/shmparam.h> -bool vmap_lazy_unmap __read_mostly = true; - /*** Page table manipulation functions ***/ static void vunmap_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end) @@ -503,9 +501,6 @@ static unsigned long lazy_max_pages(void) { unsigned int log; - if (!vmap_lazy_unmap) - return 0; - log = fls(num_online_cpus()); return log * (32UL * 1024 * 1024 / PAGE_SIZE); @@ -566,7 +561,6 @@ static void __purge_vmap_area_lazy(unsigned long *start, unsigned long *end, if (va->va_end > *end) *end = va->va_end; nr += (va->va_end - va->va_start) >> PAGE_SHIFT; - unmap_vmap_area(va); list_add_tail(&va->purge_list, &valist); va->flags |= VM_LAZY_FREEING; va->flags &= ~VM_LAZY_FREE; @@ -611,10 +605,11 @@ static void purge_vmap_area_lazy(void) } /* - * Free and unmap a vmap area, caller ensuring flush_cache_vunmap had been - * called for the correct range previously. + * Free a vmap area, caller ensuring that the area has been unmapped + * and flush_cache_vunmap had been called for the correct range + * previously. */ -static void free_unmap_vmap_area_noflush(struct vmap_area *va) +static void free_vmap_area_noflush(struct vmap_area *va) { va->flags |= VM_LAZY_FREE; atomic_add((va->va_end - va->va_start) >> PAGE_SHIFT, &vmap_lazy_nr); @@ -623,6 +618,16 @@ static void free_unmap_vmap_area_noflush(struct vmap_area *va) } /* + * Free and unmap a vmap area, caller ensuring flush_cache_vunmap had been + * called for the correct range previously. + */ +static void free_unmap_vmap_area_noflush(struct vmap_area *va) +{ + unmap_vmap_area(va); + free_vmap_area_noflush(va); +} + +/* * Free and unmap a vmap area */ static void free_unmap_vmap_area(struct vmap_area *va) @@ -798,7 +803,7 @@ static void free_vmap_block(struct vmap_block *vb) spin_unlock(&vmap_block_tree_lock); BUG_ON(tmp != vb); - free_unmap_vmap_area_noflush(vb->va); + free_vmap_area_noflush(vb->va); call_rcu(&vb->rcu_head, rcu_free_vb); } @@ -936,6 +941,8 @@ static void vb_free(const void *addr, unsigned long size) rcu_read_unlock(); BUG_ON(!vb); + vunmap_page_range((unsigned long)addr, (unsigned long)addr + size); + spin_lock(&vb->lock); BUG_ON(bitmap_allocate_region(vb->dirty_map, offset >> PAGE_SHIFT, order)); @@ -988,7 +995,6 @@ void vm_unmap_aliases(void) s = vb->va->va_start + (i << PAGE_SHIFT); e = vb->va->va_start + (j << PAGE_SHIFT); - vunmap_page_range(s, e); flush = 1; if (s < start) diff --git a/mm/vmscan.c b/mm/vmscan.c index d31d7ce52c0e..9ca587c69274 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -494,9 +494,16 @@ static int __remove_mapping(struct address_space *mapping, struct page *page) spin_unlock_irq(&mapping->tree_lock); swapcache_free(swap, page); } else { + void (*freepage)(struct page *); + + freepage = mapping->a_ops->freepage; + __remove_from_page_cache(page); spin_unlock_irq(&mapping->tree_lock); mem_cgroup_uncharge_cache_page(page); + + if (freepage != NULL) + freepage(page); } return 1; diff --git a/mm/vmstat.c b/mm/vmstat.c index 42eac4d33216..312d728976f1 100644 --- a/mm/vmstat.c +++ b/mm/vmstat.c @@ -167,36 +167,24 @@ static void refresh_zone_stat_thresholds(void) void __mod_zone_page_state(struct zone *zone, enum zone_stat_item item, int delta) { - struct per_cpu_pageset *pcp = this_cpu_ptr(zone->pageset); - - s8 *p = pcp->vm_stat_diff + item; + struct per_cpu_pageset __percpu *pcp = zone->pageset; + s8 __percpu *p = pcp->vm_stat_diff + item; long x; + long t; + + x = delta + __this_cpu_read(*p); - x = delta + *p; + t = __this_cpu_read(pcp->stat_threshold); - if (unlikely(x > pcp->stat_threshold || x < -pcp->stat_threshold)) { + if (unlikely(x > t || x < -t)) { zone_page_state_add(x, zone, item); x = 0; } - *p = x; + __this_cpu_write(*p, x); } EXPORT_SYMBOL(__mod_zone_page_state); /* - * For an unknown interrupt state - */ -void mod_zone_page_state(struct zone *zone, enum zone_stat_item item, - int delta) -{ - unsigned long flags; - - local_irq_save(flags); - __mod_zone_page_state(zone, item, delta); - local_irq_restore(flags); -} -EXPORT_SYMBOL(mod_zone_page_state); - -/* * Optimized increment and decrement functions. * * These are only for a single page and therefore can take a struct page * @@ -221,16 +209,17 @@ EXPORT_SYMBOL(mod_zone_page_state); */ void __inc_zone_state(struct zone *zone, enum zone_stat_item item) { - struct per_cpu_pageset *pcp = this_cpu_ptr(zone->pageset); - s8 *p = pcp->vm_stat_diff + item; - - (*p)++; + struct per_cpu_pageset __percpu *pcp = zone->pageset; + s8 __percpu *p = pcp->vm_stat_diff + item; + s8 v, t; - if (unlikely(*p > pcp->stat_threshold)) { - int overstep = pcp->stat_threshold / 2; + v = __this_cpu_inc_return(*p); + t = __this_cpu_read(pcp->stat_threshold); + if (unlikely(v > t)) { + s8 overstep = t >> 1; - zone_page_state_add(*p + overstep, zone, item); - *p = -overstep; + zone_page_state_add(v + overstep, zone, item); + __this_cpu_write(*p, -overstep); } } @@ -242,16 +231,17 @@ EXPORT_SYMBOL(__inc_zone_page_state); void __dec_zone_state(struct zone *zone, enum zone_stat_item item) { - struct per_cpu_pageset *pcp = this_cpu_ptr(zone->pageset); - s8 *p = pcp->vm_stat_diff + item; + struct per_cpu_pageset __percpu *pcp = zone->pageset; + s8 __percpu *p = pcp->vm_stat_diff + item; + s8 v, t; - (*p)--; + v = __this_cpu_dec_return(*p); + t = __this_cpu_read(pcp->stat_threshold); + if (unlikely(v < - t)) { + s8 overstep = t >> 1; - if (unlikely(*p < - pcp->stat_threshold)) { - int overstep = pcp->stat_threshold / 2; - - zone_page_state_add(*p - overstep, zone, item); - *p = overstep; + zone_page_state_add(v - overstep, zone, item); + __this_cpu_write(*p, overstep); } } @@ -261,6 +251,92 @@ void __dec_zone_page_state(struct page *page, enum zone_stat_item item) } EXPORT_SYMBOL(__dec_zone_page_state); +#ifdef CONFIG_CMPXCHG_LOCAL +/* + * If we have cmpxchg_local support then we do not need to incur the overhead + * that comes with local_irq_save/restore if we use this_cpu_cmpxchg. + * + * mod_state() modifies the zone counter state through atomic per cpu + * operations. + * + * Overstep mode specifies how overstep should handled: + * 0 No overstepping + * 1 Overstepping half of threshold + * -1 Overstepping minus half of threshold +*/ +static inline void mod_state(struct zone *zone, + enum zone_stat_item item, int delta, int overstep_mode) +{ + struct per_cpu_pageset __percpu *pcp = zone->pageset; + s8 __percpu *p = pcp->vm_stat_diff + item; + long o, n, t, z; + + do { + z = 0; /* overflow to zone counters */ + + /* + * The fetching of the stat_threshold is racy. We may apply + * a counter threshold to the wrong the cpu if we get + * rescheduled while executing here. However, the following + * will apply the threshold again and therefore bring the + * counter under the threshold. + */ + t = this_cpu_read(pcp->stat_threshold); + + o = this_cpu_read(*p); + n = delta + o; + + if (n > t || n < -t) { + int os = overstep_mode * (t >> 1) ; + + /* Overflow must be added to zone counters */ + z = n + os; + n = -os; + } + } while (this_cpu_cmpxchg(*p, o, n) != o); + + if (z) + zone_page_state_add(z, zone, item); +} + +void mod_zone_page_state(struct zone *zone, enum zone_stat_item item, + int delta) +{ + mod_state(zone, item, delta, 0); +} +EXPORT_SYMBOL(mod_zone_page_state); + +void inc_zone_state(struct zone *zone, enum zone_stat_item item) +{ + mod_state(zone, item, 1, 1); +} + +void inc_zone_page_state(struct page *page, enum zone_stat_item item) +{ + mod_state(page_zone(page), item, 1, 1); +} +EXPORT_SYMBOL(inc_zone_page_state); + +void dec_zone_page_state(struct page *page, enum zone_stat_item item) +{ + mod_state(page_zone(page), item, -1, -1); +} +EXPORT_SYMBOL(dec_zone_page_state); +#else +/* + * Use interrupt disable to serialize counter updates + */ +void mod_zone_page_state(struct zone *zone, enum zone_stat_item item, + int delta) +{ + unsigned long flags; + + local_irq_save(flags); + __mod_zone_page_state(zone, item, delta); + local_irq_restore(flags); +} +EXPORT_SYMBOL(mod_zone_page_state); + void inc_zone_state(struct zone *zone, enum zone_stat_item item) { unsigned long flags; @@ -291,6 +367,7 @@ void dec_zone_page_state(struct page *page, enum zone_stat_item item) local_irq_restore(flags); } EXPORT_SYMBOL(dec_zone_page_state); +#endif /* * Update the zone counters for one cpu. @@ -750,8 +827,6 @@ static const char * const vmstat_text[] = { "nr_shmem", "nr_dirtied", "nr_written", - "nr_dirty_threshold", - "nr_dirty_background_threshold", #ifdef CONFIG_NUMA "numa_hit", @@ -761,6 +836,8 @@ static const char * const vmstat_text[] = { "numa_local", "numa_other", #endif + "nr_dirty_threshold", + "nr_dirty_background_threshold", #ifdef CONFIG_VM_EVENT_COUNTERS "pgpgin", @@ -1033,7 +1110,7 @@ static int __cpuinit vmstat_cpuup_callback(struct notifier_block *nfb, break; case CPU_DOWN_PREPARE: case CPU_DOWN_PREPARE_FROZEN: - cancel_rearming_delayed_work(&per_cpu(vmstat_work, cpu)); + cancel_delayed_work_sync(&per_cpu(vmstat_work, cpu)); per_cpu(vmstat_work, cpu).work.func = NULL; break; case CPU_DOWN_FAILED: |