diff options
Diffstat (limited to 'mm')
| -rw-r--r-- | mm/Kconfig | 2 | ||||
| -rw-r--r-- | mm/allocpercpu.c | 2 | ||||
| -rw-r--r-- | mm/backing-dev.c | 10 | ||||
| -rw-r--r-- | mm/failslab.c | 1 | ||||
| -rw-r--r-- | mm/filemap.c | 24 | ||||
| -rw-r--r-- | mm/memcontrol.c | 2 | ||||
| -rw-r--r-- | mm/migrate.c | 10 | ||||
| -rw-r--r-- | mm/mmap.c | 2 | ||||
| -rw-r--r-- | mm/page_alloc.c | 8 | ||||
| -rw-r--r-- | mm/pdflush.c | 47 | ||||
| -rw-r--r-- | mm/quicklist.c | 2 | ||||
| -rw-r--r-- | mm/readahead.c | 40 | ||||
| -rw-r--r-- | mm/shmem.c | 27 | ||||
| -rw-r--r-- | mm/slab.c | 71 | ||||
| -rw-r--r-- | mm/slob.c | 31 | ||||
| -rw-r--r-- | mm/slub.c | 77 | ||||
| -rw-r--r-- | mm/swap.c | 4 | ||||
| -rw-r--r-- | mm/truncate.c | 10 | ||||
| -rw-r--r-- | mm/util.c | 32 | ||||
| -rw-r--r-- | mm/vmscan.c | 12 |
20 files changed, 344 insertions, 70 deletions
diff --git a/mm/Kconfig b/mm/Kconfig index b53427ad30a..57971d2ab84 100644 --- a/mm/Kconfig +++ b/mm/Kconfig @@ -213,6 +213,8 @@ config UNEVICTABLE_LRU will use one page flag and increase the code size a little, say Y unless you know what you are doing. + See Documentation/vm/unevictable-lru.txt for more information. + config HAVE_MLOCK bool default y if MMU=y diff --git a/mm/allocpercpu.c b/mm/allocpercpu.c index 139d5b7b662..dfdee6a4735 100644 --- a/mm/allocpercpu.c +++ b/mm/allocpercpu.c @@ -31,7 +31,7 @@ static void percpu_depopulate(void *__pdata, int cpu) * @__pdata: per-cpu data to depopulate * @mask: depopulate per-cpu data for cpu's selected through mask bits */ -static void __percpu_depopulate_mask(void *__pdata, cpumask_t *mask) +static void __percpu_depopulate_mask(void *__pdata, const cpumask_t *mask) { int cpu; for_each_cpu_mask_nr(cpu, *mask) diff --git a/mm/backing-dev.c b/mm/backing-dev.c index be68c956a66..493b468a503 100644 --- a/mm/backing-dev.c +++ b/mm/backing-dev.c @@ -284,12 +284,12 @@ static wait_queue_head_t congestion_wqh[2] = { }; -void clear_bdi_congested(struct backing_dev_info *bdi, int rw) +void clear_bdi_congested(struct backing_dev_info *bdi, int sync) { enum bdi_state bit; - wait_queue_head_t *wqh = &congestion_wqh[rw]; + wait_queue_head_t *wqh = &congestion_wqh[sync]; - bit = (rw == WRITE) ? BDI_write_congested : BDI_read_congested; + bit = sync ? BDI_sync_congested : BDI_async_congested; clear_bit(bit, &bdi->state); smp_mb__after_clear_bit(); if (waitqueue_active(wqh)) @@ -297,11 +297,11 @@ void clear_bdi_congested(struct backing_dev_info *bdi, int rw) } EXPORT_SYMBOL(clear_bdi_congested); -void set_bdi_congested(struct backing_dev_info *bdi, int rw) +void set_bdi_congested(struct backing_dev_info *bdi, int sync) { enum bdi_state bit; - bit = (rw == WRITE) ? BDI_write_congested : BDI_read_congested; + bit = sync ? BDI_sync_congested : BDI_async_congested; set_bit(bit, &bdi->state); } EXPORT_SYMBOL(set_bdi_congested); diff --git a/mm/failslab.c b/mm/failslab.c index 7c6ea6493f8..9339de5f0a9 100644 --- a/mm/failslab.c +++ b/mm/failslab.c @@ -1,4 +1,5 @@ #include <linux/fault-inject.h> +#include <linux/gfp.h> static struct { struct fault_attr attr; diff --git a/mm/filemap.c b/mm/filemap.c index 126d3973b3d..379ff0bcbf6 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -441,6 +441,7 @@ int filemap_write_and_wait_range(struct address_space *mapping, } return err; } +EXPORT_SYMBOL(filemap_write_and_wait_range); /** * add_to_page_cache_locked - add a locked page to the pagecache @@ -513,6 +514,7 @@ int add_to_page_cache_lru(struct page *page, struct address_space *mapping, } return ret; } +EXPORT_SYMBOL_GPL(add_to_page_cache_lru); #ifdef CONFIG_NUMA struct page *__page_cache_alloc(gfp_t gfp) @@ -565,6 +567,24 @@ void wait_on_page_bit(struct page *page, int bit_nr) EXPORT_SYMBOL(wait_on_page_bit); /** + * add_page_wait_queue - Add an arbitrary waiter to a page's wait queue + * @page: Page defining the wait queue of interest + * @waiter: Waiter to add to the queue + * + * Add an arbitrary @waiter to the wait queue for the nominated @page. + */ +void add_page_wait_queue(struct page *page, wait_queue_t *waiter) +{ + wait_queue_head_t *q = page_waitqueue(page); + unsigned long flags; + + spin_lock_irqsave(&q->lock, flags); + __add_wait_queue(q, waiter); + spin_unlock_irqrestore(&q->lock, flags); +} +EXPORT_SYMBOL_GPL(add_page_wait_queue); + +/** * unlock_page - unlock a locked page * @page: the page * @@ -627,6 +647,7 @@ int __lock_page_killable(struct page *page) return __wait_on_bit_lock(page_waitqueue(page), &wait, sync_page_killable, TASK_KILLABLE); } +EXPORT_SYMBOL_GPL(__lock_page_killable); /** * __lock_page_nosync - get a lock on the page, without calling sync_page() @@ -2463,6 +2484,9 @@ EXPORT_SYMBOL(generic_file_aio_write); * (presumably at page->private). If the release was successful, return `1'. * Otherwise return zero. * + * This may also be called if PG_fscache is set on a page, indicating that the + * page is known to the local caching routines. + * * The @gfp_mask argument specifies whether I/O may be performed to release * this page (__GFP_IO), and whether the call may block (__GFP_WAIT & __GFP_FS). * diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 2fc6d6c4823..e44fb0fbb80 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -932,7 +932,7 @@ static int __mem_cgroup_try_charge(struct mm_struct *mm, if (unlikely(!mem)) return 0; - VM_BUG_ON(mem_cgroup_is_obsolete(mem)); + VM_BUG_ON(!mem || mem_cgroup_is_obsolete(mem)); while (1) { int ret; diff --git a/mm/migrate.c b/mm/migrate.c index a9eff3f092f..068655d8f88 100644 --- a/mm/migrate.c +++ b/mm/migrate.c @@ -250,7 +250,7 @@ out: * The number of remaining references must be: * 1 for anonymous pages without a mapping * 2 for pages with a mapping - * 3 for pages with a mapping and PagePrivate set. + * 3 for pages with a mapping and PagePrivate/PagePrivate2 set. */ static int migrate_page_move_mapping(struct address_space *mapping, struct page *newpage, struct page *page) @@ -270,7 +270,7 @@ static int migrate_page_move_mapping(struct address_space *mapping, pslot = radix_tree_lookup_slot(&mapping->page_tree, page_index(page)); - expected_count = 2 + !!PagePrivate(page); + expected_count = 2 + !!page_has_private(page); if (page_count(page) != expected_count || (struct page *)radix_tree_deref_slot(pslot) != page) { spin_unlock_irq(&mapping->tree_lock); @@ -386,7 +386,7 @@ EXPORT_SYMBOL(fail_migrate_page); /* * Common logic to directly migrate a single page suitable for - * pages that do not use PagePrivate. + * pages that do not use PagePrivate/PagePrivate2. * * Pages are locked upon entry and exit. */ @@ -522,7 +522,7 @@ static int fallback_migrate_page(struct address_space *mapping, * Buffers may be managed in a filesystem specific way. * We must have no buffers or drop them. */ - if (PagePrivate(page) && + if (page_has_private(page) && !try_to_release_page(page, GFP_KERNEL)) return -EAGAIN; @@ -655,7 +655,7 @@ static int unmap_and_move(new_page_t get_new_page, unsigned long private, * free the metadata, so the page can be freed. */ if (!page->mapping) { - if (!PageAnon(page) && PagePrivate(page)) { + if (!PageAnon(page) && page_has_private(page)) { /* * Go direct to try_to_free_buffers() here because * a) that's what try_to_release_page() would do anyway diff --git a/mm/mmap.c b/mm/mmap.c index 4a3841186c1..3303d1ba8e8 100644 --- a/mm/mmap.c +++ b/mm/mmap.c @@ -1575,7 +1575,7 @@ static int acct_stack_growth(struct vm_area_struct *vma, unsigned long size, uns * Overcommit.. This must be the final test, as it will * update security statistics. */ - if (security_vm_enough_memory(grow)) + if (security_vm_enough_memory_mm(mm, grow)) return -ENOMEM; /* Ok, everything looks good - let it rip */ diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 0284e528748..e2f26991fff 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -331,7 +331,7 @@ static int destroy_compound_page(struct page *page, unsigned long order) for (i = 1; i < nr_pages; i++) { struct page *p = page + i; - if (unlikely(!PageTail(p) | (p->first_page != page))) { + if (unlikely(!PageTail(p) || (p->first_page != page))) { bad_page(page); bad++; } @@ -2128,7 +2128,7 @@ static int find_next_best_node(int node, nodemask_t *used_node_mask) int n, val; int min_val = INT_MAX; int best_node = -1; - node_to_cpumask_ptr(tmp, 0); + const struct cpumask *tmp = cpumask_of_node(0); /* Use the local node if we haven't already */ if (!node_isset(node, *used_node_mask)) { @@ -2149,8 +2149,8 @@ static int find_next_best_node(int node, nodemask_t *used_node_mask) val += (n < node); /* Give preference to headless and unused nodes */ - node_to_cpumask_ptr_next(tmp, n); - if (!cpus_empty(*tmp)) + tmp = cpumask_of_node(n); + if (!cpumask_empty(tmp)) val += PENALTY_FOR_NODE_WITH_CPUS; /* Slight preference for less loaded node */ diff --git a/mm/pdflush.c b/mm/pdflush.c index 118905e3d78..f2caf96993f 100644 --- a/mm/pdflush.c +++ b/mm/pdflush.c @@ -58,6 +58,14 @@ static DEFINE_SPINLOCK(pdflush_lock); int nr_pdflush_threads = 0; /* + * The max/min number of pdflush threads. R/W by sysctl at + * /proc/sys/vm/nr_pdflush_threads_max/min + */ +int nr_pdflush_threads_max __read_mostly = MAX_PDFLUSH_THREADS; +int nr_pdflush_threads_min __read_mostly = MIN_PDFLUSH_THREADS; + + +/* * The time at which the pdflush thread pool last went empty */ static unsigned long last_empty_jifs; @@ -68,7 +76,7 @@ static unsigned long last_empty_jifs; * Thread pool management algorithm: * * - The minimum and maximum number of pdflush instances are bound - * by MIN_PDFLUSH_THREADS and MAX_PDFLUSH_THREADS. + * by nr_pdflush_threads_min and nr_pdflush_threads_max. * * - If there have been no idle pdflush instances for 1 second, create * a new one. @@ -98,7 +106,6 @@ static int __pdflush(struct pdflush_work *my_work) INIT_LIST_HEAD(&my_work->list); spin_lock_irq(&pdflush_lock); - nr_pdflush_threads++; for ( ; ; ) { struct pdflush_work *pdf; @@ -126,20 +133,25 @@ static int __pdflush(struct pdflush_work *my_work) (*my_work->fn)(my_work->arg0); + spin_lock_irq(&pdflush_lock); + /* * Thread creation: For how long have there been zero * available threads? + * + * To throttle creation, we reset last_empty_jifs. */ if (time_after(jiffies, last_empty_jifs + 1 * HZ)) { - /* unlocked list_empty() test is OK here */ - if (list_empty(&pdflush_list)) { - /* unlocked test is OK here */ - if (nr_pdflush_threads < MAX_PDFLUSH_THREADS) - start_one_pdflush_thread(); + if (list_empty(&pdflush_list) && + nr_pdflush_threads < nr_pdflush_threads_max) { + last_empty_jifs = jiffies; + nr_pdflush_threads++; + spin_unlock_irq(&pdflush_lock); + start_one_pdflush_thread(); + spin_lock_irq(&pdflush_lock); } } - spin_lock_irq(&pdflush_lock); my_work->fn = NULL; /* @@ -148,7 +160,7 @@ static int __pdflush(struct pdflush_work *my_work) */ if (list_empty(&pdflush_list)) continue; - if (nr_pdflush_threads <= MIN_PDFLUSH_THREADS) + if (nr_pdflush_threads <= nr_pdflush_threads_min) continue; pdf = list_entry(pdflush_list.prev, struct pdflush_work, list); if (time_after(jiffies, pdf->when_i_went_to_sleep + 1 * HZ)) { @@ -236,14 +248,27 @@ int pdflush_operation(void (*fn)(unsigned long), unsigned long arg0) static void start_one_pdflush_thread(void) { - kthread_run(pdflush, NULL, "pdflush"); + struct task_struct *k; + + k = kthread_run(pdflush, NULL, "pdflush"); + if (unlikely(IS_ERR(k))) { + spin_lock_irq(&pdflush_lock); + nr_pdflush_threads--; + spin_unlock_irq(&pdflush_lock); + } } static int __init pdflush_init(void) { int i; - for (i = 0; i < MIN_PDFLUSH_THREADS; i++) + /* + * Pre-set nr_pdflush_threads... If we fail to create, + * the count will be decremented. + */ + nr_pdflush_threads = nr_pdflush_threads_min; + + for (i = 0; i < nr_pdflush_threads_min; i++) start_one_pdflush_thread(); return 0; } diff --git a/mm/quicklist.c b/mm/quicklist.c index 8dbb6805ef3..e66d07d1b4f 100644 --- a/mm/quicklist.c +++ b/mm/quicklist.c @@ -29,7 +29,7 @@ static unsigned long max_pages(unsigned long min_pages) int node = numa_node_id(); struct zone *zones = NODE_DATA(node)->node_zones; int num_cpus_on_node; - node_to_cpumask_ptr(cpumask_on_node, node); + const struct cpumask *cpumask_on_node = cpumask_of_node(node); node_free_pages = #ifdef CONFIG_ZONE_DMA diff --git a/mm/readahead.c b/mm/readahead.c index 9ce303d4b81..133b6d52551 100644 --- a/mm/readahead.c +++ b/mm/readahead.c @@ -31,6 +31,42 @@ EXPORT_SYMBOL_GPL(file_ra_state_init); #define list_to_page(head) (list_entry((head)->prev, struct page, lru)) +/* + * see if a page needs releasing upon read_cache_pages() failure + * - the caller of read_cache_pages() may have set PG_private or PG_fscache + * before calling, such as the NFS fs marking pages that are cached locally + * on disk, thus we need to give the fs a chance to clean up in the event of + * an error + */ +static void read_cache_pages_invalidate_page(struct address_space *mapping, + struct page *page) +{ + if (page_has_private(page)) { + if (!trylock_page(page)) + BUG(); + page->mapping = mapping; + do_invalidatepage(page, 0); + page->mapping = NULL; + unlock_page(page); + } + page_cache_release(page); +} + +/* + * release a list of pages, invalidating them first if need be + */ +static void read_cache_pages_invalidate_pages(struct address_space *mapping, + struct list_head *pages) +{ + struct page *victim; + + while (!list_empty(pages)) { + victim = list_to_page(pages); + list_del(&victim->lru); + read_cache_pages_invalidate_page(mapping, victim); + } +} + /** * read_cache_pages - populate an address space with some pages & start reads against them * @mapping: the address_space @@ -52,14 +88,14 @@ int read_cache_pages(struct address_space *mapping, struct list_head *pages, list_del(&page->lru); if (add_to_page_cache_lru(page, mapping, page->index, GFP_KERNEL)) { - page_cache_release(page); + read_cache_pages_invalidate_page(mapping, page); continue; } page_cache_release(page); ret = filler(data, page); if (unlikely(ret)) { - put_pages_list(pages); + read_cache_pages_invalidate_pages(mapping, pages); break; } task_io_account_read(PAGE_CACHE_SIZE); diff --git a/mm/shmem.c b/mm/shmem.c index d94d2e9146b..f9cb20ebb99 100644 --- a/mm/shmem.c +++ b/mm/shmem.c @@ -24,6 +24,7 @@ #include <linux/init.h> #include <linux/vfs.h> #include <linux/mount.h> +#include <linux/pagemap.h> #include <linux/file.h> #include <linux/mm.h> #include <linux/module.h> @@ -43,7 +44,6 @@ static struct vfsmount *shm_mnt; #include <linux/exportfs.h> #include <linux/generic_acl.h> #include <linux/mman.h> -#include <linux/pagemap.h> #include <linux/string.h> #include <linux/slab.h> #include <linux/backing-dev.h> @@ -65,13 +65,28 @@ static struct vfsmount *shm_mnt; #include <asm/div64.h> #include <asm/pgtable.h> +/* + * The maximum size of a shmem/tmpfs file is limited by the maximum size of + * its triple-indirect swap vector - see illustration at shmem_swp_entry(). + * + * With 4kB page size, maximum file size is just over 2TB on a 32-bit kernel, + * but one eighth of that on a 64-bit kernel. With 8kB page size, maximum + * file size is just over 4TB on a 64-bit kernel, but 16TB on a 32-bit kernel, + * MAX_LFS_FILESIZE being then more restrictive than swap vector layout. + * + * We use / and * instead of shifts in the definitions below, so that the swap + * vector can be tested with small even values (e.g. 20) for ENTRIES_PER_PAGE. + */ #define ENTRIES_PER_PAGE (PAGE_CACHE_SIZE/sizeof(unsigned long)) -#define ENTRIES_PER_PAGEPAGE (ENTRIES_PER_PAGE*ENTRIES_PER_PAGE) -#define BLOCKS_PER_PAGE (PAGE_CACHE_SIZE/512) +#define ENTRIES_PER_PAGEPAGE ((unsigned long long)ENTRIES_PER_PAGE*ENTRIES_PER_PAGE) -#define SHMEM_MAX_INDEX (SHMEM_NR_DIRECT + (ENTRIES_PER_PAGEPAGE/2) * (ENTRIES_PER_PAGE+1)) -#define SHMEM_MAX_BYTES ((unsigned long long)SHMEM_MAX_INDEX << PAGE_CACHE_SHIFT) +#define SHMSWP_MAX_INDEX (SHMEM_NR_DIRECT + (ENTRIES_PER_PAGEPAGE/2) * (ENTRIES_PER_PAGE+1)) +#define SHMSWP_MAX_BYTES (SHMSWP_MAX_INDEX << PAGE_CACHE_SHIFT) +#define SHMEM_MAX_BYTES min_t(unsigned long long, SHMSWP_MAX_BYTES, MAX_LFS_FILESIZE) +#define SHMEM_MAX_INDEX ((unsigned long)((SHMEM_MAX_BYTES+1) >> PAGE_CACHE_SHIFT)) + +#define BLOCKS_PER_PAGE (PAGE_CACHE_SIZE/512) #define VM_ACCT(size) (PAGE_CACHE_ALIGN(size) >> PAGE_SHIFT) /* info->flags needs VM_flags to handle pagein/truncate races efficiently */ @@ -2581,7 +2596,7 @@ int shmem_unuse(swp_entry_t entry, struct page *page) #define shmem_get_inode(sb, mode, dev, flags) ramfs_get_inode(sb, mode, dev) #define shmem_acct_size(flags, size) 0 #define shmem_unacct_size(flags, size) do {} while (0) -#define SHMEM_MAX_BYTES LLONG_MAX +#define SHMEM_MAX_BYTES MAX_LFS_FILESIZE #endif /* CONFIG_SHMEM */ diff --git a/mm/slab.c b/mm/slab.c index 208323fd37b..9a90b00d2f9 100644 --- a/mm/slab.c +++ b/mm/slab.c @@ -102,6 +102,7 @@ #include <linux/cpu.h> #include <linux/sysctl.h> #include <linux/module.h> +#include <trace/kmemtrace.h> #include <linux/rcupdate.h> #include <linux/string.h> #include <linux/uaccess.h> @@ -568,6 +569,14 @@ static void **dbg_userword(struct kmem_cache *cachep, void *objp) #endif +#ifdef CONFIG_KMEMTRACE +size_t slab_buffer_size(struct kmem_cache *cachep) +{ + return cachep->buffer_size; +} +EXPORT_SYMBOL(slab_buffer_size); +#endif + /* * Do not go above this order unless 0 objects fit into the slab. */ @@ -1160,7 +1169,7 @@ static void __cpuinit cpuup_canceled(long cpu) struct kmem_cache *cachep; struct kmem_list3 *l3 = NULL; int node = cpu_to_node(cpu); - node_to_cpumask_ptr(mask, node); + const struct cpumask *mask = cpumask_of_node(node); list_for_each_entry(cachep, &cache_chain, next) { struct array_cache *nc; @@ -3554,10 +3563,23 @@ static inline void __cache_free(struct kmem_cache *cachep, void *objp) */ void *kmem_cache_alloc(struct kmem_cache *cachep, gfp_t flags) { - return __cache_alloc(cachep, flags, __builtin_return_address(0)); + void *ret = __cache_alloc(cachep, flags, __builtin_return_address(0)); + + trace_kmem_cache_alloc(_RET_IP_, ret, + obj_size(cachep), cachep->buffer_size, flags); + + return ret; } EXPORT_SYMBOL(kmem_cache_alloc); +#ifdef CONFIG_KMEMTRACE +void *kmem_cache_alloc_notrace(struct kmem_cache *cachep, gfp_t flags) +{ + return __cache_alloc(cachep, flags, __builtin_return_address(0)); +} +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 @@ -3602,23 +3624,46 @@ out: #ifdef CONFIG_NUMA void *kmem_cache_alloc_node(struct kmem_cache *cachep, gfp_t flags, int nodeid) { - return __cache_alloc_node(cachep, flags, nodeid, - __builtin_return_address(0)); + void *ret = __cache_alloc_node(cachep, flags, nodeid, + __builtin_return_address(0)); + + trace_kmem_cache_alloc_node(_RET_IP_, ret, + obj_size(cachep), cachep->buffer_size, + flags, nodeid); + + return ret; } EXPORT_SYMBOL(kmem_cache_alloc_node); +#ifdef CONFIG_KMEMTRACE +void *kmem_cache_alloc_node_notrace(struct kmem_cache *cachep, + gfp_t flags, + int nodeid) +{ + return __cache_alloc_node(cachep, flags, nodeid, + __builtin_return_address(0)); +} +EXPORT_SYMBOL(kmem_cache_alloc_node_notrace); +#endif + static __always_inline void * __do_kmalloc_node(size_t size, gfp_t flags, int node, void *caller) { struct kmem_cache *cachep; + void *ret; cachep = kmem_find_general_cachep(size, flags); if (unlikely(ZERO_OR_NULL_PTR(cachep))) return cachep; - return kmem_cache_alloc_node(cachep, flags, node); + ret = kmem_cache_alloc_node_notrace(cachep, flags, node); + + trace_kmalloc_node((unsigned long) caller, ret, + size, cachep->buffer_size, flags, node); + + return ret; } -#ifdef CONFIG_DEBUG_SLAB +#if defined(CONFIG_DEBUG_SLAB) || defined(CONFIG_KMEMTRACE) void *__kmalloc_node(size_t size, gfp_t flags, int node) { return __do_kmalloc_node(size, flags, node, @@ -3651,6 +3696,7 @@ static __always_inline void *__do_kmalloc(size_t size, gfp_t flags, void *caller) { struct kmem_cache *cachep; + void *ret; /* If you want to save a few bytes .text space: replace * __ with kmem_. @@ -3660,11 +3706,16 @@ static __always_inline void *__do_kmalloc(size_t size, gfp_t flags, cachep = __find_general_cachep(size, flags); if (unlikely(ZERO_OR_NULL_PTR(cachep))) return cachep; - return __cache_alloc(cachep, flags, caller); + ret = __cache_alloc(cachep, flags, caller); + + trace_kmalloc((unsigned long) caller, ret, + size, cachep->buffer_size, flags); + + return ret; } -#ifdef CONFIG_DEBUG_SLAB +#if defined(CONFIG_DEBUG_SLAB) || defined(CONFIG_KMEMTRACE) void *__kmalloc(size_t size, gfp_t flags) { return __do_kmalloc(size, flags, __builtin_return_address(0)); @@ -3703,6 +3754,8 @@ void kmem_cache_free(struct kmem_cache *cachep, void *objp) debug_check_no_obj_freed(objp, obj_size(cachep)); __cache_free(cachep, objp); local_irq_restore(flags); + + trace_kmem_cache_free(_RET_IP_, objp); } EXPORT_SYMBOL(kmem_cache_free); @@ -3720,6 +3773,8 @@ void kfree(const void *objp) struct kmem_cache *c; unsigned long flags; + trace_kfree(_RET_IP_, objp); + if (unlikely(ZERO_OR_NULL_PTR(objp))) return; local_irq_save(flags); diff --git a/mm/slob.c b/mm/slob.c index 7a3411524da..a2d4ab32198 100644 --- a/mm/slob.c +++ b/mm/slob.c @@ -65,6 +65,7 @@ #include <linux/module.h> #include <linux/rcupdate.h> #include <linux/list.h> +#include <trace/kmemtrace.h> #include <asm/atomic.h> /* @@ -474,6 +475,7 @@ void *__kmalloc_node(size_t size, gfp_t gfp, int node) { unsigned int *m; int align = max(ARCH_KMALLOC_MINALIGN, ARCH_SLAB_MINALIGN); + void *ret; lockdep_trace_alloc(gfp); @@ -482,12 +484,16 @@ void *__kmalloc_node(size_t size, gfp_t gfp, int node) return ZERO_SIZE_PTR; m = slob_alloc(size + align, gfp, align, node); + if (!m) return NULL; *m = size; - return (void *)m + align; + ret = (void *)m + align; + + trace_kmalloc_node(_RET_IP_, ret, + size, size + align, gfp, node); } else { - void *ret; + unsigned int order = get_order(size); ret = slob_new_pages(gfp | __GFP_COMP, get_order(size), node); if (ret) { @@ -495,8 +501,12 @@ void *__kmalloc_node(size_t size, gfp_t gfp, int node) page = virt_to_page(ret); page->private = size; } - return ret; + + trace_kmalloc_node(_RET_IP_, ret, + size, PAGE_SIZE << order, gfp, node); } + + return ret; } EXPORT_SYMBOL(__kmalloc_node); @@ -504,6 +514,8 @@ void kfree(const void *block) { struct slob_page *sp; + trace_kfree(_RET_IP_, block); + if (unlikely(ZERO_OR_NULL_PTR(block))) return; @@ -583,10 +595,17 @@ void *kmem_cache_alloc_node(struct kmem_cache *c, gfp_t flags, int node) { void *b; - if (c->size < PAGE_SIZE) + if (c->size < PAGE_SIZE) { b = slob_alloc(c->size, flags, c->align, node); - else + trace_kmem_cache_alloc_node(_RET_IP_, b, c->size, + SLOB_UNITS(c->size) * SLOB_UNIT, + flags, node); + } else { b = slob_new_pages(flags, get_order(c->size), node); + trace_kmem_cache_alloc_node(_RET_IP_, b, c->size, + PAGE_SIZE << get_order(c->size), + flags, node); + } if (c->ctor) c->ctor(b); @@ -622,6 +641,8 @@ void kmem_cache_free(struct kmem_cache *c, void *b) } else { __kmem_cache_free(b, c->size); } + + trace_kmem_cache_free(_RET_IP_, b); } EXPORT_SYMBOL(kmem_cache_free); diff --git a/mm/slub.c b/mm/slub.c index c4ea9158c9f..7ab54ecbd3f 100644 --- a/mm/slub.c +++ b/mm/slub.c @@ -16,6 +16,7 @@ #include <linux/slab.h> #include <linux/proc_fs.h> #include <linux/seq_file.h> +#include <trace/kmemtrace.h> #include <linux/cpu.h> #include <linux/cpuset.h> #include <linux/mempolicy.h> @@ -1618,18 +1619,45 @@ static __always_inline void *slab_alloc(struct kmem_cache *s, void *kmem_cache_alloc(struct kmem_cache *s, gfp_t gfpflags) { - return slab_alloc(s, gfpflags, -1, _RET_IP_); + void *ret = slab_alloc(s, gfpflags, -1, _RET_IP_); + + trace_kmem_cache_alloc(_RET_IP_, ret, s->objsize, s->size, gfpflags); + + return ret; } EXPORT_SYMBOL(kmem_cache_alloc); +#ifdef CONFIG_KMEMTRACE +void *kmem_cache_alloc_notrace(struct kmem_cache *s, gfp_t gfpflags) +{ + return slab_alloc(s, gfpflags, -1, _RET_IP_); +} +EXPORT_SYMBOL(kmem_cache_alloc_notrace); +#endif + #ifdef CONFIG_NUMA void *kmem_cache_alloc_node(struct kmem_cache *s, gfp_t gfpflags, int node) { - return slab_alloc(s, gfpflags, node, _RET_IP_); + void *ret = slab_alloc(s, gfpflags, node, _RET_IP_); + + trace_kmem_cache_alloc_node(_RET_IP_, ret, + s->objsize, s->size, gfpflags, node); + + return ret; } EXPORT_SYMBOL(kmem_cache_alloc_node); #endif +#ifdef CONFIG_KMEMTRACE +void *kmem_cache_alloc_node_notrace(struct kmem_cache *s, + gfp_t gfpflags, + int node) +{ + return slab_alloc(s, gfpflags, node, _RET_IP_); +} +EXPORT_SYMBOL(kmem_cache_alloc_node_notrace); +#endif + /* * Slow patch handling. This may still be called frequently since objects * have a longer lifetime than the cpu slabs in most processing loads. @@ -1737,6 +1765,8 @@ void kmem_cache_free(struct kmem_cache *s, void *x) page = virt_to_head_page(x); slab_free(s, page, x, _RET_IP_); + + trace_kmem_cache_free(_RET_IP_, x); } EXPORT_SYMBOL(kmem_cache_free); @@ -2659,6 +2689,7 @@ static struct kmem_cache *get_slab(size_t size, gfp_t flags) void *__kmalloc(size_t size, gfp_t flags) { struct kmem_cache *s; + void *ret; if (unlikely(size > SLUB_MAX_SIZE)) return kmalloc_large(size, flags); @@ -2668,7 +2699,11 @@ void *__kmalloc(size_t size, gfp_t flags) if (unlikely(ZERO_OR_NULL_PTR(s))) return s; - return slab_alloc(s, flags, -1, _RET_IP_); + ret = slab_alloc(s, flags, -1, _RET_IP_); + + trace_kmalloc(_RET_IP_, ret, size, s->size, flags); + + return ret; } EXPORT_SYMBOL(__kmalloc); @@ -2687,16 +2722,28 @@ static void *kmalloc_large_node(size_t size, gfp_t flags, int node) void *__kmalloc_node(size_t size, gfp_t flags, int node) { struct kmem_cache *s; + void *ret; - if (unlikely(size > SLUB_MAX_SIZE)) - return kmalloc_large_node(size, flags, node); + if (unlikely(size > SLUB_MAX_SIZE)) { + ret = kmalloc_large_node(size, flags, node); + + trace_kmalloc_node(_RET_IP_, ret, + size, PAGE_SIZE << get_order(size), + flags, node); + + return ret; + } s = get_slab(size, flags); if (unlikely(ZERO_OR_NULL_PTR(s))) return s; - return slab_alloc(s, flags, node, _RET_IP_); + ret = slab_alloc(s, flags, node, _RET_IP_); + + trace_kmalloc_node(_RET_IP_, ret, size, s->size, flags, node); + + return ret; } EXPORT_SYMBOL(__kmalloc_node); #endif @@ -2745,6 +2792,8 @@ void kfree(const void *x) struct page *page; void *object = (void *)x; + trace_kfree(_RET_IP_, x); + if (unlikely(ZERO_OR_NULL_PTR(x))) return; @@ -3224,6 +3273,7 @@ static struct notifier_block __cpuinitdata slab_notifier = { void *__kmalloc_track_caller(size_t size, gfp_t gfpflags, unsigned long caller) { struct kmem_cache *s; + void *ret; if (unlikely(size > SLUB_MAX_SIZE)) return kmalloc_large(size, gfpflags); @@ -3233,13 +3283,19 @@ void *__kmalloc_track_caller(size_t size, gfp_t gfpflags, unsigned long caller) if (unlikely(ZERO_OR_NULL_PTR(s))) return s; - return slab_alloc(s, gfpflags, -1, caller); + ret = slab_alloc(s, gfpflags, -1, caller); + + /* Honor the call site pointer we recieved. */ + trace_kmalloc(caller, ret, size, s->size, gfpflags); + + return ret; } void *__kmalloc_node_track_caller(size_t size, gfp_t gfpflags, int node, unsigned long caller) { struct kmem_cache *s; + void *ret; if (unlikely(size > SLUB_MAX_SIZE)) return kmalloc_large_node(size, gfpflags, node); @@ -3249,7 +3305,12 @@ void *__kmalloc_node_track_caller(size_t size, gfp_t gfpflags, if (unlikely(ZERO_OR_NULL_PTR(s))) return s; - return slab_alloc(s, gfpflags, node, caller); + ret = slab_alloc(s, gfpflags, node, caller); + + /* Honor the call site pointer we recieved. */ + trace_kmalloc_node(caller, ret, size, s->size, gfpflags, node); + + return ret; } #ifdef CONFIG_SLUB_DEBUG diff --git a/mm/swap.c b/mm/swap.c index 6e83084c1f6..bede23ce64e 100644 --- a/mm/swap.c +++ b/mm/swap.c @@ -448,8 +448,8 @@ void pagevec_strip(struct pagevec *pvec) for (i = 0; i < pagevec_count(pvec); i++) { struct page *page = pvec->pages[i]; - if (PagePrivate(page) && trylock_page(page)) { - if (PagePrivate(page)) + if (page_has_private(page) && trylock_page(page)) { + if (page_has_private(page)) try_to_release_page(page, 0); unlock_page(page); } diff --git a/mm/truncate.c b/mm/truncate.c index 1229211104f..55206fab7b9 100644 --- a/mm/truncate.c +++ b/mm/truncate.c @@ -50,7 +50,7 @@ void do_invalidatepage(struct page *page, unsigned long offset) static inline void truncate_partial_page(struct page *page, unsigned partial) { zero_user_segment(page, partial, PAGE_CACHE_SIZE); - if (PagePrivate(page)) + if (page_has_private(page)) do_invalidatepage(page, partial); } @@ -99,7 +99,7 @@ truncate_complete_page(struct address_space *mapping, struct page *page) if (page->mapping != mapping) return; - if (PagePrivate(page)) + if (page_has_private(page)) do_invalidatepage(page, 0); cancel_dirty_page(page, PAGE_CACHE_SIZE); @@ -126,7 +126,7 @@ invalidate_complete_page(struct address_space *mapping, struct page *page) if (page->mapping != mapping) return 0; - if (PagePrivate(page) && !try_to_release_page(page, 0)) + if (page_has_private(page) && !try_to_release_page(page, 0)) return 0; clear_page_mlock(page); @@ -348,7 +348,7 @@ invalidate_complete_page2(struct address_space *mapping, struct page *page) if (page->mapping != mapping) return 0; - if (PagePrivate(page) && !try_to_release_page(page, GFP_KERNEL)) + if (page_has_private(page) && !try_to_release_page(page, GFP_KERNEL)) return 0; spin_lock_irq(&mapping->tree_lock); @@ -356,7 +356,7 @@ invalidate_complete_page2(struct address_space *mapping, struct page *page) goto failed; clear_page_mlock(page); - BUG_ON(PagePrivate(page)); + BUG_ON(page_has_private(page)); __remove_from_page_cache(page); spin_unlock_irq(&mapping->tree_lock); page_cache_release(page); /* pagecache ref */ diff --git a/mm/util.c b/mm/util.c index 7c122e49f76..55bef160b9f 100644 --- a/mm/util.c +++ b/mm/util.c @@ -4,6 +4,7 @@ #include <linux/module.h> #include <linux/err.h> #include <linux/sched.h> +#include <linux/tracepoint.h> #include <asm/uaccess.h> /** @@ -222,6 +223,22 @@ void arch_pick_mmap_layout(struct mm_struct *mm) } #endif +/** + * get_user_pages_fast() - pin user pages in memory + * @start: starting user address + * @nr_pages: number of pages from start to pin + * @write: whether pages will be written to + * @pages: array that receives pointers to the pages pinned. + * Should be at least nr_pages long. + * + * Attempt to pin user pages in memory without taking mm->mmap_sem. + * If not successful, it will fall back to taking the lock and + * calling get_user_pages(). + * + * Returns number of pages pinned. This may be fewer than the number + * requested. If nr_pages is 0 or negative, returns 0. If no pages + * were pinned, returns -errno. + */ int __attribute__((weak)) get_user_pages_fast(unsigned long start, int nr_pages, int write, struct page **pages) { @@ -236,3 +253,18 @@ int __attribute__((weak)) get_user_pages_fast(unsigned long start, return ret; } EXPORT_SYMBOL_GPL(get_user_pages_fast); + +/* Tracepoints definitions. */ +DEFINE_TRACE(kmalloc); +DEFINE_TRACE(kmem_cache_alloc); +DEFINE_TRACE(kmalloc_node); +DEFINE_TRACE(kmem_cache_alloc_node); +DEFINE_TRACE(kfree); +DEFINE_TRACE(kmem_cache_free); + +EXPORT_TRACEPOINT_SYMBOL(kmalloc); +EXPORT_TRACEPOINT_SYMBOL(kmem_cache_alloc); +EXPORT_TRACEPOINT_SYMBOL(kmalloc_node); +EXPORT_TRACEPOINT_SYMBOL(kmem_cache_alloc_node); +EXPORT_TRACEPOINT_SYMBOL(kfree); +EXPORT_TRACEPOINT_SYMBOL(kmem_cache_free); diff --git a/mm/vmscan.c b/mm/vmscan.c index 06e72693b45..39fdfb14eea 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -283,7 +283,7 @@ static inline int page_mapping_inuse(struct page *page) static inline int is_page_cache_freeable(struct page *page) { - return page_count(page) - !!PagePrivate(page) == 2; + return page_count(page) - !!page_has_private(page) == 2; } static int may_write_to_queue(struct backing_dev_info *bdi) @@ -367,7 +367,7 @@ static pageout_t pageout(struct page *page, struct address_space *mapping, * Some data journaling orphaned pages can have * page->mapping == NULL while being dirty with clean buffers. */ - if (PagePrivate(page)) { + if (page_has_private(page)) { if (try_to_free_buffers(page)) { ClearPageDirty(page); printk("%s: orphaned page\n", __func__); @@ -727,7 +727,7 @@ static unsigned long shrink_page_list(struct list_head *page_list, * process address space (page_count == 1) it can be freed. * Otherwise, leave the page on the LRU so it is swappable. */ - if (PagePrivate(page)) { + if (page_has_private(page)) { if (!try_to_release_page(page, sc->gfp_mask)) goto activate_locked; if (!mapping && page_count(page) == 1) { @@ -1967,7 +1967,7 @@ static int kswapd(void *p) struct reclaim_state reclaim_state = { .reclaimed_slab = 0, }; - node_to_cpumask_ptr(cpumask, pgdat->node_id); + const struct cpumask *cpumask = cpumask_of_node(pgdat->node_id); lockdep_set_current_reclaim_state(GFP_KERNEL); @@ -2204,7 +2204,9 @@ static int __devinit cpu_callback(struct notifier_block *nfb, if (action == CPU_ONLINE || action == CPU_ONLINE_FROZEN) { for_each_node_state(nid, N_HIGH_MEMORY) { pg_data_t *pgdat = NODE_DATA(nid); - node_to_cpumask_ptr(mask, pgdat->node_id); + const struct cpumask *mask; + + mask = cpumask_of_node(pgdat->node_id); if (cpumask_any_and(cpu_online_mask, mask) < nr_cpu_ids) /* One of our CPUs online: restore mask */ |