diff options
Diffstat (limited to 'mm')
-rw-r--r-- | mm/Kconfig | 9 | ||||
-rw-r--r-- | mm/Kconfig.debug | 26 | ||||
-rw-r--r-- | mm/Makefile | 5 | ||||
-rw-r--r-- | mm/allocpercpu.c | 36 | ||||
-rw-r--r-- | mm/backing-dev.c | 36 | ||||
-rw-r--r-- | mm/bootmem.c | 35 | ||||
-rw-r--r-- | mm/debug-pagealloc.c | 129 | ||||
-rw-r--r-- | mm/failslab.c | 1 | ||||
-rw-r--r-- | mm/filemap.c | 30 | ||||
-rw-r--r-- | mm/filemap_xip.c | 4 | ||||
-rw-r--r-- | mm/highmem.c | 110 | ||||
-rw-r--r-- | mm/hugetlb.c | 6 | ||||
-rw-r--r-- | mm/internal.h | 8 | ||||
-rw-r--r-- | mm/memcontrol.c | 687 | ||||
-rw-r--r-- | mm/memory.c | 39 | ||||
-rw-r--r-- | mm/migrate.c | 10 | ||||
-rw-r--r-- | mm/mlock.c | 7 | ||||
-rw-r--r-- | mm/mmap.c | 7 | ||||
-rw-r--r-- | mm/nommu.c | 52 | ||||
-rw-r--r-- | mm/oom_kill.c | 13 | ||||
-rw-r--r-- | mm/page-writeback.c | 59 | ||||
-rw-r--r-- | mm/page_alloc.c | 69 | ||||
-rw-r--r-- | mm/page_cgroup.c | 37 | ||||
-rw-r--r-- | mm/page_io.c | 2 | ||||
-rw-r--r-- | mm/pdflush.c | 2 | ||||
-rw-r--r-- | mm/percpu.c | 1326 | ||||
-rw-r--r-- | mm/quicklist.c | 2 | ||||
-rw-r--r-- | mm/readahead.c | 65 | ||||
-rw-r--r-- | mm/shmem.c | 48 | ||||
-rw-r--r-- | mm/slab.c | 79 | ||||
-rw-r--r-- | mm/slob.c | 77 | ||||
-rw-r--r-- | mm/slub.c | 159 | ||||
-rw-r--r-- | mm/sparse.c | 4 | ||||
-rw-r--r-- | mm/swap.c | 27 | ||||
-rw-r--r-- | mm/swapfile.c | 4 | ||||
-rw-r--r-- | mm/truncate.c | 10 | ||||
-rw-r--r-- | mm/util.c | 66 | ||||
-rw-r--r-- | mm/vmalloc.c | 136 | ||||
-rw-r--r-- | mm/vmscan.c | 145 | ||||
-rw-r--r-- | mm/vmstat.c | 18 |
40 files changed, 2901 insertions, 684 deletions
@@ -206,7 +206,6 @@ config VIRT_TO_BUS config UNEVICTABLE_LRU bool "Add LRU list to track non-evictable pages" default y - depends on MMU help Keeps unevictable pages off of the active and inactive pageout lists, so kswapd will not waste CPU time or have its balancing @@ -214,5 +213,13 @@ config UNEVICTABLE_LRU will use one page flag and increase the code size a little, say Y unless you know what you are doing. +config HAVE_MLOCK + bool + default y if MMU=y + +config HAVE_MLOCKED_PAGE_BIT + bool + default y if HAVE_MLOCK=y && UNEVICTABLE_LRU=y + config MMU_NOTIFIER bool diff --git a/mm/Kconfig.debug b/mm/Kconfig.debug new file mode 100644 index 0000000..bb01e29 --- /dev/null +++ b/mm/Kconfig.debug @@ -0,0 +1,26 @@ +config DEBUG_PAGEALLOC + bool "Debug page memory allocations" + depends on DEBUG_KERNEL && ARCH_SUPPORTS_DEBUG_PAGEALLOC + depends on !HIBERNATION || !PPC && !SPARC + ---help--- + Unmap pages from the kernel linear mapping after free_pages(). + This results in a large slowdown, but helps to find certain types + of memory corruptions. + +config WANT_PAGE_DEBUG_FLAGS + bool + +config PAGE_POISONING + bool "Debug page memory allocations" + depends on DEBUG_KERNEL && !ARCH_SUPPORTS_DEBUG_PAGEALLOC + depends on !HIBERNATION + select DEBUG_PAGEALLOC + select WANT_PAGE_DEBUG_FLAGS + help + Fill the pages with poison patterns after free_pages() and verify + the patterns before alloc_pages(). This results in a large slowdown, + but helps to find certain types of memory corruptions. + + This option cannot enalbe with hibernation. Otherwise, it will get + wrong messages for memory corruption because the free pages are not + saved to the suspend image. diff --git a/mm/Makefile b/mm/Makefile index 72255be..ec73c68 100644 --- a/mm/Makefile +++ b/mm/Makefile @@ -24,12 +24,17 @@ obj-$(CONFIG_SPARSEMEM_VMEMMAP) += sparse-vmemmap.o obj-$(CONFIG_TMPFS_POSIX_ACL) += shmem_acl.o obj-$(CONFIG_SLOB) += slob.o obj-$(CONFIG_MMU_NOTIFIER) += mmu_notifier.o +obj-$(CONFIG_PAGE_POISONING) += debug-pagealloc.o obj-$(CONFIG_SLAB) += slab.o obj-$(CONFIG_SLUB) += slub.o obj-$(CONFIG_FAILSLAB) += failslab.o obj-$(CONFIG_MEMORY_HOTPLUG) += memory_hotplug.o obj-$(CONFIG_FS_XIP) += filemap_xip.o obj-$(CONFIG_MIGRATION) += migrate.o +ifdef CONFIG_HAVE_DYNAMIC_PER_CPU_AREA +obj-$(CONFIG_SMP) += percpu.o +else obj-$(CONFIG_SMP) += allocpercpu.o +endif obj-$(CONFIG_QUICKLIST) += quicklist.o obj-$(CONFIG_CGROUP_MEM_RES_CTLR) += memcontrol.o page_cgroup.o diff --git a/mm/allocpercpu.c b/mm/allocpercpu.c index 4297bc4..dfdee6a 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) @@ -99,45 +99,51 @@ static int __percpu_populate_mask(void *__pdata, size_t size, gfp_t gfp, __percpu_populate_mask((__pdata), (size), (gfp), &(mask)) /** - * percpu_alloc_mask - initial setup of per-cpu data + * alloc_percpu - initial setup of per-cpu data * @size: size of per-cpu object - * @gfp: may sleep or not etc. - * @mask: populate per-data for cpu's selected through mask bits + * @align: alignment * - * Populating per-cpu data for all online cpu's would be a typical use case, - * which is simplified by the percpu_alloc() wrapper. - * Per-cpu objects are populated with zeroed buffers. + * Allocate dynamic percpu area. Percpu objects are populated with + * zeroed buffers. */ -void *__percpu_alloc_mask(size_t size, gfp_t gfp, cpumask_t *mask) +void *__alloc_percpu(size_t size, size_t align) { /* * We allocate whole cache lines to avoid false sharing */ size_t sz = roundup(nr_cpu_ids * sizeof(void *), cache_line_size()); - void *pdata = kzalloc(sz, gfp); + void *pdata = kzalloc(sz, GFP_KERNEL); void *__pdata = __percpu_disguise(pdata); + /* + * Can't easily make larger alignment work with kmalloc. WARN + * on it. Larger alignment should only be used for module + * percpu sections on SMP for which this path isn't used. + */ + WARN_ON_ONCE(align > SMP_CACHE_BYTES); + if (unlikely(!pdata)) return NULL; - if (likely(!__percpu_populate_mask(__pdata, size, gfp, mask))) + if (likely(!__percpu_populate_mask(__pdata, size, GFP_KERNEL, + &cpu_possible_map))) return __pdata; kfree(pdata); return NULL; } -EXPORT_SYMBOL_GPL(__percpu_alloc_mask); +EXPORT_SYMBOL_GPL(__alloc_percpu); /** - * percpu_free - final cleanup of per-cpu data + * free_percpu - final cleanup of per-cpu data * @__pdata: object to clean up * * We simply clean up any per-cpu object left. No need for the client to * track and specify through a bis mask which per-cpu objects are to free. */ -void percpu_free(void *__pdata) +void free_percpu(void *__pdata) { if (unlikely(!__pdata)) return; - __percpu_depopulate_mask(__pdata, &cpu_possible_map); + __percpu_depopulate_mask(__pdata, cpu_possible_mask); kfree(__percpu_disguise(__pdata)); } -EXPORT_SYMBOL_GPL(percpu_free); +EXPORT_SYMBOL_GPL(free_percpu); diff --git a/mm/backing-dev.c b/mm/backing-dev.c index 8e85874..493b468 100644 --- a/mm/backing-dev.c +++ b/mm/backing-dev.c @@ -2,11 +2,24 @@ #include <linux/wait.h> #include <linux/backing-dev.h> #include <linux/fs.h> +#include <linux/pagemap.h> #include <linux/sched.h> #include <linux/module.h> #include <linux/writeback.h> #include <linux/device.h> +void default_unplug_io_fn(struct backing_dev_info *bdi, struct page *page) +{ +} +EXPORT_SYMBOL(default_unplug_io_fn); + +struct backing_dev_info default_backing_dev_info = { + .ra_pages = VM_MAX_READAHEAD * 1024 / PAGE_CACHE_SIZE, + .state = 0, + .capabilities = BDI_CAP_MAP_COPY, + .unplug_io_fn = default_unplug_io_fn, +}; +EXPORT_SYMBOL_GPL(default_backing_dev_info); static struct class *bdi_class; @@ -166,9 +179,20 @@ static __init int bdi_class_init(void) bdi_debug_init(); return 0; } - postcore_initcall(bdi_class_init); +static int __init default_bdi_init(void) +{ + int err; + + err = bdi_init(&default_backing_dev_info); + if (!err) + bdi_register(&default_backing_dev_info, NULL, "default"); + + return err; +} +subsys_initcall(default_bdi_init); + int bdi_register(struct backing_dev_info *bdi, struct device *parent, const char *fmt, ...) { @@ -260,12 +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)) @@ -273,11 +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/bootmem.c b/mm/bootmem.c index 51a0ccf..daf9271 100644 --- a/mm/bootmem.c +++ b/mm/bootmem.c @@ -382,7 +382,6 @@ int __init reserve_bootmem_node(pg_data_t *pgdat, unsigned long physaddr, return mark_bootmem_node(pgdat->bdata, start, end, 1, flags); } -#ifndef CONFIG_HAVE_ARCH_BOOTMEM_NODE /** * reserve_bootmem - mark a page range as usable * @addr: starting address of the range @@ -403,7 +402,6 @@ int __init reserve_bootmem(unsigned long addr, unsigned long size, return mark_bootmem(start, end, 1, flags); } -#endif /* !CONFIG_HAVE_ARCH_BOOTMEM_NODE */ static unsigned long align_idx(struct bootmem_data *bdata, unsigned long idx, unsigned long step) @@ -429,8 +427,8 @@ static unsigned long align_off(struct bootmem_data *bdata, unsigned long off, } static void * __init alloc_bootmem_core(struct bootmem_data *bdata, - unsigned long size, unsigned long align, - unsigned long goal, unsigned long limit) + unsigned long size, unsigned long align, + unsigned long goal, unsigned long limit) { unsigned long fallback = 0; unsigned long min, max, start, sidx, midx, step; @@ -530,17 +528,34 @@ find_block: return NULL; } +static void * __init alloc_arch_preferred_bootmem(bootmem_data_t *bdata, + unsigned long size, unsigned long align, + unsigned long goal, unsigned long limit) +{ +#ifdef CONFIG_HAVE_ARCH_BOOTMEM + bootmem_data_t *p_bdata; + + p_bdata = bootmem_arch_preferred_node(bdata, size, align, goal, limit); + if (p_bdata) + return alloc_bootmem_core(p_bdata, size, align, goal, limit); +#endif + return NULL; +} + static void * __init ___alloc_bootmem_nopanic(unsigned long size, unsigned long align, unsigned long goal, unsigned long limit) { bootmem_data_t *bdata; + void *region; restart: - list_for_each_entry(bdata, &bdata_list, list) { - void *region; + region = alloc_arch_preferred_bootmem(NULL, size, align, goal, limit); + if (region) + return region; + list_for_each_entry(bdata, &bdata_list, list) { if (goal && bdata->node_low_pfn <= PFN_DOWN(goal)) continue; if (limit && bdata->node_min_pfn >= PFN_DOWN(limit)) @@ -618,6 +633,10 @@ static void * __init ___alloc_bootmem_node(bootmem_data_t *bdata, { void *ptr; + ptr = alloc_arch_preferred_bootmem(bdata, size, align, goal, limit); + if (ptr) + return ptr; + ptr = alloc_bootmem_core(bdata, size, align, goal, limit); if (ptr) return ptr; @@ -674,6 +693,10 @@ void * __init __alloc_bootmem_node_nopanic(pg_data_t *pgdat, unsigned long size, { void *ptr; + ptr = alloc_arch_preferred_bootmem(pgdat->bdata, size, align, goal, 0); + if (ptr) + return ptr; + ptr = alloc_bootmem_core(pgdat->bdata, size, align, goal, 0); if (ptr) return ptr; diff --git a/mm/debug-pagealloc.c b/mm/debug-pagealloc.c new file mode 100644 index 0000000..a1e3324 --- /dev/null +++ b/mm/debug-pagealloc.c @@ -0,0 +1,129 @@ +#include <linux/kernel.h> +#include <linux/mm.h> +#include <linux/page-debug-flags.h> +#include <linux/poison.h> + +static inline void set_page_poison(struct page *page) +{ + __set_bit(PAGE_DEBUG_FLAG_POISON, &page->debug_flags); +} + +static inline void clear_page_poison(struct page *page) +{ + __clear_bit(PAGE_DEBUG_FLAG_POISON, &page->debug_flags); +} + +static inline bool page_poison(struct page *page) +{ + return test_bit(PAGE_DEBUG_FLAG_POISON, &page->debug_flags); +} + +static void poison_highpage(struct page *page) +{ + /* + * Page poisoning for highmem pages is not implemented. + * + * This can be called from interrupt contexts. + * So we need to create a new kmap_atomic slot for this + * application and it will need interrupt protection. + */ +} + +static void poison_page(struct page *page) +{ + void *addr; + + if (PageHighMem(page)) { + poison_highpage(page); + return; + } + set_page_poison(page); + addr = page_address(page); + memset(addr, PAGE_POISON, PAGE_SIZE); +} + +static void poison_pages(struct page *page, int n) +{ + int i; + + for (i = 0; i < n; i++) + poison_page(page + i); +} + +static bool single_bit_flip(unsigned char a, unsigned char b) +{ + unsigned char error = a ^ b; + + return error && !(error & (error - 1)); +} + +static void check_poison_mem(unsigned char *mem, size_t bytes) +{ + unsigned char *start; + unsigned char *end; + + for (start = mem; start < mem + bytes; start++) { + if (*start != PAGE_POISON) + break; + } + if (start == mem + bytes) + return; + + for (end = mem + bytes - 1; end > start; end--) { + if (*end != PAGE_POISON) + break; + } + + if (!printk_ratelimit()) + return; + else if (start == end && single_bit_flip(*start, PAGE_POISON)) + printk(KERN_ERR "pagealloc: single bit error\n"); + else + printk(KERN_ERR "pagealloc: memory corruption\n"); + + print_hex_dump(KERN_ERR, "", DUMP_PREFIX_ADDRESS, 16, 1, start, + end - start + 1, 1); + dump_stack(); +} + +static void unpoison_highpage(struct page *page) +{ + /* + * See comment in poison_highpage(). + * Highmem pages should not be poisoned for now + */ + BUG_ON(page_poison(page)); +} + +static void unpoison_page(struct page *page) +{ + if (PageHighMem(page)) { + unpoison_highpage(page); + return; + } + if (page_poison(page)) { + void *addr = page_address(page); + + check_poison_mem(addr, PAGE_SIZE); + clear_page_poison(page); + } +} + +static void unpoison_pages(struct page *page, int n) +{ + int i; + + for (i = 0; i < n; i++) + unpoison_page(page + i); +} + +void kernel_map_pages(struct page *page, int numpages, int enable) +{ + if (!debug_pagealloc_enabled) + return; + + if (enable) + unpoison_pages(page, numpages); + else + poison_pages(page, numpages); +} diff --git a/mm/failslab.c b/mm/failslab.c index 7c6ea64..9339de5 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 23acefe..2e2d38e 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -513,6 +513,7 @@ 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 +566,24 @@ 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 +646,7 @@ 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() @@ -1823,7 +1843,7 @@ static size_t __iovec_copy_from_user_inatomic(char *vaddr, int copy = min(bytes, iov->iov_len - base); base = 0; - left = __copy_from_user_inatomic_nocache(vaddr, buf, copy); + left = __copy_from_user_inatomic(vaddr, buf, copy); copied += copy; bytes -= copy; vaddr += copy; @@ -1851,8 +1871,7 @@ size_t iov_iter_copy_from_user_atomic(struct page *page, if (likely(i->nr_segs == 1)) { int left; char __user *buf = i->iov->iov_base + i->iov_offset; - left = __copy_from_user_inatomic_nocache(kaddr + offset, - buf, bytes); + left = __copy_from_user_inatomic(kaddr + offset, buf, bytes); copied = bytes - left; } else { copied = __iovec_copy_from_user_inatomic(kaddr + offset, @@ -1880,7 +1899,7 @@ size_t iov_iter_copy_from_user(struct page *page, if (likely(i->nr_segs == 1)) { int left; char __user *buf = i->iov->iov_base + i->iov_offset; - left = __copy_from_user_nocache(kaddr + offset, buf, bytes); + left = __copy_from_user(kaddr + offset, buf, bytes); copied = bytes - left; } else { copied = __iovec_copy_from_user_inatomic(kaddr + offset, @@ -2464,6 +2483,9 @@ 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/filemap_xip.c b/mm/filemap_xip.c index 0c04615..427dfe3 100644 --- a/mm/filemap_xip.c +++ b/mm/filemap_xip.c @@ -89,8 +89,8 @@ do_xip_mapping_read(struct address_space *mapping, } } nr = nr - offset; - if (nr > len) - nr = len; + if (nr > len - copied) + nr = len - copied; error = mapping->a_ops->get_xip_mem(mapping, index, 0, &xip_mem, &xip_pfn); diff --git a/mm/highmem.c b/mm/highmem.c index b36b83b..68eb1d9 100644 --- a/mm/highmem.c +++ b/mm/highmem.c @@ -67,6 +67,25 @@ pte_t * pkmap_page_table; static DECLARE_WAIT_QUEUE_HEAD(pkmap_map_wait); +/* + * Most architectures have no use for kmap_high_get(), so let's abstract + * the disabling of IRQ out of the locking in that case to save on a + * potential useless overhead. + */ +#ifdef ARCH_NEEDS_KMAP_HIGH_GET +#define lock_kmap() spin_lock_irq(&kmap_lock) +#define unlock_kmap() spin_unlock_irq(&kmap_lock) +#define lock_kmap_any(flags) spin_lock_irqsave(&kmap_lock, flags) +#define unlock_kmap_any(flags) spin_unlock_irqrestore(&kmap_lock, flags) +#else +#define lock_kmap() spin_lock(&kmap_lock) +#define unlock_kmap() spin_unlock(&kmap_lock) +#define lock_kmap_any(flags) \ + do { spin_lock(&kmap_lock); (void)(flags); } while (0) +#define unlock_kmap_any(flags) \ + do { spin_unlock(&kmap_lock); (void)(flags); } while (0) +#endif + static void flush_all_zero_pkmaps(void) { int i; @@ -113,9 +132,9 @@ static void flush_all_zero_pkmaps(void) */ void kmap_flush_unused(void) { - spin_lock(&kmap_lock); + lock_kmap(); flush_all_zero_pkmaps(); - spin_unlock(&kmap_lock); + unlock_kmap(); } static inline unsigned long map_new_virtual(struct page *page) @@ -145,10 +164,10 @@ start: __set_current_state(TASK_UNINTERRUPTIBLE); add_wait_queue(&pkmap_map_wait, &wait); - spin_unlock(&kmap_lock); + unlock_kmap(); schedule(); remove_wait_queue(&pkmap_map_wait, &wait); - spin_lock(&kmap_lock); + lock_kmap(); /* Somebody else might have mapped it while we slept */ if (page_address(page)) @@ -184,29 +203,59 @@ void *kmap_high(struct page *page) * For highmem pages, we can't trust "virtual" until * after we have the lock. */ - spin_lock(&kmap_lock); + lock_kmap(); vaddr = (unsigned long)page_address(page); if (!vaddr) vaddr = map_new_virtual(page); pkmap_count[PKMAP_NR(vaddr)]++; BUG_ON(pkmap_count[PKMAP_NR(vaddr)] < 2); - spin_unlock(&kmap_lock); + unlock_kmap(); return (void*) vaddr; } EXPORT_SYMBOL(kmap_high); +#ifdef ARCH_NEEDS_KMAP_HIGH_GET +/** + * kmap_high_get - pin a highmem page into memory + * @page: &struct page to pin + * + * Returns the page's current virtual memory address, or NULL if no mapping + * exists. When and only when a non null address is returned then a + * matching call to kunmap_high() is necessary. + * + * This can be called from any context. + */ +void *kmap_high_get(struct page *page) +{ + unsigned long vaddr, flags; + + lock_kmap_any(flags); + vaddr = (unsigned long)page_address(page); + if (vaddr) { + BUG_ON(pkmap_count[PKMAP_NR(vaddr)] < 1); + pkmap_count[PKMAP_NR(vaddr)]++; + } + unlock_kmap_any(flags); + return (void*) vaddr; +} +#endif + /** * kunmap_high - map a highmem page into memory * @page: &struct page to unmap + * + * If ARCH_NEEDS_KMAP_HIGH_GET is not defined then this may be called + * only from user context. */ void kunmap_high(struct page *page) { unsigned long vaddr; unsigned long nr; + unsigned long flags; int need_wakeup; - spin_lock(&kmap_lock); + lock_kmap_any(flags); vaddr = (unsigned long)page_address(page); BUG_ON(!vaddr); nr = PKMAP_NR(vaddr); @@ -232,7 +281,7 @@ void kunmap_high(struct page *page) */ need_wakeup = waitqueue_active(&pkmap_map_wait); } - spin_unlock(&kmap_lock); + unlock_kmap_any(flags); /* do wake-up, if needed, race-free outside of the spin lock */ if (need_wakeup) @@ -373,3 +422,48 @@ void __init page_address_init(void) } #endif /* defined(CONFIG_HIGHMEM) && !defined(WANT_PAGE_VIRTUAL) */ + +#if defined(CONFIG_DEBUG_HIGHMEM) && defined(CONFIG_TRACE_IRQFLAGS_SUPPORT) + +void debug_kmap_atomic(enum km_type type) +{ + static unsigned warn_count = 10; + + if (unlikely(warn_count == 0)) + return; + + if (unlikely(in_interrupt())) { + if (in_irq()) { + if (type != KM_IRQ0 && type != KM_IRQ1 && + type != KM_BIO_SRC_IRQ && type != KM_BIO_DST_IRQ && + type != KM_BOUNCE_READ) { + WARN_ON(1); + warn_count--; + } + } else if (!irqs_disabled()) { /* softirq */ + if (type != KM_IRQ0 && type != KM_IRQ1 && + type != KM_SOFTIRQ0 && type != KM_SOFTIRQ1 && + type != KM_SKB_SUNRPC_DATA && + type != KM_SKB_DATA_SOFTIRQ && + type != KM_BOUNCE_READ) { + WARN_ON(1); + warn_count--; + } + } + } + + if (type == KM_IRQ0 || type == KM_IRQ1 || type == KM_BOUNCE_READ || + type == KM_BIO_SRC_IRQ || type == KM_BIO_DST_IRQ) { + if (!irqs_disabled()) { + WARN_ON(1); + warn_count--; + } + } else if (type == KM_SOFTIRQ0 || type == KM_SOFTIRQ1) { + if (irq_count() == 0 && !irqs_disabled()) { + WARN_ON(1); + warn_count--; + } + } +} + +#endif diff --git a/mm/hugetlb.c b/mm/hugetlb.c index 107da3d..28c655b 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -918,7 +918,7 @@ static void return_unused_surplus_pages(struct hstate *h, * an instantiated the change should be committed via vma_commit_reservation. * No action is required on failure. */ -static int vma_needs_reservation(struct hstate *h, +static long vma_needs_reservation(struct hstate *h, struct vm_area_struct *vma, unsigned long addr) { struct address_space *mapping = vma->vm_file->f_mapping; @@ -933,7 +933,7 @@ static int vma_needs_reservation(struct hstate *h, return 1; } else { - int err; + long err; pgoff_t idx = vma_hugecache_offset(h, vma, addr); struct resv_map *reservations = vma_resv_map(vma); @@ -969,7 +969,7 @@ static struct page *alloc_huge_page(struct vm_area_struct *vma, struct page *page; struct address_space *mapping = vma->vm_file->f_mapping; struct inode *inode = mapping->host; - unsigned int chg; + long chg; /* * Processes that did not create the mapping will have no reserves and diff --git a/mm/internal.h b/mm/internal.h index 478223b..987bb03 100644 --- a/mm/internal.h +++ b/mm/internal.h @@ -63,6 +63,7 @@ static inline unsigned long page_order(struct page *page) return page_private(page); } +#ifdef CONFIG_HAVE_MLOCK extern long mlock_vma_pages_range(struct vm_area_struct *vma, unsigned long start, unsigned long end); extern void munlock_vma_pages_range(struct vm_area_struct *vma, @@ -71,6 +72,7 @@ static inline void munlock_vma_pages_all(struct vm_area_struct *vma) { munlock_vma_pages_range(vma, vma->vm_start, vma->vm_end); } +#endif #ifdef CONFIG_UNEVICTABLE_LRU /* @@ -90,7 +92,7 @@ static inline void unevictable_migrate_page(struct page *new, struct page *old) } #endif -#ifdef CONFIG_UNEVICTABLE_LRU +#ifdef CONFIG_HAVE_MLOCKED_PAGE_BIT /* * Called only in fault path via page_evictable() for a new page * to determine if it's being mapped into a LOCKED vma. @@ -165,7 +167,7 @@ static inline void free_page_mlock(struct page *page) } } -#else /* CONFIG_UNEVICTABLE_LRU */ +#else /* CONFIG_HAVE_MLOCKED_PAGE_BIT */ static inline int is_mlocked_vma(struct vm_area_struct *v, struct page *p) { return 0; @@ -175,7 +177,7 @@ static inline void mlock_vma_page(struct page *page) { } static inline void mlock_migrate_page(struct page *new, struct page *old) { } static inline void free_page_mlock(struct page *page) { } -#endif /* CONFIG_UNEVICTABLE_LRU */ +#endif /* CONFIG_HAVE_MLOCKED_PAGE_BIT */ /* * Return the mem_map entry representing the 'offset' subpage within diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 8e4be9c..2fc6d6c 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -27,6 +27,7 @@ #include <linux/backing-dev.h> #include <linux/bit_spinlock.h> #include <linux/rcupdate.h> +#include <linux/limits.h> #include <linux/mutex.h> #include <linux/slab.h> #include <linux/swap.h> @@ -95,6 +96,15 @@ static s64 mem_cgroup_read_stat(struct mem_cgroup_stat *stat, return ret; } +static s64 mem_cgroup_local_usage(struct mem_cgroup_stat *stat) +{ + s64 ret; + + ret = mem_cgroup_read_stat(stat, MEM_CGROUP_STAT_CACHE); + ret += mem_cgroup_read_stat(stat, MEM_CGROUP_STAT_RSS); + return ret; +} + /* * per-zone information in memory controller. */ @@ -154,9 +164,9 @@ struct mem_cgroup { /* * While reclaiming in a hiearchy, we cache the last child we - * reclaimed from. Protected by hierarchy_mutex + * reclaimed from. */ - struct mem_cgroup *last_scanned_child; + int last_scanned_child; /* * Should the accounting and control be hierarchical, per subtree? */ @@ -247,7 +257,7 @@ page_cgroup_zoneinfo(struct page_cgroup *pc) return mem_cgroup_zoneinfo(mem, nid, zid); } -static unsigned long mem_cgroup_get_all_zonestat(struct mem_cgroup *mem, +static unsigned long mem_cgroup_get_local_zonestat(struct mem_cgroup *mem, enum lru_list idx) { int nid, zid; @@ -286,6 +296,9 @@ struct mem_cgroup *mem_cgroup_from_task(struct task_struct *p) static struct mem_cgroup *try_get_mem_cgroup_from_mm(struct mm_struct *mm) { struct mem_cgroup *mem = NULL; + + if (!mm) + return NULL; /* * Because we have no locks, mm->owner's may be being moved to other * cgroup. We use css_tryget() here even if this looks @@ -308,6 +321,42 @@ static bool mem_cgroup_is_obsolete(struct mem_cgroup *mem) return css_is_removed(&mem->css); } + +/* + * Call callback function against all cgroup under hierarchy tree. + */ +static int mem_cgroup_walk_tree(struct mem_cgroup *root, void *data, + int (*func)(struct mem_cgroup *, void *)) +{ + int found, ret, nextid; + struct cgroup_subsys_state *css; + struct mem_cgroup *mem; + + if (!root->use_hierarchy) + return (*func)(root, data); + + nextid = 1; + do { + ret = 0; + mem = NULL; + + rcu_read_lock(); + css = css_get_next(&mem_cgroup_subsys, nextid, &root->css, + &found); + if (css && css_tryget(css)) + mem = container_of(css, struct mem_cgroup, css); + rcu_read_unlock(); + + if (mem) { + ret = (*func)(mem, data); + css_put(&mem->css); + } + nextid = found + 1; + } while (!ret && css); + + return ret; +} + /* * Following LRU functions are allowed to be used without PCG_LOCK. * Operations are called by routine of global LRU independently from memcg. @@ -441,31 +490,24 @@ void mem_cgroup_move_lists(struct page *page, int task_in_mem_cgroup(struct task_struct *task, const struct mem_cgroup *mem) { int ret; + struct mem_cgroup *curr = NULL; task_lock(task); - ret = task->mm && mm_match_cgroup(task->mm, mem); + rcu_read_lock(); + curr = try_get_mem_cgroup_from_mm(task->mm); + rcu_read_unlock(); task_unlock(task); + if (!curr) + return 0; + if (curr->use_hierarchy) + ret = css_is_ancestor(&curr->css, &mem->css); + else + ret = (curr == mem); + css_put(&curr->css); return ret; } /* - * Calculate mapped_ratio under memory controller. This will be used in - * vmscan.c for deteremining we have to reclaim mapped pages. - */ -int mem_cgroup_calc_mapped_ratio(struct mem_cgroup *mem) -{ - long total, rss; - - /* - * usage is recorded in bytes. But, here, we assume the number of - * physical pages can be represented by "long" on any arch. - */ - total = (long) (mem->res.usage >> PAGE_SHIFT) + 1L; - rss = (long)mem_cgroup_read_stat(&mem->stat, MEM_CGROUP_STAT_RSS); - return (int)((rss * 100L) / total); -} - -/* * prev_priority control...this will be used in memory reclaim path. */ int mem_cgroup_get_reclaim_priority(struct mem_cgroup *mem) @@ -501,8 +543,8 @@ static int calc_inactive_ratio(struct mem_cgroup *memcg, unsigned long *present_ unsigned long gb; unsigned long inactive_ratio; - inactive = mem_cgroup_get_all_zonestat(memcg, LRU_INACTIVE_ANON); - active = mem_cgroup_get_all_zonestat(memcg, LRU_ACTIVE_ANON); + inactive = mem_cgroup_get_local_zonestat(memcg, LRU_INACTIVE_ANON); + active = mem_cgroup_get_local_zonestat(memcg, LRU_ACTIVE_ANON); gb = (inactive + active) >> (30 - PAGE_SHIFT); if (gb) @@ -629,172 +671,202 @@ unsigned long mem_cgroup_isolate_pages(unsigned long nr_to_scan, #define mem_cgroup_from_res_counter(counter, member) \ container_of(counter, struct mem_cgroup, member) -/* - * This routine finds the DFS walk successor. This routine should be - * called with hierarchy_mutex held - */ -static struct mem_cgroup * -__mem_cgroup_get_next_node(struct mem_cgroup *curr, struct mem_cgroup *root_mem) +static bool mem_cgroup_check_under_limit(struct mem_cgroup *mem) { - struct cgroup *cgroup, *curr_cgroup, *root_cgroup; - - curr_cgroup = curr->css.cgroup; - root_cgroup = root_mem->css.cgroup; + if (do_swap_account) { + if (res_counter_check_under_limit(&mem->res) && + res_counter_check_under_limit(&mem->memsw)) + return true; + } else + if (res_counter_check_under_limit(&mem->res)) + return true; + return false; +} - if (!list_empty(&curr_cgroup->children)) { - /* - * Walk down to children - */ - cgroup = list_entry(curr_cgroup->children.next, - struct cgroup, sibling); - curr = mem_cgroup_from_cont(cgroup); - goto done; - } +static unsigned int get_swappiness(struct mem_cgroup *memcg) +{ + struct cgroup *cgrp = memcg->css.cgroup; + unsigned int swappiness; -visit_parent: - if (curr_cgroup == root_cgroup) { - /* caller handles NULL case */ - curr = NULL; - goto done; - } + /* root ? */ + if (cgrp->parent == NULL) + return vm_swappiness; - /* - * Goto next sibling - */ - if (curr_cgroup->sibling.next != &curr_cgroup->parent->children) { - cgroup = list_entry(curr_cgroup->sibling.next, struct cgroup, - sibling); - curr = mem_cgroup_from_cont(cgroup); - goto done; - } + spin_lock(&memcg->reclaim_param_lock); + swappiness = memcg->swappiness; + spin_unlock(&memcg->reclaim_param_lock); - /* - * Go up to next parent and next parent's sibling if need be - */ - curr_cgroup = curr_cgroup->parent; - goto visit_parent; + return swappiness; +} -done: - return curr; +static int mem_cgroup_count_children_cb(struct mem_cgroup *mem, void *data) +{ + int *val = data; + (*val)++; + return 0; } -/* - * Visit the first child (need not be the first child as per the ordering - * of the cgroup list, since we track last_scanned_child) of @mem and use - * that to reclaim free pages from. +/** + * mem_cgroup_print_mem_info: Called from OOM with tasklist_lock held in read mode. + * @memcg: The memory cgroup that went over limit + * @p: Task that is going to be killed + * + * NOTE: @memcg and @p's mem_cgroup can be different when hierarchy is + * enabled */ -static struct mem_cgroup * -mem_cgroup_get_next_node(struct mem_cgroup *root_mem) +void mem_cgroup_print_oom_info(struct mem_cgroup *memcg, struct task_struct *p) { - struct cgroup *cgroup; - struct mem_cgroup *orig, *next; - bool obsolete; - + struct cgroup *task_cgrp; + struct cgroup *mem_cgrp; /* - * Scan all children under the mem_cgroup mem + * Need a buffer in BSS, can't rely on allocations. The code relies + * on the assumption that OOM is serialized for memory controller. + * If this assumption is broken, revisit this code. */ - mutex_lock(&mem_cgroup_subsys.hierarchy_mutex); + static char memcg_name[PATH_MAX]; + int ret; + + if (!memcg) + return; - orig = root_mem->last_scanned_child; - obsolete = mem_cgroup_is_obsolete(orig); - if (list_empty(&root_mem->css.cgroup->children)) { + rcu_read_lock(); + + mem_cgrp = memcg->css.cgroup; + task_cgrp = task_cgroup(p, mem_cgroup_subsys_id); + + ret = cgroup_path(task_cgrp, memcg_name, PATH_MAX); + if (ret < 0) { /* - * root_mem might have children before and last_scanned_child - * may point to one of them. We put it later. + * Unfortunately, we are unable to convert to a useful name + * But we'll still print out the usage information */ - if (orig) - VM_BUG_ON(!obsolete); - next = NULL; + rcu_read_unlock(); goto done; } + rcu_read_unlock(); - if (!orig || obsolete) { - cgroup = list_first_entry(&root_mem->css.cgroup->children, - struct cgroup, sibling); - next = mem_cgroup_from_cont(cgroup); - } else - next = __mem_cgroup_get_next_node(orig, root_mem); + printk(KERN_INFO "Task in %s killed", memcg_name); + rcu_read_lock(); + ret = cgroup_path(mem_cgrp, memcg_name, PATH_MAX); + if (ret < 0) { + rcu_read_unlock(); + goto done; + } + rcu_read_unlock(); + + /* + * Continues from above, so we don't need an KERN_ level + */ + printk(KERN_CONT " as a result of limit of %s\n", memcg_name); done: - if (next) - mem_cgroup_get(next); - root_mem->last_scanned_child = next; - if (orig) - mem_cgroup_put(orig); - mutex_unlock(&mem_cgroup_subsys.hierarchy_mutex); - return (next) ? next : root_mem; + + printk(KERN_INFO "memory: usage %llukB, limit %llukB, failcnt %llu\n", + res_counter_read_u64(&memcg->res, RES_USAGE) >> 10, + res_counter_read_u64(&memcg->res, RES_LIMIT) >> 10, + res_counter_read_u64(&memcg->res, RES_FAILCNT)); + printk(KERN_INFO "memory+swap: usage %llukB, limit %llukB, " + "failcnt %llu\n", + res_counter_read_u64(&memcg->memsw, RES_USAGE) >> 10, + res_counter_read_u64(&memcg->memsw, RES_LIMIT) >> 10, + res_counter_read_u64(&memcg->memsw, RES_FAILCNT)); } -static bool mem_cgroup_check_under_limit(struct mem_cgroup *mem) +/* + * This function returns the number of memcg under hierarchy tree. Returns + * 1(self count) if no children. + */ +static int mem_cgroup_count_children(struct mem_cgroup *mem) { - if (do_swap_account) { - if (res_counter_check_under_limit(&mem->res) && - res_counter_check_under_limit(&mem->memsw)) - return true; - } else - if (res_counter_check_under_limit(&mem->res)) - return true; - return false; + int num = 0; + mem_cgroup_walk_tree(mem, &num, mem_cgroup_count_children_cb); + return num; } -static unsigned int get_swappiness(struct mem_cgroup *memcg) +/* + * Visit the first child (need not be the first child as per the ordering + * of the cgroup list, since we track last_scanned_child) of @mem and use + * that to reclaim free pages from. + */ +static struct mem_cgroup * +mem_cgroup_select_victim(struct mem_cgroup *root_mem) { - struct cgroup *cgrp = memcg->css.cgroup; - unsigned int swappiness; + struct mem_cgroup *ret = NULL; + struct cgroup_subsys_state *css; + int nextid, found; - /* root ? */ - if (cgrp->parent == NULL) - return vm_swappiness; + if (!root_mem->use_hierarchy) { + css_get(&root_mem->css); + ret = root_mem; + } - spin_lock(&memcg->reclaim_param_lock); - swappiness = memcg->swappiness; - spin_unlock(&memcg->reclaim_param_lock); + while (!ret) { + rcu_read_lock(); + nextid = root_mem->last_scanned_child + 1; + css = css_get_next(&mem_cgroup_subsys, nextid, &root_mem->css, + &found); + if (css && css_tryget(css)) + ret = container_of(css, struct mem_cgroup, css); + + rcu_read_unlock(); + /* Updates scanning parameter */ + spin_lock(&root_mem->reclaim_param_lock); + if (!css) { + /* this means start scan from ID:1 */ + root_mem->last_scanned_child = 0; + } else + root_mem->last_scanned_child = found; + spin_unlock(&root_mem->reclaim_param_lock); + } - return swappiness; + return ret; } /* - * Dance down the hierarchy if needed to reclaim memory. We remember the - * last child we reclaimed from, so that we don't end up penalizing - * one child extensively based on its position in the children list. + * Scan the hierarchy if needed to reclaim memory. We remember the last child + * we reclaimed from, so that we don't end up penalizing one child extensively + * based on its position in the children list. * * root_mem is the original ancestor that we've been reclaim from. + * + * We give up and return to the caller when we visit root_mem twice. + * (other groups can be removed while we're walking....) + * + * If shrink==true, for avoiding to free too much, this returns immedieately. */ static int mem_cgroup_hierarchical_reclaim(struct mem_cgroup *root_mem, - gfp_t gfp_mask, bool noswap) -{ - struct mem_cgroup *next_mem; - int ret = 0; - - /* - * Reclaim unconditionally and don't check for return value. - * We need to reclaim in the current group and down the tree. - * One might think about checking for children before reclaiming, - * but there might be left over accounting, even after children - * have left. - */ - ret += try_to_free_mem_cgroup_pages(root_mem, gfp_mask, noswap, - get_swappiness(root_mem)); - if (mem_cgroup_check_under_limit(root_mem)) - return 1; /* indicate reclaim has succeeded */ - if (!root_mem->use_hierarchy) - return ret; - - next_mem = mem_cgroup_get_next_node(root_mem); - - while (next_mem != root_mem) { - if (mem_cgroup_is_obsolete(next_mem)) { - next_mem = mem_cgroup_get_next_node(root_mem); + gfp_t gfp_mask, bool noswap, bool shrink) +{ + struct mem_cgroup *victim; + int ret, total = 0; + int loop = 0; + + while (loop < 2) { + victim = mem_cgroup_select_victim(root_mem); + if (victim == root_mem) + loop++; + if (!mem_cgroup_local_usage(&victim->stat)) { + /* this cgroup's local usage == 0 */ + css_put(&victim->css); continue; } - ret += try_to_free_mem_cgroup_pages(next_mem, gfp_mask, noswap, - get_swappiness(next_mem)); + /* we use swappiness of local cgroup */ + ret = try_to_free_mem_cgroup_pages(victim, gfp_mask, noswap, + get_swappiness(victim)); + css_put(&victim->css); + /* + * At shrinking usage, we can't check we should stop here or + * reclaim more. It's depends on callers. last_scanned_child + * will work enough for keeping fairness under tree. + */ + if (shrink) + return ret; + total += ret; if (mem_cgroup_check_under_limit(root_mem)) - return 1; /* indicate reclaim has succeeded */ - next_mem = mem_cgroup_get_next_node(root_mem); + return 1 + total; } - return ret; + return total; } bool mem_cgroup_oom_called(struct task_struct *task) @@ -813,6 +885,19 @@ bool mem_cgroup_oom_called(struct task_struct *task) rcu_read_unlock(); return ret; } + +static int record_last_oom_cb(struct mem_cgroup *mem, void *data) +{ + mem->last_oom_jiffies = jiffies; + return 0; +} + +static void record_last_oom(struct mem_cgroup *mem) +{ + mem_cgroup_walk_tree(mem, NULL, record_last_oom_cb); +} + + /* * Unlike exported interface, "oom" parameter is added. if oom==true, * oom-killer can be invoked. @@ -875,7 +960,7 @@ static int __mem_cgroup_try_charge(struct mm_struct *mm, goto nomem; ret = mem_cgroup_hierarchical_reclaim(mem_over_limit, gfp_mask, - noswap); + noswap, false); if (ret) continue; @@ -895,7 +980,7 @@ static int __mem_cgroup_try_charge(struct mm_struct *mm, mutex_lock(&memcg_tasklist); mem_cgroup_out_of_memory(mem_over_limit, gfp_mask); mutex_unlock(&memcg_tasklist); - mem_over_limit->last_oom_jiffies = jiffies; + record_last_oom(mem_over_limit); } goto nomem; } @@ -906,20 +991,55 @@ nomem: return -ENOMEM; } + +/* + * A helper function to get mem_cgroup from ID. must be called under + * rcu_read_lock(). The caller must check css_is_removed() or some if + * it's concern. (dropping refcnt from swap can be called against removed + * 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 container_of(css, struct mem_cgroup, css); +} + static struct mem_cgroup *try_get_mem_cgroup_from_swapcache(struct page *page) { struct mem_cgroup *mem; + struct page_cgroup *pc; + unsigned short id; swp_entry_t ent; + VM_BUG_ON(!PageLocked(page)); + if (!PageSwapCache(page)) return NULL; - ent.val = page_private(page); - mem = lookup_swap_cgroup(ent); - if (!mem) - return NULL; - if (!css_tryget(&mem->css)) - return NULL; + pc = lookup_page_cgroup(page); + /* + * Used bit of swapcache is solid under page lock. + */ + if (PageCgroupUsed(pc)) { + mem = pc->mem_cgroup; + if (mem && !css_tryget(&mem->css)) + mem = NULL; + } else { + ent.val = page_private(page); + id = lookup_swap_cgroup(ent); + rcu_read_lock(); + mem = mem_cgroup_lookup(id); + if (mem && !css_tryget(&mem->css)) + mem = NULL; + rcu_read_unlock(); + } return mem; } @@ -1118,6 +1238,10 @@ int mem_cgroup_newpage_charge(struct page *page, MEM_CGROUP_CHARGE_TYPE_MAPPED, NULL); } +static void +__mem_cgroup_commit_charge_swapin(struct page *page, struct mem_cgroup *ptr, + enum charge_type ctype); + int mem_cgroup_cache_charge(struct page *page, struct mm_struct *mm, gfp_t gfp_mask) { @@ -1154,16 +1278,6 @@ int mem_cgroup_cache_charge(struct page *page, struct mm_struct *mm, unlock_page_cgroup(pc); } - if (do_swap_account && PageSwapCache(page)) { - mem = try_get_mem_cgroup_from_swapcache(page); - if (mem) - mm = NULL; - else - mem = NULL; - /* SwapCache may be still linked to LRU now. */ - mem_cgroup_lru_del_before_commit_swapcache(page); - } - if (unlikely(!mm && !mem)) mm = &init_mm; @@ -1171,22 +1285,16 @@ int mem_cgroup_cache_charge(struct page *page, struct mm_struct *mm, return mem_cgroup_charge_common(page, mm, gfp_mask, MEM_CGROUP_CHARGE_TYPE_CACHE, NULL); - ret = mem_cgroup_charge_common(page, mm, gfp_mask, - MEM_CGROUP_CHARGE_TYPE_SHMEM, mem); - if (mem) - css_put(&mem->css); - if (PageSwapCache(page)) - mem_cgroup_lru_add_after_commit_swapcache(page); + /* shmem */ + if (PageSwapCache(page)) { + ret = mem_cgroup_try_charge_swapin(mm, page, gfp_mask, &mem); + if (!ret) + __mem_cgroup_commit_charge_swapin(page, mem, + MEM_CGROUP_CHARGE_TYPE_SHMEM); + } else + ret = mem_cgroup_charge_common(page, mm, gfp_mask, + MEM_CGROUP_CHARGE_TYPE_SHMEM, mem); - if (do_swap_account && !ret && PageSwapCache(page)) { - swp_entry_t ent = {.val = page_private(page)}; - /* avoid double counting */ - mem = swap_cgroup_record(ent, NULL); - if (mem) { - res_counter_uncharge(&mem->memsw, PAGE_SIZE); - mem_cgroup_put(mem); - } - } return ret; } @@ -1229,7 +1337,9 @@ charge_cur_mm: return __mem_cgroup_try_charge(mm, mask, ptr, true); } -void mem_cgroup_commit_charge_swapin(struct page *page, struct mem_cgroup *ptr) +static void +__mem_cgroup_commit_charge_swapin(struct page *page, struct mem_cgroup *ptr, + enum charge_type ctype) { struct page_cgroup *pc; @@ -1239,7 +1349,7 @@ void mem_cgroup_commit_charge_swapin(struct page *page, struct mem_cgroup *ptr) return; pc = lookup_page_cgroup(page); mem_cgroup_lru_del_before_commit_swapcache(page); - __mem_cgroup_commit_charge(ptr, pc, MEM_CGROUP_CHARGE_TYPE_MAPPED); + __mem_cgroup_commit_charge(ptr, pc, ctype); mem_cgroup_lru_add_after_commit_swapcache(page); /* * Now swap is on-memory. This means this page may be @@ -1250,18 +1360,32 @@ void mem_cgroup_commit_charge_swapin(struct page *page, struct mem_cgroup *ptr) */ if (do_swap_account && PageSwapCache(page)) { swp_entry_t ent = {.val = page_private(page)}; + unsigned short id; struct mem_cgroup *memcg; - memcg = swap_cgroup_record(ent, NULL); + + id = swap_cgroup_record(ent, 0); + rcu_read_lock(); + memcg = mem_cgroup_lookup(id); if (memcg) { + /* + * This recorded memcg can be obsolete one. So, avoid + * calling css_tryget + */ res_counter_uncharge(&memcg->memsw, PAGE_SIZE); mem_cgroup_put(memcg); } - + rcu_read_unlock(); } /* add this page(page_cgroup) to the LRU we want. */ } +void mem_cgroup_commit_charge_swapin(struct page *page, struct mem_cgroup *ptr) +{ + __mem_cgroup_commit_charge_swapin(page, ptr, + MEM_CGROUP_CHARGE_TYPE_MAPPED); +} + void mem_cgroup_cancel_charge_swapin(struct mem_cgroup *mem) { if (mem_cgroup_disabled()) @@ -1324,8 +1448,8 @@ __mem_cgroup_uncharge_common(struct page *page, enum charge_type ctype) res_counter_uncharge(&mem->res, PAGE_SIZE); if (do_swap_account && (ctype != MEM_CGROUP_CHARGE_TYPE_SWAPOUT)) res_counter_uncharge(&mem->memsw, PAGE_SIZE); - mem_cgroup_charge_statistics(mem, pc, false); + ClearPageCgroupUsed(pc); /* * pc->mem_cgroup is not cleared here. It will be accessed when it's @@ -1377,7 +1501,7 @@ void mem_cgroup_uncharge_swapcache(struct page *page, swp_entry_t ent) MEM_CGROUP_CHARGE_TYPE_SWAPOUT); /* record memcg information */ if (do_swap_account && memcg) { - swap_cgroup_record(ent, memcg); + swap_cgroup_record(ent, css_id(&memcg->css)); mem_cgroup_get(memcg); } if (memcg) @@ -1392,15 +1516,23 @@ void mem_cgroup_uncharge_swapcache(struct page *page, swp_entry_t ent) void mem_cgroup_uncharge_swap(swp_entry_t ent) { struct mem_cgroup *memcg; + unsigned short id; if (!do_swap_account) return; - memcg = swap_cgroup_record(ent, NULL); + id = swap_cgroup_record(ent, 0); + rcu_read_lock(); + memcg = mem_cgroup_lookup(id); if (memcg) { + /* + * We uncharge this because swap is freed. + * This memcg can be obsolete one. We avoid calling css_tryget + */ res_counter_uncharge(&memcg->memsw, PAGE_SIZE); mem_cgroup_put(memcg); } + rcu_read_unlock(); } #endif @@ -1508,7 +1640,8 @@ int mem_cgroup_shrink_usage(struct page *page, return 0; do { - progress = mem_cgroup_hierarchical_reclaim(mem, gfp_mask, true); + progress = mem_cgroup_hierarchical_reclaim(mem, + gfp_mask, true, false); progress += mem_cgroup_check_under_limit(mem); } while (!progress && --retry); @@ -1523,11 +1656,21 @@ static DEFINE_MUTEX(set_limit_mutex); static int mem_cgroup_resize_limit(struct mem_cgroup *memcg, unsigned long long val) { - - int retry_count = MEM_CGROUP_RECLAIM_RETRIES; + int retry_count; int progress; u64 memswlimit; int ret = 0; + int children = mem_cgroup_count_children(memcg); + u64 curusage, oldusage; + + /* + * For keeping hierarchical_reclaim simple, how long we should retry + * is depends on callers. We set our retry-count to be function + * of # of children which we should visit in this loop. + */ + retry_count = MEM_CGROUP_RECLAIM_RETRIES * children; + + oldusage = res_counter_read_u64(&memcg->res, RES_USAGE); while (retry_count) { if (signal_pending(current)) { @@ -1553,8 +1696,13 @@ static int mem_cgroup_resize_limit(struct mem_cgroup *memcg, break; progress = mem_cgroup_hierarchical_reclaim(memcg, GFP_KERNEL, - false); - if (!progress) retry_count--; + false, true); + curusage = res_counter_read_u64(&memcg->res, RES_USAGE); + /* Usage is reduced ? */ + if (curusage >= oldusage) + retry_count--; + else + oldusage = curusage; } return ret; @@ -1563,13 +1711,16 @@ static int mem_cgroup_resize_limit(struct mem_cgroup *memcg, int mem_cgroup_resize_memsw_limit(struct mem_cgroup *memcg, unsigned long long val) { - int retry_count = MEM_CGROUP_RECLAIM_RETRIES; + int retry_count; u64 memlimit, oldusage, curusage; - int ret; + int children = mem_cgroup_count_children(memcg); + int ret = -EBUSY; if (!do_swap_account) return -EINVAL; - + /* see mem_cgroup_resize_res_limit */ + retry_count = children * MEM_CGROUP_RECLAIM_RETRIES; + oldusage = res_counter_read_u64(&memcg->memsw, RES_USAGE); while (retry_count) { if (signal_pending(current)) { ret = -EINTR; @@ -1593,11 +1744,13 @@ int mem_cgroup_resize_memsw_limit(struct mem_cgroup *memcg, if (!ret) break; - oldusage = res_counter_read_u64(&memcg->memsw, RES_USAGE); - mem_cgroup_hierarchical_reclaim(memcg, GFP_KERNEL, true); + mem_cgroup_hierarchical_reclaim(memcg, GFP_KERNEL, true, true); curusage = res_counter_read_u64(&memcg->memsw, RES_USAGE); + /* Usage is reduced ? */ if (curusage >= oldusage) retry_count--; + else + oldusage = curusage; } return ret; } @@ -1893,54 +2046,90 @@ static int mem_cgroup_reset(struct cgroup *cont, unsigned int event) return 0; } -static const struct mem_cgroup_stat_desc { - const char *msg; - u64 unit; -} mem_cgroup_stat_desc[] = { - [MEM_CGROUP_STAT_CACHE] = { "cache", PAGE_SIZE, }, - [MEM_CGROUP_STAT_RSS] = { "rss", PAGE_SIZE, }, - [MEM_CGROUP_STAT_PGPGIN_COUNT] = {"pgpgin", 1, }, - [MEM_CGROUP_STAT_PGPGOUT_COUNT] = {"pgpgout", 1, }, + +/* For read statistics */ +enum { + MCS_CACHE, + MCS_RSS, + MCS_PGPGIN, + MCS_PGPGOUT, + MCS_INACTIVE_ANON, + MCS_ACTIVE_ANON, + MCS_INACTIVE_FILE, + MCS_ACTIVE_FILE, + MCS_UNEVICTABLE, + NR_MCS_STAT, +}; + +struct mcs_total_stat { + s64 stat[NR_MCS_STAT]; +}; + +struct { + char *local_name; + char *total_name; +} memcg_stat_strings[NR_MCS_STAT] = { + {"cache", "total_cache"}, + {"rss", "total_rss"}, + {"pgpgin", "total_pgpgin"}, + {"pgpgout", "total_pgpgout"}, + {"inactive_anon", "total_inactive_anon"}, + {"active_anon", "total_active_anon"}, + {"inactive_file", "total_inactive_file"}, + {"active_file", "total_active_file"}, + {"unevictable", "total_unevictable"} }; + +static int mem_cgroup_get_local_stat(struct mem_cgroup *mem, void *data) +{ + struct mcs_total_stat *s = data; + s64 val; + + /* per cpu stat */ + val = mem_cgroup_read_stat(&mem->stat, MEM_CGROUP_STAT_CACHE); + s->stat[MCS_CACHE] += val * PAGE_SIZE; + val = mem_cgroup_read_stat(&mem->stat, MEM_CGROUP_STAT_RSS); + s->stat[MCS_RSS] += val * PAGE_SIZE; + val = mem_cgroup_read_stat(&mem->stat, MEM_CGROUP_STAT_PGPGIN_COUNT); + s->stat[MCS_PGPGIN] += val; + val = mem_cgroup_read_stat(&mem->stat, MEM_CGROUP_STAT_PGPGOUT_COUNT); + s->stat[MCS_PGPGOUT] += val; + + /* per zone stat */ + val = mem_cgroup_get_local_zonestat(mem, LRU_INACTIVE_ANON); + s->stat[MCS_INACTIVE_ANON] += val * PAGE_SIZE; + val = mem_cgroup_get_local_zonestat(mem, LRU_ACTIVE_ANON); + s->stat[MCS_ACTIVE_ANON] += val * PAGE_SIZE; + val = mem_cgroup_get_local_zonestat(mem, LRU_INACTIVE_FILE); + s->stat[MCS_INACTIVE_FILE] += val * PAGE_SIZE; + val = mem_cgroup_get_local_zonestat(mem, LRU_ACTIVE_FILE); + s->stat[MCS_ACTIVE_FILE] += val * PAGE_SIZE; + val = mem_cgroup_get_local_zonestat(mem, LRU_UNEVICTABLE); + s->stat[MCS_UNEVICTABLE] += val * PAGE_SIZE; + return 0; +} + +static void +mem_cgroup_get_total_stat(struct mem_cgroup *mem, struct mcs_total_stat *s) +{ + mem_cgroup_walk_tree(mem, s, mem_cgroup_get_local_stat); +} + static int mem_control_stat_show(struct cgroup *cont, struct cftype *cft, struct cgroup_map_cb *cb) { struct mem_cgroup *mem_cont = mem_cgroup_from_cont(cont); - struct mem_cgroup_stat *stat = &mem_cont->stat; + struct mcs_total_stat mystat; int i; - for (i = 0; i < ARRAY_SIZE(stat->cpustat[0].count); i++) { - s64 val; + memset(&mystat, 0, sizeof(mystat)); + mem_cgroup_get_local_stat(mem_cont, &mystat); - val = mem_cgroup_read_stat(stat, i); - val *= mem_cgroup_stat_desc[i].unit; - cb->fill(cb, mem_cgroup_stat_desc[i].msg, val); - } - /* showing # of active pages */ - { - unsigned long active_anon, inactive_anon; - unsigned long active_file, inactive_file; - unsigned long unevictable; - - inactive_anon = mem_cgroup_get_all_zonestat(mem_cont, - LRU_INACTIVE_ANON); - active_anon = mem_cgroup_get_all_zonestat(mem_cont, - LRU_ACTIVE_ANON); - inactive_file = mem_cgroup_get_all_zonestat(mem_cont, - LRU_INACTIVE_FILE); - active_file = mem_cgroup_get_all_zonestat(mem_cont, - LRU_ACTIVE_FILE); - unevictable = mem_cgroup_get_all_zonestat(mem_cont, - LRU_UNEVICTABLE); - - cb->fill(cb, "active_anon", (active_anon) * PAGE_SIZE); - cb->fill(cb, "inactive_anon", (inactive_anon) * PAGE_SIZE); - cb->fill(cb, "active_file", (active_file) * PAGE_SIZE); - cb->fill(cb, "inactive_file", (inactive_file) * PAGE_SIZE); - cb->fill(cb, "unevictable", unevictable * PAGE_SIZE); + for (i = 0; i < NR_MCS_STAT; i++) + cb->fill(cb, memcg_stat_strings[i].local_name, mystat.stat[i]); - } + /* Hierarchical information */ { unsigned long long limit, memsw_limit; memcg_get_hierarchical_limit(mem_cont, &limit, &memsw_limit); @@ -1949,6 +2138,12 @@ static int mem_control_stat_show(struct cgroup *cont, struct cftype *cft, cb->fill(cb, "hierarchical_memsw_limit", memsw_limit); } + memset(&mystat, 0, sizeof(mystat)); + mem_cgroup_get_total_stat(mem_cont, &mystat); + for (i = 0; i < NR_MCS_STAT; i++) + cb->fill(cb, memcg_stat_strings[i].total_name, mystat.stat[i]); + + #ifdef CONFIG_DEBUG_VM cb->fill(cb, "inactive_ratio", calc_inactive_ratio(mem_cont, NULL)); @@ -2178,6 +2373,8 @@ static void __mem_cgroup_free(struct mem_cgroup *mem) { int node; + free_css_id(&mem_cgroup_subsys, &mem->css); + for_each_node_state(node, N_POSSIBLE) free_mem_cgroup_per_zone_info(mem, node); @@ -2228,11 +2425,12 @@ static struct cgroup_subsys_state * __ref mem_cgroup_create(struct cgroup_subsys *ss, struct cgroup *cont) { struct mem_cgroup *mem, *parent; + long error = -ENOMEM; int node; mem = mem_cgroup_alloc(); if (!mem) - return ERR_PTR(-ENOMEM); + return ERR_PTR(error); for_each_node_state(node, N_POSSIBLE) if (alloc_mem_cgroup_per_zone_info(mem, node)) @@ -2260,7 +2458,7 @@ mem_cgroup_create(struct cgroup_subsys *ss, struct cgroup *cont) res_counter_init(&mem->res, NULL); res_counter_init(&mem->memsw, NULL); } - mem->last_scanned_child = NULL; + mem->last_scanned_child = 0; spin_lock_init(&mem->reclaim_param_lock); if (parent) @@ -2269,26 +2467,22 @@ mem_cgroup_create(struct cgroup_subsys *ss, struct cgroup *cont) return &mem->css; free_out: __mem_cgroup_free(mem); - return ERR_PTR(-ENOMEM); + return ERR_PTR(error); } -static void mem_cgroup_pre_destroy(struct cgroup_subsys *ss, +static int mem_cgroup_pre_destroy(struct cgroup_subsys *ss, struct cgroup *cont) { struct mem_cgroup *mem = mem_cgroup_from_cont(cont); - mem_cgroup_force_empty(mem, false); + + return mem_cgroup_force_empty(mem, false); } static void mem_cgroup_destroy(struct cgroup_subsys *ss, struct cgroup *cont) { struct mem_cgroup *mem = mem_cgroup_from_cont(cont); - struct mem_cgroup *last_scanned_child = mem->last_scanned_child; - if (last_scanned_child) { - VM_BUG_ON(!mem_cgroup_is_obsolete(last_scanned_child)); - mem_cgroup_put(last_scanned_child); - } mem_cgroup_put(mem); } @@ -2327,6 +2521,7 @@ struct cgroup_subsys mem_cgroup_subsys = { .populate = mem_cgroup_populate, .attach = mem_cgroup_move_task, .early_init = 0, + .use_id = 1, }; #ifdef CONFIG_CGROUP_MEM_RES_CTLR_SWAP diff --git a/mm/memory.c b/mm/memory.c index baa999e..cf6873e 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -1151,6 +1151,11 @@ struct page *follow_page(struct vm_area_struct *vma, unsigned long address, if ((flags & FOLL_WRITE) && !pte_dirty(pte) && !PageDirty(page)) set_page_dirty(page); + /* + * pte_mkyoung() would be more correct here, but atomic care + * is needed to avoid losing the dirty bit: it is easier to use + * mark_page_accessed(). + */ mark_page_accessed(page); } unlock: @@ -1665,9 +1670,10 @@ int remap_pfn_range(struct vm_area_struct *vma, unsigned long addr, * behaviour that some programs depend on. We mark the "original" * un-COW'ed pages by matching them up with "vma->vm_pgoff". */ - if (addr == vma->vm_start && end == vma->vm_end) + if (addr == vma->vm_start && end == vma->vm_end) { vma->vm_pgoff = pfn; - else if (is_cow_mapping(vma->vm_flags)) + vma->vm_flags |= VM_PFN_AT_MMAP; + } else if (is_cow_mapping(vma->vm_flags)) return -EINVAL; vma->vm_flags |= VM_IO | VM_RESERVED | VM_PFNMAP; @@ -1679,6 +1685,7 @@ int remap_pfn_range(struct vm_area_struct *vma, unsigned long addr, * needed from higher level routine calling unmap_vmas */ vma->vm_flags &= ~(VM_IO | VM_RESERVED | VM_PFNMAP); + vma->vm_flags &= ~VM_PFN_AT_MMAP; return -EINVAL; } @@ -1938,6 +1945,15 @@ static int do_wp_page(struct mm_struct *mm, struct vm_area_struct *vma, * get_user_pages(.write=1, .force=1). */ if (vma->vm_ops && vma->vm_ops->page_mkwrite) { + struct vm_fault vmf; + int tmp; + + vmf.virtual_address = (void __user *)(address & + PAGE_MASK); + vmf.pgoff = old_page->index; + vmf.flags = FAULT_FLAG_WRITE|FAULT_FLAG_MKWRITE; + vmf.page = old_page; + /* * Notify the address space that the page is about to * become writable so that it can prohibit this or wait @@ -1949,8 +1965,12 @@ static int do_wp_page(struct mm_struct *mm, struct vm_area_struct *vma, page_cache_get(old_page); pte_unmap_unlock(page_table, ptl); - if (vma->vm_ops->page_mkwrite(vma, old_page) < 0) + tmp = vma->vm_ops->page_mkwrite(vma, &vmf); + if (unlikely(tmp & + (VM_FAULT_ERROR | VM_FAULT_NOPAGE))) { + ret = tmp; goto unwritable_page; + } /* * Since we dropped the lock we need to revalidate @@ -2099,7 +2119,7 @@ oom: unwritable_page: page_cache_release(old_page); - return VM_FAULT_SIGBUS; + return ret; } /* @@ -2433,8 +2453,6 @@ static int do_swap_page(struct mm_struct *mm, struct vm_area_struct *vma, count_vm_event(PGMAJFAULT); } - mark_page_accessed(page); - lock_page(page); delayacct_clear_flag(DELAYACCT_PF_SWAPIN); @@ -2643,9 +2661,14 @@ static int __do_fault(struct mm_struct *mm, struct vm_area_struct *vma, * to become writable */ if (vma->vm_ops->page_mkwrite) { + int tmp; + unlock_page(page); - if (vma->vm_ops->page_mkwrite(vma, page) < 0) { - ret = VM_FAULT_SIGBUS; + vmf.flags |= FAULT_FLAG_MKWRITE; + tmp = vma->vm_ops->page_mkwrite(vma, &vmf); + if (unlikely(tmp & + (VM_FAULT_ERROR | VM_FAULT_NOPAGE))) { + ret = tmp; anon = 1; /* no anon but release vmf.page */ goto out_unlocked; } diff --git a/mm/migrate.c b/mm/migrate.c index a9eff3f..068655d8 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 @@ -660,7 +660,7 @@ void *alloc_locked_buffer(size_t size) return buffer; } -void free_locked_buffer(void *buffer, size_t size) +void release_locked_buffer(void *buffer, size_t size) { unsigned long pgsz = PAGE_ALIGN(size) >> PAGE_SHIFT; @@ -670,6 +670,11 @@ void free_locked_buffer(void *buffer, size_t size) current->mm->locked_vm -= pgsz; up_write(¤t->mm->mmap_sem); +} + +void free_locked_buffer(void *buffer, size_t size) +{ + release_locked_buffer(buffer, size); kfree(buffer); } @@ -20,6 +20,7 @@ #include <linux/fs.h> #include <linux/personality.h> #include <linux/security.h> +#include <linux/ima.h> #include <linux/hugetlb.h> #include <linux/profile.h> #include <linux/module.h> @@ -1049,6 +1050,9 @@ unsigned long do_mmap_pgoff(struct file *file, unsigned long addr, error = security_file_mmap(file, reqprot, prot, flags, addr, 0); if (error) return error; + error = ima_file_mmap(file, prot); + if (error) + return error; return mmap_region(file, addr, len, flags, vm_flags, pgoff); } @@ -2477,7 +2481,4 @@ void mm_drop_all_locks(struct mm_struct *mm) */ void __init mmap_init(void) { - vm_area_cachep = kmem_cache_create("vm_area_struct", - sizeof(struct vm_area_struct), 0, - SLAB_PANIC, NULL); } @@ -69,7 +69,7 @@ int sysctl_max_map_count = DEFAULT_MAX_MAP_COUNT; int sysctl_nr_trim_pages = 1; /* page trimming behaviour */ int heap_stack_gap = 0; -atomic_t mmap_pages_allocated; +atomic_long_t mmap_pages_allocated; EXPORT_SYMBOL(mem_map); EXPORT_SYMBOL(num_physpages); @@ -463,12 +463,7 @@ SYSCALL_DEFINE1(brk, unsigned long, brk) */ void __init mmap_init(void) { - vm_region_jar = kmem_cache_create("vm_region_jar", - sizeof(struct vm_region), 0, - SLAB_PANIC, NULL); - vm_area_cachep = kmem_cache_create("vm_area_struct", - sizeof(struct vm_area_struct), 0, - SLAB_PANIC, NULL); + vm_region_jar = KMEM_CACHE(vm_region, SLAB_PANIC); } /* @@ -486,27 +481,24 @@ static noinline void validate_nommu_regions(void) return; last = rb_entry(lastp, struct vm_region, vm_rb); - if (unlikely(last->vm_end <= last->vm_start)) - BUG(); - if (unlikely(last->vm_top < last->vm_end)) - BUG(); + BUG_ON(unlikely(last->vm_end <= last->vm_start)); + BUG_ON(unlikely(last->vm_top < last->vm_end)); while ((p = rb_next(lastp))) { region = rb_entry(p, struct vm_region, vm_rb); last = rb_entry(lastp, struct vm_region, vm_rb); - if (unlikely(region->vm_end <= region->vm_start)) - BUG(); - if (unlikely(region->vm_top < region->vm_end)) - BUG(); - if (unlikely(region->vm_start < last->vm_top)) - BUG(); + BUG_ON(unlikely(region->vm_end <= region->vm_start)); + BUG_ON(unlikely(region->vm_top < region->vm_end)); + BUG_ON(unlikely(region->vm_start < last->vm_top)); lastp = p; } } #else -#define validate_nommu_regions() do {} while(0) +static void validate_nommu_regions(void) +{ +} #endif /* @@ -563,16 +555,17 @@ static void free_page_series(unsigned long from, unsigned long to) struct page *page = virt_to_page(from); kdebug("- free %lx", from); - atomic_dec(&mmap_pages_allocated); + atomic_long_dec(&mmap_pages_allocated); if (page_count(page) != 1) - kdebug("free page %p [%d]", page, page_count(page)); + kdebug("free page %p: refcount not one: %d", + page, page_count(page)); put_page(page); } } /* * release a reference to a region - * - the caller must hold the region semaphore, which this releases + * - the caller must hold the region semaphore for writing, which this releases * - the region may not have been added to the tree yet, in which case vm_top * will equal vm_start */ @@ -1096,7 +1089,7 @@ static int do_mmap_private(struct vm_area_struct *vma, goto enomem; total = 1 << order; - atomic_add(total, &mmap_pages_allocated); + atomic_long_add(total, &mmap_pages_allocated); point = rlen >> PAGE_SHIFT; @@ -1107,7 +1100,7 @@ static int do_mmap_private(struct vm_area_struct *vma, order = ilog2(total - point); n = 1 << order; kdebug("shave %lu/%lu @%lu", n, total - point, total); - atomic_sub(n, &mmap_pages_allocated); + atomic_long_sub(n, &mmap_pages_allocated); total -= n; set_page_refcounted(pages + total); __free_pages(pages + total, order); @@ -1536,10 +1529,15 @@ int do_munmap(struct mm_struct *mm, unsigned long start, size_t len) /* find the first potentially overlapping VMA */ vma = find_vma(mm, start); if (!vma) { - printk(KERN_WARNING - "munmap of memory not mmapped by process %d (%s):" - " 0x%lx-0x%lx\n", - current->pid, current->comm, start, start + len - 1); + static int limit = 0; + if (limit < 5) { + printk(KERN_WARNING + "munmap of memory not mmapped by process %d" + " (%s): 0x%lx-0x%lx\n", + current->pid, current->comm, + start, start + len - 1); + limit++; + } return -EINVAL; } diff --git a/mm/oom_kill.c b/mm/oom_kill.c index 40ba050..2f3166e 100644 --- a/mm/oom_kill.c +++ b/mm/oom_kill.c @@ -55,7 +55,7 @@ static DEFINE_SPINLOCK(zone_scan_lock); unsigned long badness(struct task_struct *p, unsigned long uptime) { - unsigned long points, cpu_time, run_time, s; + unsigned long points, cpu_time, run_time; struct mm_struct *mm; struct task_struct *child; @@ -110,12 +110,10 @@ unsigned long badness(struct task_struct *p, unsigned long uptime) else run_time = 0; - s = int_sqrt(cpu_time); - if (s) - points /= s; - s = int_sqrt(int_sqrt(run_time)); - if (s) - points /= s; + if (cpu_time) + points /= int_sqrt(cpu_time); + if (run_time) + points /= int_sqrt(int_sqrt(run_time)); /* * Niced processes are most likely less important, so double @@ -396,6 +394,7 @@ static int oom_kill_process(struct task_struct *p, gfp_t gfp_mask, int order, cpuset_print_task_mems_allowed(current); task_unlock(current); dump_stack(); + mem_cgroup_print_oom_info(mem, current); show_mem(); if (sysctl_oom_dump_tasks) dump_tasks(mem); diff --git a/mm/page-writeback.c b/mm/page-writeback.c index 6106a5c..30351f0 100644 --- a/mm/page-writeback.c +++ b/mm/page-writeback.c @@ -66,7 +66,7 @@ static inline long sync_writeback_pages(void) /* * Start background writeback (via pdflush) at this percentage */ -int dirty_background_ratio = 5; +int dirty_background_ratio = 10; /* * dirty_background_bytes starts at 0 (disabled) so that it is a function of @@ -83,7 +83,7 @@ int vm_highmem_is_dirtyable; /* * The generator of dirty data starts writeback at this percentage */ -int vm_dirty_ratio = 10; +int vm_dirty_ratio = 20; /* * vm_dirty_bytes starts at 0 (disabled) so that it is a function of @@ -92,14 +92,14 @@ int vm_dirty_ratio = 10; unsigned long vm_dirty_bytes; /* - * The interval between `kupdate'-style writebacks, in jiffies + * The interval between `kupdate'-style writebacks */ -int dirty_writeback_interval = 5 * HZ; +unsigned int dirty_writeback_interval = 5 * 100; /* sentiseconds */ /* - * The longest number of jiffies for which data is allowed to remain dirty + * The longest time for which data is allowed to remain dirty */ -int dirty_expire_interval = 30 * HZ; +unsigned int dirty_expire_interval = 30 * 100; /* sentiseconds */ /* * Flag that makes the machine dump writes/reads and block dirtyings. @@ -240,7 +240,7 @@ void bdi_writeout_inc(struct backing_dev_info *bdi) } EXPORT_SYMBOL_GPL(bdi_writeout_inc); -static inline void task_dirty_inc(struct task_struct *tsk) +void task_dirty_inc(struct task_struct *tsk) { prop_inc_single(&vm_dirties, &tsk->dirties); } @@ -770,9 +770,9 @@ static void wb_kupdate(unsigned long arg) sync_supers(); - oldest_jif = jiffies - dirty_expire_interval; + oldest_jif = jiffies - msecs_to_jiffies(dirty_expire_interval); start_jif = jiffies; - next_jif = start_jif + dirty_writeback_interval; + next_jif = start_jif + msecs_to_jiffies(dirty_writeback_interval * 10); nr_to_write = global_page_state(NR_FILE_DIRTY) + global_page_state(NR_UNSTABLE_NFS) + (inodes_stat.nr_inodes - inodes_stat.nr_unused); @@ -801,9 +801,10 @@ static void wb_kupdate(unsigned long arg) int dirty_writeback_centisecs_handler(ctl_table *table, int write, struct file *file, void __user *buffer, size_t *length, loff_t *ppos) { - proc_dointvec_userhz_jiffies(table, write, file, buffer, length, ppos); + proc_dointvec(table, write, file, buffer, length, ppos); if (dirty_writeback_interval) - mod_timer(&wb_timer, jiffies + dirty_writeback_interval); + mod_timer(&wb_timer, jiffies + + msecs_to_jiffies(dirty_writeback_interval * 10)); else del_timer(&wb_timer); return 0; @@ -905,7 +906,8 @@ void __init page_writeback_init(void) { int shift; - mod_timer(&wb_timer, jiffies + dirty_writeback_interval); + mod_timer(&wb_timer, + jiffies + msecs_to_jiffies(dirty_writeback_interval * 10)); writeback_set_ratelimit(); register_cpu_notifier(&ratelimit_nb); @@ -1079,7 +1081,7 @@ continue_unlock: pagevec_release(&pvec); cond_resched(); } - if (!cycled) { + if (!cycled && !done) { /* * range_cyclic: * We hit the last page and there is more work to be done: wrap @@ -1198,6 +1200,20 @@ int __set_page_dirty_no_writeback(struct page *page) } /* + * Helper function for set_page_dirty family. + * NOTE: This relies on being atomic wrt interrupts. + */ +void account_page_dirtied(struct page *page, struct address_space *mapping) +{ + if (mapping_cap_account_dirty(mapping)) { + __inc_zone_page_state(page, NR_FILE_DIRTY); + __inc_bdi_stat(mapping->backing_dev_info, BDI_RECLAIMABLE); + task_dirty_inc(current); + task_io_account_write(PAGE_CACHE_SIZE); + } +} + +/* * For address_spaces which do not use buffers. Just tag the page as dirty in * its radix tree. * @@ -1226,12 +1242,7 @@ int __set_page_dirty_nobuffers(struct page *page) if (mapping2) { /* Race with truncate? */ BUG_ON(mapping2 != mapping); WARN_ON_ONCE(!PagePrivate(page) && !PageUptodate(page)); - if (mapping_cap_account_dirty(mapping)) { - __inc_zone_page_state(page, NR_FILE_DIRTY); - __inc_bdi_stat(mapping->backing_dev_info, - BDI_RECLAIMABLE); - task_io_account_write(PAGE_CACHE_SIZE); - } + account_page_dirtied(page, mapping); radix_tree_tag_set(&mapping->page_tree, page_index(page), PAGECACHE_TAG_DIRTY); } @@ -1262,7 +1273,7 @@ EXPORT_SYMBOL(redirty_page_for_writepage); * If the mapping doesn't provide a set_page_dirty a_op, then * just fall through and assume that it wants buffer_heads. */ -static int __set_page_dirty(struct page *page) +int set_page_dirty(struct page *page) { struct address_space *mapping = page_mapping(page); @@ -1280,14 +1291,6 @@ static int __set_page_dirty(struct page *page) } return 0; } - -int set_page_dirty(struct page *page) -{ - int ret = __set_page_dirty(page); - if (ret) - task_dirty_inc(current); - return ret; -} EXPORT_SYMBOL(set_page_dirty); /* diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 5675b30..e2f2699 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++; } @@ -922,13 +922,10 @@ static void drain_pages(unsigned int cpu) unsigned long flags; struct zone *zone; - for_each_zone(zone) { + for_each_populated_zone(zone) { struct per_cpu_pageset *pset; struct per_cpu_pages *pcp; - if (!populated_zone(zone)) - continue; - pset = zone_pcp(zone, cpu); pcp = &pset->pcp; @@ -1479,6 +1476,8 @@ __alloc_pages_internal(gfp_t gfp_mask, unsigned int order, unsigned long did_some_progress; unsigned long pages_reclaimed = 0; + lockdep_trace_alloc(gfp_mask); + might_sleep_if(wait); if (should_fail_alloc_page(gfp_mask, order)) @@ -1578,12 +1577,16 @@ nofail_alloc: */ cpuset_update_task_memory_state(); p->flags |= PF_MEMALLOC; + + lockdep_set_current_reclaim_state(gfp_mask); reclaim_state.reclaimed_slab = 0; p->reclaim_state = &reclaim_state; - did_some_progress = try_to_free_pages(zonelist, order, gfp_mask); + did_some_progress = try_to_free_pages(zonelist, order, + gfp_mask, nodemask); p->reclaim_state = NULL; + lockdep_clear_current_reclaim_state(); p->flags &= ~PF_MEMALLOC; cond_resched(); @@ -1874,10 +1877,7 @@ void show_free_areas(void) int cpu; struct zone *zone; - for_each_zone(zone) { - if (!populated_zone(zone)) - continue; - + for_each_populated_zone(zone) { show_node(zone); printk("%s per-cpu:\n", zone->name); @@ -1917,12 +1917,9 @@ void show_free_areas(void) global_page_state(NR_PAGETABLE), global_page_state(NR_BOUNCE)); - for_each_zone(zone) { + for_each_populated_zone(zone) { int i; - if (!populated_zone(zone)) - continue; - show_node(zone); printk("%s" " free:%lukB" @@ -1962,12 +1959,9 @@ void show_free_areas(void) printk("\n"); } - for_each_zone(zone) { + for_each_populated_zone(zone) { unsigned long nr[MAX_ORDER], flags, order, total = 0; - if (!populated_zone(zone)) - continue; - show_node(zone); printk("%s: ", zone->name); @@ -2134,7 +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)) { @@ -2155,8 +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 */ @@ -2779,11 +2773,7 @@ static int __cpuinit process_zones(int cpu) node_set_state(node, N_CPU); /* this node has a cpu */ - for_each_zone(zone) { - - if (!populated_zone(zone)) - continue; - + for_each_populated_zone(zone) { zone_pcp(zone, cpu) = kmalloc_node(sizeof(struct per_cpu_pageset), GFP_KERNEL, node); if (!zone_pcp(zone, cpu)) @@ -2989,7 +2979,7 @@ static int __meminit next_active_region_index_in_nid(int index, int nid) * was used and there are no special requirements, this is a convenient * alternative */ -int __meminit early_pfn_to_nid(unsigned long pfn) +int __meminit __early_pfn_to_nid(unsigned long pfn) { int i; @@ -3000,10 +2990,33 @@ int __meminit early_pfn_to_nid(unsigned long pfn) if (start_pfn <= pfn && pfn < end_pfn) return early_node_map[i].nid; } + /* This is a memory hole */ + return -1; +} +#endif /* CONFIG_HAVE_ARCH_EARLY_PFN_TO_NID */ + +int __meminit early_pfn_to_nid(unsigned long pfn) +{ + int nid; + nid = __early_pfn_to_nid(pfn); + if (nid >= 0) + return nid; + /* just returns 0 */ return 0; } -#endif /* CONFIG_HAVE_ARCH_EARLY_PFN_TO_NID */ + +#ifdef CONFIG_NODES_SPAN_OTHER_NODES +bool __meminit early_pfn_in_nid(unsigned long pfn, int node) +{ + int nid; + + nid = __early_pfn_to_nid(pfn); + if (nid >= 0 && nid != node) + return false; + return true; +} +#endif /* Basic iterator support to walk early_node_map[] */ #define for_each_active_range_index_in_nid(i, nid) \ diff --git a/mm/page_cgroup.c b/mm/page_cgroup.c index ceecfbb..791905c 100644 --- a/mm/page_cgroup.c +++ b/mm/page_cgroup.c @@ -285,12 +285,8 @@ struct swap_cgroup_ctrl { struct swap_cgroup_ctrl swap_cgroup_ctrl[MAX_SWAPFILES]; -/* - * This 8bytes seems big..maybe we can reduce this when we can use "id" for - * cgroup rather than pointer. - */ struct swap_cgroup { - struct mem_cgroup *val; + unsigned short id; }; #define SC_PER_PAGE (PAGE_SIZE/sizeof(struct swap_cgroup)) #define SC_POS_MASK (SC_PER_PAGE - 1) @@ -342,10 +338,10 @@ not_enough_page: * @ent: swap entry to be recorded into * @mem: mem_cgroup to be recorded * - * Returns old value at success, NULL at failure. - * (Of course, old value can be NULL.) + * Returns old value at success, 0 at failure. + * (Of course, old value can be 0.) */ -struct mem_cgroup *swap_cgroup_record(swp_entry_t ent, struct mem_cgroup *mem) +unsigned short swap_cgroup_record(swp_entry_t ent, unsigned short id) { int type = swp_type(ent); unsigned long offset = swp_offset(ent); @@ -354,18 +350,18 @@ struct mem_cgroup *swap_cgroup_record(swp_entry_t ent, struct mem_cgroup *mem) struct swap_cgroup_ctrl *ctrl; struct page *mappage; struct swap_cgroup *sc; - struct mem_cgroup *old; + unsigned short old; if (!do_swap_account) - return NULL; + return 0; ctrl = &swap_cgroup_ctrl[type]; mappage = ctrl->map[idx]; sc = page_address(mappage); sc += pos; - old = sc->val; - sc->val = mem; + old = sc->id; + sc->id = id; return old; } @@ -374,9 +370,9 @@ struct mem_cgroup *swap_cgroup_record(swp_entry_t ent, struct mem_cgroup *mem) * lookup_swap_cgroup - lookup mem_cgroup tied to swap entry * @ent: swap entry to be looked up. * - * Returns pointer to mem_cgroup at success. NULL at failure. + * Returns CSS ID of mem_cgroup at success. 0 at failure. (0 is invalid ID) */ -struct mem_cgroup *lookup_swap_cgroup(swp_entry_t ent) +unsigned short lookup_swap_cgroup(swp_entry_t ent) { int type = swp_type(ent); unsigned long offset = swp_offset(ent); @@ -385,16 +381,16 @@ struct mem_cgroup *lookup_swap_cgroup(swp_entry_t ent) struct swap_cgroup_ctrl *ctrl; struct page *mappage; struct swap_cgroup *sc; - struct mem_cgroup *ret; + unsigned short ret; if (!do_swap_account) - return NULL; + return 0; ctrl = &swap_cgroup_ctrl[type]; mappage = ctrl->map[idx]; sc = page_address(mappage); sc += pos; - ret = sc->val; + ret = sc->id; return ret; } @@ -430,13 +426,6 @@ int swap_cgroup_swapon(int type, unsigned long max_pages) } mutex_unlock(&swap_cgroup_mutex); - printk(KERN_INFO - "swap_cgroup: uses %ld bytes of vmalloc for pointer array space" - " and %ld bytes to hold mem_cgroup pointers on swap\n", - array_size, length * PAGE_SIZE); - printk(KERN_INFO - "swap_cgroup can be disabled by noswapaccount boot option.\n"); - return 0; nomem: printk(KERN_INFO "couldn't allocate enough memory for swap_cgroup.\n"); diff --git a/mm/page_io.c b/mm/page_io.c index dc6ce0a..3023c47 100644 --- a/mm/page_io.c +++ b/mm/page_io.c @@ -111,7 +111,7 @@ int swap_writepage(struct page *page, struct writeback_control *wbc) goto out; } if (wbc->sync_mode == WB_SYNC_ALL) - rw |= (1 << BIO_RW_SYNC); + rw |= (1 << BIO_RW_SYNCIO) | (1 << BIO_RW_UNPLUG); count_vm_event(PSWPOUT); set_page_writeback(page); unlock_page(page); diff --git a/mm/pdflush.c b/mm/pdflush.c index 15de509..118905e 100644 --- a/mm/pdflush.c +++ b/mm/pdflush.c @@ -191,7 +191,7 @@ static int pdflush(void *dummy) /* * Some configs put our parent kthread in a limited cpuset, - * which kthread() overrides, forcing cpus_allowed == CPU_MASK_ALL. + * which kthread() overrides, forcing cpus_allowed == cpu_all_mask. * Our needs are more modest - cut back to our cpusets cpus_allowed. * This is needed as pdflush's are dynamically created and destroyed. * The boottime pdflush's are easily placed w/o these 2 lines. diff --git a/mm/percpu.c b/mm/percpu.c new file mode 100644 index 0000000..1aa5d8f --- /dev/null +++ b/mm/percpu.c @@ -0,0 +1,1326 @@ +/* + * linux/mm/percpu.c - percpu memory allocator + * + * Copyright (C) 2009 SUSE Linux Products GmbH + * Copyright (C) 2009 Tejun Heo <tj@kernel.org> + * + * This file is released under the GPLv2. + * + * This is percpu allocator which can handle both static and dynamic + * areas. Percpu areas are allocated in chunks in vmalloc area. Each + * chunk is consisted of num_possible_cpus() units and the first chunk + * is used for static percpu variables in the kernel image (special + * boot time alloc/init handling necessary as these areas need to be + * brought up before allocation services are running). Unit grows as + * necessary and all units grow or shrink in unison. When a chunk is + * filled up, another chunk is allocated. ie. in vmalloc area + * + * c0 c1 c2 + * ------------------- ------------------- ------------ + * | u0 | u1 | u2 | u3 | | u0 | u1 | u2 | u3 | | u0 | u1 | u + * ------------------- ...... ------------------- .... ------------ + * + * Allocation is done in offset-size areas of single unit space. Ie, + * an area of 512 bytes at 6k in c1 occupies 512 bytes at 6k of c1:u0, + * c1:u1, c1:u2 and c1:u3. Percpu access can be done by configuring + * percpu base registers UNIT_SIZE apart. + * + * There are usually many small percpu allocations many of them as + * small as 4 bytes. The allocator organizes chunks into lists + * according to free size and tries to allocate from the fullest one. + * Each chunk keeps the maximum contiguous area size hint which is + * guaranteed to be eqaul to or larger than the maximum contiguous + * area in the chunk. This helps the allocator not to iterate the + * chunk maps unnecessarily. + * + * Allocation state in each chunk is kept using an array of integers + * on chunk->map. A positive value in the map represents a free + * region and negative allocated. Allocation inside a chunk is done + * by scanning this map sequentially and serving the first matching + * entry. This is mostly copied from the percpu_modalloc() allocator. + * Chunks are also linked into a rb tree to ease address to chunk + * mapping during free. + * + * To use this allocator, arch code should do the followings. + * + * - define CONFIG_HAVE_DYNAMIC_PER_CPU_AREA + * + * - define __addr_to_pcpu_ptr() and __pcpu_ptr_to_addr() to translate + * regular address to percpu pointer and back if they need to be + * different from the default + * + * - use pcpu_setup_first_chunk() during percpu area initialization to + * setup the first chunk containing the kernel static percpu area + */ + +#include <linux/bitmap.h> +#include <linux/bootmem.h> +#include <linux/list.h> +#include <linux/mm.h> +#include <linux/module.h> +#include <linux/mutex.h> +#include <linux/percpu.h> +#include <linux/pfn.h> +#include <linux/rbtree.h> +#include <linux/slab.h> +#include <linux/spinlock.h> +#include <linux/vmalloc.h> +#include <linux/workqueue.h> + +#include <asm/cacheflush.h> +#include <asm/sections.h> +#include <asm/tlbflush.h> + +#define PCPU_SLOT_BASE_SHIFT 5 /* 1-31 shares the same slot */ +#define PCPU_DFL_MAP_ALLOC 16 /* start a map with 16 ents */ + +/* default addr <-> pcpu_ptr mapping, override in asm/percpu.h if necessary */ +#ifndef __addr_to_pcpu_ptr +#define __addr_to_pcpu_ptr(addr) \ + (void *)((unsigned long)(addr) - (unsigned long)pcpu_base_addr \ + + (unsigned long)__per_cpu_start) +#endif +#ifndef __pcpu_ptr_to_addr +#define __pcpu_ptr_to_addr(ptr) \ + (void *)((unsigned long)(ptr) + (unsigned long)pcpu_base_addr \ + - (unsigned long)__per_cpu_start) +#endif + +struct pcpu_chunk { + struct list_head list; /* linked to pcpu_slot lists */ + struct rb_node rb_node; /* key is chunk->vm->addr */ + int free_size; /* free bytes in the chunk */ + int contig_hint; /* max contiguous size hint */ + struct vm_struct *vm; /* mapped vmalloc region */ + int map_used; /* # of map entries used */ + int map_alloc; /* # of map entries allocated */ + int *map; /* allocation map */ + bool immutable; /* no [de]population allowed */ + struct page **page; /* points to page array */ + struct page *page_ar[]; /* #cpus * UNIT_PAGES */ +}; + +static int pcpu_unit_pages __read_mostly; +static int pcpu_unit_size __read_mostly; +static int pcpu_chunk_size __read_mostly; +static int pcpu_nr_slots __read_mostly; +static size_t pcpu_chunk_struct_size __read_mostly; + +/* the address of the first chunk which starts with the kernel static area */ +void *pcpu_base_addr __read_mostly; +EXPORT_SYMBOL_GPL(pcpu_base_addr); + +/* optional reserved chunk, only accessible for reserved allocations */ +static struct pcpu_chunk *pcpu_reserved_chunk; +/* offset limit of the reserved chunk */ +static int pcpu_reserved_chunk_limit; + +/* + * Synchronization rules. + * + * There are two locks - pcpu_alloc_mutex and pcpu_lock. The former + * protects allocation/reclaim paths, chunks and chunk->page arrays. + * The latter is a spinlock and protects the index data structures - + * chunk slots, rbtree, chunks and area maps in chunks. + * + * During allocation, pcpu_alloc_mutex is kept locked all the time and + * pcpu_lock is grabbed and released as necessary. All actual memory + * allocations are done using GFP_KERNEL with pcpu_lock released. + * + * Free path accesses and alters only the index data structures, so it + * can be safely called from atomic context. When memory needs to be + * returned to the system, free path schedules reclaim_work which + * grabs both pcpu_alloc_mutex and pcpu_lock, unlinks chunks to be + * reclaimed, release both locks and frees the chunks. Note that it's + * necessary to grab both locks to remove a chunk from circulation as + * allocation path might be referencing the chunk with only + * pcpu_alloc_mutex locked. + */ +static DEFINE_MUTEX(pcpu_alloc_mutex); /* protects whole alloc and reclaim */ +static DEFINE_SPINLOCK(pcpu_lock); /* protects index data structures */ + +static struct list_head *pcpu_slot __read_mostly; /* chunk list slots */ +static struct rb_root pcpu_addr_root = RB_ROOT; /* chunks by address */ + +/* reclaim work to release fully free chunks, scheduled from free path */ +static void pcpu_reclaim(struct work_struct *work); +static DECLARE_WORK(pcpu_reclaim_work, pcpu_reclaim); + +static int __pcpu_size_to_slot(int size) +{ + int highbit = fls(size); /* size is in bytes */ + return max(highbit - PCPU_SLOT_BASE_SHIFT + 2, 1); +} + +static int pcpu_size_to_slot(int size) +{ + if (size == pcpu_unit_size) + return pcpu_nr_slots - 1; + return __pcpu_size_to_slot(size); +} + +static int pcpu_chunk_slot(const struct pcpu_chunk *chunk) +{ + if (chunk->free_size < sizeof(int) || chunk->contig_hint < sizeof(int)) + return 0; + + return pcpu_size_to_slot(chunk->free_size); +} + +static int pcpu_page_idx(unsigned int cpu, int page_idx) +{ + return cpu * pcpu_unit_pages + page_idx; +} + +static struct page **pcpu_chunk_pagep(struct pcpu_chunk *chunk, + unsigned int cpu, int page_idx) +{ + return &chunk->page[pcpu_page_idx(cpu, page_idx)]; +} + +static unsigned long pcpu_chunk_addr(struct pcpu_chunk *chunk, + unsigned int cpu, int page_idx) +{ + return (unsigned long)chunk->vm->addr + + (pcpu_page_idx(cpu, page_idx) << PAGE_SHIFT); +} + +static bool pcpu_chunk_page_occupied(struct pcpu_chunk *chunk, + int page_idx) +{ + return *pcpu_chunk_pagep(chunk, 0, page_idx) != NULL; +} + +/** + * pcpu_mem_alloc - allocate memory + * @size: bytes to allocate + * + * Allocate @size bytes. If @size is smaller than PAGE_SIZE, + * kzalloc() is used; otherwise, vmalloc() is used. The returned + * memory is always zeroed. + * + * CONTEXT: + * Does GFP_KERNEL allocation. + * + * RETURNS: + * Pointer to the allocated area on success, NULL on failure. + */ +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; + } +} + +/** + * pcpu_mem_free - free memory + * @ptr: memory to free + * @size: size of the area + * + * Free @ptr. @ptr should have been allocated using pcpu_mem_alloc(). + */ +static void pcpu_mem_free(void *ptr, size_t size) +{ + if (size <= PAGE_SIZE) + kfree(ptr); + else + vfree(ptr); +} + +/** + * pcpu_chunk_relocate - put chunk in the appropriate chunk slot + * @chunk: chunk of interest + * @oslot: the previous slot it was on + * + * This function is called after an allocation or free changed @chunk. + * New slot according to the changed state is determined and @chunk is + * moved to the slot. Note that the reserved chunk is never put on + * chunk slots. + * + * CONTEXT: + * pcpu_lock. + */ +static void pcpu_chunk_relocate(struct pcpu_chunk *chunk, int oslot) +{ + int nslot = pcpu_chunk_slot(chunk); + + if (chunk != pcpu_reserved_chunk && oslot != nslot) { + if (oslot < nslot) + list_move(&chunk->list, &pcpu_slot[nslot]); + else + list_move_tail(&chunk->list, &pcpu_slot[nslot]); + } +} + +static struct rb_node **pcpu_chunk_rb_search(void *addr, + struct rb_node **parentp) +{ + struct rb_node **p = &pcpu_addr_root.rb_node; + struct rb_node *parent = NULL; + struct pcpu_chunk *chunk; + + while (*p) { + parent = *p; + chunk = rb_entry(parent, struct pcpu_chunk, rb_node); + + if (addr < chunk->vm->addr) + p = &(*p)->rb_left; + else if (addr > chunk->vm->addr) + p = &(*p)->rb_right; + else + break; + } + + if (parentp) + *parentp = parent; + return p; +} + +/** + * pcpu_chunk_addr_search - search for chunk containing specified address + * @addr: address to search for + * + * Look for chunk which might contain @addr. More specifically, it + * searchs for the chunk with the highest start address which isn't + * beyond @addr. + * + * CONTEXT: + * pcpu_lock. + * + * RETURNS: + * The address of the found chunk. + */ +static struct pcpu_chunk *pcpu_chunk_addr_search(void *addr) +{ + struct rb_node *n, *parent; + struct pcpu_chunk *chunk; + + /* is it in the reserved chunk? */ + if (pcpu_reserved_chunk) { + void *start = pcpu_reserved_chunk->vm->addr; + + if (addr >= start && addr < start + pcpu_reserved_chunk_limit) + return pcpu_reserved_chunk; + } + + /* nah... search the regular ones */ + n = *pcpu_chunk_rb_search(addr, &parent); + if (!n) { + /* no exactly matching chunk, the parent is the closest */ + n = parent; + BUG_ON(!n); + } + chunk = rb_entry(n, struct pcpu_chunk, rb_node); + + if (addr < chunk->vm->addr) { + /* the parent was the next one, look for the previous one */ + n = rb_prev(n); + BUG_ON(!n); + chunk = rb_entry(n, struct pcpu_chunk, rb_node); + } + + return chunk; +} + +/** + * pcpu_chunk_addr_insert - insert chunk into address rb tree + * @new: chunk to insert + * + * Insert @new into address rb tree. + * + * CONTEXT: + * pcpu_lock. + */ +static void pcpu_chunk_addr_insert(struct pcpu_chunk *new) +{ + struct rb_node **p, *parent; + + p = pcpu_chunk_rb_search(new->vm->addr, &parent); + BUG_ON(*p); + rb_link_node(&new->rb_node, parent, p); + rb_insert_color(&new->rb_node, &pcpu_addr_root); +} + +/** + * pcpu_extend_area_map - extend area map for allocation + * @chunk: target chunk + * + * Extend area map of @chunk so that it can accomodate an allocation. + * A single allocation can split an area into three areas, so this + * function makes sure that @chunk->map has at least two extra slots. + * + * CONTEXT: + * pcpu_alloc_mutex, pcpu_lock. pcpu_lock is released and reacquired + * if area map is extended. + * + * RETURNS: + * 0 if noop, 1 if successfully extended, -errno on failure. + */ +static int pcpu_extend_area_map(struct pcpu_chunk *chunk) +{ + int new_alloc; + int *new; + size_t size; + + /* has enough? */ + if (chunk->map_alloc >= chunk->map_used + 2) + return 0; + + spin_unlock_irq(&pcpu_lock); + + new_alloc = PCPU_DFL_MAP_ALLOC; + while (new_alloc < chunk->map_used + 2) + new_alloc *= 2; + + new = pcpu_mem_alloc(new_alloc * sizeof(new[0])); + if (!new) { + spin_lock_irq(&pcpu_lock); + return -ENOMEM; + } + + /* + * Acquire pcpu_lock and switch to new area map. Only free + * could have happened inbetween, so map_used couldn't have + * grown. + */ + spin_lock_irq(&pcpu_lock); + BUG_ON(new_alloc < chunk->map_used + 2); + + size = chunk->map_alloc * sizeof(chunk->map[0]); + memcpy(new, chunk->map, size); + + /* + * map_alloc < PCPU_DFL_MAP_ALLOC indicates that the chunk is + * one of the first chunks and still using static map. + */ + if (chunk->map_alloc >= PCPU_DFL_MAP_ALLOC) + pcpu_mem_free(chunk->map, size); + + chunk->map_alloc = new_alloc; + chunk->map = new; + return 0; +} + +/** + * pcpu_split_block - split a map block + * @chunk: chunk of interest + * @i: index of map block to split + * @head: head size in bytes (can be 0) + * @tail: tail size in bytes (can be 0) + * + * Split the @i'th map block into two or three blocks. If @head is + * non-zero, @head bytes block is inserted before block @i moving it + * to @i+1 and reducing its size by @head bytes. + * + * If @tail is non-zero, the target block, which can be @i or @i+1 + * depending on @head, is reduced by @tail bytes and @tail byte block + * is inserted after the target block. + * + * @chunk->map must have enough free slots to accomodate the split. + * + * CONTEXT: + * pcpu_lock. + */ +static void pcpu_split_block(struct pcpu_chunk *chunk, int i, + int head, int tail) +{ + int nr_extra = !!head + !!tail; + + BUG_ON(chunk->map_alloc < chunk->map_used + nr_extra); + + /* insert new subblocks */ + memmove(&chunk->map[i + nr_extra], &chunk->map[i], + sizeof(chunk->map[0]) * (chunk->map_used - i)); + chunk->map_used += nr_extra; + + if (head) { + chunk->map[i + 1] = chunk->map[i] - head; + chunk->map[i++] = head; + } + if (tail) { + chunk->map[i++] -= tail; + chunk->map[i] = tail; + } +} + +/** + * pcpu_alloc_area - allocate area from a pcpu_chunk + * @chunk: chunk of interest + * @size: wanted size in bytes + * @align: wanted align + * + * Try to allocate @size bytes area aligned at @align from @chunk. + * Note that this function only allocates the offset. It doesn't + * populate or map the area. + * + * @chunk->map must have at least two free slots. + * + * CONTEXT: + * pcpu_lock. + * + * RETURNS: + * Allocated offset in @chunk on success, -1 if no matching area is + * found. + */ +static int pcpu_alloc_area(struct pcpu_chunk *chunk, int size, int align) +{ + int oslot = pcpu_chunk_slot(chunk); + int max_contig = 0; + int i, off; + + for (i = 0, off = 0; i < chunk->map_used; off += abs(chunk->map[i++])) { + bool is_last = i + 1 == chunk->map_used; + int head, tail; + + /* extra for alignment requirement */ + head = ALIGN(off, align) - off; + BUG_ON(i == 0 && head != 0); + + if (chunk->map[i] < 0) + continue; + if (chunk->map[i] < head + size) { + max_contig = max(chunk->map[i], max_contig); + continue; + } + + /* + * If head is small or the previous block is free, + * merge'em. Note that 'small' is defined as smaller + * than sizeof(int), which is very small but isn't too + * uncommon for percpu allocations. + */ + if (head && (head < sizeof(int) || chunk->map[i - 1] > 0)) { + if (chunk->map[i - 1] > 0) + chunk->map[i - 1] += head; + else { + chunk->map[i - 1] -= head; + chunk->free_size -= head; + } + chunk->map[i] -= head; + off += head; + head = 0; + } + + /* if tail is small, just keep it around */ + tail = chunk->map[i] - head - size; + if (tail < sizeof(int)) + tail = 0; + + /* split if warranted */ + if (head || tail) { + pcpu_split_block(chunk, i, head, tail); + if (head) { + i++; + off += head; + max_contig = max(chunk->map[i - 1], max_contig); + } + if (tail) + max_contig = max(chunk->map[i + 1], max_contig); + } + + /* update hint and mark allocated */ + if (is_last) + chunk->contig_hint = max_contig; /* fully scanned */ + else + chunk->contig_hint = max(chunk->contig_hint, + max_contig); + + chunk->free_size -= chunk->map[i]; + chunk->map[i] = -chunk->map[i]; + + pcpu_chunk_relocate(chunk, oslot); + return off; + } + + chunk->contig_hint = max_contig; /* fully scanned */ + pcpu_chunk_relocate(chunk, oslot); + + /* tell the upper layer that this chunk has no matching area */ + return -1; +} + +/** + * pcpu_free_area - free area to a pcpu_chunk + * @chunk: chunk of interest + * @freeme: offset of area to free + * + * Free area starting from @freeme to @chunk. Note that this function + * only modifies the allocation map. It doesn't depopulate or unmap + * the area. + * + * CONTEXT: + * pcpu_lock. + */ +static void pcpu_free_area(struct pcpu_chunk *chunk, int freeme) +{ + int oslot = pcpu_chunk_slot(chunk); + int i, off; + + for (i = 0, off = 0; i < chunk->map_used; off += abs(chunk->map[i++])) + if (off == freeme) + break; + BUG_ON(off != freeme); + BUG_ON(chunk->map[i] > 0); + + chunk->map[i] = -chunk->map[i]; + chunk->free_size += chunk->map[i]; + + /* merge with previous? */ + if (i > 0 && chunk->map[i - 1] >= 0) { + chunk->map[i - 1] += chunk->map[i]; + chunk->map_used--; + memmove(&chunk->map[i], &chunk->map[i + 1], + (chunk->map_used - i) * sizeof(chunk->map[0])); + i--; + } + /* merge with next? */ + if (i + 1 < chunk->map_used && chunk->map[i + 1] >= 0) { + chunk->map[i] += chunk->map[i + 1]; + chunk->map_used--; + memmove(&chunk->map[i + 1], &chunk->map[i + 2], + (chunk->map_used - (i + 1)) * sizeof(chunk->map[0])); + } + + chunk->contig_hint = max(chunk->map[i], chunk->contig_hint); + pcpu_chunk_relocate(chunk, oslot); +} + +/** + * pcpu_unmap - unmap pages out of a pcpu_chunk + * @chunk: chunk of interest + * @page_start: page index of the first page to unmap + * @page_end: page index of the last page to unmap + 1 + * @flush: whether to flush cache and tlb or not + * + * For each cpu, unmap pages [@page_start,@page_end) out of @chunk. + * If @flush is true, vcache is flushed before unmapping and tlb + * after. + */ +static void pcpu_unmap(struct pcpu_chunk *chunk, int page_start, int page_end, + bool flush) +{ + unsigned int last = num_possible_cpus() - 1; + unsigned int cpu; + + /* unmap must not be done on immutable chunk */ + WARN_ON(chunk->immutable); + + /* + * Each flushing trial can be very expensive, issue flush on + * the whole region at once rather than doing it for each cpu. + * This could be an overkill but is more scalable. + */ + if (flush) + flush_cache_vunmap(pcpu_chunk_addr(chunk, 0, page_start), + pcpu_chunk_addr(chunk, last, page_end)); + + for_each_possible_cpu(cpu) + unmap_kernel_range_noflush( + pcpu_chunk_addr(chunk, cpu, page_start), + (page_end - page_start) << PAGE_SHIFT); + + /* ditto as flush_cache_vunmap() */ + if (flush) + flush_tlb_kernel_range(pcpu_chunk_addr(chunk, 0, page_start), + pcpu_chunk_addr(chunk, last, page_end)); +} + +/** + * pcpu_depopulate_chunk - depopulate and unmap an area of a pcpu_chunk + * @chunk: chunk to depopulate + * @off: offset to the area to depopulate + * @size: size of the area to depopulate in bytes + * @flush: whether to flush cache and tlb or not + * + * For each cpu, depopulate and unmap pages [@page_start,@page_end) + * from @chunk. If @flush is true, vcache is flushed before unmapping + * and tlb after. + * + * CONTEXT: + * pcpu_alloc_mutex. + */ +static void pcpu_depopulate_chunk(struct pcpu_chunk *chunk, int off, int size, + bool flush) +{ + int page_start = PFN_DOWN(off); + int page_end = PFN_UP(off + size); + int unmap_start = -1; + int uninitialized_var(unmap_end); + unsigned int cpu; + int i; + + for (i = page_start; i < page_end; i++) { + for_each_possible_cpu(cpu) { + struct page **pagep = pcpu_chunk_pagep(chunk, cpu, i); + + if (!*pagep) + continue; + + __free_page(*pagep); + + /* + * If it's partial depopulation, it might get + * populated or depopulated again. Mark the + * page gone. + */ + *pagep = NULL; + + unmap_start = unmap_start < 0 ? i : unmap_start; + unmap_end = i + 1; + } + } + + if (unmap_start >= 0) + pcpu_unmap(chunk, unmap_start, unmap_end, flush); +} + +/** + * pcpu_map - map pages into a pcpu_chunk + * @chunk: chunk of interest + * @page_start: page index of the first page to map + * @page_end: page index of the last page to map + 1 + * + * For each cpu, map pages [@page_start,@page_end) into @chunk. + * vcache is flushed afterwards. + */ +static int pcpu_map(struct pcpu_chunk *chunk, int page_start, int page_end) +{ + unsigned int last = num_possible_cpus() - 1; + unsigned int cpu; + int err; + + /* map must not be done on immutable chunk */ + WARN_ON(chunk->immutable); + + for_each_possible_cpu(cpu) { + err = map_kernel_range_noflush( + pcpu_chunk_addr(chunk, cpu, page_start), + (page_end - page_start) << PAGE_SHIFT, + PAGE_KERNEL, + pcpu_chunk_pagep(chunk, cpu, page_start)); + if (err < 0) + return err; + } + + /* flush at once, please read comments in pcpu_unmap() */ + flush_cache_vmap(pcpu_chunk_addr(chunk, 0, page_start), + pcpu_chunk_addr(chunk, last, page_end)); + return 0; +} + +/** + * pcpu_populate_chunk - populate and map an area of a pcpu_chunk + * @chunk: chunk of interest + * @off: offset to the area to populate + * @size: size of the area to populate in bytes + * + * For each cpu, populate and map pages [@page_start,@page_end) into + * @chunk. The area is cleared on return. + * + * CONTEXT: + * pcpu_alloc_mutex, does GFP_KERNEL allocation. + */ +static int pcpu_populate_chunk(struct pcpu_chunk *chunk, int off, int size) +{ + const gfp_t alloc_mask = GFP_KERNEL | __GFP_HIGHMEM | __GFP_COLD; + int page_start = PFN_DOWN(off); + int page_end = PFN_UP(off + size); + int map_start = -1; + int uninitialized_var(map_end); + unsigned int cpu; + int i; + + for (i = page_start; i < page_end; i++) { + if (pcpu_chunk_page_occupied(chunk, i)) { + if (map_start >= 0) { + if (pcpu_map(chunk, map_start, map_end)) + goto err; + map_start = -1; + } + continue; + } + + map_start = map_start < 0 ? i : map_start; + map_end = i + 1; + + for_each_possible_cpu(cpu) { + struct page **pagep = pcpu_chunk_pagep(chunk, cpu, i); + + *pagep = alloc_pages_node(cpu_to_node(cpu), + alloc_mask, 0); + if (!*pagep) + goto err; + } + } + + if (map_start >= 0 && pcpu_map(chunk, map_start, map_end)) + goto err; + + for_each_possible_cpu(cpu) + memset(chunk->vm->addr + cpu * pcpu_unit_size + off, 0, + size); + + return 0; +err: + /* likely under heavy memory pressure, give memory back */ + pcpu_depopulate_chunk(chunk, off, size, true); + return -ENOMEM; +} + +static void free_pcpu_chunk(struct pcpu_chunk *chunk) +{ + if (!chunk) + return; + if (chunk->vm) + free_vm_area(chunk->vm); + pcpu_mem_free(chunk->map, chunk->map_alloc * sizeof(chunk->map[0])); + kfree(chunk); +} + +static struct pcpu_chunk *alloc_pcpu_chunk(void) +{ + struct pcpu_chunk *chunk; + + chunk = kzalloc(pcpu_chunk_struct_size, GFP_KERNEL); + if (!chunk) + return NULL; + + chunk->map = pcpu_mem_alloc(PCPU_DFL_MAP_ALLOC * sizeof(chunk->map[0])); + chunk->map_alloc = PCPU_DFL_MAP_ALLOC; + chunk->map[chunk->map_used++] = pcpu_unit_size; + chunk->page = chunk->page_ar; + + chunk->vm = get_vm_area(pcpu_chunk_size, GFP_KERNEL); + if (!chunk->vm) { + free_pcpu_chunk(chunk); + return NULL; + } + + INIT_LIST_HEAD(&chunk->list); + chunk->free_size = pcpu_unit_size; + chunk->contig_hint = pcpu_unit_size; + + return chunk; +} + +/** + * pcpu_alloc - the percpu allocator + * @size: size of area to allocate in bytes + * @align: alignment of area (max PAGE_SIZE) + * @reserved: allocate from the reserved chunk if available + * + * Allocate percpu area of @size bytes aligned at @align. + * + * CONTEXT: + * Does GFP_KERNEL allocation. + * + * RETURNS: + * Percpu pointer to the allocated area on success, NULL on failure. + */ +static void *pcpu_alloc(size_t size, size_t align, bool reserved) +{ + struct pcpu_chunk *chunk; + int slot, off; + + if (unlikely(!size || size > PCPU_MIN_UNIT_SIZE || align > PAGE_SIZE)) { + WARN(true, "illegal size (%zu) or align (%zu) for " + "percpu allocation\n", size, align); + return NULL; + } + + mutex_lock(&pcpu_alloc_mutex); + spin_lock_irq(&pcpu_lock); + + /* serve reserved allocations from the reserved chunk if available */ + if (reserved && pcpu_reserved_chunk) { + chunk = pcpu_reserved_chunk; + if (size > chunk->contig_hint || + pcpu_extend_area_map(chunk) < 0) + goto fail_unlock; + off = pcpu_alloc_area(chunk, size, align); + if (off >= 0) + goto area_found; + goto fail_unlock; + } + +restart: + /* search through normal chunks */ + for (slot = pcpu_size_to_slot(size); slot < pcpu_nr_slots; slot++) { + list_for_each_entry(chunk, &pcpu_slot[slot], list) { + if (size > chunk->contig_hint) + continue; + + switch (pcpu_extend_area_map(chunk)) { + case 0: + break; + case 1: + goto restart; /* pcpu_lock dropped, restart */ + default: + goto fail_unlock; + } + + off = pcpu_alloc_area(chunk, size, align); + if (off >= 0) + goto area_found; + } + } + + /* hmmm... no space left, create a new chunk */ + spin_unlock_irq(&pcpu_lock); + + chunk = alloc_pcpu_chunk(); + if (!chunk) + goto fail_unlock_mutex; + + spin_lock_irq(&pcpu_lock); + pcpu_chunk_relocate(chunk, -1); + pcpu_chunk_addr_insert(chunk); + goto restart; + +area_found: + spin_unlock_irq(&pcpu_lock); + + /* populate, map and clear the area */ + if (pcpu_populate_chunk(chunk, off, size)) { + spin_lock_irq(&pcpu_lock); + pcpu_free_area(chunk, off); + goto fail_unlock; + } + + mutex_unlock(&pcpu_alloc_mutex); + + return __addr_to_pcpu_ptr(chunk->vm->addr + off); + +fail_unlock: + spin_unlock_irq(&pcpu_lock); +fail_unlock_mutex: + mutex_unlock(&pcpu_alloc_mutex); + return NULL; +} + +/** + * __alloc_percpu - allocate dynamic percpu area + * @size: size of area to allocate in bytes + * @align: alignment of area (max PAGE_SIZE) + * + * Allocate percpu area of @size bytes aligned at @align. Might + * sleep. Might trigger writeouts. + * + * CONTEXT: + * Does GFP_KERNEL allocation. + * + * RETURNS: + * Percpu pointer to the allocated area on success, NULL on failure. + */ +void *__alloc_percpu(size_t size, size_t align) +{ + return pcpu_alloc(size, align, false); +} +EXPORT_SYMBOL_GPL(__alloc_percpu); + +/** + * __alloc_reserved_percpu - allocate reserved percpu area + * @size: size of area to allocate in bytes + * @align: alignment of area (max PAGE_SIZE) + * + * Allocate percpu area of @size bytes aligned at @align from reserved + * percpu area if arch has set it up; otherwise, allocation is served + * from the same dynamic area. Might sleep. Might trigger writeouts. + * + * CONTEXT: + * Does GFP_KERNEL allocation. + * + * RETURNS: + * Percpu pointer to the allocated area on success, NULL on failure. + */ +void *__alloc_reserved_percpu(size_t size, size_t align) +{ + return pcpu_alloc(size, align, true); +} + +/** + * pcpu_reclaim - reclaim fully free chunks, workqueue function + * @work: unused + * + * Reclaim all fully free chunks except for the first one. + * + * CONTEXT: + * workqueue context. + */ +static void pcpu_reclaim(struct work_struct *work) +{ + LIST_HEAD(todo); + struct list_head *head = &pcpu_slot[pcpu_nr_slots - 1]; + struct pcpu_chunk *chunk, *next; + + mutex_lock(&pcpu_alloc_mutex); + spin_lock_irq(&pcpu_lock); + + list_for_each_entry_safe(chunk, next, head, list) { + WARN_ON(chunk->immutable); + + /* spare the first one */ + if (chunk == list_first_entry(head, struct pcpu_chunk, list)) + continue; + + rb_erase(&chunk->rb_node, &pcpu_addr_root); + list_move(&chunk->list, &todo); + } + + spin_unlock_irq(&pcpu_lock); + mutex_unlock(&pcpu_alloc_mutex); + + list_for_each_entry_safe(chunk, next, &todo, list) { + pcpu_depopulate_chunk(chunk, 0, pcpu_unit_size, false); + free_pcpu_chunk(chunk); + } +} + +/** + * free_percpu - free percpu area + * @ptr: pointer to area to free + * + * Free percpu area @ptr. + * + * CONTEXT: + * Can be called from atomic context. + */ +void free_percpu(void *ptr) +{ + void *addr = __pcpu_ptr_to_addr(ptr); + struct pcpu_chunk *chunk; + unsigned long flags; + int off; + + if (!ptr) + return; + + spin_lock_irqsave(&pcpu_lock, flags); + + chunk = pcpu_chunk_addr_search(addr); + off = addr - chunk->vm->addr; + + pcpu_free_area(chunk, off); + + /* if there are more than one fully free chunks, wake up grim reaper */ + if (chunk->free_size == pcpu_unit_size) { + struct pcpu_chunk *pos; + + list_for_each_entry(pos, &pcpu_slot[pcpu_nr_slots - 1], list) + if (pos != chunk) { + schedule_work(&pcpu_reclaim_work); + break; + } + } + + spin_unlock_irqrestore(&pcpu_lock, flags); +} +EXPORT_SYMBOL_GPL(free_percpu); + +/** + * pcpu_setup_first_chunk - initialize the first percpu chunk + * @get_page_fn: callback to fetch page pointer + * @static_size: the size of static percpu area in bytes + * @reserved_size: the size of reserved percpu area in bytes + * @dyn_size: free size for dynamic allocation in bytes, -1 for auto + * @unit_size: unit size in bytes, must be multiple of PAGE_SIZE, -1 for auto + * @base_addr: mapped address, NULL for auto + * @populate_pte_fn: callback to allocate pagetable, NULL if unnecessary + * + * Initialize the first percpu chunk which contains the kernel static + * perpcu area. This function is to be called from arch percpu area + * setup path. The first two parameters are mandatory. The rest are + * optional. + * + * @get_page_fn() should return pointer to percpu page given cpu + * number and page number. It should at least return enough pages to + * cover the static area. The returned pages for static area should + * have been initialized with valid data. If @unit_size is specified, + * it can also return pages after the static area. NULL return + * indicates end of pages for the cpu. Note that @get_page_fn() must + * return the same number of pages for all cpus. + * + * @reserved_size, if non-zero, specifies the amount of bytes to + * reserve after the static area in the first chunk. This reserves + * the first chunk such that it's available only through reserved + * percpu allocation. This is primarily used to serve module percpu + * static areas on architectures where the addressing model has + * limited offset range for symbol relocations to guarantee module + * percpu symbols fall inside the relocatable range. + * + * @dyn_size, if non-negative, determines the number of bytes + * available for dynamic allocation in the first chunk. Specifying + * non-negative value makes percpu leave alone the area beyond + * @static_size + @reserved_size + @dyn_size. + * + * @unit_size, if non-negative, specifies unit size and must be + * aligned to PAGE_SIZE and equal to or larger than @static_size + + * @reserved_size + if non-negative, @dyn_size. + * + * Non-null @base_addr means that the caller already allocated virtual + * region for the first chunk and mapped it. percpu must not mess + * with the chunk. Note that @base_addr with 0 @unit_size or non-NULL + * @populate_pte_fn doesn't make any sense. + * + * @populate_pte_fn is used to populate the pagetable. NULL means the + * caller already populated the pagetable. + * + * If the first chunk ends up with both reserved and dynamic areas, it + * is served by two chunks - one to serve the core static and reserved + * areas and the other for the dynamic area. They share the same vm + * and page map but uses different area allocation map to stay away + * from each other. The latter chunk is circulated in the chunk slots + * and available for dynamic allocation like any other chunks. + * + * RETURNS: + * The determined pcpu_unit_size which can be used to initialize + * percpu access. + */ +size_t __init pcpu_setup_first_chunk(pcpu_get_page_fn_t get_page_fn, + size_t static_size, size_t reserved_size, + ssize_t dyn_size, ssize_t unit_size, + void *base_addr, + pcpu_populate_pte_fn_t populate_pte_fn) +{ + static struct vm_struct first_vm; + static int smap[2], dmap[2]; + size_t size_sum = static_size + reserved_size + + (dyn_size >= 0 ? dyn_size : 0); + struct pcpu_chunk *schunk, *dchunk = NULL; + unsigned int cpu; + int nr_pages; + int err, i; + + /* santiy checks */ + BUILD_BUG_ON(ARRAY_SIZE(smap) >= PCPU_DFL_MAP_ALLOC || + ARRAY_SIZE(dmap) >= PCPU_DFL_MAP_ALLOC); + BUG_ON(!static_size); + if (unit_size >= 0) { + BUG_ON(unit_size < size_sum); + BUG_ON(unit_size & ~PAGE_MASK); + BUG_ON(unit_size < PCPU_MIN_UNIT_SIZE); + } else + BUG_ON(base_addr); + BUG_ON(base_addr && populate_pte_fn); + + if (unit_size >= 0) + pcpu_unit_pages = unit_size >> PAGE_SHIFT; + else + pcpu_unit_pages = max_t(int, PCPU_MIN_UNIT_SIZE >> PAGE_SHIFT, + PFN_UP(size_sum)); + + pcpu_unit_size = pcpu_unit_pages << PAGE_SHIFT; + pcpu_chunk_size = num_possible_cpus() * pcpu_unit_size; + pcpu_chunk_struct_size = sizeof(struct pcpu_chunk) + + num_possible_cpus() * pcpu_unit_pages * sizeof(struct page *); + + if (dyn_size < 0) + dyn_size = pcpu_unit_size - static_size - reserved_size; + + /* + * Allocate chunk slots. The additional last slot is for + * empty chunks. + */ + pcpu_nr_slots = __pcpu_size_to_slot(pcpu_unit_size) + 2; + pcpu_slot = alloc_bootmem(pcpu_nr_slots * sizeof(pcpu_slot[0])); + for (i = 0; i < pcpu_nr_slots; i++) + INIT_LIST_HEAD(&pcpu_slot[i]); + + /* + * Initialize static chunk. If reserved_size is zero, the + * static chunk covers static area + dynamic allocation area + * in the first chunk. If reserved_size is not zero, it + * covers static area + reserved area (mostly used for module + * static percpu allocation). + */ + schunk = alloc_bootmem(pcpu_chunk_struct_size); + INIT_LIST_HEAD(&schunk->list); + schunk->vm = &first_vm; + schunk->map = smap; + schunk->map_alloc = ARRAY_SIZE(smap); + schunk->page = schunk->page_ar; + + if (reserved_size) { + schunk->free_size = reserved_size; + pcpu_reserved_chunk = schunk; /* not for dynamic alloc */ + } else { + schunk->free_size = dyn_size; + dyn_size = 0; /* dynamic area covered */ + } + schunk->contig_hint = schunk->free_size; + + schunk->map[schunk->map_used++] = -static_size; + if (schunk->free_size) + schunk->map[schunk->map_used++] = schunk->free_size; + + pcpu_reserved_chunk_limit = static_size + schunk->free_size; + + /* init dynamic chunk if necessary */ + if (dyn_size) { + dchunk = alloc_bootmem(sizeof(struct pcpu_chunk)); + INIT_LIST_HEAD(&dchunk->list); + dchunk->vm = &first_vm; + dchunk->map = dmap; + dchunk->map_alloc = ARRAY_SIZE(dmap); + dchunk->page = schunk->page_ar; /* share page map with schunk */ + + dchunk->contig_hint = dchunk->free_size = dyn_size; + dchunk->map[dchunk->map_used++] = -pcpu_reserved_chunk_limit; + dchunk->map[dchunk->map_used++] = dchunk->free_size; + } + + /* allocate vm address */ + first_vm.flags = VM_ALLOC; + first_vm.size = pcpu_chunk_size; + + if (!base_addr) + vm_area_register_early(&first_vm, PAGE_SIZE); + else { + /* + * Pages already mapped. No need to remap into + * vmalloc area. In this case the first chunks can't + * be mapped or unmapped by percpu and are marked + * immutable. + */ + first_vm.addr = base_addr; + schunk->immutable = true; + if (dchunk) + dchunk->immutable = true; + } + + /* assign pages */ + nr_pages = -1; + for_each_possible_cpu(cpu) { + for (i = 0; i < pcpu_unit_pages; i++) { + struct page *page = get_page_fn(cpu, i); + + if (!page) + break; + *pcpu_chunk_pagep(schunk, cpu, i) = page; + } + + BUG_ON(i < PFN_UP(static_size)); + + if (nr_pages < 0) + nr_pages = i; + else + BUG_ON(nr_pages != i); + } + + /* map them */ + if (populate_pte_fn) { + for_each_possible_cpu(cpu) + for (i = 0; i < nr_pages; i++) + populate_pte_fn(pcpu_chunk_addr(schunk, + cpu, i)); + + err = pcpu_map(schunk, 0, nr_pages); + if (err) + panic("failed to setup static percpu area, err=%d\n", + err); + } + + /* link the first chunk in */ + if (!dchunk) { + pcpu_chunk_relocate(schunk, -1); + pcpu_chunk_addr_insert(schunk); + } else { + pcpu_chunk_relocate(dchunk, -1); + pcpu_chunk_addr_insert(dchunk); + } + + /* we're done */ + pcpu_base_addr = (void *)pcpu_chunk_addr(schunk, 0, 0); + return pcpu_unit_size; +} + +/* + * Embedding first chunk setup helper. + */ +static void *pcpue_ptr __initdata; +static size_t pcpue_size __initdata; +static size_t pcpue_unit_size __initdata; + +static struct page * __init pcpue_get_page(unsigned int cpu, int pageno) +{ + size_t off = (size_t)pageno << PAGE_SHIFT; + + if (off >= pcpue_size) + return NULL; + + return virt_to_page(pcpue_ptr + cpu * pcpue_unit_size + off); +} + +/** + * pcpu_embed_first_chunk - embed the first percpu chunk into bootmem + * @static_size: the size of static percpu area in bytes + * @reserved_size: the size of reserved percpu area in bytes + * @dyn_size: free size for dynamic allocation in bytes, -1 for auto + * @unit_size: unit size in bytes, must be multiple of PAGE_SIZE, -1 for auto + * + * This is a helper to ease setting up embedded first percpu chunk and + * can be called where pcpu_setup_first_chunk() is expected. + * + * If this function is used to setup the first chunk, it is allocated + * as a contiguous area using bootmem allocator and used as-is without + * being mapped into vmalloc area. This enables the first chunk to + * piggy back on the linear physical mapping which often uses larger + * page size. + * + * When @dyn_size is positive, dynamic area might be larger than + * specified to fill page alignment. Also, when @dyn_size is auto, + * @dyn_size does not fill the whole first chunk but only what's + * necessary for page alignment after static and reserved areas. + * + * If the needed size is smaller than the minimum or specified unit + * size, the leftover is returned to the bootmem allocator. + * + * RETURNS: + * The determined pcpu_unit_size which can be used to initialize + * percpu access on success, -errno on failure. + */ +ssize_t __init pcpu_embed_first_chunk(size_t static_size, size_t reserved_size, + ssize_t dyn_size, ssize_t unit_size) +{ + unsigned int cpu; + + /* determine parameters and allocate */ + pcpue_size = PFN_ALIGN(static_size + reserved_size + + (dyn_size >= 0 ? dyn_size : 0)); + if (dyn_size != 0) + dyn_size = pcpue_size - static_size - reserved_size; + + if (unit_size >= 0) { + BUG_ON(unit_size < pcpue_size); + pcpue_unit_size = unit_size; + } else + pcpue_unit_size = max_t(size_t, pcpue_size, PCPU_MIN_UNIT_SIZE); + + pcpue_ptr = __alloc_bootmem_nopanic( + num_possible_cpus() * pcpue_unit_size, + PAGE_SIZE, __pa(MAX_DMA_ADDRESS)); + if (!pcpue_ptr) + return -ENOMEM; + + /* return the leftover and copy */ + for_each_possible_cpu(cpu) { + void *ptr = pcpue_ptr + cpu * pcpue_unit_size; + + free_bootmem(__pa(ptr + pcpue_size), + pcpue_unit_size - pcpue_size); + memcpy(ptr, __per_cpu_load, static_size); + } + + /* we're ready, commit */ + pr_info("PERCPU: Embedded %zu pages at %p, static data %zu bytes\n", + pcpue_size >> PAGE_SHIFT, pcpue_ptr, static_size); + + return pcpu_setup_first_chunk(pcpue_get_page, static_size, + reserved_size, dyn_size, + pcpue_unit_size, pcpue_ptr, NULL); +} diff --git a/mm/quicklist.c b/mm/quicklist.c index 8dbb680..e66d07d 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 bec83c1..133b6d5 100644 --- a/mm/readahead.c +++ b/mm/readahead.c @@ -17,19 +17,6 @@ #include <linux/pagevec.h> #include <linux/pagemap.h> -void default_unplug_io_fn(struct backing_dev_info *bdi, struct page *page) -{ -} -EXPORT_SYMBOL(default_unplug_io_fn); - -struct backing_dev_info default_backing_dev_info = { - .ra_pages = VM_MAX_READAHEAD * 1024 / PAGE_CACHE_SIZE, - .state = 0, - .capabilities = BDI_CAP_MAP_COPY, - .unplug_io_fn = default_unplug_io_fn, -}; -EXPORT_SYMBOL_GPL(default_backing_dev_info); - /* * Initialise a struct file's readahead state. Assumes that the caller has * memset *ra to zero. @@ -44,6 +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 @@ -65,14 +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); @@ -233,18 +256,6 @@ unsigned long max_sane_readahead(unsigned long nr) + node_page_state(numa_node_id(), NR_FREE_PAGES)) / 2); } -static int __init readahead_init(void) -{ - int err; - - err = bdi_init(&default_backing_dev_info); - if (!err) - bdi_register(&default_backing_dev_info, NULL, "default"); - - return err; -} -subsys_initcall(readahead_init); - /* * Submit IO for the read-ahead request in file_ra_state. */ @@ -28,6 +28,7 @@ #include <linux/mm.h> #include <linux/module.h> #include <linux/swap.h> +#include <linux/ima.h> static struct vfsmount *shm_mnt; @@ -169,13 +170,13 @@ static inline struct shmem_sb_info *SHMEM_SB(struct super_block *sb) */ static inline int shmem_acct_size(unsigned long flags, loff_t size) { - return (flags & VM_ACCOUNT) ? - security_vm_enough_memory_kern(VM_ACCT(size)) : 0; + return (flags & VM_NORESERVE) ? + 0 : security_vm_enough_memory_kern(VM_ACCT(size)); } static inline void shmem_unacct_size(unsigned long flags, loff_t size) { - if (flags & VM_ACCOUNT) + if (!(flags & VM_NORESERVE)) vm_unacct_memory(VM_ACCT(size)); } @@ -187,13 +188,13 @@ static inline void shmem_unacct_size(unsigned long flags, loff_t size) */ static inline int shmem_acct_block(unsigned long flags) { - return (flags & VM_ACCOUNT) ? - 0 : security_vm_enough_memory_kern(VM_ACCT(PAGE_CACHE_SIZE)); + return (flags & VM_NORESERVE) ? + security_vm_enough_memory_kern(VM_ACCT(PAGE_CACHE_SIZE)) : 0; } static inline void shmem_unacct_blocks(unsigned long flags, long pages) { - if (!(flags & VM_ACCOUNT)) + if (flags & VM_NORESERVE) vm_unacct_memory(pages * VM_ACCT(PAGE_CACHE_SIZE)); } @@ -1067,8 +1068,7 @@ static int shmem_writepage(struct page *page, struct writeback_control *wbc) swap_duplicate(swap); BUG_ON(page_mapped(page)); page_cache_release(page); /* pagecache ref */ - set_page_dirty(page); - unlock_page(page); + swap_writepage(page, wbc); if (inode) { mutex_lock(&shmem_swaplist_mutex); /* move instead of add in case we're racing */ @@ -1515,8 +1515,8 @@ static int shmem_mmap(struct file *file, struct vm_area_struct *vma) return 0; } -static struct inode * -shmem_get_inode(struct super_block *sb, int mode, dev_t dev) +static struct inode *shmem_get_inode(struct super_block *sb, int mode, + dev_t dev, unsigned long flags) { struct inode *inode; struct shmem_inode_info *info; @@ -1537,6 +1537,7 @@ shmem_get_inode(struct super_block *sb, int mode, dev_t dev) info = SHMEM_I(inode); memset(info, 0, (char *)inode - (char *)info); spin_lock_init(&info->lock); + info->flags = flags & VM_NORESERVE; INIT_LIST_HEAD(&info->swaplist); switch (mode & S_IFMT) { @@ -1779,9 +1780,10 @@ static int shmem_statfs(struct dentry *dentry, struct kstatfs *buf) static int shmem_mknod(struct inode *dir, struct dentry *dentry, int mode, dev_t dev) { - struct inode *inode = shmem_get_inode(dir->i_sb, mode, dev); + struct inode *inode; int error = -ENOSPC; + inode = shmem_get_inode(dir->i_sb, mode, dev, VM_NORESERVE); if (inode) { error = security_inode_init_security(inode, dir, NULL, NULL, NULL); @@ -1920,7 +1922,7 @@ static int shmem_symlink(struct inode *dir, struct dentry *dentry, const char *s if (len > PAGE_CACHE_SIZE) return -ENAMETOOLONG; - inode = shmem_get_inode(dir->i_sb, S_IFLNK|S_IRWXUGO, 0); + inode = shmem_get_inode(dir->i_sb, S_IFLNK|S_IRWXUGO, 0, VM_NORESERVE); if (!inode) return -ENOSPC; @@ -2332,7 +2334,7 @@ static int shmem_fill_super(struct super_block *sb, sb->s_flags |= MS_POSIXACL; #endif - inode = shmem_get_inode(sb, S_IFDIR | sbinfo->mode, 0); + inode = shmem_get_inode(sb, S_IFDIR | sbinfo->mode, 0, VM_NORESERVE); if (!inode) goto failed; inode->i_uid = sbinfo->uid; @@ -2574,12 +2576,12 @@ int shmem_unuse(swp_entry_t entry, struct page *page) return 0; } -#define shmem_file_operations ramfs_file_operations -#define shmem_vm_ops generic_file_vm_ops -#define shmem_get_inode ramfs_get_inode -#define shmem_acct_size(a, b) 0 -#define shmem_unacct_size(a, b) do {} while (0) -#define SHMEM_MAX_BYTES LLONG_MAX +#define shmem_vm_ops generic_file_vm_ops +#define shmem_file_operations ramfs_file_operations +#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 #endif /* CONFIG_SHMEM */ @@ -2589,7 +2591,7 @@ int shmem_unuse(swp_entry_t entry, struct page *page) * shmem_file_setup - get an unlinked file living in tmpfs * @name: name for dentry (to be seen in /proc/<pid>/maps * @size: size to be set for the file - * @flags: vm_flags + * @flags: VM_NORESERVE suppresses pre-accounting of the entire object size */ struct file *shmem_file_setup(char *name, loff_t size, unsigned long flags) { @@ -2623,13 +2625,10 @@ struct file *shmem_file_setup(char *name, loff_t size, unsigned long flags) goto put_dentry; error = -ENOSPC; - inode = shmem_get_inode(root->d_sb, S_IFREG | S_IRWXUGO, 0); + inode = shmem_get_inode(root->d_sb, S_IFREG | S_IRWXUGO, 0, flags); if (!inode) goto close_file; -#ifdef CONFIG_SHMEM - SHMEM_I(inode)->flags = (flags & VM_NORESERVE) ? 0 : VM_ACCOUNT; -#endif d_instantiate(dentry, inode); inode->i_size = size; inode->i_nlink = 0; /* It is unlinked */ @@ -2666,6 +2665,7 @@ int shmem_zero_setup(struct vm_area_struct *vma) if (IS_ERR(file)) return PTR_ERR(file); + ima_shm_check(file); if (vma->vm_file) fput(vma->vm_file); vma->vm_file = file; @@ -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; @@ -3318,6 +3327,8 @@ __cache_alloc_node(struct kmem_cache *cachep, gfp_t flags, int nodeid, unsigned long save_flags; void *ptr; + lockdep_trace_alloc(flags); + if (slab_should_failslab(cachep, flags)) return NULL; @@ -3394,6 +3405,8 @@ __cache_alloc(struct kmem_cache *cachep, gfp_t flags, void *caller) unsigned long save_flags; void *objp; + lockdep_trace_alloc(flags); + if (slab_should_failslab(cachep, flags)) return NULL; @@ -3550,10 +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 @@ -3598,23 +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, @@ -3647,6 +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_. @@ -3656,11 +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)); @@ -3699,6 +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); @@ -3716,6 +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); @@ -3988,8 +4047,7 @@ static void cache_reap(struct work_struct *w) struct kmem_cache *searchp; struct kmem_list3 *l3; int node = numa_node_id(); - struct delayed_work *work = - container_of(w, struct delayed_work, work); + struct delayed_work *work = to_delayed_work(w); if (!mutex_trylock(&cache_chain_mutex)) /* Give up. Setup the next iteration. */ @@ -4457,3 +4515,4 @@ size_t ksize(const void *objp) return obj_size(virt_to_cache(objp)); } +EXPORT_SYMBOL(ksize); @@ -65,6 +65,7 @@ #include <linux/module.h> #include <linux/rcupdate.h> #include <linux/list.h> +#include <trace/kmemtrace.h> #include <asm/atomic.h> /* @@ -126,9 +127,9 @@ static LIST_HEAD(free_slob_medium); static LIST_HEAD(free_slob_large); /* - * slob_page: True for all slob pages (false for bigblock pages) + * is_slob_page: True for all slob pages (false for bigblock pages) */ -static inline int slob_page(struct slob_page *sp) +static inline int is_slob_page(struct slob_page *sp) { return PageSlobPage((struct page *)sp); } @@ -143,6 +144,11 @@ static inline void clear_slob_page(struct slob_page *sp) __ClearPageSlobPage((struct page *)sp); } +static inline struct slob_page *slob_page(const void *addr) +{ + return (struct slob_page *)virt_to_page(addr); +} + /* * slob_page_free: true for pages on free_slob_pages list. */ @@ -230,7 +236,7 @@ static int slob_last(slob_t *s) return !((unsigned long)slob_next(s) & ~PAGE_MASK); } -static void *slob_new_page(gfp_t gfp, int order, int node) +static void *slob_new_pages(gfp_t gfp, int order, int node) { void *page; @@ -247,12 +253,17 @@ static void *slob_new_page(gfp_t gfp, int order, int node) return page_address(page); } +static void slob_free_pages(void *b, int order) +{ + free_pages((unsigned long)b, order); +} + /* * Allocate a slob block within a given slob_page sp. */ static void *slob_page_alloc(struct slob_page *sp, size_t size, int align) { - slob_t *prev, *cur, *aligned = 0; + slob_t *prev, *cur, *aligned = NULL; int delta = 0, units = SLOB_UNITS(size); for (prev = NULL, cur = sp->free; ; prev = cur, cur = slob_next(cur)) { @@ -349,10 +360,10 @@ static void *slob_alloc(size_t size, gfp_t gfp, int align, int node) /* Not enough space: must allocate a new page */ if (!b) { - b = slob_new_page(gfp & ~__GFP_ZERO, 0, node); + b = slob_new_pages(gfp & ~__GFP_ZERO, 0, node); if (!b) - return 0; - sp = (struct slob_page *)virt_to_page(b); + return NULL; + sp = slob_page(b); set_slob_page(sp); spin_lock_irqsave(&slob_lock, flags); @@ -384,7 +395,7 @@ static void slob_free(void *block, int size) return; BUG_ON(!size); - sp = (struct slob_page *)virt_to_page(block); + sp = slob_page(block); units = SLOB_UNITS(size); spin_lock_irqsave(&slob_lock, flags); @@ -393,10 +404,11 @@ static void slob_free(void *block, int size) /* Go directly to page allocator. Do not pass slob allocator */ if (slob_page_free(sp)) clear_slob_page_free(sp); + spin_unlock_irqrestore(&slob_lock, flags); clear_slob_page(sp); free_slob_page(sp); free_page((unsigned long)b); - goto out; + return; } if (!slob_page_free(sp)) { @@ -463,27 +475,38 @@ 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); if (size < PAGE_SIZE - align) { if (!size) 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_page(gfp | __GFP_COMP, get_order(size), node); + ret = slob_new_pages(gfp | __GFP_COMP, get_order(size), node); if (ret) { struct page *page; 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); @@ -491,11 +514,13 @@ void kfree(const void *block) { struct slob_page *sp; + trace_kfree(_RET_IP_, block); + if (unlikely(ZERO_OR_NULL_PTR(block))) return; - sp = (struct slob_page *)virt_to_page(block); - if (slob_page(sp)) { + sp = slob_page(block); + if (is_slob_page(sp)) { int align = max(ARCH_KMALLOC_MINALIGN, ARCH_SLAB_MINALIGN); unsigned int *m = (unsigned int *)(block - align); slob_free(m, *m + align); @@ -513,14 +538,15 @@ size_t ksize(const void *block) if (unlikely(block == ZERO_SIZE_PTR)) return 0; - sp = (struct slob_page *)virt_to_page(block); - if (slob_page(sp)) { + sp = slob_page(block); + if (is_slob_page(sp)) { int align = max(ARCH_KMALLOC_MINALIGN, ARCH_SLAB_MINALIGN); unsigned int *m = (unsigned int *)(block - align); return SLOB_UNITS(*m) * SLOB_UNIT; } else return sp->page.private; } +EXPORT_SYMBOL(ksize); struct kmem_cache { unsigned int size, align; @@ -569,10 +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 - b = slob_new_page(flags, get_order(c->size), node); + 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); @@ -586,7 +619,7 @@ static void __kmem_cache_free(void *b, int size) if (size < PAGE_SIZE) slob_free(b, size); else - free_pages((unsigned long)b, get_order(size)); + slob_free_pages(b, get_order(size)); } static void kmem_rcu_free(struct rcu_head *head) @@ -608,6 +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); @@ -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> @@ -374,14 +375,8 @@ static struct track *get_track(struct kmem_cache *s, void *object, static void set_track(struct kmem_cache *s, void *object, enum track_item alloc, unsigned long addr) { - struct track *p; + struct track *p = get_track(s, object, alloc); - if (s->offset) - p = object + s->offset + sizeof(void *); - else - p = object + s->inuse; - - p += alloc; if (addr) { p->addr = addr; p->cpu = smp_processor_id(); @@ -1335,7 +1330,7 @@ static struct page *get_any_partial(struct kmem_cache *s, gfp_t flags) n = get_node(s, zone_to_nid(zone)); if (n && cpuset_zone_allowed_hardwall(zone, flags) && - n->nr_partial > n->min_partial) { + n->nr_partial > s->min_partial) { page = get_partial_node(n); if (page) return page; @@ -1387,7 +1382,7 @@ static void unfreeze_slab(struct kmem_cache *s, struct page *page, int tail) slab_unlock(page); } else { stat(c, DEACTIVATE_EMPTY); - if (n->nr_partial < n->min_partial) { + if (n->nr_partial < s->min_partial) { /* * Adding an empty slab to the partial slabs in order * to avoid page allocator overhead. This slab needs @@ -1596,6 +1591,7 @@ static __always_inline void *slab_alloc(struct kmem_cache *s, unsigned long flags; unsigned int objsize; + lockdep_trace_alloc(gfpflags); might_sleep_if(gfpflags & __GFP_WAIT); if (should_failslab(s->objsize, gfpflags)) @@ -1623,18 +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. @@ -1724,7 +1747,7 @@ static __always_inline void slab_free(struct kmem_cache *s, c = get_cpu_slab(s, smp_processor_id()); debug_check_no_locks_freed(object, c->objsize); if (!(s->flags & SLAB_DEBUG_OBJECTS)) - debug_check_no_obj_freed(object, s->objsize); + debug_check_no_obj_freed(object, c->objsize); if (likely(page == c->page && c->node >= 0)) { object[c->offset] = c->freelist; c->freelist = object; @@ -1742,6 +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); @@ -1844,6 +1869,7 @@ static inline int calculate_order(int size) int order; int min_objects; int fraction; + int max_objects; /* * Attempt to find best configuration for a slab. This @@ -1856,6 +1882,9 @@ static inline int calculate_order(int size) min_objects = slub_min_objects; if (!min_objects) min_objects = 4 * (fls(nr_cpu_ids) + 1); + max_objects = (PAGE_SIZE << slub_max_order)/size; + min_objects = min(min_objects, max_objects); + while (min_objects > 1) { fraction = 16; while (fraction >= 4) { @@ -1865,7 +1894,7 @@ static inline int calculate_order(int size) return order; fraction /= 2; } - min_objects /= 2; + min_objects --; } /* @@ -1928,17 +1957,6 @@ static void init_kmem_cache_node(struct kmem_cache_node *n, struct kmem_cache *s) { n->nr_partial = 0; - - /* - * The larger the object size is, the more pages we want on the partial - * list to avoid pounding the page allocator excessively. - */ - n->min_partial = ilog2(s->size); - if (n->min_partial < MIN_PARTIAL) - n->min_partial = MIN_PARTIAL; - else if (n->min_partial > MAX_PARTIAL) - n->min_partial = MAX_PARTIAL; - spin_lock_init(&n->list_lock); INIT_LIST_HEAD(&n->partial); #ifdef CONFIG_SLUB_DEBUG @@ -2181,6 +2199,15 @@ static int init_kmem_cache_nodes(struct kmem_cache *s, gfp_t gfpflags) } #endif +static void set_min_partial(struct kmem_cache *s, unsigned long min) +{ + if (min < MIN_PARTIAL) + min = MIN_PARTIAL; + else if (min > MAX_PARTIAL) + min = MAX_PARTIAL; + s->min_partial = min; +} + /* * calculate_sizes() determines the order and the distribution of data within * a slab object. @@ -2319,6 +2346,11 @@ static int kmem_cache_open(struct kmem_cache *s, gfp_t gfpflags, if (!calculate_sizes(s, -1)) goto error; + /* + * The larger the object size is, the more pages we want on the partial + * list to avoid pounding the page allocator excessively. + */ + set_min_partial(s, ilog2(s->size)); s->refcount = 1; #ifdef CONFIG_NUMA s->remote_node_defrag_ratio = 1000; @@ -2475,7 +2507,7 @@ EXPORT_SYMBOL(kmem_cache_destroy); * Kmalloc subsystem *******************************************************************/ -struct kmem_cache kmalloc_caches[PAGE_SHIFT + 1] __cacheline_aligned; +struct kmem_cache kmalloc_caches[SLUB_PAGE_SHIFT] __cacheline_aligned; EXPORT_SYMBOL(kmalloc_caches); static int __init setup_slub_min_order(char *str) @@ -2537,7 +2569,7 @@ panic: } #ifdef CONFIG_ZONE_DMA -static struct kmem_cache *kmalloc_caches_dma[PAGE_SHIFT + 1]; +static struct kmem_cache *kmalloc_caches_dma[SLUB_PAGE_SHIFT]; static void sysfs_add_func(struct work_struct *w) { @@ -2657,8 +2689,9 @@ 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 > PAGE_SIZE)) + if (unlikely(size > SLUB_MAX_SIZE)) return kmalloc_large(size, flags); s = get_slab(size, flags); @@ -2666,7 +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); @@ -2685,16 +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)) { + ret = kmalloc_large_node(size, flags, node); - if (unlikely(size > PAGE_SIZE)) - return 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 @@ -2736,12 +2785,15 @@ size_t ksize(const void *object) */ return s->size; } +EXPORT_SYMBOL(ksize); 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; @@ -2985,7 +3037,7 @@ void __init kmem_cache_init(void) caches++; } - for (i = KMALLOC_SHIFT_LOW; i <= PAGE_SHIFT; i++) { + for (i = KMALLOC_SHIFT_LOW; i < SLUB_PAGE_SHIFT; i++) { create_kmalloc_cache(&kmalloc_caches[i], "kmalloc", 1 << i, GFP_KERNEL); caches++; @@ -3022,7 +3074,7 @@ void __init kmem_cache_init(void) slab_state = UP; /* Provide the correct kmalloc names now that the caches are up */ - for (i = KMALLOC_SHIFT_LOW; i <= PAGE_SHIFT; i++) + for (i = KMALLOC_SHIFT_LOW; i < SLUB_PAGE_SHIFT; i++) kmalloc_caches[i]. name = kasprintf(GFP_KERNEL, "kmalloc-%d", 1 << i); @@ -3221,8 +3273,9 @@ 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 > PAGE_SIZE)) + if (unlikely(size > SLUB_MAX_SIZE)) return kmalloc_large(size, gfpflags); s = get_slab(size, gfpflags); @@ -3230,15 +3283,21 @@ 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 > PAGE_SIZE)) + if (unlikely(size > SLUB_MAX_SIZE)) return kmalloc_large_node(size, gfpflags, node); s = get_slab(size, gfpflags); @@ -3246,7 +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 @@ -3835,6 +3899,26 @@ static ssize_t order_show(struct kmem_cache *s, char *buf) } SLAB_ATTR(order); +static ssize_t min_partial_show(struct kmem_cache *s, char *buf) +{ + return sprintf(buf, "%lu\n", s->min_partial); +} + +static ssize_t min_partial_store(struct kmem_cache *s, const char *buf, + size_t length) +{ + unsigned long min; + int err; + + err = strict_strtoul(buf, 10, &min); + if (err) + return err; + + set_min_partial(s, min); + return length; +} +SLAB_ATTR(min_partial); + static ssize_t ctor_show(struct kmem_cache *s, char *buf) { if (s->ctor) { @@ -4150,6 +4234,7 @@ static struct attribute *slab_attrs[] = { &object_size_attr.attr, &objs_per_slab_attr.attr, &order_attr.attr, + &min_partial_attr.attr, &objects_attr.attr, &objects_partial_attr.attr, &total_objects_attr.attr, diff --git a/mm/sparse.c b/mm/sparse.c index 083f5b6..da432d9 100644 --- a/mm/sparse.c +++ b/mm/sparse.c @@ -164,9 +164,7 @@ void __meminit mminit_validate_memmodel_limits(unsigned long *start_pfn, WARN_ON_ONCE(1); *start_pfn = max_sparsemem_pfn; *end_pfn = max_sparsemem_pfn; - } - - if (*end_pfn > max_sparsemem_pfn) { + } else if (*end_pfn > max_sparsemem_pfn) { mminit_dprintk(MMINIT_WARNING, "pfnvalidation", "End of range %lu -> %lu exceeds SPARSEMEM max %lu\n", *start_pfn, *end_pfn, max_sparsemem_pfn); @@ -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); } @@ -457,29 +457,6 @@ void pagevec_strip(struct pagevec *pvec) } /** - * pagevec_swap_free - try to free swap space from the pages in a pagevec - * @pvec: pagevec with swapcache pages to free the swap space of - * - * The caller needs to hold an extra reference to each page and - * not hold the page lock on the pages. This function uses a - * trylock on the page lock so it may not always free the swap - * space associated with a page. - */ -void pagevec_swap_free(struct pagevec *pvec) -{ - int i; - - for (i = 0; i < pagevec_count(pvec); i++) { - struct page *page = pvec->pages[i]; - - if (PageSwapCache(page) && trylock_page(page)) { - try_to_free_swap(page); - unlock_page(page); - } - } -} - -/** * pagevec_lookup - gang pagecache lookup * @pvec: Where the resulting pages are placed * @mapping: The address_space to search diff --git a/mm/swapfile.c b/mm/swapfile.c index 7e6304d..312fafe 100644 --- a/mm/swapfile.c +++ b/mm/swapfile.c @@ -635,7 +635,7 @@ int swap_type_of(dev_t device, sector_t offset, struct block_device **bdev_p) if (!bdev) { if (bdev_p) - *bdev_p = sis->bdev; + *bdev_p = bdget(sis->bdev->bd_dev); spin_unlock(&swap_lock); return i; @@ -647,7 +647,7 @@ int swap_type_of(dev_t device, sector_t offset, struct block_device **bdev_p) struct swap_extent, list); if (se->start_block == offset) { if (bdev_p) - *bdev_p = sis->bdev; + *bdev_p = bdget(sis->bdev->bd_dev); spin_unlock(&swap_lock); bdput(bdev); diff --git a/mm/truncate.c b/mm/truncate.c index 1229211..55206fa 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 */ @@ -4,6 +4,7 @@ #include <linux/module.h> #include <linux/err.h> #include <linux/sched.h> +#include <linux/tracepoint.h> #include <asm/uaccess.h> /** @@ -70,6 +71,36 @@ void *kmemdup(const void *src, size_t len, gfp_t gfp) EXPORT_SYMBOL(kmemdup); /** + * memdup_user - duplicate memory region from user space + * + * @src: source address in user space + * @len: number of bytes to copy + * + * Returns an ERR_PTR() on failure. + */ +void *memdup_user(const void __user *src, size_t len) +{ + void *p; + + /* + * Always use GFP_KERNEL, since copy_from_user() can sleep and + * cause pagefault, which makes it pointless to use GFP_NOFS + * or GFP_ATOMIC. + */ + p = kmalloc_track_caller(len, GFP_KERNEL); + if (!p) + return ERR_PTR(-ENOMEM); + + if (copy_from_user(p, src, len)) { + kfree(p); + return ERR_PTR(-EFAULT); + } + + return p; +} +EXPORT_SYMBOL(memdup_user); + +/** * __krealloc - like krealloc() but don't free @p. * @p: object to reallocate memory for. * @new_size: how many bytes of memory are required. @@ -129,6 +160,26 @@ void *krealloc(const void *p, size_t new_size, gfp_t flags) } EXPORT_SYMBOL(krealloc); +/** + * kzfree - like kfree but zero memory + * @p: object to free memory of + * + * The memory of the object @p points to is zeroed before freed. + * If @p is %NULL, kzfree() does nothing. + */ +void kzfree(const void *p) +{ + size_t ks; + void *mem = (void *)p; + + if (unlikely(ZERO_OR_NULL_PTR(mem))) + return; + ks = ksize(mem); + memset(mem, 0, ks); + kfree(mem); +} +EXPORT_SYMBOL(kzfree); + /* * strndup_user - duplicate an existing string from user space * @s: The string to duplicate @@ -186,3 +237,18 @@ 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/vmalloc.c b/mm/vmalloc.c index 75f49d3..fab1987 100644 --- a/mm/vmalloc.c +++ b/mm/vmalloc.c @@ -24,6 +24,7 @@ #include <linux/radix-tree.h> #include <linux/rcupdate.h> #include <linux/bootmem.h> +#include <linux/pfn.h> #include <asm/atomic.h> #include <asm/uaccess.h> @@ -152,8 +153,8 @@ static int vmap_pud_range(pgd_t *pgd, unsigned long addr, * * Ie. pte at addr+N*PAGE_SIZE shall point to pfn corresponding to pages[N] */ -static int vmap_page_range(unsigned long start, unsigned long end, - pgprot_t prot, struct page **pages) +static int vmap_page_range_noflush(unsigned long start, unsigned long end, + pgprot_t prot, struct page **pages) { pgd_t *pgd; unsigned long next; @@ -169,13 +170,22 @@ static int vmap_page_range(unsigned long start, unsigned long end, if (err) break; } while (pgd++, addr = next, addr != end); - flush_cache_vmap(start, end); if (unlikely(err)) return err; return nr; } +static int vmap_page_range(unsigned long start, unsigned long end, + pgprot_t prot, struct page **pages) +{ + int ret; + + ret = vmap_page_range_noflush(start, end, prot, pages); + flush_cache_vmap(start, end); + return ret; +} + static inline int is_vmalloc_or_module_addr(const void *x) { /* @@ -323,6 +333,7 @@ static struct vmap_area *alloc_vmap_area(unsigned long size, unsigned long addr; int purged = 0; + BUG_ON(!size); BUG_ON(size & ~PAGE_MASK); va = kmalloc_node(sizeof(struct vmap_area), @@ -334,6 +345,9 @@ retry: addr = ALIGN(vstart, align); spin_lock(&vmap_area_lock); + if (addr + size - 1 < addr) + goto overflow; + /* XXX: could have a last_hole cache */ n = vmap_area_root.rb_node; if (n) { @@ -365,6 +379,8 @@ retry: while (addr + size > first->va_start && addr + size <= vend) { addr = ALIGN(first->va_end + PAGE_SIZE, align); + if (addr + size - 1 < addr) + goto overflow; n = rb_next(&first->rb_node); if (n) @@ -375,6 +391,7 @@ retry: } found: if (addr + size > vend) { +overflow: spin_unlock(&vmap_area_lock); if (!purged) { purge_vmap_area_lazy(); @@ -498,6 +515,7 @@ static void __purge_vmap_area_lazy(unsigned long *start, unsigned long *end, static DEFINE_SPINLOCK(purge_lock); LIST_HEAD(valist); struct vmap_area *va; + struct vmap_area *n_va; int nr = 0; /* @@ -537,7 +555,7 @@ static void __purge_vmap_area_lazy(unsigned long *start, unsigned long *end, if (nr) { spin_lock(&vmap_area_lock); - list_for_each_entry(va, &valist, purge_list) + list_for_each_entry_safe(va, n_va, &valist, purge_list) __free_vmap_area(va); spin_unlock(&vmap_area_lock); } @@ -653,10 +671,7 @@ struct vmap_block { DECLARE_BITMAP(alloc_map, VMAP_BBMAP_BITS); DECLARE_BITMAP(dirty_map, VMAP_BBMAP_BITS); union { - struct { - struct list_head free_list; - struct list_head dirty_list; - }; + struct list_head free_list; struct rcu_head rcu_head; }; }; @@ -723,7 +738,6 @@ static struct vmap_block *new_vmap_block(gfp_t gfp_mask) bitmap_zero(vb->alloc_map, VMAP_BBMAP_BITS); bitmap_zero(vb->dirty_map, VMAP_BBMAP_BITS); INIT_LIST_HEAD(&vb->free_list); - INIT_LIST_HEAD(&vb->dirty_list); vb_idx = addr_to_vb_idx(va->va_start); spin_lock(&vmap_block_tree_lock); @@ -754,12 +768,7 @@ static void free_vmap_block(struct vmap_block *vb) struct vmap_block *tmp; unsigned long vb_idx; - spin_lock(&vb->vbq->lock); - if (!list_empty(&vb->free_list)) - list_del(&vb->free_list); - if (!list_empty(&vb->dirty_list)) - list_del(&vb->dirty_list); - spin_unlock(&vb->vbq->lock); + BUG_ON(!list_empty(&vb->free_list)); vb_idx = addr_to_vb_idx(vb->va->va_start); spin_lock(&vmap_block_tree_lock); @@ -844,11 +853,7 @@ static void vb_free(const void *addr, unsigned long size) spin_lock(&vb->lock); bitmap_allocate_region(vb->dirty_map, offset >> PAGE_SHIFT, order); - if (!vb->dirty) { - spin_lock(&vb->vbq->lock); - list_add(&vb->dirty_list, &vb->vbq->dirty); - spin_unlock(&vb->vbq->lock); - } + vb->dirty += 1UL << order; if (vb->dirty == VMAP_BBMAP_BITS) { BUG_ON(vb->free || !list_empty(&vb->free_list)); @@ -982,6 +987,32 @@ void *vm_map_ram(struct page **pages, unsigned int count, int node, pgprot_t pro } EXPORT_SYMBOL(vm_map_ram); +/** + * vm_area_register_early - register vmap area early during boot + * @vm: vm_struct to register + * @align: requested alignment + * + * This function is used to register kernel vm area before + * vmalloc_init() is called. @vm->size and @vm->flags should contain + * proper values on entry and other fields should be zero. On return, + * vm->addr contains the allocated address. + * + * DO NOT USE THIS FUNCTION UNLESS YOU KNOW WHAT YOU'RE DOING. + */ +void __init vm_area_register_early(struct vm_struct *vm, size_t align) +{ + static size_t vm_init_off __initdata; + unsigned long addr; + + addr = ALIGN(VMALLOC_START + vm_init_off, align); + vm_init_off = PFN_ALIGN(addr + vm->size) - VMALLOC_START; + + vm->addr = (void *)addr; + + vm->next = vmlist; + vmlist = vm; +} + void __init vmalloc_init(void) { struct vmap_area *va; @@ -1009,9 +1040,63 @@ void __init vmalloc_init(void) vmap_initialized = true; } +/** + * map_kernel_range_noflush - map kernel VM area with the specified pages + * @addr: start of the VM area to map + * @size: size of the VM area to map + * @prot: page protection flags to use + * @pages: pages to map + * + * Map PFN_UP(@size) pages at @addr. The VM area @addr and @size + * specify should have been allocated using get_vm_area() and its + * friends. + * + * NOTE: + * This function does NOT do any cache flushing. The caller is + * responsible for calling flush_cache_vmap() on to-be-mapped areas + * before calling this function. + * + * RETURNS: + * The number of pages mapped on success, -errno on failure. + */ +int map_kernel_range_noflush(unsigned long addr, unsigned long size, + pgprot_t prot, struct page **pages) +{ + return vmap_page_range_noflush(addr, addr + size, prot, pages); +} + +/** + * unmap_kernel_range_noflush - unmap kernel VM area + * @addr: start of the VM area to unmap + * @size: size of the VM area to unmap + * + * Unmap PFN_UP(@size) pages at @addr. The VM area @addr and @size + * specify should have been allocated using get_vm_area() and its + * friends. + * + * NOTE: + * This function does NOT do any cache flushing. The caller is + * responsible for calling flush_cache_vunmap() on to-be-mapped areas + * before calling this function and flush_tlb_kernel_range() after. + */ +void unmap_kernel_range_noflush(unsigned long addr, unsigned long size) +{ + vunmap_page_range(addr, addr + size); +} + +/** + * unmap_kernel_range - unmap kernel VM area and flush cache and TLB + * @addr: start of the VM area to unmap + * @size: size of the VM area to unmap + * + * Similar to unmap_kernel_range_noflush() but flushes vcache before + * the unmapping and tlb after. + */ void unmap_kernel_range(unsigned long addr, unsigned long size) { unsigned long end = addr + size; + + flush_cache_vunmap(addr, end); vunmap_page_range(addr, end); flush_tlb_kernel_range(addr, end); } @@ -1106,6 +1191,14 @@ struct vm_struct *__get_vm_area(unsigned long size, unsigned long flags, } EXPORT_SYMBOL_GPL(__get_vm_area); +struct vm_struct *__get_vm_area_caller(unsigned long size, unsigned long flags, + unsigned long start, unsigned long end, + void *caller) +{ + return __get_vm_area_node(size, flags, start, end, -1, GFP_KERNEL, + caller); +} + /** * get_vm_area - reserve a contiguous kernel virtual area * @size: size of the area @@ -1249,6 +1342,7 @@ EXPORT_SYMBOL(vfree); void vunmap(const void *addr) { BUG_ON(in_interrupt()); + might_sleep(); __vunmap(addr, 0); } EXPORT_SYMBOL(vunmap); @@ -1268,6 +1362,8 @@ void *vmap(struct page **pages, unsigned int count, { struct vm_struct *area; + might_sleep(); + if (count > num_physpages) return NULL; diff --git a/mm/vmscan.c b/mm/vmscan.c index 9a27c44..39fdfb1 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -60,8 +60,8 @@ struct scan_control { int may_writepage; - /* Can pages be swapped as part of reclaim? */ - int may_swap; + /* Can mapped pages be reclaimed? */ + int may_unmap; /* This context's SWAP_CLUSTER_MAX. If freeing memory for * suspend, we effectively ignore SWAP_CLUSTER_MAX. @@ -78,6 +78,12 @@ struct scan_control { /* Which cgroup do we reclaim from */ struct mem_cgroup *mem_cgroup; + /* + * Nodemask of nodes allowed by the caller. If NULL, all nodes + * are scanned. + */ + nodemask_t *nodemask; + /* Pluggable isolate pages callback */ unsigned long (*isolate_pages)(unsigned long nr, struct list_head *dst, unsigned long *scanned, int order, int mode, @@ -214,8 +220,9 @@ unsigned long shrink_slab(unsigned long scanned, gfp_t gfp_mask, do_div(delta, lru_pages + 1); shrinker->nr += delta; if (shrinker->nr < 0) { - printk(KERN_ERR "%s: nr=%ld\n", - __func__, shrinker->nr); + printk(KERN_ERR "shrink_slab: %pF negative objects to " + "delete nr=%ld\n", + shrinker->shrink, shrinker->nr); shrinker->nr = max_pass; } @@ -276,7 +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) @@ -360,7 +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__); @@ -606,7 +613,7 @@ static unsigned long shrink_page_list(struct list_head *page_list, if (unlikely(!page_evictable(page, NULL))) goto cull_mlocked; - if (!sc->may_swap && page_mapped(page)) + if (!sc->may_unmap && page_mapped(page)) goto keep_locked; /* Double the slab pressure for mapped and swapcache pages */ @@ -720,7 +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) { @@ -1262,7 +1269,6 @@ static void shrink_active_list(unsigned long nr_pages, struct zone *zone, * Move the pages to the [file or anon] inactive list. */ pagevec_init(&pvec, 1); - pgmoved = 0; lru = LRU_BASE + file * LRU_FILE; spin_lock_irq(&zone->lru_lock); @@ -1274,6 +1280,7 @@ static void shrink_active_list(unsigned long nr_pages, struct zone *zone, */ reclaim_stat->recent_rotated[!!file] += pgmoved; + pgmoved = 0; while (!list_empty(&l_inactive)) { page = lru_to_page(&l_inactive); prefetchw_prev_lru_page(page, &l_inactive, flags); @@ -1298,17 +1305,11 @@ static void shrink_active_list(unsigned long nr_pages, struct zone *zone, } __mod_zone_page_state(zone, NR_LRU_BASE + lru, pgmoved); pgdeactivate += pgmoved; - if (buffer_heads_over_limit) { - spin_unlock_irq(&zone->lru_lock); - pagevec_strip(&pvec); - spin_lock_irq(&zone->lru_lock); - } __count_zone_vm_events(PGREFILL, zone, pgscanned); __count_vm_events(PGDEACTIVATE, pgdeactivate); spin_unlock_irq(&zone->lru_lock); - if (vm_swap_full()) - pagevec_swap_free(&pvec); - + if (buffer_heads_over_limit) + pagevec_strip(&pvec); pagevec_release(&pvec); } @@ -1469,7 +1470,7 @@ static void shrink_zone(int priority, struct zone *zone, int file = is_file_lru(l); int scan; - scan = zone_page_state(zone, NR_LRU_BASE + l); + scan = zone_nr_pages(zone, sc, l); if (priority) { scan >>= priority; scan = (scan * percent[file]) / 100; @@ -1543,7 +1544,8 @@ static void shrink_zones(int priority, struct zonelist *zonelist, struct zone *zone; sc->all_unreclaimable = 1; - for_each_zone_zonelist(zone, z, zonelist, high_zoneidx) { + for_each_zone_zonelist_nodemask(zone, z, zonelist, high_zoneidx, + sc->nodemask) { if (!populated_zone(zone)) continue; /* @@ -1688,17 +1690,18 @@ out: } unsigned long try_to_free_pages(struct zonelist *zonelist, int order, - gfp_t gfp_mask) + gfp_t gfp_mask, nodemask_t *nodemask) { struct scan_control sc = { .gfp_mask = gfp_mask, .may_writepage = !laptop_mode, .swap_cluster_max = SWAP_CLUSTER_MAX, - .may_swap = 1, + .may_unmap = 1, .swappiness = vm_swappiness, .order = order, .mem_cgroup = NULL, .isolate_pages = isolate_pages_global, + .nodemask = nodemask, }; return do_try_to_free_pages(zonelist, &sc); @@ -1713,17 +1716,18 @@ unsigned long try_to_free_mem_cgroup_pages(struct mem_cgroup *mem_cont, { struct scan_control sc = { .may_writepage = !laptop_mode, - .may_swap = 1, + .may_unmap = 1, .swap_cluster_max = SWAP_CLUSTER_MAX, .swappiness = swappiness, .order = 0, .mem_cgroup = mem_cont, .isolate_pages = mem_cgroup_isolate_pages, + .nodemask = NULL, /* we don't care the placement */ }; struct zonelist *zonelist; if (noswap) - sc.may_swap = 0; + sc.may_unmap = 0; sc.gfp_mask = (gfp_mask & GFP_RECLAIM_MASK) | (GFP_HIGHUSER_MOVABLE & ~GFP_RECLAIM_MASK); @@ -1762,7 +1766,7 @@ static unsigned long balance_pgdat(pg_data_t *pgdat, int order) struct reclaim_state *reclaim_state = current->reclaim_state; struct scan_control sc = { .gfp_mask = GFP_KERNEL, - .may_swap = 1, + .may_unmap = 1, .swap_cluster_max = SWAP_CLUSTER_MAX, .swappiness = vm_swappiness, .order = order, @@ -1963,7 +1967,9 @@ 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); if (!cpumask_empty(cpumask)) set_cpus_allowed_ptr(tsk, cpumask); @@ -2048,49 +2054,47 @@ unsigned long global_lru_pages(void) #ifdef CONFIG_PM /* * Helper function for shrink_all_memory(). Tries to reclaim 'nr_pages' pages - * from LRU lists system-wide, for given pass and priority, and returns the - * number of reclaimed pages + * from LRU lists system-wide, for given pass and priority. * * For pass > 3 we also try to shrink the LRU lists that contain a few pages */ -static unsigned long shrink_all_zones(unsigned long nr_pages, int prio, +static void shrink_all_zones(unsigned long nr_pages, int prio, int pass, struct scan_control *sc) { struct zone *zone; - unsigned long nr_to_scan, ret = 0; - enum lru_list l; - - for_each_zone(zone) { + unsigned long nr_reclaimed = 0; - if (!populated_zone(zone)) - continue; + for_each_populated_zone(zone) { + enum lru_list l; if (zone_is_all_unreclaimable(zone) && prio != DEF_PRIORITY) continue; for_each_evictable_lru(l) { + enum zone_stat_item ls = NR_LRU_BASE + l; + unsigned long lru_pages = zone_page_state(zone, ls); + /* For pass = 0, we don't shrink the active list */ - if (pass == 0 && - (l == LRU_ACTIVE || l == LRU_ACTIVE_FILE)) + if (pass == 0 && (l == LRU_ACTIVE_ANON || + l == LRU_ACTIVE_FILE)) continue; - zone->lru[l].nr_scan += - (zone_page_state(zone, NR_LRU_BASE + l) - >> prio) + 1; + zone->lru[l].nr_scan += (lru_pages >> prio) + 1; if (zone->lru[l].nr_scan >= nr_pages || pass > 3) { + unsigned long nr_to_scan; + zone->lru[l].nr_scan = 0; - nr_to_scan = min(nr_pages, - zone_page_state(zone, - NR_LRU_BASE + l)); - ret += shrink_list(l, nr_to_scan, zone, + nr_to_scan = min(nr_pages, lru_pages); + nr_reclaimed += shrink_list(l, nr_to_scan, zone, sc, prio); - if (ret >= nr_pages) - return ret; + if (nr_reclaimed >= nr_pages) { + sc->nr_reclaimed = nr_reclaimed; + return; + } } } } - - return ret; + sc->nr_reclaimed = nr_reclaimed; } /* @@ -2104,15 +2108,12 @@ static unsigned long shrink_all_zones(unsigned long nr_pages, int prio, unsigned long shrink_all_memory(unsigned long nr_pages) { unsigned long lru_pages, nr_slab; - unsigned long ret = 0; int pass; struct reclaim_state reclaim_state; struct scan_control sc = { .gfp_mask = GFP_KERNEL, - .may_swap = 0, - .swap_cluster_max = nr_pages, + .may_unmap = 0, .may_writepage = 1, - .swappiness = vm_swappiness, .isolate_pages = isolate_pages_global, }; @@ -2127,8 +2128,8 @@ unsigned long shrink_all_memory(unsigned long nr_pages) if (!reclaim_state.reclaimed_slab) break; - ret += reclaim_state.reclaimed_slab; - if (ret >= nr_pages) + sc.nr_reclaimed += reclaim_state.reclaimed_slab; + if (sc.nr_reclaimed >= nr_pages) goto out; nr_slab -= reclaim_state.reclaimed_slab; @@ -2146,24 +2147,23 @@ unsigned long shrink_all_memory(unsigned long nr_pages) int prio; /* Force reclaiming mapped pages in the passes #3 and #4 */ - if (pass > 2) { - sc.may_swap = 1; - sc.swappiness = 100; - } + if (pass > 2) + sc.may_unmap = 1; for (prio = DEF_PRIORITY; prio >= 0; prio--) { - unsigned long nr_to_scan = nr_pages - ret; + unsigned long nr_to_scan = nr_pages - sc.nr_reclaimed; sc.nr_scanned = 0; - ret += shrink_all_zones(nr_to_scan, prio, pass, &sc); - if (ret >= nr_pages) + sc.swap_cluster_max = nr_to_scan; + shrink_all_zones(nr_to_scan, prio, pass, &sc); + if (sc.nr_reclaimed >= nr_pages) goto out; reclaim_state.reclaimed_slab = 0; shrink_slab(sc.nr_scanned, sc.gfp_mask, global_lru_pages()); - ret += reclaim_state.reclaimed_slab; - if (ret >= nr_pages) + sc.nr_reclaimed += reclaim_state.reclaimed_slab; + if (sc.nr_reclaimed >= nr_pages) goto out; if (sc.nr_scanned && prio < DEF_PRIORITY - 2) @@ -2172,21 +2172,23 @@ unsigned long shrink_all_memory(unsigned long nr_pages) } /* - * If ret = 0, we could not shrink LRUs, but there may be something - * in slab caches + * If sc.nr_reclaimed = 0, we could not shrink LRUs, but there may be + * something in slab caches */ - if (!ret) { + if (!sc.nr_reclaimed) { do { reclaim_state.reclaimed_slab = 0; shrink_slab(nr_pages, sc.gfp_mask, global_lru_pages()); - ret += reclaim_state.reclaimed_slab; - } while (ret < nr_pages && reclaim_state.reclaimed_slab > 0); + sc.nr_reclaimed += reclaim_state.reclaimed_slab; + } while (sc.nr_reclaimed < nr_pages && + reclaim_state.reclaimed_slab > 0); } + out: current->reclaim_state = NULL; - return ret; + return sc.nr_reclaimed; } #endif @@ -2202,7 +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 */ @@ -2292,11 +2296,12 @@ static int __zone_reclaim(struct zone *zone, gfp_t gfp_mask, unsigned int order) int priority; struct scan_control sc = { .may_writepage = !!(zone_reclaim_mode & RECLAIM_WRITE), - .may_swap = !!(zone_reclaim_mode & RECLAIM_SWAP), + .may_unmap = !!(zone_reclaim_mode & RECLAIM_SWAP), .swap_cluster_max = max_t(unsigned long, nr_pages, SWAP_CLUSTER_MAX), .gfp_mask = gfp_mask, .swappiness = vm_swappiness, + .order = order, .isolate_pages = isolate_pages_global, }; unsigned long slab_reclaimable; diff --git a/mm/vmstat.c b/mm/vmstat.c index 9114974..66f6130 100644 --- a/mm/vmstat.c +++ b/mm/vmstat.c @@ -27,7 +27,7 @@ static void sum_vm_events(unsigned long *ret, const struct cpumask *cpumask) memset(ret, 0, NR_VM_EVENT_ITEMS * sizeof(unsigned long)); - for_each_cpu_mask_nr(cpu, *cpumask) { + for_each_cpu(cpu, cpumask) { struct vm_event_state *this = &per_cpu(vm_event_states, cpu); for (i = 0; i < NR_VM_EVENT_ITEMS; i++) @@ -135,11 +135,7 @@ static void refresh_zone_stat_thresholds(void) int cpu; int threshold; - for_each_zone(zone) { - - if (!zone->present_pages) - continue; - + for_each_populated_zone(zone) { threshold = calculate_threshold(zone); for_each_online_cpu(cpu) @@ -301,12 +297,9 @@ void refresh_cpu_vm_stats(int cpu) int i; int global_diff[NR_VM_ZONE_STAT_ITEMS] = { 0, }; - for_each_zone(zone) { + for_each_populated_zone(zone) { struct per_cpu_pageset *p; - if (!populated_zone(zone)) - continue; - p = zone_pcp(zone, cpu); for (i = 0; i < NR_VM_ZONE_STAT_ITEMS; i++) @@ -898,7 +891,7 @@ static void vmstat_update(struct work_struct *w) { refresh_cpu_vm_stats(smp_processor_id()); schedule_delayed_work(&__get_cpu_var(vmstat_work), - sysctl_stat_interval); + round_jiffies_relative(sysctl_stat_interval)); } static void __cpuinit start_cpu_timer(int cpu) @@ -906,7 +899,8 @@ static void __cpuinit start_cpu_timer(int cpu) struct delayed_work *vmstat_work = &per_cpu(vmstat_work, cpu); INIT_DELAYED_WORK_DEFERRABLE(vmstat_work, vmstat_update); - schedule_delayed_work_on(cpu, vmstat_work, HZ + cpu); + schedule_delayed_work_on(cpu, vmstat_work, + __round_jiffies_relative(HZ, cpu)); } /* |