diff options
author | Tejun Heo <tj@kernel.org> | 2011-11-28 17:46:22 (GMT) |
---|---|---|
committer | Tejun Heo <tj@kernel.org> | 2011-11-28 17:46:22 (GMT) |
commit | d4bbf7e7759afc172e2bfbc5c416324590049cdd (patch) | |
tree | 7eab5ee5481cd3dcf1162329fec827177640018a /mm | |
parent | a150439c4a97db379f0ed6faa46fbbb6e7bf3cb2 (diff) | |
parent | 401d0069cb344f401bc9d264c31db55876ff78c0 (diff) | |
download | linux-d4bbf7e7759afc172e2bfbc5c416324590049cdd.tar.xz |
Merge branch 'master' into x86/memblock
Conflicts & resolutions:
* arch/x86/xen/setup.c
dc91c728fd "xen: allow extra memory to be in multiple regions"
24aa07882b "memblock, x86: Replace memblock_x86_reserve/free..."
conflicted on xen_add_extra_mem() updates. The resolution is
trivial as the latter just want to replace
memblock_x86_reserve_range() with memblock_reserve().
* drivers/pci/intel-iommu.c
166e9278a3f "x86/ia64: intel-iommu: move to drivers/iommu/"
5dfe8660a3d "bootmem: Replace work_with_active_regions() with..."
conflicted as the former moved the file under drivers/iommu/.
Resolved by applying the chnages from the latter on the moved
file.
* mm/Kconfig
6661672053a "memblock: add NO_BOOTMEM config symbol"
c378ddd53f9 "memblock, x86: Make ARCH_DISCARD_MEMBLOCK a config option"
conflicted trivially. Both added config options. Just
letting both add their own options resolves the conflict.
* mm/memblock.c
d1f0ece6cdc "mm/memblock.c: small function definition fixes"
ed7b56a799c "memblock: Remove memblock_memory_can_coalesce()"
confliected. The former updates function removed by the
latter. Resolution is trivial.
Signed-off-by: Tejun Heo <tj@kernel.org>
Diffstat (limited to 'mm')
63 files changed, 5101 insertions, 3349 deletions
@@ -137,6 +137,9 @@ config HAVE_MEMBLOCK_NODE_MAP config ARCH_DISCARD_MEMBLOCK boolean +config NO_BOOTMEM + boolean + # eventually, we can have this option just 'select SPARSEMEM' config MEMORY_HOTPLUG bool "Allow for memory hot-add" @@ -362,7 +365,7 @@ config CLEANCACHE for clean pages that the kernel's pageframe replacement algorithm (PFRA) would like to keep around, but can't since there isn't enough memory. So when the PFRA "evicts" a page, it first attempts to use - cleancacne code to put the data contained in that page into + cleancache code to put the data contained in that page into "transcendent memory", memory that is not directly accessible or addressable by the kernel and is of unknown and possibly time-varying size. And when a cleancache-enabled diff --git a/mm/Makefile b/mm/Makefile index 836e416..50ec00e 100644 --- a/mm/Makefile +++ b/mm/Makefile @@ -5,7 +5,8 @@ mmu-y := nommu.o mmu-$(CONFIG_MMU) := fremap.o highmem.o madvise.o memory.o mincore.o \ mlock.o mmap.o mprotect.o mremap.o msync.o rmap.o \ - vmalloc.o pagewalk.o pgtable-generic.o + vmalloc.o pagewalk.o pgtable-generic.o \ + process_vm_access.o obj-y := filemap.o mempool.o oom_kill.o fadvise.o \ maccess.o page_alloc.o page-writeback.o \ diff --git a/mm/backing-dev.c b/mm/backing-dev.c index f032e6e..71034f4 100644 --- a/mm/backing-dev.c +++ b/mm/backing-dev.c @@ -45,6 +45,17 @@ static struct timer_list sync_supers_timer; static int bdi_sync_supers(void *); static void sync_supers_timer_fn(unsigned long); +void bdi_lock_two(struct bdi_writeback *wb1, struct bdi_writeback *wb2) +{ + if (wb1 < wb2) { + spin_lock(&wb1->list_lock); + spin_lock_nested(&wb2->list_lock, 1); + } else { + spin_lock(&wb2->list_lock); + spin_lock_nested(&wb1->list_lock, 1); + } +} + #ifdef CONFIG_DEBUG_FS #include <linux/debugfs.h> #include <linux/seq_file.h> @@ -67,34 +78,44 @@ static int bdi_debug_stats_show(struct seq_file *m, void *v) struct inode *inode; nr_dirty = nr_io = nr_more_io = 0; - spin_lock(&inode_wb_list_lock); + spin_lock(&wb->list_lock); list_for_each_entry(inode, &wb->b_dirty, i_wb_list) nr_dirty++; list_for_each_entry(inode, &wb->b_io, i_wb_list) nr_io++; list_for_each_entry(inode, &wb->b_more_io, i_wb_list) nr_more_io++; - spin_unlock(&inode_wb_list_lock); + spin_unlock(&wb->list_lock); global_dirty_limits(&background_thresh, &dirty_thresh); bdi_thresh = bdi_dirty_limit(bdi, dirty_thresh); #define K(x) ((x) << (PAGE_SHIFT - 10)) seq_printf(m, - "BdiWriteback: %8lu kB\n" - "BdiReclaimable: %8lu kB\n" - "BdiDirtyThresh: %8lu kB\n" - "DirtyThresh: %8lu kB\n" - "BackgroundThresh: %8lu kB\n" - "b_dirty: %8lu\n" - "b_io: %8lu\n" - "b_more_io: %8lu\n" - "bdi_list: %8u\n" - "state: %8lx\n", + "BdiWriteback: %10lu kB\n" + "BdiReclaimable: %10lu kB\n" + "BdiDirtyThresh: %10lu kB\n" + "DirtyThresh: %10lu kB\n" + "BackgroundThresh: %10lu kB\n" + "BdiDirtied: %10lu kB\n" + "BdiWritten: %10lu kB\n" + "BdiWriteBandwidth: %10lu kBps\n" + "b_dirty: %10lu\n" + "b_io: %10lu\n" + "b_more_io: %10lu\n" + "bdi_list: %10u\n" + "state: %10lx\n", (unsigned long) K(bdi_stat(bdi, BDI_WRITEBACK)), (unsigned long) K(bdi_stat(bdi, BDI_RECLAIMABLE)), - K(bdi_thresh), K(dirty_thresh), - K(background_thresh), nr_dirty, nr_io, nr_more_io, + K(bdi_thresh), + K(dirty_thresh), + K(background_thresh), + (unsigned long) K(bdi_stat(bdi, BDI_DIRTIED)), + (unsigned long) K(bdi_stat(bdi, BDI_WRITTEN)), + (unsigned long) K(bdi->write_bandwidth), + nr_dirty, + nr_io, + nr_more_io, !list_empty(&bdi->bdi_list), bdi->state); #undef K @@ -249,18 +270,6 @@ int bdi_has_dirty_io(struct backing_dev_info *bdi) return wb_has_dirty_io(&bdi->wb); } -static void bdi_flush_io(struct backing_dev_info *bdi) -{ - struct writeback_control wbc = { - .sync_mode = WB_SYNC_NONE, - .older_than_this = NULL, - .range_cyclic = 1, - .nr_to_write = 1024, - }; - - writeback_inodes_wb(&bdi->wb, &wbc); -} - /* * kupdated() used to do this. We cannot do it from the bdi_forker_thread() * or we risk deadlocking on ->s_umount. The longer term solution would be @@ -352,6 +361,17 @@ static unsigned long bdi_longest_inactive(void) return max(5UL * 60 * HZ, interval); } +/* + * Clear pending bit and wakeup anybody waiting for flusher thread creation or + * shutdown + */ +static void bdi_clear_pending(struct backing_dev_info *bdi) +{ + clear_bit(BDI_pending, &bdi->state); + smp_mb__after_clear_bit(); + wake_up_bit(&bdi->state, BDI_pending); +} + static int bdi_forker_thread(void *ptr) { struct bdi_writeback *me = ptr; @@ -383,6 +403,12 @@ static int bdi_forker_thread(void *ptr) } spin_lock_bh(&bdi_lock); + /* + * In the following loop we are going to check whether we have + * some work to do without any synchronization with tasks + * waking us up to do work for them. Set the task state here + * so that we don't miss wakeups after verifying conditions. + */ set_current_state(TASK_INTERRUPTIBLE); list_for_each_entry(bdi, &bdi_list, bdi_list) { @@ -446,9 +472,11 @@ static int bdi_forker_thread(void *ptr) if (IS_ERR(task)) { /* * If thread creation fails, force writeout of - * the bdi from the thread. + * the bdi from the thread. Hopefully 1024 is + * large enough for efficient IO. */ - bdi_flush_io(bdi); + writeback_inodes_wb(&bdi->wb, 1024, + WB_REASON_FORKER_THREAD); } else { /* * The spinlock makes sure we do not lose @@ -461,11 +489,13 @@ static int bdi_forker_thread(void *ptr) spin_unlock_bh(&bdi->wb_lock); wake_up_process(task); } + bdi_clear_pending(bdi); break; case KILL_THREAD: __set_current_state(TASK_RUNNING); kthread_stop(task); + bdi_clear_pending(bdi); break; case NO_ACTION: @@ -481,16 +511,8 @@ static int bdi_forker_thread(void *ptr) else schedule_timeout(msecs_to_jiffies(dirty_writeback_interval * 10)); try_to_freeze(); - /* Back to the main loop */ - continue; + break; } - - /* - * Clear pending bit and wakeup anybody waiting to tear us down. - */ - clear_bit(BDI_pending, &bdi->state); - smp_mb__after_clear_bit(); - wake_up_bit(&bdi->state, BDI_pending); } return 0; @@ -505,7 +527,7 @@ static void bdi_remove_from_list(struct backing_dev_info *bdi) list_del_rcu(&bdi->bdi_list); spin_unlock_bh(&bdi_lock); - synchronize_rcu(); + synchronize_rcu_expedited(); } int bdi_register(struct backing_dev_info *bdi, struct device *parent, @@ -606,6 +628,7 @@ static void bdi_prune_sb(struct backing_dev_info *bdi) void bdi_unregister(struct backing_dev_info *bdi) { if (bdi->dev) { + bdi_set_min_ratio(bdi, 0); trace_writeback_bdi_unregister(bdi); bdi_prune_sb(bdi); del_timer_sync(&bdi->wb.wakeup_timer); @@ -628,9 +651,15 @@ static void bdi_wb_init(struct bdi_writeback *wb, struct backing_dev_info *bdi) INIT_LIST_HEAD(&wb->b_dirty); INIT_LIST_HEAD(&wb->b_io); INIT_LIST_HEAD(&wb->b_more_io); + spin_lock_init(&wb->list_lock); setup_timer(&wb->wakeup_timer, wakeup_timer_fn, (unsigned long)bdi); } +/* + * Initial write bandwidth: 100 MB/s + */ +#define INIT_BW (100 << (20 - PAGE_SHIFT)) + int bdi_init(struct backing_dev_info *bdi) { int i, err; @@ -653,6 +682,15 @@ int bdi_init(struct backing_dev_info *bdi) } bdi->dirty_exceeded = 0; + + bdi->bw_time_stamp = jiffies; + bdi->written_stamp = 0; + + bdi->balanced_dirty_ratelimit = INIT_BW; + bdi->dirty_ratelimit = INIT_BW; + bdi->write_bandwidth = INIT_BW; + bdi->avg_write_bandwidth = INIT_BW; + err = prop_local_init_percpu(&bdi->completions); if (err) { @@ -676,15 +714,24 @@ void bdi_destroy(struct backing_dev_info *bdi) if (bdi_has_dirty_io(bdi)) { struct bdi_writeback *dst = &default_backing_dev_info.wb; - spin_lock(&inode_wb_list_lock); + bdi_lock_two(&bdi->wb, dst); list_splice(&bdi->wb.b_dirty, &dst->b_dirty); list_splice(&bdi->wb.b_io, &dst->b_io); list_splice(&bdi->wb.b_more_io, &dst->b_more_io); - spin_unlock(&inode_wb_list_lock); + spin_unlock(&bdi->wb.list_lock); + spin_unlock(&dst->list_lock); } bdi_unregister(bdi); + /* + * If bdi_unregister() had already been called earlier, the + * wakeup_timer could still be armed because bdi_prune_sb() + * can race with the bdi_wakeup_thread_delayed() calls from + * __mark_inode_dirty(). + */ + del_timer_sync(&bdi->wb.wakeup_timer); + for (i = 0; i < NR_BDI_STAT_ITEMS; i++) percpu_counter_destroy(&bdi->bdi_stat[i]); diff --git a/mm/bootmem.c b/mm/bootmem.c index 01d5a4b3..1a77012 100644 --- a/mm/bootmem.c +++ b/mm/bootmem.c @@ -12,7 +12,7 @@ #include <linux/pfn.h> #include <linux/slab.h> #include <linux/bootmem.h> -#include <linux/module.h> +#include <linux/export.h> #include <linux/kmemleak.h> #include <linux/range.h> #include <linux/memblock.h> diff --git a/mm/bounce.c b/mm/bounce.c index 1481de6..4e9ae72 100644 --- a/mm/bounce.c +++ b/mm/bounce.c @@ -4,7 +4,7 @@ */ #include <linux/mm.h> -#include <linux/module.h> +#include <linux/export.h> #include <linux/swap.h> #include <linux/gfp.h> #include <linux/bio.h> @@ -14,6 +14,7 @@ #include <linux/init.h> #include <linux/hash.h> #include <linux/highmem.h> +#include <linux/bootmem.h> #include <asm/tlbflush.h> #include <trace/events/block.h> @@ -26,12 +27,10 @@ static mempool_t *page_pool, *isa_page_pool; #ifdef CONFIG_HIGHMEM static __init int init_emergency_pool(void) { - struct sysinfo i; - si_meminfo(&i); - si_swapinfo(&i); - - if (!i.totalhigh) +#ifndef CONFIG_MEMORY_HOTPLUG + if (max_pfn <= max_low_pfn) return 0; +#endif page_pool = mempool_create_page_pool(POOL_SIZE, 0); BUG_ON(!page_pool); diff --git a/mm/compaction.c b/mm/compaction.c index 6cc604b..899d956 100644 --- a/mm/compaction.c +++ b/mm/compaction.c @@ -35,10 +35,6 @@ struct compact_control { unsigned long migrate_pfn; /* isolate_migratepages search base */ bool sync; /* Synchronous migration */ - /* Account for isolated anon and file pages */ - unsigned long nr_anon; - unsigned long nr_file; - unsigned int order; /* order a direct compactor needs */ int migratetype; /* MOVABLE, RECLAIMABLE etc */ struct zone *zone; @@ -223,17 +219,13 @@ static void isolate_freepages(struct zone *zone, static void acct_isolated(struct zone *zone, struct compact_control *cc) { struct page *page; - unsigned int count[NR_LRU_LISTS] = { 0, }; + unsigned int count[2] = { 0, }; - list_for_each_entry(page, &cc->migratepages, lru) { - int lru = page_lru_base_type(page); - count[lru]++; - } + list_for_each_entry(page, &cc->migratepages, lru) + count[!!page_is_file_cache(page)]++; - cc->nr_anon = count[LRU_ACTIVE_ANON] + count[LRU_INACTIVE_ANON]; - cc->nr_file = count[LRU_ACTIVE_FILE] + count[LRU_INACTIVE_FILE]; - __mod_zone_page_state(zone, NR_ISOLATED_ANON, cc->nr_anon); - __mod_zone_page_state(zone, NR_ISOLATED_FILE, cc->nr_file); + __mod_zone_page_state(zone, NR_ISOLATED_ANON, count[0]); + __mod_zone_page_state(zone, NR_ISOLATED_FILE, count[1]); } /* Similar to reclaim, but different enough that they don't share logic */ @@ -269,6 +261,7 @@ static isolate_migrate_t isolate_migratepages(struct zone *zone, unsigned long last_pageblock_nr = 0, pageblock_nr; unsigned long nr_scanned = 0, nr_isolated = 0; struct list_head *migratelist = &cc->migratepages; + isolate_mode_t mode = ISOLATE_ACTIVE|ISOLATE_INACTIVE; /* Do not scan outside zone boundaries */ low_pfn = max(cc->migrate_pfn, zone->zone_start_pfn); @@ -356,8 +349,11 @@ static isolate_migrate_t isolate_migratepages(struct zone *zone, continue; } + if (!cc->sync) + mode |= ISOLATE_CLEAN; + /* Try isolate the page */ - if (__isolate_lru_page(page, ISOLATE_BOTH, 0) != 0) + if (__isolate_lru_page(page, mode, 0) != 0) continue; VM_BUG_ON(PageTransCompound(page)); @@ -586,7 +582,7 @@ out: return ret; } -unsigned long compact_zone_order(struct zone *zone, +static unsigned long compact_zone_order(struct zone *zone, int order, gfp_t gfp_mask, bool sync) { diff --git a/mm/debug-pagealloc.c b/mm/debug-pagealloc.c index a1e3324..7cea557 100644 --- a/mm/debug-pagealloc.c +++ b/mm/debug-pagealloc.c @@ -1,7 +1,10 @@ #include <linux/kernel.h> +#include <linux/string.h> #include <linux/mm.h> +#include <linux/highmem.h> #include <linux/page-debug-flags.h> #include <linux/poison.h> +#include <linux/ratelimit.h> static inline void set_page_poison(struct page *page) { @@ -18,28 +21,13 @@ 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; + void *addr = kmap_atomic(page); - if (PageHighMem(page)) { - poison_highpage(page); - return; - } set_page_poison(page); - addr = page_address(page); memset(addr, PAGE_POISON, PAGE_SIZE); + kunmap_atomic(addr); } static void poison_pages(struct page *page, int n) @@ -59,14 +47,12 @@ static bool single_bit_flip(unsigned char a, unsigned char b) static void check_poison_mem(unsigned char *mem, size_t bytes) { + static DEFINE_RATELIMIT_STATE(ratelimit, 5 * HZ, 10); unsigned char *start; unsigned char *end; - for (start = mem; start < mem + bytes; start++) { - if (*start != PAGE_POISON) - break; - } - if (start == mem + bytes) + start = memchr_inv(mem, PAGE_POISON, bytes); + if (!start) return; for (end = mem + bytes - 1; end > start; end--) { @@ -74,7 +60,7 @@ static void check_poison_mem(unsigned char *mem, size_t bytes) break; } - if (!printk_ratelimit()) + if (!__ratelimit(&ratelimit)) return; else if (start == end && single_bit_flip(*start, PAGE_POISON)) printk(KERN_ERR "pagealloc: single bit error\n"); @@ -86,27 +72,17 @@ static void check_poison_mem(unsigned char *mem, size_t bytes) 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); + void *addr; + + if (!page_poison(page)) return; - } - if (page_poison(page)) { - void *addr = page_address(page); - check_poison_mem(addr, PAGE_SIZE); - clear_page_poison(page); - } + addr = kmap_atomic(page); + check_poison_mem(addr, PAGE_SIZE); + clear_page_poison(page); + kunmap_atomic(addr); } static void unpoison_pages(struct page *page, int n) diff --git a/mm/dmapool.c b/mm/dmapool.c index 03bf3bb..c5ab33b 100644 --- a/mm/dmapool.c +++ b/mm/dmapool.c @@ -27,11 +27,12 @@ #include <linux/dmapool.h> #include <linux/kernel.h> #include <linux/list.h> -#include <linux/module.h> +#include <linux/export.h> #include <linux/mutex.h> #include <linux/poison.h> #include <linux/sched.h> #include <linux/slab.h> +#include <linux/stat.h> #include <linux/spinlock.h> #include <linux/string.h> #include <linux/types.h> @@ -500,7 +501,7 @@ void dmam_pool_destroy(struct dma_pool *pool) { struct device *dev = pool->dev; - dma_pool_destroy(pool); WARN_ON(devres_destroy(dev, dmam_pool_release, dmam_pool_match, pool)); + dma_pool_destroy(pool); } EXPORT_SYMBOL(dmam_pool_destroy); diff --git a/mm/failslab.c b/mm/failslab.c index c5f88f2..0dd7b8f 100644 --- a/mm/failslab.c +++ b/mm/failslab.c @@ -5,10 +5,6 @@ static struct { struct fault_attr attr; u32 ignore_gfp_wait; int cache_filter; -#ifdef CONFIG_FAULT_INJECTION_DEBUG_FS - struct dentry *ignore_gfp_wait_file; - struct dentry *cache_filter_file; -#endif } failslab = { .attr = FAULT_ATTR_INITIALIZER, .ignore_gfp_wait = 1, @@ -38,32 +34,25 @@ __setup("failslab=", setup_failslab); #ifdef CONFIG_FAULT_INJECTION_DEBUG_FS static int __init failslab_debugfs_init(void) { - mode_t mode = S_IFREG | S_IRUSR | S_IWUSR; struct dentry *dir; - int err; - - err = init_fault_attr_dentries(&failslab.attr, "failslab"); - if (err) - return err; - dir = failslab.attr.dentries.dir; + mode_t mode = S_IFREG | S_IRUSR | S_IWUSR; - failslab.ignore_gfp_wait_file = - debugfs_create_bool("ignore-gfp-wait", mode, dir, - &failslab.ignore_gfp_wait); + dir = fault_create_debugfs_attr("failslab", NULL, &failslab.attr); + if (IS_ERR(dir)) + return PTR_ERR(dir); - failslab.cache_filter_file = - debugfs_create_bool("cache-filter", mode, dir, - &failslab.cache_filter); + if (!debugfs_create_bool("ignore-gfp-wait", mode, dir, + &failslab.ignore_gfp_wait)) + goto fail; + if (!debugfs_create_bool("cache-filter", mode, dir, + &failslab.cache_filter)) + goto fail; - if (!failslab.ignore_gfp_wait_file || - !failslab.cache_filter_file) { - err = -ENOMEM; - debugfs_remove(failslab.cache_filter_file); - debugfs_remove(failslab.ignore_gfp_wait_file); - cleanup_fault_attr_dentries(&failslab.attr); - } + return 0; +fail: + debugfs_remove_recursive(dir); - return err; + return -ENOMEM; } late_initcall(failslab_debugfs_init); diff --git a/mm/filemap.c b/mm/filemap.c index a8251a8..c0018f2 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -9,7 +9,7 @@ * most "normal" filesystems (but you don't /have/ to use this: * the NFS filesystem used to do this differently, for example) */ -#include <linux/module.h> +#include <linux/export.h> #include <linux/compiler.h> #include <linux/fs.h> #include <linux/uaccess.h> @@ -33,7 +33,6 @@ #include <linux/cpuset.h> #include <linux/hardirq.h> /* for BUG_ON(!in_atomic()) only */ #include <linux/memcontrol.h> -#include <linux/mm_inline.h> /* for page_is_file_cache() */ #include <linux/cleancache.h> #include "internal.h" @@ -78,10 +77,7 @@ * ->i_mutex (generic_file_buffered_write) * ->mmap_sem (fault_in_pages_readable->do_page_fault) * - * ->i_mutex - * ->i_alloc_sem (various) - * - * inode_wb_list_lock + * bdi->wb.list_lock * sb_lock (fs/fs-writeback.c) * ->mapping->tree_lock (__sync_single_inode) * @@ -99,9 +95,9 @@ * ->zone.lru_lock (check_pte_range->isolate_lru_page) * ->private_lock (page_remove_rmap->set_page_dirty) * ->tree_lock (page_remove_rmap->set_page_dirty) - * inode_wb_list_lock (page_remove_rmap->set_page_dirty) + * bdi.wb->list_lock (page_remove_rmap->set_page_dirty) * ->inode->i_lock (page_remove_rmap->set_page_dirty) - * inode_wb_list_lock (zap_pte_range->set_page_dirty) + * bdi.wb->list_lock (zap_pte_range->set_page_dirty) * ->inode->i_lock (zap_pte_range->set_page_dirty) * ->private_lock (zap_pte_range->__set_page_dirty_buffers) * @@ -131,6 +127,7 @@ void __delete_from_page_cache(struct page *page) radix_tree_delete(&mapping->page_tree, page->index); page->mapping = NULL; + /* Leave page->index set: truncation lookup relies upon it */ mapping->nrpages--; __dec_zone_page_state(page, NR_FILE_PAGES); if (PageSwapBacked(page)) @@ -464,6 +461,7 @@ int add_to_page_cache_locked(struct page *page, struct address_space *mapping, int error; VM_BUG_ON(!PageLocked(page)); + VM_BUG_ON(PageSwapBacked(page)); error = mem_cgroup_cache_charge(page, current->mm, gfp_mask & GFP_RECLAIM_MASK); @@ -481,11 +479,10 @@ int add_to_page_cache_locked(struct page *page, struct address_space *mapping, if (likely(!error)) { mapping->nrpages++; __inc_zone_page_state(page, NR_FILE_PAGES); - if (PageSwapBacked(page)) - __inc_zone_page_state(page, NR_SHMEM); spin_unlock_irq(&mapping->tree_lock); } else { page->mapping = NULL; + /* Leave page->index set: truncation relies upon it */ spin_unlock_irq(&mapping->tree_lock); mem_cgroup_uncharge_cache_page(page); page_cache_release(page); @@ -503,22 +500,9 @@ int add_to_page_cache_lru(struct page *page, struct address_space *mapping, { int ret; - /* - * Splice_read and readahead add shmem/tmpfs pages into the page cache - * before shmem_readpage has a chance to mark them as SwapBacked: they - * need to go on the anon lru below, and mem_cgroup_cache_charge - * (called in add_to_page_cache) needs to know where they're going too. - */ - if (mapping_cap_swap_backed(mapping)) - SetPageSwapBacked(page); - ret = add_to_page_cache(page, mapping, offset, gfp_mask); - if (ret == 0) { - if (page_is_file_cache(page)) - lru_cache_add_file(page); - else - lru_cache_add_anon(page); - } + if (ret == 0) + lru_cache_add_file(page); return ret; } EXPORT_SYMBOL_GPL(add_to_page_cache_lru); @@ -715,9 +699,16 @@ repeat: page = radix_tree_deref_slot(pagep); if (unlikely(!page)) goto out; - if (radix_tree_deref_retry(page)) - goto repeat; - + if (radix_tree_exception(page)) { + if (radix_tree_deref_retry(page)) + goto repeat; + /* + * Otherwise, shmem/tmpfs must be storing a swap entry + * here as an exceptional entry: so return it without + * attempting to raise page count. + */ + goto out; + } if (!page_cache_get_speculative(page)) goto repeat; @@ -754,7 +745,7 @@ struct page *find_lock_page(struct address_space *mapping, pgoff_t offset) repeat: page = find_get_page(mapping, offset); - if (page) { + if (page && !radix_tree_exception(page)) { lock_page(page); /* Has the page been truncated? */ if (unlikely(page->mapping != mapping)) { @@ -836,13 +827,14 @@ unsigned find_get_pages(struct address_space *mapping, pgoff_t start, { unsigned int i; unsigned int ret; - unsigned int nr_found; + unsigned int nr_found, nr_skip; rcu_read_lock(); restart: nr_found = radix_tree_gang_lookup_slot(&mapping->page_tree, - (void ***)pages, start, nr_pages); + (void ***)pages, NULL, start, nr_pages); ret = 0; + nr_skip = 0; for (i = 0; i < nr_found; i++) { struct page *page; repeat: @@ -850,13 +842,23 @@ repeat: if (unlikely(!page)) continue; - /* - * This can only trigger when the entry at index 0 moves out - * of or back to the root: none yet gotten, safe to restart. - */ - if (radix_tree_deref_retry(page)) { - WARN_ON(start | i); - goto restart; + if (radix_tree_exception(page)) { + if (radix_tree_deref_retry(page)) { + /* + * Transient condition which can only trigger + * when entry at index 0 moves out of or back + * to root: none yet gotten, safe to restart. + */ + WARN_ON(start | i); + goto restart; + } + /* + * Otherwise, shmem/tmpfs must be storing a swap entry + * here as an exceptional entry: so skip over it - + * we only reach this from invalidate_mapping_pages(). + */ + nr_skip++; + continue; } if (!page_cache_get_speculative(page)) @@ -876,7 +878,7 @@ repeat: * If all entries were removed before we could secure them, * try again, because callers stop trying once 0 is returned. */ - if (unlikely(!ret && nr_found)) + if (unlikely(!ret && nr_found > nr_skip)) goto restart; rcu_read_unlock(); return ret; @@ -904,7 +906,7 @@ unsigned find_get_pages_contig(struct address_space *mapping, pgoff_t index, rcu_read_lock(); restart: nr_found = radix_tree_gang_lookup_slot(&mapping->page_tree, - (void ***)pages, index, nr_pages); + (void ***)pages, NULL, index, nr_pages); ret = 0; for (i = 0; i < nr_found; i++) { struct page *page; @@ -913,12 +915,22 @@ repeat: if (unlikely(!page)) continue; - /* - * This can only trigger when the entry at index 0 moves out - * of or back to the root: none yet gotten, safe to restart. - */ - if (radix_tree_deref_retry(page)) - goto restart; + if (radix_tree_exception(page)) { + if (radix_tree_deref_retry(page)) { + /* + * Transient condition which can only trigger + * when entry at index 0 moves out of or back + * to root: none yet gotten, safe to restart. + */ + goto restart; + } + /* + * Otherwise, shmem/tmpfs must be storing a swap entry + * here as an exceptional entry: so stop looking for + * contiguous pages. + */ + break; + } if (!page_cache_get_speculative(page)) goto repeat; @@ -978,12 +990,21 @@ repeat: if (unlikely(!page)) continue; - /* - * This can only trigger when the entry at index 0 moves out - * of or back to the root: none yet gotten, safe to restart. - */ - if (radix_tree_deref_retry(page)) - goto restart; + if (radix_tree_exception(page)) { + if (radix_tree_deref_retry(page)) { + /* + * Transient condition which can only trigger + * when entry at index 0 moves out of or back + * to root: none yet gotten, safe to restart. + */ + goto restart; + } + /* + * This function is never used on a shmem/tmpfs + * mapping, so a swap entry won't be found here. + */ + BUG(); + } if (!page_cache_get_speculative(page)) goto repeat; @@ -1795,7 +1816,7 @@ EXPORT_SYMBOL(generic_file_readonly_mmap); static struct page *__read_cache_page(struct address_space *mapping, pgoff_t index, - int (*filler)(void *,struct page*), + int (*filler)(void *, struct page *), void *data, gfp_t gfp) { @@ -1826,7 +1847,7 @@ repeat: static struct page *do_read_cache_page(struct address_space *mapping, pgoff_t index, - int (*filler)(void *,struct page*), + int (*filler)(void *, struct page *), void *data, gfp_t gfp) @@ -1866,7 +1887,7 @@ out: * @mapping: the page's address_space * @index: the page index * @filler: function to perform the read - * @data: destination for read data + * @data: first arg to filler(data, page) function, often left as NULL * * Same as read_cache_page, but don't wait for page to become unlocked * after submitting it to the filler. @@ -1878,7 +1899,7 @@ out: */ struct page *read_cache_page_async(struct address_space *mapping, pgoff_t index, - int (*filler)(void *,struct page*), + int (*filler)(void *, struct page *), void *data) { return do_read_cache_page(mapping, index, filler, data, mapping_gfp_mask(mapping)); @@ -1926,7 +1947,7 @@ EXPORT_SYMBOL(read_cache_page_gfp); * @mapping: the page's address_space * @index: the page index * @filler: function to perform the read - * @data: destination for read data + * @data: first arg to filler(data, page) function, often left as NULL * * Read into the page cache. If a page already exists, and PageUptodate() is * not set, try to fill the page then wait for it to become unlocked. @@ -1935,7 +1956,7 @@ EXPORT_SYMBOL(read_cache_page_gfp); */ struct page *read_cache_page(struct address_space *mapping, pgoff_t index, - int (*filler)(void *,struct page*), + int (*filler)(void *, struct page *), void *data) { return wait_on_page_read(read_cache_page_async(mapping, index, filler, data)); @@ -2094,6 +2115,7 @@ void iov_iter_advance(struct iov_iter *i, size_t bytes) } else { const struct iovec *iov = i->iov; size_t base = i->iov_offset; + unsigned long nr_segs = i->nr_segs; /* * The !iov->iov_len check ensures we skip over unlikely @@ -2109,11 +2131,13 @@ void iov_iter_advance(struct iov_iter *i, size_t bytes) base += copy; if (iov->iov_len == base) { iov++; + nr_segs--; base = 0; } } i->iov = iov; i->iov_offset = base; + i->nr_segs = nr_segs; } } EXPORT_SYMBOL(iov_iter_advance); diff --git a/mm/filemap_xip.c b/mm/filemap_xip.c index 93356cd..f91b2f6 100644 --- a/mm/filemap_xip.c +++ b/mm/filemap_xip.c @@ -10,7 +10,7 @@ #include <linux/fs.h> #include <linux/pagemap.h> -#include <linux/module.h> +#include <linux/export.h> #include <linux/uio.h> #include <linux/rmap.h> #include <linux/mmu_notifier.h> diff --git a/mm/fremap.c b/mm/fremap.c index b8e0e2d..9ed4fd4 100644 --- a/mm/fremap.c +++ b/mm/fremap.c @@ -13,7 +13,6 @@ #include <linux/pagemap.h> #include <linux/swapops.h> #include <linux/rmap.h> -#include <linux/module.h> #include <linux/syscalls.h> #include <linux/mmu_notifier.h> diff --git a/mm/highmem.c b/mm/highmem.c index 693394d..57d82c6 100644 --- a/mm/highmem.c +++ b/mm/highmem.c @@ -17,7 +17,7 @@ */ #include <linux/mm.h> -#include <linux/module.h> +#include <linux/export.h> #include <linux/swap.h> #include <linux/bio.h> #include <linux/pagemap.h> @@ -250,7 +250,7 @@ void *kmap_high_get(struct page *page) #endif /** - * kunmap_high - map a highmem page into memory + * kunmap_high - unmap a highmem page into memory * @page: &struct page to unmap * * If ARCH_NEEDS_KMAP_HIGH_GET is not defined then this may be called @@ -326,7 +326,7 @@ static struct page_address_slot { spinlock_t lock; /* Protect this bucket's list */ } ____cacheline_aligned_in_smp page_address_htable[1<<PA_HASH_ORDER]; -static struct page_address_slot *page_slot(struct page *page) +static struct page_address_slot *page_slot(const struct page *page) { return &page_address_htable[hash_ptr(page, PA_HASH_ORDER)]; } @@ -337,7 +337,7 @@ static struct page_address_slot *page_slot(struct page *page) * * Returns the page's virtual address. */ -void *page_address(struct page *page) +void *page_address(const struct page *page) { unsigned long flags; void *ret; diff --git a/mm/huge_memory.c b/mm/huge_memory.c index 81532f2..4298aba 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -89,7 +89,8 @@ struct khugepaged_scan { struct list_head mm_head; struct mm_slot *mm_slot; unsigned long address; -} khugepaged_scan = { +}; +static struct khugepaged_scan khugepaged_scan = { .mm_head = LIST_HEAD_INIT(khugepaged_scan.mm_head), }; @@ -829,7 +830,7 @@ static int do_huge_pmd_wp_page_fallback(struct mm_struct *mm, for (i = 0; i < HPAGE_PMD_NR; i++) { copy_user_highpage(pages[i], page + i, - haddr + PAGE_SHIFT*i, vma); + haddr + PAGE_SIZE * i, vma); __SetPageUptodate(pages[i]); cond_resched(); } @@ -989,7 +990,7 @@ struct page *follow_trans_huge_pmd(struct mm_struct *mm, page += (addr & ~HPAGE_PMD_MASK) >> PAGE_SHIFT; VM_BUG_ON(!PageCompound(page)); if (flags & FOLL_GET) - get_page(page); + get_page_foll(page); out: return page; @@ -1052,6 +1053,51 @@ int mincore_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd, return ret; } +int move_huge_pmd(struct vm_area_struct *vma, struct vm_area_struct *new_vma, + unsigned long old_addr, + unsigned long new_addr, unsigned long old_end, + pmd_t *old_pmd, pmd_t *new_pmd) +{ + int ret = 0; + pmd_t pmd; + + struct mm_struct *mm = vma->vm_mm; + + if ((old_addr & ~HPAGE_PMD_MASK) || + (new_addr & ~HPAGE_PMD_MASK) || + old_end - old_addr < HPAGE_PMD_SIZE || + (new_vma->vm_flags & VM_NOHUGEPAGE)) + goto out; + + /* + * The destination pmd shouldn't be established, free_pgtables() + * should have release it. + */ + if (WARN_ON(!pmd_none(*new_pmd))) { + VM_BUG_ON(pmd_trans_huge(*new_pmd)); + goto out; + } + + spin_lock(&mm->page_table_lock); + if (likely(pmd_trans_huge(*old_pmd))) { + if (pmd_trans_splitting(*old_pmd)) { + spin_unlock(&mm->page_table_lock); + wait_split_huge_page(vma->anon_vma, old_pmd); + ret = -1; + } else { + pmd = pmdp_get_and_clear(mm, old_addr, old_pmd); + VM_BUG_ON(!pmd_none(*new_pmd)); + set_pmd_at(mm, new_addr, new_pmd, pmd); + spin_unlock(&mm->page_table_lock); + ret = 1; + } + } else { + spin_unlock(&mm->page_table_lock); + } +out: + return ret; +} + int change_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd, unsigned long addr, pgprot_t newprot) { @@ -1156,6 +1202,7 @@ static void __split_huge_page_refcount(struct page *page) unsigned long head_index = page->index; struct zone *zone = page_zone(page); int zonestat; + int tail_count = 0; /* prevent PageLRU to go away from under us, and freeze lru stats */ spin_lock_irq(&zone->lru_lock); @@ -1164,11 +1211,27 @@ static void __split_huge_page_refcount(struct page *page) for (i = 1; i < HPAGE_PMD_NR; i++) { struct page *page_tail = page + i; - /* tail_page->_count cannot change */ - atomic_sub(atomic_read(&page_tail->_count), &page->_count); - BUG_ON(page_count(page) <= 0); - atomic_add(page_mapcount(page) + 1, &page_tail->_count); - BUG_ON(atomic_read(&page_tail->_count) <= 0); + /* tail_page->_mapcount cannot change */ + BUG_ON(page_mapcount(page_tail) < 0); + tail_count += page_mapcount(page_tail); + /* check for overflow */ + BUG_ON(tail_count < 0); + BUG_ON(atomic_read(&page_tail->_count) != 0); + /* + * tail_page->_count is zero and not changing from + * under us. But get_page_unless_zero() may be running + * from under us on the tail_page. If we used + * atomic_set() below instead of atomic_add(), we + * would then run atomic_set() concurrently with + * get_page_unless_zero(), and atomic_set() is + * implemented in C not using locked ops. spin_unlock + * on x86 sometime uses locked ops because of PPro + * errata 66, 92, so unless somebody can guarantee + * atomic_set() here would be safe on all archs (and + * not only on x86), it's safer to use atomic_add(). + */ + atomic_add(page_mapcount(page) + page_mapcount(page_tail) + 1, + &page_tail->_count); /* after clearing PageTail the gup refcount can be released */ smp_mb(); @@ -1186,10 +1249,7 @@ static void __split_huge_page_refcount(struct page *page) (1L << PG_uptodate))); page_tail->flags |= (1L << PG_dirty); - /* - * 1) clear PageTail before overwriting first_page - * 2) clear PageTail before clearing PageHead for VM_BUG_ON - */ + /* clear PageTail before overwriting first_page */ smp_wmb(); /* @@ -1206,7 +1266,6 @@ static void __split_huge_page_refcount(struct page *page) * status is achieved setting a reserved bit in the * pmd, not by clearing the present bit. */ - BUG_ON(page_mapcount(page_tail)); page_tail->_mapcount = page->_mapcount; BUG_ON(page_tail->mapping); @@ -1223,6 +1282,8 @@ static void __split_huge_page_refcount(struct page *page) lru_add_page_tail(zone, page, page_tail); } + atomic_sub(tail_count, &page->_count); + BUG_ON(atomic_read(&page->_count) <= 0); __dec_zone_page_state(page, NR_ANON_TRANSPARENT_HUGEPAGES); __mod_zone_page_state(zone, NR_ANON_PAGES, HPAGE_PMD_NR); @@ -1596,14 +1657,13 @@ void __khugepaged_exit(struct mm_struct *mm) list_del(&mm_slot->mm_node); free = 1; } + spin_unlock(&khugepaged_mm_lock); if (free) { - spin_unlock(&khugepaged_mm_lock); clear_bit(MMF_VM_HUGEPAGE, &mm->flags); free_mm_slot(mm_slot); mmdrop(mm); } else if (mm_slot) { - spin_unlock(&khugepaged_mm_lock); /* * This is required to serialize against * khugepaged_test_exit() (which is guaranteed to run @@ -1614,8 +1674,7 @@ void __khugepaged_exit(struct mm_struct *mm) */ down_write(&mm->mmap_sem); up_write(&mm->mmap_sem); - } else - spin_unlock(&khugepaged_mm_lock); + } } static void release_pte_page(struct page *page) @@ -1908,7 +1967,7 @@ static void collapse_huge_page(struct mm_struct *mm, BUG_ON(!pmd_none(*pmd)); page_add_new_anon_rmap(new_page, vma, address); set_pmd_at(mm, address, pmd, _pmd); - update_mmu_cache(vma, address, entry); + update_mmu_cache(vma, address, _pmd); prepare_pmd_huge_pte(pgtable, mm); mm->nr_ptes--; spin_unlock(&mm->page_table_lock); @@ -2026,6 +2085,8 @@ static void collect_mm_slot(struct mm_slot *mm_slot) static unsigned int khugepaged_scan_mm_slot(unsigned int pages, struct page **hpage) + __releases(&khugepaged_mm_lock) + __acquires(&khugepaged_mm_lock) { struct mm_slot *mm_slot; struct mm_struct *mm; diff --git a/mm/hugetlb.c b/mm/hugetlb.c index bfcf153..bb28a5f 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -24,7 +24,7 @@ #include <asm/page.h> #include <asm/pgtable.h> -#include <asm/io.h> +#include <linux/io.h> #include <linux/hugetlb.h> #include <linux/node.h> @@ -62,10 +62,10 @@ static DEFINE_SPINLOCK(hugetlb_lock); * must either hold the mmap_sem for write, or the mmap_sem for read and * the hugetlb_instantiation mutex: * - * down_write(&mm->mmap_sem); + * down_write(&mm->mmap_sem); * or - * down_read(&mm->mmap_sem); - * mutex_lock(&hugetlb_instantiation_mutex); + * down_read(&mm->mmap_sem); + * mutex_lock(&hugetlb_instantiation_mutex); */ struct file_region { struct list_head link; @@ -503,9 +503,10 @@ static void update_and_free_page(struct hstate *h, struct page *page) h->nr_huge_pages--; h->nr_huge_pages_node[page_to_nid(page)]--; for (i = 0; i < pages_per_huge_page(h); i++) { - page[i].flags &= ~(1 << PG_locked | 1 << PG_error | 1 << PG_referenced | - 1 << PG_dirty | 1 << PG_active | 1 << PG_reserved | - 1 << PG_private | 1<< PG_writeback); + page[i].flags &= ~(1 << PG_locked | 1 << PG_error | + 1 << PG_referenced | 1 << PG_dirty | + 1 << PG_active | 1 << PG_reserved | + 1 << PG_private | 1 << PG_writeback); } set_compound_page_dtor(page, NULL); set_page_refcounted(page); @@ -591,7 +592,6 @@ int PageHuge(struct page *page) return dtor == free_huge_page; } - EXPORT_SYMBOL_GPL(PageHuge); static struct page *alloc_fresh_huge_page_node(struct hstate *h, int nid) @@ -1105,8 +1105,16 @@ static void __init gather_bootmem_prealloc(void) struct huge_bootmem_page *m; list_for_each_entry(m, &huge_boot_pages, list) { - struct page *page = virt_to_page(m); struct hstate *h = m->hstate; + struct page *page; + +#ifdef CONFIG_HIGHMEM + page = pfn_to_page(m->phys >> PAGE_SHIFT); + free_bootmem_late((unsigned long)m, + sizeof(struct huge_bootmem_page)); +#else + page = virt_to_page(m); +#endif __ClearPageReserved(page); WARN_ON(page_count(page) != 1); prep_compound_huge_page(page, h->order); @@ -2124,9 +2132,8 @@ static void set_huge_ptep_writable(struct vm_area_struct *vma, pte_t entry; entry = pte_mkwrite(pte_mkdirty(huge_ptep_get(ptep))); - if (huge_ptep_set_access_flags(vma, address, ptep, entry, 1)) { + if (huge_ptep_set_access_flags(vma, address, ptep, entry, 1)) update_mmu_cache(vma, address, ptep); - } } @@ -2181,9 +2188,9 @@ static int is_hugetlb_entry_migration(pte_t pte) if (huge_pte_none(pte) || pte_present(pte)) return 0; swp = pte_to_swp_entry(pte); - if (non_swap_entry(swp) && is_migration_entry(swp)) { + if (non_swap_entry(swp) && is_migration_entry(swp)) return 1; - } else + else return 0; } @@ -2194,9 +2201,9 @@ static int is_hugetlb_entry_hwpoisoned(pte_t pte) if (huge_pte_none(pte) || pte_present(pte)) return 0; swp = pte_to_swp_entry(pte); - if (non_swap_entry(swp) && is_hwpoison_entry(swp)) { + if (non_swap_entry(swp) && is_hwpoison_entry(swp)) return 1; - } else + else return 0; } @@ -2415,6 +2422,8 @@ retry_avoidcopy: * anon_vma prepared. */ if (unlikely(anon_vma_prepare(vma))) { + page_cache_release(new_page); + page_cache_release(old_page); /* Caller expects lock to be held */ spin_lock(&mm->page_table_lock); return VM_FAULT_OOM; @@ -2559,7 +2568,7 @@ retry: * So we need to block hugepage fault by PG_hwpoison bit check. */ if (unlikely(PageHWPoison(page))) { - ret = VM_FAULT_HWPOISON | + ret = VM_FAULT_HWPOISON | VM_FAULT_SET_HINDEX(h - hstates); goto backout_unlocked; } @@ -2627,7 +2636,7 @@ int hugetlb_fault(struct mm_struct *mm, struct vm_area_struct *vma, migration_entry_wait(mm, (pmd_t *)ptep, address); return 0; } else if (unlikely(is_hugetlb_entry_hwpoisoned(entry))) - return VM_FAULT_HWPOISON_LARGE | + return VM_FAULT_HWPOISON_LARGE | VM_FAULT_SET_HINDEX(h - hstates); } diff --git a/mm/init-mm.c b/mm/init-mm.c index 4019979..a56a851 100644 --- a/mm/init-mm.c +++ b/mm/init-mm.c @@ -5,7 +5,7 @@ #include <linux/list.h> #include <linux/cpumask.h> -#include <asm/atomic.h> +#include <linux/atomic.h> #include <asm/pgtable.h> #include <asm/mmu.h> diff --git a/mm/internal.h b/mm/internal.h index d071d38..2189af4 100644 --- a/mm/internal.h +++ b/mm/internal.h @@ -37,6 +37,52 @@ static inline void __put_page(struct page *page) atomic_dec(&page->_count); } +static inline void __get_page_tail_foll(struct page *page, + bool get_page_head) +{ + /* + * If we're getting a tail page, the elevated page->_count is + * required only in the head page and we will elevate the head + * page->_count and tail page->_mapcount. + * + * We elevate page_tail->_mapcount for tail pages to force + * page_tail->_count to be zero at all times to avoid getting + * false positives from get_page_unless_zero() with + * speculative page access (like in + * page_cache_get_speculative()) on tail pages. + */ + VM_BUG_ON(atomic_read(&page->first_page->_count) <= 0); + VM_BUG_ON(atomic_read(&page->_count) != 0); + VM_BUG_ON(page_mapcount(page) < 0); + if (get_page_head) + atomic_inc(&page->first_page->_count); + atomic_inc(&page->_mapcount); +} + +/* + * This is meant to be called as the FOLL_GET operation of + * follow_page() and it must be called while holding the proper PT + * lock while the pte (or pmd_trans_huge) is still mapping the page. + */ +static inline void get_page_foll(struct page *page) +{ + if (unlikely(PageTail(page))) + /* + * This is safe only because + * __split_huge_page_refcount() can't run under + * get_page_foll() because we hold the proper PT lock. + */ + __get_page_tail_foll(page, true); + else { + /* + * Getting a normal page or the head of a compound page + * requires to already have an elevated page->_count. + */ + VM_BUG_ON(atomic_read(&page->_count) <= 0); + atomic_inc(&page->_count); + } +} + extern unsigned long highest_memmap_pfn; /* diff --git a/mm/kmemleak.c b/mm/kmemleak.c index aacee45..f3b2a00 100644 --- a/mm/kmemleak.c +++ b/mm/kmemleak.c @@ -69,7 +69,7 @@ #include <linux/sched.h> #include <linux/jiffies.h> #include <linux/delay.h> -#include <linux/module.h> +#include <linux/export.h> #include <linux/kthread.h> #include <linux/prio_tree.h> #include <linux/fs.h> @@ -96,7 +96,7 @@ #include <asm/sections.h> #include <asm/processor.h> -#include <asm/atomic.h> +#include <linux/atomic.h> #include <linux/kmemcheck.h> #include <linux/kmemleak.h> @@ -1905,7 +1905,8 @@ static ssize_t run_store(struct kobject *kobj, struct kobj_attribute *attr, oom_score_adj = test_set_oom_score_adj(OOM_SCORE_ADJ_MAX); err = unmerge_and_remove_all_rmap_items(); - test_set_oom_score_adj(oom_score_adj); + compare_swap_oom_score_adj(OOM_SCORE_ADJ_MAX, + oom_score_adj); if (err) { ksm_run = KSM_RUN_STOP; count = err; diff --git a/mm/maccess.c b/mm/maccess.c index 4cee182..d53adf9 100644 --- a/mm/maccess.c +++ b/mm/maccess.c @@ -1,7 +1,7 @@ /* * Access kernel memory without faulting. */ -#include <linux/module.h> +#include <linux/export.h> #include <linux/mm.h> #include <linux/uaccess.h> diff --git a/mm/madvise.c b/mm/madvise.c index 2221491..74bf193 100644 --- a/mm/madvise.c +++ b/mm/madvise.c @@ -218,7 +218,7 @@ static long madvise_remove(struct vm_area_struct *vma, endoff = (loff_t)(end - vma->vm_start - 1) + ((loff_t)vma->vm_pgoff << PAGE_SHIFT); - /* vmtruncate_range needs to take i_mutex and i_alloc_sem */ + /* vmtruncate_range needs to take i_mutex */ up_read(¤t->mm->mmap_sem); error = vmtruncate_range(mapping->host, offset, endoff); down_read(¤t->mm->mmap_sem); diff --git a/mm/memblock.c b/mm/memblock.c index a75723d..a57092f 100644 --- a/mm/memblock.c +++ b/mm/memblock.c @@ -47,7 +47,8 @@ static unsigned long __init_memblock memblock_addrs_overlap(phys_addr_t base1, p return ((base1 < (base2 + size2)) && (base2 < (base1 + size1))); } -long __init_memblock memblock_overlaps_region(struct memblock_type *type, phys_addr_t base, phys_addr_t size) +static long __init_memblock memblock_overlaps_region(struct memblock_type *type, + phys_addr_t base, phys_addr_t size) { unsigned long i; @@ -773,6 +774,12 @@ phys_addr_t __init memblock_phys_mem_size(void) return memblock.memory_size; } +/* lowest address */ +phys_addr_t __init_memblock memblock_start_of_DRAM(void) +{ + return memblock.memory.regions[0].base; +} + phys_addr_t __init_memblock memblock_end_of_DRAM(void) { int idx = memblock.memory.cnt - 1; @@ -912,9 +919,9 @@ void __init memblock_analyze(void) /* Check marker in the unused last array entry */ WARN_ON(memblock_memory_init_regions[INIT_MEMBLOCK_REGIONS].base - != (phys_addr_t)RED_INACTIVE); + != MEMBLOCK_INACTIVE); WARN_ON(memblock_reserved_init_regions[INIT_MEMBLOCK_REGIONS].base - != (phys_addr_t)RED_INACTIVE); + != MEMBLOCK_INACTIVE); memblock.memory_size = 0; @@ -940,8 +947,8 @@ void __init memblock_init(void) memblock.reserved.max = INIT_MEMBLOCK_REGIONS; /* Write a marker in the unused last array entry */ - memblock.memory.regions[INIT_MEMBLOCK_REGIONS].base = (phys_addr_t)RED_INACTIVE; - memblock.reserved.regions[INIT_MEMBLOCK_REGIONS].base = (phys_addr_t)RED_INACTIVE; + memblock.memory.regions[INIT_MEMBLOCK_REGIONS].base = MEMBLOCK_INACTIVE; + memblock.reserved.regions[INIT_MEMBLOCK_REGIONS].base = MEMBLOCK_INACTIVE; /* Create a dummy zero size MEMBLOCK which will get coalesced away later. * This simplifies the memblock_add() code below... diff --git a/mm/memcontrol.c b/mm/memcontrol.c index e013b8e..6aff93c 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -33,9 +33,9 @@ #include <linux/bit_spinlock.h> #include <linux/rcupdate.h> #include <linux/limits.h> +#include <linux/export.h> #include <linux/mutex.h> #include <linux/rbtree.h> -#include <linux/shmem_fs.h> #include <linux/slab.h> #include <linux/swap.h> #include <linux/swapops.h> @@ -202,8 +202,8 @@ struct mem_cgroup_eventfd_list { struct eventfd_ctx *eventfd; }; -static void mem_cgroup_threshold(struct mem_cgroup *mem); -static void mem_cgroup_oom_notify(struct mem_cgroup *mem); +static void mem_cgroup_threshold(struct mem_cgroup *memcg); +static void mem_cgroup_oom_notify(struct mem_cgroup *memcg); /* * The memory controller data structure. The memory controller controls both @@ -246,10 +246,13 @@ struct mem_cgroup { * Should the accounting and control be hierarchical, per subtree? */ bool use_hierarchy; - atomic_t oom_lock; + + bool oom_lock; + atomic_t under_oom; + atomic_t refcnt; - unsigned int swappiness; + int swappiness; /* OOM-Killer disable */ int oom_kill_disable; @@ -360,29 +363,29 @@ enum charge_type { #define MEM_CGROUP_RECLAIM_SOFT_BIT 0x2 #define MEM_CGROUP_RECLAIM_SOFT (1 << MEM_CGROUP_RECLAIM_SOFT_BIT) -static void mem_cgroup_get(struct mem_cgroup *mem); -static void mem_cgroup_put(struct mem_cgroup *mem); -static struct mem_cgroup *parent_mem_cgroup(struct mem_cgroup *mem); -static void drain_all_stock_async(struct mem_cgroup *mem); +static void mem_cgroup_get(struct mem_cgroup *memcg); +static void mem_cgroup_put(struct mem_cgroup *memcg); +static struct mem_cgroup *parent_mem_cgroup(struct mem_cgroup *memcg); +static void drain_all_stock_async(struct mem_cgroup *memcg); static struct mem_cgroup_per_zone * -mem_cgroup_zoneinfo(struct mem_cgroup *mem, int nid, int zid) +mem_cgroup_zoneinfo(struct mem_cgroup *memcg, int nid, int zid) { - return &mem->info.nodeinfo[nid]->zoneinfo[zid]; + return &memcg->info.nodeinfo[nid]->zoneinfo[zid]; } -struct cgroup_subsys_state *mem_cgroup_css(struct mem_cgroup *mem) +struct cgroup_subsys_state *mem_cgroup_css(struct mem_cgroup *memcg) { - return &mem->css; + return &memcg->css; } static struct mem_cgroup_per_zone * -page_cgroup_zoneinfo(struct mem_cgroup *mem, struct page *page) +page_cgroup_zoneinfo(struct mem_cgroup *memcg, struct page *page) { int nid = page_to_nid(page); int zid = page_zonenum(page); - return mem_cgroup_zoneinfo(mem, nid, zid); + return mem_cgroup_zoneinfo(memcg, nid, zid); } static struct mem_cgroup_tree_per_zone * @@ -401,7 +404,7 @@ soft_limit_tree_from_page(struct page *page) } static void -__mem_cgroup_insert_exceeded(struct mem_cgroup *mem, +__mem_cgroup_insert_exceeded(struct mem_cgroup *memcg, struct mem_cgroup_per_zone *mz, struct mem_cgroup_tree_per_zone *mctz, unsigned long long new_usage_in_excess) @@ -435,7 +438,7 @@ __mem_cgroup_insert_exceeded(struct mem_cgroup *mem, } static void -__mem_cgroup_remove_exceeded(struct mem_cgroup *mem, +__mem_cgroup_remove_exceeded(struct mem_cgroup *memcg, struct mem_cgroup_per_zone *mz, struct mem_cgroup_tree_per_zone *mctz) { @@ -446,17 +449,17 @@ __mem_cgroup_remove_exceeded(struct mem_cgroup *mem, } static void -mem_cgroup_remove_exceeded(struct mem_cgroup *mem, +mem_cgroup_remove_exceeded(struct mem_cgroup *memcg, struct mem_cgroup_per_zone *mz, struct mem_cgroup_tree_per_zone *mctz) { spin_lock(&mctz->lock); - __mem_cgroup_remove_exceeded(mem, mz, mctz); + __mem_cgroup_remove_exceeded(memcg, mz, mctz); spin_unlock(&mctz->lock); } -static void mem_cgroup_update_tree(struct mem_cgroup *mem, struct page *page) +static void mem_cgroup_update_tree(struct mem_cgroup *memcg, struct page *page) { unsigned long long excess; struct mem_cgroup_per_zone *mz; @@ -469,9 +472,9 @@ static void mem_cgroup_update_tree(struct mem_cgroup *mem, struct page *page) * Necessary to update all ancestors when hierarchy is used. * because their event counter is not touched. */ - for (; mem; mem = parent_mem_cgroup(mem)) { - mz = mem_cgroup_zoneinfo(mem, nid, zid); - excess = res_counter_soft_limit_excess(&mem->res); + for (; memcg; memcg = parent_mem_cgroup(memcg)) { + mz = mem_cgroup_zoneinfo(memcg, nid, zid); + excess = res_counter_soft_limit_excess(&memcg->res); /* * We have to update the tree if mz is on RB-tree or * mem is over its softlimit. @@ -480,18 +483,18 @@ static void mem_cgroup_update_tree(struct mem_cgroup *mem, struct page *page) spin_lock(&mctz->lock); /* if on-tree, remove it */ if (mz->on_tree) - __mem_cgroup_remove_exceeded(mem, mz, mctz); + __mem_cgroup_remove_exceeded(memcg, mz, mctz); /* * Insert again. mz->usage_in_excess will be updated. * If excess is 0, no tree ops. */ - __mem_cgroup_insert_exceeded(mem, mz, mctz, excess); + __mem_cgroup_insert_exceeded(memcg, mz, mctz, excess); spin_unlock(&mctz->lock); } } } -static void mem_cgroup_remove_from_trees(struct mem_cgroup *mem) +static void mem_cgroup_remove_from_trees(struct mem_cgroup *memcg) { int node, zone; struct mem_cgroup_per_zone *mz; @@ -499,9 +502,9 @@ static void mem_cgroup_remove_from_trees(struct mem_cgroup *mem) for_each_node_state(node, N_POSSIBLE) { for (zone = 0; zone < MAX_NR_ZONES; zone++) { - mz = mem_cgroup_zoneinfo(mem, node, zone); + mz = mem_cgroup_zoneinfo(memcg, node, zone); mctz = soft_limit_tree_node_zone(node, zone); - mem_cgroup_remove_exceeded(mem, mz, mctz); + mem_cgroup_remove_exceeded(memcg, mz, mctz); } } } @@ -562,7 +565,7 @@ mem_cgroup_largest_soft_limit_node(struct mem_cgroup_tree_per_zone *mctz) * common workload, threashold and synchonization as vmstat[] should be * implemented. */ -static long mem_cgroup_read_stat(struct mem_cgroup *mem, +static long mem_cgroup_read_stat(struct mem_cgroup *memcg, enum mem_cgroup_stat_index idx) { long val = 0; @@ -570,111 +573,131 @@ static long mem_cgroup_read_stat(struct mem_cgroup *mem, get_online_cpus(); for_each_online_cpu(cpu) - val += per_cpu(mem->stat->count[idx], cpu); + val += per_cpu(memcg->stat->count[idx], cpu); #ifdef CONFIG_HOTPLUG_CPU - spin_lock(&mem->pcp_counter_lock); - val += mem->nocpu_base.count[idx]; - spin_unlock(&mem->pcp_counter_lock); + spin_lock(&memcg->pcp_counter_lock); + val += memcg->nocpu_base.count[idx]; + spin_unlock(&memcg->pcp_counter_lock); #endif put_online_cpus(); return val; } -static void mem_cgroup_swap_statistics(struct mem_cgroup *mem, +static void mem_cgroup_swap_statistics(struct mem_cgroup *memcg, bool charge) { int val = (charge) ? 1 : -1; - this_cpu_add(mem->stat->count[MEM_CGROUP_STAT_SWAPOUT], val); + this_cpu_add(memcg->stat->count[MEM_CGROUP_STAT_SWAPOUT], val); } -void mem_cgroup_pgfault(struct mem_cgroup *mem, int val) +void mem_cgroup_pgfault(struct mem_cgroup *memcg, int val) { - this_cpu_add(mem->stat->events[MEM_CGROUP_EVENTS_PGFAULT], val); + this_cpu_add(memcg->stat->events[MEM_CGROUP_EVENTS_PGFAULT], val); } -void mem_cgroup_pgmajfault(struct mem_cgroup *mem, int val) +void mem_cgroup_pgmajfault(struct mem_cgroup *memcg, int val) { - this_cpu_add(mem->stat->events[MEM_CGROUP_EVENTS_PGMAJFAULT], val); + this_cpu_add(memcg->stat->events[MEM_CGROUP_EVENTS_PGMAJFAULT], val); } -static unsigned long mem_cgroup_read_events(struct mem_cgroup *mem, +static unsigned long mem_cgroup_read_events(struct mem_cgroup *memcg, enum mem_cgroup_events_index idx) { unsigned long val = 0; int cpu; for_each_online_cpu(cpu) - val += per_cpu(mem->stat->events[idx], cpu); + val += per_cpu(memcg->stat->events[idx], cpu); #ifdef CONFIG_HOTPLUG_CPU - spin_lock(&mem->pcp_counter_lock); - val += mem->nocpu_base.events[idx]; - spin_unlock(&mem->pcp_counter_lock); + spin_lock(&memcg->pcp_counter_lock); + val += memcg->nocpu_base.events[idx]; + spin_unlock(&memcg->pcp_counter_lock); #endif return val; } -static void mem_cgroup_charge_statistics(struct mem_cgroup *mem, +static void mem_cgroup_charge_statistics(struct mem_cgroup *memcg, bool file, int nr_pages) { preempt_disable(); if (file) - __this_cpu_add(mem->stat->count[MEM_CGROUP_STAT_CACHE], nr_pages); + __this_cpu_add(memcg->stat->count[MEM_CGROUP_STAT_CACHE], + nr_pages); else - __this_cpu_add(mem->stat->count[MEM_CGROUP_STAT_RSS], nr_pages); + __this_cpu_add(memcg->stat->count[MEM_CGROUP_STAT_RSS], + nr_pages); /* pagein of a big page is an event. So, ignore page size */ if (nr_pages > 0) - __this_cpu_inc(mem->stat->events[MEM_CGROUP_EVENTS_PGPGIN]); + __this_cpu_inc(memcg->stat->events[MEM_CGROUP_EVENTS_PGPGIN]); else { - __this_cpu_inc(mem->stat->events[MEM_CGROUP_EVENTS_PGPGOUT]); + __this_cpu_inc(memcg->stat->events[MEM_CGROUP_EVENTS_PGPGOUT]); nr_pages = -nr_pages; /* for event */ } - __this_cpu_add(mem->stat->events[MEM_CGROUP_EVENTS_COUNT], nr_pages); + __this_cpu_add(memcg->stat->events[MEM_CGROUP_EVENTS_COUNT], nr_pages); preempt_enable(); } -static unsigned long -mem_cgroup_get_zonestat_node(struct mem_cgroup *mem, int nid, enum lru_list idx) +unsigned long +mem_cgroup_zone_nr_lru_pages(struct mem_cgroup *memcg, int nid, int zid, + unsigned int lru_mask) { struct mem_cgroup_per_zone *mz; + enum lru_list l; + unsigned long ret = 0; + + mz = mem_cgroup_zoneinfo(memcg, nid, zid); + + for_each_lru(l) { + if (BIT(l) & lru_mask) + ret += MEM_CGROUP_ZSTAT(mz, l); + } + return ret; +} + +static unsigned long +mem_cgroup_node_nr_lru_pages(struct mem_cgroup *memcg, + int nid, unsigned int lru_mask) +{ u64 total = 0; int zid; - for (zid = 0; zid < MAX_NR_ZONES; zid++) { - mz = mem_cgroup_zoneinfo(mem, nid, zid); - total += MEM_CGROUP_ZSTAT(mz, idx); - } + for (zid = 0; zid < MAX_NR_ZONES; zid++) + total += mem_cgroup_zone_nr_lru_pages(memcg, + nid, zid, lru_mask); + return total; } -static unsigned long mem_cgroup_get_local_zonestat(struct mem_cgroup *mem, - enum lru_list idx) + +static unsigned long mem_cgroup_nr_lru_pages(struct mem_cgroup *memcg, + unsigned int lru_mask) { int nid; u64 total = 0; - for_each_online_node(nid) - total += mem_cgroup_get_zonestat_node(mem, nid, idx); + for_each_node_state(nid, N_HIGH_MEMORY) + total += mem_cgroup_node_nr_lru_pages(memcg, nid, lru_mask); return total; } -static bool __memcg_event_check(struct mem_cgroup *mem, int target) +static bool __memcg_event_check(struct mem_cgroup *memcg, int target) { unsigned long val, next; - val = this_cpu_read(mem->stat->events[MEM_CGROUP_EVENTS_COUNT]); - next = this_cpu_read(mem->stat->targets[target]); + val = __this_cpu_read(memcg->stat->events[MEM_CGROUP_EVENTS_COUNT]); + next = __this_cpu_read(memcg->stat->targets[target]); /* from time_after() in jiffies.h */ return ((long)next - (long)val < 0); } -static void __mem_cgroup_target_update(struct mem_cgroup *mem, int target) +static void __mem_cgroup_target_update(struct mem_cgroup *memcg, int target) { unsigned long val, next; - val = this_cpu_read(mem->stat->events[MEM_CGROUP_EVENTS_COUNT]); + val = __this_cpu_read(memcg->stat->events[MEM_CGROUP_EVENTS_COUNT]); switch (target) { case MEM_CGROUP_TARGET_THRESH: @@ -690,34 +713,36 @@ static void __mem_cgroup_target_update(struct mem_cgroup *mem, int target) return; } - this_cpu_write(mem->stat->targets[target], next); + __this_cpu_write(memcg->stat->targets[target], next); } /* * Check events in order. * */ -static void memcg_check_events(struct mem_cgroup *mem, struct page *page) +static void memcg_check_events(struct mem_cgroup *memcg, struct page *page) { + preempt_disable(); /* threshold event is triggered in finer grain than soft limit */ - if (unlikely(__memcg_event_check(mem, MEM_CGROUP_TARGET_THRESH))) { - mem_cgroup_threshold(mem); - __mem_cgroup_target_update(mem, MEM_CGROUP_TARGET_THRESH); - if (unlikely(__memcg_event_check(mem, + if (unlikely(__memcg_event_check(memcg, MEM_CGROUP_TARGET_THRESH))) { + mem_cgroup_threshold(memcg); + __mem_cgroup_target_update(memcg, MEM_CGROUP_TARGET_THRESH); + if (unlikely(__memcg_event_check(memcg, MEM_CGROUP_TARGET_SOFTLIMIT))) { - mem_cgroup_update_tree(mem, page); - __mem_cgroup_target_update(mem, + mem_cgroup_update_tree(memcg, page); + __mem_cgroup_target_update(memcg, MEM_CGROUP_TARGET_SOFTLIMIT); } #if MAX_NUMNODES > 1 - if (unlikely(__memcg_event_check(mem, + if (unlikely(__memcg_event_check(memcg, MEM_CGROUP_TARGET_NUMAINFO))) { - atomic_inc(&mem->numainfo_events); - __mem_cgroup_target_update(mem, + atomic_inc(&memcg->numainfo_events); + __mem_cgroup_target_update(memcg, MEM_CGROUP_TARGET_NUMAINFO); } #endif } + preempt_enable(); } static struct mem_cgroup *mem_cgroup_from_cont(struct cgroup *cont) @@ -743,7 +768,7 @@ struct mem_cgroup *mem_cgroup_from_task(struct task_struct *p) struct mem_cgroup *try_get_mem_cgroup_from_mm(struct mm_struct *mm) { - struct mem_cgroup *mem = NULL; + struct mem_cgroup *memcg = NULL; if (!mm) return NULL; @@ -754,25 +779,25 @@ struct mem_cgroup *try_get_mem_cgroup_from_mm(struct mm_struct *mm) */ rcu_read_lock(); do { - mem = mem_cgroup_from_task(rcu_dereference(mm->owner)); - if (unlikely(!mem)) + memcg = mem_cgroup_from_task(rcu_dereference(mm->owner)); + if (unlikely(!memcg)) break; - } while (!css_tryget(&mem->css)); + } while (!css_tryget(&memcg->css)); rcu_read_unlock(); - return mem; + return memcg; } /* The caller has to guarantee "mem" exists before calling this */ -static struct mem_cgroup *mem_cgroup_start_loop(struct mem_cgroup *mem) +static struct mem_cgroup *mem_cgroup_start_loop(struct mem_cgroup *memcg) { struct cgroup_subsys_state *css; int found; - if (!mem) /* ROOT cgroup has the smallest ID */ + if (!memcg) /* ROOT cgroup has the smallest ID */ return root_mem_cgroup; /*css_put/get against root is ignored*/ - if (!mem->use_hierarchy) { - if (css_tryget(&mem->css)) - return mem; + if (!memcg->use_hierarchy) { + if (css_tryget(&memcg->css)) + return memcg; return NULL; } rcu_read_lock(); @@ -780,13 +805,13 @@ static struct mem_cgroup *mem_cgroup_start_loop(struct mem_cgroup *mem) * searching a memory cgroup which has the smallest ID under given * ROOT cgroup. (ID >= 1) */ - css = css_get_next(&mem_cgroup_subsys, 1, &mem->css, &found); + css = css_get_next(&mem_cgroup_subsys, 1, &memcg->css, &found); if (css && css_tryget(css)) - mem = container_of(css, struct mem_cgroup, css); + memcg = container_of(css, struct mem_cgroup, css); else - mem = NULL; + memcg = NULL; rcu_read_unlock(); - return mem; + return memcg; } static struct mem_cgroup *mem_cgroup_get_next(struct mem_cgroup *iter, @@ -840,29 +865,29 @@ static struct mem_cgroup *mem_cgroup_get_next(struct mem_cgroup *iter, for_each_mem_cgroup_tree_cond(iter, NULL, true) -static inline bool mem_cgroup_is_root(struct mem_cgroup *mem) +static inline bool mem_cgroup_is_root(struct mem_cgroup *memcg) { - return (mem == root_mem_cgroup); + return (memcg == root_mem_cgroup); } void mem_cgroup_count_vm_event(struct mm_struct *mm, enum vm_event_item idx) { - struct mem_cgroup *mem; + struct mem_cgroup *memcg; if (!mm) return; rcu_read_lock(); - mem = mem_cgroup_from_task(rcu_dereference(mm->owner)); - if (unlikely(!mem)) + memcg = mem_cgroup_from_task(rcu_dereference(mm->owner)); + if (unlikely(!memcg)) goto out; switch (idx) { case PGMAJFAULT: - mem_cgroup_pgmajfault(mem, 1); + mem_cgroup_pgmajfault(memcg, 1); break; case PGFAULT: - mem_cgroup_pgfault(mem, 1); + mem_cgroup_pgfault(memcg, 1); break; default: BUG(); @@ -971,6 +996,16 @@ void mem_cgroup_add_lru_list(struct page *page, enum lru_list lru) return; pc = lookup_page_cgroup(page); VM_BUG_ON(PageCgroupAcctLRU(pc)); + /* + * putback: charge: + * SetPageLRU SetPageCgroupUsed + * smp_mb smp_mb + * PageCgroupUsed && add to memcg LRU PageLRU && add to memcg LRU + * + * Ensure that one of the two sides adds the page to the memcg + * LRU during a race. + */ + smp_mb(); if (!PageCgroupUsed(pc)) return; /* Ensure pc->mem_cgroup is visible after reading PCG_USED. */ @@ -1022,7 +1057,16 @@ static void mem_cgroup_lru_add_after_commit(struct page *page) unsigned long flags; struct zone *zone = page_zone(page); struct page_cgroup *pc = lookup_page_cgroup(page); - + /* + * putback: charge: + * SetPageLRU SetPageCgroupUsed + * smp_mb smp_mb + * PageCgroupUsed && add to memcg LRU PageLRU && add to memcg LRU + * + * Ensure that one of the two sides adds the page to the memcg + * LRU during a race. + */ + smp_mb(); /* taking care of that the page is added to LRU while we commit it */ if (likely(!PageLRU(page))) return; @@ -1043,7 +1087,22 @@ void mem_cgroup_move_lists(struct page *page, mem_cgroup_add_lru_list(page, to); } -int task_in_mem_cgroup(struct task_struct *task, const struct mem_cgroup *mem) +/* + * Checks whether given mem is same or in the root_mem_cgroup's + * hierarchy subtree + */ +static bool mem_cgroup_same_or_subtree(const struct mem_cgroup *root_memcg, + struct mem_cgroup *memcg) +{ + if (root_memcg != memcg) { + return (root_memcg->use_hierarchy && + css_is_ancestor(&memcg->css, &root_memcg->css)); + } + + return true; +} + +int task_in_mem_cgroup(struct task_struct *task, const struct mem_cgroup *memcg) { int ret; struct mem_cgroup *curr = NULL; @@ -1057,28 +1116,29 @@ int task_in_mem_cgroup(struct task_struct *task, const struct mem_cgroup *mem) if (!curr) return 0; /* - * We should check use_hierarchy of "mem" not "curr". Because checking + * We should check use_hierarchy of "memcg" not "curr". Because checking * use_hierarchy of "curr" here make this function true if hierarchy is - * enabled in "curr" and "curr" is a child of "mem" in *cgroup* - * hierarchy(even if use_hierarchy is disabled in "mem"). + * enabled in "curr" and "curr" is a child of "memcg" in *cgroup* + * hierarchy(even if use_hierarchy is disabled in "memcg"). */ - if (mem->use_hierarchy) - ret = css_is_ancestor(&curr->css, &mem->css); - else - ret = (curr == mem); + ret = mem_cgroup_same_or_subtree(memcg, curr); css_put(&curr->css); return ret; } -static int calc_inactive_ratio(struct mem_cgroup *memcg, unsigned long *present_pages) +int mem_cgroup_inactive_anon_is_low(struct mem_cgroup *memcg, struct zone *zone) { - unsigned long active; + unsigned long inactive_ratio; + int nid = zone_to_nid(zone); + int zid = zone_idx(zone); unsigned long inactive; + unsigned long active; unsigned long gb; - unsigned long inactive_ratio; - inactive = mem_cgroup_get_local_zonestat(memcg, LRU_INACTIVE_ANON); - active = mem_cgroup_get_local_zonestat(memcg, LRU_ACTIVE_ANON); + inactive = mem_cgroup_zone_nr_lru_pages(memcg, nid, zid, + BIT(LRU_INACTIVE_ANON)); + active = mem_cgroup_zone_nr_lru_pages(memcg, nid, zid, + BIT(LRU_ACTIVE_ANON)); gb = (inactive + active) >> (30 - PAGE_SHIFT); if (gb) @@ -1086,139 +1146,23 @@ static int calc_inactive_ratio(struct mem_cgroup *memcg, unsigned long *present_ else inactive_ratio = 1; - if (present_pages) { - present_pages[0] = inactive; - present_pages[1] = active; - } - - return inactive_ratio; + return inactive * inactive_ratio < active; } -int mem_cgroup_inactive_anon_is_low(struct mem_cgroup *memcg) +int mem_cgroup_inactive_file_is_low(struct mem_cgroup *memcg, struct zone *zone) { unsigned long active; unsigned long inactive; - unsigned long present_pages[2]; - unsigned long inactive_ratio; - - inactive_ratio = calc_inactive_ratio(memcg, present_pages); - - inactive = present_pages[0]; - active = present_pages[1]; - - if (inactive * inactive_ratio < active) - return 1; - - return 0; -} - -int mem_cgroup_inactive_file_is_low(struct mem_cgroup *memcg) -{ - unsigned long active; - unsigned long inactive; - - inactive = mem_cgroup_get_local_zonestat(memcg, LRU_INACTIVE_FILE); - active = mem_cgroup_get_local_zonestat(memcg, LRU_ACTIVE_FILE); - - return (active > inactive); -} - -unsigned long mem_cgroup_zone_nr_lru_pages(struct mem_cgroup *memcg, - struct zone *zone, - enum lru_list lru) -{ - int nid = zone_to_nid(zone); int zid = zone_idx(zone); - struct mem_cgroup_per_zone *mz = mem_cgroup_zoneinfo(memcg, nid, zid); - - return MEM_CGROUP_ZSTAT(mz, lru); -} - -static unsigned long mem_cgroup_node_nr_file_lru_pages(struct mem_cgroup *memcg, - int nid) -{ - unsigned long ret; - - ret = mem_cgroup_get_zonestat_node(memcg, nid, LRU_INACTIVE_FILE) + - mem_cgroup_get_zonestat_node(memcg, nid, LRU_ACTIVE_FILE); - - return ret; -} - -static unsigned long mem_cgroup_node_nr_anon_lru_pages(struct mem_cgroup *memcg, - int nid) -{ - unsigned long ret; - - ret = mem_cgroup_get_zonestat_node(memcg, nid, LRU_INACTIVE_ANON) + - mem_cgroup_get_zonestat_node(memcg, nid, LRU_ACTIVE_ANON); - return ret; -} - -#if MAX_NUMNODES > 1 -static unsigned long mem_cgroup_nr_file_lru_pages(struct mem_cgroup *memcg) -{ - u64 total = 0; - int nid; - - for_each_node_state(nid, N_HIGH_MEMORY) - total += mem_cgroup_node_nr_file_lru_pages(memcg, nid); - - return total; -} - -static unsigned long mem_cgroup_nr_anon_lru_pages(struct mem_cgroup *memcg) -{ - u64 total = 0; - int nid; - - for_each_node_state(nid, N_HIGH_MEMORY) - total += mem_cgroup_node_nr_anon_lru_pages(memcg, nid); - - return total; -} - -static unsigned long -mem_cgroup_node_nr_unevictable_lru_pages(struct mem_cgroup *memcg, int nid) -{ - return mem_cgroup_get_zonestat_node(memcg, nid, LRU_UNEVICTABLE); -} - -static unsigned long -mem_cgroup_nr_unevictable_lru_pages(struct mem_cgroup *memcg) -{ - u64 total = 0; - int nid; - - for_each_node_state(nid, N_HIGH_MEMORY) - total += mem_cgroup_node_nr_unevictable_lru_pages(memcg, nid); - - return total; -} - -static unsigned long mem_cgroup_node_nr_lru_pages(struct mem_cgroup *memcg, - int nid) -{ - enum lru_list l; - u64 total = 0; - - for_each_lru(l) - total += mem_cgroup_get_zonestat_node(memcg, nid, l); - - return total; -} - -static unsigned long mem_cgroup_nr_lru_pages(struct mem_cgroup *memcg) -{ - u64 total = 0; - int nid; + int nid = zone_to_nid(zone); - for_each_node_state(nid, N_HIGH_MEMORY) - total += mem_cgroup_node_nr_lru_pages(memcg, nid); + inactive = mem_cgroup_zone_nr_lru_pages(memcg, nid, zid, + BIT(LRU_INACTIVE_FILE)); + active = mem_cgroup_zone_nr_lru_pages(memcg, nid, zid, + BIT(LRU_ACTIVE_FILE)); - return total; + return (active > inactive); } -#endif /* CONFIG_NUMA */ struct zone_reclaim_stat *mem_cgroup_get_reclaim_stat(struct mem_cgroup *memcg, struct zone *zone) @@ -1251,7 +1195,8 @@ mem_cgroup_get_reclaim_stat_from_page(struct page *page) unsigned long mem_cgroup_isolate_pages(unsigned long nr_to_scan, struct list_head *dst, unsigned long *scanned, int order, - int mode, struct zone *z, + isolate_mode_t mode, + struct zone *z, struct mem_cgroup *mem_cont, int active, int file) { @@ -1319,17 +1264,17 @@ unsigned long mem_cgroup_isolate_pages(unsigned long nr_to_scan, * Returns the maximum amount of memory @mem can be charged with, in * pages. */ -static unsigned long mem_cgroup_margin(struct mem_cgroup *mem) +static unsigned long mem_cgroup_margin(struct mem_cgroup *memcg) { unsigned long long margin; - margin = res_counter_margin(&mem->res); + margin = res_counter_margin(&memcg->res); if (do_swap_account) - margin = min(margin, res_counter_margin(&mem->memsw)); + margin = min(margin, res_counter_margin(&memcg->memsw)); return margin >> PAGE_SHIFT; } -static unsigned int get_swappiness(struct mem_cgroup *memcg) +int mem_cgroup_swappiness(struct mem_cgroup *memcg) { struct cgroup *cgrp = memcg->css.cgroup; @@ -1340,33 +1285,33 @@ static unsigned int get_swappiness(struct mem_cgroup *memcg) return memcg->swappiness; } -static void mem_cgroup_start_move(struct mem_cgroup *mem) +static void mem_cgroup_start_move(struct mem_cgroup *memcg) { int cpu; get_online_cpus(); - spin_lock(&mem->pcp_counter_lock); + spin_lock(&memcg->pcp_counter_lock); for_each_online_cpu(cpu) - per_cpu(mem->stat->count[MEM_CGROUP_ON_MOVE], cpu) += 1; - mem->nocpu_base.count[MEM_CGROUP_ON_MOVE] += 1; - spin_unlock(&mem->pcp_counter_lock); + per_cpu(memcg->stat->count[MEM_CGROUP_ON_MOVE], cpu) += 1; + memcg->nocpu_base.count[MEM_CGROUP_ON_MOVE] += 1; + spin_unlock(&memcg->pcp_counter_lock); put_online_cpus(); synchronize_rcu(); } -static void mem_cgroup_end_move(struct mem_cgroup *mem) +static void mem_cgroup_end_move(struct mem_cgroup *memcg) { int cpu; - if (!mem) + if (!memcg) return; get_online_cpus(); - spin_lock(&mem->pcp_counter_lock); + spin_lock(&memcg->pcp_counter_lock); for_each_online_cpu(cpu) - per_cpu(mem->stat->count[MEM_CGROUP_ON_MOVE], cpu) -= 1; - mem->nocpu_base.count[MEM_CGROUP_ON_MOVE] -= 1; - spin_unlock(&mem->pcp_counter_lock); + per_cpu(memcg->stat->count[MEM_CGROUP_ON_MOVE], cpu) -= 1; + memcg->nocpu_base.count[MEM_CGROUP_ON_MOVE] -= 1; + spin_unlock(&memcg->pcp_counter_lock); put_online_cpus(); } /* @@ -1381,13 +1326,13 @@ static void mem_cgroup_end_move(struct mem_cgroup *mem) * waiting at hith-memory prressure caused by "move". */ -static bool mem_cgroup_stealed(struct mem_cgroup *mem) +static bool mem_cgroup_stealed(struct mem_cgroup *memcg) { VM_BUG_ON(!rcu_read_lock_held()); - return this_cpu_read(mem->stat->count[MEM_CGROUP_ON_MOVE]) > 0; + return this_cpu_read(memcg->stat->count[MEM_CGROUP_ON_MOVE]) > 0; } -static bool mem_cgroup_under_move(struct mem_cgroup *mem) +static bool mem_cgroup_under_move(struct mem_cgroup *memcg) { struct mem_cgroup *from; struct mem_cgroup *to; @@ -1401,19 +1346,18 @@ static bool mem_cgroup_under_move(struct mem_cgroup *mem) to = mc.to; if (!from) goto unlock; - if (from == mem || to == mem - || (mem->use_hierarchy && css_is_ancestor(&from->css, &mem->css)) - || (mem->use_hierarchy && css_is_ancestor(&to->css, &mem->css))) - ret = true; + + ret = mem_cgroup_same_or_subtree(memcg, from) + || mem_cgroup_same_or_subtree(memcg, to); unlock: spin_unlock(&mc.lock); return ret; } -static bool mem_cgroup_wait_acct_move(struct mem_cgroup *mem) +static bool mem_cgroup_wait_acct_move(struct mem_cgroup *memcg) { if (mc.moving_task && current != mc.moving_task) { - if (mem_cgroup_under_move(mem)) { + if (mem_cgroup_under_move(memcg)) { DEFINE_WAIT(wait); prepare_to_wait(&mc.waitq, &wait, TASK_INTERRUPTIBLE); /* moving charge context might have finished. */ @@ -1497,12 +1441,12 @@ done: * 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) +static int mem_cgroup_count_children(struct mem_cgroup *memcg) { int num = 0; struct mem_cgroup *iter; - for_each_mem_cgroup_tree(iter, mem) + for_each_mem_cgroup_tree(iter, memcg) num++; return num; } @@ -1532,21 +1476,21 @@ u64 mem_cgroup_get_limit(struct mem_cgroup *memcg) * that to reclaim free pages from. */ static struct mem_cgroup * -mem_cgroup_select_victim(struct mem_cgroup *root_mem) +mem_cgroup_select_victim(struct mem_cgroup *root_memcg) { struct mem_cgroup *ret = NULL; struct cgroup_subsys_state *css; int nextid, found; - if (!root_mem->use_hierarchy) { - css_get(&root_mem->css); - ret = root_mem; + if (!root_memcg->use_hierarchy) { + css_get(&root_memcg->css); + ret = root_memcg; } while (!ret) { rcu_read_lock(); - nextid = root_mem->last_scanned_child + 1; - css = css_get_next(&mem_cgroup_subsys, nextid, &root_mem->css, + nextid = root_memcg->last_scanned_child + 1; + css = css_get_next(&mem_cgroup_subsys, nextid, &root_memcg->css, &found); if (css && css_tryget(css)) ret = container_of(css, struct mem_cgroup, css); @@ -1555,9 +1499,9 @@ mem_cgroup_select_victim(struct mem_cgroup *root_mem) /* Updates scanning parameter */ if (!css) { /* this means start scan from ID:1 */ - root_mem->last_scanned_child = 0; + root_memcg->last_scanned_child = 0; } else - root_mem->last_scanned_child = found; + root_memcg->last_scanned_child = found; } return ret; @@ -1573,14 +1517,14 @@ mem_cgroup_select_victim(struct mem_cgroup *root_mem) * reclaimable pages on a node. Returns true if there are any reclaimable * pages in the node. */ -static bool test_mem_cgroup_node_reclaimable(struct mem_cgroup *mem, +static bool test_mem_cgroup_node_reclaimable(struct mem_cgroup *memcg, int nid, bool noswap) { - if (mem_cgroup_node_nr_file_lru_pages(mem, nid)) + if (mem_cgroup_node_nr_lru_pages(memcg, nid, LRU_ALL_FILE)) return true; if (noswap || !total_swap_pages) return false; - if (mem_cgroup_node_nr_anon_lru_pages(mem, nid)) + if (mem_cgroup_node_nr_lru_pages(memcg, nid, LRU_ALL_ANON)) return true; return false; @@ -1593,29 +1537,29 @@ static bool test_mem_cgroup_node_reclaimable(struct mem_cgroup *mem, * nodes based on the zonelist. So update the list loosely once per 10 secs. * */ -static void mem_cgroup_may_update_nodemask(struct mem_cgroup *mem) +static void mem_cgroup_may_update_nodemask(struct mem_cgroup *memcg) { int nid; /* * numainfo_events > 0 means there was at least NUMAINFO_EVENTS_TARGET * pagein/pageout changes since the last update. */ - if (!atomic_read(&mem->numainfo_events)) + if (!atomic_read(&memcg->numainfo_events)) return; - if (atomic_inc_return(&mem->numainfo_updating) > 1) + if (atomic_inc_return(&memcg->numainfo_updating) > 1) return; /* make a nodemask where this memcg uses memory from */ - mem->scan_nodes = node_states[N_HIGH_MEMORY]; + memcg->scan_nodes = node_states[N_HIGH_MEMORY]; for_each_node_mask(nid, node_states[N_HIGH_MEMORY]) { - if (!test_mem_cgroup_node_reclaimable(mem, nid, false)) - node_clear(nid, mem->scan_nodes); + if (!test_mem_cgroup_node_reclaimable(memcg, nid, false)) + node_clear(nid, memcg->scan_nodes); } - atomic_set(&mem->numainfo_events, 0); - atomic_set(&mem->numainfo_updating, 0); + atomic_set(&memcg->numainfo_events, 0); + atomic_set(&memcg->numainfo_updating, 0); } /* @@ -1630,16 +1574,16 @@ static void mem_cgroup_may_update_nodemask(struct mem_cgroup *mem) * * Now, we use round-robin. Better algorithm is welcomed. */ -int mem_cgroup_select_victim_node(struct mem_cgroup *mem) +int mem_cgroup_select_victim_node(struct mem_cgroup *memcg) { int node; - mem_cgroup_may_update_nodemask(mem); - node = mem->last_scanned_node; + mem_cgroup_may_update_nodemask(memcg); + node = memcg->last_scanned_node; - node = next_node(node, mem->scan_nodes); + node = next_node(node, memcg->scan_nodes); if (node == MAX_NUMNODES) - node = first_node(mem->scan_nodes); + node = first_node(memcg->scan_nodes); /* * We call this when we hit limit, not when pages are added to LRU. * No LRU may hold pages because all pages are UNEVICTABLE or @@ -1649,7 +1593,7 @@ int mem_cgroup_select_victim_node(struct mem_cgroup *mem) if (unlikely(node == MAX_NUMNODES)) node = numa_node_id(); - mem->last_scanned_node = node; + memcg->last_scanned_node = node; return node; } @@ -1659,7 +1603,7 @@ int mem_cgroup_select_victim_node(struct mem_cgroup *mem) * unused nodes. But scan_nodes is lazily updated and may not cotain * enough new information. We need to do double check. */ -bool mem_cgroup_reclaimable(struct mem_cgroup *mem, bool noswap) +bool mem_cgroup_reclaimable(struct mem_cgroup *memcg, bool noswap) { int nid; @@ -1667,12 +1611,12 @@ bool mem_cgroup_reclaimable(struct mem_cgroup *mem, bool noswap) * quick check...making use of scan_node. * We can skip unused nodes. */ - if (!nodes_empty(mem->scan_nodes)) { - for (nid = first_node(mem->scan_nodes); + if (!nodes_empty(memcg->scan_nodes)) { + for (nid = first_node(memcg->scan_nodes); nid < MAX_NUMNODES; - nid = next_node(nid, mem->scan_nodes)) { + nid = next_node(nid, memcg->scan_nodes)) { - if (test_mem_cgroup_node_reclaimable(mem, nid, noswap)) + if (test_mem_cgroup_node_reclaimable(memcg, nid, noswap)) return true; } } @@ -1680,23 +1624,23 @@ bool mem_cgroup_reclaimable(struct mem_cgroup *mem, bool noswap) * Check rest of nodes. */ for_each_node_state(nid, N_HIGH_MEMORY) { - if (node_isset(nid, mem->scan_nodes)) + if (node_isset(nid, memcg->scan_nodes)) continue; - if (test_mem_cgroup_node_reclaimable(mem, nid, noswap)) + if (test_mem_cgroup_node_reclaimable(memcg, nid, noswap)) return true; } return false; } #else -int mem_cgroup_select_victim_node(struct mem_cgroup *mem) +int mem_cgroup_select_victim_node(struct mem_cgroup *memcg) { return 0; } -bool mem_cgroup_reclaimable(struct mem_cgroup *mem, bool noswap) +bool mem_cgroup_reclaimable(struct mem_cgroup *memcg, bool noswap) { - return test_mem_cgroup_node_reclaimable(mem, 0, noswap); + return test_mem_cgroup_node_reclaimable(memcg, 0, noswap); } #endif @@ -1705,14 +1649,14 @@ bool mem_cgroup_reclaimable(struct mem_cgroup *mem, bool noswap) * 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. + * root_memcg is the original ancestor that we've been reclaim from. * - * We give up and return to the caller when we visit root_mem twice. + * We give up and return to the caller when we visit root_memcg 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, +static int mem_cgroup_hierarchical_reclaim(struct mem_cgroup *root_memcg, struct zone *zone, gfp_t gfp_mask, unsigned long reclaim_options, @@ -1727,15 +1671,15 @@ static int mem_cgroup_hierarchical_reclaim(struct mem_cgroup *root_mem, unsigned long excess; unsigned long nr_scanned; - excess = res_counter_soft_limit_excess(&root_mem->res) >> PAGE_SHIFT; + excess = res_counter_soft_limit_excess(&root_memcg->res) >> PAGE_SHIFT; /* If memsw_is_minimum==1, swap-out is of-no-use. */ - if (!check_soft && root_mem->memsw_is_minimum) + if (!check_soft && !shrink && root_memcg->memsw_is_minimum) noswap = true; while (1) { - victim = mem_cgroup_select_victim(root_mem); - if (victim == root_mem) { + victim = mem_cgroup_select_victim(root_memcg); + if (victim == root_memcg) { loop++; /* * We are not draining per cpu cached charges during @@ -1744,7 +1688,7 @@ static int mem_cgroup_hierarchical_reclaim(struct mem_cgroup *root_mem, * charges will not give any. */ if (!check_soft && loop >= 1) - drain_all_stock_async(root_mem); + drain_all_stock_async(root_memcg); if (loop >= 2) { /* * If we have not been able to reclaim @@ -1776,12 +1720,11 @@ static int mem_cgroup_hierarchical_reclaim(struct mem_cgroup *root_mem, /* we use swappiness of local cgroup */ if (check_soft) { ret = mem_cgroup_shrink_node_zone(victim, gfp_mask, - noswap, get_swappiness(victim), zone, - &nr_scanned); + noswap, zone, &nr_scanned); *total_scanned += nr_scanned; } else ret = try_to_free_mem_cgroup_pages(victim, gfp_mask, - noswap, get_swappiness(victim)); + noswap); css_put(&victim->css); /* * At shrinking usage, we can't check we should stop here or @@ -1792,9 +1735,9 @@ static int mem_cgroup_hierarchical_reclaim(struct mem_cgroup *root_mem, return ret; total += ret; if (check_soft) { - if (!res_counter_soft_limit_excess(&root_mem->res)) + if (!res_counter_soft_limit_excess(&root_memcg->res)) return total; - } else if (mem_cgroup_margin(root_mem)) + } else if (mem_cgroup_margin(root_memcg)) return total; } return total; @@ -1803,23 +1746,64 @@ static int mem_cgroup_hierarchical_reclaim(struct mem_cgroup *root_mem, /* * Check OOM-Killer is already running under our hierarchy. * If someone is running, return false. + * Has to be called with memcg_oom_lock */ -static bool mem_cgroup_oom_lock(struct mem_cgroup *mem) +static bool mem_cgroup_oom_lock(struct mem_cgroup *memcg) { - int x, lock_count = 0; - struct mem_cgroup *iter; + struct mem_cgroup *iter, *failed = NULL; + bool cond = true; - for_each_mem_cgroup_tree(iter, mem) { - x = atomic_inc_return(&iter->oom_lock); - lock_count = max(x, lock_count); + for_each_mem_cgroup_tree_cond(iter, memcg, cond) { + if (iter->oom_lock) { + /* + * this subtree of our hierarchy is already locked + * so we cannot give a lock. + */ + failed = iter; + cond = false; + } else + iter->oom_lock = true; } - if (lock_count == 1) + if (!failed) return true; + + /* + * OK, we failed to lock the whole subtree so we have to clean up + * what we set up to the failing subtree + */ + cond = true; + for_each_mem_cgroup_tree_cond(iter, memcg, cond) { + if (iter == failed) { + cond = false; + continue; + } + iter->oom_lock = false; + } return false; } -static int mem_cgroup_oom_unlock(struct mem_cgroup *mem) +/* + * Has to be called with memcg_oom_lock + */ +static int mem_cgroup_oom_unlock(struct mem_cgroup *memcg) +{ + struct mem_cgroup *iter; + + for_each_mem_cgroup_tree(iter, memcg) + iter->oom_lock = false; + return 0; +} + +static void mem_cgroup_mark_under_oom(struct mem_cgroup *memcg) +{ + struct mem_cgroup *iter; + + for_each_mem_cgroup_tree(iter, memcg) + atomic_inc(&iter->under_oom); +} + +static void mem_cgroup_unmark_under_oom(struct mem_cgroup *memcg) { struct mem_cgroup *iter; @@ -1828,13 +1812,11 @@ static int mem_cgroup_oom_unlock(struct mem_cgroup *mem) * mem_cgroup_oom_lock() may not be called. We have to use * atomic_add_unless() here. */ - for_each_mem_cgroup_tree(iter, mem) - atomic_add_unless(&iter->oom_lock, -1, 0); - return 0; + for_each_mem_cgroup_tree(iter, memcg) + atomic_add_unless(&iter->under_oom, -1, 0); } - -static DEFINE_MUTEX(memcg_oom_mutex); +static DEFINE_SPINLOCK(memcg_oom_lock); static DECLARE_WAIT_QUEUE_HEAD(memcg_oom_waitq); struct oom_wait_info { @@ -1845,85 +1827,85 @@ struct oom_wait_info { static int memcg_oom_wake_function(wait_queue_t *wait, unsigned mode, int sync, void *arg) { - struct mem_cgroup *wake_mem = (struct mem_cgroup *)arg; + struct mem_cgroup *wake_memcg = (struct mem_cgroup *)arg, + *oom_wait_memcg; struct oom_wait_info *oom_wait_info; oom_wait_info = container_of(wait, struct oom_wait_info, wait); + oom_wait_memcg = oom_wait_info->mem; - if (oom_wait_info->mem == wake_mem) - goto wakeup; - /* if no hierarchy, no match */ - if (!oom_wait_info->mem->use_hierarchy || !wake_mem->use_hierarchy) - return 0; /* * Both of oom_wait_info->mem and wake_mem are stable under us. * Then we can use css_is_ancestor without taking care of RCU. */ - if (!css_is_ancestor(&oom_wait_info->mem->css, &wake_mem->css) && - !css_is_ancestor(&wake_mem->css, &oom_wait_info->mem->css)) + if (!mem_cgroup_same_or_subtree(oom_wait_memcg, wake_memcg) + && !mem_cgroup_same_or_subtree(wake_memcg, oom_wait_memcg)) return 0; - -wakeup: return autoremove_wake_function(wait, mode, sync, arg); } -static void memcg_wakeup_oom(struct mem_cgroup *mem) +static void memcg_wakeup_oom(struct mem_cgroup *memcg) { - /* for filtering, pass "mem" as argument. */ - __wake_up(&memcg_oom_waitq, TASK_NORMAL, 0, mem); + /* for filtering, pass "memcg" as argument. */ + __wake_up(&memcg_oom_waitq, TASK_NORMAL, 0, memcg); } -static void memcg_oom_recover(struct mem_cgroup *mem) +static void memcg_oom_recover(struct mem_cgroup *memcg) { - if (mem && atomic_read(&mem->oom_lock)) - memcg_wakeup_oom(mem); + if (memcg && atomic_read(&memcg->under_oom)) + memcg_wakeup_oom(memcg); } /* * try to call OOM killer. returns false if we should exit memory-reclaim loop. */ -bool mem_cgroup_handle_oom(struct mem_cgroup *mem, gfp_t mask) +bool mem_cgroup_handle_oom(struct mem_cgroup *memcg, gfp_t mask) { struct oom_wait_info owait; bool locked, need_to_kill; - owait.mem = mem; + owait.mem = memcg; owait.wait.flags = 0; owait.wait.func = memcg_oom_wake_function; owait.wait.private = current; INIT_LIST_HEAD(&owait.wait.task_list); need_to_kill = true; - /* At first, try to OOM lock hierarchy under mem.*/ - mutex_lock(&memcg_oom_mutex); - locked = mem_cgroup_oom_lock(mem); + mem_cgroup_mark_under_oom(memcg); + + /* At first, try to OOM lock hierarchy under memcg.*/ + spin_lock(&memcg_oom_lock); + locked = mem_cgroup_oom_lock(memcg); /* * Even if signal_pending(), we can't quit charge() loop without * accounting. So, UNINTERRUPTIBLE is appropriate. But SIGKILL * under OOM is always welcomed, use TASK_KILLABLE here. */ prepare_to_wait(&memcg_oom_waitq, &owait.wait, TASK_KILLABLE); - if (!locked || mem->oom_kill_disable) + if (!locked || memcg->oom_kill_disable) need_to_kill = false; if (locked) - mem_cgroup_oom_notify(mem); - mutex_unlock(&memcg_oom_mutex); + mem_cgroup_oom_notify(memcg); + spin_unlock(&memcg_oom_lock); if (need_to_kill) { finish_wait(&memcg_oom_waitq, &owait.wait); - mem_cgroup_out_of_memory(mem, mask); + mem_cgroup_out_of_memory(memcg, mask); } else { schedule(); finish_wait(&memcg_oom_waitq, &owait.wait); } - mutex_lock(&memcg_oom_mutex); - mem_cgroup_oom_unlock(mem); - memcg_wakeup_oom(mem); - mutex_unlock(&memcg_oom_mutex); + spin_lock(&memcg_oom_lock); + if (locked) + mem_cgroup_oom_unlock(memcg); + memcg_wakeup_oom(memcg); + spin_unlock(&memcg_oom_lock); + + mem_cgroup_unmark_under_oom(memcg); if (test_thread_flag(TIF_MEMDIE) || fatal_signal_pending(current)) return false; /* Give chance to dying process */ - schedule_timeout(1); + schedule_timeout_uninterruptible(1); return true; } @@ -1954,7 +1936,7 @@ bool mem_cgroup_handle_oom(struct mem_cgroup *mem, gfp_t mask) void mem_cgroup_update_page_stat(struct page *page, enum mem_cgroup_page_stat_item idx, int val) { - struct mem_cgroup *mem; + struct mem_cgroup *memcg; struct page_cgroup *pc = lookup_page_cgroup(page); bool need_unlock = false; unsigned long uninitialized_var(flags); @@ -1963,16 +1945,16 @@ void mem_cgroup_update_page_stat(struct page *page, return; rcu_read_lock(); - mem = pc->mem_cgroup; - if (unlikely(!mem || !PageCgroupUsed(pc))) + memcg = pc->mem_cgroup; + if (unlikely(!memcg || !PageCgroupUsed(pc))) goto out; /* pc->mem_cgroup is unstable ? */ - if (unlikely(mem_cgroup_stealed(mem)) || PageTransHuge(page)) { + if (unlikely(mem_cgroup_stealed(memcg)) || PageTransHuge(page)) { /* take a lock against to access pc->mem_cgroup */ move_lock_page_cgroup(pc, &flags); need_unlock = true; - mem = pc->mem_cgroup; - if (!mem || !PageCgroupUsed(pc)) + memcg = pc->mem_cgroup; + if (!memcg || !PageCgroupUsed(pc)) goto out; } @@ -1988,7 +1970,7 @@ void mem_cgroup_update_page_stat(struct page *page, BUG(); } - this_cpu_add(mem->stat->count[idx], val); + this_cpu_add(memcg->stat->count[idx], val); out: if (unlikely(need_unlock)) @@ -2019,13 +2001,13 @@ static DEFINE_MUTEX(percpu_charge_mutex); * cgroup which is not current target, returns false. This stock will be * refilled. */ -static bool consume_stock(struct mem_cgroup *mem) +static bool consume_stock(struct mem_cgroup *memcg) { struct memcg_stock_pcp *stock; bool ret = true; stock = &get_cpu_var(memcg_stock); - if (mem == stock->cached && stock->nr_pages) + if (memcg == stock->cached && stock->nr_pages) stock->nr_pages--; else /* need to call res_counter_charge */ ret = false; @@ -2066,72 +2048,83 @@ static void drain_local_stock(struct work_struct *dummy) * Cache charges(val) which is from res_counter, to local per_cpu area. * This will be consumed by consume_stock() function, later. */ -static void refill_stock(struct mem_cgroup *mem, unsigned int nr_pages) +static void refill_stock(struct mem_cgroup *memcg, unsigned int nr_pages) { struct memcg_stock_pcp *stock = &get_cpu_var(memcg_stock); - if (stock->cached != mem) { /* reset if necessary */ + if (stock->cached != memcg) { /* reset if necessary */ drain_stock(stock); - stock->cached = mem; + stock->cached = memcg; } stock->nr_pages += nr_pages; put_cpu_var(memcg_stock); } /* - * Tries to drain stocked charges in other cpus. This function is asynchronous - * and just put a work per cpu for draining localy on each cpu. Caller can - * expects some charges will be back to res_counter later but cannot wait for - * it. + * Drains all per-CPU charge caches for given root_memcg resp. subtree + * of the hierarchy under it. sync flag says whether we should block + * until the work is done. */ -static void drain_all_stock_async(struct mem_cgroup *root_mem) +static void drain_all_stock(struct mem_cgroup *root_memcg, bool sync) { int cpu, curcpu; - /* - * If someone calls draining, avoid adding more kworker runs. - */ - if (!mutex_trylock(&percpu_charge_mutex)) - return; + /* Notify other cpus that system-wide "drain" is running */ get_online_cpus(); - /* - * Get a hint for avoiding draining charges on the current cpu, - * which must be exhausted by our charging. It is not required that - * this be a precise check, so we use raw_smp_processor_id() instead of - * getcpu()/putcpu(). - */ - curcpu = raw_smp_processor_id(); + curcpu = get_cpu(); for_each_online_cpu(cpu) { struct memcg_stock_pcp *stock = &per_cpu(memcg_stock, cpu); - struct mem_cgroup *mem; + struct mem_cgroup *memcg; - if (cpu == curcpu) + memcg = stock->cached; + if (!memcg || !stock->nr_pages) continue; - - mem = stock->cached; - if (!mem) + if (!mem_cgroup_same_or_subtree(root_memcg, memcg)) continue; - if (mem != root_mem) { - if (!root_mem->use_hierarchy) - continue; - /* check whether "mem" is under tree of "root_mem" */ - if (!css_is_ancestor(&mem->css, &root_mem->css)) - continue; + if (!test_and_set_bit(FLUSHING_CACHED_CHARGE, &stock->flags)) { + if (cpu == curcpu) + drain_local_stock(&stock->work); + else + schedule_work_on(cpu, &stock->work); } - if (!test_and_set_bit(FLUSHING_CACHED_CHARGE, &stock->flags)) - schedule_work_on(cpu, &stock->work); } + put_cpu(); + + if (!sync) + goto out; + + for_each_online_cpu(cpu) { + struct memcg_stock_pcp *stock = &per_cpu(memcg_stock, cpu); + if (test_bit(FLUSHING_CACHED_CHARGE, &stock->flags)) + flush_work(&stock->work); + } +out: put_online_cpus(); +} + +/* + * Tries to drain stocked charges in other cpus. This function is asynchronous + * and just put a work per cpu for draining localy on each cpu. Caller can + * expects some charges will be back to res_counter later but cannot wait for + * it. + */ +static void drain_all_stock_async(struct mem_cgroup *root_memcg) +{ + /* + * If someone calls draining, avoid adding more kworker runs. + */ + if (!mutex_trylock(&percpu_charge_mutex)) + return; + drain_all_stock(root_memcg, false); mutex_unlock(&percpu_charge_mutex); - /* We don't wait for flush_work */ } /* This is a synchronous drain interface. */ -static void drain_all_stock_sync(void) +static void drain_all_stock_sync(struct mem_cgroup *root_memcg) { /* called when force_empty is called */ mutex_lock(&percpu_charge_mutex); - schedule_on_each_cpu(drain_local_stock); + drain_all_stock(root_memcg, true); mutex_unlock(&percpu_charge_mutex); } @@ -2139,35 +2132,35 @@ static void drain_all_stock_sync(void) * This function drains percpu counter value from DEAD cpu and * move it to local cpu. Note that this function can be preempted. */ -static void mem_cgroup_drain_pcp_counter(struct mem_cgroup *mem, int cpu) +static void mem_cgroup_drain_pcp_counter(struct mem_cgroup *memcg, int cpu) { int i; - spin_lock(&mem->pcp_counter_lock); + spin_lock(&memcg->pcp_counter_lock); for (i = 0; i < MEM_CGROUP_STAT_DATA; i++) { - long x = per_cpu(mem->stat->count[i], cpu); + long x = per_cpu(memcg->stat->count[i], cpu); - per_cpu(mem->stat->count[i], cpu) = 0; - mem->nocpu_base.count[i] += x; + per_cpu(memcg->stat->count[i], cpu) = 0; + memcg->nocpu_base.count[i] += x; } for (i = 0; i < MEM_CGROUP_EVENTS_NSTATS; i++) { - unsigned long x = per_cpu(mem->stat->events[i], cpu); + unsigned long x = per_cpu(memcg->stat->events[i], cpu); - per_cpu(mem->stat->events[i], cpu) = 0; - mem->nocpu_base.events[i] += x; + per_cpu(memcg->stat->events[i], cpu) = 0; + memcg->nocpu_base.events[i] += x; } /* need to clear ON_MOVE value, works as a kind of lock. */ - per_cpu(mem->stat->count[MEM_CGROUP_ON_MOVE], cpu) = 0; - spin_unlock(&mem->pcp_counter_lock); + per_cpu(memcg->stat->count[MEM_CGROUP_ON_MOVE], cpu) = 0; + spin_unlock(&memcg->pcp_counter_lock); } -static void synchronize_mem_cgroup_on_move(struct mem_cgroup *mem, int cpu) +static void synchronize_mem_cgroup_on_move(struct mem_cgroup *memcg, int cpu) { int idx = MEM_CGROUP_ON_MOVE; - spin_lock(&mem->pcp_counter_lock); - per_cpu(mem->stat->count[idx], cpu) = mem->nocpu_base.count[idx]; - spin_unlock(&mem->pcp_counter_lock); + spin_lock(&memcg->pcp_counter_lock); + per_cpu(memcg->stat->count[idx], cpu) = memcg->nocpu_base.count[idx]; + spin_unlock(&memcg->pcp_counter_lock); } static int __cpuinit memcg_cpu_hotplug_callback(struct notifier_block *nb, @@ -2205,7 +2198,7 @@ enum { CHARGE_OOM_DIE, /* the current is killed because of OOM */ }; -static int mem_cgroup_do_charge(struct mem_cgroup *mem, gfp_t gfp_mask, +static int mem_cgroup_do_charge(struct mem_cgroup *memcg, gfp_t gfp_mask, unsigned int nr_pages, bool oom_check) { unsigned long csize = nr_pages * PAGE_SIZE; @@ -2214,16 +2207,16 @@ static int mem_cgroup_do_charge(struct mem_cgroup *mem, gfp_t gfp_mask, unsigned long flags = 0; int ret; - ret = res_counter_charge(&mem->res, csize, &fail_res); + ret = res_counter_charge(&memcg->res, csize, &fail_res); if (likely(!ret)) { if (!do_swap_account) return CHARGE_OK; - ret = res_counter_charge(&mem->memsw, csize, &fail_res); + ret = res_counter_charge(&memcg->memsw, csize, &fail_res); if (likely(!ret)) return CHARGE_OK; - res_counter_uncharge(&mem->res, csize); + res_counter_uncharge(&memcg->res, csize); mem_over_limit = mem_cgroup_from_res_counter(fail_res, memsw); flags |= MEM_CGROUP_RECLAIM_NOSWAP; } else @@ -2281,12 +2274,12 @@ static int mem_cgroup_do_charge(struct mem_cgroup *mem, gfp_t gfp_mask, static int __mem_cgroup_try_charge(struct mm_struct *mm, gfp_t gfp_mask, unsigned int nr_pages, - struct mem_cgroup **memcg, + struct mem_cgroup **ptr, bool oom) { unsigned int batch = max(CHARGE_BATCH, nr_pages); int nr_oom_retries = MEM_CGROUP_RECLAIM_RETRIES; - struct mem_cgroup *mem = NULL; + struct mem_cgroup *memcg = NULL; int ret; /* @@ -2304,17 +2297,17 @@ static int __mem_cgroup_try_charge(struct mm_struct *mm, * thread group leader migrates. It's possible that mm is not * set, if so charge the init_mm (happens for pagecache usage). */ - if (!*memcg && !mm) + if (!*ptr && !mm) goto bypass; again: - if (*memcg) { /* css should be a valid one */ - mem = *memcg; - VM_BUG_ON(css_is_removed(&mem->css)); - if (mem_cgroup_is_root(mem)) + if (*ptr) { /* css should be a valid one */ + memcg = *ptr; + VM_BUG_ON(css_is_removed(&memcg->css)); + if (mem_cgroup_is_root(memcg)) goto done; - if (nr_pages == 1 && consume_stock(mem)) + if (nr_pages == 1 && consume_stock(memcg)) goto done; - css_get(&mem->css); + css_get(&memcg->css); } else { struct task_struct *p; @@ -2322,7 +2315,7 @@ again: p = rcu_dereference(mm->owner); /* * Because we don't have task_lock(), "p" can exit. - * In that case, "mem" can point to root or p can be NULL with + * In that case, "memcg" can point to root or p can be NULL with * race with swapoff. Then, we have small risk of mis-accouning. * But such kind of mis-account by race always happens because * we don't have cgroup_mutex(). It's overkill and we allo that @@ -2330,12 +2323,12 @@ again: * (*) swapoff at el will charge against mm-struct not against * task-struct. So, mm->owner can be NULL. */ - mem = mem_cgroup_from_task(p); - if (!mem || mem_cgroup_is_root(mem)) { + memcg = mem_cgroup_from_task(p); + if (!memcg || mem_cgroup_is_root(memcg)) { rcu_read_unlock(); goto done; } - if (nr_pages == 1 && consume_stock(mem)) { + if (nr_pages == 1 && consume_stock(memcg)) { /* * It seems dagerous to access memcg without css_get(). * But considering how consume_stok works, it's not @@ -2348,7 +2341,7 @@ again: goto done; } /* after here, we may be blocked. we need to get refcnt */ - if (!css_tryget(&mem->css)) { + if (!css_tryget(&memcg->css)) { rcu_read_unlock(); goto again; } @@ -2360,7 +2353,7 @@ again: /* If killed, bypass charge */ if (fatal_signal_pending(current)) { - css_put(&mem->css); + css_put(&memcg->css); goto bypass; } @@ -2370,43 +2363,43 @@ again: nr_oom_retries = MEM_CGROUP_RECLAIM_RETRIES; } - ret = mem_cgroup_do_charge(mem, gfp_mask, batch, oom_check); + ret = mem_cgroup_do_charge(memcg, gfp_mask, batch, oom_check); switch (ret) { case CHARGE_OK: break; case CHARGE_RETRY: /* not in OOM situation but retry */ batch = nr_pages; - css_put(&mem->css); - mem = NULL; + css_put(&memcg->css); + memcg = NULL; goto again; case CHARGE_WOULDBLOCK: /* !__GFP_WAIT */ - css_put(&mem->css); + css_put(&memcg->css); goto nomem; case CHARGE_NOMEM: /* OOM routine works */ if (!oom) { - css_put(&mem->css); + css_put(&memcg->css); goto nomem; } /* If oom, we never return -ENOMEM */ nr_oom_retries--; break; case CHARGE_OOM_DIE: /* Killed by OOM Killer */ - css_put(&mem->css); + css_put(&memcg->css); goto bypass; } } while (ret != CHARGE_OK); if (batch > nr_pages) - refill_stock(mem, batch - nr_pages); - css_put(&mem->css); + refill_stock(memcg, batch - nr_pages); + css_put(&memcg->css); done: - *memcg = mem; + *ptr = memcg; return 0; nomem: - *memcg = NULL; + *ptr = NULL; return -ENOMEM; bypass: - *memcg = NULL; + *ptr = NULL; return 0; } @@ -2415,15 +2408,15 @@ bypass: * This function is for that and do uncharge, put css's refcnt. * gotten by try_charge(). */ -static void __mem_cgroup_cancel_charge(struct mem_cgroup *mem, +static void __mem_cgroup_cancel_charge(struct mem_cgroup *memcg, unsigned int nr_pages) { - if (!mem_cgroup_is_root(mem)) { + if (!mem_cgroup_is_root(memcg)) { unsigned long bytes = nr_pages * PAGE_SIZE; - res_counter_uncharge(&mem->res, bytes); + res_counter_uncharge(&memcg->res, bytes); if (do_swap_account) - res_counter_uncharge(&mem->memsw, bytes); + res_counter_uncharge(&memcg->memsw, bytes); } } @@ -2448,7 +2441,7 @@ static struct mem_cgroup *mem_cgroup_lookup(unsigned short id) struct mem_cgroup *try_get_mem_cgroup_from_page(struct page *page) { - struct mem_cgroup *mem = NULL; + struct mem_cgroup *memcg = NULL; struct page_cgroup *pc; unsigned short id; swp_entry_t ent; @@ -2458,23 +2451,23 @@ struct mem_cgroup *try_get_mem_cgroup_from_page(struct page *page) pc = lookup_page_cgroup(page); lock_page_cgroup(pc); if (PageCgroupUsed(pc)) { - mem = pc->mem_cgroup; - if (mem && !css_tryget(&mem->css)) - mem = NULL; + memcg = pc->mem_cgroup; + if (memcg && !css_tryget(&memcg->css)) + memcg = NULL; } else if (PageSwapCache(page)) { 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; + memcg = mem_cgroup_lookup(id); + if (memcg && !css_tryget(&memcg->css)) + memcg = NULL; rcu_read_unlock(); } unlock_page_cgroup(pc); - return mem; + return memcg; } -static void __mem_cgroup_commit_charge(struct mem_cgroup *mem, +static void __mem_cgroup_commit_charge(struct mem_cgroup *memcg, struct page *page, unsigned int nr_pages, struct page_cgroup *pc, @@ -2483,14 +2476,14 @@ static void __mem_cgroup_commit_charge(struct mem_cgroup *mem, lock_page_cgroup(pc); if (unlikely(PageCgroupUsed(pc))) { unlock_page_cgroup(pc); - __mem_cgroup_cancel_charge(mem, nr_pages); + __mem_cgroup_cancel_charge(memcg, nr_pages); return; } /* * we don't need page_cgroup_lock about tail pages, becase they are not * accessed by any other context at this point. */ - pc->mem_cgroup = mem; + pc->mem_cgroup = memcg; /* * We access a page_cgroup asynchronously without lock_page_cgroup(). * Especially when a page_cgroup is taken from a page, pc->mem_cgroup @@ -2513,14 +2506,14 @@ static void __mem_cgroup_commit_charge(struct mem_cgroup *mem, break; } - mem_cgroup_charge_statistics(mem, PageCgroupCache(pc), nr_pages); + mem_cgroup_charge_statistics(memcg, PageCgroupCache(pc), nr_pages); unlock_page_cgroup(pc); /* * "charge_statistics" updated event counter. Then, check it. * Insert ancestor (and ancestor's ancestors), to softlimit RB-tree. * if they exceeds softlimit. */ - memcg_check_events(mem, page); + memcg_check_events(memcg, page); } #ifdef CONFIG_TRANSPARENT_HUGEPAGE @@ -2707,7 +2700,7 @@ out: static int mem_cgroup_charge_common(struct page *page, struct mm_struct *mm, gfp_t gfp_mask, enum charge_type ctype) { - struct mem_cgroup *mem = NULL; + struct mem_cgroup *memcg = NULL; unsigned int nr_pages = 1; struct page_cgroup *pc; bool oom = true; @@ -2726,11 +2719,11 @@ static int mem_cgroup_charge_common(struct page *page, struct mm_struct *mm, pc = lookup_page_cgroup(page); BUG_ON(!pc); /* XXX: remove this and move pc lookup into commit */ - ret = __mem_cgroup_try_charge(mm, gfp_mask, nr_pages, &mem, oom); - if (ret || !mem) + ret = __mem_cgroup_try_charge(mm, gfp_mask, nr_pages, &memcg, oom); + if (ret || !memcg) return ret; - __mem_cgroup_commit_charge(mem, page, nr_pages, pc, ctype); + __mem_cgroup_commit_charge(memcg, page, nr_pages, pc, ctype); return 0; } @@ -2759,7 +2752,7 @@ __mem_cgroup_commit_charge_swapin(struct page *page, struct mem_cgroup *ptr, enum charge_type ctype); static void -__mem_cgroup_commit_charge_lrucare(struct page *page, struct mem_cgroup *mem, +__mem_cgroup_commit_charge_lrucare(struct page *page, struct mem_cgroup *memcg, enum charge_type ctype) { struct page_cgroup *pc = lookup_page_cgroup(page); @@ -2769,7 +2762,7 @@ __mem_cgroup_commit_charge_lrucare(struct page *page, struct mem_cgroup *mem, * LRU. Take care of it. */ mem_cgroup_lru_del_before_commit(page); - __mem_cgroup_commit_charge(mem, page, 1, pc, ctype); + __mem_cgroup_commit_charge(memcg, page, 1, pc, ctype); mem_cgroup_lru_add_after_commit(page); return; } @@ -2777,44 +2770,20 @@ __mem_cgroup_commit_charge_lrucare(struct page *page, struct mem_cgroup *mem, int mem_cgroup_cache_charge(struct page *page, struct mm_struct *mm, gfp_t gfp_mask) { - struct mem_cgroup *mem = NULL; + struct mem_cgroup *memcg = NULL; int ret; if (mem_cgroup_disabled()) return 0; if (PageCompound(page)) return 0; - /* - * Corner case handling. This is called from add_to_page_cache() - * in usual. But some FS (shmem) precharges this page before calling it - * and call add_to_page_cache() with GFP_NOWAIT. - * - * For GFP_NOWAIT case, the page may be pre-charged before calling - * add_to_page_cache(). (See shmem.c) check it here and avoid to call - * charge twice. (It works but has to pay a bit larger cost.) - * And when the page is SwapCache, it should take swap information - * into account. This is under lock_page() now. - */ - if (!(gfp_mask & __GFP_WAIT)) { - struct page_cgroup *pc; - - pc = lookup_page_cgroup(page); - if (!pc) - return 0; - lock_page_cgroup(pc); - if (PageCgroupUsed(pc)) { - unlock_page_cgroup(pc); - return 0; - } - unlock_page_cgroup(pc); - } if (unlikely(!mm)) mm = &init_mm; if (page_is_file_cache(page)) { - ret = __mem_cgroup_try_charge(mm, gfp_mask, 1, &mem, true); - if (ret || !mem) + ret = __mem_cgroup_try_charge(mm, gfp_mask, 1, &memcg, true); + if (ret || !memcg) return ret; /* @@ -2822,15 +2791,15 @@ int mem_cgroup_cache_charge(struct page *page, struct mm_struct *mm, * put that would remove them from the LRU list, make * sure that they get relinked properly. */ - __mem_cgroup_commit_charge_lrucare(page, mem, + __mem_cgroup_commit_charge_lrucare(page, memcg, MEM_CGROUP_CHARGE_TYPE_CACHE); return ret; } /* shmem */ if (PageSwapCache(page)) { - ret = mem_cgroup_try_charge_swapin(mm, page, gfp_mask, &mem); + ret = mem_cgroup_try_charge_swapin(mm, page, gfp_mask, &memcg); if (!ret) - __mem_cgroup_commit_charge_swapin(page, mem, + __mem_cgroup_commit_charge_swapin(page, memcg, MEM_CGROUP_CHARGE_TYPE_SHMEM); } else ret = mem_cgroup_charge_common(page, mm, gfp_mask, @@ -2849,7 +2818,7 @@ int mem_cgroup_try_charge_swapin(struct mm_struct *mm, struct page *page, gfp_t mask, struct mem_cgroup **ptr) { - struct mem_cgroup *mem; + struct mem_cgroup *memcg; int ret; *ptr = NULL; @@ -2867,12 +2836,12 @@ int mem_cgroup_try_charge_swapin(struct mm_struct *mm, */ if (!PageSwapCache(page)) goto charge_cur_mm; - mem = try_get_mem_cgroup_from_page(page); - if (!mem) + memcg = try_get_mem_cgroup_from_page(page); + if (!memcg) goto charge_cur_mm; - *ptr = mem; + *ptr = memcg; ret = __mem_cgroup_try_charge(NULL, mask, 1, ptr, true); - css_put(&mem->css); + css_put(&memcg->css); return ret; charge_cur_mm: if (unlikely(!mm)) @@ -2932,16 +2901,16 @@ void mem_cgroup_commit_charge_swapin(struct page *page, struct mem_cgroup *ptr) MEM_CGROUP_CHARGE_TYPE_MAPPED); } -void mem_cgroup_cancel_charge_swapin(struct mem_cgroup *mem) +void mem_cgroup_cancel_charge_swapin(struct mem_cgroup *memcg) { if (mem_cgroup_disabled()) return; - if (!mem) + if (!memcg) return; - __mem_cgroup_cancel_charge(mem, 1); + __mem_cgroup_cancel_charge(memcg, 1); } -static void mem_cgroup_do_uncharge(struct mem_cgroup *mem, +static void mem_cgroup_do_uncharge(struct mem_cgroup *memcg, unsigned int nr_pages, const enum charge_type ctype) { @@ -2959,7 +2928,7 @@ static void mem_cgroup_do_uncharge(struct mem_cgroup *mem, * uncharges. Then, it's ok to ignore memcg's refcnt. */ if (!batch->memcg) - batch->memcg = mem; + batch->memcg = memcg; /* * do_batch > 0 when unmapping pages or inode invalidate/truncate. * In those cases, all pages freed continuously can be expected to be in @@ -2979,7 +2948,7 @@ static void mem_cgroup_do_uncharge(struct mem_cgroup *mem, * merge a series of uncharges to an uncharge of res_counter. * If not, we uncharge res_counter ony by one. */ - if (batch->memcg != mem) + if (batch->memcg != memcg) goto direct_uncharge; /* remember freed charge and uncharge it later */ batch->nr_pages++; @@ -2987,11 +2956,11 @@ static void mem_cgroup_do_uncharge(struct mem_cgroup *mem, batch->memsw_nr_pages++; return; direct_uncharge: - res_counter_uncharge(&mem->res, nr_pages * PAGE_SIZE); + res_counter_uncharge(&memcg->res, nr_pages * PAGE_SIZE); if (uncharge_memsw) - res_counter_uncharge(&mem->memsw, nr_pages * PAGE_SIZE); - if (unlikely(batch->memcg != mem)) - memcg_oom_recover(mem); + res_counter_uncharge(&memcg->memsw, nr_pages * PAGE_SIZE); + if (unlikely(batch->memcg != memcg)) + memcg_oom_recover(memcg); return; } @@ -3001,7 +2970,7 @@ direct_uncharge: static struct mem_cgroup * __mem_cgroup_uncharge_common(struct page *page, enum charge_type ctype) { - struct mem_cgroup *mem = NULL; + struct mem_cgroup *memcg = NULL; unsigned int nr_pages = 1; struct page_cgroup *pc; @@ -3024,7 +2993,7 @@ __mem_cgroup_uncharge_common(struct page *page, enum charge_type ctype) lock_page_cgroup(pc); - mem = pc->mem_cgroup; + memcg = pc->mem_cgroup; if (!PageCgroupUsed(pc)) goto unlock_out; @@ -3047,7 +3016,7 @@ __mem_cgroup_uncharge_common(struct page *page, enum charge_type ctype) break; } - mem_cgroup_charge_statistics(mem, PageCgroupCache(pc), -nr_pages); + mem_cgroup_charge_statistics(memcg, PageCgroupCache(pc), -nr_pages); ClearPageCgroupUsed(pc); /* @@ -3059,18 +3028,18 @@ __mem_cgroup_uncharge_common(struct page *page, enum charge_type ctype) unlock_page_cgroup(pc); /* - * even after unlock, we have mem->res.usage here and this memcg + * even after unlock, we have memcg->res.usage here and this memcg * will never be freed. */ - memcg_check_events(mem, page); + memcg_check_events(memcg, page); if (do_swap_account && ctype == MEM_CGROUP_CHARGE_TYPE_SWAPOUT) { - mem_cgroup_swap_statistics(mem, true); - mem_cgroup_get(mem); + mem_cgroup_swap_statistics(memcg, true); + mem_cgroup_get(memcg); } - if (!mem_cgroup_is_root(mem)) - mem_cgroup_do_uncharge(mem, nr_pages, ctype); + if (!mem_cgroup_is_root(memcg)) + mem_cgroup_do_uncharge(memcg, nr_pages, ctype); - return mem; + return memcg; unlock_out: unlock_page_cgroup(pc); @@ -3260,7 +3229,7 @@ static inline int mem_cgroup_move_swap_account(swp_entry_t entry, int mem_cgroup_prepare_migration(struct page *page, struct page *newpage, struct mem_cgroup **ptr, gfp_t gfp_mask) { - struct mem_cgroup *mem = NULL; + struct mem_cgroup *memcg = NULL; struct page_cgroup *pc; enum charge_type ctype; int ret = 0; @@ -3274,8 +3243,8 @@ int mem_cgroup_prepare_migration(struct page *page, pc = lookup_page_cgroup(page); lock_page_cgroup(pc); if (PageCgroupUsed(pc)) { - mem = pc->mem_cgroup; - css_get(&mem->css); + memcg = pc->mem_cgroup; + css_get(&memcg->css); /* * At migrating an anonymous page, its mapcount goes down * to 0 and uncharge() will be called. But, even if it's fully @@ -3313,12 +3282,12 @@ int mem_cgroup_prepare_migration(struct page *page, * If the page is not charged at this point, * we return here. */ - if (!mem) + if (!memcg) return 0; - *ptr = mem; + *ptr = memcg; ret = __mem_cgroup_try_charge(NULL, gfp_mask, 1, ptr, false); - css_put(&mem->css);/* drop extra refcnt */ + css_put(&memcg->css);/* drop extra refcnt */ if (ret || *ptr == NULL) { if (PageAnon(page)) { lock_page_cgroup(pc); @@ -3344,21 +3313,21 @@ int mem_cgroup_prepare_migration(struct page *page, ctype = MEM_CGROUP_CHARGE_TYPE_CACHE; else ctype = MEM_CGROUP_CHARGE_TYPE_SHMEM; - __mem_cgroup_commit_charge(mem, page, 1, pc, ctype); + __mem_cgroup_commit_charge(memcg, page, 1, pc, ctype); return ret; } /* remove redundant charge if migration failed*/ -void mem_cgroup_end_migration(struct mem_cgroup *mem, +void mem_cgroup_end_migration(struct mem_cgroup *memcg, struct page *oldpage, struct page *newpage, bool migration_ok) { struct page *used, *unused; struct page_cgroup *pc; - if (!mem) + if (!memcg) return; /* blocks rmdir() */ - cgroup_exclude_rmdir(&mem->css); + cgroup_exclude_rmdir(&memcg->css); if (!migration_ok) { used = oldpage; unused = newpage; @@ -3394,32 +3363,7 @@ void mem_cgroup_end_migration(struct mem_cgroup *mem, * So, rmdir()->pre_destroy() can be called while we do this charge. * In that case, we need to call pre_destroy() again. check it here. */ - cgroup_release_and_wakeup_rmdir(&mem->css); -} - -/* - * A call to try to shrink memory usage on charge failure at shmem's swapin. - * Calling hierarchical_reclaim is not enough because we should update - * last_oom_jiffies to prevent pagefault_out_of_memory from invoking global OOM. - * Moreover considering hierarchy, we should reclaim from the mem_over_limit, - * not from the memcg which this page would be charged to. - * try_charge_swapin does all of these works properly. - */ -int mem_cgroup_shmem_charge_fallback(struct page *page, - struct mm_struct *mm, - gfp_t gfp_mask) -{ - struct mem_cgroup *mem; - int ret; - - if (mem_cgroup_disabled()) - return 0; - - ret = mem_cgroup_try_charge_swapin(mm, page, gfp_mask, &mem); - if (!ret) - mem_cgroup_cancel_charge_swapin(mem); /* it does !mem check */ - - return ret; + cgroup_release_and_wakeup_rmdir(&memcg->css); } #ifdef CONFIG_DEBUG_VM @@ -3498,7 +3442,7 @@ static int mem_cgroup_resize_limit(struct mem_cgroup *memcg, /* * Rather than hide all in some function, I do this in * open coded manner. You see what this really does. - * We have to guarantee mem->res.limit < mem->memsw.limit. + * We have to guarantee memcg->res.limit < memcg->memsw.limit. */ mutex_lock(&set_limit_mutex); memswlimit = res_counter_read_u64(&memcg->memsw, RES_LIMIT); @@ -3560,7 +3504,7 @@ static int mem_cgroup_resize_memsw_limit(struct mem_cgroup *memcg, /* * Rather than hide all in some function, I do this in * open coded manner. You see what this really does. - * We have to guarantee mem->res.limit < mem->memsw.limit. + * We have to guarantee memcg->res.limit < memcg->memsw.limit. */ mutex_lock(&set_limit_mutex); memlimit = res_counter_read_u64(&memcg->res, RES_LIMIT); @@ -3698,7 +3642,7 @@ unsigned long mem_cgroup_soft_limit_reclaim(struct zone *zone, int order, * This routine traverse page_cgroup in given list and drop them all. * *And* this routine doesn't reclaim page itself, just removes page_cgroup. */ -static int mem_cgroup_force_empty_list(struct mem_cgroup *mem, +static int mem_cgroup_force_empty_list(struct mem_cgroup *memcg, int node, int zid, enum lru_list lru) { struct zone *zone; @@ -3709,7 +3653,7 @@ static int mem_cgroup_force_empty_list(struct mem_cgroup *mem, int ret = 0; zone = &NODE_DATA(node)->node_zones[zid]; - mz = mem_cgroup_zoneinfo(mem, node, zid); + mz = mem_cgroup_zoneinfo(memcg, node, zid); list = &mz->lists[lru]; loop = MEM_CGROUP_ZSTAT(mz, lru); @@ -3736,7 +3680,7 @@ static int mem_cgroup_force_empty_list(struct mem_cgroup *mem, page = lookup_cgroup_page(pc); - ret = mem_cgroup_move_parent(page, pc, mem, GFP_KERNEL); + ret = mem_cgroup_move_parent(page, pc, memcg, GFP_KERNEL); if (ret == -ENOMEM) break; @@ -3757,14 +3701,14 @@ static int mem_cgroup_force_empty_list(struct mem_cgroup *mem, * make mem_cgroup's charge to be 0 if there is no task. * This enables deleting this mem_cgroup. */ -static int mem_cgroup_force_empty(struct mem_cgroup *mem, bool free_all) +static int mem_cgroup_force_empty(struct mem_cgroup *memcg, bool free_all) { int ret; int node, zid, shrink; int nr_retries = MEM_CGROUP_RECLAIM_RETRIES; - struct cgroup *cgrp = mem->css.cgroup; + struct cgroup *cgrp = memcg->css.cgroup; - css_get(&mem->css); + css_get(&memcg->css); shrink = 0; /* should free all ? */ @@ -3780,14 +3724,14 @@ move_account: goto out; /* This is for making all *used* pages to be on LRU. */ lru_add_drain_all(); - drain_all_stock_sync(); + drain_all_stock_sync(memcg); ret = 0; - mem_cgroup_start_move(mem); + mem_cgroup_start_move(memcg); for_each_node_state(node, N_HIGH_MEMORY) { for (zid = 0; !ret && zid < MAX_NR_ZONES; zid++) { enum lru_list l; for_each_lru(l) { - ret = mem_cgroup_force_empty_list(mem, + ret = mem_cgroup_force_empty_list(memcg, node, zid, l); if (ret) break; @@ -3796,16 +3740,16 @@ move_account: if (ret) break; } - mem_cgroup_end_move(mem); - memcg_oom_recover(mem); + mem_cgroup_end_move(memcg); + memcg_oom_recover(memcg); /* it seems parent cgroup doesn't have enough mem */ if (ret == -ENOMEM) goto try_to_free; cond_resched(); /* "ret" should also be checked to ensure all lists are empty. */ - } while (mem->res.usage > 0 || ret); + } while (memcg->res.usage > 0 || ret); out: - css_put(&mem->css); + css_put(&memcg->css); return ret; try_to_free: @@ -3818,15 +3762,15 @@ try_to_free: lru_add_drain_all(); /* try to free all pages in this cgroup */ shrink = 1; - while (nr_retries && mem->res.usage > 0) { + while (nr_retries && memcg->res.usage > 0) { int progress; if (signal_pending(current)) { ret = -EINTR; goto out; } - progress = try_to_free_mem_cgroup_pages(mem, GFP_KERNEL, - false, get_swappiness(mem)); + progress = try_to_free_mem_cgroup_pages(memcg, GFP_KERNEL, + false); if (!progress) { nr_retries--; /* maybe some writeback is necessary */ @@ -3854,12 +3798,12 @@ static int mem_cgroup_hierarchy_write(struct cgroup *cont, struct cftype *cft, u64 val) { int retval = 0; - struct mem_cgroup *mem = mem_cgroup_from_cont(cont); + struct mem_cgroup *memcg = mem_cgroup_from_cont(cont); struct cgroup *parent = cont->parent; - struct mem_cgroup *parent_mem = NULL; + struct mem_cgroup *parent_memcg = NULL; if (parent) - parent_mem = mem_cgroup_from_cont(parent); + parent_memcg = mem_cgroup_from_cont(parent); cgroup_lock(); /* @@ -3870,10 +3814,10 @@ static int mem_cgroup_hierarchy_write(struct cgroup *cont, struct cftype *cft, * For the root cgroup, parent_mem is NULL, we allow value to be * set if there are no children. */ - if ((!parent_mem || !parent_mem->use_hierarchy) && + if ((!parent_memcg || !parent_memcg->use_hierarchy) && (val == 1 || val == 0)) { if (list_empty(&cont->children)) - mem->use_hierarchy = val; + memcg->use_hierarchy = val; else retval = -EBUSY; } else @@ -3884,14 +3828,14 @@ static int mem_cgroup_hierarchy_write(struct cgroup *cont, struct cftype *cft, } -static unsigned long mem_cgroup_recursive_stat(struct mem_cgroup *mem, +static unsigned long mem_cgroup_recursive_stat(struct mem_cgroup *memcg, enum mem_cgroup_stat_index idx) { struct mem_cgroup *iter; long val = 0; /* Per-cpu values can be negative, use a signed accumulator */ - for_each_mem_cgroup_tree(iter, mem) + for_each_mem_cgroup_tree(iter, memcg) val += mem_cgroup_read_stat(iter, idx); if (val < 0) /* race ? */ @@ -3899,29 +3843,29 @@ static unsigned long mem_cgroup_recursive_stat(struct mem_cgroup *mem, return val; } -static inline u64 mem_cgroup_usage(struct mem_cgroup *mem, bool swap) +static inline u64 mem_cgroup_usage(struct mem_cgroup *memcg, bool swap) { u64 val; - if (!mem_cgroup_is_root(mem)) { + if (!mem_cgroup_is_root(memcg)) { if (!swap) - return res_counter_read_u64(&mem->res, RES_USAGE); + return res_counter_read_u64(&memcg->res, RES_USAGE); else - return res_counter_read_u64(&mem->memsw, RES_USAGE); + return res_counter_read_u64(&memcg->memsw, RES_USAGE); } - val = mem_cgroup_recursive_stat(mem, MEM_CGROUP_STAT_CACHE); - val += mem_cgroup_recursive_stat(mem, MEM_CGROUP_STAT_RSS); + val = mem_cgroup_recursive_stat(memcg, MEM_CGROUP_STAT_CACHE); + val += mem_cgroup_recursive_stat(memcg, MEM_CGROUP_STAT_RSS); if (swap) - val += mem_cgroup_recursive_stat(mem, MEM_CGROUP_STAT_SWAPOUT); + val += mem_cgroup_recursive_stat(memcg, MEM_CGROUP_STAT_SWAPOUT); return val << PAGE_SHIFT; } static u64 mem_cgroup_read(struct cgroup *cont, struct cftype *cft) { - struct mem_cgroup *mem = mem_cgroup_from_cont(cont); + struct mem_cgroup *memcg = mem_cgroup_from_cont(cont); u64 val; int type, name; @@ -3930,15 +3874,15 @@ static u64 mem_cgroup_read(struct cgroup *cont, struct cftype *cft) switch (type) { case _MEM: if (name == RES_USAGE) - val = mem_cgroup_usage(mem, false); + val = mem_cgroup_usage(memcg, false); else - val = res_counter_read_u64(&mem->res, name); + val = res_counter_read_u64(&memcg->res, name); break; case _MEMSWAP: if (name == RES_USAGE) - val = mem_cgroup_usage(mem, true); + val = mem_cgroup_usage(memcg, true); else - val = res_counter_read_u64(&mem->memsw, name); + val = res_counter_read_u64(&memcg->memsw, name); break; default: BUG(); @@ -4026,24 +3970,24 @@ out: static int mem_cgroup_reset(struct cgroup *cont, unsigned int event) { - struct mem_cgroup *mem; + struct mem_cgroup *memcg; int type, name; - mem = mem_cgroup_from_cont(cont); + memcg = mem_cgroup_from_cont(cont); type = MEMFILE_TYPE(event); name = MEMFILE_ATTR(event); switch (name) { case RES_MAX_USAGE: if (type == _MEM) - res_counter_reset_max(&mem->res); + res_counter_reset_max(&memcg->res); else - res_counter_reset_max(&mem->memsw); + res_counter_reset_max(&memcg->memsw); break; case RES_FAILCNT: if (type == _MEM) - res_counter_reset_failcnt(&mem->res); + res_counter_reset_failcnt(&memcg->res); else - res_counter_reset_failcnt(&mem->memsw); + res_counter_reset_failcnt(&memcg->memsw); break; } @@ -4060,7 +4004,7 @@ static u64 mem_cgroup_move_charge_read(struct cgroup *cgrp, static int mem_cgroup_move_charge_write(struct cgroup *cgrp, struct cftype *cft, u64 val) { - struct mem_cgroup *mem = mem_cgroup_from_cont(cgrp); + struct mem_cgroup *memcg = mem_cgroup_from_cont(cgrp); if (val >= (1 << NR_MOVE_TYPE)) return -EINVAL; @@ -4070,7 +4014,7 @@ static int mem_cgroup_move_charge_write(struct cgroup *cgrp, * inconsistent. */ cgroup_lock(); - mem->move_charge_at_immigrate = val; + memcg->move_charge_at_immigrate = val; cgroup_unlock(); return 0; @@ -4127,49 +4071,49 @@ struct { static void -mem_cgroup_get_local_stat(struct mem_cgroup *mem, struct mcs_total_stat *s) +mem_cgroup_get_local_stat(struct mem_cgroup *memcg, struct mcs_total_stat *s) { s64 val; /* per cpu stat */ - val = mem_cgroup_read_stat(mem, MEM_CGROUP_STAT_CACHE); + val = mem_cgroup_read_stat(memcg, MEM_CGROUP_STAT_CACHE); s->stat[MCS_CACHE] += val * PAGE_SIZE; - val = mem_cgroup_read_stat(mem, MEM_CGROUP_STAT_RSS); + val = mem_cgroup_read_stat(memcg, MEM_CGROUP_STAT_RSS); s->stat[MCS_RSS] += val * PAGE_SIZE; - val = mem_cgroup_read_stat(mem, MEM_CGROUP_STAT_FILE_MAPPED); + val = mem_cgroup_read_stat(memcg, MEM_CGROUP_STAT_FILE_MAPPED); s->stat[MCS_FILE_MAPPED] += val * PAGE_SIZE; - val = mem_cgroup_read_events(mem, MEM_CGROUP_EVENTS_PGPGIN); + val = mem_cgroup_read_events(memcg, MEM_CGROUP_EVENTS_PGPGIN); s->stat[MCS_PGPGIN] += val; - val = mem_cgroup_read_events(mem, MEM_CGROUP_EVENTS_PGPGOUT); + val = mem_cgroup_read_events(memcg, MEM_CGROUP_EVENTS_PGPGOUT); s->stat[MCS_PGPGOUT] += val; if (do_swap_account) { - val = mem_cgroup_read_stat(mem, MEM_CGROUP_STAT_SWAPOUT); + val = mem_cgroup_read_stat(memcg, MEM_CGROUP_STAT_SWAPOUT); s->stat[MCS_SWAP] += val * PAGE_SIZE; } - val = mem_cgroup_read_events(mem, MEM_CGROUP_EVENTS_PGFAULT); + val = mem_cgroup_read_events(memcg, MEM_CGROUP_EVENTS_PGFAULT); s->stat[MCS_PGFAULT] += val; - val = mem_cgroup_read_events(mem, MEM_CGROUP_EVENTS_PGMAJFAULT); + val = mem_cgroup_read_events(memcg, MEM_CGROUP_EVENTS_PGMAJFAULT); s->stat[MCS_PGMAJFAULT] += val; /* per zone stat */ - val = mem_cgroup_get_local_zonestat(mem, LRU_INACTIVE_ANON); + val = mem_cgroup_nr_lru_pages(memcg, BIT(LRU_INACTIVE_ANON)); s->stat[MCS_INACTIVE_ANON] += val * PAGE_SIZE; - val = mem_cgroup_get_local_zonestat(mem, LRU_ACTIVE_ANON); + val = mem_cgroup_nr_lru_pages(memcg, BIT(LRU_ACTIVE_ANON)); s->stat[MCS_ACTIVE_ANON] += val * PAGE_SIZE; - val = mem_cgroup_get_local_zonestat(mem, LRU_INACTIVE_FILE); + val = mem_cgroup_nr_lru_pages(memcg, BIT(LRU_INACTIVE_FILE)); s->stat[MCS_INACTIVE_FILE] += val * PAGE_SIZE; - val = mem_cgroup_get_local_zonestat(mem, LRU_ACTIVE_FILE); + val = mem_cgroup_nr_lru_pages(memcg, BIT(LRU_ACTIVE_FILE)); s->stat[MCS_ACTIVE_FILE] += val * PAGE_SIZE; - val = mem_cgroup_get_local_zonestat(mem, LRU_UNEVICTABLE); + val = mem_cgroup_nr_lru_pages(memcg, BIT(LRU_UNEVICTABLE)); s->stat[MCS_UNEVICTABLE] += val * PAGE_SIZE; } static void -mem_cgroup_get_total_stat(struct mem_cgroup *mem, struct mcs_total_stat *s) +mem_cgroup_get_total_stat(struct mem_cgroup *memcg, struct mcs_total_stat *s) { struct mem_cgroup *iter; - for_each_mem_cgroup_tree(iter, mem) + for_each_mem_cgroup_tree(iter, memcg) mem_cgroup_get_local_stat(iter, s); } @@ -4182,35 +4126,37 @@ static int mem_control_numa_stat_show(struct seq_file *m, void *arg) struct cgroup *cont = m->private; struct mem_cgroup *mem_cont = mem_cgroup_from_cont(cont); - total_nr = mem_cgroup_nr_lru_pages(mem_cont); + total_nr = mem_cgroup_nr_lru_pages(mem_cont, LRU_ALL); seq_printf(m, "total=%lu", total_nr); for_each_node_state(nid, N_HIGH_MEMORY) { - node_nr = mem_cgroup_node_nr_lru_pages(mem_cont, nid); + node_nr = mem_cgroup_node_nr_lru_pages(mem_cont, nid, LRU_ALL); seq_printf(m, " N%d=%lu", nid, node_nr); } seq_putc(m, '\n'); - file_nr = mem_cgroup_nr_file_lru_pages(mem_cont); + file_nr = mem_cgroup_nr_lru_pages(mem_cont, LRU_ALL_FILE); seq_printf(m, "file=%lu", file_nr); for_each_node_state(nid, N_HIGH_MEMORY) { - node_nr = mem_cgroup_node_nr_file_lru_pages(mem_cont, nid); + node_nr = mem_cgroup_node_nr_lru_pages(mem_cont, nid, + LRU_ALL_FILE); seq_printf(m, " N%d=%lu", nid, node_nr); } seq_putc(m, '\n'); - anon_nr = mem_cgroup_nr_anon_lru_pages(mem_cont); + anon_nr = mem_cgroup_nr_lru_pages(mem_cont, LRU_ALL_ANON); seq_printf(m, "anon=%lu", anon_nr); for_each_node_state(nid, N_HIGH_MEMORY) { - node_nr = mem_cgroup_node_nr_anon_lru_pages(mem_cont, nid); + node_nr = mem_cgroup_node_nr_lru_pages(mem_cont, nid, + LRU_ALL_ANON); seq_printf(m, " N%d=%lu", nid, node_nr); } seq_putc(m, '\n'); - unevictable_nr = mem_cgroup_nr_unevictable_lru_pages(mem_cont); + unevictable_nr = mem_cgroup_nr_lru_pages(mem_cont, BIT(LRU_UNEVICTABLE)); seq_printf(m, "unevictable=%lu", unevictable_nr); for_each_node_state(nid, N_HIGH_MEMORY) { - node_nr = mem_cgroup_node_nr_unevictable_lru_pages(mem_cont, - nid); + node_nr = mem_cgroup_node_nr_lru_pages(mem_cont, nid, + BIT(LRU_UNEVICTABLE)); seq_printf(m, " N%d=%lu", nid, node_nr); } seq_putc(m, '\n'); @@ -4253,8 +4199,6 @@ static int mem_control_stat_show(struct cgroup *cont, struct cftype *cft, } #ifdef CONFIG_DEBUG_VM - cb->fill(cb, "inactive_ratio", calc_inactive_ratio(mem_cont, NULL)); - { int nid, zid; struct mem_cgroup_per_zone *mz; @@ -4288,7 +4232,7 @@ static u64 mem_cgroup_swappiness_read(struct cgroup *cgrp, struct cftype *cft) { struct mem_cgroup *memcg = mem_cgroup_from_cont(cgrp); - return get_swappiness(memcg); + return mem_cgroup_swappiness(memcg); } static int mem_cgroup_swappiness_write(struct cgroup *cgrp, struct cftype *cft, @@ -4391,20 +4335,20 @@ static int compare_thresholds(const void *a, const void *b) return _a->threshold - _b->threshold; } -static int mem_cgroup_oom_notify_cb(struct mem_cgroup *mem) +static int mem_cgroup_oom_notify_cb(struct mem_cgroup *memcg) { struct mem_cgroup_eventfd_list *ev; - list_for_each_entry(ev, &mem->oom_notify, list) + list_for_each_entry(ev, &memcg->oom_notify, list) eventfd_signal(ev->eventfd, 1); return 0; } -static void mem_cgroup_oom_notify(struct mem_cgroup *mem) +static void mem_cgroup_oom_notify(struct mem_cgroup *memcg) { struct mem_cgroup *iter; - for_each_mem_cgroup_tree(iter, mem) + for_each_mem_cgroup_tree(iter, memcg) mem_cgroup_oom_notify_cb(iter); } @@ -4578,15 +4522,15 @@ static int mem_cgroup_oom_register_event(struct cgroup *cgrp, if (!event) return -ENOMEM; - mutex_lock(&memcg_oom_mutex); + spin_lock(&memcg_oom_lock); event->eventfd = eventfd; list_add(&event->list, &memcg->oom_notify); /* already in OOM ? */ - if (atomic_read(&memcg->oom_lock)) + if (atomic_read(&memcg->under_oom)) eventfd_signal(eventfd, 1); - mutex_unlock(&memcg_oom_mutex); + spin_unlock(&memcg_oom_lock); return 0; } @@ -4594,32 +4538,32 @@ static int mem_cgroup_oom_register_event(struct cgroup *cgrp, static void mem_cgroup_oom_unregister_event(struct cgroup *cgrp, struct cftype *cft, struct eventfd_ctx *eventfd) { - struct mem_cgroup *mem = mem_cgroup_from_cont(cgrp); + struct mem_cgroup *memcg = mem_cgroup_from_cont(cgrp); struct mem_cgroup_eventfd_list *ev, *tmp; int type = MEMFILE_TYPE(cft->private); BUG_ON(type != _OOM_TYPE); - mutex_lock(&memcg_oom_mutex); + spin_lock(&memcg_oom_lock); - list_for_each_entry_safe(ev, tmp, &mem->oom_notify, list) { + list_for_each_entry_safe(ev, tmp, &memcg->oom_notify, list) { if (ev->eventfd == eventfd) { list_del(&ev->list); kfree(ev); } } - mutex_unlock(&memcg_oom_mutex); + spin_unlock(&memcg_oom_lock); } static int mem_cgroup_oom_control_read(struct cgroup *cgrp, struct cftype *cft, struct cgroup_map_cb *cb) { - struct mem_cgroup *mem = mem_cgroup_from_cont(cgrp); + struct mem_cgroup *memcg = mem_cgroup_from_cont(cgrp); - cb->fill(cb, "oom_kill_disable", mem->oom_kill_disable); + cb->fill(cb, "oom_kill_disable", memcg->oom_kill_disable); - if (atomic_read(&mem->oom_lock)) + if (atomic_read(&memcg->under_oom)) cb->fill(cb, "under_oom", 1); else cb->fill(cb, "under_oom", 0); @@ -4629,7 +4573,7 @@ static int mem_cgroup_oom_control_read(struct cgroup *cgrp, static int mem_cgroup_oom_control_write(struct cgroup *cgrp, struct cftype *cft, u64 val) { - struct mem_cgroup *mem = mem_cgroup_from_cont(cgrp); + struct mem_cgroup *memcg = mem_cgroup_from_cont(cgrp); struct mem_cgroup *parent; /* cannot set to root cgroup and only 0 and 1 are allowed */ @@ -4641,13 +4585,13 @@ static int mem_cgroup_oom_control_write(struct cgroup *cgrp, cgroup_lock(); /* oom-kill-disable is a flag for subhierarchy. */ if ((parent->use_hierarchy) || - (mem->use_hierarchy && !list_empty(&cgrp->children))) { + (memcg->use_hierarchy && !list_empty(&cgrp->children))) { cgroup_unlock(); return -EINVAL; } - mem->oom_kill_disable = val; + memcg->oom_kill_disable = val; if (!val) - memcg_oom_recover(mem); + memcg_oom_recover(memcg); cgroup_unlock(); return 0; } @@ -4783,7 +4727,7 @@ static int register_memsw_files(struct cgroup *cont, struct cgroup_subsys *ss) } #endif -static int alloc_mem_cgroup_per_zone_info(struct mem_cgroup *mem, int node) +static int alloc_mem_cgroup_per_zone_info(struct mem_cgroup *memcg, int node) { struct mem_cgroup_per_node *pn; struct mem_cgroup_per_zone *mz; @@ -4803,21 +4747,21 @@ static int alloc_mem_cgroup_per_zone_info(struct mem_cgroup *mem, int node) if (!pn) return 1; - mem->info.nodeinfo[node] = pn; for (zone = 0; zone < MAX_NR_ZONES; zone++) { mz = &pn->zoneinfo[zone]; for_each_lru(l) INIT_LIST_HEAD(&mz->lists[l]); mz->usage_in_excess = 0; mz->on_tree = false; - mz->mem = mem; + mz->mem = memcg; } + memcg->info.nodeinfo[node] = pn; return 0; } -static void free_mem_cgroup_per_zone_info(struct mem_cgroup *mem, int node) +static void free_mem_cgroup_per_zone_info(struct mem_cgroup *memcg, int node) { - kfree(mem->info.nodeinfo[node]); + kfree(memcg->info.nodeinfo[node]); } static struct mem_cgroup *mem_cgroup_alloc(void) @@ -4859,51 +4803,51 @@ out_free: * Removal of cgroup itself succeeds regardless of refs from swap. */ -static void __mem_cgroup_free(struct mem_cgroup *mem) +static void __mem_cgroup_free(struct mem_cgroup *memcg) { int node; - mem_cgroup_remove_from_trees(mem); - free_css_id(&mem_cgroup_subsys, &mem->css); + mem_cgroup_remove_from_trees(memcg); + free_css_id(&mem_cgroup_subsys, &memcg->css); for_each_node_state(node, N_POSSIBLE) - free_mem_cgroup_per_zone_info(mem, node); + free_mem_cgroup_per_zone_info(memcg, node); - free_percpu(mem->stat); + free_percpu(memcg->stat); if (sizeof(struct mem_cgroup) < PAGE_SIZE) - kfree(mem); + kfree(memcg); else - vfree(mem); + vfree(memcg); } -static void mem_cgroup_get(struct mem_cgroup *mem) +static void mem_cgroup_get(struct mem_cgroup *memcg) { - atomic_inc(&mem->refcnt); + atomic_inc(&memcg->refcnt); } -static void __mem_cgroup_put(struct mem_cgroup *mem, int count) +static void __mem_cgroup_put(struct mem_cgroup *memcg, int count) { - if (atomic_sub_and_test(count, &mem->refcnt)) { - struct mem_cgroup *parent = parent_mem_cgroup(mem); - __mem_cgroup_free(mem); + if (atomic_sub_and_test(count, &memcg->refcnt)) { + struct mem_cgroup *parent = parent_mem_cgroup(memcg); + __mem_cgroup_free(memcg); if (parent) mem_cgroup_put(parent); } } -static void mem_cgroup_put(struct mem_cgroup *mem) +static void mem_cgroup_put(struct mem_cgroup *memcg) { - __mem_cgroup_put(mem, 1); + __mem_cgroup_put(memcg, 1); } /* * Returns the parent mem_cgroup in memcgroup hierarchy with hierarchy enabled. */ -static struct mem_cgroup *parent_mem_cgroup(struct mem_cgroup *mem) +static struct mem_cgroup *parent_mem_cgroup(struct mem_cgroup *memcg) { - if (!mem->res.parent) + if (!memcg->res.parent) return NULL; - return mem_cgroup_from_res_counter(mem->res.parent, res); + return mem_cgroup_from_res_counter(memcg->res.parent, res); } #ifdef CONFIG_CGROUP_MEM_RES_CTLR_SWAP @@ -4946,16 +4890,16 @@ static int mem_cgroup_soft_limit_tree_init(void) static struct cgroup_subsys_state * __ref mem_cgroup_create(struct cgroup_subsys *ss, struct cgroup *cont) { - struct mem_cgroup *mem, *parent; + struct mem_cgroup *memcg, *parent; long error = -ENOMEM; int node; - mem = mem_cgroup_alloc(); - if (!mem) + memcg = mem_cgroup_alloc(); + if (!memcg) return ERR_PTR(error); for_each_node_state(node, N_POSSIBLE) - if (alloc_mem_cgroup_per_zone_info(mem, node)) + if (alloc_mem_cgroup_per_zone_info(memcg, node)) goto free_out; /* root ? */ @@ -4963,7 +4907,7 @@ mem_cgroup_create(struct cgroup_subsys *ss, struct cgroup *cont) int cpu; enable_swap_cgroup(); parent = NULL; - root_mem_cgroup = mem; + root_mem_cgroup = memcg; if (mem_cgroup_soft_limit_tree_init()) goto free_out; for_each_possible_cpu(cpu) { @@ -4974,13 +4918,13 @@ mem_cgroup_create(struct cgroup_subsys *ss, struct cgroup *cont) hotcpu_notifier(memcg_cpu_hotplug_callback, 0); } else { parent = mem_cgroup_from_cont(cont->parent); - mem->use_hierarchy = parent->use_hierarchy; - mem->oom_kill_disable = parent->oom_kill_disable; + memcg->use_hierarchy = parent->use_hierarchy; + memcg->oom_kill_disable = parent->oom_kill_disable; } if (parent && parent->use_hierarchy) { - res_counter_init(&mem->res, &parent->res); - res_counter_init(&mem->memsw, &parent->memsw); + res_counter_init(&memcg->res, &parent->res); + res_counter_init(&memcg->memsw, &parent->memsw); /* * We increment refcnt of the parent to ensure that we can * safely access it on res_counter_charge/uncharge. @@ -4989,21 +4933,21 @@ mem_cgroup_create(struct cgroup_subsys *ss, struct cgroup *cont) */ mem_cgroup_get(parent); } else { - res_counter_init(&mem->res, NULL); - res_counter_init(&mem->memsw, NULL); + res_counter_init(&memcg->res, NULL); + res_counter_init(&memcg->memsw, NULL); } - mem->last_scanned_child = 0; - mem->last_scanned_node = MAX_NUMNODES; - INIT_LIST_HEAD(&mem->oom_notify); + memcg->last_scanned_child = 0; + memcg->last_scanned_node = MAX_NUMNODES; + INIT_LIST_HEAD(&memcg->oom_notify); if (parent) - mem->swappiness = get_swappiness(parent); - atomic_set(&mem->refcnt, 1); - mem->move_charge_at_immigrate = 0; - mutex_init(&mem->thresholds_lock); - return &mem->css; + memcg->swappiness = mem_cgroup_swappiness(parent); + atomic_set(&memcg->refcnt, 1); + memcg->move_charge_at_immigrate = 0; + mutex_init(&memcg->thresholds_lock); + return &memcg->css; free_out: - __mem_cgroup_free(mem); + __mem_cgroup_free(memcg); root_mem_cgroup = NULL; return ERR_PTR(error); } @@ -5011,17 +4955,17 @@ free_out: static int mem_cgroup_pre_destroy(struct cgroup_subsys *ss, struct cgroup *cont) { - struct mem_cgroup *mem = mem_cgroup_from_cont(cont); + struct mem_cgroup *memcg = mem_cgroup_from_cont(cont); - return mem_cgroup_force_empty(mem, false); + return mem_cgroup_force_empty(memcg, 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 *memcg = mem_cgroup_from_cont(cont); - mem_cgroup_put(mem); + mem_cgroup_put(memcg); } static int mem_cgroup_populate(struct cgroup_subsys *ss, @@ -5044,9 +4988,9 @@ static int mem_cgroup_do_precharge(unsigned long count) { int ret = 0; int batch_count = PRECHARGE_COUNT_AT_ONCE; - struct mem_cgroup *mem = mc.to; + struct mem_cgroup *memcg = mc.to; - if (mem_cgroup_is_root(mem)) { + if (mem_cgroup_is_root(memcg)) { mc.precharge += count; /* we don't need css_get for root */ return ret; @@ -5055,16 +4999,16 @@ static int mem_cgroup_do_precharge(unsigned long count) if (count > 1) { struct res_counter *dummy; /* - * "mem" cannot be under rmdir() because we've already checked + * "memcg" cannot be under rmdir() because we've already checked * by cgroup_lock_live_cgroup() that it is not removed and we * are still under the same cgroup_mutex. So we can postpone * css_get(). */ - if (res_counter_charge(&mem->res, PAGE_SIZE * count, &dummy)) + if (res_counter_charge(&memcg->res, PAGE_SIZE * count, &dummy)) goto one_by_one; - if (do_swap_account && res_counter_charge(&mem->memsw, + if (do_swap_account && res_counter_charge(&memcg->memsw, PAGE_SIZE * count, &dummy)) { - res_counter_uncharge(&mem->res, PAGE_SIZE * count); + res_counter_uncharge(&memcg->res, PAGE_SIZE * count); goto one_by_one; } mc.precharge += count; @@ -5081,8 +5025,9 @@ one_by_one: batch_count = PRECHARGE_COUNT_AT_ONCE; cond_resched(); } - ret = __mem_cgroup_try_charge(NULL, GFP_KERNEL, 1, &mem, false); - if (ret || !mem) + ret = __mem_cgroup_try_charge(NULL, + GFP_KERNEL, 1, &memcg, false); + if (ret || !memcg) /* mem_cgroup_clear_mc() will do uncharge later */ return -ENOMEM; mc.precharge++; @@ -5181,15 +5126,17 @@ static struct page *mc_handle_file_pte(struct vm_area_struct *vma, pgoff = pte_to_pgoff(ptent); /* page is moved even if it's not RSS of this task(page-faulted). */ - if (!mapping_cap_swap_backed(mapping)) { /* normal file */ - page = find_get_page(mapping, pgoff); - } else { /* shmem/tmpfs file. we should take account of swap too. */ - swp_entry_t ent; - mem_cgroup_get_shmem_target(inode, pgoff, &page, &ent); + page = find_get_page(mapping, pgoff); + +#ifdef CONFIG_SWAP + /* shmem/tmpfs may report page out on swap: account for that too. */ + if (radix_tree_exceptional_entry(page)) { + swp_entry_t swap = radix_to_swp_entry(page); if (do_swap_account) - entry->val = ent.val; + *entry = swap; + page = find_get_page(&swapper_space, swap.val); } - +#endif return page; } @@ -5354,13 +5301,13 @@ static int mem_cgroup_can_attach(struct cgroup_subsys *ss, struct task_struct *p) { int ret = 0; - struct mem_cgroup *mem = mem_cgroup_from_cont(cgroup); + struct mem_cgroup *memcg = mem_cgroup_from_cont(cgroup); - if (mem->move_charge_at_immigrate) { + if (memcg->move_charge_at_immigrate) { struct mm_struct *mm; struct mem_cgroup *from = mem_cgroup_from_task(p); - VM_BUG_ON(from == mem); + VM_BUG_ON(from == memcg); mm = get_task_mm(p); if (!mm) @@ -5375,7 +5322,7 @@ static int mem_cgroup_can_attach(struct cgroup_subsys *ss, mem_cgroup_start_move(from); spin_lock(&mc.lock); mc.from = from; - mc.to = mem; + mc.to = memcg; spin_unlock(&mc.lock); /* We set mc.moving_task later */ diff --git a/mm/memory-failure.c b/mm/memory-failure.c index 740c4f5..06d3479 100644 --- a/mm/memory-failure.c +++ b/mm/memory-failure.c @@ -42,6 +42,7 @@ #include <linux/sched.h> #include <linux/ksm.h> #include <linux/rmap.h> +#include <linux/export.h> #include <linux/pagemap.h> #include <linux/swap.h> #include <linux/backing-dev.h> @@ -53,6 +54,7 @@ #include <linux/hugetlb.h> #include <linux/memory_hotplug.h> #include <linux/mm_inline.h> +#include <linux/kfifo.h> #include "internal.h" int sysctl_memory_failure_early_kill __read_mostly = 0; @@ -1178,6 +1180,97 @@ void memory_failure(unsigned long pfn, int trapno) __memory_failure(pfn, trapno, 0); } +#define MEMORY_FAILURE_FIFO_ORDER 4 +#define MEMORY_FAILURE_FIFO_SIZE (1 << MEMORY_FAILURE_FIFO_ORDER) + +struct memory_failure_entry { + unsigned long pfn; + int trapno; + int flags; +}; + +struct memory_failure_cpu { + DECLARE_KFIFO(fifo, struct memory_failure_entry, + MEMORY_FAILURE_FIFO_SIZE); + spinlock_t lock; + struct work_struct work; +}; + +static DEFINE_PER_CPU(struct memory_failure_cpu, memory_failure_cpu); + +/** + * memory_failure_queue - Schedule handling memory failure of a page. + * @pfn: Page Number of the corrupted page + * @trapno: Trap number reported in the signal to user space. + * @flags: Flags for memory failure handling + * + * This function is called by the low level hardware error handler + * when it detects hardware memory corruption of a page. It schedules + * the recovering of error page, including dropping pages, killing + * processes etc. + * + * The function is primarily of use for corruptions that + * happen outside the current execution context (e.g. when + * detected by a background scrubber) + * + * Can run in IRQ context. + */ +void memory_failure_queue(unsigned long pfn, int trapno, int flags) +{ + struct memory_failure_cpu *mf_cpu; + unsigned long proc_flags; + struct memory_failure_entry entry = { + .pfn = pfn, + .trapno = trapno, + .flags = flags, + }; + + mf_cpu = &get_cpu_var(memory_failure_cpu); + spin_lock_irqsave(&mf_cpu->lock, proc_flags); + if (kfifo_put(&mf_cpu->fifo, &entry)) + schedule_work_on(smp_processor_id(), &mf_cpu->work); + else + pr_err("Memory failure: buffer overflow when queuing memory failure at 0x%#lx\n", + pfn); + spin_unlock_irqrestore(&mf_cpu->lock, proc_flags); + put_cpu_var(memory_failure_cpu); +} +EXPORT_SYMBOL_GPL(memory_failure_queue); + +static void memory_failure_work_func(struct work_struct *work) +{ + struct memory_failure_cpu *mf_cpu; + struct memory_failure_entry entry = { 0, }; + unsigned long proc_flags; + int gotten; + + mf_cpu = &__get_cpu_var(memory_failure_cpu); + for (;;) { + spin_lock_irqsave(&mf_cpu->lock, proc_flags); + gotten = kfifo_get(&mf_cpu->fifo, &entry); + spin_unlock_irqrestore(&mf_cpu->lock, proc_flags); + if (!gotten) + break; + __memory_failure(entry.pfn, entry.trapno, entry.flags); + } +} + +static int __init memory_failure_init(void) +{ + struct memory_failure_cpu *mf_cpu; + int cpu; + + for_each_possible_cpu(cpu) { + mf_cpu = &per_cpu(memory_failure_cpu, cpu); + spin_lock_init(&mf_cpu->lock); + INIT_KFIFO(mf_cpu->fifo); + INIT_WORK(&mf_cpu->work, memory_failure_work_func); + } + + return 0; +} +core_initcall(memory_failure_init); + /** * unpoison_memory - Unpoison a previously poisoned page * @pfn: Page number of the to be unpoisoned page @@ -1218,7 +1311,7 @@ int unpoison_memory(unsigned long pfn) * to the end. */ if (PageHuge(page)) { - pr_debug("MCE: Memory failure is now running on free hugepage %#lx\n", pfn); + pr_info("MCE: Memory failure is now running on free hugepage %#lx\n", pfn); return 0; } if (TestClearPageHWPoison(p)) @@ -1327,7 +1420,7 @@ static int soft_offline_huge_page(struct page *page, int flags) if (PageHWPoison(hpage)) { put_page(hpage); - pr_debug("soft offline: %#lx hugepage already poisoned\n", pfn); + pr_info("soft offline: %#lx hugepage already poisoned\n", pfn); return -EBUSY; } @@ -1341,8 +1434,8 @@ static int soft_offline_huge_page(struct page *page, int flags) list_for_each_entry_safe(page1, page2, &pagelist, lru) put_page(page1); - pr_debug("soft offline: %#lx: migration failed %d, type %lx\n", - pfn, ret, page->flags); + pr_info("soft offline: %#lx: migration failed %d, type %lx\n", + pfn, ret, page->flags); if (ret > 0) ret = -EIO; return ret; @@ -1413,7 +1506,7 @@ int soft_offline_page(struct page *page, int flags) } if (!PageLRU(page)) { pr_info("soft_offline: %#lx: unknown non LRU page type %lx\n", - pfn, page->flags); + pfn, page->flags); return -EIO; } @@ -1474,7 +1567,7 @@ int soft_offline_page(struct page *page, int flags) } } else { pr_info("soft offline: %#lx: isolation failed: %d, page count %d, type %lx\n", - pfn, ret, page_count(page), page->flags); + pfn, ret, page_count(page), page->flags); } if (ret) return ret; diff --git a/mm/memory.c b/mm/memory.c index 9b8a01d..829d437 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -47,7 +47,7 @@ #include <linux/pagemap.h> #include <linux/ksm.h> #include <linux/rmap.h> -#include <linux/module.h> +#include <linux/export.h> #include <linux/delayacct.h> #include <linux/init.h> #include <linux/writeback.h> @@ -1290,13 +1290,6 @@ static unsigned long unmap_page_range(struct mmu_gather *tlb, return addr; } -#ifdef CONFIG_PREEMPT -# define ZAP_BLOCK_SIZE (8 * PAGE_SIZE) -#else -/* No preempt: go for improved straight-line efficiency */ -# define ZAP_BLOCK_SIZE (1024 * PAGE_SIZE) -#endif - /** * unmap_vmas - unmap a range of memory covered by a list of vma's * @tlb: address of the caller's struct mmu_gather @@ -1310,10 +1303,6 @@ static unsigned long unmap_page_range(struct mmu_gather *tlb, * * Unmap all pages in the vma list. * - * We aim to not hold locks for too long (for scheduling latency reasons). - * So zap pages in ZAP_BLOCK_SIZE bytecounts. This means we need to - * return the ending mmu_gather to the caller. - * * Only addresses between `start' and `end' will be unmapped. * * The VMA list must be sorted in ascending virtual address order. @@ -1514,7 +1503,7 @@ split_fallthrough: } if (flags & FOLL_GET) - get_page(page); + get_page_foll(page); if (flags & FOLL_TOUCH) { if ((flags & FOLL_WRITE) && !pte_dirty(pte) && !PageDirty(page)) @@ -1816,7 +1805,63 @@ next_page: } EXPORT_SYMBOL(__get_user_pages); -/** +/* + * fixup_user_fault() - manually resolve a user page fault + * @tsk: the task_struct to use for page fault accounting, or + * NULL if faults are not to be recorded. + * @mm: mm_struct of target mm + * @address: user address + * @fault_flags:flags to pass down to handle_mm_fault() + * + * This is meant to be called in the specific scenario where for locking reasons + * we try to access user memory in atomic context (within a pagefault_disable() + * section), this returns -EFAULT, and we want to resolve the user fault before + * trying again. + * + * Typically this is meant to be used by the futex code. + * + * The main difference with get_user_pages() is that this function will + * unconditionally call handle_mm_fault() which will in turn perform all the + * necessary SW fixup of the dirty and young bits in the PTE, while + * handle_mm_fault() only guarantees to update these in the struct page. + * + * This is important for some architectures where those bits also gate the + * access permission to the page because they are maintained in software. On + * such architectures, gup() will not be enough to make a subsequent access + * succeed. + * + * This should be called with the mm_sem held for read. + */ +int fixup_user_fault(struct task_struct *tsk, struct mm_struct *mm, + unsigned long address, unsigned int fault_flags) +{ + struct vm_area_struct *vma; + int ret; + + vma = find_extend_vma(mm, address); + if (!vma || address < vma->vm_start) + return -EFAULT; + + ret = handle_mm_fault(mm, vma, address, fault_flags); + if (ret & VM_FAULT_ERROR) { + if (ret & VM_FAULT_OOM) + return -ENOMEM; + if (ret & (VM_FAULT_HWPOISON | VM_FAULT_HWPOISON_LARGE)) + return -EHWPOISON; + if (ret & VM_FAULT_SIGBUS) + return -EFAULT; + BUG(); + } + if (tsk) { + if (ret & VM_FAULT_MAJOR) + tsk->maj_flt++; + else + tsk->min_flt++; + } + return 0; +} + +/* * get_user_pages() - pin user pages in memory * @tsk: the task_struct to use for page fault accounting, or * NULL if faults are not to be recorded. @@ -3104,14 +3149,34 @@ static int __do_fault(struct mm_struct *mm, struct vm_area_struct *vma, pte_t *page_table; spinlock_t *ptl; struct page *page; + struct page *cow_page; pte_t entry; int anon = 0; - int charged = 0; struct page *dirty_page = NULL; struct vm_fault vmf; int ret; int page_mkwrite = 0; + /* + * If we do COW later, allocate page befor taking lock_page() + * on the file cache page. This will reduce lock holding time. + */ + if ((flags & FAULT_FLAG_WRITE) && !(vma->vm_flags & VM_SHARED)) { + + if (unlikely(anon_vma_prepare(vma))) + return VM_FAULT_OOM; + + cow_page = alloc_page_vma(GFP_HIGHUSER_MOVABLE, vma, address); + if (!cow_page) + return VM_FAULT_OOM; + + if (mem_cgroup_newpage_charge(cow_page, mm, GFP_KERNEL)) { + page_cache_release(cow_page); + return VM_FAULT_OOM; + } + } else + cow_page = NULL; + vmf.virtual_address = (void __user *)(address & PAGE_MASK); vmf.pgoff = pgoff; vmf.flags = flags; @@ -3120,12 +3185,13 @@ static int __do_fault(struct mm_struct *mm, struct vm_area_struct *vma, ret = vma->vm_ops->fault(vma, &vmf); if (unlikely(ret & (VM_FAULT_ERROR | VM_FAULT_NOPAGE | VM_FAULT_RETRY))) - return ret; + goto uncharge_out; if (unlikely(PageHWPoison(vmf.page))) { if (ret & VM_FAULT_LOCKED) unlock_page(vmf.page); - return VM_FAULT_HWPOISON; + ret = VM_FAULT_HWPOISON; + goto uncharge_out; } /* @@ -3143,23 +3209,8 @@ static int __do_fault(struct mm_struct *mm, struct vm_area_struct *vma, page = vmf.page; if (flags & FAULT_FLAG_WRITE) { if (!(vma->vm_flags & VM_SHARED)) { + page = cow_page; anon = 1; - if (unlikely(anon_vma_prepare(vma))) { - ret = VM_FAULT_OOM; - goto out; - } - page = alloc_page_vma(GFP_HIGHUSER_MOVABLE, - vma, address); - if (!page) { - ret = VM_FAULT_OOM; - goto out; - } - if (mem_cgroup_newpage_charge(page, mm, GFP_KERNEL)) { - ret = VM_FAULT_OOM; - page_cache_release(page); - goto out; - } - charged = 1; copy_user_highpage(page, vmf.page, address, vma); __SetPageUptodate(page); } else { @@ -3228,8 +3279,8 @@ static int __do_fault(struct mm_struct *mm, struct vm_area_struct *vma, /* no need to invalidate: a not-present page won't be cached */ update_mmu_cache(vma, address, page_table); } else { - if (charged) - mem_cgroup_uncharge_page(page); + if (cow_page) + mem_cgroup_uncharge_page(cow_page); if (anon) page_cache_release(page); else @@ -3238,7 +3289,6 @@ static int __do_fault(struct mm_struct *mm, struct vm_area_struct *vma, pte_unmap_unlock(page_table, ptl); -out: if (dirty_page) { struct address_space *mapping = page->mapping; @@ -3268,6 +3318,13 @@ out: unwritable_page: page_cache_release(page); return ret; +uncharge_out: + /* fs's fault handler get error */ + if (cow_page) { + mem_cgroup_uncharge_page(cow_page); + page_cache_release(cow_page); + } + return ret; } static int do_linear_fault(struct mm_struct *mm, struct vm_area_struct *vma, diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c index c46887b..2168489 100644 --- a/mm/memory_hotplug.c +++ b/mm/memory_hotplug.c @@ -11,7 +11,7 @@ #include <linux/pagemap.h> #include <linux/bootmem.h> #include <linux/compiler.h> -#include <linux/module.h> +#include <linux/export.h> #include <linux/pagevec.h> #include <linux/writeback.h> #include <linux/slab.h> @@ -34,6 +34,17 @@ #include "internal.h" +/* + * online_page_callback contains pointer to current page onlining function. + * Initially it is generic_online_page(). If it is required it could be + * changed by calling set_online_page_callback() for callback registration + * and restore_online_page_callback() for generic callback restore. + */ + +static void generic_online_page(struct page *page); + +static online_page_callback_t online_page_callback = generic_online_page; + DEFINE_MUTEX(mem_hotplug_mutex); void lock_memory_hotplug(void) @@ -361,23 +372,74 @@ int __remove_pages(struct zone *zone, unsigned long phys_start_pfn, } EXPORT_SYMBOL_GPL(__remove_pages); -void online_page(struct page *page) +int set_online_page_callback(online_page_callback_t callback) +{ + int rc = -EINVAL; + + lock_memory_hotplug(); + + if (online_page_callback == generic_online_page) { + online_page_callback = callback; + rc = 0; + } + + unlock_memory_hotplug(); + + return rc; +} +EXPORT_SYMBOL_GPL(set_online_page_callback); + +int restore_online_page_callback(online_page_callback_t callback) +{ + int rc = -EINVAL; + + lock_memory_hotplug(); + + if (online_page_callback == callback) { + online_page_callback = generic_online_page; + rc = 0; + } + + unlock_memory_hotplug(); + + return rc; +} +EXPORT_SYMBOL_GPL(restore_online_page_callback); + +void __online_page_set_limits(struct page *page) { unsigned long pfn = page_to_pfn(page); - totalram_pages++; if (pfn >= num_physpages) num_physpages = pfn + 1; +} +EXPORT_SYMBOL_GPL(__online_page_set_limits); + +void __online_page_increment_counters(struct page *page) +{ + totalram_pages++; #ifdef CONFIG_HIGHMEM if (PageHighMem(page)) totalhigh_pages++; #endif +} +EXPORT_SYMBOL_GPL(__online_page_increment_counters); +void __online_page_free(struct page *page) +{ ClearPageReserved(page); init_page_count(page); __free_page(page); } +EXPORT_SYMBOL_GPL(__online_page_free); + +static void generic_online_page(struct page *page) +{ + __online_page_set_limits(page); + __online_page_increment_counters(page); + __online_page_free(page); +} static int online_pages_range(unsigned long start_pfn, unsigned long nr_pages, void *arg) @@ -388,7 +450,7 @@ static int online_pages_range(unsigned long start_pfn, unsigned long nr_pages, if (PageReserved(pfn_to_page(start_pfn))) for (i = 0; i < nr_pages; i++) { page = pfn_to_page(start_pfn + i); - online_page(page); + (*online_page_callback)(page); onlined_pages++; } *(unsigned long *)arg = onlined_pages; diff --git a/mm/mempolicy.c b/mm/mempolicy.c index e7fb9d2..adc3954 100644 --- a/mm/mempolicy.c +++ b/mm/mempolicy.c @@ -75,7 +75,7 @@ #include <linux/cpuset.h> #include <linux/slab.h> #include <linux/string.h> -#include <linux/module.h> +#include <linux/export.h> #include <linux/nsproxy.h> #include <linux/interrupt.h> #include <linux/init.h> @@ -93,6 +93,7 @@ #include <asm/tlbflush.h> #include <asm/uaccess.h> +#include <linux/random.h> #include "internal.h" @@ -110,7 +111,7 @@ enum zone_type policy_zone = 0; /* * run-time system-wide default policy => local allocation */ -struct mempolicy default_policy = { +static struct mempolicy default_policy = { .refcnt = ATOMIC_INIT(1), /* never free it */ .mode = MPOL_PREFERRED, .flags = MPOL_F_LOCAL, @@ -635,7 +636,6 @@ static int mbind_range(struct mm_struct *mm, unsigned long start, struct vm_area_struct *prev; struct vm_area_struct *vma; int err = 0; - pgoff_t pgoff; unsigned long vmstart; unsigned long vmend; @@ -648,9 +648,9 @@ static int mbind_range(struct mm_struct *mm, unsigned long start, vmstart = max(start, vma->vm_start); vmend = min(end, vma->vm_end); - pgoff = vma->vm_pgoff + ((start - vma->vm_start) >> PAGE_SHIFT); prev = vma_merge(mm, prev, vmstart, vmend, vma->vm_flags, - vma->anon_vma, vma->vm_file, pgoff, new_pol); + vma->anon_vma, vma->vm_file, vma->vm_pgoff, + new_pol); if (prev) { vma = prev; next = vma->vm_next; @@ -1411,7 +1411,9 @@ asmlinkage long compat_sys_get_mempolicy(int __user *policy, err = sys_get_mempolicy(policy, nm, nr_bits+1, addr, flags); if (!err && nmask) { - err = copy_from_user(bm, nm, alloc_size); + unsigned long copy_size; + copy_size = min_t(unsigned long, sizeof(bm), alloc_size); + err = copy_from_user(bm, nm, copy_size); /* ensure entire bitmap is zeroed */ err |= clear_user(nmask, ALIGN(maxnode-1, 8) / 8); err |= compat_put_bitmap(nmask, bm, nr_bits); @@ -1645,6 +1647,21 @@ static inline unsigned interleave_nid(struct mempolicy *pol, return interleave_nodes(pol); } +/* + * Return the bit number of a random bit set in the nodemask. + * (returns -1 if nodemask is empty) + */ +int node_random(const nodemask_t *maskp) +{ + int w, bit = -1; + + w = nodes_weight(*maskp); + if (w) + bit = bitmap_ord_to_pos(maskp->bits, + get_random_int() % w, MAX_NUMNODES); + return bit; +} + #ifdef CONFIG_HUGETLBFS /* * huge_zonelist(@vma, @addr, @gfp_flags, @mpol) diff --git a/mm/mempool.c b/mm/mempool.c index 1a3bc3d..e73641b 100644 --- a/mm/mempool.c +++ b/mm/mempool.c @@ -10,7 +10,7 @@ #include <linux/mm.h> #include <linux/slab.h> -#include <linux/module.h> +#include <linux/export.h> #include <linux/mempool.h> #include <linux/blkdev.h> #include <linux/writeback.h> diff --git a/mm/migrate.c b/mm/migrate.c index 666e4e6..578e291 100644 --- a/mm/migrate.c +++ b/mm/migrate.c @@ -13,7 +13,7 @@ */ #include <linux/migrate.h> -#include <linux/module.h> +#include <linux/export.h> #include <linux/swap.h> #include <linux/swapops.h> #include <linux/pagemap.h> @@ -120,10 +120,10 @@ static int remove_migration_pte(struct page *new, struct vm_area_struct *vma, ptep = pte_offset_map(pmd, addr); - if (!is_swap_pte(*ptep)) { - pte_unmap(ptep); - goto out; - } + /* + * Peek to check is_swap_pte() before taking ptlock? No, we + * can race mremap's move_ptes(), which skips anon_vma lock. + */ ptl = pte_lockptr(mm, pmd); } @@ -621,38 +621,18 @@ static int move_to_new_page(struct page *newpage, struct page *page, return rc; } -/* - * Obtain the lock on page, remove all ptes and migrate the page - * to the newly allocated page in newpage. - */ -static int unmap_and_move(new_page_t get_new_page, unsigned long private, - struct page *page, int force, bool offlining, bool sync) +static int __unmap_and_move(struct page *page, struct page *newpage, + int force, bool offlining, bool sync) { - int rc = 0; - int *result = NULL; - struct page *newpage = get_new_page(page, private, &result); + int rc = -EAGAIN; int remap_swapcache = 1; int charge = 0; struct mem_cgroup *mem; struct anon_vma *anon_vma = NULL; - if (!newpage) - return -ENOMEM; - - if (page_count(page) == 1) { - /* page was freed from under us. So we are done. */ - goto move_newpage; - } - if (unlikely(PageTransHuge(page))) - if (unlikely(split_huge_page(page))) - goto move_newpage; - - /* prepare cgroup just returns 0 or -ENOMEM */ - rc = -EAGAIN; - if (!trylock_page(page)) { if (!force || !sync) - goto move_newpage; + goto out; /* * It's not safe for direct compaction to call lock_page. @@ -668,7 +648,7 @@ static int unmap_and_move(new_page_t get_new_page, unsigned long private, * altogether. */ if (current->flags & PF_MEMALLOC) - goto move_newpage; + goto out; lock_page(page); } @@ -785,27 +765,52 @@ uncharge: mem_cgroup_end_migration(mem, page, newpage, rc == 0); unlock: unlock_page(page); +out: + return rc; +} -move_newpage: +/* + * Obtain the lock on page, remove all ptes and migrate the page + * to the newly allocated page in newpage. + */ +static int unmap_and_move(new_page_t get_new_page, unsigned long private, + struct page *page, int force, bool offlining, bool sync) +{ + int rc = 0; + int *result = NULL; + struct page *newpage = get_new_page(page, private, &result); + + if (!newpage) + return -ENOMEM; + + if (page_count(page) == 1) { + /* page was freed from under us. So we are done. */ + goto out; + } + + if (unlikely(PageTransHuge(page))) + if (unlikely(split_huge_page(page))) + goto out; + + rc = __unmap_and_move(page, newpage, force, offlining, sync); +out: if (rc != -EAGAIN) { - /* - * A page that has been migrated has all references - * removed and will be freed. A page that has not been - * migrated will have kepts its references and be - * restored. - */ - list_del(&page->lru); + /* + * A page that has been migrated has all references + * removed and will be freed. A page that has not been + * migrated will have kepts its references and be + * restored. + */ + list_del(&page->lru); dec_zone_page_state(page, NR_ISOLATED_ANON + page_is_file_cache(page)); putback_lru_page(page); } - /* * Move the new page to the LRU. If migration was not successful * then this will free the page. */ putback_lru_page(newpage); - if (result) { if (rc) *result = rc; diff --git a/mm/mincore.c b/mm/mincore.c index a4e6b9d..636a868 100644 --- a/mm/mincore.c +++ b/mm/mincore.c @@ -69,12 +69,15 @@ static unsigned char mincore_page(struct address_space *mapping, pgoff_t pgoff) * file will not get a swp_entry_t in its pte, but rather it is like * any other file mapping (ie. marked !present and faulted in with * tmpfs's .fault). So swapped out tmpfs mappings are tested here. - * - * However when tmpfs moves the page from pagecache and into swapcache, - * it is still in core, but the find_get_page below won't find it. - * No big deal, but make a note of it. */ page = find_get_page(mapping, pgoff); +#ifdef CONFIG_SWAP + /* shmem/tmpfs may return swap: account for swapcache page too. */ + if (radix_tree_exceptional_entry(page)) { + swp_entry_t swap = radix_to_swp_entry(page); + page = find_get_page(&swapper_space, swap.val); + } +#endif if (page) { present = PageUptodate(page); page_cache_release(page); @@ -14,7 +14,7 @@ #include <linux/mempolicy.h> #include <linux/syscalls.h> #include <linux/sched.h> -#include <linux/module.h> +#include <linux/export.h> #include <linux/rmap.h> #include <linux/mmzone.h> #include <linux/hugetlb.h> @@ -110,7 +110,15 @@ void munlock_vma_page(struct page *page) if (TestClearPageMlocked(page)) { dec_zone_page_state(page, NR_MLOCK); if (!isolate_lru_page(page)) { - int ret = try_to_munlock(page); + int ret = SWAP_AGAIN; + + /* + * Optimization: if the page was mapped just once, + * that's our mapping and we don't need to check all the + * other vmas. + */ + if (page_mapcount(page) > 1) + ret = try_to_munlock(page); /* * did try_to_unlock() succeed or punt? */ @@ -549,7 +557,8 @@ SYSCALL_DEFINE1(mlockall, int, flags) if (!can_do_mlock()) goto out; - lru_add_drain_all(); /* flush pagevec */ + if (flags & MCL_CURRENT) + lru_add_drain_all(); /* flush pagevec */ down_write(¤t->mm->mmap_sem); diff --git a/mm/mm_init.c b/mm/mm_init.c index 4e0e265..1ffd97a 100644 --- a/mm/mm_init.c +++ b/mm/mm_init.c @@ -8,7 +8,7 @@ #include <linux/kernel.h> #include <linux/init.h> #include <linux/kobject.h> -#include <linux/module.h> +#include <linux/export.h> #include "internal.h" #ifdef CONFIG_DEBUG_MEMORY_INIT @@ -22,7 +22,7 @@ #include <linux/security.h> #include <linux/hugetlb.h> #include <linux/profile.h> -#include <linux/module.h> +#include <linux/export.h> #include <linux/mount.h> #include <linux/mempolicy.h> #include <linux/rmap.h> @@ -122,9 +122,17 @@ int __vm_enough_memory(struct mm_struct *mm, long pages, int cap_sys_admin) return 0; if (sysctl_overcommit_memory == OVERCOMMIT_GUESS) { - unsigned long n; + free = global_page_state(NR_FREE_PAGES); + free += global_page_state(NR_FILE_PAGES); + + /* + * shmem pages shouldn't be counted as free in this + * case, they can't be purged, only swapped out, and + * that won't affect the overall amount of available + * memory in the system. + */ + free -= global_page_state(NR_SHMEM); - free = global_page_state(NR_FILE_PAGES); free += nr_swap_pages; /* @@ -136,34 +144,18 @@ int __vm_enough_memory(struct mm_struct *mm, long pages, int cap_sys_admin) free += global_page_state(NR_SLAB_RECLAIMABLE); /* - * Leave the last 3% for root - */ - if (!cap_sys_admin) - free -= free / 32; - - if (free > pages) - return 0; - - /* - * nr_free_pages() is very expensive on large systems, - * only call if we're about to fail. - */ - n = nr_free_pages(); - - /* * Leave reserved pages. The pages are not for anonymous pages. */ - if (n <= totalreserve_pages) + if (free <= totalreserve_pages) goto error; else - n -= totalreserve_pages; + free -= totalreserve_pages; /* * Leave the last 3% for root */ if (!cap_sys_admin) - n -= n / 32; - free += n; + free -= free / 32; if (free > pages) return 0; @@ -2566,7 +2558,6 @@ int mm_take_all_locks(struct mm_struct *mm) { struct vm_area_struct *vma; struct anon_vma_chain *avc; - int ret = -EINTR; BUG_ON(down_read_trylock(&mm->mmap_sem)); @@ -2587,13 +2578,11 @@ int mm_take_all_locks(struct mm_struct *mm) vm_lock_anon_vma(mm, avc->anon_vma); } - ret = 0; + return 0; out_unlock: - if (ret) - mm_drop_all_locks(mm); - - return ret; + mm_drop_all_locks(mm); + return -EINTR; } static void vm_unlock_anon_vma(struct anon_vma *anon_vma) diff --git a/mm/mmu_context.c b/mm/mmu_context.c index 9e82e93..cf332bc 100644 --- a/mm/mmu_context.c +++ b/mm/mmu_context.c @@ -5,7 +5,7 @@ #include <linux/mm.h> #include <linux/mmu_context.h> -#include <linux/module.h> +#include <linux/export.h> #include <linux/sched.h> #include <asm/mmu_context.h> diff --git a/mm/mmu_notifier.c b/mm/mmu_notifier.c index 8d032de..9a611d3 100644 --- a/mm/mmu_notifier.c +++ b/mm/mmu_notifier.c @@ -11,7 +11,7 @@ #include <linux/rculist.h> #include <linux/mmu_notifier.h> -#include <linux/module.h> +#include <linux/export.h> #include <linux/mm.h> #include <linux/err.h> #include <linux/rcupdate.h> diff --git a/mm/mmzone.c b/mm/mmzone.c index f5b7d17..7cf7b7d 100644 --- a/mm/mmzone.c +++ b/mm/mmzone.c @@ -8,7 +8,6 @@ #include <linux/stddef.h> #include <linux/mm.h> #include <linux/mmzone.h> -#include <linux/module.h> struct pglist_data *first_online_pgdat(void) { diff --git a/mm/mremap.c b/mm/mremap.c index 506fa44..d6959cb 100644 --- a/mm/mremap.c +++ b/mm/mremap.c @@ -41,8 +41,7 @@ static pmd_t *get_old_pmd(struct mm_struct *mm, unsigned long addr) return NULL; pmd = pmd_offset(pud, addr); - split_huge_page_pmd(mm, pmd); - if (pmd_none_or_clear_bad(pmd)) + if (pmd_none(*pmd)) return NULL; return pmd; @@ -65,8 +64,6 @@ static pmd_t *alloc_new_pmd(struct mm_struct *mm, struct vm_area_struct *vma, return NULL; VM_BUG_ON(pmd_trans_huge(*pmd)); - if (pmd_none(*pmd) && __pte_alloc(mm, vma, pmd, addr)) - return NULL; return pmd; } @@ -80,11 +77,7 @@ static void move_ptes(struct vm_area_struct *vma, pmd_t *old_pmd, struct mm_struct *mm = vma->vm_mm; pte_t *old_pte, *new_pte, pte; spinlock_t *old_ptl, *new_ptl; - unsigned long old_start; - old_start = old_addr; - mmu_notifier_invalidate_range_start(vma->vm_mm, - old_start, old_end); if (vma->vm_file) { /* * Subtle point from Rajesh Venkatasubramanian: before @@ -111,7 +104,7 @@ static void move_ptes(struct vm_area_struct *vma, pmd_t *old_pmd, new_pte++, new_addr += PAGE_SIZE) { if (pte_none(*old_pte)) continue; - pte = ptep_clear_flush(vma, old_addr, old_pte); + pte = ptep_get_and_clear(mm, old_addr, old_pte); pte = move_pte(pte, new_vma->vm_page_prot, old_addr, new_addr); set_pte_at(mm, new_addr, new_pte, pte); } @@ -123,7 +116,6 @@ static void move_ptes(struct vm_area_struct *vma, pmd_t *old_pmd, pte_unmap_unlock(old_pte - 1, old_ptl); if (mapping) mutex_unlock(&mapping->i_mmap_mutex); - mmu_notifier_invalidate_range_end(vma->vm_mm, old_start, old_end); } #define LATENCY_LIMIT (64 * PAGE_SIZE) @@ -134,22 +126,43 @@ unsigned long move_page_tables(struct vm_area_struct *vma, { unsigned long extent, next, old_end; pmd_t *old_pmd, *new_pmd; + bool need_flush = false; old_end = old_addr + len; flush_cache_range(vma, old_addr, old_end); + mmu_notifier_invalidate_range_start(vma->vm_mm, old_addr, old_end); + for (; old_addr < old_end; old_addr += extent, new_addr += extent) { cond_resched(); next = (old_addr + PMD_SIZE) & PMD_MASK; - if (next - 1 > old_end) - next = old_end; + /* even if next overflowed, extent below will be ok */ extent = next - old_addr; + if (extent > old_end - old_addr) + extent = old_end - old_addr; old_pmd = get_old_pmd(vma->vm_mm, old_addr); if (!old_pmd) continue; new_pmd = alloc_new_pmd(vma->vm_mm, vma, new_addr); if (!new_pmd) break; + if (pmd_trans_huge(*old_pmd)) { + int err = 0; + if (extent == HPAGE_PMD_SIZE) + err = move_huge_pmd(vma, new_vma, old_addr, + new_addr, old_end, + old_pmd, new_pmd); + if (err > 0) { + need_flush = true; + continue; + } else if (!err) { + split_huge_page_pmd(vma->vm_mm, old_pmd); + } + VM_BUG_ON(pmd_trans_huge(*old_pmd)); + } + if (pmd_none(*new_pmd) && __pte_alloc(new_vma->vm_mm, new_vma, + new_pmd, new_addr)) + break; next = (new_addr + PMD_SIZE) & PMD_MASK; if (extent > next - new_addr) extent = next - new_addr; @@ -157,7 +170,12 @@ unsigned long move_page_tables(struct vm_area_struct *vma, extent = LATENCY_LIMIT; move_ptes(vma, old_pmd, old_addr, old_addr + extent, new_vma, new_pmd, new_addr); + need_flush = true; } + if (likely(need_flush)) + flush_tlb_range(vma, old_end-len, old_addr); + + mmu_notifier_invalidate_range_end(vma->vm_mm, old_end-len, old_end); return len + old_addr - old_end; /* how much done */ } diff --git a/mm/nobootmem.c b/mm/nobootmem.c index 29d948c..24f0fc1 100644 --- a/mm/nobootmem.c +++ b/mm/nobootmem.c @@ -12,7 +12,7 @@ #include <linux/pfn.h> #include <linux/slab.h> #include <linux/bootmem.h> -#include <linux/module.h> +#include <linux/export.h> #include <linux/kmemleak.h> #include <linux/range.h> #include <linux/memblock.h> @@ -13,7 +13,7 @@ * Copyright (c) 2007-2010 Paul Mundt <lethal@linux-sh.org> */ -#include <linux/module.h> +#include <linux/export.h> #include <linux/mm.h> #include <linux/mman.h> #include <linux/swap.h> @@ -22,7 +22,6 @@ #include <linux/pagemap.h> #include <linux/slab.h> #include <linux/vmalloc.h> -#include <linux/tracehook.h> #include <linux/blkdev.h> #include <linux/backing-dev.h> #include <linux/mount.h> @@ -455,7 +454,7 @@ void __attribute__((weak)) vmalloc_sync_all(void) * between processes, it syncs the pagetable across all * processes. */ -struct vm_struct *alloc_vm_area(size_t size) +struct vm_struct *alloc_vm_area(size_t size, pte_t **ptes) { BUG(); return NULL; @@ -1087,7 +1086,7 @@ static unsigned long determine_vm_flags(struct file *file, * it's being traced - otherwise breakpoints set in it may interfere * with another untraced process */ - if ((flags & MAP_PRIVATE) && tracehook_expect_breakpoints(current)) + if ((flags & MAP_PRIVATE) && current->ptrace) vm_flags &= ~VM_MAYSHARE; return vm_flags; @@ -1885,9 +1884,17 @@ int __vm_enough_memory(struct mm_struct *mm, long pages, int cap_sys_admin) return 0; if (sysctl_overcommit_memory == OVERCOMMIT_GUESS) { - unsigned long n; + free = global_page_state(NR_FREE_PAGES); + free += global_page_state(NR_FILE_PAGES); + + /* + * shmem pages shouldn't be counted as free in this + * case, they can't be purged, only swapped out, and + * that won't affect the overall amount of available + * memory in the system. + */ + free -= global_page_state(NR_SHMEM); - free = global_page_state(NR_FILE_PAGES); free += nr_swap_pages; /* @@ -1899,34 +1906,18 @@ int __vm_enough_memory(struct mm_struct *mm, long pages, int cap_sys_admin) free += global_page_state(NR_SLAB_RECLAIMABLE); /* - * Leave the last 3% for root - */ - if (!cap_sys_admin) - free -= free / 32; - - if (free > pages) - return 0; - - /* - * nr_free_pages() is very expensive on large systems, - * only call if we're about to fail. - */ - n = nr_free_pages(); - - /* * Leave reserved pages. The pages are not for anonymous pages. */ - if (n <= totalreserve_pages) + if (free <= totalreserve_pages) goto error; else - n -= totalreserve_pages; + free -= totalreserve_pages; /* * Leave the last 3% for root */ if (!cap_sys_admin) - n -= n / 32; - free += n; + free -= free / 32; if (free > pages) return 0; diff --git a/mm/oom_kill.c b/mm/oom_kill.c index e4b0991..76f2c5a 100644 --- a/mm/oom_kill.c +++ b/mm/oom_kill.c @@ -26,18 +26,38 @@ #include <linux/timex.h> #include <linux/jiffies.h> #include <linux/cpuset.h> -#include <linux/module.h> +#include <linux/export.h> #include <linux/notifier.h> #include <linux/memcontrol.h> #include <linux/mempolicy.h> #include <linux/security.h> #include <linux/ptrace.h> +#include <linux/freezer.h> int sysctl_panic_on_oom; int sysctl_oom_kill_allocating_task; int sysctl_oom_dump_tasks = 1; static DEFINE_SPINLOCK(zone_scan_lock); +/* + * compare_swap_oom_score_adj() - compare and swap current's oom_score_adj + * @old_val: old oom_score_adj for compare + * @new_val: new oom_score_adj for swap + * + * Sets the oom_score_adj value for current to @new_val iff its present value is + * @old_val. Usually used to reinstate a previous value to prevent racing with + * userspacing tuning the value in the interim. + */ +void compare_swap_oom_score_adj(int old_val, int new_val) +{ + struct sighand_struct *sighand = current->sighand; + + spin_lock_irq(&sighand->siglock); + if (current->signal->oom_score_adj == old_val) + current->signal->oom_score_adj = new_val; + spin_unlock_irq(&sighand->siglock); +} + /** * test_set_oom_score_adj() - set current's oom_score_adj and return old value * @new_val: new oom_score_adj value @@ -53,13 +73,7 @@ int test_set_oom_score_adj(int new_val) spin_lock_irq(&sighand->siglock); old_val = current->signal->oom_score_adj; - if (new_val != old_val) { - if (new_val == OOM_SCORE_ADJ_MIN) - atomic_inc(¤t->mm->oom_disable_count); - else if (old_val == OOM_SCORE_ADJ_MIN) - atomic_dec(¤t->mm->oom_disable_count); - current->signal->oom_score_adj = new_val; - } + current->signal->oom_score_adj = new_val; spin_unlock_irq(&sighand->siglock); return old_val; @@ -171,12 +185,7 @@ unsigned int oom_badness(struct task_struct *p, struct mem_cgroup *mem, if (!p) return 0; - /* - * Shortcut check for a thread sharing p->mm that is OOM_SCORE_ADJ_MIN - * so the entire heuristic doesn't need to be executed for something - * that cannot be killed. - */ - if (atomic_read(&p->mm->oom_disable_count)) { + if (p->signal->oom_score_adj == OOM_SCORE_ADJ_MIN) { task_unlock(p); return 0; } @@ -303,7 +312,7 @@ static struct task_struct *select_bad_process(unsigned int *ppoints, do_each_thread(g, p) { unsigned int points; - if (!p->mm) + if (p->exit_state) continue; if (oom_unkillable_task(p, mem, nodemask)) continue; @@ -317,8 +326,13 @@ static struct task_struct *select_bad_process(unsigned int *ppoints, * blocked waiting for another task which itself is waiting * for memory. Is there a better alternative? */ - if (test_tsk_thread_flag(p, TIF_MEMDIE)) + if (test_tsk_thread_flag(p, TIF_MEMDIE)) { + if (unlikely(frozen(p))) + thaw_process(p); return ERR_PTR(-1UL); + } + if (!p->mm) + continue; if (p->flags & PF_EXITING) { /* @@ -339,8 +353,7 @@ static struct task_struct *select_bad_process(unsigned int *ppoints, * then wait for it to finish before killing * some other task unnecessarily. */ - if (!(task_ptrace(p->group_leader) & - PT_TRACE_EXIT)) + if (!(p->group_leader->ptrace & PT_TRACE_EXIT)) return ERR_PTR(-1UL); } } @@ -434,7 +447,7 @@ static int oom_kill_task(struct task_struct *p, struct mem_cgroup *mem) task_unlock(p); /* - * Kill all processes sharing p->mm in other thread groups, if any. + * Kill all user processes sharing p->mm in other thread groups, if any. * They don't get access to memory reserves or a higher scheduler * priority, though, to avoid depletion of all memory or task * starvation. This prevents mm->mmap_sem livelock when an oom killed @@ -444,7 +457,11 @@ static int oom_kill_task(struct task_struct *p, struct mem_cgroup *mem) * signal. */ for_each_process(q) - if (q->mm == mm && !same_thread_group(q, p)) { + if (q->mm == mm && !same_thread_group(q, p) && + !(q->flags & PF_KTHREAD)) { + if (q->signal->oom_score_adj == OOM_SCORE_ADJ_MIN) + continue; + task_lock(q); /* Protect ->comm from prctl() */ pr_err("Kill process %d (%s) sharing same memory\n", task_pid_nr(q), q->comm); @@ -488,7 +505,7 @@ static int oom_kill_process(struct task_struct *p, gfp_t gfp_mask, int order, /* * If any of p's children has a different mm and is eligible for kill, - * the one with the highest badness() score is sacrificed for its + * the one with the highest oom_badness() score is sacrificed for its * parent. This attempts to lose the minimal amount of work done while * still freeing memory. */ @@ -721,7 +738,7 @@ void out_of_memory(struct zonelist *zonelist, gfp_t gfp_mask, read_lock(&tasklist_lock); if (sysctl_oom_kill_allocating_task && !oom_unkillable_task(current, NULL, nodemask) && - current->mm && !atomic_read(¤t->mm->oom_disable_count)) { + current->mm) { /* * oom_kill_process() needs tasklist_lock held. If it returns * non-zero, current could not be killed so we must fallback to diff --git a/mm/page-writeback.c b/mm/page-writeback.c index 31f6988..7125248 100644 --- a/mm/page-writeback.c +++ b/mm/page-writeback.c @@ -12,7 +12,7 @@ */ #include <linux/kernel.h> -#include <linux/module.h> +#include <linux/export.h> #include <linux/spinlock.h> #include <linux/fs.h> #include <linux/mm.h> @@ -37,24 +37,22 @@ #include <trace/events/writeback.h> /* - * After a CPU has dirtied this many pages, balance_dirty_pages_ratelimited - * will look to see if it needs to force writeback or throttling. + * Sleep at most 200ms at a time in balance_dirty_pages(). */ -static long ratelimit_pages = 32; +#define MAX_PAUSE max(HZ/5, 1) /* - * When balance_dirty_pages decides that the caller needs to perform some - * non-background writeback, this is how many pages it will attempt to write. - * It should be somewhat larger than dirtied pages to ensure that reasonably - * large amounts of I/O are submitted. + * Estimate write bandwidth at 200ms intervals. */ -static inline long sync_writeback_pages(unsigned long dirtied) -{ - if (dirtied < ratelimit_pages) - dirtied = ratelimit_pages; +#define BANDWIDTH_INTERVAL max(HZ/5, 1) - return dirtied + dirtied / 2; -} +#define RATELIMIT_CALC_SHIFT 10 + +/* + * After a CPU has dirtied this many pages, balance_dirty_pages_ratelimited + * will look to see if it needs to force writeback or throttling. + */ +static long ratelimit_pages = 32; /* The following parameters are exported via /proc/sys/vm */ @@ -111,6 +109,7 @@ EXPORT_SYMBOL(laptop_mode); /* End of sysctl-exported parameters */ +unsigned long global_dirty_limit; /* * Scale the writeback cache size proportional to the relative writeout speeds. @@ -129,7 +128,6 @@ EXPORT_SYMBOL(laptop_mode); * */ static struct prop_descriptor vm_completions; -static struct prop_descriptor vm_dirties; /* * couple the period to the dirty_ratio: @@ -155,7 +153,8 @@ static void update_completion_period(void) { int shift = calc_period_shift(); prop_change_shift(&vm_completions, shift); - prop_change_shift(&vm_dirties, shift); + + writeback_set_ratelimit(); } int dirty_background_ratio_handler(struct ctl_table *table, int write, @@ -219,6 +218,7 @@ int dirty_bytes_handler(struct ctl_table *table, int write, */ static inline void __bdi_writeout_inc(struct backing_dev_info *bdi) { + __inc_bdi_stat(bdi, BDI_WRITTEN); __prop_inc_percpu_max(&vm_completions, &bdi->completions, bdi->max_prop_frac); } @@ -233,65 +233,20 @@ void bdi_writeout_inc(struct backing_dev_info *bdi) } EXPORT_SYMBOL_GPL(bdi_writeout_inc); -void task_dirty_inc(struct task_struct *tsk) -{ - prop_inc_single(&vm_dirties, &tsk->dirties); -} - /* * Obtain an accurate fraction of the BDI's portion. */ static void bdi_writeout_fraction(struct backing_dev_info *bdi, long *numerator, long *denominator) { - if (bdi_cap_writeback_dirty(bdi)) { - prop_fraction_percpu(&vm_completions, &bdi->completions, + prop_fraction_percpu(&vm_completions, &bdi->completions, numerator, denominator); - } else { - *numerator = 0; - *denominator = 1; - } -} - -static inline void task_dirties_fraction(struct task_struct *tsk, - long *numerator, long *denominator) -{ - prop_fraction_single(&vm_dirties, &tsk->dirties, - numerator, denominator); -} - -/* - * task_dirty_limit - scale down dirty throttling threshold for one task - * - * task specific dirty limit: - * - * dirty -= (dirty/8) * p_{t} - * - * To protect light/slow dirtying tasks from heavier/fast ones, we start - * throttling individual tasks before reaching the bdi dirty limit. - * Relatively low thresholds will be allocated to heavy dirtiers. So when - * dirty pages grow large, heavy dirtiers will be throttled first, which will - * effectively curb the growth of dirty pages. Light dirtiers with high enough - * dirty threshold may never get throttled. - */ -static unsigned long task_dirty_limit(struct task_struct *tsk, - unsigned long bdi_dirty) -{ - long numerator, denominator; - unsigned long dirty = bdi_dirty; - u64 inv = dirty >> 3; - - task_dirties_fraction(tsk, &numerator, &denominator); - inv *= numerator; - do_div(inv, denominator); - - dirty -= inv; - - return max(dirty, bdi_dirty/2); } /* - * + * bdi_min_ratio keeps the sum of the minimum dirty shares of all + * registered backing devices, which, for obvious reasons, can not + * exceed 100%. */ static unsigned int bdi_min_ratio; @@ -397,6 +352,17 @@ unsigned long determine_dirtyable_memory(void) return x + 1; /* Ensure that we never return 0 */ } +static unsigned long dirty_freerun_ceiling(unsigned long thresh, + unsigned long bg_thresh) +{ + return (thresh + bg_thresh) / 2; +} + +static unsigned long hard_dirty_limit(unsigned long thresh) +{ + return max(thresh, global_dirty_limit); +} + /* * global_dirty_limits - background-writeback and dirty-throttling thresholds * @@ -435,12 +401,20 @@ void global_dirty_limits(unsigned long *pbackground, unsigned long *pdirty) } *pbackground = background; *pdirty = dirty; + trace_global_dirty_state(background, dirty); } -/* +/** * bdi_dirty_limit - @bdi's share of dirty throttling threshold + * @bdi: the backing_dev_info to query + * @dirty: global dirty limit in pages * - * Allocate high/low dirty limits to fast/slow devices, in order to prevent + * Returns @bdi's dirty limit in pages. The term "dirty" in the context of + * dirty balancing includes all PG_dirty, PG_writeback and NFS unstable pages. + * And the "limit" in the name is not seriously taken as hard limit in + * balance_dirty_pages(). + * + * It allocates high/low dirty limits to fast/slow devices, in order to prevent * - starving fast devices * - piling up dirty pages (that will take long time to sync) on slow devices * @@ -469,36 +443,587 @@ unsigned long bdi_dirty_limit(struct backing_dev_info *bdi, unsigned long dirty) } /* + * Dirty position control. + * + * (o) global/bdi setpoints + * + * We want the dirty pages be balanced around the global/bdi setpoints. + * When the number of dirty pages is higher/lower than the setpoint, the + * dirty position control ratio (and hence task dirty ratelimit) will be + * decreased/increased to bring the dirty pages back to the setpoint. + * + * pos_ratio = 1 << RATELIMIT_CALC_SHIFT + * + * if (dirty < setpoint) scale up pos_ratio + * if (dirty > setpoint) scale down pos_ratio + * + * if (bdi_dirty < bdi_setpoint) scale up pos_ratio + * if (bdi_dirty > bdi_setpoint) scale down pos_ratio + * + * task_ratelimit = dirty_ratelimit * pos_ratio >> RATELIMIT_CALC_SHIFT + * + * (o) global control line + * + * ^ pos_ratio + * | + * | |<===== global dirty control scope ======>| + * 2.0 .............* + * | .* + * | . * + * | . * + * | . * + * | . * + * | . * + * 1.0 ................................* + * | . . * + * | . . * + * | . . * + * | . . * + * | . . * + * 0 +------------.------------------.----------------------*-------------> + * freerun^ setpoint^ limit^ dirty pages + * + * (o) bdi control line + * + * ^ pos_ratio + * | + * | * + * | * + * | * + * | * + * | * |<=========== span ============>| + * 1.0 .......................* + * | . * + * | . * + * | . * + * | . * + * | . * + * | . * + * | . * + * | . * + * | . * + * | . * + * | . * + * 1/4 ...............................................* * * * * * * * * * * * + * | . . + * | . . + * | . . + * 0 +----------------------.-------------------------------.-------------> + * bdi_setpoint^ x_intercept^ + * + * The bdi control line won't drop below pos_ratio=1/4, so that bdi_dirty can + * be smoothly throttled down to normal if it starts high in situations like + * - start writing to a slow SD card and a fast disk at the same time. The SD + * card's bdi_dirty may rush to many times higher than bdi_setpoint. + * - the bdi dirty thresh drops quickly due to change of JBOD workload + */ +static unsigned long bdi_position_ratio(struct backing_dev_info *bdi, + unsigned long thresh, + unsigned long bg_thresh, + unsigned long dirty, + unsigned long bdi_thresh, + unsigned long bdi_dirty) +{ + unsigned long write_bw = bdi->avg_write_bandwidth; + unsigned long freerun = dirty_freerun_ceiling(thresh, bg_thresh); + unsigned long limit = hard_dirty_limit(thresh); + unsigned long x_intercept; + unsigned long setpoint; /* dirty pages' target balance point */ + unsigned long bdi_setpoint; + unsigned long span; + long long pos_ratio; /* for scaling up/down the rate limit */ + long x; + + if (unlikely(dirty >= limit)) + return 0; + + /* + * global setpoint + * + * setpoint - dirty 3 + * f(dirty) := 1.0 + (----------------) + * limit - setpoint + * + * it's a 3rd order polynomial that subjects to + * + * (1) f(freerun) = 2.0 => rampup dirty_ratelimit reasonably fast + * (2) f(setpoint) = 1.0 => the balance point + * (3) f(limit) = 0 => the hard limit + * (4) df/dx <= 0 => negative feedback control + * (5) the closer to setpoint, the smaller |df/dx| (and the reverse) + * => fast response on large errors; small oscillation near setpoint + */ + setpoint = (freerun + limit) / 2; + x = div_s64((setpoint - dirty) << RATELIMIT_CALC_SHIFT, + limit - setpoint + 1); + pos_ratio = x; + pos_ratio = pos_ratio * x >> RATELIMIT_CALC_SHIFT; + pos_ratio = pos_ratio * x >> RATELIMIT_CALC_SHIFT; + pos_ratio += 1 << RATELIMIT_CALC_SHIFT; + + /* + * We have computed basic pos_ratio above based on global situation. If + * the bdi is over/under its share of dirty pages, we want to scale + * pos_ratio further down/up. That is done by the following mechanism. + */ + + /* + * bdi setpoint + * + * f(bdi_dirty) := 1.0 + k * (bdi_dirty - bdi_setpoint) + * + * x_intercept - bdi_dirty + * := -------------------------- + * x_intercept - bdi_setpoint + * + * The main bdi control line is a linear function that subjects to + * + * (1) f(bdi_setpoint) = 1.0 + * (2) k = - 1 / (8 * write_bw) (in single bdi case) + * or equally: x_intercept = bdi_setpoint + 8 * write_bw + * + * For single bdi case, the dirty pages are observed to fluctuate + * regularly within range + * [bdi_setpoint - write_bw/2, bdi_setpoint + write_bw/2] + * for various filesystems, where (2) can yield in a reasonable 12.5% + * fluctuation range for pos_ratio. + * + * For JBOD case, bdi_thresh (not bdi_dirty!) could fluctuate up to its + * own size, so move the slope over accordingly and choose a slope that + * yields 100% pos_ratio fluctuation on suddenly doubled bdi_thresh. + */ + if (unlikely(bdi_thresh > thresh)) + bdi_thresh = thresh; + bdi_thresh = max(bdi_thresh, (limit - dirty) / 8); + /* + * scale global setpoint to bdi's: + * bdi_setpoint = setpoint * bdi_thresh / thresh + */ + x = div_u64((u64)bdi_thresh << 16, thresh + 1); + bdi_setpoint = setpoint * (u64)x >> 16; + /* + * Use span=(8*write_bw) in single bdi case as indicated by + * (thresh - bdi_thresh ~= 0) and transit to bdi_thresh in JBOD case. + * + * bdi_thresh thresh - bdi_thresh + * span = ---------- * (8 * write_bw) + ------------------- * bdi_thresh + * thresh thresh + */ + span = (thresh - bdi_thresh + 8 * write_bw) * (u64)x >> 16; + x_intercept = bdi_setpoint + span; + + if (bdi_dirty < x_intercept - span / 4) { + pos_ratio = div_u64(pos_ratio * (x_intercept - bdi_dirty), + x_intercept - bdi_setpoint + 1); + } else + pos_ratio /= 4; + + /* + * bdi reserve area, safeguard against dirty pool underrun and disk idle + * It may push the desired control point of global dirty pages higher + * than setpoint. + */ + x_intercept = bdi_thresh / 2; + if (bdi_dirty < x_intercept) { + if (bdi_dirty > x_intercept / 8) + pos_ratio = div_u64(pos_ratio * x_intercept, bdi_dirty); + else + pos_ratio *= 8; + } + + return pos_ratio; +} + +static void bdi_update_write_bandwidth(struct backing_dev_info *bdi, + unsigned long elapsed, + unsigned long written) +{ + const unsigned long period = roundup_pow_of_two(3 * HZ); + unsigned long avg = bdi->avg_write_bandwidth; + unsigned long old = bdi->write_bandwidth; + u64 bw; + + /* + * bw = written * HZ / elapsed + * + * bw * elapsed + write_bandwidth * (period - elapsed) + * write_bandwidth = --------------------------------------------------- + * period + */ + bw = written - bdi->written_stamp; + bw *= HZ; + if (unlikely(elapsed > period)) { + do_div(bw, elapsed); + avg = bw; + goto out; + } + bw += (u64)bdi->write_bandwidth * (period - elapsed); + bw >>= ilog2(period); + + /* + * one more level of smoothing, for filtering out sudden spikes + */ + if (avg > old && old >= (unsigned long)bw) + avg -= (avg - old) >> 3; + + if (avg < old && old <= (unsigned long)bw) + avg += (old - avg) >> 3; + +out: + bdi->write_bandwidth = bw; + bdi->avg_write_bandwidth = avg; +} + +/* + * The global dirtyable memory and dirty threshold could be suddenly knocked + * down by a large amount (eg. on the startup of KVM in a swapless system). + * This may throw the system into deep dirty exceeded state and throttle + * heavy/light dirtiers alike. To retain good responsiveness, maintain + * global_dirty_limit for tracking slowly down to the knocked down dirty + * threshold. + */ +static void update_dirty_limit(unsigned long thresh, unsigned long dirty) +{ + unsigned long limit = global_dirty_limit; + + /* + * Follow up in one step. + */ + if (limit < thresh) { + limit = thresh; + goto update; + } + + /* + * Follow down slowly. Use the higher one as the target, because thresh + * may drop below dirty. This is exactly the reason to introduce + * global_dirty_limit which is guaranteed to lie above the dirty pages. + */ + thresh = max(thresh, dirty); + if (limit > thresh) { + limit -= (limit - thresh) >> 5; + goto update; + } + return; +update: + global_dirty_limit = limit; +} + +static void global_update_bandwidth(unsigned long thresh, + unsigned long dirty, + unsigned long now) +{ + static DEFINE_SPINLOCK(dirty_lock); + static unsigned long update_time; + + /* + * check locklessly first to optimize away locking for the most time + */ + if (time_before(now, update_time + BANDWIDTH_INTERVAL)) + return; + + spin_lock(&dirty_lock); + if (time_after_eq(now, update_time + BANDWIDTH_INTERVAL)) { + update_dirty_limit(thresh, dirty); + update_time = now; + } + spin_unlock(&dirty_lock); +} + +/* + * Maintain bdi->dirty_ratelimit, the base dirty throttle rate. + * + * Normal bdi tasks will be curbed at or below it in long term. + * Obviously it should be around (write_bw / N) when there are N dd tasks. + */ +static void bdi_update_dirty_ratelimit(struct backing_dev_info *bdi, + unsigned long thresh, + unsigned long bg_thresh, + unsigned long dirty, + unsigned long bdi_thresh, + unsigned long bdi_dirty, + unsigned long dirtied, + unsigned long elapsed) +{ + unsigned long freerun = dirty_freerun_ceiling(thresh, bg_thresh); + unsigned long limit = hard_dirty_limit(thresh); + unsigned long setpoint = (freerun + limit) / 2; + unsigned long write_bw = bdi->avg_write_bandwidth; + unsigned long dirty_ratelimit = bdi->dirty_ratelimit; + unsigned long dirty_rate; + unsigned long task_ratelimit; + unsigned long balanced_dirty_ratelimit; + unsigned long pos_ratio; + unsigned long step; + unsigned long x; + + /* + * The dirty rate will match the writeout rate in long term, except + * when dirty pages are truncated by userspace or re-dirtied by FS. + */ + dirty_rate = (dirtied - bdi->dirtied_stamp) * HZ / elapsed; + + pos_ratio = bdi_position_ratio(bdi, thresh, bg_thresh, dirty, + bdi_thresh, bdi_dirty); + /* + * task_ratelimit reflects each dd's dirty rate for the past 200ms. + */ + task_ratelimit = (u64)dirty_ratelimit * + pos_ratio >> RATELIMIT_CALC_SHIFT; + task_ratelimit++; /* it helps rampup dirty_ratelimit from tiny values */ + + /* + * A linear estimation of the "balanced" throttle rate. The theory is, + * if there are N dd tasks, each throttled at task_ratelimit, the bdi's + * dirty_rate will be measured to be (N * task_ratelimit). So the below + * formula will yield the balanced rate limit (write_bw / N). + * + * Note that the expanded form is not a pure rate feedback: + * rate_(i+1) = rate_(i) * (write_bw / dirty_rate) (1) + * but also takes pos_ratio into account: + * rate_(i+1) = rate_(i) * (write_bw / dirty_rate) * pos_ratio (2) + * + * (1) is not realistic because pos_ratio also takes part in balancing + * the dirty rate. Consider the state + * pos_ratio = 0.5 (3) + * rate = 2 * (write_bw / N) (4) + * If (1) is used, it will stuck in that state! Because each dd will + * be throttled at + * task_ratelimit = pos_ratio * rate = (write_bw / N) (5) + * yielding + * dirty_rate = N * task_ratelimit = write_bw (6) + * put (6) into (1) we get + * rate_(i+1) = rate_(i) (7) + * + * So we end up using (2) to always keep + * rate_(i+1) ~= (write_bw / N) (8) + * regardless of the value of pos_ratio. As long as (8) is satisfied, + * pos_ratio is able to drive itself to 1.0, which is not only where + * the dirty count meet the setpoint, but also where the slope of + * pos_ratio is most flat and hence task_ratelimit is least fluctuated. + */ + balanced_dirty_ratelimit = div_u64((u64)task_ratelimit * write_bw, + dirty_rate | 1); + + /* + * We could safely do this and return immediately: + * + * bdi->dirty_ratelimit = balanced_dirty_ratelimit; + * + * However to get a more stable dirty_ratelimit, the below elaborated + * code makes use of task_ratelimit to filter out sigular points and + * limit the step size. + * + * The below code essentially only uses the relative value of + * + * task_ratelimit - dirty_ratelimit + * = (pos_ratio - 1) * dirty_ratelimit + * + * which reflects the direction and size of dirty position error. + */ + + /* + * dirty_ratelimit will follow balanced_dirty_ratelimit iff + * task_ratelimit is on the same side of dirty_ratelimit, too. + * For example, when + * - dirty_ratelimit > balanced_dirty_ratelimit + * - dirty_ratelimit > task_ratelimit (dirty pages are above setpoint) + * lowering dirty_ratelimit will help meet both the position and rate + * control targets. Otherwise, don't update dirty_ratelimit if it will + * only help meet the rate target. After all, what the users ultimately + * feel and care are stable dirty rate and small position error. + * + * |task_ratelimit - dirty_ratelimit| is used to limit the step size + * and filter out the sigular points of balanced_dirty_ratelimit. Which + * keeps jumping around randomly and can even leap far away at times + * due to the small 200ms estimation period of dirty_rate (we want to + * keep that period small to reduce time lags). + */ + step = 0; + if (dirty < setpoint) { + x = min(bdi->balanced_dirty_ratelimit, + min(balanced_dirty_ratelimit, task_ratelimit)); + if (dirty_ratelimit < x) + step = x - dirty_ratelimit; + } else { + x = max(bdi->balanced_dirty_ratelimit, + max(balanced_dirty_ratelimit, task_ratelimit)); + if (dirty_ratelimit > x) + step = dirty_ratelimit - x; + } + + /* + * Don't pursue 100% rate matching. It's impossible since the balanced + * rate itself is constantly fluctuating. So decrease the track speed + * when it gets close to the target. Helps eliminate pointless tremors. + */ + step >>= dirty_ratelimit / (2 * step + 1); + /* + * Limit the tracking speed to avoid overshooting. + */ + step = (step + 7) / 8; + + if (dirty_ratelimit < balanced_dirty_ratelimit) + dirty_ratelimit += step; + else + dirty_ratelimit -= step; + + bdi->dirty_ratelimit = max(dirty_ratelimit, 1UL); + bdi->balanced_dirty_ratelimit = balanced_dirty_ratelimit; + + trace_bdi_dirty_ratelimit(bdi, dirty_rate, task_ratelimit); +} + +void __bdi_update_bandwidth(struct backing_dev_info *bdi, + unsigned long thresh, + unsigned long bg_thresh, + unsigned long dirty, + unsigned long bdi_thresh, + unsigned long bdi_dirty, + unsigned long start_time) +{ + unsigned long now = jiffies; + unsigned long elapsed = now - bdi->bw_time_stamp; + unsigned long dirtied; + unsigned long written; + + /* + * rate-limit, only update once every 200ms. + */ + if (elapsed < BANDWIDTH_INTERVAL) + return; + + dirtied = percpu_counter_read(&bdi->bdi_stat[BDI_DIRTIED]); + written = percpu_counter_read(&bdi->bdi_stat[BDI_WRITTEN]); + + /* + * Skip quiet periods when disk bandwidth is under-utilized. + * (at least 1s idle time between two flusher runs) + */ + if (elapsed > HZ && time_before(bdi->bw_time_stamp, start_time)) + goto snapshot; + + if (thresh) { + global_update_bandwidth(thresh, dirty, now); + bdi_update_dirty_ratelimit(bdi, thresh, bg_thresh, dirty, + bdi_thresh, bdi_dirty, + dirtied, elapsed); + } + bdi_update_write_bandwidth(bdi, elapsed, written); + +snapshot: + bdi->dirtied_stamp = dirtied; + bdi->written_stamp = written; + bdi->bw_time_stamp = now; +} + +static void bdi_update_bandwidth(struct backing_dev_info *bdi, + unsigned long thresh, + unsigned long bg_thresh, + unsigned long dirty, + unsigned long bdi_thresh, + unsigned long bdi_dirty, + unsigned long start_time) +{ + if (time_is_after_eq_jiffies(bdi->bw_time_stamp + BANDWIDTH_INTERVAL)) + return; + spin_lock(&bdi->wb.list_lock); + __bdi_update_bandwidth(bdi, thresh, bg_thresh, dirty, + bdi_thresh, bdi_dirty, start_time); + spin_unlock(&bdi->wb.list_lock); +} + +/* + * After a task dirtied this many pages, balance_dirty_pages_ratelimited_nr() + * will look to see if it needs to start dirty throttling. + * + * If dirty_poll_interval is too low, big NUMA machines will call the expensive + * global_page_state() too often. So scale it near-sqrt to the safety margin + * (the number of pages we may dirty without exceeding the dirty limits). + */ +static unsigned long dirty_poll_interval(unsigned long dirty, + unsigned long thresh) +{ + if (thresh > dirty) + return 1UL << (ilog2(thresh - dirty) >> 1); + + return 1; +} + +static unsigned long bdi_max_pause(struct backing_dev_info *bdi, + unsigned long bdi_dirty) +{ + unsigned long bw = bdi->avg_write_bandwidth; + unsigned long hi = ilog2(bw); + unsigned long lo = ilog2(bdi->dirty_ratelimit); + unsigned long t; + + /* target for 20ms max pause on 1-dd case */ + t = HZ / 50; + + /* + * Scale up pause time for concurrent dirtiers in order to reduce CPU + * overheads. + * + * (N * 20ms) on 2^N concurrent tasks. + */ + if (hi > lo) + t += (hi - lo) * (20 * HZ) / 1024; + + /* + * Limit pause time for small memory systems. If sleeping for too long + * time, a small pool of dirty/writeback pages may go empty and disk go + * idle. + * + * 8 serves as the safety ratio. + */ + if (bdi_dirty) + t = min(t, bdi_dirty * HZ / (8 * bw + 1)); + + /* + * The pause time will be settled within range (max_pause/4, max_pause). + * Apply a minimal value of 4 to get a non-zero max_pause/4. + */ + return clamp_val(t, 4, MAX_PAUSE); +} + +/* * balance_dirty_pages() must be called by processes which are generating dirty * data. It looks at the number of dirty pages in the machine and will force - * the caller to perform writeback if the system is over `vm_dirty_ratio'. + * the caller to wait once crossing the (background_thresh + dirty_thresh) / 2. * If we're over `background_thresh' then the writeback threads are woken to * perform some writeout. */ static void balance_dirty_pages(struct address_space *mapping, - unsigned long write_chunk) + unsigned long pages_dirtied) { - long nr_reclaimable, bdi_nr_reclaimable; - long nr_writeback, bdi_nr_writeback; + unsigned long nr_reclaimable; /* = file_dirty + unstable_nfs */ + unsigned long bdi_reclaimable; + unsigned long nr_dirty; /* = file_dirty + writeback + unstable_nfs */ + unsigned long bdi_dirty; + unsigned long freerun; unsigned long background_thresh; unsigned long dirty_thresh; unsigned long bdi_thresh; - unsigned long pages_written = 0; - unsigned long pause = 1; + long pause = 0; + long uninitialized_var(max_pause); bool dirty_exceeded = false; + unsigned long task_ratelimit; + unsigned long uninitialized_var(dirty_ratelimit); + unsigned long pos_ratio; struct backing_dev_info *bdi = mapping->backing_dev_info; + unsigned long start_time = jiffies; for (;;) { - struct writeback_control wbc = { - .sync_mode = WB_SYNC_NONE, - .older_than_this = NULL, - .nr_to_write = write_chunk, - .range_cyclic = 1, - }; - + /* + * Unstable writes are a feature of certain networked + * filesystems (i.e. NFS) in which data may have been + * written to the server's write cache, but has not yet + * been flushed to permanent storage. + */ nr_reclaimable = global_page_state(NR_FILE_DIRTY) + global_page_state(NR_UNSTABLE_NFS); - nr_writeback = global_page_state(NR_WRITEBACK); + nr_dirty = nr_reclaimable + global_page_state(NR_WRITEBACK); global_dirty_limits(&background_thresh, &dirty_thresh); @@ -507,12 +1032,28 @@ static void balance_dirty_pages(struct address_space *mapping, * catch-up. This avoids (excessively) small writeouts * when the bdi limits are ramping up. */ - if (nr_reclaimable + nr_writeback <= - (background_thresh + dirty_thresh) / 2) + freerun = dirty_freerun_ceiling(dirty_thresh, + background_thresh); + if (nr_dirty <= freerun) break; + if (unlikely(!writeback_in_progress(bdi))) + bdi_start_background_writeback(bdi); + + /* + * bdi_thresh is not treated as some limiting factor as + * dirty_thresh, due to reasons + * - in JBOD setup, bdi_thresh can fluctuate a lot + * - in a system with HDD and USB key, the USB key may somehow + * go into state (bdi_dirty >> bdi_thresh) either because + * bdi_dirty starts high, or because bdi_thresh drops low. + * In this case we don't want to hard throttle the USB key + * dirtiers for 100 seconds until bdi_dirty drops under + * bdi_thresh. Instead the auxiliary bdi control line in + * bdi_position_ratio() will let the dirtier task progress + * at some rate <= (write_bw / 2) for bringing down bdi_dirty. + */ bdi_thresh = bdi_dirty_limit(bdi, dirty_thresh); - bdi_thresh = task_dirty_limit(current, bdi_thresh); /* * In order to avoid the stacked BDI deadlock we need @@ -524,63 +1065,101 @@ static void balance_dirty_pages(struct address_space *mapping, * actually dirty; with m+n sitting in the percpu * deltas. */ - if (bdi_thresh < 2*bdi_stat_error(bdi)) { - bdi_nr_reclaimable = bdi_stat_sum(bdi, BDI_RECLAIMABLE); - bdi_nr_writeback = bdi_stat_sum(bdi, BDI_WRITEBACK); + if (bdi_thresh < 2 * bdi_stat_error(bdi)) { + bdi_reclaimable = bdi_stat_sum(bdi, BDI_RECLAIMABLE); + bdi_dirty = bdi_reclaimable + + bdi_stat_sum(bdi, BDI_WRITEBACK); } else { - bdi_nr_reclaimable = bdi_stat(bdi, BDI_RECLAIMABLE); - bdi_nr_writeback = bdi_stat(bdi, BDI_WRITEBACK); + bdi_reclaimable = bdi_stat(bdi, BDI_RECLAIMABLE); + bdi_dirty = bdi_reclaimable + + bdi_stat(bdi, BDI_WRITEBACK); } - /* - * The bdi thresh is somehow "soft" limit derived from the - * global "hard" limit. The former helps to prevent heavy IO - * bdi or process from holding back light ones; The latter is - * the last resort safeguard. - */ - dirty_exceeded = - (bdi_nr_reclaimable + bdi_nr_writeback > bdi_thresh) - || (nr_reclaimable + nr_writeback > dirty_thresh); - - if (!dirty_exceeded) - break; - - if (!bdi->dirty_exceeded) + dirty_exceeded = (bdi_dirty > bdi_thresh) || + (nr_dirty > dirty_thresh); + if (dirty_exceeded && !bdi->dirty_exceeded) bdi->dirty_exceeded = 1; - /* Note: nr_reclaimable denotes nr_dirty + nr_unstable. - * Unstable writes are a feature of certain networked - * filesystems (i.e. NFS) in which data may have been - * written to the server's write cache, but has not yet - * been flushed to permanent storage. - * Only move pages to writeback if this bdi is over its - * threshold otherwise wait until the disk writes catch - * up. - */ - trace_wbc_balance_dirty_start(&wbc, bdi); - if (bdi_nr_reclaimable > bdi_thresh) { - writeback_inodes_wb(&bdi->wb, &wbc); - pages_written += write_chunk - wbc.nr_to_write; - trace_wbc_balance_dirty_written(&wbc, bdi); - if (pages_written >= write_chunk) - break; /* We've done our duty */ + bdi_update_bandwidth(bdi, dirty_thresh, background_thresh, + nr_dirty, bdi_thresh, bdi_dirty, + start_time); + + max_pause = bdi_max_pause(bdi, bdi_dirty); + + dirty_ratelimit = bdi->dirty_ratelimit; + pos_ratio = bdi_position_ratio(bdi, dirty_thresh, + background_thresh, nr_dirty, + bdi_thresh, bdi_dirty); + task_ratelimit = ((u64)dirty_ratelimit * pos_ratio) >> + RATELIMIT_CALC_SHIFT; + if (unlikely(task_ratelimit == 0)) { + pause = max_pause; + goto pause; } - trace_wbc_balance_dirty_wait(&wbc, bdi); - __set_current_state(TASK_UNINTERRUPTIBLE); + pause = HZ * pages_dirtied / task_ratelimit; + if (unlikely(pause <= 0)) { + trace_balance_dirty_pages(bdi, + dirty_thresh, + background_thresh, + nr_dirty, + bdi_thresh, + bdi_dirty, + dirty_ratelimit, + task_ratelimit, + pages_dirtied, + pause, + start_time); + pause = 1; /* avoid resetting nr_dirtied_pause below */ + break; + } + pause = min(pause, max_pause); + +pause: + trace_balance_dirty_pages(bdi, + dirty_thresh, + background_thresh, + nr_dirty, + bdi_thresh, + bdi_dirty, + dirty_ratelimit, + task_ratelimit, + pages_dirtied, + pause, + start_time); + __set_current_state(TASK_KILLABLE); io_schedule_timeout(pause); /* - * Increase the delay for each loop, up to our previous - * default of taking a 100ms nap. + * This is typically equal to (nr_dirty < dirty_thresh) and can + * also keep "1000+ dd on a slow USB stick" under control. */ - pause <<= 1; - if (pause > HZ / 10) - pause = HZ / 10; + if (task_ratelimit) + break; + + if (fatal_signal_pending(current)) + break; } if (!dirty_exceeded && bdi->dirty_exceeded) bdi->dirty_exceeded = 0; + current->nr_dirtied = 0; + if (pause == 0) { /* in freerun area */ + current->nr_dirtied_pause = + dirty_poll_interval(nr_dirty, dirty_thresh); + } else if (pause <= max_pause / 4 && + pages_dirtied >= current->nr_dirtied_pause) { + current->nr_dirtied_pause = clamp_val( + dirty_ratelimit * (max_pause / 2) / HZ, + pages_dirtied + pages_dirtied / 8, + pages_dirtied * 4); + } else if (pause >= max_pause) { + current->nr_dirtied_pause = 1 | clamp_val( + dirty_ratelimit * (max_pause / 2) / HZ, + pages_dirtied / 4, + pages_dirtied - pages_dirtied / 8); + } + if (writeback_in_progress(bdi)) return; @@ -592,8 +1171,10 @@ static void balance_dirty_pages(struct address_space *mapping, * In normal mode, we start background writeout at the lower * background_thresh, to keep the amount of dirty memory low. */ - if ((laptop_mode && pages_written) || - (!laptop_mode && (nr_reclaimable > background_thresh))) + if (laptop_mode) + return; + + if (nr_reclaimable > background_thresh) bdi_start_background_writeback(bdi); } @@ -607,7 +1188,7 @@ void set_page_dirty_balance(struct page *page, int page_mkwrite) } } -static DEFINE_PER_CPU(unsigned long, bdp_ratelimits) = 0; +static DEFINE_PER_CPU(int, bdp_ratelimits); /** * balance_dirty_pages_ratelimited_nr - balance dirty memory state @@ -626,28 +1207,40 @@ static DEFINE_PER_CPU(unsigned long, bdp_ratelimits) = 0; void balance_dirty_pages_ratelimited_nr(struct address_space *mapping, unsigned long nr_pages_dirtied) { - unsigned long ratelimit; - unsigned long *p; + struct backing_dev_info *bdi = mapping->backing_dev_info; + int ratelimit; + int *p; + + if (!bdi_cap_account_dirty(bdi)) + return; - ratelimit = ratelimit_pages; - if (mapping->backing_dev_info->dirty_exceeded) - ratelimit = 8; + ratelimit = current->nr_dirtied_pause; + if (bdi->dirty_exceeded) + ratelimit = min(ratelimit, 32 >> (PAGE_SHIFT - 10)); + current->nr_dirtied += nr_pages_dirtied; + + preempt_disable(); /* - * Check the rate limiting. Also, we do not want to throttle real-time - * tasks in balance_dirty_pages(). Period. + * This prevents one CPU to accumulate too many dirtied pages without + * calling into balance_dirty_pages(), which can happen when there are + * 1000+ tasks, all of them start dirtying pages at exactly the same + * time, hence all honoured too large initial task->nr_dirtied_pause. */ - preempt_disable(); p = &__get_cpu_var(bdp_ratelimits); - *p += nr_pages_dirtied; - if (unlikely(*p >= ratelimit)) { - ratelimit = sync_writeback_pages(*p); + if (unlikely(current->nr_dirtied >= ratelimit)) *p = 0; - preempt_enable(); - balance_dirty_pages(mapping, ratelimit); - return; + else { + *p += nr_pages_dirtied; + if (unlikely(*p >= ratelimit_pages)) { + *p = 0; + ratelimit = 0; + } } preempt_enable(); + + if (unlikely(current->nr_dirtied >= ratelimit)) + balance_dirty_pages(mapping, current->nr_dirtied); } EXPORT_SYMBOL(balance_dirty_pages_ratelimited_nr); @@ -703,7 +1296,8 @@ void laptop_mode_timer_fn(unsigned long data) * threshold */ if (bdi_has_dirty_io(&q->backing_dev_info)) - bdi_start_writeback(&q->backing_dev_info, nr_pages); + bdi_start_writeback(&q->backing_dev_info, nr_pages, + WB_REASON_LAPTOP_TIMER); } /* @@ -742,22 +1336,17 @@ void laptop_sync_completion(void) * * Here we set ratelimit_pages to a level which ensures that when all CPUs are * dirtying in parallel, we cannot go more than 3% (1/32) over the dirty memory - * thresholds before writeback cuts in. - * - * But the limit should not be set too high. Because it also controls the - * amount of memory which the balance_dirty_pages() caller has to write back. - * If this is too large then the caller will block on the IO queue all the - * time. So limit it to four megabytes - the balance_dirty_pages() caller - * will write six megabyte chunks, max. + * thresholds. */ void writeback_set_ratelimit(void) { - ratelimit_pages = vm_total_pages / (num_online_cpus() * 32); + unsigned long background_thresh; + unsigned long dirty_thresh; + global_dirty_limits(&background_thresh, &dirty_thresh); + ratelimit_pages = dirty_thresh / (num_online_cpus() * 32); if (ratelimit_pages < 16) ratelimit_pages = 16; - if (ratelimit_pages * PAGE_CACHE_SIZE > 4096 * 1024) - ratelimit_pages = (4096 * 1024) / PAGE_CACHE_SIZE; } static int __cpuinit @@ -799,7 +1388,6 @@ void __init page_writeback_init(void) shift = calc_period_shift(); prop_descriptor_init(&vm_completions, shift); - prop_descriptor_init(&vm_dirties, shift); } /** @@ -892,12 +1480,12 @@ int write_cache_pages(struct address_space *mapping, range_whole = 1; cycled = 1; /* ignore range_cyclic tests */ } - if (wbc->sync_mode == WB_SYNC_ALL) + if (wbc->sync_mode == WB_SYNC_ALL || wbc->tagged_writepages) tag = PAGECACHE_TAG_TOWRITE; else tag = PAGECACHE_TAG_DIRTY; retry: - if (wbc->sync_mode == WB_SYNC_ALL) + if (wbc->sync_mode == WB_SYNC_ALL || wbc->tagged_writepages) tag_pages_for_writeback(mapping, index, end); done_index = index; while (!done && (index <= end)) { @@ -1127,7 +1715,7 @@ void account_page_dirtied(struct page *page, struct address_space *mapping) __inc_zone_page_state(page, NR_FILE_DIRTY); __inc_zone_page_state(page, NR_DIRTIED); __inc_bdi_stat(mapping->backing_dev_info, BDI_RECLAIMABLE); - task_dirty_inc(current); + __inc_bdi_stat(mapping->backing_dev_info, BDI_DIRTIED); task_io_account_write(PAGE_CACHE_SIZE); } } @@ -1141,7 +1729,6 @@ EXPORT_SYMBOL(account_page_dirtied); void account_page_writeback(struct page *page) { inc_zone_page_state(page, NR_WRITEBACK); - inc_zone_page_state(page, NR_WRITTEN); } EXPORT_SYMBOL(account_page_writeback); @@ -1358,8 +1945,10 @@ int test_clear_page_writeback(struct page *page) } else { ret = TestClearPageWriteback(page); } - if (ret) + if (ret) { dec_zone_page_state(page, NR_WRITEBACK); + inc_zone_page_state(page, NR_WRITTEN); + } return ret; } @@ -1405,10 +1994,6 @@ EXPORT_SYMBOL(test_set_page_writeback); */ int mapping_tagged(struct address_space *mapping, int tag) { - int ret; - rcu_read_lock(); - ret = radix_tree_tagged(&mapping->page_tree, tag); - rcu_read_unlock(); - return ret; + return radix_tree_tagged(&mapping->page_tree, tag); } EXPORT_SYMBOL(mapping_tagged); diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 3c7ea45..6ce2733 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -321,6 +321,7 @@ static void bad_page(struct page *page) current->comm, page_to_pfn(page)); dump_page(page); + print_modules(); dump_stack(); out: /* Leave bad fields for debug, except PageBuddy could make trouble */ @@ -1373,21 +1374,12 @@ failed: #ifdef CONFIG_FAIL_PAGE_ALLOC -static struct fail_page_alloc_attr { +static struct { struct fault_attr attr; u32 ignore_gfp_highmem; u32 ignore_gfp_wait; u32 min_order; - -#ifdef CONFIG_FAULT_INJECTION_DEBUG_FS - - struct dentry *ignore_gfp_highmem_file; - struct dentry *ignore_gfp_wait_file; - struct dentry *min_order_file; - -#endif /* CONFIG_FAULT_INJECTION_DEBUG_FS */ - } fail_page_alloc = { .attr = FAULT_ATTR_INITIALIZER, .ignore_gfp_wait = 1, @@ -1421,36 +1413,27 @@ static int __init fail_page_alloc_debugfs(void) { mode_t mode = S_IFREG | S_IRUSR | S_IWUSR; struct dentry *dir; - int err; - - err = init_fault_attr_dentries(&fail_page_alloc.attr, - "fail_page_alloc"); - if (err) - return err; - dir = fail_page_alloc.attr.dentries.dir; - - fail_page_alloc.ignore_gfp_wait_file = - debugfs_create_bool("ignore-gfp-wait", mode, dir, - &fail_page_alloc.ignore_gfp_wait); - - fail_page_alloc.ignore_gfp_highmem_file = - debugfs_create_bool("ignore-gfp-highmem", mode, dir, - &fail_page_alloc.ignore_gfp_highmem); - fail_page_alloc.min_order_file = - debugfs_create_u32("min-order", mode, dir, - &fail_page_alloc.min_order); - - if (!fail_page_alloc.ignore_gfp_wait_file || - !fail_page_alloc.ignore_gfp_highmem_file || - !fail_page_alloc.min_order_file) { - err = -ENOMEM; - debugfs_remove(fail_page_alloc.ignore_gfp_wait_file); - debugfs_remove(fail_page_alloc.ignore_gfp_highmem_file); - debugfs_remove(fail_page_alloc.min_order_file); - cleanup_fault_attr_dentries(&fail_page_alloc.attr); - } - return err; + dir = fault_create_debugfs_attr("fail_page_alloc", NULL, + &fail_page_alloc.attr); + if (IS_ERR(dir)) + return PTR_ERR(dir); + + if (!debugfs_create_bool("ignore-gfp-wait", mode, dir, + &fail_page_alloc.ignore_gfp_wait)) + goto fail; + if (!debugfs_create_bool("ignore-gfp-highmem", mode, dir, + &fail_page_alloc.ignore_gfp_highmem)) + goto fail; + if (!debugfs_create_u32("min-order", mode, dir, + &fail_page_alloc.min_order)) + goto fail; + + return 0; +fail: + debugfs_remove_recursive(dir); + + return -ENOMEM; } late_initcall(fail_page_alloc_debugfs); @@ -1619,6 +1602,21 @@ static void zlc_mark_zone_full(struct zonelist *zonelist, struct zoneref *z) set_bit(i, zlc->fullzones); } +/* + * clear all zones full, called after direct reclaim makes progress so that + * a zone that was recently full is not skipped over for up to a second + */ +static void zlc_clear_zones_full(struct zonelist *zonelist) +{ + struct zonelist_cache *zlc; /* cached zonelist speedup info */ + + zlc = zonelist->zlcache_ptr; + if (!zlc) + return; + + bitmap_zero(zlc->fullzones, MAX_ZONES_PER_ZONELIST); +} + #else /* CONFIG_NUMA */ static nodemask_t *zlc_setup(struct zonelist *zonelist, int alloc_flags) @@ -1635,6 +1633,10 @@ static int zlc_zone_worth_trying(struct zonelist *zonelist, struct zoneref *z, static void zlc_mark_zone_full(struct zonelist *zonelist, struct zoneref *z) { } + +static void zlc_clear_zones_full(struct zonelist *zonelist) +{ +} #endif /* CONFIG_NUMA */ /* @@ -1667,7 +1669,7 @@ zonelist_scan: continue; if ((alloc_flags & ALLOC_CPUSET) && !cpuset_zone_allowed_softwall(zone, gfp_mask)) - goto try_next_zone; + continue; BUILD_BUG_ON(ALLOC_NO_WATERMARKS < NR_WMARK); if (!(alloc_flags & ALLOC_NO_WATERMARKS)) { @@ -1679,17 +1681,36 @@ zonelist_scan: classzone_idx, alloc_flags)) goto try_this_zone; + if (NUMA_BUILD && !did_zlc_setup && nr_online_nodes > 1) { + /* + * we do zlc_setup if there are multiple nodes + * and before considering the first zone allowed + * by the cpuset. + */ + allowednodes = zlc_setup(zonelist, alloc_flags); + zlc_active = 1; + did_zlc_setup = 1; + } + if (zone_reclaim_mode == 0) goto this_zone_full; + /* + * As we may have just activated ZLC, check if the first + * eligible zone has failed zone_reclaim recently. + */ + if (NUMA_BUILD && zlc_active && + !zlc_zone_worth_trying(zonelist, z, allowednodes)) + continue; + ret = zone_reclaim(zone, gfp_mask, order); switch (ret) { case ZONE_RECLAIM_NOSCAN: /* did not scan */ - goto try_next_zone; + continue; case ZONE_RECLAIM_FULL: /* scanned but unreclaimable */ - goto this_zone_full; + continue; default: /* did we reclaim enough */ if (!zone_watermark_ok(zone, order, mark, @@ -1706,16 +1727,6 @@ try_this_zone: this_zone_full: if (NUMA_BUILD) zlc_mark_zone_full(zonelist, z); -try_next_zone: - if (NUMA_BUILD && !did_zlc_setup && nr_online_nodes > 1) { - /* - * we do zlc_setup after the first zone is tried but only - * if there are multiple nodes make it worthwhile - */ - allowednodes = zlc_setup(zonelist, alloc_flags); - zlc_active = 1; - did_zlc_setup = 1; - } } if (unlikely(NUMA_BUILD && page == NULL && zlc_active)) { @@ -1746,7 +1757,6 @@ static DEFINE_RATELIMIT_STATE(nopage_rs, void warn_alloc_failed(gfp_t gfp_mask, int order, const char *fmt, ...) { - va_list args; unsigned int filter = SHOW_MEM_FILTER_NODES; if ((gfp_mask & __GFP_NOWARN) || !__ratelimit(&nopage_rs)) @@ -1765,14 +1775,21 @@ void warn_alloc_failed(gfp_t gfp_mask, int order, const char *fmt, ...) filter &= ~SHOW_MEM_FILTER_NODES; if (fmt) { - printk(KERN_WARNING); + struct va_format vaf; + va_list args; + va_start(args, fmt); - vprintk(fmt, args); + + vaf.fmt = fmt; + vaf.va = &args; + + pr_warn("%pV", &vaf); + va_end(args); } - pr_warning("%s: page allocation failure: order:%d, mode:0x%x\n", - current->comm, order, gfp_mask); + pr_warn("%s: page allocation failure: order:%d, mode:0x%x\n", + current->comm, order, gfp_mask); dump_stack(); if (!should_suppress_show_mem()) @@ -1957,6 +1974,10 @@ __alloc_pages_direct_reclaim(gfp_t gfp_mask, unsigned int order, if (unlikely(!(*did_some_progress))) return NULL; + /* After successful reclaim, reconsider all zones for allocation */ + if (NUMA_BUILD) + zlc_clear_zones_full(zonelist); + retry: page = get_page_from_freelist(gfp_mask, nodemask, order, zonelist, high_zoneidx, diff --git a/mm/page_cgroup.c b/mm/page_cgroup.c index 53bffc6..2d123f9 100644 --- a/mm/page_cgroup.c +++ b/mm/page_cgroup.c @@ -133,10 +133,13 @@ struct page *lookup_cgroup_page(struct page_cgroup *pc) static void *__meminit alloc_page_cgroup(size_t size, int nid) { void *addr = NULL; + gfp_t flags = GFP_KERNEL | __GFP_NOWARN; - addr = alloc_pages_exact_nid(nid, size, GFP_KERNEL | __GFP_NOWARN); - if (addr) + addr = alloc_pages_exact_nid(nid, size, flags); + if (addr) { + kmemleak_alloc(addr, size, 1, flags); return addr; + } if (node_state(nid, N_HIGH_MEMORY)) addr = vmalloc_node(size, nid); @@ -225,8 +228,8 @@ int __meminit online_page_cgroup(unsigned long start_pfn, unsigned long start, end, pfn; int fail = 0; - start = start_pfn & ~(PAGES_PER_SECTION - 1); - end = ALIGN(start_pfn + nr_pages, PAGES_PER_SECTION); + start = SECTION_ALIGN_DOWN(start_pfn); + end = SECTION_ALIGN_UP(start_pfn + nr_pages); if (nid == -1) { /* @@ -258,8 +261,8 @@ int __meminit offline_page_cgroup(unsigned long start_pfn, { unsigned long start, end, pfn; - start = start_pfn & ~(PAGES_PER_SECTION - 1); - end = ALIGN(start_pfn + nr_pages, PAGES_PER_SECTION); + start = SECTION_ALIGN_DOWN(start_pfn); + end = SECTION_ALIGN_UP(start_pfn + nr_pages); for (pfn = start; pfn < end; pfn += PAGES_PER_SECTION) __free_page_cgroup(pfn); @@ -357,7 +360,7 @@ struct swap_cgroup_ctrl { spinlock_t lock; }; -struct swap_cgroup_ctrl swap_cgroup_ctrl[MAX_SWAPFILES]; +static struct swap_cgroup_ctrl swap_cgroup_ctrl[MAX_SWAPFILES]; struct swap_cgroup { unsigned short id; @@ -513,11 +516,10 @@ int swap_cgroup_swapon(int type, unsigned long max_pages) length = DIV_ROUND_UP(max_pages, SC_PER_PAGE); array_size = length * sizeof(void *); - array = vmalloc(array_size); + array = vzalloc(array_size); if (!array) goto nomem; - memset(array, 0, array_size); ctrl = &swap_cgroup_ctrl[type]; mutex_lock(&swap_cgroup_mutex); ctrl->length = length; @@ -537,7 +539,7 @@ int swap_cgroup_swapon(int type, unsigned long max_pages) nomem: printk(KERN_INFO "couldn't allocate enough memory for swap_cgroup.\n"); printk(KERN_INFO - "swap_cgroup can be disabled by noswapaccount boot option\n"); + "swap_cgroup can be disabled by swapaccount=0 boot option\n"); return -ENOMEM; } diff --git a/mm/pagewalk.c b/mm/pagewalk.c index c3450d5..2f5cf10 100644 --- a/mm/pagewalk.c +++ b/mm/pagewalk.c @@ -126,7 +126,39 @@ static int walk_hugetlb_range(struct vm_area_struct *vma, return 0; } -#endif + +static struct vm_area_struct* hugetlb_vma(unsigned long addr, struct mm_walk *walk) +{ + struct vm_area_struct *vma; + + /* We don't need vma lookup at all. */ + if (!walk->hugetlb_entry) + return NULL; + + VM_BUG_ON(!rwsem_is_locked(&walk->mm->mmap_sem)); + vma = find_vma(walk->mm, addr); + if (vma && vma->vm_start <= addr && is_vm_hugetlb_page(vma)) + return vma; + + return NULL; +} + +#else /* CONFIG_HUGETLB_PAGE */ +static struct vm_area_struct* hugetlb_vma(unsigned long addr, struct mm_walk *walk) +{ + return NULL; +} + +static int walk_hugetlb_range(struct vm_area_struct *vma, + unsigned long addr, unsigned long end, + struct mm_walk *walk) +{ + return 0; +} + +#endif /* CONFIG_HUGETLB_PAGE */ + + /** * walk_page_range - walk a memory map's page tables with a callback @@ -144,11 +176,15 @@ static int walk_hugetlb_range(struct vm_area_struct *vma, * associated range, and a copy of the original mm_walk for access to * the ->private or ->mm fields. * - * No locks are taken, but the bottom level iterator will map PTE + * Usually no locks are taken, but splitting transparent huge page may + * take page table lock. And the bottom level iterator will map PTE * directories from highmem if necessary. * * If any callback returns a non-zero value, the walk is aborted and * the return value is propagated back to the caller. Otherwise 0 is returned. + * + * walk->mm->mmap_sem must be held for at least read if walk->hugetlb_entry + * is !NULL. */ int walk_page_range(unsigned long addr, unsigned long end, struct mm_walk *walk) @@ -165,18 +201,17 @@ int walk_page_range(unsigned long addr, unsigned long end, pgd = pgd_offset(walk->mm, addr); do { - struct vm_area_struct *uninitialized_var(vma); + struct vm_area_struct *vma; next = pgd_addr_end(addr, end); -#ifdef CONFIG_HUGETLB_PAGE /* * handle hugetlb vma individually because pagetable walk for * the hugetlb page is dependent on the architecture and * we can't handled it in the same manner as non-huge pages. */ - vma = find_vma(walk->mm, addr); - if (vma && is_vm_hugetlb_page(vma)) { + vma = hugetlb_vma(addr, walk); + if (vma) { if (vma->vm_end < next) next = vma->vm_end; /* @@ -189,7 +224,7 @@ int walk_page_range(unsigned long addr, unsigned long end, pgd = pgd_offset(walk->mm, next); continue; } -#endif + if (pgd_none_or_clear_bad(pgd)) { if (walk->pte_hole) err = walk->pte_hole(addr, next, walk); diff --git a/mm/process_vm_access.c b/mm/process_vm_access.c new file mode 100644 index 0000000..e920aa3 --- /dev/null +++ b/mm/process_vm_access.c @@ -0,0 +1,496 @@ +/* + * linux/mm/process_vm_access.c + * + * Copyright (C) 2010-2011 Christopher Yeoh <cyeoh@au1.ibm.com>, IBM Corp. + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; either version + * 2 of the License, or (at your option) any later version. + */ + +#include <linux/mm.h> +#include <linux/uio.h> +#include <linux/sched.h> +#include <linux/highmem.h> +#include <linux/ptrace.h> +#include <linux/slab.h> +#include <linux/syscalls.h> + +#ifdef CONFIG_COMPAT +#include <linux/compat.h> +#endif + +/** + * process_vm_rw_pages - read/write pages from task specified + * @task: task to read/write from + * @mm: mm for task + * @process_pages: struct pages area that can store at least + * nr_pages_to_copy struct page pointers + * @pa: address of page in task to start copying from/to + * @start_offset: offset in page to start copying from/to + * @len: number of bytes to copy + * @lvec: iovec array specifying where to copy to/from + * @lvec_cnt: number of elements in iovec array + * @lvec_current: index in iovec array we are up to + * @lvec_offset: offset in bytes from current iovec iov_base we are up to + * @vm_write: 0 means copy from, 1 means copy to + * @nr_pages_to_copy: number of pages to copy + * @bytes_copied: returns number of bytes successfully copied + * Returns 0 on success, error code otherwise + */ +static int process_vm_rw_pages(struct task_struct *task, + struct mm_struct *mm, + struct page **process_pages, + unsigned long pa, + unsigned long start_offset, + unsigned long len, + const struct iovec *lvec, + unsigned long lvec_cnt, + unsigned long *lvec_current, + size_t *lvec_offset, + int vm_write, + unsigned int nr_pages_to_copy, + ssize_t *bytes_copied) +{ + int pages_pinned; + void *target_kaddr; + int pgs_copied = 0; + int j; + int ret; + ssize_t bytes_to_copy; + ssize_t rc = 0; + + *bytes_copied = 0; + + /* Get the pages we're interested in */ + down_read(&mm->mmap_sem); + pages_pinned = get_user_pages(task, mm, pa, + nr_pages_to_copy, + vm_write, 0, process_pages, NULL); + up_read(&mm->mmap_sem); + + if (pages_pinned != nr_pages_to_copy) { + rc = -EFAULT; + goto end; + } + + /* Do the copy for each page */ + for (pgs_copied = 0; + (pgs_copied < nr_pages_to_copy) && (*lvec_current < lvec_cnt); + pgs_copied++) { + /* Make sure we have a non zero length iovec */ + while (*lvec_current < lvec_cnt + && lvec[*lvec_current].iov_len == 0) + (*lvec_current)++; + if (*lvec_current == lvec_cnt) + break; + + /* + * Will copy smallest of: + * - bytes remaining in page + * - bytes remaining in destination iovec + */ + bytes_to_copy = min_t(ssize_t, PAGE_SIZE - start_offset, + len - *bytes_copied); + bytes_to_copy = min_t(ssize_t, bytes_to_copy, + lvec[*lvec_current].iov_len + - *lvec_offset); + + target_kaddr = kmap(process_pages[pgs_copied]) + start_offset; + + if (vm_write) + ret = copy_from_user(target_kaddr, + lvec[*lvec_current].iov_base + + *lvec_offset, + bytes_to_copy); + else + ret = copy_to_user(lvec[*lvec_current].iov_base + + *lvec_offset, + target_kaddr, bytes_to_copy); + kunmap(process_pages[pgs_copied]); + if (ret) { + *bytes_copied += bytes_to_copy - ret; + pgs_copied++; + rc = -EFAULT; + goto end; + } + *bytes_copied += bytes_to_copy; + *lvec_offset += bytes_to_copy; + if (*lvec_offset == lvec[*lvec_current].iov_len) { + /* + * Need to copy remaining part of page into the + * next iovec if there are any bytes left in page + */ + (*lvec_current)++; + *lvec_offset = 0; + start_offset = (start_offset + bytes_to_copy) + % PAGE_SIZE; + if (start_offset) + pgs_copied--; + } else { + start_offset = 0; + } + } + +end: + if (vm_write) { + for (j = 0; j < pages_pinned; j++) { + if (j < pgs_copied) + set_page_dirty_lock(process_pages[j]); + put_page(process_pages[j]); + } + } else { + for (j = 0; j < pages_pinned; j++) + put_page(process_pages[j]); + } + + return rc; +} + +/* Maximum number of pages kmalloc'd to hold struct page's during copy */ +#define PVM_MAX_KMALLOC_PAGES (PAGE_SIZE * 2) + +/** + * process_vm_rw_single_vec - read/write pages from task specified + * @addr: start memory address of target process + * @len: size of area to copy to/from + * @lvec: iovec array specifying where to copy to/from locally + * @lvec_cnt: number of elements in iovec array + * @lvec_current: index in iovec array we are up to + * @lvec_offset: offset in bytes from current iovec iov_base we are up to + * @process_pages: struct pages area that can store at least + * nr_pages_to_copy struct page pointers + * @mm: mm for task + * @task: task to read/write from + * @vm_write: 0 means copy from, 1 means copy to + * @bytes_copied: returns number of bytes successfully copied + * Returns 0 on success or on failure error code + */ +static int process_vm_rw_single_vec(unsigned long addr, + unsigned long len, + const struct iovec *lvec, + unsigned long lvec_cnt, + unsigned long *lvec_current, + size_t *lvec_offset, + struct page **process_pages, + struct mm_struct *mm, + struct task_struct *task, + int vm_write, + ssize_t *bytes_copied) +{ + unsigned long pa = addr & PAGE_MASK; + unsigned long start_offset = addr - pa; + unsigned long nr_pages; + ssize_t bytes_copied_loop; + ssize_t rc = 0; + unsigned long nr_pages_copied = 0; + unsigned long nr_pages_to_copy; + unsigned long max_pages_per_loop = PVM_MAX_KMALLOC_PAGES + / sizeof(struct pages *); + + *bytes_copied = 0; + + /* Work out address and page range required */ + if (len == 0) + return 0; + nr_pages = (addr + len - 1) / PAGE_SIZE - addr / PAGE_SIZE + 1; + + while ((nr_pages_copied < nr_pages) && (*lvec_current < lvec_cnt)) { + nr_pages_to_copy = min(nr_pages - nr_pages_copied, + max_pages_per_loop); + + rc = process_vm_rw_pages(task, mm, process_pages, pa, + start_offset, len, + lvec, lvec_cnt, + lvec_current, lvec_offset, + vm_write, nr_pages_to_copy, + &bytes_copied_loop); + start_offset = 0; + *bytes_copied += bytes_copied_loop; + + if (rc < 0) { + return rc; + } else { + len -= bytes_copied_loop; + nr_pages_copied += nr_pages_to_copy; + pa += nr_pages_to_copy * PAGE_SIZE; + } + } + + return rc; +} + +/* Maximum number of entries for process pages array + which lives on stack */ +#define PVM_MAX_PP_ARRAY_COUNT 16 + +/** + * process_vm_rw_core - core of reading/writing pages from task specified + * @pid: PID of process to read/write from/to + * @lvec: iovec array specifying where to copy to/from locally + * @liovcnt: size of lvec array + * @rvec: iovec array specifying where to copy to/from in the other process + * @riovcnt: size of rvec array + * @flags: currently unused + * @vm_write: 0 if reading from other process, 1 if writing to other process + * Returns the number of bytes read/written or error code. May + * return less bytes than expected if an error occurs during the copying + * process. + */ +static ssize_t process_vm_rw_core(pid_t pid, const struct iovec *lvec, + unsigned long liovcnt, + const struct iovec *rvec, + unsigned long riovcnt, + unsigned long flags, int vm_write) +{ + struct task_struct *task; + struct page *pp_stack[PVM_MAX_PP_ARRAY_COUNT]; + struct page **process_pages = pp_stack; + struct mm_struct *mm; + unsigned long i; + ssize_t rc = 0; + ssize_t bytes_copied_loop; + ssize_t bytes_copied = 0; + unsigned long nr_pages = 0; + unsigned long nr_pages_iov; + unsigned long iov_l_curr_idx = 0; + size_t iov_l_curr_offset = 0; + ssize_t iov_len; + + /* + * Work out how many pages of struct pages we're going to need + * when eventually calling get_user_pages + */ + for (i = 0; i < riovcnt; i++) { + iov_len = rvec[i].iov_len; + if (iov_len > 0) { + nr_pages_iov = ((unsigned long)rvec[i].iov_base + + iov_len) + / PAGE_SIZE - (unsigned long)rvec[i].iov_base + / PAGE_SIZE + 1; + nr_pages = max(nr_pages, nr_pages_iov); + } + } + + if (nr_pages == 0) + return 0; + + if (nr_pages > PVM_MAX_PP_ARRAY_COUNT) { + /* For reliability don't try to kmalloc more than + 2 pages worth */ + process_pages = kmalloc(min_t(size_t, PVM_MAX_KMALLOC_PAGES, + sizeof(struct pages *)*nr_pages), + GFP_KERNEL); + + if (!process_pages) + return -ENOMEM; + } + + /* Get process information */ + rcu_read_lock(); + task = find_task_by_vpid(pid); + if (task) + get_task_struct(task); + rcu_read_unlock(); + if (!task) { + rc = -ESRCH; + goto free_proc_pages; + } + + task_lock(task); + if (__ptrace_may_access(task, PTRACE_MODE_ATTACH)) { + task_unlock(task); + rc = -EPERM; + goto put_task_struct; + } + mm = task->mm; + + if (!mm || (task->flags & PF_KTHREAD)) { + task_unlock(task); + rc = -EINVAL; + goto put_task_struct; + } + + atomic_inc(&mm->mm_users); + task_unlock(task); + + for (i = 0; i < riovcnt && iov_l_curr_idx < liovcnt; i++) { + rc = process_vm_rw_single_vec( + (unsigned long)rvec[i].iov_base, rvec[i].iov_len, + lvec, liovcnt, &iov_l_curr_idx, &iov_l_curr_offset, + process_pages, mm, task, vm_write, &bytes_copied_loop); + bytes_copied += bytes_copied_loop; + if (rc != 0) { + /* If we have managed to copy any data at all then + we return the number of bytes copied. Otherwise + we return the error code */ + if (bytes_copied) + rc = bytes_copied; + goto put_mm; + } + } + + rc = bytes_copied; +put_mm: + mmput(mm); + +put_task_struct: + put_task_struct(task); + +free_proc_pages: + if (process_pages != pp_stack) + kfree(process_pages); + return rc; +} + +/** + * process_vm_rw - check iovecs before calling core routine + * @pid: PID of process to read/write from/to + * @lvec: iovec array specifying where to copy to/from locally + * @liovcnt: size of lvec array + * @rvec: iovec array specifying where to copy to/from in the other process + * @riovcnt: size of rvec array + * @flags: currently unused + * @vm_write: 0 if reading from other process, 1 if writing to other process + * Returns the number of bytes read/written or error code. May + * return less bytes than expected if an error occurs during the copying + * process. + */ +static ssize_t process_vm_rw(pid_t pid, + const struct iovec __user *lvec, + unsigned long liovcnt, + const struct iovec __user *rvec, + unsigned long riovcnt, + unsigned long flags, int vm_write) +{ + struct iovec iovstack_l[UIO_FASTIOV]; + struct iovec iovstack_r[UIO_FASTIOV]; + struct iovec *iov_l = iovstack_l; + struct iovec *iov_r = iovstack_r; + ssize_t rc; + + if (flags != 0) + return -EINVAL; + + /* Check iovecs */ + if (vm_write) + rc = rw_copy_check_uvector(WRITE, lvec, liovcnt, UIO_FASTIOV, + iovstack_l, &iov_l, 1); + else + rc = rw_copy_check_uvector(READ, lvec, liovcnt, UIO_FASTIOV, + iovstack_l, &iov_l, 1); + if (rc <= 0) + goto free_iovecs; + + rc = rw_copy_check_uvector(READ, rvec, riovcnt, UIO_FASTIOV, + iovstack_r, &iov_r, 0); + if (rc <= 0) + goto free_iovecs; + + rc = process_vm_rw_core(pid, iov_l, liovcnt, iov_r, riovcnt, flags, + vm_write); + +free_iovecs: + if (iov_r != iovstack_r) + kfree(iov_r); + if (iov_l != iovstack_l) + kfree(iov_l); + + return rc; +} + +SYSCALL_DEFINE6(process_vm_readv, pid_t, pid, const struct iovec __user *, lvec, + unsigned long, liovcnt, const struct iovec __user *, rvec, + unsigned long, riovcnt, unsigned long, flags) +{ + return process_vm_rw(pid, lvec, liovcnt, rvec, riovcnt, flags, 0); +} + +SYSCALL_DEFINE6(process_vm_writev, pid_t, pid, + const struct iovec __user *, lvec, + unsigned long, liovcnt, const struct iovec __user *, rvec, + unsigned long, riovcnt, unsigned long, flags) +{ + return process_vm_rw(pid, lvec, liovcnt, rvec, riovcnt, flags, 1); +} + +#ifdef CONFIG_COMPAT + +asmlinkage ssize_t +compat_process_vm_rw(compat_pid_t pid, + const struct compat_iovec __user *lvec, + unsigned long liovcnt, + const struct compat_iovec __user *rvec, + unsigned long riovcnt, + unsigned long flags, int vm_write) +{ + struct iovec iovstack_l[UIO_FASTIOV]; + struct iovec iovstack_r[UIO_FASTIOV]; + struct iovec *iov_l = iovstack_l; + struct iovec *iov_r = iovstack_r; + ssize_t rc = -EFAULT; + + if (flags != 0) + return -EINVAL; + + if (!access_ok(VERIFY_READ, lvec, liovcnt * sizeof(*lvec))) + goto out; + + if (!access_ok(VERIFY_READ, rvec, riovcnt * sizeof(*rvec))) + goto out; + + if (vm_write) + rc = compat_rw_copy_check_uvector(WRITE, lvec, liovcnt, + UIO_FASTIOV, iovstack_l, + &iov_l, 1); + else + rc = compat_rw_copy_check_uvector(READ, lvec, liovcnt, + UIO_FASTIOV, iovstack_l, + &iov_l, 1); + if (rc <= 0) + goto free_iovecs; + rc = compat_rw_copy_check_uvector(READ, rvec, riovcnt, + UIO_FASTIOV, iovstack_r, + &iov_r, 0); + if (rc <= 0) + goto free_iovecs; + + rc = process_vm_rw_core(pid, iov_l, liovcnt, iov_r, riovcnt, flags, + vm_write); + +free_iovecs: + if (iov_r != iovstack_r) + kfree(iov_r); + if (iov_l != iovstack_l) + kfree(iov_l); + +out: + return rc; +} + +asmlinkage ssize_t +compat_sys_process_vm_readv(compat_pid_t pid, + const struct compat_iovec __user *lvec, + unsigned long liovcnt, + const struct compat_iovec __user *rvec, + unsigned long riovcnt, + unsigned long flags) +{ + return compat_process_vm_rw(pid, lvec, liovcnt, rvec, + riovcnt, flags, 0); +} + +asmlinkage ssize_t +compat_sys_process_vm_writev(compat_pid_t pid, + const struct compat_iovec __user *lvec, + unsigned long liovcnt, + const struct compat_iovec __user *rvec, + unsigned long riovcnt, + unsigned long flags) +{ + return compat_process_vm_rw(pid, lvec, liovcnt, rvec, + riovcnt, flags, 1); +} + +#endif diff --git a/mm/quicklist.c b/mm/quicklist.c index 2876349..9422129 100644 --- a/mm/quicklist.c +++ b/mm/quicklist.c @@ -17,7 +17,6 @@ #include <linux/gfp.h> #include <linux/mm.h> #include <linux/mmzone.h> -#include <linux/module.h> #include <linux/quicklist.h> DEFINE_PER_CPU(struct quicklist [CONFIG_NR_QUICK], quicklist); diff --git a/mm/readahead.c b/mm/readahead.c index 867f9dd..cbcbb02 100644 --- a/mm/readahead.c +++ b/mm/readahead.c @@ -11,7 +11,7 @@ #include <linux/fs.h> #include <linux/gfp.h> #include <linux/mm.h> -#include <linux/module.h> +#include <linux/export.h> #include <linux/blkdev.h> #include <linux/backing-dev.h> #include <linux/task_io_accounting_ops.h> @@ -21,7 +21,6 @@ * Lock ordering in mm: * * inode->i_mutex (while writing or truncating, not reading or faulting) - * inode->i_alloc_sem (vmtruncate_range) * mm->mmap_sem * page->flags PG_locked (lock_page) * mapping->i_mmap_mutex @@ -32,11 +31,11 @@ * mmlist_lock (in mmput, drain_mmlist and others) * mapping->private_lock (in __set_page_dirty_buffers) * inode->i_lock (in set_page_dirty's __mark_inode_dirty) - * inode_wb_list_lock (in set_page_dirty's __mark_inode_dirty) + * bdi.wb->list_lock (in set_page_dirty's __mark_inode_dirty) * sb_lock (within inode_lock in fs/fs-writeback.c) * mapping->tree_lock (widely used, in set_page_dirty, * in arch-dependent flush_dcache_mmap_lock, - * within inode_wb_list_lock in __sync_single_inode) + * within bdi.wb->list_lock in __sync_single_inode) * * anon_vma->mutex,mapping->i_mutex (memory_failure, collect_procs_anon) * ->tasklist_lock @@ -52,7 +51,7 @@ #include <linux/ksm.h> #include <linux/rmap.h> #include <linux/rcupdate.h> -#include <linux/module.h> +#include <linux/export.h> #include <linux/memcontrol.h> #include <linux/mmu_notifier.h> #include <linux/migrate.h> @@ -870,11 +869,11 @@ int page_referenced(struct page *page, vm_flags); if (we_locked) unlock_page(page); + + if (page_test_and_clear_young(page_to_pfn(page))) + referenced++; } out: - if (page_test_and_clear_young(page_to_pfn(page))) - referenced++; - return referenced; } @@ -1165,7 +1164,7 @@ void page_remove_rmap(struct page *page) /* * Subfunctions of try_to_unmap: try_to_unmap_one called - * repeatedly from either try_to_unmap_anon or try_to_unmap_file. + * repeatedly from try_to_unmap_ksm, try_to_unmap_anon or try_to_unmap_file. */ int try_to_unmap_one(struct page *page, struct vm_area_struct *vma, unsigned long address, enum ttu_flags flags) @@ -6,7 +6,8 @@ * 2000-2001 Christoph Rohland * 2000-2001 SAP AG * 2002 Red Hat Inc. - * Copyright (C) 2002-2005 Hugh Dickins. + * Copyright (C) 2002-2011 Hugh Dickins. + * Copyright (C) 2011 Google Inc. * Copyright (C) 2002-2005 VERITAS Software Corporation. * Copyright (C) 2004 Andi Kleen, SuSE Labs * @@ -27,8 +28,7 @@ #include <linux/pagemap.h> #include <linux/file.h> #include <linux/mm.h> -#include <linux/module.h> -#include <linux/percpu_counter.h> +#include <linux/export.h> #include <linux/swap.h> static struct vfsmount *shm_mnt; @@ -51,6 +51,9 @@ static struct vfsmount *shm_mnt; #include <linux/shmem_fs.h> #include <linux/writeback.h> #include <linux/blkdev.h> +#include <linux/pagevec.h> +#include <linux/percpu_counter.h> +#include <linux/splice.h> #include <linux/security.h> #include <linux/swapops.h> #include <linux/mempolicy.h> @@ -62,43 +65,17 @@ static struct vfsmount *shm_mnt; #include <linux/magic.h> #include <asm/uaccess.h> -#include <asm/div64.h> #include <asm/pgtable.h> -/* - * The maximum size of a shmem/tmpfs file is limited by the maximum size of - * its triple-indirect swap vector - see illustration at shmem_swp_entry(). - * - * With 4kB page size, maximum file size is just over 2TB on a 32-bit kernel, - * but one eighth of that on a 64-bit kernel. With 8kB page size, maximum - * file size is just over 4TB on a 64-bit kernel, but 16TB on a 32-bit kernel, - * MAX_LFS_FILESIZE being then more restrictive than swap vector layout. - * - * We use / and * instead of shifts in the definitions below, so that the swap - * vector can be tested with small even values (e.g. 20) for ENTRIES_PER_PAGE. - */ -#define ENTRIES_PER_PAGE (PAGE_CACHE_SIZE/sizeof(unsigned long)) -#define ENTRIES_PER_PAGEPAGE ((unsigned long long)ENTRIES_PER_PAGE*ENTRIES_PER_PAGE) - -#define SHMSWP_MAX_INDEX (SHMEM_NR_DIRECT + (ENTRIES_PER_PAGEPAGE/2) * (ENTRIES_PER_PAGE+1)) -#define SHMSWP_MAX_BYTES (SHMSWP_MAX_INDEX << PAGE_CACHE_SHIFT) - -#define SHMEM_MAX_BYTES min_t(unsigned long long, SHMSWP_MAX_BYTES, MAX_LFS_FILESIZE) -#define SHMEM_MAX_INDEX ((unsigned long)((SHMEM_MAX_BYTES+1) >> PAGE_CACHE_SHIFT)) - #define BLOCKS_PER_PAGE (PAGE_CACHE_SIZE/512) #define VM_ACCT(size) (PAGE_CACHE_ALIGN(size) >> PAGE_SHIFT) -/* info->flags needs VM_flags to handle pagein/truncate races efficiently */ -#define SHMEM_PAGEIN VM_READ -#define SHMEM_TRUNCATE VM_WRITE - -/* Definition to limit shmem_truncate's steps between cond_rescheds */ -#define LATENCY_LIMIT 64 - /* Pretend that each entry is of this size in directory's i_size */ #define BOGO_DIRENT_SIZE 20 +/* Symlink up to this size is kmalloc'ed instead of using a swappable page */ +#define SHORT_SYMLINK_LEN 128 + struct shmem_xattr { struct list_head list; /* anchored by shmem_inode_info->xattr_list */ char *name; /* xattr name */ @@ -106,7 +83,7 @@ struct shmem_xattr { char value[0]; }; -/* Flag allocation requirements to shmem_getpage and shmem_swp_alloc */ +/* Flag allocation requirements to shmem_getpage */ enum sgp_type { SGP_READ, /* don't exceed i_size, don't allocate page */ SGP_CACHE, /* don't exceed i_size, may allocate page */ @@ -126,57 +103,14 @@ static unsigned long shmem_default_max_inodes(void) } #endif -static int shmem_getpage(struct inode *inode, unsigned long idx, - struct page **pagep, enum sgp_type sgp, int *type); - -static inline struct page *shmem_dir_alloc(gfp_t gfp_mask) -{ - /* - * The above definition of ENTRIES_PER_PAGE, and the use of - * BLOCKS_PER_PAGE on indirect pages, assume PAGE_CACHE_SIZE: - * might be reconsidered if it ever diverges from PAGE_SIZE. - * - * Mobility flags are masked out as swap vectors cannot move - */ - return alloc_pages((gfp_mask & ~GFP_MOVABLE_MASK) | __GFP_ZERO, - PAGE_CACHE_SHIFT-PAGE_SHIFT); -} - -static inline void shmem_dir_free(struct page *page) -{ - __free_pages(page, PAGE_CACHE_SHIFT-PAGE_SHIFT); -} - -static struct page **shmem_dir_map(struct page *page) -{ - return (struct page **)kmap_atomic(page, KM_USER0); -} - -static inline void shmem_dir_unmap(struct page **dir) -{ - kunmap_atomic(dir, KM_USER0); -} - -static swp_entry_t *shmem_swp_map(struct page *page) -{ - return (swp_entry_t *)kmap_atomic(page, KM_USER1); -} - -static inline void shmem_swp_balance_unmap(void) -{ - /* - * When passing a pointer to an i_direct entry, to code which - * also handles indirect entries and so will shmem_swp_unmap, - * we must arrange for the preempt count to remain in balance. - * What kmap_atomic of a lowmem page does depends on config - * and architecture, so pretend to kmap_atomic some lowmem page. - */ - (void) kmap_atomic(ZERO_PAGE(0), KM_USER1); -} +static int shmem_getpage_gfp(struct inode *inode, pgoff_t index, + struct page **pagep, enum sgp_type sgp, gfp_t gfp, int *fault_type); -static inline void shmem_swp_unmap(swp_entry_t *entry) +static inline int shmem_getpage(struct inode *inode, pgoff_t index, + struct page **pagep, enum sgp_type sgp, int *fault_type) { - kunmap_atomic(entry, KM_USER1); + return shmem_getpage_gfp(inode, index, pagep, sgp, + mapping_gfp_mask(inode->i_mapping), fault_type); } static inline struct shmem_sb_info *SHMEM_SB(struct super_block *sb) @@ -236,17 +170,6 @@ static struct backing_dev_info shmem_backing_dev_info __read_mostly = { static LIST_HEAD(shmem_swaplist); static DEFINE_MUTEX(shmem_swaplist_mutex); -static void shmem_free_blocks(struct inode *inode, long pages) -{ - struct shmem_sb_info *sbinfo = SHMEM_SB(inode->i_sb); - if (sbinfo->max_blocks) { - percpu_counter_add(&sbinfo->used_blocks, -pages); - spin_lock(&inode->i_lock); - inode->i_blocks -= pages*BLOCKS_PER_PAGE; - spin_unlock(&inode->i_lock); - } -} - static int shmem_reserve_inode(struct super_block *sb) { struct shmem_sb_info *sbinfo = SHMEM_SB(sb); @@ -273,7 +196,7 @@ static void shmem_free_inode(struct super_block *sb) } /** - * shmem_recalc_inode - recalculate the size of an inode + * shmem_recalc_inode - recalculate the block usage of an inode * @inode: inode to recalc * * We have to calculate the free blocks since the mm can drop @@ -291,474 +214,297 @@ static void shmem_recalc_inode(struct inode *inode) freed = info->alloced - info->swapped - inode->i_mapping->nrpages; if (freed > 0) { + struct shmem_sb_info *sbinfo = SHMEM_SB(inode->i_sb); + if (sbinfo->max_blocks) + percpu_counter_add(&sbinfo->used_blocks, -freed); info->alloced -= freed; + inode->i_blocks -= freed * BLOCKS_PER_PAGE; shmem_unacct_blocks(info->flags, freed); - shmem_free_blocks(inode, freed); } } -/** - * shmem_swp_entry - find the swap vector position in the info structure - * @info: info structure for the inode - * @index: index of the page to find - * @page: optional page to add to the structure. Has to be preset to - * all zeros - * - * If there is no space allocated yet it will return NULL when - * page is NULL, else it will use the page for the needed block, - * setting it to NULL on return to indicate that it has been used. - * - * The swap vector is organized the following way: - * - * There are SHMEM_NR_DIRECT entries directly stored in the - * shmem_inode_info structure. So small files do not need an addional - * allocation. - * - * For pages with index > SHMEM_NR_DIRECT there is the pointer - * i_indirect which points to a page which holds in the first half - * doubly indirect blocks, in the second half triple indirect blocks: - * - * For an artificial ENTRIES_PER_PAGE = 4 this would lead to the - * following layout (for SHMEM_NR_DIRECT == 16): - * - * i_indirect -> dir --> 16-19 - * | +-> 20-23 - * | - * +-->dir2 --> 24-27 - * | +-> 28-31 - * | +-> 32-35 - * | +-> 36-39 - * | - * +-->dir3 --> 40-43 - * +-> 44-47 - * +-> 48-51 - * +-> 52-55 +/* + * Replace item expected in radix tree by a new item, while holding tree lock. */ -static swp_entry_t *shmem_swp_entry(struct shmem_inode_info *info, unsigned long index, struct page **page) -{ - unsigned long offset; - struct page **dir; - struct page *subdir; +static int shmem_radix_tree_replace(struct address_space *mapping, + pgoff_t index, void *expected, void *replacement) +{ + void **pslot; + void *item = NULL; + + VM_BUG_ON(!expected); + pslot = radix_tree_lookup_slot(&mapping->page_tree, index); + if (pslot) + item = radix_tree_deref_slot_protected(pslot, + &mapping->tree_lock); + if (item != expected) + return -ENOENT; + if (replacement) + radix_tree_replace_slot(pslot, replacement); + else + radix_tree_delete(&mapping->page_tree, index); + return 0; +} - if (index < SHMEM_NR_DIRECT) { - shmem_swp_balance_unmap(); - return info->i_direct+index; - } - if (!info->i_indirect) { - if (page) { - info->i_indirect = *page; - *page = NULL; - } - return NULL; /* need another page */ - } +/* + * Like add_to_page_cache_locked, but error if expected item has gone. + */ +static int shmem_add_to_page_cache(struct page *page, + struct address_space *mapping, + pgoff_t index, gfp_t gfp, void *expected) +{ + int error = 0; - index -= SHMEM_NR_DIRECT; - offset = index % ENTRIES_PER_PAGE; - index /= ENTRIES_PER_PAGE; - dir = shmem_dir_map(info->i_indirect); - - if (index >= ENTRIES_PER_PAGE/2) { - index -= ENTRIES_PER_PAGE/2; - dir += ENTRIES_PER_PAGE/2 + index/ENTRIES_PER_PAGE; - index %= ENTRIES_PER_PAGE; - subdir = *dir; - if (!subdir) { - if (page) { - *dir = *page; - *page = NULL; - } - shmem_dir_unmap(dir); - return NULL; /* need another page */ - } - shmem_dir_unmap(dir); - dir = shmem_dir_map(subdir); - } + VM_BUG_ON(!PageLocked(page)); + VM_BUG_ON(!PageSwapBacked(page)); - dir += index; - subdir = *dir; - if (!subdir) { - if (!page || !(subdir = *page)) { - shmem_dir_unmap(dir); - return NULL; /* need a page */ + if (!expected) + error = radix_tree_preload(gfp & GFP_RECLAIM_MASK); + if (!error) { + page_cache_get(page); + page->mapping = mapping; + page->index = index; + + spin_lock_irq(&mapping->tree_lock); + if (!expected) + error = radix_tree_insert(&mapping->page_tree, + index, page); + else + error = shmem_radix_tree_replace(mapping, index, + expected, page); + if (!error) { + mapping->nrpages++; + __inc_zone_page_state(page, NR_FILE_PAGES); + __inc_zone_page_state(page, NR_SHMEM); + spin_unlock_irq(&mapping->tree_lock); + } else { + page->mapping = NULL; + spin_unlock_irq(&mapping->tree_lock); + page_cache_release(page); } - *dir = subdir; - *page = NULL; + if (!expected) + radix_tree_preload_end(); } - shmem_dir_unmap(dir); - return shmem_swp_map(subdir) + offset; + if (error) + mem_cgroup_uncharge_cache_page(page); + return error; } -static void shmem_swp_set(struct shmem_inode_info *info, swp_entry_t *entry, unsigned long value) +/* + * Like delete_from_page_cache, but substitutes swap for page. + */ +static void shmem_delete_from_page_cache(struct page *page, void *radswap) { - long incdec = value? 1: -1; + struct address_space *mapping = page->mapping; + int error; - entry->val = value; - info->swapped += incdec; - if ((unsigned long)(entry - info->i_direct) >= SHMEM_NR_DIRECT) { - struct page *page = kmap_atomic_to_page(entry); - set_page_private(page, page_private(page) + incdec); - } + spin_lock_irq(&mapping->tree_lock); + error = shmem_radix_tree_replace(mapping, page->index, page, radswap); + page->mapping = NULL; + mapping->nrpages--; + __dec_zone_page_state(page, NR_FILE_PAGES); + __dec_zone_page_state(page, NR_SHMEM); + spin_unlock_irq(&mapping->tree_lock); + page_cache_release(page); + BUG_ON(error); } -/** - * shmem_swp_alloc - get the position of the swap entry for the page. - * @info: info structure for the inode - * @index: index of the page to find - * @sgp: check and recheck i_size? skip allocation? - * - * If the entry does not exist, allocate it. +/* + * Like find_get_pages, but collecting swap entries as well as pages. */ -static swp_entry_t *shmem_swp_alloc(struct shmem_inode_info *info, unsigned long index, enum sgp_type sgp) -{ - struct inode *inode = &info->vfs_inode; - struct shmem_sb_info *sbinfo = SHMEM_SB(inode->i_sb); - struct page *page = NULL; - swp_entry_t *entry; - - if (sgp != SGP_WRITE && - ((loff_t) index << PAGE_CACHE_SHIFT) >= i_size_read(inode)) - return ERR_PTR(-EINVAL); - - while (!(entry = shmem_swp_entry(info, index, &page))) { - if (sgp == SGP_READ) - return shmem_swp_map(ZERO_PAGE(0)); - /* - * Test used_blocks against 1 less max_blocks, since we have 1 data - * page (and perhaps indirect index pages) yet to allocate: - * a waste to allocate index if we cannot allocate data. - */ - if (sbinfo->max_blocks) { - if (percpu_counter_compare(&sbinfo->used_blocks, - sbinfo->max_blocks - 1) >= 0) - return ERR_PTR(-ENOSPC); - percpu_counter_inc(&sbinfo->used_blocks); - spin_lock(&inode->i_lock); - inode->i_blocks += BLOCKS_PER_PAGE; - spin_unlock(&inode->i_lock); +static unsigned shmem_find_get_pages_and_swap(struct address_space *mapping, + pgoff_t start, unsigned int nr_pages, + struct page **pages, pgoff_t *indices) +{ + unsigned int i; + unsigned int ret; + unsigned int nr_found; + + rcu_read_lock(); +restart: + nr_found = radix_tree_gang_lookup_slot(&mapping->page_tree, + (void ***)pages, indices, start, nr_pages); + ret = 0; + for (i = 0; i < nr_found; i++) { + struct page *page; +repeat: + page = radix_tree_deref_slot((void **)pages[i]); + if (unlikely(!page)) + continue; + if (radix_tree_exception(page)) { + if (radix_tree_deref_retry(page)) + goto restart; + /* + * Otherwise, we must be storing a swap entry + * here as an exceptional entry: so return it + * without attempting to raise page count. + */ + goto export; } + if (!page_cache_get_speculative(page)) + goto repeat; - spin_unlock(&info->lock); - page = shmem_dir_alloc(mapping_gfp_mask(inode->i_mapping)); - spin_lock(&info->lock); - - if (!page) { - shmem_free_blocks(inode, 1); - return ERR_PTR(-ENOMEM); - } - if (sgp != SGP_WRITE && - ((loff_t) index << PAGE_CACHE_SHIFT) >= i_size_read(inode)) { - entry = ERR_PTR(-EINVAL); - break; + /* Has the page moved? */ + if (unlikely(page != *((void **)pages[i]))) { + page_cache_release(page); + goto repeat; } - if (info->next_index <= index) - info->next_index = index + 1; - } - if (page) { - /* another task gave its page, or truncated the file */ - shmem_free_blocks(inode, 1); - shmem_dir_free(page); - } - if (info->next_index <= index && !IS_ERR(entry)) - info->next_index = index + 1; - return entry; +export: + indices[ret] = indices[i]; + pages[ret] = page; + ret++; + } + if (unlikely(!ret && nr_found)) + goto restart; + rcu_read_unlock(); + return ret; } -/** - * shmem_free_swp - free some swap entries in a directory - * @dir: pointer to the directory - * @edir: pointer after last entry of the directory - * @punch_lock: pointer to spinlock when needed for the holepunch case +/* + * Remove swap entry from radix tree, free the swap and its page cache. */ -static int shmem_free_swp(swp_entry_t *dir, swp_entry_t *edir, - spinlock_t *punch_lock) -{ - spinlock_t *punch_unlock = NULL; - swp_entry_t *ptr; - int freed = 0; - - for (ptr = dir; ptr < edir; ptr++) { - if (ptr->val) { - if (unlikely(punch_lock)) { - punch_unlock = punch_lock; - punch_lock = NULL; - spin_lock(punch_unlock); - if (!ptr->val) - continue; - } - free_swap_and_cache(*ptr); - *ptr = (swp_entry_t){0}; - freed++; - } - } - if (punch_unlock) - spin_unlock(punch_unlock); - return freed; -} - -static int shmem_map_and_free_swp(struct page *subdir, int offset, - int limit, struct page ***dir, spinlock_t *punch_lock) -{ - swp_entry_t *ptr; - int freed = 0; - - ptr = shmem_swp_map(subdir); - for (; offset < limit; offset += LATENCY_LIMIT) { - int size = limit - offset; - if (size > LATENCY_LIMIT) - size = LATENCY_LIMIT; - freed += shmem_free_swp(ptr+offset, ptr+offset+size, - punch_lock); - if (need_resched()) { - shmem_swp_unmap(ptr); - if (*dir) { - shmem_dir_unmap(*dir); - *dir = NULL; - } - cond_resched(); - ptr = shmem_swp_map(subdir); - } - } - shmem_swp_unmap(ptr); - return freed; +static int shmem_free_swap(struct address_space *mapping, + pgoff_t index, void *radswap) +{ + int error; + + spin_lock_irq(&mapping->tree_lock); + error = shmem_radix_tree_replace(mapping, index, radswap, NULL); + spin_unlock_irq(&mapping->tree_lock); + if (!error) + free_swap_and_cache(radix_to_swp_entry(radswap)); + return error; } -static void shmem_free_pages(struct list_head *next) +/* + * Pagevec may contain swap entries, so shuffle up pages before releasing. + */ +static void shmem_pagevec_release(struct pagevec *pvec) { - struct page *page; - int freed = 0; - - do { - page = container_of(next, struct page, lru); - next = next->next; - shmem_dir_free(page); - freed++; - if (freed >= LATENCY_LIMIT) { - cond_resched(); - freed = 0; - } - } while (next); + int i, j; + + for (i = 0, j = 0; i < pagevec_count(pvec); i++) { + struct page *page = pvec->pages[i]; + if (!radix_tree_exceptional_entry(page)) + pvec->pages[j++] = page; + } + pvec->nr = j; + pagevec_release(pvec); } -void shmem_truncate_range(struct inode *inode, loff_t start, loff_t end) +/* + * Remove range of pages and swap entries from radix tree, and free them. + */ +void shmem_truncate_range(struct inode *inode, loff_t lstart, loff_t lend) { + struct address_space *mapping = inode->i_mapping; struct shmem_inode_info *info = SHMEM_I(inode); - unsigned long idx; - unsigned long size; - unsigned long limit; - unsigned long stage; - unsigned long diroff; - struct page **dir; - struct page *topdir; - struct page *middir; - struct page *subdir; - swp_entry_t *ptr; - LIST_HEAD(pages_to_free); - long nr_pages_to_free = 0; + pgoff_t start = (lstart + PAGE_CACHE_SIZE - 1) >> PAGE_CACHE_SHIFT; + unsigned partial = lstart & (PAGE_CACHE_SIZE - 1); + pgoff_t end = (lend >> PAGE_CACHE_SHIFT); + struct pagevec pvec; + pgoff_t indices[PAGEVEC_SIZE]; long nr_swaps_freed = 0; - int offset; - int freed; - int punch_hole; - spinlock_t *needs_lock; - spinlock_t *punch_lock; - unsigned long upper_limit; + pgoff_t index; + int i; - truncate_inode_pages_range(inode->i_mapping, start, end); + BUG_ON((lend & (PAGE_CACHE_SIZE - 1)) != (PAGE_CACHE_SIZE - 1)); - inode->i_ctime = inode->i_mtime = CURRENT_TIME; - idx = (start + PAGE_CACHE_SIZE - 1) >> PAGE_CACHE_SHIFT; - if (idx >= info->next_index) - return; + pagevec_init(&pvec, 0); + index = start; + while (index <= end) { + pvec.nr = shmem_find_get_pages_and_swap(mapping, index, + min(end - index, (pgoff_t)PAGEVEC_SIZE - 1) + 1, + pvec.pages, indices); + if (!pvec.nr) + break; + mem_cgroup_uncharge_start(); + for (i = 0; i < pagevec_count(&pvec); i++) { + struct page *page = pvec.pages[i]; - spin_lock(&info->lock); - info->flags |= SHMEM_TRUNCATE; - if (likely(end == (loff_t) -1)) { - limit = info->next_index; - upper_limit = SHMEM_MAX_INDEX; - info->next_index = idx; - needs_lock = NULL; - punch_hole = 0; - } else { - if (end + 1 >= inode->i_size) { /* we may free a little more */ - limit = (inode->i_size + PAGE_CACHE_SIZE - 1) >> - PAGE_CACHE_SHIFT; - upper_limit = SHMEM_MAX_INDEX; - } else { - limit = (end + 1) >> PAGE_CACHE_SHIFT; - upper_limit = limit; - } - needs_lock = &info->lock; - punch_hole = 1; - } + index = indices[i]; + if (index > end) + break; - topdir = info->i_indirect; - if (topdir && idx <= SHMEM_NR_DIRECT && !punch_hole) { - info->i_indirect = NULL; - nr_pages_to_free++; - list_add(&topdir->lru, &pages_to_free); + if (radix_tree_exceptional_entry(page)) { + nr_swaps_freed += !shmem_free_swap(mapping, + index, page); + continue; + } + + if (!trylock_page(page)) + continue; + if (page->mapping == mapping) { + VM_BUG_ON(PageWriteback(page)); + truncate_inode_page(mapping, page); + } + unlock_page(page); + } + shmem_pagevec_release(&pvec); + mem_cgroup_uncharge_end(); + cond_resched(); + index++; } - spin_unlock(&info->lock); - if (info->swapped && idx < SHMEM_NR_DIRECT) { - ptr = info->i_direct; - size = limit; - if (size > SHMEM_NR_DIRECT) - size = SHMEM_NR_DIRECT; - nr_swaps_freed = shmem_free_swp(ptr+idx, ptr+size, needs_lock); + if (partial) { + struct page *page = NULL; + shmem_getpage(inode, start - 1, &page, SGP_READ, NULL); + if (page) { + zero_user_segment(page, partial, PAGE_CACHE_SIZE); + set_page_dirty(page); + unlock_page(page); + page_cache_release(page); + } } - /* - * If there are no indirect blocks or we are punching a hole - * below indirect blocks, nothing to be done. - */ - if (!topdir || limit <= SHMEM_NR_DIRECT) - goto done2; + index = start; + for ( ; ; ) { + cond_resched(); + pvec.nr = shmem_find_get_pages_and_swap(mapping, index, + min(end - index, (pgoff_t)PAGEVEC_SIZE - 1) + 1, + pvec.pages, indices); + if (!pvec.nr) { + if (index == start) + break; + index = start; + continue; + } + if (index == start && indices[0] > end) { + shmem_pagevec_release(&pvec); + break; + } + mem_cgroup_uncharge_start(); + for (i = 0; i < pagevec_count(&pvec); i++) { + struct page *page = pvec.pages[i]; - /* - * The truncation case has already dropped info->lock, and we're safe - * because i_size and next_index have already been lowered, preventing - * access beyond. But in the punch_hole case, we still need to take - * the lock when updating the swap directory, because there might be - * racing accesses by shmem_getpage(SGP_CACHE), shmem_unuse_inode or - * shmem_writepage. However, whenever we find we can remove a whole - * directory page (not at the misaligned start or end of the range), - * we first NULLify its pointer in the level above, and then have no - * need to take the lock when updating its contents: needs_lock and - * punch_lock (either pointing to info->lock or NULL) manage this. - */ + index = indices[i]; + if (index > end) + break; - upper_limit -= SHMEM_NR_DIRECT; - limit -= SHMEM_NR_DIRECT; - idx = (idx > SHMEM_NR_DIRECT)? (idx - SHMEM_NR_DIRECT): 0; - offset = idx % ENTRIES_PER_PAGE; - idx -= offset; - - dir = shmem_dir_map(topdir); - stage = ENTRIES_PER_PAGEPAGE/2; - if (idx < ENTRIES_PER_PAGEPAGE/2) { - middir = topdir; - diroff = idx/ENTRIES_PER_PAGE; - } else { - dir += ENTRIES_PER_PAGE/2; - dir += (idx - ENTRIES_PER_PAGEPAGE/2)/ENTRIES_PER_PAGEPAGE; - while (stage <= idx) - stage += ENTRIES_PER_PAGEPAGE; - middir = *dir; - if (*dir) { - diroff = ((idx - ENTRIES_PER_PAGEPAGE/2) % - ENTRIES_PER_PAGEPAGE) / ENTRIES_PER_PAGE; - if (!diroff && !offset && upper_limit >= stage) { - if (needs_lock) { - spin_lock(needs_lock); - *dir = NULL; - spin_unlock(needs_lock); - needs_lock = NULL; - } else - *dir = NULL; - nr_pages_to_free++; - list_add(&middir->lru, &pages_to_free); + if (radix_tree_exceptional_entry(page)) { + nr_swaps_freed += !shmem_free_swap(mapping, + index, page); + continue; } - shmem_dir_unmap(dir); - dir = shmem_dir_map(middir); - } else { - diroff = 0; - offset = 0; - idx = stage; - } - } - for (; idx < limit; idx += ENTRIES_PER_PAGE, diroff++) { - if (unlikely(idx == stage)) { - shmem_dir_unmap(dir); - dir = shmem_dir_map(topdir) + - ENTRIES_PER_PAGE/2 + idx/ENTRIES_PER_PAGEPAGE; - while (!*dir) { - dir++; - idx += ENTRIES_PER_PAGEPAGE; - if (idx >= limit) - goto done1; + lock_page(page); + if (page->mapping == mapping) { + VM_BUG_ON(PageWriteback(page)); + truncate_inode_page(mapping, page); } - stage = idx + ENTRIES_PER_PAGEPAGE; - middir = *dir; - if (punch_hole) - needs_lock = &info->lock; - if (upper_limit >= stage) { - if (needs_lock) { - spin_lock(needs_lock); - *dir = NULL; - spin_unlock(needs_lock); - needs_lock = NULL; - } else - *dir = NULL; - nr_pages_to_free++; - list_add(&middir->lru, &pages_to_free); - } - shmem_dir_unmap(dir); - cond_resched(); - dir = shmem_dir_map(middir); - diroff = 0; - } - punch_lock = needs_lock; - subdir = dir[diroff]; - if (subdir && !offset && upper_limit-idx >= ENTRIES_PER_PAGE) { - if (needs_lock) { - spin_lock(needs_lock); - dir[diroff] = NULL; - spin_unlock(needs_lock); - punch_lock = NULL; - } else - dir[diroff] = NULL; - nr_pages_to_free++; - list_add(&subdir->lru, &pages_to_free); - } - if (subdir && page_private(subdir) /* has swap entries */) { - size = limit - idx; - if (size > ENTRIES_PER_PAGE) - size = ENTRIES_PER_PAGE; - freed = shmem_map_and_free_swp(subdir, - offset, size, &dir, punch_lock); - if (!dir) - dir = shmem_dir_map(middir); - nr_swaps_freed += freed; - if (offset || punch_lock) { - spin_lock(&info->lock); - set_page_private(subdir, - page_private(subdir) - freed); - spin_unlock(&info->lock); - } else - BUG_ON(page_private(subdir) != freed); + unlock_page(page); } - offset = 0; - } -done1: - shmem_dir_unmap(dir); -done2: - if (inode->i_mapping->nrpages && (info->flags & SHMEM_PAGEIN)) { - /* - * Call truncate_inode_pages again: racing shmem_unuse_inode - * may have swizzled a page in from swap since - * truncate_pagecache or generic_delete_inode did it, before we - * lowered next_index. Also, though shmem_getpage checks - * i_size before adding to cache, no recheck after: so fix the - * narrow window there too. - */ - truncate_inode_pages_range(inode->i_mapping, start, end); + shmem_pagevec_release(&pvec); + mem_cgroup_uncharge_end(); + index++; } spin_lock(&info->lock); - info->flags &= ~SHMEM_TRUNCATE; info->swapped -= nr_swaps_freed; - if (nr_pages_to_free) - shmem_free_blocks(inode, nr_pages_to_free); shmem_recalc_inode(inode); spin_unlock(&info->lock); - /* - * Empty swap vector directory pages to be freed? - */ - if (!list_empty(&pages_to_free)) { - pages_to_free.prev->next = NULL; - shmem_free_pages(pages_to_free.next); - } + inode->i_ctime = inode->i_mtime = CURRENT_TIME; } EXPORT_SYMBOL_GPL(shmem_truncate_range); @@ -774,37 +520,7 @@ static int shmem_setattr(struct dentry *dentry, struct iattr *attr) if (S_ISREG(inode->i_mode) && (attr->ia_valid & ATTR_SIZE)) { loff_t oldsize = inode->i_size; loff_t newsize = attr->ia_size; - struct page *page = NULL; - if (newsize < oldsize) { - /* - * If truncating down to a partial page, then - * if that page is already allocated, hold it - * in memory until the truncation is over, so - * truncate_partial_page cannot miss it were - * it assigned to swap. - */ - if (newsize & (PAGE_CACHE_SIZE-1)) { - (void) shmem_getpage(inode, - newsize >> PAGE_CACHE_SHIFT, - &page, SGP_READ, NULL); - if (page) - unlock_page(page); - } - /* - * Reset SHMEM_PAGEIN flag so that shmem_truncate can - * detect if any pages might have been added to cache - * after truncate_inode_pages. But we needn't bother - * if it's being fully truncated to zero-length: the - * nrpages check is efficient enough in that case. - */ - if (newsize) { - struct shmem_inode_info *info = SHMEM_I(inode); - spin_lock(&info->lock); - info->flags &= ~SHMEM_PAGEIN; - spin_unlock(&info->lock); - } - } if (newsize != oldsize) { i_size_write(inode, newsize); inode->i_ctime = inode->i_mtime = CURRENT_TIME; @@ -816,8 +532,6 @@ static int shmem_setattr(struct dentry *dentry, struct iattr *attr) /* unmap again to remove racily COWed private pages */ unmap_mapping_range(inode->i_mapping, holebegin, 0, 1); } - if (page) - page_cache_release(page); } setattr_copy(inode, attr); @@ -842,7 +556,8 @@ static void shmem_evict_inode(struct inode *inode) list_del_init(&info->swaplist); mutex_unlock(&shmem_swaplist_mutex); } - } + } else + kfree(info->symlink); list_for_each_entry_safe(xattr, nxattr, &info->xattr_list, list) { kfree(xattr->name); @@ -853,106 +568,27 @@ static void shmem_evict_inode(struct inode *inode) end_writeback(inode); } -static inline int shmem_find_swp(swp_entry_t entry, swp_entry_t *dir, swp_entry_t *edir) -{ - swp_entry_t *ptr; - - for (ptr = dir; ptr < edir; ptr++) { - if (ptr->val == entry.val) - return ptr - dir; - } - return -1; -} - -static int shmem_unuse_inode(struct shmem_inode_info *info, swp_entry_t entry, struct page *page) +/* + * If swap found in inode, free it and move page from swapcache to filecache. + */ +static int shmem_unuse_inode(struct shmem_inode_info *info, + swp_entry_t swap, struct page *page) { - struct address_space *mapping; - unsigned long idx; - unsigned long size; - unsigned long limit; - unsigned long stage; - struct page **dir; - struct page *subdir; - swp_entry_t *ptr; - int offset; + struct address_space *mapping = info->vfs_inode.i_mapping; + void *radswap; + pgoff_t index; int error; - idx = 0; - ptr = info->i_direct; - spin_lock(&info->lock); - if (!info->swapped) { - list_del_init(&info->swaplist); - goto lost2; - } - limit = info->next_index; - size = limit; - if (size > SHMEM_NR_DIRECT) - size = SHMEM_NR_DIRECT; - offset = shmem_find_swp(entry, ptr, ptr+size); - if (offset >= 0) { - shmem_swp_balance_unmap(); - goto found; - } - if (!info->i_indirect) - goto lost2; - - dir = shmem_dir_map(info->i_indirect); - stage = SHMEM_NR_DIRECT + ENTRIES_PER_PAGEPAGE/2; - - for (idx = SHMEM_NR_DIRECT; idx < limit; idx += ENTRIES_PER_PAGE, dir++) { - if (unlikely(idx == stage)) { - shmem_dir_unmap(dir-1); - if (cond_resched_lock(&info->lock)) { - /* check it has not been truncated */ - if (limit > info->next_index) { - limit = info->next_index; - if (idx >= limit) - goto lost2; - } - } - dir = shmem_dir_map(info->i_indirect) + - ENTRIES_PER_PAGE/2 + idx/ENTRIES_PER_PAGEPAGE; - while (!*dir) { - dir++; - idx += ENTRIES_PER_PAGEPAGE; - if (idx >= limit) - goto lost1; - } - stage = idx + ENTRIES_PER_PAGEPAGE; - subdir = *dir; - shmem_dir_unmap(dir); - dir = shmem_dir_map(subdir); - } - subdir = *dir; - if (subdir && page_private(subdir)) { - ptr = shmem_swp_map(subdir); - size = limit - idx; - if (size > ENTRIES_PER_PAGE) - size = ENTRIES_PER_PAGE; - offset = shmem_find_swp(entry, ptr, ptr+size); - shmem_swp_unmap(ptr); - if (offset >= 0) { - shmem_dir_unmap(dir); - ptr = shmem_swp_map(subdir); - goto found; - } - } - } -lost1: - shmem_dir_unmap(dir-1); -lost2: - spin_unlock(&info->lock); - return 0; -found: - idx += offset; - ptr += offset; + radswap = swp_to_radix_entry(swap); + index = radix_tree_locate_item(&mapping->page_tree, radswap); + if (index == -1) + return 0; /* * Move _head_ to start search for next from here. * But be careful: shmem_evict_inode checks list_empty without taking * mutex, and there's an instant in list_move_tail when info->swaplist - * would appear empty, if it were the only one on shmem_swaplist. We - * could avoid doing it if inode NULL; or use this minor optimization. + * would appear empty, if it were the only one on shmem_swaplist. */ if (shmem_swaplist.next != &info->swaplist) list_move_tail(&shmem_swaplist, &info->swaplist); @@ -962,42 +598,34 @@ found: * but also to hold up shmem_evict_inode(): so inode cannot be freed * beneath us (pagelock doesn't help until the page is in pagecache). */ - mapping = info->vfs_inode.i_mapping; - error = add_to_page_cache_locked(page, mapping, idx, GFP_NOWAIT); + error = shmem_add_to_page_cache(page, mapping, index, + GFP_NOWAIT, radswap); /* which does mem_cgroup_uncharge_cache_page on error */ - if (error == -EEXIST) { - struct page *filepage = find_get_page(mapping, idx); - error = 1; - if (filepage) { - /* - * There might be a more uptodate page coming down - * from a stacked writepage: forget our swappage if so. - */ - if (PageUptodate(filepage)) - error = 0; - page_cache_release(filepage); - } - } - if (!error) { + if (error != -ENOMEM) { + /* + * Truncation and eviction use free_swap_and_cache(), which + * only does trylock page: if we raced, best clean up here. + */ delete_from_swap_cache(page); set_page_dirty(page); - info->flags |= SHMEM_PAGEIN; - shmem_swp_set(info, ptr, 0); - swap_free(entry); + if (!error) { + spin_lock(&info->lock); + info->swapped--; + spin_unlock(&info->lock); + swap_free(swap); + } error = 1; /* not an error, but entry was found */ } - shmem_swp_unmap(ptr); - spin_unlock(&info->lock); return error; } /* - * shmem_unuse() search for an eventually swapped out shmem page. + * Search through swapped inodes to find and replace swap by page. */ -int shmem_unuse(swp_entry_t entry, struct page *page) +int shmem_unuse(swp_entry_t swap, struct page *page) { - struct list_head *p, *next; + struct list_head *this, *next; struct shmem_inode_info *info; int found = 0; int error; @@ -1006,32 +634,25 @@ int shmem_unuse(swp_entry_t entry, struct page *page) * Charge page using GFP_KERNEL while we can wait, before taking * the shmem_swaplist_mutex which might hold up shmem_writepage(). * Charged back to the user (not to caller) when swap account is used. - * add_to_page_cache() will be called with GFP_NOWAIT. */ error = mem_cgroup_cache_charge(page, current->mm, GFP_KERNEL); if (error) goto out; - /* - * Try to preload while we can wait, to not make a habit of - * draining atomic reserves; but don't latch on to this cpu, - * it's okay if sometimes we get rescheduled after this. - */ - error = radix_tree_preload(GFP_KERNEL); - if (error) - goto uncharge; - radix_tree_preload_end(); + /* No radix_tree_preload: swap entry keeps a place for page in tree */ mutex_lock(&shmem_swaplist_mutex); - list_for_each_safe(p, next, &shmem_swaplist) { - info = list_entry(p, struct shmem_inode_info, swaplist); - found = shmem_unuse_inode(info, entry, page); + list_for_each_safe(this, next, &shmem_swaplist) { + info = list_entry(this, struct shmem_inode_info, swaplist); + if (info->swapped) + found = shmem_unuse_inode(info, swap, page); + else + list_del_init(&info->swaplist); cond_resched(); if (found) break; } mutex_unlock(&shmem_swaplist_mutex); -uncharge: if (!found) mem_cgroup_uncharge_cache_page(page); if (found < 0) @@ -1048,10 +669,10 @@ out: static int shmem_writepage(struct page *page, struct writeback_control *wbc) { struct shmem_inode_info *info; - swp_entry_t *entry, swap; struct address_space *mapping; - unsigned long index; struct inode *inode; + swp_entry_t swap; + pgoff_t index; BUG_ON(!PageLocked(page)); mapping = page->mapping; @@ -1066,69 +687,46 @@ static int shmem_writepage(struct page *page, struct writeback_control *wbc) /* * shmem_backing_dev_info's capabilities prevent regular writeback or * sync from ever calling shmem_writepage; but a stacking filesystem - * may use the ->writepage of its underlying filesystem, in which case + * might use ->writepage of its underlying filesystem, in which case * tmpfs should write out to swap only in response to memory pressure, - * and not for the writeback threads or sync. However, in those cases, - * we do still want to check if there's a redundant swappage to be - * discarded. + * and not for the writeback threads or sync. */ - if (wbc->for_reclaim) - swap = get_swap_page(); - else - swap.val = 0; + if (!wbc->for_reclaim) { + WARN_ON_ONCE(1); /* Still happens? Tell us about it! */ + goto redirty; + } + swap = get_swap_page(); + if (!swap.val) + goto redirty; /* * Add inode to shmem_unuse()'s list of swapped-out inodes, - * if it's not already there. Do it now because we cannot take - * mutex while holding spinlock, and must do so before the page - * is moved to swap cache, when its pagelock no longer protects + * if it's not already there. Do it now before the page is + * moved to swap cache, when its pagelock no longer protects * the inode from eviction. But don't unlock the mutex until - * we've taken the spinlock, because shmem_unuse_inode() will - * prune a !swapped inode from the swaplist under both locks. + * we've incremented swapped, because shmem_unuse_inode() will + * prune a !swapped inode from the swaplist under this mutex. */ - if (swap.val) { - mutex_lock(&shmem_swaplist_mutex); - if (list_empty(&info->swaplist)) - list_add_tail(&info->swaplist, &shmem_swaplist); - } - - spin_lock(&info->lock); - if (swap.val) - mutex_unlock(&shmem_swaplist_mutex); - - if (index >= info->next_index) { - BUG_ON(!(info->flags & SHMEM_TRUNCATE)); - goto unlock; - } - entry = shmem_swp_entry(info, index, NULL); - if (entry->val) { - /* - * The more uptodate page coming down from a stacked - * writepage should replace our old swappage. - */ - free_swap_and_cache(*entry); - shmem_swp_set(info, entry, 0); - } - shmem_recalc_inode(inode); + mutex_lock(&shmem_swaplist_mutex); + if (list_empty(&info->swaplist)) + list_add_tail(&info->swaplist, &shmem_swaplist); - if (swap.val && add_to_swap_cache(page, swap, GFP_ATOMIC) == 0) { - delete_from_page_cache(page); - shmem_swp_set(info, entry, swap.val); - shmem_swp_unmap(entry); + if (add_to_swap_cache(page, swap, GFP_ATOMIC) == 0) { swap_shmem_alloc(swap); + shmem_delete_from_page_cache(page, swp_to_radix_entry(swap)); + + spin_lock(&info->lock); + info->swapped++; + shmem_recalc_inode(inode); spin_unlock(&info->lock); + + mutex_unlock(&shmem_swaplist_mutex); BUG_ON(page_mapped(page)); swap_writepage(page, wbc); return 0; } - shmem_swp_unmap(entry); -unlock: - spin_unlock(&info->lock); - /* - * add_to_swap_cache() doesn't return -EEXIST, so we can safely - * clear SWAP_HAS_CACHE flag. - */ + mutex_unlock(&shmem_swaplist_mutex); swapcache_free(swap, NULL); redirty: set_page_dirty(page); @@ -1165,35 +763,33 @@ static struct mempolicy *shmem_get_sbmpol(struct shmem_sb_info *sbinfo) } #endif /* CONFIG_TMPFS */ -static struct page *shmem_swapin(swp_entry_t entry, gfp_t gfp, - struct shmem_inode_info *info, unsigned long idx) +static struct page *shmem_swapin(swp_entry_t swap, gfp_t gfp, + struct shmem_inode_info *info, pgoff_t index) { struct mempolicy mpol, *spol; struct vm_area_struct pvma; - struct page *page; spol = mpol_cond_copy(&mpol, - mpol_shared_policy_lookup(&info->policy, idx)); + mpol_shared_policy_lookup(&info->policy, index)); /* Create a pseudo vma that just contains the policy */ pvma.vm_start = 0; - pvma.vm_pgoff = idx; + pvma.vm_pgoff = index; pvma.vm_ops = NULL; pvma.vm_policy = spol; - page = swapin_readahead(entry, gfp, &pvma, 0); - return page; + return swapin_readahead(swap, gfp, &pvma, 0); } static struct page *shmem_alloc_page(gfp_t gfp, - struct shmem_inode_info *info, unsigned long idx) + struct shmem_inode_info *info, pgoff_t index) { struct vm_area_struct pvma; /* Create a pseudo vma that just contains the policy */ pvma.vm_start = 0; - pvma.vm_pgoff = idx; + pvma.vm_pgoff = index; pvma.vm_ops = NULL; - pvma.vm_policy = mpol_shared_policy_lookup(&info->policy, idx); + pvma.vm_policy = mpol_shared_policy_lookup(&info->policy, index); /* * alloc_page_vma() will drop the shared policy reference @@ -1202,19 +798,19 @@ static struct page *shmem_alloc_page(gfp_t gfp, } #else /* !CONFIG_NUMA */ #ifdef CONFIG_TMPFS -static inline void shmem_show_mpol(struct seq_file *seq, struct mempolicy *p) +static inline void shmem_show_mpol(struct seq_file *seq, struct mempolicy *mpol) { } #endif /* CONFIG_TMPFS */ -static inline struct page *shmem_swapin(swp_entry_t entry, gfp_t gfp, - struct shmem_inode_info *info, unsigned long idx) +static inline struct page *shmem_swapin(swp_entry_t swap, gfp_t gfp, + struct shmem_inode_info *info, pgoff_t index) { - return swapin_readahead(entry, gfp, NULL, 0); + return swapin_readahead(swap, gfp, NULL, 0); } static inline struct page *shmem_alloc_page(gfp_t gfp, - struct shmem_inode_info *info, unsigned long idx) + struct shmem_inode_info *info, pgoff_t index) { return alloc_page(gfp); } @@ -1228,311 +824,195 @@ static inline struct mempolicy *shmem_get_sbmpol(struct shmem_sb_info *sbinfo) #endif /* - * shmem_getpage - either get the page from swap or allocate a new one + * shmem_getpage_gfp - find page in cache, or get from swap, or allocate * * If we allocate a new one we do not mark it dirty. That's up to the * vm. If we swap it in we mark it dirty since we also free the swap * entry since a page cannot live in both the swap and page cache */ -static int shmem_getpage(struct inode *inode, unsigned long idx, - struct page **pagep, enum sgp_type sgp, int *type) +static int shmem_getpage_gfp(struct inode *inode, pgoff_t index, + struct page **pagep, enum sgp_type sgp, gfp_t gfp, int *fault_type) { struct address_space *mapping = inode->i_mapping; - struct shmem_inode_info *info = SHMEM_I(inode); + struct shmem_inode_info *info; struct shmem_sb_info *sbinfo; - struct page *filepage = *pagep; - struct page *swappage; - struct page *prealloc_page = NULL; - swp_entry_t *entry; + struct page *page; swp_entry_t swap; - gfp_t gfp; int error; + int once = 0; - if (idx >= SHMEM_MAX_INDEX) + if (index > (MAX_LFS_FILESIZE >> PAGE_CACHE_SHIFT)) return -EFBIG; +repeat: + swap.val = 0; + page = find_lock_page(mapping, index); + if (radix_tree_exceptional_entry(page)) { + swap = radix_to_swp_entry(page); + page = NULL; + } - if (type) - *type = 0; + if (sgp != SGP_WRITE && + ((loff_t)index << PAGE_CACHE_SHIFT) >= i_size_read(inode)) { + error = -EINVAL; + goto failed; + } - /* - * Normally, filepage is NULL on entry, and either found - * uptodate immediately, or allocated and zeroed, or read - * in under swappage, which is then assigned to filepage. - * But shmem_readpage (required for splice) passes in a locked - * filepage, which may be found not uptodate by other callers - * too, and may need to be copied from the swappage read in. - */ -repeat: - if (!filepage) - filepage = find_lock_page(mapping, idx); - if (filepage && PageUptodate(filepage)) - goto done; - gfp = mapping_gfp_mask(mapping); - if (!filepage) { + if (page || (sgp == SGP_READ && !swap.val)) { /* - * Try to preload while we can wait, to not make a habit of - * draining atomic reserves; but don't latch on to this cpu. + * Once we can get the page lock, it must be uptodate: + * if there were an error in reading back from swap, + * the page would not be inserted into the filecache. */ - error = radix_tree_preload(gfp & ~__GFP_HIGHMEM); - if (error) - goto failed; - radix_tree_preload_end(); - if (sgp != SGP_READ && !prealloc_page) { - /* We don't care if this fails */ - prealloc_page = shmem_alloc_page(gfp, info, idx); - if (prealloc_page) { - if (mem_cgroup_cache_charge(prealloc_page, - current->mm, GFP_KERNEL)) { - page_cache_release(prealloc_page); - prealloc_page = NULL; - } - } - } + BUG_ON(page && !PageUptodate(page)); + *pagep = page; + return 0; } - error = 0; - spin_lock(&info->lock); - shmem_recalc_inode(inode); - entry = shmem_swp_alloc(info, idx, sgp); - if (IS_ERR(entry)) { - spin_unlock(&info->lock); - error = PTR_ERR(entry); - goto failed; - } - swap = *entry; + /* + * Fast cache lookup did not find it: + * bring it back from swap or allocate. + */ + info = SHMEM_I(inode); + sbinfo = SHMEM_SB(inode->i_sb); if (swap.val) { /* Look it up and read it in.. */ - swappage = lookup_swap_cache(swap); - if (!swappage) { - shmem_swp_unmap(entry); - spin_unlock(&info->lock); + page = lookup_swap_cache(swap); + if (!page) { /* here we actually do the io */ - if (type) - *type |= VM_FAULT_MAJOR; - swappage = shmem_swapin(swap, gfp, info, idx); - if (!swappage) { - spin_lock(&info->lock); - entry = shmem_swp_alloc(info, idx, sgp); - if (IS_ERR(entry)) - error = PTR_ERR(entry); - else { - if (entry->val == swap.val) - error = -ENOMEM; - shmem_swp_unmap(entry); - } - spin_unlock(&info->lock); - if (error) - goto failed; - goto repeat; + if (fault_type) + *fault_type |= VM_FAULT_MAJOR; + page = shmem_swapin(swap, gfp, info, index); + if (!page) { + error = -ENOMEM; + goto failed; } - wait_on_page_locked(swappage); - page_cache_release(swappage); - goto repeat; } /* We have to do this with page locked to prevent races */ - if (!trylock_page(swappage)) { - shmem_swp_unmap(entry); - spin_unlock(&info->lock); - wait_on_page_locked(swappage); - page_cache_release(swappage); - goto repeat; - } - if (PageWriteback(swappage)) { - shmem_swp_unmap(entry); - spin_unlock(&info->lock); - wait_on_page_writeback(swappage); - unlock_page(swappage); - page_cache_release(swappage); - goto repeat; - } - if (!PageUptodate(swappage)) { - shmem_swp_unmap(entry); - spin_unlock(&info->lock); - unlock_page(swappage); - page_cache_release(swappage); + lock_page(page); + if (!PageUptodate(page)) { error = -EIO; goto failed; } - - if (filepage) { - shmem_swp_set(info, entry, 0); - shmem_swp_unmap(entry); - delete_from_swap_cache(swappage); - spin_unlock(&info->lock); - copy_highpage(filepage, swappage); - unlock_page(swappage); - page_cache_release(swappage); - flush_dcache_page(filepage); - SetPageUptodate(filepage); - set_page_dirty(filepage); - swap_free(swap); - } else if (!(error = add_to_page_cache_locked(swappage, mapping, - idx, GFP_NOWAIT))) { - info->flags |= SHMEM_PAGEIN; - shmem_swp_set(info, entry, 0); - shmem_swp_unmap(entry); - delete_from_swap_cache(swappage); - spin_unlock(&info->lock); - filepage = swappage; - set_page_dirty(filepage); - swap_free(swap); - } else { - shmem_swp_unmap(entry); - spin_unlock(&info->lock); - if (error == -ENOMEM) { - /* - * reclaim from proper memory cgroup and - * call memcg's OOM if needed. - */ - error = mem_cgroup_shmem_charge_fallback( - swappage, - current->mm, - gfp); - if (error) { - unlock_page(swappage); - page_cache_release(swappage); - goto failed; - } - } - unlock_page(swappage); - page_cache_release(swappage); - goto repeat; - } - } else if (sgp == SGP_READ && !filepage) { - shmem_swp_unmap(entry); - filepage = find_get_page(mapping, idx); - if (filepage && - (!PageUptodate(filepage) || !trylock_page(filepage))) { - spin_unlock(&info->lock); - wait_on_page_locked(filepage); - page_cache_release(filepage); - filepage = NULL; - goto repeat; + wait_on_page_writeback(page); + + /* Someone may have already done it for us */ + if (page->mapping) { + if (page->mapping == mapping && + page->index == index) + goto done; + error = -EEXIST; + goto failed; } + + error = mem_cgroup_cache_charge(page, current->mm, + gfp & GFP_RECLAIM_MASK); + if (!error) + error = shmem_add_to_page_cache(page, mapping, index, + gfp, swp_to_radix_entry(swap)); + if (error) + goto failed; + + spin_lock(&info->lock); + info->swapped--; + shmem_recalc_inode(inode); spin_unlock(&info->lock); + + delete_from_swap_cache(page); + set_page_dirty(page); + swap_free(swap); + } else { - shmem_swp_unmap(entry); - sbinfo = SHMEM_SB(inode->i_sb); + if (shmem_acct_block(info->flags)) { + error = -ENOSPC; + goto failed; + } if (sbinfo->max_blocks) { if (percpu_counter_compare(&sbinfo->used_blocks, - sbinfo->max_blocks) >= 0 || - shmem_acct_block(info->flags)) - goto nospace; - percpu_counter_inc(&sbinfo->used_blocks); - spin_lock(&inode->i_lock); - inode->i_blocks += BLOCKS_PER_PAGE; - spin_unlock(&inode->i_lock); - } else if (shmem_acct_block(info->flags)) - goto nospace; - - if (!filepage) { - int ret; - - if (!prealloc_page) { - spin_unlock(&info->lock); - filepage = shmem_alloc_page(gfp, info, idx); - if (!filepage) { - shmem_unacct_blocks(info->flags, 1); - shmem_free_blocks(inode, 1); - error = -ENOMEM; - goto failed; - } - SetPageSwapBacked(filepage); - - /* - * Precharge page while we can wait, compensate - * after - */ - error = mem_cgroup_cache_charge(filepage, - current->mm, GFP_KERNEL); - if (error) { - page_cache_release(filepage); - shmem_unacct_blocks(info->flags, 1); - shmem_free_blocks(inode, 1); - filepage = NULL; - goto failed; - } - - spin_lock(&info->lock); - } else { - filepage = prealloc_page; - prealloc_page = NULL; - SetPageSwapBacked(filepage); + sbinfo->max_blocks) >= 0) { + error = -ENOSPC; + goto unacct; } + percpu_counter_inc(&sbinfo->used_blocks); + } - entry = shmem_swp_alloc(info, idx, sgp); - if (IS_ERR(entry)) - error = PTR_ERR(entry); - else { - swap = *entry; - shmem_swp_unmap(entry); - } - ret = error || swap.val; - if (ret) - mem_cgroup_uncharge_cache_page(filepage); - else - ret = add_to_page_cache_lru(filepage, mapping, - idx, GFP_NOWAIT); - /* - * At add_to_page_cache_lru() failure, uncharge will - * be done automatically. - */ - if (ret) { - spin_unlock(&info->lock); - page_cache_release(filepage); - shmem_unacct_blocks(info->flags, 1); - shmem_free_blocks(inode, 1); - filepage = NULL; - if (error) - goto failed; - goto repeat; - } - info->flags |= SHMEM_PAGEIN; + page = shmem_alloc_page(gfp, info, index); + if (!page) { + error = -ENOMEM; + goto decused; } + SetPageSwapBacked(page); + __set_page_locked(page); + error = mem_cgroup_cache_charge(page, current->mm, + gfp & GFP_RECLAIM_MASK); + if (!error) + error = shmem_add_to_page_cache(page, mapping, index, + gfp, NULL); + if (error) + goto decused; + lru_cache_add_anon(page); + + spin_lock(&info->lock); info->alloced++; + inode->i_blocks += BLOCKS_PER_PAGE; + shmem_recalc_inode(inode); spin_unlock(&info->lock); - clear_highpage(filepage); - flush_dcache_page(filepage); - SetPageUptodate(filepage); + + clear_highpage(page); + flush_dcache_page(page); + SetPageUptodate(page); if (sgp == SGP_DIRTY) - set_page_dirty(filepage); + set_page_dirty(page); } done: - *pagep = filepage; - error = 0; - goto out; + /* Perhaps the file has been truncated since we checked */ + if (sgp != SGP_WRITE && + ((loff_t)index << PAGE_CACHE_SHIFT) >= i_size_read(inode)) { + error = -EINVAL; + goto trunc; + } + *pagep = page; + return 0; -nospace: /* - * Perhaps the page was brought in from swap between find_lock_page - * and taking info->lock? We allow for that at add_to_page_cache_lru, - * but must also avoid reporting a spurious ENOSPC while working on a - * full tmpfs. (When filepage has been passed in to shmem_getpage, it - * is already in page cache, which prevents this race from occurring.) + * Error recovery. */ - if (!filepage) { - struct page *page = find_get_page(mapping, idx); - if (page) { - spin_unlock(&info->lock); - page_cache_release(page); - goto repeat; - } - } +trunc: + ClearPageDirty(page); + delete_from_page_cache(page); + spin_lock(&info->lock); + info->alloced--; + inode->i_blocks -= BLOCKS_PER_PAGE; spin_unlock(&info->lock); - error = -ENOSPC; +decused: + if (sbinfo->max_blocks) + percpu_counter_add(&sbinfo->used_blocks, -1); +unacct: + shmem_unacct_blocks(info->flags, 1); failed: - if (*pagep != filepage) { - unlock_page(filepage); - page_cache_release(filepage); + if (swap.val && error != -EINVAL) { + struct page *test = find_get_page(mapping, index); + if (test && !radix_tree_exceptional_entry(test)) + page_cache_release(test); + /* Have another try if the entry has changed */ + if (test != swp_to_radix_entry(swap)) + error = -EEXIST; } -out: - if (prealloc_page) { - mem_cgroup_uncharge_cache_page(prealloc_page); - page_cache_release(prealloc_page); + if (page) { + unlock_page(page); + page_cache_release(page); } + if (error == -ENOSPC && !once++) { + info = SHMEM_I(inode); + spin_lock(&info->lock); + shmem_recalc_inode(inode); + spin_unlock(&info->lock); + goto repeat; + } + if (error == -EEXIST) + goto repeat; return error; } @@ -1540,36 +1020,34 @@ static int shmem_fault(struct vm_area_struct *vma, struct vm_fault *vmf) { struct inode *inode = vma->vm_file->f_path.dentry->d_inode; int error; - int ret; - - if (((loff_t)vmf->pgoff << PAGE_CACHE_SHIFT) >= i_size_read(inode)) - return VM_FAULT_SIGBUS; + int ret = VM_FAULT_LOCKED; error = shmem_getpage(inode, vmf->pgoff, &vmf->page, SGP_CACHE, &ret); if (error) return ((error == -ENOMEM) ? VM_FAULT_OOM : VM_FAULT_SIGBUS); + if (ret & VM_FAULT_MAJOR) { count_vm_event(PGMAJFAULT); mem_cgroup_count_vm_event(vma->vm_mm, PGMAJFAULT); } - return ret | VM_FAULT_LOCKED; + return ret; } #ifdef CONFIG_NUMA -static int shmem_set_policy(struct vm_area_struct *vma, struct mempolicy *new) +static int shmem_set_policy(struct vm_area_struct *vma, struct mempolicy *mpol) { - struct inode *i = vma->vm_file->f_path.dentry->d_inode; - return mpol_set_shared_policy(&SHMEM_I(i)->policy, vma, new); + struct inode *inode = vma->vm_file->f_path.dentry->d_inode; + return mpol_set_shared_policy(&SHMEM_I(inode)->policy, vma, mpol); } static struct mempolicy *shmem_get_policy(struct vm_area_struct *vma, unsigned long addr) { - struct inode *i = vma->vm_file->f_path.dentry->d_inode; - unsigned long idx; + struct inode *inode = vma->vm_file->f_path.dentry->d_inode; + pgoff_t index; - idx = ((addr - vma->vm_start) >> PAGE_SHIFT) + vma->vm_pgoff; - return mpol_shared_policy_lookup(&SHMEM_I(i)->policy, idx); + index = ((addr - vma->vm_start) >> PAGE_SHIFT) + vma->vm_pgoff; + return mpol_shared_policy_lookup(&SHMEM_I(inode)->policy, index); } #endif @@ -1590,6 +1068,12 @@ int shmem_lock(struct file *file, int lock, struct user_struct *user) user_shm_unlock(inode->i_size, user); info->flags &= ~VM_LOCKED; mapping_clear_unevictable(file->f_mapping); + /* + * Ensure that a racing putback_lru_page() can see + * the pages of this mapping are evictable when we + * skip them due to !PageLRU during the scan. + */ + smp_mb__after_clear_bit(); scan_mapping_unevictable_pages(file->f_mapping); } retval = 0; @@ -1667,20 +1151,7 @@ static struct inode *shmem_get_inode(struct super_block *sb, const struct inode #ifdef CONFIG_TMPFS static const struct inode_operations shmem_symlink_inode_operations; -static const struct inode_operations shmem_symlink_inline_operations; - -/* - * Normally tmpfs avoids the use of shmem_readpage and shmem_write_begin; - * but providing them allows a tmpfs file to be used for splice, sendfile, and - * below the loop driver, in the generic fashion that many filesystems support. - */ -static int shmem_readpage(struct file *file, struct page *page) -{ - struct inode *inode = page->mapping->host; - int error = shmem_getpage(inode, page->index, &page, SGP_CACHE, NULL); - unlock_page(page); - return error; -} +static const struct inode_operations shmem_short_symlink_operations; static int shmem_write_begin(struct file *file, struct address_space *mapping, @@ -1689,7 +1160,6 @@ shmem_write_begin(struct file *file, struct address_space *mapping, { struct inode *inode = mapping->host; pgoff_t index = pos >> PAGE_CACHE_SHIFT; - *pagep = NULL; return shmem_getpage(inode, index, pagep, SGP_WRITE, NULL); } @@ -1714,7 +1184,8 @@ static void do_shmem_file_read(struct file *filp, loff_t *ppos, read_descriptor_ { struct inode *inode = filp->f_path.dentry->d_inode; struct address_space *mapping = inode->i_mapping; - unsigned long index, offset; + pgoff_t index; + unsigned long offset; enum sgp_type sgp = SGP_READ; /* @@ -1730,7 +1201,8 @@ static void do_shmem_file_read(struct file *filp, loff_t *ppos, read_descriptor_ for (;;) { struct page *page = NULL; - unsigned long end_index, nr, ret; + pgoff_t end_index; + unsigned long nr, ret; loff_t i_size = i_size_read(inode); end_index = i_size >> PAGE_CACHE_SHIFT; @@ -1846,6 +1318,119 @@ static ssize_t shmem_file_aio_read(struct kiocb *iocb, return retval; } +static ssize_t shmem_file_splice_read(struct file *in, loff_t *ppos, + struct pipe_inode_info *pipe, size_t len, + unsigned int flags) +{ + struct address_space *mapping = in->f_mapping; + struct inode *inode = mapping->host; + unsigned int loff, nr_pages, req_pages; + struct page *pages[PIPE_DEF_BUFFERS]; + struct partial_page partial[PIPE_DEF_BUFFERS]; + struct page *page; + pgoff_t index, end_index; + loff_t isize, left; + int error, page_nr; + struct splice_pipe_desc spd = { + .pages = pages, + .partial = partial, + .flags = flags, + .ops = &page_cache_pipe_buf_ops, + .spd_release = spd_release_page, + }; + + isize = i_size_read(inode); + if (unlikely(*ppos >= isize)) + return 0; + + left = isize - *ppos; + if (unlikely(left < len)) + len = left; + + if (splice_grow_spd(pipe, &spd)) + return -ENOMEM; + + index = *ppos >> PAGE_CACHE_SHIFT; + loff = *ppos & ~PAGE_CACHE_MASK; + req_pages = (len + loff + PAGE_CACHE_SIZE - 1) >> PAGE_CACHE_SHIFT; + nr_pages = min(req_pages, pipe->buffers); + + spd.nr_pages = find_get_pages_contig(mapping, index, + nr_pages, spd.pages); + index += spd.nr_pages; + error = 0; + + while (spd.nr_pages < nr_pages) { + error = shmem_getpage(inode, index, &page, SGP_CACHE, NULL); + if (error) + break; + unlock_page(page); + spd.pages[spd.nr_pages++] = page; + index++; + } + + index = *ppos >> PAGE_CACHE_SHIFT; + nr_pages = spd.nr_pages; + spd.nr_pages = 0; + + for (page_nr = 0; page_nr < nr_pages; page_nr++) { + unsigned int this_len; + + if (!len) + break; + + this_len = min_t(unsigned long, len, PAGE_CACHE_SIZE - loff); + page = spd.pages[page_nr]; + + if (!PageUptodate(page) || page->mapping != mapping) { + error = shmem_getpage(inode, index, &page, + SGP_CACHE, NULL); + if (error) + break; + unlock_page(page); + page_cache_release(spd.pages[page_nr]); + spd.pages[page_nr] = page; + } + + isize = i_size_read(inode); + end_index = (isize - 1) >> PAGE_CACHE_SHIFT; + if (unlikely(!isize || index > end_index)) + break; + + if (end_index == index) { + unsigned int plen; + + plen = ((isize - 1) & ~PAGE_CACHE_MASK) + 1; + if (plen <= loff) + break; + + this_len = min(this_len, plen - loff); + len = this_len; + } + + spd.partial[page_nr].offset = loff; + spd.partial[page_nr].len = this_len; + len -= this_len; + loff = 0; + spd.nr_pages++; + index++; + } + + while (page_nr < nr_pages) + page_cache_release(spd.pages[page_nr++]); + + if (spd.nr_pages) + error = splice_to_pipe(pipe, &spd); + + splice_shrink_spd(pipe, &spd); + + if (error > 0) { + *ppos += error; + file_accessed(in); + } + return error; +} + static int shmem_statfs(struct dentry *dentry, struct kstatfs *buf) { struct shmem_sb_info *sbinfo = SHMEM_SB(dentry->d_sb); @@ -1855,8 +1440,9 @@ static int shmem_statfs(struct dentry *dentry, struct kstatfs *buf) buf->f_namelen = NAME_MAX; if (sbinfo->max_blocks) { buf->f_blocks = sbinfo->max_blocks; - buf->f_bavail = buf->f_bfree = - sbinfo->max_blocks - percpu_counter_sum(&sbinfo->used_blocks); + buf->f_bavail = + buf->f_bfree = sbinfo->max_blocks - + percpu_counter_sum(&sbinfo->used_blocks); } if (sbinfo->max_inodes) { buf->f_files = sbinfo->max_inodes; @@ -1878,7 +1464,7 @@ shmem_mknod(struct inode *dir, struct dentry *dentry, int mode, dev_t dev) inode = shmem_get_inode(dir->i_sb, dir, mode, dev, VM_NORESERVE); if (inode) { error = security_inode_init_security(inode, dir, - &dentry->d_name, NULL, + &dentry->d_name, NULL, NULL); if (error) { if (error != -EOPNOTSUPP) { @@ -2006,7 +1592,7 @@ static int shmem_symlink(struct inode *dir, struct dentry *dentry, const char *s int error; int len; struct inode *inode; - struct page *page = NULL; + struct page *page; char *kaddr; struct shmem_inode_info *info; @@ -2018,7 +1604,7 @@ static int shmem_symlink(struct inode *dir, struct dentry *dentry, const char *s if (!inode) return -ENOSPC; - error = security_inode_init_security(inode, dir, &dentry->d_name, NULL, + error = security_inode_init_security(inode, dir, &dentry->d_name, NULL, NULL); if (error) { if (error != -EOPNOTSUPP) { @@ -2030,10 +1616,13 @@ static int shmem_symlink(struct inode *dir, struct dentry *dentry, const char *s info = SHMEM_I(inode); inode->i_size = len-1; - if (len <= SHMEM_SYMLINK_INLINE_LEN) { - /* do it inline */ - memcpy(info->inline_symlink, symname, len); - inode->i_op = &shmem_symlink_inline_operations; + if (len <= SHORT_SYMLINK_LEN) { + info->symlink = kmemdup(symname, len, GFP_KERNEL); + if (!info->symlink) { + iput(inode); + return -ENOMEM; + } + inode->i_op = &shmem_short_symlink_operations; } else { error = shmem_getpage(inode, 0, &page, SGP_WRITE, NULL); if (error) { @@ -2056,17 +1645,17 @@ static int shmem_symlink(struct inode *dir, struct dentry *dentry, const char *s return 0; } -static void *shmem_follow_link_inline(struct dentry *dentry, struct nameidata *nd) +static void *shmem_follow_short_symlink(struct dentry *dentry, struct nameidata *nd) { - nd_set_link(nd, SHMEM_I(dentry->d_inode)->inline_symlink); + nd_set_link(nd, SHMEM_I(dentry->d_inode)->symlink); return NULL; } static void *shmem_follow_link(struct dentry *dentry, struct nameidata *nd) { struct page *page = NULL; - int res = shmem_getpage(dentry->d_inode, 0, &page, SGP_READ, NULL); - nd_set_link(nd, res ? ERR_PTR(res) : kmap(page)); + int error = shmem_getpage(dentry->d_inode, 0, &page, SGP_READ, NULL); + nd_set_link(nd, error ? ERR_PTR(error) : kmap(page)); if (page) unlock_page(page); return page; @@ -2177,7 +1766,6 @@ out: return err; } - static const struct xattr_handler *shmem_xattr_handlers[] = { #ifdef CONFIG_TMPFS_POSIX_ACL &generic_acl_access_handler, @@ -2307,9 +1895,9 @@ static ssize_t shmem_listxattr(struct dentry *dentry, char *buffer, size_t size) } #endif /* CONFIG_TMPFS_XATTR */ -static const struct inode_operations shmem_symlink_inline_operations = { +static const struct inode_operations shmem_short_symlink_operations = { .readlink = generic_readlink, - .follow_link = shmem_follow_link_inline, + .follow_link = shmem_follow_short_symlink, #ifdef CONFIG_TMPFS_XATTR .setxattr = shmem_setxattr, .getxattr = shmem_getxattr, @@ -2509,8 +2097,7 @@ static int shmem_remount_fs(struct super_block *sb, int *flags, char *data) if (config.max_inodes < inodes) goto out; /* - * Those tests also disallow limited->unlimited while any are in - * use, so i_blocks will always be zero when max_blocks is zero; + * Those tests disallow limited->unlimited while any are in use; * but we must separately disallow unlimited->limited, because * in that case we have no record of how much is already in use. */ @@ -2602,7 +2189,7 @@ int shmem_fill_super(struct super_block *sb, void *data, int silent) goto failed; sbinfo->free_inodes = sbinfo->max_inodes; - sb->s_maxbytes = SHMEM_MAX_BYTES; + sb->s_maxbytes = MAX_LFS_FILESIZE; sb->s_blocksize = PAGE_CACHE_SIZE; sb->s_blocksize_bits = PAGE_CACHE_SHIFT; sb->s_magic = TMPFS_MAGIC; @@ -2637,14 +2224,14 @@ static struct kmem_cache *shmem_inode_cachep; static struct inode *shmem_alloc_inode(struct super_block *sb) { - struct shmem_inode_info *p; - p = (struct shmem_inode_info *)kmem_cache_alloc(shmem_inode_cachep, GFP_KERNEL); - if (!p) + struct shmem_inode_info *info; + info = kmem_cache_alloc(shmem_inode_cachep, GFP_KERNEL); + if (!info) return NULL; - return &p->vfs_inode; + return &info->vfs_inode; } -static void shmem_i_callback(struct rcu_head *head) +static void shmem_destroy_callback(struct rcu_head *head) { struct inode *inode = container_of(head, struct inode, i_rcu); INIT_LIST_HEAD(&inode->i_dentry); @@ -2653,29 +2240,26 @@ static void shmem_i_callback(struct rcu_head *head) static void shmem_destroy_inode(struct inode *inode) { - if ((inode->i_mode & S_IFMT) == S_IFREG) { - /* only struct inode is valid if it's an inline symlink */ + if ((inode->i_mode & S_IFMT) == S_IFREG) mpol_free_shared_policy(&SHMEM_I(inode)->policy); - } - call_rcu(&inode->i_rcu, shmem_i_callback); + call_rcu(&inode->i_rcu, shmem_destroy_callback); } -static void init_once(void *foo) +static void shmem_init_inode(void *foo) { - struct shmem_inode_info *p = (struct shmem_inode_info *) foo; - - inode_init_once(&p->vfs_inode); + struct shmem_inode_info *info = foo; + inode_init_once(&info->vfs_inode); } -static int init_inodecache(void) +static int shmem_init_inodecache(void) { shmem_inode_cachep = kmem_cache_create("shmem_inode_cache", sizeof(struct shmem_inode_info), - 0, SLAB_PANIC, init_once); + 0, SLAB_PANIC, shmem_init_inode); return 0; } -static void destroy_inodecache(void) +static void shmem_destroy_inodecache(void) { kmem_cache_destroy(shmem_inode_cachep); } @@ -2684,7 +2268,6 @@ static const struct address_space_operations shmem_aops = { .writepage = shmem_writepage, .set_page_dirty = __set_page_dirty_no_writeback, #ifdef CONFIG_TMPFS - .readpage = shmem_readpage, .write_begin = shmem_write_begin, .write_end = shmem_write_end, #endif @@ -2701,7 +2284,7 @@ static const struct file_operations shmem_file_operations = { .aio_read = shmem_file_aio_read, .aio_write = generic_file_aio_write, .fsync = noop_fsync, - .splice_read = generic_file_splice_read, + .splice_read = shmem_file_splice_read, .splice_write = generic_file_splice_write, #endif }; @@ -2715,10 +2298,6 @@ static const struct inode_operations shmem_inode_operations = { .listxattr = shmem_listxattr, .removexattr = shmem_removexattr, #endif -#ifdef CONFIG_TMPFS_POSIX_ACL - .check_acl = generic_check_acl, -#endif - }; static const struct inode_operations shmem_dir_inode_operations = { @@ -2741,7 +2320,6 @@ static const struct inode_operations shmem_dir_inode_operations = { #endif #ifdef CONFIG_TMPFS_POSIX_ACL .setattr = shmem_setattr, - .check_acl = generic_check_acl, #endif }; @@ -2754,7 +2332,6 @@ static const struct inode_operations shmem_special_inode_operations = { #endif #ifdef CONFIG_TMPFS_POSIX_ACL .setattr = shmem_setattr, - .check_acl = generic_check_acl, #endif }; @@ -2779,21 +2356,20 @@ static const struct vm_operations_struct shmem_vm_ops = { #endif }; - static struct dentry *shmem_mount(struct file_system_type *fs_type, int flags, const char *dev_name, void *data) { return mount_nodev(fs_type, flags, data, shmem_fill_super); } -static struct file_system_type tmpfs_fs_type = { +static struct file_system_type shmem_fs_type = { .owner = THIS_MODULE, .name = "tmpfs", .mount = shmem_mount, .kill_sb = kill_litter_super, }; -int __init init_tmpfs(void) +int __init shmem_init(void) { int error; @@ -2801,18 +2377,18 @@ int __init init_tmpfs(void) if (error) goto out4; - error = init_inodecache(); + error = shmem_init_inodecache(); if (error) goto out3; - error = register_filesystem(&tmpfs_fs_type); + error = register_filesystem(&shmem_fs_type); if (error) { printk(KERN_ERR "Could not register tmpfs\n"); goto out2; } - shm_mnt = vfs_kern_mount(&tmpfs_fs_type, MS_NOUSER, - tmpfs_fs_type.name, NULL); + shm_mnt = vfs_kern_mount(&shmem_fs_type, MS_NOUSER, + shmem_fs_type.name, NULL); if (IS_ERR(shm_mnt)) { error = PTR_ERR(shm_mnt); printk(KERN_ERR "Could not kern_mount tmpfs\n"); @@ -2821,9 +2397,9 @@ int __init init_tmpfs(void) return 0; out1: - unregister_filesystem(&tmpfs_fs_type); + unregister_filesystem(&shmem_fs_type); out2: - destroy_inodecache(); + shmem_destroy_inodecache(); out3: bdi_destroy(&shmem_backing_dev_info); out4: @@ -2831,45 +2407,6 @@ out4: return error; } -#ifdef CONFIG_CGROUP_MEM_RES_CTLR -/** - * mem_cgroup_get_shmem_target - find a page or entry assigned to the shmem file - * @inode: the inode to be searched - * @pgoff: the offset to be searched - * @pagep: the pointer for the found page to be stored - * @ent: the pointer for the found swap entry to be stored - * - * If a page is found, refcount of it is incremented. Callers should handle - * these refcount. - */ -void mem_cgroup_get_shmem_target(struct inode *inode, pgoff_t pgoff, - struct page **pagep, swp_entry_t *ent) -{ - swp_entry_t entry = { .val = 0 }, *ptr; - struct page *page = NULL; - struct shmem_inode_info *info = SHMEM_I(inode); - - if ((pgoff << PAGE_CACHE_SHIFT) >= i_size_read(inode)) - goto out; - - spin_lock(&info->lock); - ptr = shmem_swp_entry(info, pgoff, NULL); -#ifdef CONFIG_SWAP - if (ptr && ptr->val) { - entry.val = ptr->val; - page = find_get_page(&swapper_space, entry.val); - } else -#endif - page = find_get_page(inode->i_mapping, pgoff); - if (ptr) - shmem_swp_unmap(ptr); - spin_unlock(&info->lock); -out: - *pagep = page; - *ent = entry; -} -#endif - #else /* !CONFIG_SHMEM */ /* @@ -2883,23 +2420,23 @@ out: #include <linux/ramfs.h> -static struct file_system_type tmpfs_fs_type = { +static struct file_system_type shmem_fs_type = { .name = "tmpfs", .mount = ramfs_mount, .kill_sb = kill_litter_super, }; -int __init init_tmpfs(void) +int __init shmem_init(void) { - BUG_ON(register_filesystem(&tmpfs_fs_type) != 0); + BUG_ON(register_filesystem(&shmem_fs_type) != 0); - shm_mnt = kern_mount(&tmpfs_fs_type); + shm_mnt = kern_mount(&shmem_fs_type); BUG_ON(IS_ERR(shm_mnt)); return 0; } -int shmem_unuse(swp_entry_t entry, struct page *page) +int shmem_unuse(swp_entry_t swap, struct page *page) { return 0; } @@ -2909,43 +2446,17 @@ int shmem_lock(struct file *file, int lock, struct user_struct *user) return 0; } -void shmem_truncate_range(struct inode *inode, loff_t start, loff_t end) +void shmem_truncate_range(struct inode *inode, loff_t lstart, loff_t lend) { - truncate_inode_pages_range(inode->i_mapping, start, end); + truncate_inode_pages_range(inode->i_mapping, lstart, lend); } EXPORT_SYMBOL_GPL(shmem_truncate_range); -#ifdef CONFIG_CGROUP_MEM_RES_CTLR -/** - * mem_cgroup_get_shmem_target - find a page or entry assigned to the shmem file - * @inode: the inode to be searched - * @pgoff: the offset to be searched - * @pagep: the pointer for the found page to be stored - * @ent: the pointer for the found swap entry to be stored - * - * If a page is found, refcount of it is incremented. Callers should handle - * these refcount. - */ -void mem_cgroup_get_shmem_target(struct inode *inode, pgoff_t pgoff, - struct page **pagep, swp_entry_t *ent) -{ - struct page *page = NULL; - - if ((pgoff << PAGE_CACHE_SHIFT) >= i_size_read(inode)) - goto out; - page = find_get_page(inode->i_mapping, pgoff); -out: - *pagep = page; - *ent = (swp_entry_t){ .val = 0 }; -} -#endif - #define shmem_vm_ops generic_file_vm_ops #define shmem_file_operations ramfs_file_operations #define shmem_get_inode(sb, dir, mode, dev, flags) ramfs_get_inode(sb, dir, mode, dev) #define shmem_acct_size(flags, size) 0 #define shmem_unacct_size(flags, size) do {} while (0) -#define SHMEM_MAX_BYTES MAX_LFS_FILESIZE #endif /* CONFIG_SHMEM */ @@ -2969,7 +2480,7 @@ struct file *shmem_file_setup(const char *name, loff_t size, unsigned long flags if (IS_ERR(shm_mnt)) return (void *)shm_mnt; - if (size < 0 || size > SHMEM_MAX_BYTES) + if (size < 0 || size > MAX_LFS_FILESIZE) return ERR_PTR(-EINVAL); if (shmem_acct_size(flags, size)) @@ -2992,7 +2503,7 @@ struct file *shmem_file_setup(const char *name, loff_t size, unsigned long flags d_instantiate(path.dentry, inode); inode->i_size = size; - inode->i_nlink = 0; /* It is unlinked */ + clear_nlink(inode); /* It is unlinked */ #ifndef CONFIG_MMU error = ramfs_nommu_expand_for_mapping(inode, size); if (error) @@ -3048,13 +2559,29 @@ int shmem_zero_setup(struct vm_area_struct *vma) * suit tmpfs, since it may have pages in swapcache, and needs to find those * for itself; although drivers/gpu/drm i915 and ttm rely upon this support. * - * Provide a stub for those callers to start using now, then later - * flesh it out to call shmem_getpage() with additional gfp mask, when - * shmem_file_splice_read() is added and shmem_readpage() is removed. + * i915_gem_object_get_pages_gtt() mixes __GFP_NORETRY | __GFP_NOWARN in + * with the mapping_gfp_mask(), to avoid OOMing the machine unnecessarily. */ struct page *shmem_read_mapping_page_gfp(struct address_space *mapping, pgoff_t index, gfp_t gfp) { +#ifdef CONFIG_SHMEM + struct inode *inode = mapping->host; + struct page *page; + int error; + + BUG_ON(mapping->a_ops != &shmem_aops); + error = shmem_getpage_gfp(inode, index, &page, SGP_CACHE, gfp, NULL); + if (error) + page = ERR_PTR(error); + else + unlock_page(page); + return page; +#else + /* + * The tiny !SHMEM case uses ramfs without swap + */ return read_cache_page_gfp(mapping, index, gfp); +#endif } EXPORT_SYMBOL_GPL(shmem_read_mapping_page_gfp); @@ -574,7 +574,9 @@ static struct arraycache_init initarray_generic = { {0, BOOT_CPUCACHE_ENTRIES, 1, 0} }; /* internal cache of cache description objs */ +static struct kmem_list3 *cache_cache_nodelists[MAX_NUMNODES]; static struct kmem_cache cache_cache = { + .nodelists = cache_cache_nodelists, .batchcount = 1, .limit = BOOT_CPUCACHE_ENTRIES, .shared = 1, @@ -620,6 +622,51 @@ int slab_is_available(void) static struct lock_class_key on_slab_l3_key; static struct lock_class_key on_slab_alc_key; +static struct lock_class_key debugobj_l3_key; +static struct lock_class_key debugobj_alc_key; + +static void slab_set_lock_classes(struct kmem_cache *cachep, + struct lock_class_key *l3_key, struct lock_class_key *alc_key, + int q) +{ + struct array_cache **alc; + struct kmem_list3 *l3; + int r; + + l3 = cachep->nodelists[q]; + if (!l3) + return; + + lockdep_set_class(&l3->list_lock, l3_key); + alc = l3->alien; + /* + * FIXME: This check for BAD_ALIEN_MAGIC + * should go away when common slab code is taught to + * work even without alien caches. + * Currently, non NUMA code returns BAD_ALIEN_MAGIC + * for alloc_alien_cache, + */ + if (!alc || (unsigned long)alc == BAD_ALIEN_MAGIC) + return; + for_each_node(r) { + if (alc[r]) + lockdep_set_class(&alc[r]->lock, alc_key); + } +} + +static void slab_set_debugobj_lock_classes_node(struct kmem_cache *cachep, int node) +{ + slab_set_lock_classes(cachep, &debugobj_l3_key, &debugobj_alc_key, node); +} + +static void slab_set_debugobj_lock_classes(struct kmem_cache *cachep) +{ + int node; + + for_each_online_node(node) + slab_set_debugobj_lock_classes_node(cachep, node); +} + static void init_node_lock_keys(int q) { struct cache_sizes *s = malloc_sizes; @@ -628,29 +675,14 @@ static void init_node_lock_keys(int q) return; for (s = malloc_sizes; s->cs_size != ULONG_MAX; s++) { - struct array_cache **alc; struct kmem_list3 *l3; - int r; l3 = s->cs_cachep->nodelists[q]; if (!l3 || OFF_SLAB(s->cs_cachep)) continue; - lockdep_set_class(&l3->list_lock, &on_slab_l3_key); - alc = l3->alien; - /* - * FIXME: This check for BAD_ALIEN_MAGIC - * should go away when common slab code is taught to - * work even without alien caches. - * Currently, non NUMA code returns BAD_ALIEN_MAGIC - * for alloc_alien_cache, - */ - if (!alc || (unsigned long)alc == BAD_ALIEN_MAGIC) - continue; - for_each_node(r) { - if (alc[r]) - lockdep_set_class(&alc[r]->lock, - &on_slab_alc_key); - } + + slab_set_lock_classes(s->cs_cachep, &on_slab_l3_key, + &on_slab_alc_key, q); } } @@ -669,6 +701,14 @@ static void init_node_lock_keys(int q) static inline void init_lock_keys(void) { } + +static void slab_set_debugobj_lock_classes_node(struct kmem_cache *cachep, int node) +{ +} + +static void slab_set_debugobj_lock_classes(struct kmem_cache *cachep) +{ +} #endif /* @@ -1262,6 +1302,8 @@ static int __cpuinit cpuup_prepare(long cpu) spin_unlock_irq(&l3->list_lock); kfree(shared); free_alien_cache(alien); + if (cachep->flags & SLAB_DEBUG_OBJECTS) + slab_set_debugobj_lock_classes_node(cachep, node); } init_node_lock_keys(node); @@ -1492,11 +1534,10 @@ void __init kmem_cache_init(void) cache_cache.nodelists[node] = &initkmem_list3[CACHE_CACHE + node]; /* - * struct kmem_cache size depends on nr_node_ids, which - * can be less than MAX_NUMNODES. + * struct kmem_cache size depends on nr_node_ids & nr_cpu_ids */ - cache_cache.buffer_size = offsetof(struct kmem_cache, nodelists) + - nr_node_ids * sizeof(struct kmem_list3 *); + cache_cache.buffer_size = offsetof(struct kmem_cache, array[nr_cpu_ids]) + + nr_node_ids * sizeof(struct kmem_list3 *); #if DEBUG cache_cache.obj_size = cache_cache.buffer_size; #endif @@ -1625,6 +1666,9 @@ void __init kmem_cache_init_late(void) { struct kmem_cache *cachep; + /* Annotate slab for lockdep -- annotate the malloc caches */ + init_lock_keys(); + /* 6) resize the head arrays to their final sizes */ mutex_lock(&cache_chain_mutex); list_for_each_entry(cachep, &cache_chain, next) @@ -1635,9 +1679,6 @@ void __init kmem_cache_init_late(void) /* Done! */ g_cpucache_up = FULL; - /* Annotate slab for lockdep -- annotate the malloc caches */ - init_lock_keys(); - /* * Register a cpu startup notifier callback that initializes * cpu_cache_get for all new cpus @@ -1810,15 +1851,15 @@ static void dump_line(char *data, int offset, int limit) unsigned char error = 0; int bad_count = 0; - printk(KERN_ERR "%03x:", offset); + printk(KERN_ERR "%03x: ", offset); for (i = 0; i < limit; i++) { if (data[offset + i] != POISON_FREE) { error = data[offset + i]; bad_count++; } - printk(" %02x", (unsigned char)data[offset + i]); } - printk("\n"); + print_hex_dump(KERN_CONT, "", 0, 16, 1, + &data[offset], limit, 1); if (bad_count == 1) { error ^= POISON_FREE; @@ -2308,6 +2349,7 @@ kmem_cache_create (const char *name, size_t size, size_t align, if (!cachep) goto oops; + cachep->nodelists = (struct kmem_list3 **)&cachep->array[nr_cpu_ids]; #if DEBUG cachep->obj_size = size; @@ -2424,6 +2466,16 @@ kmem_cache_create (const char *name, size_t size, size_t align, goto oops; } + if (flags & SLAB_DEBUG_OBJECTS) { + /* + * Would deadlock through slab_destroy()->call_rcu()-> + * debug_object_activate()->kmem_cache_alloc(). + */ + WARN_ON_ONCE(flags & SLAB_DESTROY_BY_RCU); + + slab_set_debugobj_lock_classes(cachep); + } + /* cache setup completed, link it into the list */ list_add(&cachep->next, &cache_chain); oops: @@ -2987,14 +3039,9 @@ bad: printk(KERN_ERR "slab: Internal list corruption detected in " "cache '%s'(%d), slabp %p(%d). Hexdump:\n", cachep->name, cachep->num, slabp, slabp->inuse); - for (i = 0; - i < sizeof(*slabp) + cachep->num * sizeof(kmem_bufctl_t); - i++) { - if (i % 16 == 0) - printk("\n%03x:", i); - printk(" %02x", ((unsigned char *)slabp)[i]); - } - printk("\n"); + print_hex_dump(KERN_ERR, "", DUMP_PREFIX_OFFSET, 16, 1, slabp, + sizeof(*slabp) + cachep->num * sizeof(kmem_bufctl_t), + 1); BUG(); } } @@ -3153,12 +3200,11 @@ static void *cache_alloc_debugcheck_after(struct kmem_cache *cachep, objp += obj_offset(cachep); if (cachep->ctor && cachep->flags & SLAB_POISON) cachep->ctor(objp); -#if ARCH_SLAB_MINALIGN - if ((u32)objp & (ARCH_SLAB_MINALIGN-1)) { + if (ARCH_SLAB_MINALIGN && + ((unsigned long)objp & (ARCH_SLAB_MINALIGN-1))) { printk(KERN_ERR "0x%p: not aligned to ARCH_SLAB_MINALIGN=%d\n", - objp, ARCH_SLAB_MINALIGN); + objp, (int)ARCH_SLAB_MINALIGN); } -#endif return objp; } #else @@ -3402,7 +3448,7 @@ __cache_alloc_node(struct kmem_cache *cachep, gfp_t flags, int nodeid, cache_alloc_debugcheck_before(cachep, flags); local_irq_save(save_flags); - if (nodeid == -1) + if (nodeid == NUMA_NO_NODE) nodeid = slab_node; if (unlikely(!cachep->nodelists[nodeid])) { @@ -3933,7 +3979,7 @@ fail: struct ccupdate_struct { struct kmem_cache *cachep; - struct array_cache *new[NR_CPUS]; + struct array_cache *new[0]; }; static void do_ccupdate_local(void *info) @@ -3955,7 +4001,8 @@ static int do_tune_cpucache(struct kmem_cache *cachep, int limit, struct ccupdate_struct *new; int i; - new = kzalloc(sizeof(*new), gfp); + new = kzalloc(sizeof(*new) + nr_cpu_ids * sizeof(struct array_cache *), + gfp); if (!new) return -ENOMEM; @@ -4532,7 +4579,7 @@ static const struct file_operations proc_slabstats_operations = { static int __init slab_proc_init(void) { - proc_create("slabinfo",S_IWUSR|S_IRUGO,NULL,&proc_slabinfo_operations); + proc_create("slabinfo",S_IWUSR|S_IRUSR,NULL,&proc_slabinfo_operations); #ifdef CONFIG_DEBUG_SLAB_LEAK proc_create("slab_allocators", 0, NULL, &proc_slabstats_operations); #endif @@ -63,14 +63,14 @@ #include <linux/swap.h> /* struct reclaim_state */ #include <linux/cache.h> #include <linux/init.h> -#include <linux/module.h> +#include <linux/export.h> #include <linux/rcupdate.h> #include <linux/list.h> #include <linux/kmemleak.h> #include <trace/events/kmem.h> -#include <asm/atomic.h> +#include <linux/atomic.h> /* * slob_block has a field 'units', which indicates size of block if +ve, @@ -482,6 +482,8 @@ void *__kmalloc_node(size_t size, gfp_t gfp, int node) int align = max(ARCH_KMALLOC_MINALIGN, ARCH_SLAB_MINALIGN); void *ret; + gfp &= gfp_allowed_mask; + lockdep_trace_alloc(gfp); if (size < PAGE_SIZE - align) { @@ -608,6 +610,10 @@ void *kmem_cache_alloc_node(struct kmem_cache *c, gfp_t flags, int node) { void *b; + flags &= gfp_allowed_mask; + + lockdep_trace_alloc(flags); + if (c->size < PAGE_SIZE) { b = slob_alloc(c->size, flags, c->align, node); trace_kmem_cache_alloc_node(_RET_IP_, b, c->size, @@ -2,10 +2,11 @@ * SLUB: A slab allocator that limits cache line use instead of queuing * objects in per cpu and per node lists. * - * The allocator synchronizes using per slab locks and only - * uses a centralized lock to manage a pool of partial slabs. + * The allocator synchronizes using per slab locks or atomic operatios + * and only uses a centralized lock to manage a pool of partial slabs. * * (C) 2007 SGI, Christoph Lameter + * (C) 2011 Linux Foundation, Christoph Lameter */ #include <linux/mm.h> @@ -27,20 +28,33 @@ #include <linux/memory.h> #include <linux/math64.h> #include <linux/fault-inject.h> +#include <linux/stacktrace.h> #include <trace/events/kmem.h> /* * Lock order: - * 1. slab_lock(page) - * 2. slab->list_lock + * 1. slub_lock (Global Semaphore) + * 2. node->list_lock + * 3. slab_lock(page) (Only on some arches and for debugging) * - * The slab_lock protects operations on the object of a particular - * slab and its metadata in the page struct. If the slab lock - * has been taken then no allocations nor frees can be performed - * on the objects in the slab nor can the slab be added or removed - * from the partial or full lists since this would mean modifying - * the page_struct of the slab. + * slub_lock + * + * The role of the slub_lock is to protect the list of all the slabs + * and to synchronize major metadata changes to slab cache structures. + * + * The slab_lock is only used for debugging and on arches that do not + * have the ability to do a cmpxchg_double. It only protects the second + * double word in the page struct. Meaning + * A. page->freelist -> List of object free in a page + * B. page->counters -> Counters of objects + * C. page->frozen -> frozen state + * + * If a slab is frozen then it is exempt from list management. It is not + * on any list. The processor that froze the slab is the one who can + * perform list operations on the page. Other processors may put objects + * onto the freelist but the processor that froze the slab is the only + * one that can retrieve the objects from the page's freelist. * * The list_lock protects the partial and full list on each node and * the partial slab counter. If taken then no new slabs may be added or @@ -53,20 +67,6 @@ * slabs, operations can continue without any centralized lock. F.e. * allocating a long series of objects that fill up slabs does not require * the list lock. - * - * The lock order is sometimes inverted when we are trying to get a slab - * off a list. We take the list_lock and then look for a page on the list - * to use. While we do that objects in the slabs may be freed. We can - * only operate on the slab if we have also taken the slab_lock. So we use - * a slab_trylock() on the slab. If trylock was successful then no frees - * can occur anymore and we can use the slab for allocations etc. If the - * slab_trylock() does not succeed then frees are in progress in the slab and - * we must stay away from it for a while since we may cause a bouncing - * cacheline if we try to acquire the lock. So go onto the next slab. - * If all pages are busy then we may allocate a new slab instead of reusing - * a partial slab. A new slab has no one operating on it and thus there is - * no danger of cacheline contention. - * * Interrupts are disabled during allocation and deallocation in order to * make the slab allocator safe to use in the context of an irq. In addition * interrupts are disabled to ensure that the processor does not change @@ -131,6 +131,9 @@ static inline int kmem_cache_debug(struct kmem_cache *s) /* Enable to test recovery from slab corruption on boot */ #undef SLUB_RESILIENCY_TEST +/* Enable to log cmpxchg failures */ +#undef SLUB_DEBUG_CMPXCHG + /* * Mininum number of partial slabs. These will be left on the partial * lists even if they are empty. kmem_cache_shrink may reclaim them. @@ -166,10 +169,11 @@ static inline int kmem_cache_debug(struct kmem_cache *s) #define OO_SHIFT 16 #define OO_MASK ((1 << OO_SHIFT) - 1) -#define MAX_OBJS_PER_PAGE 65535 /* since page.objects is u16 */ +#define MAX_OBJS_PER_PAGE 32767 /* since page.objects is u15 */ /* Internal SLUB flags */ #define __OBJECT_POISON 0x80000000UL /* Poison object */ +#define __CMPXCHG_DOUBLE 0x40000000UL /* Use cmpxchg_double */ static int kmem_size = sizeof(struct kmem_cache); @@ -191,8 +195,12 @@ static LIST_HEAD(slab_caches); /* * Tracking user of a slab. */ +#define TRACK_ADDRS_COUNT 16 struct track { unsigned long addr; /* Called from address */ +#ifdef CONFIG_STACKTRACE + unsigned long addrs[TRACK_ADDRS_COUNT]; /* Called from address */ +#endif int cpu; /* Was running on cpu */ int pid; /* Pid context */ unsigned long when; /* When did the operation occur */ @@ -338,11 +346,99 @@ static inline int oo_objects(struct kmem_cache_order_objects x) return x.x & OO_MASK; } +/* + * Per slab locking using the pagelock + */ +static __always_inline void slab_lock(struct page *page) +{ + bit_spin_lock(PG_locked, &page->flags); +} + +static __always_inline void slab_unlock(struct page *page) +{ + __bit_spin_unlock(PG_locked, &page->flags); +} + +/* Interrupts must be disabled (for the fallback code to work right) */ +static inline bool __cmpxchg_double_slab(struct kmem_cache *s, struct page *page, + void *freelist_old, unsigned long counters_old, + void *freelist_new, unsigned long counters_new, + const char *n) +{ + VM_BUG_ON(!irqs_disabled()); +#ifdef CONFIG_CMPXCHG_DOUBLE + if (s->flags & __CMPXCHG_DOUBLE) { + if (cmpxchg_double(&page->freelist, + freelist_old, counters_old, + freelist_new, counters_new)) + return 1; + } else +#endif + { + slab_lock(page); + if (page->freelist == freelist_old && page->counters == counters_old) { + page->freelist = freelist_new; + page->counters = counters_new; + slab_unlock(page); + return 1; + } + slab_unlock(page); + } + + cpu_relax(); + stat(s, CMPXCHG_DOUBLE_FAIL); + +#ifdef SLUB_DEBUG_CMPXCHG + printk(KERN_INFO "%s %s: cmpxchg double redo ", n, s->name); +#endif + + return 0; +} + +static inline bool cmpxchg_double_slab(struct kmem_cache *s, struct page *page, + void *freelist_old, unsigned long counters_old, + void *freelist_new, unsigned long counters_new, + const char *n) +{ +#ifdef CONFIG_CMPXCHG_DOUBLE + if (s->flags & __CMPXCHG_DOUBLE) { + if (cmpxchg_double(&page->freelist, + freelist_old, counters_old, + freelist_new, counters_new)) + return 1; + } else +#endif + { + unsigned long flags; + + local_irq_save(flags); + slab_lock(page); + if (page->freelist == freelist_old && page->counters == counters_old) { + page->freelist = freelist_new; + page->counters = counters_new; + slab_unlock(page); + local_irq_restore(flags); + return 1; + } + slab_unlock(page); + local_irq_restore(flags); + } + + cpu_relax(); + stat(s, CMPXCHG_DOUBLE_FAIL); + +#ifdef SLUB_DEBUG_CMPXCHG + printk(KERN_INFO "%s %s: cmpxchg double redo ", n, s->name); +#endif + + return 0; +} + #ifdef CONFIG_SLUB_DEBUG /* * Determine a map of object in use on a page. * - * Slab lock or node listlock must be held to guarantee that the page does + * Node listlock must be held to guarantee that the page does * not vanish from under us. */ static void get_map(struct kmem_cache *s, struct page *page, unsigned long *map) @@ -371,34 +467,8 @@ static int disable_higher_order_debug; */ static void print_section(char *text, u8 *addr, unsigned int length) { - int i, offset; - int newline = 1; - char ascii[17]; - - ascii[16] = 0; - - for (i = 0; i < length; i++) { - if (newline) { - printk(KERN_ERR "%8s 0x%p: ", text, addr + i); - newline = 0; - } - printk(KERN_CONT " %02x", addr[i]); - offset = i % 16; - ascii[offset] = isgraph(addr[i]) ? addr[i] : '.'; - if (offset == 15) { - printk(KERN_CONT " %s\n", ascii); - newline = 1; - } - } - if (!newline) { - i %= 16; - while (i < 16) { - printk(KERN_CONT " "); - ascii[i] = ' '; - i++; - } - printk(KERN_CONT " %s\n", ascii); - } + print_hex_dump(KERN_ERR, text, DUMP_PREFIX_ADDRESS, 16, 1, addr, + length, 1); } static struct track *get_track(struct kmem_cache *s, void *object, @@ -420,6 +490,24 @@ static void set_track(struct kmem_cache *s, void *object, struct track *p = get_track(s, object, alloc); if (addr) { +#ifdef CONFIG_STACKTRACE + struct stack_trace trace; + int i; + + trace.nr_entries = 0; + trace.max_entries = TRACK_ADDRS_COUNT; + trace.entries = p->addrs; + trace.skip = 3; + save_stack_trace(&trace); + + /* See rant in lockdep.c */ + if (trace.nr_entries != 0 && + trace.entries[trace.nr_entries - 1] == ULONG_MAX) + trace.nr_entries--; + + for (i = trace.nr_entries; i < TRACK_ADDRS_COUNT; i++) + p->addrs[i] = 0; +#endif p->addr = addr; p->cpu = smp_processor_id(); p->pid = current->pid; @@ -444,6 +532,16 @@ static void print_track(const char *s, struct track *t) printk(KERN_ERR "INFO: %s in %pS age=%lu cpu=%u pid=%d\n", s, (void *)t->addr, jiffies - t->when, t->cpu, t->pid); +#ifdef CONFIG_STACKTRACE + { + int i; + for (i = 0; i < TRACK_ADDRS_COUNT; i++) + if (t->addrs[i]) + printk(KERN_ERR "\t%pS\n", (void *)t->addrs[i]); + else + break; + } +#endif } static void print_tracking(struct kmem_cache *s, void *object) @@ -501,12 +599,12 @@ static void print_trailer(struct kmem_cache *s, struct page *page, u8 *p) p, p - addr, get_freepointer(s, p)); if (p > addr + 16) - print_section("Bytes b4", p - 16, 16); - - print_section("Object", p, min_t(unsigned long, s->objsize, PAGE_SIZE)); + print_section("Bytes b4 ", p - 16, 16); + print_section("Object ", p, min_t(unsigned long, s->objsize, + PAGE_SIZE)); if (s->flags & SLAB_RED_ZONE) - print_section("Redzone", p + s->objsize, + print_section("Redzone ", p + s->objsize, s->inuse - s->objsize); if (s->offset) @@ -519,7 +617,7 @@ static void print_trailer(struct kmem_cache *s, struct page *page, u8 *p) if (off != s->size) /* Beginning of the filler is the free pointer */ - print_section("Padding", p + off, s->size - off); + print_section("Padding ", p + off, s->size - off); dump_stack(); } @@ -557,17 +655,6 @@ static void init_object(struct kmem_cache *s, void *object, u8 val) memset(p + s->objsize, val, s->inuse - s->objsize); } -static u8 *check_bytes(u8 *start, unsigned int value, unsigned int bytes) -{ - while (bytes) { - if (*start != (u8)value) - return start; - start++; - bytes--; - } - return NULL; -} - static void restore_bytes(struct kmem_cache *s, char *message, u8 data, void *from, void *to) { @@ -582,7 +669,7 @@ static int check_bytes_and_report(struct kmem_cache *s, struct page *page, u8 *fault; u8 *end; - fault = check_bytes(start, value, bytes); + fault = memchr_inv(start, value, bytes); if (!fault) return 1; @@ -675,14 +762,14 @@ static int slab_pad_check(struct kmem_cache *s, struct page *page) if (!remainder) return 1; - fault = check_bytes(end - remainder, POISON_INUSE, remainder); + fault = memchr_inv(end - remainder, POISON_INUSE, remainder); if (!fault) return 1; while (end > fault && end[-1] == POISON_INUSE) end--; slab_err(s, page, "Padding overwritten. 0x%p-0x%p", fault, end - 1); - print_section("Padding", end - remainder, remainder); + print_section("Padding ", end - remainder, remainder); restore_bytes(s, "slab padding", POISON_INUSE, end - remainder, end); return 0; @@ -773,10 +860,11 @@ static int check_slab(struct kmem_cache *s, struct page *page) static int on_freelist(struct kmem_cache *s, struct page *page, void *search) { int nr = 0; - void *fp = page->freelist; + void *fp; void *object = NULL; unsigned long max_objects; + fp = page->freelist; while (fp && nr <= page->objects) { if (fp == search) return 1; @@ -830,7 +918,7 @@ static void trace(struct kmem_cache *s, struct page *page, void *object, page->freelist); if (!alloc) - print_section("Object", (void *)object, s->objsize); + print_section("Object ", (void *)object, s->objsize); dump_stack(); } @@ -881,26 +969,27 @@ static inline void slab_free_hook(struct kmem_cache *s, void *x) /* * Tracking of fully allocated slabs for debugging purposes. + * + * list_lock must be held. */ -static void add_full(struct kmem_cache_node *n, struct page *page) +static void add_full(struct kmem_cache *s, + struct kmem_cache_node *n, struct page *page) { - spin_lock(&n->list_lock); + if (!(s->flags & SLAB_STORE_USER)) + return; + list_add(&page->lru, &n->full); - spin_unlock(&n->list_lock); } +/* + * list_lock must be held. + */ static void remove_full(struct kmem_cache *s, struct page *page) { - struct kmem_cache_node *n; - if (!(s->flags & SLAB_STORE_USER)) return; - n = get_node(s, page_to_nid(page)); - - spin_lock(&n->list_lock); list_del(&page->lru); - spin_unlock(&n->list_lock); } /* Tracking of the number of slabs for debugging purposes */ @@ -956,11 +1045,6 @@ static noinline int alloc_debug_processing(struct kmem_cache *s, struct page *pa if (!check_slab(s, page)) goto bad; - if (!on_freelist(s, page, object)) { - object_err(s, page, object, "Object already allocated"); - goto bad; - } - if (!check_valid_pointer(s, page, object)) { object_err(s, page, object, "Freelist Pointer check fails"); goto bad; @@ -993,6 +1077,12 @@ bad: static noinline int free_debug_processing(struct kmem_cache *s, struct page *page, void *object, unsigned long addr) { + unsigned long flags; + int rc = 0; + + local_irq_save(flags); + slab_lock(page); + if (!check_slab(s, page)) goto fail; @@ -1007,7 +1097,7 @@ static noinline int free_debug_processing(struct kmem_cache *s, } if (!check_object(s, page, object, SLUB_RED_ACTIVE)) - return 0; + goto out; if (unlikely(s != page->slab)) { if (!PageSlab(page)) { @@ -1024,18 +1114,19 @@ static noinline int free_debug_processing(struct kmem_cache *s, goto fail; } - /* Special debug activities for freeing objects */ - if (!PageSlubFrozen(page) && !page->freelist) - remove_full(s, page); if (s->flags & SLAB_STORE_USER) set_track(s, object, TRACK_FREE, addr); trace(s, page, object, 0); init_object(s, object, SLUB_RED_INACTIVE); - return 1; + rc = 1; +out: + slab_unlock(page); + local_irq_restore(flags); + return rc; fail: slab_fix(s, "Object at 0x%p not freed", object); - return 0; + goto out; } static int __init setup_slub_debug(char *str) @@ -1135,7 +1226,9 @@ static inline int slab_pad_check(struct kmem_cache *s, struct page *page) { return 1; } static inline int check_object(struct kmem_cache *s, struct page *page, void *object, u8 val) { return 1; } -static inline void add_full(struct kmem_cache_node *n, struct page *page) {} +static inline void add_full(struct kmem_cache *s, struct kmem_cache_node *n, + struct page *page) {} +static inline void remove_full(struct kmem_cache *s, struct page *page) {} static inline unsigned long kmem_cache_flags(unsigned long objsize, unsigned long flags, const char *name, void (*ctor)(void *)) @@ -1187,6 +1280,11 @@ static struct page *allocate_slab(struct kmem_cache *s, gfp_t flags, int node) struct kmem_cache_order_objects oo = s->oo; gfp_t alloc_gfp; + flags &= gfp_allowed_mask; + + if (flags & __GFP_WAIT) + local_irq_enable(); + flags |= s->allocflags; /* @@ -1203,12 +1301,17 @@ static struct page *allocate_slab(struct kmem_cache *s, gfp_t flags, int node) * Try a lower order alloc if possible */ page = alloc_slab_page(flags, node, oo); - if (!page) - return NULL; - stat(s, ORDER_FALLBACK); + if (page) + stat(s, ORDER_FALLBACK); } + if (flags & __GFP_WAIT) + local_irq_disable(); + + if (!page) + return NULL; + if (kmemcheck_enabled && !(s->flags & (SLAB_NOTRACK | DEBUG_DEFAULT_FLAGS))) { int pages = 1 << oo_order(oo); @@ -1275,7 +1378,8 @@ static struct page *new_slab(struct kmem_cache *s, gfp_t flags, int node) set_freepointer(s, last, NULL); page->freelist = start; - page->inuse = 0; + page->inuse = page->objects; + page->frozen = 1; out: return page; } @@ -1353,79 +1457,80 @@ static void discard_slab(struct kmem_cache *s, struct page *page) } /* - * Per slab locking using the pagelock - */ -static __always_inline void slab_lock(struct page *page) -{ - bit_spin_lock(PG_locked, &page->flags); -} - -static __always_inline void slab_unlock(struct page *page) -{ - __bit_spin_unlock(PG_locked, &page->flags); -} - -static __always_inline int slab_trylock(struct page *page) -{ - int rc = 1; - - rc = bit_spin_trylock(PG_locked, &page->flags); - return rc; -} - -/* - * Management of partially allocated slabs + * Management of partially allocated slabs. + * + * list_lock must be held. */ -static void add_partial(struct kmem_cache_node *n, +static inline void add_partial(struct kmem_cache_node *n, struct page *page, int tail) { - spin_lock(&n->list_lock); n->nr_partial++; - if (tail) + if (tail == DEACTIVATE_TO_TAIL) list_add_tail(&page->lru, &n->partial); else list_add(&page->lru, &n->partial); - spin_unlock(&n->list_lock); } -static inline void __remove_partial(struct kmem_cache_node *n, +/* + * list_lock must be held. + */ +static inline void remove_partial(struct kmem_cache_node *n, struct page *page) { list_del(&page->lru); n->nr_partial--; } -static void remove_partial(struct kmem_cache *s, struct page *page) -{ - struct kmem_cache_node *n = get_node(s, page_to_nid(page)); - - spin_lock(&n->list_lock); - __remove_partial(n, page); - spin_unlock(&n->list_lock); -} - /* - * Lock slab and remove from the partial list. + * Lock slab, remove from the partial list and put the object into the + * per cpu freelist. + * + * Returns a list of objects or NULL if it fails. * * Must hold list_lock. */ -static inline int lock_and_freeze_slab(struct kmem_cache_node *n, - struct page *page) +static inline void *acquire_slab(struct kmem_cache *s, + struct kmem_cache_node *n, struct page *page, + int mode) { - if (slab_trylock(page)) { - __remove_partial(n, page); - __SetPageSlubFrozen(page); - return 1; - } - return 0; + void *freelist; + unsigned long counters; + struct page new; + + /* + * Zap the freelist and set the frozen bit. + * The old freelist is the list of objects for the + * per cpu allocation list. + */ + do { + freelist = page->freelist; + counters = page->counters; + new.counters = counters; + if (mode) + new.inuse = page->objects; + + VM_BUG_ON(new.frozen); + new.frozen = 1; + + } while (!__cmpxchg_double_slab(s, page, + freelist, counters, + NULL, new.counters, + "lock and freeze")); + + remove_partial(n, page); + return freelist; } +static int put_cpu_partial(struct kmem_cache *s, struct page *page, int drain); + /* * Try to allocate a partial slab from a specific node. */ -static struct page *get_partial_node(struct kmem_cache_node *n) +static void *get_partial_node(struct kmem_cache *s, + struct kmem_cache_node *n, struct kmem_cache_cpu *c) { - struct page *page; + struct page *page, *page2; + void *object = NULL; /* * Racy check. If we mistakenly see no partial slabs then we @@ -1437,26 +1542,43 @@ static struct page *get_partial_node(struct kmem_cache_node *n) return NULL; spin_lock(&n->list_lock); - list_for_each_entry(page, &n->partial, lru) - if (lock_and_freeze_slab(n, page)) - goto out; - page = NULL; -out: + list_for_each_entry_safe(page, page2, &n->partial, lru) { + void *t = acquire_slab(s, n, page, object == NULL); + int available; + + if (!t) + break; + + if (!object) { + c->page = page; + c->node = page_to_nid(page); + stat(s, ALLOC_FROM_PARTIAL); + object = t; + available = page->objects - page->inuse; + } else { + page->freelist = t; + available = put_cpu_partial(s, page, 0); + } + if (kmem_cache_debug(s) || available > s->cpu_partial / 2) + break; + + } spin_unlock(&n->list_lock); - return page; + return object; } /* * Get a page from somewhere. Search in increasing NUMA distances. */ -static struct page *get_any_partial(struct kmem_cache *s, gfp_t flags) +static struct page *get_any_partial(struct kmem_cache *s, gfp_t flags, + struct kmem_cache_cpu *c) { #ifdef CONFIG_NUMA struct zonelist *zonelist; struct zoneref *z; struct zone *zone; enum zone_type high_zoneidx = gfp_zone(flags); - struct page *page; + void *object; /* * The defrag ratio allows a configuration of the tradeoffs between @@ -1489,10 +1611,10 @@ static struct page *get_any_partial(struct kmem_cache *s, gfp_t flags) if (n && cpuset_zone_allowed_hardwall(zone, flags) && n->nr_partial > s->min_partial) { - page = get_partial_node(n); - if (page) { + object = get_partial_node(s, n, c); + if (object) { put_mems_allowed(); - return page; + return object; } } } @@ -1504,63 +1626,17 @@ static struct page *get_any_partial(struct kmem_cache *s, gfp_t flags) /* * Get a partial page, lock it and return it. */ -static struct page *get_partial(struct kmem_cache *s, gfp_t flags, int node) +static void *get_partial(struct kmem_cache *s, gfp_t flags, int node, + struct kmem_cache_cpu *c) { - struct page *page; + void *object; int searchnode = (node == NUMA_NO_NODE) ? numa_node_id() : node; - page = get_partial_node(get_node(s, searchnode)); - if (page || node != NUMA_NO_NODE) - return page; - - return get_any_partial(s, flags); -} - -/* - * Move a page back to the lists. - * - * Must be called with the slab lock held. - * - * On exit the slab lock will have been dropped. - */ -static void unfreeze_slab(struct kmem_cache *s, struct page *page, int tail) - __releases(bitlock) -{ - struct kmem_cache_node *n = get_node(s, page_to_nid(page)); - - __ClearPageSlubFrozen(page); - if (page->inuse) { + object = get_partial_node(s, get_node(s, searchnode), c); + if (object || node != NUMA_NO_NODE) + return object; - if (page->freelist) { - add_partial(n, page, tail); - stat(s, tail ? DEACTIVATE_TO_TAIL : DEACTIVATE_TO_HEAD); - } else { - stat(s, DEACTIVATE_FULL); - if (kmem_cache_debug(s) && (s->flags & SLAB_STORE_USER)) - add_full(n, page); - } - slab_unlock(page); - } else { - stat(s, DEACTIVATE_EMPTY); - 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 - * to come after the other slabs with objects in - * so that the others get filled first. That way the - * size of the partial list stays small. - * - * kmem_cache_shrink can reclaim any empty slabs from - * the partial list. - */ - add_partial(n, page, 1); - slab_unlock(page); - } else { - slab_unlock(page); - stat(s, FREE_SLAB); - discard_slab(s, page); - } - } + return get_any_partial(s, flags, c); } #ifdef CONFIG_PREEMPT @@ -1629,45 +1705,278 @@ void init_kmem_cache_cpus(struct kmem_cache *s) for_each_possible_cpu(cpu) per_cpu_ptr(s->cpu_slab, cpu)->tid = init_tid(cpu); } + /* * Remove the cpu slab */ static void deactivate_slab(struct kmem_cache *s, struct kmem_cache_cpu *c) - __releases(bitlock) { + enum slab_modes { M_NONE, M_PARTIAL, M_FULL, M_FREE }; struct page *page = c->page; - int tail = 1; - - if (page->freelist) + struct kmem_cache_node *n = get_node(s, page_to_nid(page)); + int lock = 0; + enum slab_modes l = M_NONE, m = M_NONE; + void *freelist; + void *nextfree; + int tail = DEACTIVATE_TO_HEAD; + struct page new; + struct page old; + + if (page->freelist) { stat(s, DEACTIVATE_REMOTE_FREES); + tail = DEACTIVATE_TO_TAIL; + } + + c->tid = next_tid(c->tid); + c->page = NULL; + freelist = c->freelist; + c->freelist = NULL; + + /* + * Stage one: Free all available per cpu objects back + * to the page freelist while it is still frozen. Leave the + * last one. + * + * There is no need to take the list->lock because the page + * is still frozen. + */ + while (freelist && (nextfree = get_freepointer(s, freelist))) { + void *prior; + unsigned long counters; + + do { + prior = page->freelist; + counters = page->counters; + set_freepointer(s, freelist, prior); + new.counters = counters; + new.inuse--; + VM_BUG_ON(!new.frozen); + + } while (!__cmpxchg_double_slab(s, page, + prior, counters, + freelist, new.counters, + "drain percpu freelist")); + + freelist = nextfree; + } + /* - * Merge cpu freelist into slab freelist. Typically we get here - * because both freelists are empty. So this is unlikely - * to occur. + * Stage two: Ensure that the page is unfrozen while the + * list presence reflects the actual number of objects + * during unfreeze. + * + * We setup the list membership and then perform a cmpxchg + * with the count. If there is a mismatch then the page + * is not unfrozen but the page is on the wrong list. + * + * Then we restart the process which may have to remove + * the page from the list that we just put it on again + * because the number of objects in the slab may have + * changed. */ - while (unlikely(c->freelist)) { - void **object; +redo: + + old.freelist = page->freelist; + old.counters = page->counters; + VM_BUG_ON(!old.frozen); - tail = 0; /* Hot objects. Put the slab first */ + /* Determine target state of the slab */ + new.counters = old.counters; + if (freelist) { + new.inuse--; + set_freepointer(s, freelist, old.freelist); + new.freelist = freelist; + } else + new.freelist = old.freelist; - /* Retrieve object from cpu_freelist */ - object = c->freelist; - c->freelist = get_freepointer(s, c->freelist); + new.frozen = 0; - /* And put onto the regular freelist */ - set_freepointer(s, object, page->freelist); - page->freelist = object; - page->inuse--; + if (!new.inuse && n->nr_partial > s->min_partial) + m = M_FREE; + else if (new.freelist) { + m = M_PARTIAL; + if (!lock) { + lock = 1; + /* + * Taking the spinlock removes the possiblity + * that acquire_slab() will see a slab page that + * is frozen + */ + spin_lock(&n->list_lock); + } + } else { + m = M_FULL; + if (kmem_cache_debug(s) && !lock) { + lock = 1; + /* + * This also ensures that the scanning of full + * slabs from diagnostic functions will not see + * any frozen slabs. + */ + spin_lock(&n->list_lock); + } + } + + if (l != m) { + + if (l == M_PARTIAL) + + remove_partial(n, page); + + else if (l == M_FULL) + + remove_full(s, page); + + if (m == M_PARTIAL) { + + add_partial(n, page, tail); + stat(s, tail); + + } else if (m == M_FULL) { + + stat(s, DEACTIVATE_FULL); + add_full(s, n, page); + + } + } + + l = m; + if (!__cmpxchg_double_slab(s, page, + old.freelist, old.counters, + new.freelist, new.counters, + "unfreezing slab")) + goto redo; + + if (lock) + spin_unlock(&n->list_lock); + + if (m == M_FREE) { + stat(s, DEACTIVATE_EMPTY); + discard_slab(s, page); + stat(s, FREE_SLAB); } - c->page = NULL; - c->tid = next_tid(c->tid); - unfreeze_slab(s, page, tail); +} + +/* Unfreeze all the cpu partial slabs */ +static void unfreeze_partials(struct kmem_cache *s) +{ + struct kmem_cache_node *n = NULL; + struct kmem_cache_cpu *c = this_cpu_ptr(s->cpu_slab); + struct page *page; + + while ((page = c->partial)) { + enum slab_modes { M_PARTIAL, M_FREE }; + enum slab_modes l, m; + struct page new; + struct page old; + + c->partial = page->next; + l = M_FREE; + + do { + + old.freelist = page->freelist; + old.counters = page->counters; + VM_BUG_ON(!old.frozen); + + new.counters = old.counters; + new.freelist = old.freelist; + + new.frozen = 0; + + if (!new.inuse && (!n || n->nr_partial > s->min_partial)) + m = M_FREE; + else { + struct kmem_cache_node *n2 = get_node(s, + page_to_nid(page)); + + m = M_PARTIAL; + if (n != n2) { + if (n) + spin_unlock(&n->list_lock); + + n = n2; + spin_lock(&n->list_lock); + } + } + + if (l != m) { + if (l == M_PARTIAL) + remove_partial(n, page); + else + add_partial(n, page, 1); + + l = m; + } + + } while (!cmpxchg_double_slab(s, page, + old.freelist, old.counters, + new.freelist, new.counters, + "unfreezing slab")); + + if (m == M_FREE) { + stat(s, DEACTIVATE_EMPTY); + discard_slab(s, page); + stat(s, FREE_SLAB); + } + } + + if (n) + spin_unlock(&n->list_lock); +} + +/* + * Put a page that was just frozen (in __slab_free) into a partial page + * slot if available. This is done without interrupts disabled and without + * preemption disabled. The cmpxchg is racy and may put the partial page + * onto a random cpus partial slot. + * + * If we did not find a slot then simply move all the partials to the + * per node partial list. + */ +int put_cpu_partial(struct kmem_cache *s, struct page *page, int drain) +{ + struct page *oldpage; + int pages; + int pobjects; + + do { + pages = 0; + pobjects = 0; + oldpage = this_cpu_read(s->cpu_slab->partial); + + if (oldpage) { + pobjects = oldpage->pobjects; + pages = oldpage->pages; + if (drain && pobjects > s->cpu_partial) { + unsigned long flags; + /* + * partial array is full. Move the existing + * set to the per node partial list. + */ + local_irq_save(flags); + unfreeze_partials(s); + local_irq_restore(flags); + pobjects = 0; + pages = 0; + } + } + + pages++; + pobjects += page->objects - page->inuse; + + page->pages = pages; + page->pobjects = pobjects; + page->next = oldpage; + + } while (this_cpu_cmpxchg(s->cpu_slab->partial, oldpage, page) != oldpage); + stat(s, CPU_PARTIAL_FREE); + return pobjects; } static inline void flush_slab(struct kmem_cache *s, struct kmem_cache_cpu *c) { stat(s, CPUSLAB_FLUSH); - slab_lock(c->page); deactivate_slab(s, c); } @@ -1680,8 +1989,12 @@ static inline void __flush_cpu_slab(struct kmem_cache *s, int cpu) { struct kmem_cache_cpu *c = per_cpu_ptr(s->cpu_slab, cpu); - if (likely(c && c->page)) - flush_slab(s, c); + if (likely(c)) { + if (c->page) + flush_slab(s, c); + + unfreeze_partials(s); + } } static void flush_cpu_slab(void *d) @@ -1772,12 +2085,39 @@ slab_out_of_memory(struct kmem_cache *s, gfp_t gfpflags, int nid) } } +static inline void *new_slab_objects(struct kmem_cache *s, gfp_t flags, + int node, struct kmem_cache_cpu **pc) +{ + void *object; + struct kmem_cache_cpu *c; + struct page *page = new_slab(s, flags, node); + + if (page) { + c = __this_cpu_ptr(s->cpu_slab); + if (c->page) + flush_slab(s, c); + + /* + * No other reference to the page yet so we can + * muck around with it freely without cmpxchg + */ + object = page->freelist; + page->freelist = NULL; + + stat(s, ALLOC_SLAB); + c->node = page_to_nid(page); + c->page = page; + *pc = c; + } else + object = NULL; + + return object; +} + /* * Slow path. The lockless freelist is empty or we need to perform * debugging duties. * - * Interrupts are disabled. - * * Processing is still very fast if new objects have been freed to the * regular freelist. In that case we simply take over the regular freelist * as the lockless freelist and zap the regular freelist. @@ -1794,8 +2134,9 @@ static void *__slab_alloc(struct kmem_cache *s, gfp_t gfpflags, int node, unsigned long addr, struct kmem_cache_cpu *c) { void **object; - struct page *page; unsigned long flags; + struct page new; + unsigned long counters; local_irq_save(flags); #ifdef CONFIG_PREEMPT @@ -1807,81 +2148,91 @@ static void *__slab_alloc(struct kmem_cache *s, gfp_t gfpflags, int node, c = this_cpu_ptr(s->cpu_slab); #endif - /* We handle __GFP_ZERO in the caller */ - gfpflags &= ~__GFP_ZERO; - - page = c->page; - if (!page) + if (!c->page) + goto new_slab; +redo: + if (unlikely(!node_match(c, node))) { + stat(s, ALLOC_NODE_MISMATCH); + deactivate_slab(s, c); goto new_slab; + } - slab_lock(page); - if (unlikely(!node_match(c, node))) - goto another_slab; + stat(s, ALLOC_SLOWPATH); + + do { + object = c->page->freelist; + counters = c->page->counters; + new.counters = counters; + VM_BUG_ON(!new.frozen); + + /* + * If there is no object left then we use this loop to + * deactivate the slab which is simple since no objects + * are left in the slab and therefore we do not need to + * put the page back onto the partial list. + * + * If there are objects left then we retrieve them + * and use them to refill the per cpu queue. + */ + + new.inuse = c->page->objects; + new.frozen = object != NULL; + + } while (!__cmpxchg_double_slab(s, c->page, + object, counters, + NULL, new.counters, + "__slab_alloc")); + + if (!object) { + c->page = NULL; + stat(s, DEACTIVATE_BYPASS); + goto new_slab; + } stat(s, ALLOC_REFILL); load_freelist: - object = page->freelist; - if (unlikely(!object)) - goto another_slab; - if (kmem_cache_debug(s)) - goto debug; - c->freelist = get_freepointer(s, object); - page->inuse = page->objects; - page->freelist = NULL; - - slab_unlock(page); c->tid = next_tid(c->tid); local_irq_restore(flags); - stat(s, ALLOC_SLOWPATH); return object; -another_slab: - deactivate_slab(s, c); - new_slab: - page = get_partial(s, gfpflags, node); - if (page) { - stat(s, ALLOC_FROM_PARTIAL); - c->node = page_to_nid(page); - c->page = page; - goto load_freelist; + + if (c->partial) { + c->page = c->partial; + c->partial = c->page->next; + c->node = page_to_nid(c->page); + stat(s, CPU_PARTIAL_ALLOC); + c->freelist = NULL; + goto redo; } - gfpflags &= gfp_allowed_mask; - if (gfpflags & __GFP_WAIT) - local_irq_enable(); + /* Then do expensive stuff like retrieving pages from the partial lists */ + object = get_partial(s, gfpflags, node, c); - page = new_slab(s, gfpflags, node); + if (unlikely(!object)) { - if (gfpflags & __GFP_WAIT) - local_irq_disable(); + object = new_slab_objects(s, gfpflags, node, &c); - if (page) { - c = __this_cpu_ptr(s->cpu_slab); - stat(s, ALLOC_SLAB); - if (c->page) - flush_slab(s, c); + if (unlikely(!object)) { + if (!(gfpflags & __GFP_NOWARN) && printk_ratelimit()) + slab_out_of_memory(s, gfpflags, node); - slab_lock(page); - __SetPageSlubFrozen(page); - c->node = page_to_nid(page); - c->page = page; - goto load_freelist; + local_irq_restore(flags); + return NULL; + } } - if (!(gfpflags & __GFP_NOWARN) && printk_ratelimit()) - slab_out_of_memory(s, gfpflags, node); - local_irq_restore(flags); - return NULL; -debug: - if (!alloc_debug_processing(s, page, object, addr)) - goto another_slab; - page->inuse++; - page->freelist = get_freepointer(s, object); + if (likely(!kmem_cache_debug(s))) + goto load_freelist; + + /* Only entered in the debug case */ + if (!alloc_debug_processing(s, c->page, object, addr)) + goto new_slab; /* Slab failed checks. Next slab needed */ + + c->freelist = get_freepointer(s, object); deactivate_slab(s, c); - c->page = NULL; c->node = NUMA_NO_NODE; local_irq_restore(flags); return object; @@ -2031,52 +2382,110 @@ static void __slab_free(struct kmem_cache *s, struct page *page, { void *prior; void **object = (void *)x; - unsigned long flags; + int was_frozen; + int inuse; + struct page new; + unsigned long counters; + struct kmem_cache_node *n = NULL; + unsigned long uninitialized_var(flags); - local_irq_save(flags); - slab_lock(page); stat(s, FREE_SLOWPATH); if (kmem_cache_debug(s) && !free_debug_processing(s, page, x, addr)) - goto out_unlock; + return; - prior = page->freelist; - set_freepointer(s, object, prior); - page->freelist = object; - page->inuse--; + do { + prior = page->freelist; + counters = page->counters; + set_freepointer(s, object, prior); + new.counters = counters; + was_frozen = new.frozen; + new.inuse--; + if ((!new.inuse || !prior) && !was_frozen && !n) { - if (unlikely(PageSlubFrozen(page))) { - stat(s, FREE_FROZEN); - goto out_unlock; - } + if (!kmem_cache_debug(s) && !prior) + + /* + * Slab was on no list before and will be partially empty + * We can defer the list move and instead freeze it. + */ + new.frozen = 1; + + else { /* Needs to be taken off a list */ + + n = get_node(s, page_to_nid(page)); + /* + * Speculatively acquire the list_lock. + * If the cmpxchg does not succeed then we may + * drop the list_lock without any processing. + * + * Otherwise the list_lock will synchronize with + * other processors updating the list of slabs. + */ + spin_lock_irqsave(&n->list_lock, flags); + + } + } + inuse = new.inuse; + + } while (!cmpxchg_double_slab(s, page, + prior, counters, + object, new.counters, + "__slab_free")); + + if (likely(!n)) { + + /* + * If we just froze the page then put it onto the + * per cpu partial list. + */ + if (new.frozen && !was_frozen) + put_cpu_partial(s, page, 1); - if (unlikely(!page->inuse)) - goto slab_empty; + /* + * The list lock was not taken therefore no list + * activity can be necessary. + */ + if (was_frozen) + stat(s, FREE_FROZEN); + return; + } /* - * Objects left in the slab. If it was not on the partial list before - * then add it. + * was_frozen may have been set after we acquired the list_lock in + * an earlier loop. So we need to check it here again. */ - if (unlikely(!prior)) { - add_partial(get_node(s, page_to_nid(page)), page, 1); - stat(s, FREE_ADD_PARTIAL); - } + if (was_frozen) + stat(s, FREE_FROZEN); + else { + if (unlikely(!inuse && n->nr_partial > s->min_partial)) + goto slab_empty; -out_unlock: - slab_unlock(page); - local_irq_restore(flags); + /* + * Objects left in the slab. If it was not on the partial list before + * then add it. + */ + if (unlikely(!prior)) { + remove_full(s, page); + add_partial(n, page, DEACTIVATE_TO_TAIL); + stat(s, FREE_ADD_PARTIAL); + } + } + spin_unlock_irqrestore(&n->list_lock, flags); return; slab_empty: if (prior) { /* - * Slab still on the partial list. + * Slab on the partial list. */ - remove_partial(s, page); + remove_partial(n, page); stat(s, FREE_REMOVE_PARTIAL); - } - slab_unlock(page); - local_irq_restore(flags); + } else + /* Slab must be on the full list */ + remove_full(s, page); + + spin_unlock_irqrestore(&n->list_lock, flags); stat(s, FREE_SLAB); discard_slab(s, page); } @@ -2102,7 +2511,6 @@ static __always_inline void slab_free(struct kmem_cache *s, slab_free_hook(s, x); redo: - /* * Determine the currently cpus per cpu slab. * The cpu may change afterward. However that does not matter since @@ -2350,7 +2758,6 @@ static void early_kmem_cache_node_alloc(int node) { struct page *page; struct kmem_cache_node *n; - unsigned long flags; BUG_ON(kmem_cache_node->size < sizeof(struct kmem_cache_node)); @@ -2367,7 +2774,8 @@ static void early_kmem_cache_node_alloc(int node) n = page->freelist; BUG_ON(!n); page->freelist = get_freepointer(kmem_cache_node, n); - page->inuse++; + page->inuse = 1; + page->frozen = 0; kmem_cache_node->node[node] = n; #ifdef CONFIG_SLUB_DEBUG init_object(kmem_cache_node, n, SLUB_RED_ACTIVE); @@ -2376,14 +2784,7 @@ static void early_kmem_cache_node_alloc(int node) init_kmem_cache_node(n, kmem_cache_node); inc_slabs_node(kmem_cache_node, node, page->objects); - /* - * lockdep requires consistent irq usage for each lock - * so even though there cannot be a race this early in - * the boot sequence, we still disable irqs. - */ - local_irq_save(flags); - add_partial(n, page, 0); - local_irq_restore(flags); + add_partial(n, page, DEACTIVATE_TO_HEAD); } static void free_kmem_cache_nodes(struct kmem_cache *s) @@ -2589,11 +2990,44 @@ static int kmem_cache_open(struct kmem_cache *s, } } +#ifdef CONFIG_CMPXCHG_DOUBLE + if (system_has_cmpxchg_double() && (s->flags & SLAB_DEBUG_FLAGS) == 0) + /* Enable fast mode */ + s->flags |= __CMPXCHG_DOUBLE; +#endif + /* * 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)); + set_min_partial(s, ilog2(s->size) / 2); + + /* + * cpu_partial determined the maximum number of objects kept in the + * per cpu partial lists of a processor. + * + * Per cpu partial lists mainly contain slabs that just have one + * object freed. If they are used for allocation then they can be + * filled up again with minimal effort. The slab will never hit the + * per node partial lists and therefore no locking will be required. + * + * This setting also determines + * + * A) The number of objects from per cpu partial slabs dumped to the + * per node list when we reach the limit. + * B) The number of objects in cpu partial slabs to extract from the + * per node list when we run out of per cpu objects. We only fetch 50% + * to keep some capacity around for frees. + */ + if (s->size >= PAGE_SIZE) + s->cpu_partial = 2; + else if (s->size >= 1024) + s->cpu_partial = 6; + else if (s->size >= 256) + s->cpu_partial = 13; + else + s->cpu_partial = 30; + s->refcount = 1; #ifdef CONFIG_NUMA s->remote_node_defrag_ratio = 1000; @@ -2652,23 +3086,22 @@ static void list_slab_objects(struct kmem_cache *s, struct page *page, /* * Attempt to free all partial slabs on a node. + * This is called from kmem_cache_close(). We must be the last thread + * using the cache and therefore we do not need to lock anymore. */ static void free_partial(struct kmem_cache *s, struct kmem_cache_node *n) { - unsigned long flags; struct page *page, *h; - spin_lock_irqsave(&n->list_lock, flags); list_for_each_entry_safe(page, h, &n->partial, lru) { if (!page->inuse) { - __remove_partial(n, page); + remove_partial(n, page); discard_slab(s, page); } else { list_slab_objects(s, page, "Objects remaining on kmem_cache_close()"); } } - spin_unlock_irqrestore(&n->list_lock, flags); } /* @@ -2702,6 +3135,7 @@ void kmem_cache_destroy(struct kmem_cache *s) s->refcount--; if (!s->refcount) { list_del(&s->list); + up_write(&slub_lock); if (kmem_cache_close(s)) { printk(KERN_ERR "SLUB %s: %s called for cache that " "still has objects.\n", s->name, __func__); @@ -2710,8 +3144,8 @@ void kmem_cache_destroy(struct kmem_cache *s) if (s->flags & SLAB_DESTROY_BY_RCU) rcu_barrier(); sysfs_slab_remove(s); - } - up_write(&slub_lock); + } else + up_write(&slub_lock); } EXPORT_SYMBOL(kmem_cache_destroy); @@ -2928,6 +3362,42 @@ size_t ksize(const void *object) } EXPORT_SYMBOL(ksize); +#ifdef CONFIG_SLUB_DEBUG +bool verify_mem_not_deleted(const void *x) +{ + struct page *page; + void *object = (void *)x; + unsigned long flags; + bool rv; + + if (unlikely(ZERO_OR_NULL_PTR(x))) + return false; + + local_irq_save(flags); + + page = virt_to_head_page(x); + if (unlikely(!PageSlab(page))) { + /* maybe it was from stack? */ + rv = true; + goto out_unlock; + } + + slab_lock(page); + if (on_freelist(page->slab, page, object)) { + object_err(page->slab, page, object, "Object is on free-list"); + rv = false; + } else { + rv = true; + } + slab_unlock(page); + +out_unlock: + local_irq_restore(flags); + return rv; +} +EXPORT_SYMBOL(verify_mem_not_deleted); +#endif + void kfree(const void *x) { struct page *page; @@ -2993,29 +3463,23 @@ int kmem_cache_shrink(struct kmem_cache *s) * list_lock. page->inuse here is the upper limit. */ list_for_each_entry_safe(page, t, &n->partial, lru) { - if (!page->inuse && slab_trylock(page)) { - /* - * Must hold slab lock here because slab_free - * may have freed the last object and be - * waiting to release the slab. - */ - __remove_partial(n, page); - slab_unlock(page); - discard_slab(s, page); - } else { - list_move(&page->lru, - slabs_by_inuse + page->inuse); - } + list_move(&page->lru, slabs_by_inuse + page->inuse); + if (!page->inuse) + n->nr_partial--; } /* * Rebuild the partial list with the slabs filled up most * first and the least used slabs at the end. */ - for (i = objects - 1; i >= 0; i--) + for (i = objects - 1; i > 0; i--) list_splice(slabs_by_inuse + i, n->partial.prev); spin_unlock_irqrestore(&n->list_lock, flags); + + /* Release empty slabs */ + list_for_each_entry_safe(page, t, slabs_by_inuse, lru) + discard_slab(s, page); } kfree(slabs_by_inuse); @@ -3588,12 +4052,9 @@ static int validate_slab(struct kmem_cache *s, struct page *page, static void validate_slab_slab(struct kmem_cache *s, struct page *page, unsigned long *map) { - if (slab_trylock(page)) { - validate_slab(s, page, map); - slab_unlock(page); - } else - printk(KERN_INFO "SLUB %s: Skipped busy slab 0x%p\n", - s->name, page); + slab_lock(page); + validate_slab(s, page, map); + slab_unlock(page); } static int validate_slab_node(struct kmem_cache *s, @@ -3974,6 +4435,7 @@ static ssize_t show_slab_objects(struct kmem_cache *s, for_each_possible_cpu(cpu) { struct kmem_cache_cpu *c = per_cpu_ptr(s->cpu_slab, cpu); + struct page *page; if (!c || c->node < 0) continue; @@ -3989,6 +4451,13 @@ static ssize_t show_slab_objects(struct kmem_cache *s, total += x; nodes[c->node] += x; } + page = c->partial; + + if (page) { + x = page->pobjects; + total += x; + nodes[c->node] += x; + } per_cpu[c->node]++; } } @@ -4058,7 +4527,7 @@ static int any_slab_objects(struct kmem_cache *s) #endif #define to_slab_attr(n) container_of(n, struct slab_attribute, attr) -#define to_slab(n) container_of(n, struct kmem_cache, kobj); +#define to_slab(n) container_of(n, struct kmem_cache, kobj) struct slab_attribute { struct attribute attr; @@ -4067,11 +4536,12 @@ struct slab_attribute { }; #define SLAB_ATTR_RO(_name) \ - static struct slab_attribute _name##_attr = __ATTR_RO(_name) + static struct slab_attribute _name##_attr = \ + __ATTR(_name, 0400, _name##_show, NULL) #define SLAB_ATTR(_name) \ static struct slab_attribute _name##_attr = \ - __ATTR(_name, 0644, _name##_show, _name##_store) + __ATTR(_name, 0600, _name##_show, _name##_store) static ssize_t slab_size_show(struct kmem_cache *s, char *buf) { @@ -4140,6 +4610,27 @@ static ssize_t min_partial_store(struct kmem_cache *s, const char *buf, } SLAB_ATTR(min_partial); +static ssize_t cpu_partial_show(struct kmem_cache *s, char *buf) +{ + return sprintf(buf, "%u\n", s->cpu_partial); +} + +static ssize_t cpu_partial_store(struct kmem_cache *s, const char *buf, + size_t length) +{ + unsigned long objects; + int err; + + err = strict_strtoul(buf, 10, &objects); + if (err) + return err; + + s->cpu_partial = objects; + flush_all(s); + return length; +} +SLAB_ATTR(cpu_partial); + static ssize_t ctor_show(struct kmem_cache *s, char *buf) { if (!s->ctor) @@ -4178,6 +4669,37 @@ static ssize_t objects_partial_show(struct kmem_cache *s, char *buf) } SLAB_ATTR_RO(objects_partial); +static ssize_t slabs_cpu_partial_show(struct kmem_cache *s, char *buf) +{ + int objects = 0; + int pages = 0; + int cpu; + int len; + + for_each_online_cpu(cpu) { + struct page *page = per_cpu_ptr(s->cpu_slab, cpu)->partial; + + if (page) { + pages += page->pages; + objects += page->pobjects; + } + } + + len = sprintf(buf, "%d(%d)", objects, pages); + +#ifdef CONFIG_SMP + for_each_online_cpu(cpu) { + struct page *page = per_cpu_ptr(s->cpu_slab, cpu) ->partial; + + if (page && len < PAGE_SIZE - 20) + len += sprintf(buf + len, " C%d=%d(%d)", cpu, + page->pobjects, page->pages); + } +#endif + return len + sprintf(buf + len, "\n"); +} +SLAB_ATTR_RO(slabs_cpu_partial); + static ssize_t reclaim_account_show(struct kmem_cache *s, char *buf) { return sprintf(buf, "%d\n", !!(s->flags & SLAB_RECLAIM_ACCOUNT)); @@ -4241,8 +4763,10 @@ static ssize_t sanity_checks_store(struct kmem_cache *s, const char *buf, size_t length) { s->flags &= ~SLAB_DEBUG_FREE; - if (buf[0] == '1') + if (buf[0] == '1') { + s->flags &= ~__CMPXCHG_DOUBLE; s->flags |= SLAB_DEBUG_FREE; + } return length; } SLAB_ATTR(sanity_checks); @@ -4256,8 +4780,10 @@ static ssize_t trace_store(struct kmem_cache *s, const char *buf, size_t length) { s->flags &= ~SLAB_TRACE; - if (buf[0] == '1') + if (buf[0] == '1') { + s->flags &= ~__CMPXCHG_DOUBLE; s->flags |= SLAB_TRACE; + } return length; } SLAB_ATTR(trace); @@ -4274,8 +4800,10 @@ static ssize_t red_zone_store(struct kmem_cache *s, return -EBUSY; s->flags &= ~SLAB_RED_ZONE; - if (buf[0] == '1') + if (buf[0] == '1') { + s->flags &= ~__CMPXCHG_DOUBLE; s->flags |= SLAB_RED_ZONE; + } calculate_sizes(s, -1); return length; } @@ -4293,8 +4821,10 @@ static ssize_t poison_store(struct kmem_cache *s, return -EBUSY; s->flags &= ~SLAB_POISON; - if (buf[0] == '1') + if (buf[0] == '1') { + s->flags &= ~__CMPXCHG_DOUBLE; s->flags |= SLAB_POISON; + } calculate_sizes(s, -1); return length; } @@ -4312,8 +4842,10 @@ static ssize_t store_user_store(struct kmem_cache *s, return -EBUSY; s->flags &= ~SLAB_STORE_USER; - if (buf[0] == '1') + if (buf[0] == '1') { + s->flags &= ~__CMPXCHG_DOUBLE; s->flags |= SLAB_STORE_USER; + } calculate_sizes(s, -1); return length; } @@ -4478,6 +5010,7 @@ STAT_ATTR(FREE_REMOVE_PARTIAL, free_remove_partial); STAT_ATTR(ALLOC_FROM_PARTIAL, alloc_from_partial); STAT_ATTR(ALLOC_SLAB, alloc_slab); STAT_ATTR(ALLOC_REFILL, alloc_refill); +STAT_ATTR(ALLOC_NODE_MISMATCH, alloc_node_mismatch); STAT_ATTR(FREE_SLAB, free_slab); STAT_ATTR(CPUSLAB_FLUSH, cpuslab_flush); STAT_ATTR(DEACTIVATE_FULL, deactivate_full); @@ -4485,7 +5018,12 @@ STAT_ATTR(DEACTIVATE_EMPTY, deactivate_empty); STAT_ATTR(DEACTIVATE_TO_HEAD, deactivate_to_head); STAT_ATTR(DEACTIVATE_TO_TAIL, deactivate_to_tail); STAT_ATTR(DEACTIVATE_REMOTE_FREES, deactivate_remote_frees); +STAT_ATTR(DEACTIVATE_BYPASS, deactivate_bypass); STAT_ATTR(ORDER_FALLBACK, order_fallback); +STAT_ATTR(CMPXCHG_DOUBLE_CPU_FAIL, cmpxchg_double_cpu_fail); +STAT_ATTR(CMPXCHG_DOUBLE_FAIL, cmpxchg_double_fail); +STAT_ATTR(CPU_PARTIAL_ALLOC, cpu_partial_alloc); +STAT_ATTR(CPU_PARTIAL_FREE, cpu_partial_free); #endif static struct attribute *slab_attrs[] = { @@ -4494,6 +5032,7 @@ static struct attribute *slab_attrs[] = { &objs_per_slab_attr.attr, &order_attr.attr, &min_partial_attr.attr, + &cpu_partial_attr.attr, &objects_attr.attr, &objects_partial_attr.attr, &partial_attr.attr, @@ -4506,6 +5045,7 @@ static struct attribute *slab_attrs[] = { &destroy_by_rcu_attr.attr, &shrink_attr.attr, &reserved_attr.attr, + &slabs_cpu_partial_attr.attr, #ifdef CONFIG_SLUB_DEBUG &total_objects_attr.attr, &slabs_attr.attr, @@ -4535,6 +5075,7 @@ static struct attribute *slab_attrs[] = { &alloc_from_partial_attr.attr, &alloc_slab_attr.attr, &alloc_refill_attr.attr, + &alloc_node_mismatch_attr.attr, &free_slab_attr.attr, &cpuslab_flush_attr.attr, &deactivate_full_attr.attr, @@ -4542,7 +5083,12 @@ static struct attribute *slab_attrs[] = { &deactivate_to_head_attr.attr, &deactivate_to_tail_attr.attr, &deactivate_remote_frees_attr.attr, + &deactivate_bypass_attr.attr, &order_fallback_attr.attr, + &cmpxchg_double_fail_attr.attr, + &cmpxchg_double_cpu_fail_attr.attr, + &cpu_partial_alloc_attr.attr, + &cpu_partial_free_attr.attr, #endif #ifdef CONFIG_FAILSLAB &failslab_attr.attr, @@ -4894,7 +5440,7 @@ static const struct file_operations proc_slabinfo_operations = { static int __init slab_proc_init(void) { - proc_create("slabinfo", S_IRUGO, NULL, &proc_slabinfo_operations); + proc_create("slabinfo", S_IRUSR, NULL, &proc_slabinfo_operations); return 0; } module_init(slab_proc_init); diff --git a/mm/sparse-vmemmap.c b/mm/sparse-vmemmap.c index 64b9840..1b7e22a 100644 --- a/mm/sparse-vmemmap.c +++ b/mm/sparse-vmemmap.c @@ -21,7 +21,6 @@ #include <linux/mmzone.h> #include <linux/bootmem.h> #include <linux/highmem.h> -#include <linux/module.h> #include <linux/slab.h> #include <linux/spinlock.h> #include <linux/vmalloc.h> diff --git a/mm/sparse.c b/mm/sparse.c index aa64b12..61d7cde 100644 --- a/mm/sparse.c +++ b/mm/sparse.c @@ -6,7 +6,7 @@ #include <linux/mmzone.h> #include <linux/bootmem.h> #include <linux/highmem.h> -#include <linux/module.h> +#include <linux/export.h> #include <linux/spinlock.h> #include <linux/vmalloc.h> #include "internal.h" @@ -40,7 +40,7 @@ static u8 section_to_node_table[NR_MEM_SECTIONS] __cacheline_aligned; static u16 section_to_node_table[NR_MEM_SECTIONS] __cacheline_aligned; #endif -int page_to_nid(struct page *page) +int page_to_nid(const struct page *page) { return section_to_node_table[page_to_section(page)]; } @@ -21,7 +21,7 @@ #include <linux/pagemap.h> #include <linux/pagevec.h> #include <linux/init.h> -#include <linux/module.h> +#include <linux/export.h> #include <linux/mm_inline.h> #include <linux/buffer_head.h> /* for try_to_release_page() */ #include <linux/percpu_counter.h> @@ -78,39 +78,22 @@ static void put_compound_page(struct page *page) { if (unlikely(PageTail(page))) { /* __split_huge_page_refcount can run under us */ - struct page *page_head = page->first_page; - smp_rmb(); - /* - * If PageTail is still set after smp_rmb() we can be sure - * that the page->first_page we read wasn't a dangling pointer. - * See __split_huge_page_refcount() smp_wmb(). - */ - if (likely(PageTail(page) && get_page_unless_zero(page_head))) { + struct page *page_head = compound_trans_head(page); + + if (likely(page != page_head && + get_page_unless_zero(page_head))) { unsigned long flags; /* - * Verify that our page_head wasn't converted - * to a a regular page before we got a - * reference on it. + * page_head wasn't a dangling pointer but it + * may not be a head page anymore by the time + * we obtain the lock. That is ok as long as it + * can't be freed from under us. */ - if (unlikely(!PageHead(page_head))) { - /* PageHead is cleared after PageTail */ - smp_rmb(); - VM_BUG_ON(PageTail(page)); - goto out_put_head; - } - /* - * Only run compound_lock on a valid PageHead, - * after having it pinned with - * get_page_unless_zero() above. - */ - smp_mb(); - /* page_head wasn't a dangling pointer */ flags = compound_lock_irqsave(page_head); if (unlikely(!PageTail(page))) { /* __split_huge_page_refcount run before us */ compound_unlock_irqrestore(page_head, flags); VM_BUG_ON(PageHead(page_head)); - out_put_head: if (put_page_testzero(page_head)) __put_single_page(page_head); out_put_single: @@ -121,16 +104,17 @@ static void put_compound_page(struct page *page) VM_BUG_ON(page_head != page->first_page); /* * We can release the refcount taken by - * get_page_unless_zero now that - * split_huge_page_refcount is blocked on the - * compound_lock. + * get_page_unless_zero() now that + * __split_huge_page_refcount() is blocked on + * the compound_lock. */ if (put_page_testzero(page_head)) VM_BUG_ON(1); /* __split_huge_page_refcount will wait now */ - VM_BUG_ON(atomic_read(&page->_count) <= 0); - atomic_dec(&page->_count); + VM_BUG_ON(page_mapcount(page) <= 0); + atomic_dec(&page->_mapcount); VM_BUG_ON(atomic_read(&page_head->_count) <= 0); + VM_BUG_ON(atomic_read(&page->_count) != 0); compound_unlock_irqrestore(page_head, flags); if (put_page_testzero(page_head)) { if (PageHead(page_head)) @@ -160,6 +144,45 @@ void put_page(struct page *page) } EXPORT_SYMBOL(put_page); +/* + * This function is exported but must not be called by anything other + * than get_page(). It implements the slow path of get_page(). + */ +bool __get_page_tail(struct page *page) +{ + /* + * This takes care of get_page() if run on a tail page + * returned by one of the get_user_pages/follow_page variants. + * get_user_pages/follow_page itself doesn't need the compound + * lock because it runs __get_page_tail_foll() under the + * proper PT lock that already serializes against + * split_huge_page(). + */ + unsigned long flags; + bool got = false; + struct page *page_head = compound_trans_head(page); + + if (likely(page != page_head && get_page_unless_zero(page_head))) { + /* + * page_head wasn't a dangling pointer but it + * may not be a head page anymore by the time + * we obtain the lock. That is ok as long as it + * can't be freed from under us. + */ + flags = compound_lock_irqsave(page_head); + /* here __split_huge_page_refcount won't run anymore */ + if (likely(PageTail(page))) { + __get_page_tail_foll(page, false); + got = true; + } + compound_unlock_irqrestore(page_head, flags); + if (unlikely(!got)) + put_page(page_head); + } + return got; +} +EXPORT_SYMBOL(__get_page_tail); + /** * put_pages_list() - release a list of pages * @pages: list of pages threaded on page->lru diff --git a/mm/swap_state.c b/mm/swap_state.c index 46680461..78cc4d1 100644 --- a/mm/swap_state.c +++ b/mm/swap_state.c @@ -6,7 +6,6 @@ * * Rewritten to use page cache, (C) 1998 Stephen Tweedie */ -#include <linux/module.h> #include <linux/mm.h> #include <linux/gfp.h> #include <linux/kernel_stat.h> diff --git a/mm/swapfile.c b/mm/swapfile.c index ff8dc1a..b1cd120 100644 --- a/mm/swapfile.c +++ b/mm/swapfile.c @@ -21,7 +21,6 @@ #include <linux/proc_fs.h> #include <linux/seq_file.h> #include <linux/init.h> -#include <linux/module.h> #include <linux/ksm.h> #include <linux/rmap.h> #include <linux/security.h> @@ -1617,7 +1616,7 @@ SYSCALL_DEFINE1(swapoff, const char __user *, specialfile) oom_score_adj = test_set_oom_score_adj(OOM_SCORE_ADJ_MAX); err = try_to_unuse(type); - test_set_oom_score_adj(oom_score_adj); + compare_swap_oom_score_adj(OOM_SCORE_ADJ_MAX, oom_score_adj); if (err) { /* @@ -1681,19 +1680,14 @@ out: } #ifdef CONFIG_PROC_FS -struct proc_swaps { - struct seq_file seq; - int event; -}; - static unsigned swaps_poll(struct file *file, poll_table *wait) { - struct proc_swaps *s = file->private_data; + struct seq_file *seq = file->private_data; poll_wait(file, &proc_poll_wait, wait); - if (s->event != atomic_read(&proc_poll_event)) { - s->event = atomic_read(&proc_poll_event); + if (seq->poll_event != atomic_read(&proc_poll_event)) { + seq->poll_event = atomic_read(&proc_poll_event); return POLLIN | POLLRDNORM | POLLERR | POLLPRI; } @@ -1783,24 +1777,16 @@ static const struct seq_operations swaps_op = { static int swaps_open(struct inode *inode, struct file *file) { - struct proc_swaps *s; + struct seq_file *seq; int ret; - s = kmalloc(sizeof(struct proc_swaps), GFP_KERNEL); - if (!s) - return -ENOMEM; - - file->private_data = s; - ret = seq_open(file, &swaps_op); - if (ret) { - kfree(s); + if (ret) return ret; - } - s->seq.private = s; - s->event = atomic_read(&proc_poll_event); - return ret; + seq = file->private_data; + seq->poll_event = atomic_read(&proc_poll_event); + return 0; } static const struct file_operations proc_swaps_operations = { @@ -1937,20 +1923,24 @@ static unsigned long read_swap_header(struct swap_info_struct *p, /* * Find out how many pages are allowed for a single swap - * device. There are two limiting factors: 1) the number of - * bits for the swap offset in the swp_entry_t type and - * 2) the number of bits in the a swap pte as defined by - * the different architectures. In order to find the - * largest possible bit mask a swap entry with swap type 0 + * device. There are three limiting factors: 1) the number + * of bits for the swap offset in the swp_entry_t type, and + * 2) the number of bits in the swap pte as defined by the + * the different architectures, and 3) the number of free bits + * in an exceptional radix_tree entry. In order to find the + * largest possible bit mask, a swap entry with swap type 0 * and swap offset ~0UL is created, encoded to a swap pte, - * decoded to a swp_entry_t again and finally the swap + * decoded to a swp_entry_t again, and finally the swap * offset is extracted. This will mask all the bits from * the initial ~0UL mask that can't be encoded in either * the swp_entry_t or the architecture definition of a - * swap pte. + * swap pte. Then the same is done for a radix_tree entry. */ maxpages = swp_offset(pte_to_swp_entry( - swp_entry_to_pte(swp_entry(0, ~0UL)))) + 1; + swp_entry_to_pte(swp_entry(0, ~0UL)))); + maxpages = swp_offset(radix_to_swp_entry( + swp_to_radix_entry(swp_entry(0, maxpages)))) + 1; + if (maxpages > swap_header->info.last_page) { maxpages = swap_header->info.last_page + 1; /* p->max is an unsigned int: don't overflow it */ diff --git a/mm/thrash.c b/mm/thrash.c index fabf2d0..57ad495 100644 --- a/mm/thrash.c +++ b/mm/thrash.c @@ -6,7 +6,7 @@ * Released under the GPL, see the file COPYING for details. * * Simple token based thrashing protection, using the algorithm - * described in: http://www.cs.wm.edu/~sjiang/token.pdf + * described in: http://www.cse.ohio-state.edu/hpcs/WWW/HTML/publications/abs05-1.html * * Sep 2006, Ashwin Chaugule <ashwin.chaugule@celunite.com> * Improved algorithm to pass token: @@ -29,9 +29,7 @@ static DEFINE_SPINLOCK(swap_token_lock); struct mm_struct *swap_token_mm; -struct mem_cgroup *swap_token_memcg; -static unsigned int global_faults; -static unsigned int last_aging; +static struct mem_cgroup *swap_token_memcg; #ifdef CONFIG_CGROUP_MEM_RES_CTLR static struct mem_cgroup *swap_token_memcg_from_mm(struct mm_struct *mm) @@ -55,6 +53,8 @@ void grab_swap_token(struct mm_struct *mm) { int current_interval; unsigned int old_prio = mm->token_priority; + static unsigned int global_faults; + static unsigned int last_aging; global_faults++; @@ -67,6 +67,17 @@ void grab_swap_token(struct mm_struct *mm) if (!swap_token_mm) goto replace_token; + /* + * Usually, we don't need priority aging because long interval faults + * makes priority decrease quickly. But there is one exception. If the + * token owner task is sleeping, it never make long interval faults. + * Thus, we need a priority aging mechanism instead. The requirements + * of priority aging are + * 1) An aging interval is reasonable enough long. Too short aging + * interval makes quick swap token lost and decrease performance. + * 2) The swap token owner task have to get priority aging even if + * it's under sleep. + */ if ((global_faults - last_aging) > TOKEN_AGING_INTERVAL) { swap_token_mm->token_priority /= 2; last_aging = global_faults; diff --git a/mm/truncate.c b/mm/truncate.c index e13f22e..632b15e 100644 --- a/mm/truncate.c +++ b/mm/truncate.c @@ -12,7 +12,7 @@ #include <linux/gfp.h> #include <linux/mm.h> #include <linux/swap.h> -#include <linux/module.h> +#include <linux/export.h> #include <linux/pagemap.h> #include <linux/highmem.h> #include <linux/pagevec.h> @@ -199,9 +199,6 @@ int invalidate_inode_page(struct page *page) * The first pass will remove most pages, so the search cost of the second pass * is low. * - * When looking at page->index outside the page lock we need to be careful to - * copy it into a local to avoid races (it could change at any time). - * * We pass down the cache-hot hint to the page freeing code. Even if the * mapping is large, it is probably the case that the final pages are the most * recently touched, and freeing happens in ascending file offset order. @@ -210,10 +207,10 @@ void truncate_inode_pages_range(struct address_space *mapping, loff_t lstart, loff_t lend) { const pgoff_t start = (lstart + PAGE_CACHE_SIZE-1) >> PAGE_CACHE_SHIFT; - pgoff_t end; const unsigned partial = lstart & (PAGE_CACHE_SIZE - 1); struct pagevec pvec; - pgoff_t next; + pgoff_t index; + pgoff_t end; int i; cleancache_flush_inode(mapping); @@ -224,24 +221,21 @@ void truncate_inode_pages_range(struct address_space *mapping, end = (lend >> PAGE_CACHE_SHIFT); pagevec_init(&pvec, 0); - next = start; - while (next <= end && - pagevec_lookup(&pvec, mapping, next, PAGEVEC_SIZE)) { + index = start; + while (index <= end && pagevec_lookup(&pvec, mapping, index, + min(end - index, (pgoff_t)PAGEVEC_SIZE - 1) + 1)) { mem_cgroup_uncharge_start(); for (i = 0; i < pagevec_count(&pvec); i++) { struct page *page = pvec.pages[i]; - pgoff_t page_index = page->index; - if (page_index > end) { - next = page_index; + /* We rely upon deletion not changing page->index */ + index = page->index; + if (index > end) break; - } - if (page_index > next) - next = page_index; - next++; if (!trylock_page(page)) continue; + WARN_ON(page->index != index); if (PageWriteback(page)) { unlock_page(page); continue; @@ -252,6 +246,7 @@ void truncate_inode_pages_range(struct address_space *mapping, pagevec_release(&pvec); mem_cgroup_uncharge_end(); cond_resched(); + index++; } if (partial) { @@ -264,16 +259,17 @@ void truncate_inode_pages_range(struct address_space *mapping, } } - next = start; + index = start; for ( ; ; ) { cond_resched(); - if (!pagevec_lookup(&pvec, mapping, next, PAGEVEC_SIZE)) { - if (next == start) + if (!pagevec_lookup(&pvec, mapping, index, + min(end - index, (pgoff_t)PAGEVEC_SIZE - 1) + 1)) { + if (index == start) break; - next = start; + index = start; continue; } - if (pvec.pages[0]->index > end) { + if (index == start && pvec.pages[0]->index > end) { pagevec_release(&pvec); break; } @@ -281,18 +277,20 @@ void truncate_inode_pages_range(struct address_space *mapping, for (i = 0; i < pagevec_count(&pvec); i++) { struct page *page = pvec.pages[i]; - if (page->index > end) + /* We rely upon deletion not changing page->index */ + index = page->index; + if (index > end) break; + lock_page(page); + WARN_ON(page->index != index); wait_on_page_writeback(page); truncate_inode_page(mapping, page); - if (page->index > next) - next = page->index; - next++; unlock_page(page); } pagevec_release(&pvec); mem_cgroup_uncharge_end(); + index++; } cleancache_flush_inode(mapping); } @@ -333,35 +331,34 @@ unsigned long invalidate_mapping_pages(struct address_space *mapping, pgoff_t start, pgoff_t end) { struct pagevec pvec; - pgoff_t next = start; + pgoff_t index = start; unsigned long ret; unsigned long count = 0; int i; + /* + * Note: this function may get called on a shmem/tmpfs mapping: + * pagevec_lookup() might then return 0 prematurely (because it + * got a gangful of swap entries); but it's hardly worth worrying + * about - it can rarely have anything to free from such a mapping + * (most pages are dirty), and already skips over any difficulties. + */ + pagevec_init(&pvec, 0); - while (next <= end && - pagevec_lookup(&pvec, mapping, next, PAGEVEC_SIZE)) { + while (index <= end && pagevec_lookup(&pvec, mapping, index, + min(end - index, (pgoff_t)PAGEVEC_SIZE - 1) + 1)) { mem_cgroup_uncharge_start(); for (i = 0; i < pagevec_count(&pvec); i++) { struct page *page = pvec.pages[i]; - pgoff_t index; - int lock_failed; - lock_failed = !trylock_page(page); - - /* - * We really shouldn't be looking at the ->index of an - * unlocked page. But we're not allowed to lock these - * pages. So we rely upon nobody altering the ->index - * of this (pinned-by-us) page. - */ + /* We rely upon deletion not changing page->index */ index = page->index; - if (index > next) - next = index; - next++; - if (lock_failed) - continue; + if (index > end) + break; + if (!trylock_page(page)) + continue; + WARN_ON(page->index != index); ret = invalidate_inode_page(page); unlock_page(page); /* @@ -371,12 +368,11 @@ unsigned long invalidate_mapping_pages(struct address_space *mapping, if (!ret) deactivate_page(page); count += ret; - if (next > end) - break; } pagevec_release(&pvec); mem_cgroup_uncharge_end(); cond_resched(); + index++; } return count; } @@ -442,37 +438,32 @@ int invalidate_inode_pages2_range(struct address_space *mapping, pgoff_t start, pgoff_t end) { struct pagevec pvec; - pgoff_t next; + pgoff_t index; int i; int ret = 0; int ret2 = 0; int did_range_unmap = 0; - int wrapped = 0; cleancache_flush_inode(mapping); pagevec_init(&pvec, 0); - next = start; - while (next <= end && !wrapped && - pagevec_lookup(&pvec, mapping, next, - min(end - next, (pgoff_t)PAGEVEC_SIZE - 1) + 1)) { + index = start; + while (index <= end && pagevec_lookup(&pvec, mapping, index, + min(end - index, (pgoff_t)PAGEVEC_SIZE - 1) + 1)) { mem_cgroup_uncharge_start(); for (i = 0; i < pagevec_count(&pvec); i++) { struct page *page = pvec.pages[i]; - pgoff_t page_index; + + /* We rely upon deletion not changing page->index */ + index = page->index; + if (index > end) + break; lock_page(page); + WARN_ON(page->index != index); if (page->mapping != mapping) { unlock_page(page); continue; } - page_index = page->index; - next = page_index + 1; - if (next == 0) - wrapped = 1; - if (page_index > end) { - unlock_page(page); - break; - } wait_on_page_writeback(page); if (page_mapped(page)) { if (!did_range_unmap) { @@ -480,9 +471,9 @@ int invalidate_inode_pages2_range(struct address_space *mapping, * Zap the rest of the file in one hit. */ unmap_mapping_range(mapping, - (loff_t)page_index<<PAGE_CACHE_SHIFT, - (loff_t)(end - page_index + 1) - << PAGE_CACHE_SHIFT, + (loff_t)index << PAGE_CACHE_SHIFT, + (loff_t)(1 + end - index) + << PAGE_CACHE_SHIFT, 0); did_range_unmap = 1; } else { @@ -490,8 +481,8 @@ int invalidate_inode_pages2_range(struct address_space *mapping, * Just zap this page */ unmap_mapping_range(mapping, - (loff_t)page_index<<PAGE_CACHE_SHIFT, - PAGE_CACHE_SIZE, 0); + (loff_t)index << PAGE_CACHE_SHIFT, + PAGE_CACHE_SIZE, 0); } } BUG_ON(page_mapped(page)); @@ -507,6 +498,7 @@ int invalidate_inode_pages2_range(struct address_space *mapping, pagevec_release(&pvec); mem_cgroup_uncharge_end(); cond_resched(); + index++; } cleancache_flush_inode(mapping); return ret; @@ -531,8 +523,8 @@ EXPORT_SYMBOL_GPL(invalidate_inode_pages2); /** * truncate_pagecache - unmap and remove pagecache that has been truncated * @inode: inode - * @old: old file offset - * @new: new file offset + * @oldsize: old file size + * @newsize: new file size * * inode's new i_size must already be written before truncate_pagecache * is called. @@ -544,9 +536,10 @@ EXPORT_SYMBOL_GPL(invalidate_inode_pages2); * situations such as writepage being called for a page that has already * had its underlying blocks deallocated. */ -void truncate_pagecache(struct inode *inode, loff_t old, loff_t new) +void truncate_pagecache(struct inode *inode, loff_t oldsize, loff_t newsize) { struct address_space *mapping = inode->i_mapping; + loff_t holebegin = round_up(newsize, PAGE_SIZE); /* * unmap_mapping_range is called twice, first simply for @@ -557,9 +550,9 @@ void truncate_pagecache(struct inode *inode, loff_t old, loff_t new) * truncate_inode_pages finishes, hence the second * unmap_mapping_range call must be made for correctness. */ - unmap_mapping_range(mapping, new + PAGE_SIZE - 1, 0, 1); - truncate_inode_pages(mapping, new); - unmap_mapping_range(mapping, new + PAGE_SIZE - 1, 0, 1); + unmap_mapping_range(mapping, holebegin, 0, 1); + truncate_inode_pages(mapping, newsize); + unmap_mapping_range(mapping, holebegin, 0, 1); } EXPORT_SYMBOL(truncate_pagecache); @@ -589,29 +582,31 @@ EXPORT_SYMBOL(truncate_setsize); /** * vmtruncate - unmap mappings "freed" by truncate() syscall * @inode: inode of the file used - * @offset: file offset to start truncating + * @newsize: file offset to start truncating * * This function is deprecated and truncate_setsize or truncate_pagecache * should be used instead, together with filesystem specific block truncation. */ -int vmtruncate(struct inode *inode, loff_t offset) +int vmtruncate(struct inode *inode, loff_t newsize) { int error; - error = inode_newsize_ok(inode, offset); + error = inode_newsize_ok(inode, newsize); if (error) return error; - truncate_setsize(inode, offset); + truncate_setsize(inode, newsize); if (inode->i_op->truncate) inode->i_op->truncate(inode); return 0; } EXPORT_SYMBOL(vmtruncate); -int vmtruncate_range(struct inode *inode, loff_t offset, loff_t end) +int vmtruncate_range(struct inode *inode, loff_t lstart, loff_t lend) { struct address_space *mapping = inode->i_mapping; + loff_t holebegin = round_up(lstart, PAGE_SIZE); + loff_t holelen = 1 + lend - holebegin; /* * If the underlying filesystem is not going to provide @@ -622,12 +617,11 @@ int vmtruncate_range(struct inode *inode, loff_t offset, loff_t end) return -ENOSYS; mutex_lock(&inode->i_mutex); - down_write(&inode->i_alloc_sem); - unmap_mapping_range(mapping, offset, (end - offset), 1); - inode->i_op->truncate_range(inode, offset, end); + inode_dio_wait(inode); + unmap_mapping_range(mapping, holebegin, holelen, 1); + inode->i_op->truncate_range(inode, lstart, lend); /* unmap again to remove racily COWed private pages */ - unmap_mapping_range(mapping, offset, (end - offset), 1); - up_write(&inode->i_alloc_sem); + unmap_mapping_range(mapping, holebegin, holelen, 1); mutex_unlock(&inode->i_mutex); return 0; @@ -1,7 +1,7 @@ #include <linux/mm.h> #include <linux/slab.h> #include <linux/string.h> -#include <linux/module.h> +#include <linux/export.h> #include <linux/err.h> #include <linux/sched.h> #include <asm/uaccess.h> diff --git a/mm/vmalloc.c b/mm/vmalloc.c index 1d34d75..3231bf3 100644 --- a/mm/vmalloc.c +++ b/mm/vmalloc.c @@ -26,7 +26,7 @@ #include <linux/rcupdate.h> #include <linux/pfn.h> #include <linux/kmemleak.h> -#include <asm/atomic.h> +#include <linux/atomic.h> #include <asm/uaccess.h> #include <asm/tlbflush.h> #include <asm/shmparam.h> @@ -452,13 +452,6 @@ overflow: return ERR_PTR(-EBUSY); } -static void rcu_free_va(struct rcu_head *head) -{ - struct vmap_area *va = container_of(head, struct vmap_area, rcu_head); - - kfree(va); -} - static void __free_vmap_area(struct vmap_area *va) { BUG_ON(RB_EMPTY_NODE(&va->rb_node)); @@ -491,7 +484,7 @@ static void __free_vmap_area(struct vmap_area *va) if (va->va_end > VMALLOC_START && va->va_end <= VMALLOC_END) vmap_area_pcpu_hole = max(vmap_area_pcpu_hole, va->va_end); - call_rcu(&va->rcu_head, rcu_free_va); + kfree_rcu(va, rcu_head); } /* @@ -732,9 +725,10 @@ static void free_unmap_vmap_area_addr(unsigned long addr) #define VMAP_BBMAP_BITS_MIN (VMAP_MAX_ALLOC*2) #define VMAP_MIN(x, y) ((x) < (y) ? (x) : (y)) /* can't use min() */ #define VMAP_MAX(x, y) ((x) > (y) ? (x) : (y)) /* can't use max() */ -#define VMAP_BBMAP_BITS VMAP_MIN(VMAP_BBMAP_BITS_MAX, \ - VMAP_MAX(VMAP_BBMAP_BITS_MIN, \ - VMALLOC_PAGES / NR_CPUS / 16)) +#define VMAP_BBMAP_BITS \ + VMAP_MIN(VMAP_BBMAP_BITS_MAX, \ + VMAP_MAX(VMAP_BBMAP_BITS_MIN, \ + VMALLOC_PAGES / roundup_pow_of_two(NR_CPUS) / 16)) #define VMAP_BLOCK_SIZE (VMAP_BBMAP_BITS * PAGE_SIZE) @@ -837,13 +831,6 @@ static struct vmap_block *new_vmap_block(gfp_t gfp_mask) return vb; } -static void rcu_free_vb(struct rcu_head *head) -{ - struct vmap_block *vb = container_of(head, struct vmap_block, rcu_head); - - kfree(vb); -} - static void free_vmap_block(struct vmap_block *vb) { struct vmap_block *tmp; @@ -856,7 +843,7 @@ static void free_vmap_block(struct vmap_block *vb) BUG_ON(tmp != vb); free_vmap_area_noflush(vb->va); - call_rcu(&vb->rcu_head, rcu_free_vb); + kfree_rcu(vb, rcu_head); } static void purge_fragmented_blocks(int cpu) @@ -1266,18 +1253,22 @@ EXPORT_SYMBOL_GPL(map_vm_area); DEFINE_RWLOCK(vmlist_lock); struct vm_struct *vmlist; -static void insert_vmalloc_vm(struct vm_struct *vm, struct vmap_area *va, +static void setup_vmalloc_vm(struct vm_struct *vm, struct vmap_area *va, unsigned long flags, void *caller) { - struct vm_struct *tmp, **p; - vm->flags = flags; vm->addr = (void *)va->va_start; vm->size = va->va_end - va->va_start; vm->caller = caller; va->private = vm; va->flags |= VM_VM_AREA; +} + +static void insert_vmalloc_vmlist(struct vm_struct *vm) +{ + struct vm_struct *tmp, **p; + vm->flags &= ~VM_UNLIST; write_lock(&vmlist_lock); for (p = &vmlist; (tmp = *p) != NULL; p = &tmp->next) { if (tmp->addr >= vm->addr) @@ -1288,6 +1279,13 @@ static void insert_vmalloc_vm(struct vm_struct *vm, struct vmap_area *va, write_unlock(&vmlist_lock); } +static void insert_vmalloc_vm(struct vm_struct *vm, struct vmap_area *va, + unsigned long flags, void *caller) +{ + setup_vmalloc_vm(vm, va, flags, caller); + insert_vmalloc_vmlist(vm); +} + static struct vm_struct *__get_vm_area_node(unsigned long size, unsigned long align, unsigned long flags, unsigned long start, unsigned long end, int node, gfp_t gfp_mask, void *caller) @@ -1326,7 +1324,18 @@ static struct vm_struct *__get_vm_area_node(unsigned long size, return NULL; } - insert_vmalloc_vm(area, va, flags, caller); + /* + * When this function is called from __vmalloc_node_range, + * we do not add vm_struct to vmlist here to avoid + * accessing uninitialized members of vm_struct such as + * pages and nr_pages fields. They will be set later. + * To distinguish it from others, we use a VM_UNLIST flag. + */ + if (flags & VM_UNLIST) + setup_vmalloc_vm(area, va, flags, caller); + else + insert_vmalloc_vm(area, va, flags, caller); + return area; } @@ -1394,17 +1403,20 @@ struct vm_struct *remove_vm_area(const void *addr) va = find_vmap_area((unsigned long)addr); if (va && va->flags & VM_VM_AREA) { struct vm_struct *vm = va->private; - struct vm_struct *tmp, **p; - /* - * remove from list and disallow access to this vm_struct - * before unmap. (address range confliction is maintained by - * vmap.) - */ - write_lock(&vmlist_lock); - for (p = &vmlist; (tmp = *p) != vm; p = &tmp->next) - ; - *p = tmp->next; - write_unlock(&vmlist_lock); + + if (!(vm->flags & VM_UNLIST)) { + struct vm_struct *tmp, **p; + /* + * remove from list and disallow access to + * this vm_struct before unmap. (address range + * confliction is maintained by vmap.) + */ + write_lock(&vmlist_lock); + for (p = &vmlist; (tmp = *p) != vm; p = &tmp->next) + ; + *p = tmp->next; + write_unlock(&vmlist_lock); + } vmap_debug_free_range(va->va_start, va->va_end); free_unmap_vmap_area(va); @@ -1581,8 +1593,8 @@ static void *__vmalloc_area_node(struct vm_struct *area, gfp_t gfp_mask, return area->addr; fail: - warn_alloc_failed(gfp_mask, order, "vmalloc: allocation failure, " - "allocated %ld of %ld bytes\n", + warn_alloc_failed(gfp_mask, order, + "vmalloc: allocation failure, allocated %ld of %ld bytes\n", (area->nr_pages*PAGE_SIZE), area->size); vfree(area->addr); return NULL; @@ -1613,17 +1625,22 @@ void *__vmalloc_node_range(unsigned long size, unsigned long align, size = PAGE_ALIGN(size); if (!size || (size >> PAGE_SHIFT) > totalram_pages) - return NULL; - - area = __get_vm_area_node(size, align, VM_ALLOC, start, end, node, - gfp_mask, caller); + goto fail; + area = __get_vm_area_node(size, align, VM_ALLOC | VM_UNLIST, + start, end, node, gfp_mask, caller); if (!area) - return NULL; + goto fail; addr = __vmalloc_area_node(area, gfp_mask, prot, node, caller); /* + * In this function, newly allocated vm_struct is not added + * to vmlist at __get_vm_area_node(). so, it is added here. + */ + insert_vmalloc_vmlist(area); + + /* * A ref_count = 3 is needed because the vm_struct and vmap_area * structures allocated in the __get_vm_area_node() function contain * references to the virtual address of the vmalloc'ed block. @@ -1631,6 +1648,12 @@ void *__vmalloc_node_range(unsigned long size, unsigned long align, kmemleak_alloc(addr, real_size, 3, gfp_mask); return addr; + +fail: + warn_alloc_failed(gfp_mask, 0, + "vmalloc: allocation failure: %lu bytes\n", + real_size); + return NULL; } /** @@ -2118,23 +2141,30 @@ void __attribute__((weak)) vmalloc_sync_all(void) static int f(pte_t *pte, pgtable_t table, unsigned long addr, void *data) { - /* apply_to_page_range() does all the hard work. */ + pte_t ***p = data; + + if (p) { + *(*p) = pte; + (*p)++; + } return 0; } /** * alloc_vm_area - allocate a range of kernel address space * @size: size of the area + * @ptes: returns the PTEs for the address space * * Returns: NULL on failure, vm_struct on success * * This function reserves a range of kernel address space, and * allocates pagetables to map that range. No actual mappings - * are created. If the kernel address space is not shared - * between processes, it syncs the pagetable across all - * processes. + * are created. + * + * If @ptes is non-NULL, pointers to the PTEs (in init_mm) + * allocated for the VM area are returned. */ -struct vm_struct *alloc_vm_area(size_t size) +struct vm_struct *alloc_vm_area(size_t size, pte_t **ptes) { struct vm_struct *area; @@ -2148,7 +2178,7 @@ struct vm_struct *alloc_vm_area(size_t size) * of kernel virtual address space and mapped into init_mm. */ if (apply_to_page_range(&init_mm, (unsigned long)area->addr, - area->size, f, NULL)) { + size, f, ptes ? &ptes : NULL)) { free_vm_area(area); return NULL; } diff --git a/mm/vmscan.c b/mm/vmscan.c index 5ed24b9..a1893c0 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -95,8 +95,6 @@ struct scan_control { /* Can pages be swapped as part of reclaim? */ int may_swap; - int swappiness; - int order; /* @@ -173,7 +171,8 @@ static unsigned long zone_nr_lru_pages(struct zone *zone, struct scan_control *sc, enum lru_list lru) { if (!scanning_global_lru(sc)) - return mem_cgroup_zone_nr_lru_pages(sc->mem_cgroup, zone, lru); + return mem_cgroup_zone_nr_lru_pages(sc->mem_cgroup, + zone_to_nid(zone), zone_idx(zone), BIT(lru)); return zone_page_state(zone, NR_LRU_BASE + lru); } @@ -250,49 +249,90 @@ unsigned long shrink_slab(struct shrink_control *shrink, unsigned long long delta; unsigned long total_scan; unsigned long max_pass; + int shrink_ret = 0; + long nr; + long new_nr; + long batch_size = shrinker->batch ? shrinker->batch + : SHRINK_BATCH; + + /* + * copy the current shrinker scan count into a local variable + * and zero it so that other concurrent shrinker invocations + * don't also do this scanning work. + */ + do { + nr = shrinker->nr; + } while (cmpxchg(&shrinker->nr, nr, 0) != nr); + total_scan = nr; max_pass = do_shrinker_shrink(shrinker, shrink, 0); delta = (4 * nr_pages_scanned) / shrinker->seeks; delta *= max_pass; do_div(delta, lru_pages + 1); - shrinker->nr += delta; - if (shrinker->nr < 0) { + total_scan += delta; + if (total_scan < 0) { printk(KERN_ERR "shrink_slab: %pF negative objects to " "delete nr=%ld\n", - shrinker->shrink, shrinker->nr); - shrinker->nr = max_pass; + shrinker->shrink, total_scan); + total_scan = max_pass; } /* + * We need to avoid excessive windup on filesystem shrinkers + * due to large numbers of GFP_NOFS allocations causing the + * shrinkers to return -1 all the time. This results in a large + * nr being built up so when a shrink that can do some work + * comes along it empties the entire cache due to nr >>> + * max_pass. This is bad for sustaining a working set in + * memory. + * + * Hence only allow the shrinker to scan the entire cache when + * a large delta change is calculated directly. + */ + if (delta < max_pass / 4) + total_scan = min(total_scan, max_pass / 2); + + /* * Avoid risking looping forever due to too large nr value: * never try to free more than twice the estimate number of * freeable entries. */ - if (shrinker->nr > max_pass * 2) - shrinker->nr = max_pass * 2; + if (total_scan > max_pass * 2) + total_scan = max_pass * 2; - total_scan = shrinker->nr; - shrinker->nr = 0; + trace_mm_shrink_slab_start(shrinker, shrink, nr, + nr_pages_scanned, lru_pages, + max_pass, delta, total_scan); - while (total_scan >= SHRINK_BATCH) { - long this_scan = SHRINK_BATCH; - int shrink_ret; + while (total_scan >= batch_size) { int nr_before; nr_before = do_shrinker_shrink(shrinker, shrink, 0); shrink_ret = do_shrinker_shrink(shrinker, shrink, - this_scan); + batch_size); if (shrink_ret == -1) break; if (shrink_ret < nr_before) ret += nr_before - shrink_ret; - count_vm_events(SLABS_SCANNED, this_scan); - total_scan -= this_scan; + count_vm_events(SLABS_SCANNED, batch_size); + total_scan -= batch_size; cond_resched(); } - shrinker->nr += total_scan; + /* + * move the unused scan count back into the shrinker in a + * manner that handles concurrent updates. If we exhausted the + * scan, there is no need to do an update. + */ + do { + nr = shrinker->nr; + new_nr = total_scan + nr; + if (total_scan <= 0) + break; + } while (cmpxchg(&shrinker->nr, nr, new_nr) != nr); + + trace_mm_shrink_slab_end(shrinker, shrink_ret, nr, new_nr); } up_read(&shrinker_rwsem); out: @@ -455,15 +495,6 @@ static pageout_t pageout(struct page *page, struct address_space *mapping, return PAGE_ACTIVATE; } - /* - * Wait on writeback if requested to. This happens when - * direct reclaiming a large contiguous area and the - * first attempt to free a range of pages fails. - */ - if (PageWriteback(page) && - (sc->reclaim_mode & RECLAIM_MODE_SYNC)) - wait_on_page_writeback(page); - if (!PageWriteback(page)) { /* synchronous write or broken a_ops? */ ClearPageReclaim(page); @@ -602,13 +633,14 @@ redo: lru = LRU_UNEVICTABLE; add_page_to_unevictable_list(page); /* - * When racing with an mlock clearing (page is - * unlocked), make sure that if the other thread does - * not observe our setting of PG_lru and fails - * isolation, we see PG_mlocked cleared below and move + * When racing with an mlock or AS_UNEVICTABLE clearing + * (page is unlocked) make sure that if the other thread + * does not observe our setting of PG_lru and fails + * isolation/check_move_unevictable_page, + * we see PG_mlocked/AS_UNEVICTABLE cleared below and move * the page back to the evictable list. * - * The other side is TestClearPageMlocked(). + * The other side is TestClearPageMlocked() or shmem_lock(). */ smp_mb(); } @@ -719,7 +751,10 @@ static noinline_for_stack void free_page_list(struct list_head *free_pages) */ static unsigned long shrink_page_list(struct list_head *page_list, struct zone *zone, - struct scan_control *sc) + struct scan_control *sc, + int priority, + unsigned long *ret_nr_dirty, + unsigned long *ret_nr_writeback) { LIST_HEAD(ret_pages); LIST_HEAD(free_pages); @@ -727,6 +762,7 @@ static unsigned long shrink_page_list(struct list_head *page_list, unsigned long nr_dirty = 0; unsigned long nr_congested = 0; unsigned long nr_reclaimed = 0; + unsigned long nr_writeback = 0; cond_resched(); @@ -763,13 +799,12 @@ static unsigned long shrink_page_list(struct list_head *page_list, (PageSwapCache(page) && (sc->gfp_mask & __GFP_IO)); if (PageWriteback(page)) { + nr_writeback++; /* - * Synchronous reclaim is performed in two passes, - * first an asynchronous pass over the list to - * start parallel writeback, and a second synchronous - * pass to wait for the IO to complete. Wait here - * for any page for which writeback has already - * started. + * Synchronous reclaim cannot queue pages for + * writeback due to the possibility of stack overflow + * but if it encounters a page under writeback, wait + * for the IO to complete. */ if ((sc->reclaim_mode & RECLAIM_MODE_SYNC) && may_enter_fs) @@ -825,6 +860,25 @@ static unsigned long shrink_page_list(struct list_head *page_list, if (PageDirty(page)) { nr_dirty++; + /* + * Only kswapd can writeback filesystem pages to + * avoid risk of stack overflow but do not writeback + * unless under significant pressure. + */ + if (page_is_file_cache(page) && + (!current_is_kswapd() || priority >= DEF_PRIORITY - 2)) { + /* + * Immediately reclaim when written back. + * Similar in principal to deactivate_page() + * except we already have the page isolated + * and know it's dirty + */ + inc_zone_page_state(page, NR_VMSCAN_IMMEDIATE); + SetPageReclaim(page); + + goto keep_locked; + } + if (references == PAGEREF_RECLAIM_CLEAN) goto keep_locked; if (!may_enter_fs) @@ -959,6 +1013,8 @@ keep_lumpy: list_splice(&ret_pages, page_list); count_vm_events(PGACTIVATE, pgactivate); + *ret_nr_dirty += nr_dirty; + *ret_nr_writeback += nr_writeback; return nr_reclaimed; } @@ -972,23 +1028,27 @@ keep_lumpy: * * returns 0 on success, -ve errno on failure. */ -int __isolate_lru_page(struct page *page, int mode, int file) +int __isolate_lru_page(struct page *page, isolate_mode_t mode, int file) { + bool all_lru_mode; int ret = -EINVAL; /* Only take pages on the LRU. */ if (!PageLRU(page)) return ret; + all_lru_mode = (mode & (ISOLATE_ACTIVE|ISOLATE_INACTIVE)) == + (ISOLATE_ACTIVE|ISOLATE_INACTIVE); + /* * When checking the active state, we need to be sure we are * dealing with comparible boolean values. Take the logical not * of each. */ - if (mode != ISOLATE_BOTH && (!PageActive(page) != !mode)) + if (!all_lru_mode && !PageActive(page) != !(mode & ISOLATE_ACTIVE)) return ret; - if (mode != ISOLATE_BOTH && page_is_file_cache(page) != file) + if (!all_lru_mode && !!page_is_file_cache(page) != file) return ret; /* @@ -1001,6 +1061,12 @@ int __isolate_lru_page(struct page *page, int mode, int file) ret = -EBUSY; + if ((mode & ISOLATE_CLEAN) && (PageDirty(page) || PageWriteback(page))) + return ret; + + if ((mode & ISOLATE_UNMAPPED) && page_mapped(page)) + return ret; + if (likely(get_page_unless_zero(page))) { /* * Be careful not to clear PageLRU until after we're @@ -1036,7 +1102,8 @@ int __isolate_lru_page(struct page *page, int mode, int file) */ static unsigned long isolate_lru_pages(unsigned long nr_to_scan, struct list_head *src, struct list_head *dst, - unsigned long *scanned, int order, int mode, int file) + unsigned long *scanned, int order, isolate_mode_t mode, + int file) { unsigned long nr_taken = 0; unsigned long nr_lumpy_taken = 0; @@ -1161,8 +1228,8 @@ static unsigned long isolate_lru_pages(unsigned long nr_to_scan, static unsigned long isolate_pages_global(unsigned long nr, struct list_head *dst, unsigned long *scanned, int order, - int mode, struct zone *z, - int active, int file) + isolate_mode_t mode, + struct zone *z, int active, int file) { int lru = LRU_BASE; if (active) @@ -1354,7 +1421,7 @@ static noinline_for_stack void update_isolated_counts(struct zone *zone, } /* - * Returns true if the caller should wait to clean dirty/writeback pages. + * Returns true if a direct reclaim should wait on pages under writeback. * * If we are direct reclaiming for contiguous pages and we do not reclaim * everything in the list, try again and wait for writeback IO to complete. @@ -1376,7 +1443,7 @@ static inline bool should_reclaim_stall(unsigned long nr_taken, if (sc->reclaim_mode & RECLAIM_MODE_SINGLE) return false; - /* If we have relaimed everything on the isolated list, no stall */ + /* If we have reclaimed everything on the isolated list, no stall */ if (nr_freed == nr_taken) return false; @@ -1408,6 +1475,9 @@ shrink_inactive_list(unsigned long nr_to_scan, struct zone *zone, unsigned long nr_taken; unsigned long nr_anon; unsigned long nr_file; + unsigned long nr_dirty = 0; + unsigned long nr_writeback = 0; + isolate_mode_t reclaim_mode = ISOLATE_INACTIVE; while (unlikely(too_many_isolated(zone, file, sc))) { congestion_wait(BLK_RW_ASYNC, HZ/10); @@ -1418,15 +1488,21 @@ shrink_inactive_list(unsigned long nr_to_scan, struct zone *zone, } set_reclaim_mode(priority, sc, false); + if (sc->reclaim_mode & RECLAIM_MODE_LUMPYRECLAIM) + reclaim_mode |= ISOLATE_ACTIVE; + lru_add_drain(); + + if (!sc->may_unmap) + reclaim_mode |= ISOLATE_UNMAPPED; + if (!sc->may_writepage) + reclaim_mode |= ISOLATE_CLEAN; + spin_lock_irq(&zone->lru_lock); if (scanning_global_lru(sc)) { - nr_taken = isolate_pages_global(nr_to_scan, - &page_list, &nr_scanned, sc->order, - sc->reclaim_mode & RECLAIM_MODE_LUMPYRECLAIM ? - ISOLATE_BOTH : ISOLATE_INACTIVE, - zone, 0, file); + nr_taken = isolate_pages_global(nr_to_scan, &page_list, + &nr_scanned, sc->order, reclaim_mode, zone, 0, file); zone->pages_scanned += nr_scanned; if (current_is_kswapd()) __count_zone_vm_events(PGSCAN_KSWAPD, zone, @@ -1435,12 +1511,9 @@ shrink_inactive_list(unsigned long nr_to_scan, struct zone *zone, __count_zone_vm_events(PGSCAN_DIRECT, zone, nr_scanned); } else { - nr_taken = mem_cgroup_isolate_pages(nr_to_scan, - &page_list, &nr_scanned, sc->order, - sc->reclaim_mode & RECLAIM_MODE_LUMPYRECLAIM ? - ISOLATE_BOTH : ISOLATE_INACTIVE, - zone, sc->mem_cgroup, - 0, file); + nr_taken = mem_cgroup_isolate_pages(nr_to_scan, &page_list, + &nr_scanned, sc->order, reclaim_mode, zone, + sc->mem_cgroup, 0, file); /* * mem_cgroup_isolate_pages() keeps track of * scanned pages on its own. @@ -1456,12 +1529,14 @@ shrink_inactive_list(unsigned long nr_to_scan, struct zone *zone, spin_unlock_irq(&zone->lru_lock); - nr_reclaimed = shrink_page_list(&page_list, zone, sc); + nr_reclaimed = shrink_page_list(&page_list, zone, sc, priority, + &nr_dirty, &nr_writeback); /* Check if we should syncronously wait for writeback */ if (should_reclaim_stall(nr_taken, nr_reclaimed, priority, sc)) { set_reclaim_mode(priority, sc, true); - nr_reclaimed += shrink_page_list(&page_list, zone, sc); + nr_reclaimed += shrink_page_list(&page_list, zone, sc, + priority, &nr_dirty, &nr_writeback); } local_irq_disable(); @@ -1471,6 +1546,32 @@ shrink_inactive_list(unsigned long nr_to_scan, struct zone *zone, putback_lru_pages(zone, sc, nr_anon, nr_file, &page_list); + /* + * If reclaim is isolating dirty pages under writeback, it implies + * that the long-lived page allocation rate is exceeding the page + * laundering rate. Either the global limits are not being effective + * at throttling processes due to the page distribution throughout + * zones or there is heavy usage of a slow backing device. The + * only option is to throttle from reclaim context which is not ideal + * as there is no guarantee the dirtying process is throttled in the + * same way balance_dirty_pages() manages. + * + * This scales the number of dirty pages that must be under writeback + * before throttling depending on priority. It is a simple backoff + * function that has the most effect in the range DEF_PRIORITY to + * DEF_PRIORITY-2 which is the priority reclaim is considered to be + * in trouble and reclaim is considered to be in trouble. + * + * DEF_PRIORITY 100% isolated pages must be PageWriteback to throttle + * DEF_PRIORITY-1 50% must be PageWriteback + * DEF_PRIORITY-2 25% must be PageWriteback, kswapd in trouble + * ... + * DEF_PRIORITY-6 For SWAP_CLUSTER_MAX isolated pages, throttle if any + * isolated page is PageWriteback + */ + if (nr_writeback && nr_writeback >= (nr_taken >> (DEF_PRIORITY-priority))) + wait_iff_congested(zone, BLK_RW_ASYNC, HZ/10); + trace_mm_vmscan_lru_shrink_inactive(zone->zone_pgdat->node_id, zone_idx(zone), nr_scanned, nr_reclaimed, @@ -1542,19 +1643,26 @@ static void shrink_active_list(unsigned long nr_pages, struct zone *zone, struct page *page; struct zone_reclaim_stat *reclaim_stat = get_reclaim_stat(zone, sc); unsigned long nr_rotated = 0; + isolate_mode_t reclaim_mode = ISOLATE_ACTIVE; lru_add_drain(); + + if (!sc->may_unmap) + reclaim_mode |= ISOLATE_UNMAPPED; + if (!sc->may_writepage) + reclaim_mode |= ISOLATE_CLEAN; + spin_lock_irq(&zone->lru_lock); if (scanning_global_lru(sc)) { nr_taken = isolate_pages_global(nr_pages, &l_hold, &pgscanned, sc->order, - ISOLATE_ACTIVE, zone, + reclaim_mode, zone, 1, file); zone->pages_scanned += pgscanned; } else { nr_taken = mem_cgroup_isolate_pages(nr_pages, &l_hold, &pgscanned, sc->order, - ISOLATE_ACTIVE, zone, + reclaim_mode, zone, sc->mem_cgroup, 1, file); /* * mem_cgroup_isolate_pages() keeps track of @@ -1659,7 +1767,7 @@ static int inactive_anon_is_low(struct zone *zone, struct scan_control *sc) if (scanning_global_lru(sc)) low = inactive_anon_is_low_global(zone); else - low = mem_cgroup_inactive_anon_is_low(sc->mem_cgroup); + low = mem_cgroup_inactive_anon_is_low(sc->mem_cgroup, zone); return low; } #else @@ -1702,7 +1810,7 @@ static int inactive_file_is_low(struct zone *zone, struct scan_control *sc) if (scanning_global_lru(sc)) low = inactive_file_is_low_global(zone); else - low = mem_cgroup_inactive_file_is_low(sc->mem_cgroup); + low = mem_cgroup_inactive_file_is_low(sc->mem_cgroup, zone); return low; } @@ -1729,6 +1837,13 @@ static unsigned long shrink_list(enum lru_list lru, unsigned long nr_to_scan, return shrink_inactive_list(nr_to_scan, zone, sc, priority, file); } +static int vmscan_swappiness(struct scan_control *sc) +{ + if (scanning_global_lru(sc)) + return vm_swappiness; + return mem_cgroup_swappiness(sc->mem_cgroup); +} + /* * Determine how aggressively the anon and file LRU lists should be * scanned. The relative value of each set of LRU lists is determined @@ -1747,22 +1862,22 @@ static void get_scan_count(struct zone *zone, struct scan_control *sc, u64 fraction[2], denominator; enum lru_list l; int noswap = 0; - int force_scan = 0; - - - anon = zone_nr_lru_pages(zone, sc, LRU_ACTIVE_ANON) + - zone_nr_lru_pages(zone, sc, LRU_INACTIVE_ANON); - file = zone_nr_lru_pages(zone, sc, LRU_ACTIVE_FILE) + - zone_nr_lru_pages(zone, sc, LRU_INACTIVE_FILE); + bool force_scan = false; - if (((anon + file) >> priority) < SWAP_CLUSTER_MAX) { - /* kswapd does zone balancing and need to scan this zone */ - if (scanning_global_lru(sc) && current_is_kswapd()) - force_scan = 1; - /* memcg may have small limit and need to avoid priority drop */ - if (!scanning_global_lru(sc)) - force_scan = 1; - } + /* + * If the zone or memcg is small, nr[l] can be 0. This + * results in no scanning on this priority and a potential + * priority drop. Global direct reclaim can go to the next + * zone and tends to have no problems. Global kswapd is for + * zone balancing and it needs to scan a minimum amount. When + * reclaiming for a memcg, a priority drop can cause high + * latencies, so it's better to scan a minimum amount there as + * well. + */ + if (scanning_global_lru(sc) && current_is_kswapd()) + force_scan = true; + if (!scanning_global_lru(sc)) + force_scan = true; /* If we have no swap space, do not bother scanning anon pages. */ if (!sc->may_swap || (nr_swap_pages <= 0)) { @@ -1773,6 +1888,11 @@ static void get_scan_count(struct zone *zone, struct scan_control *sc, goto out; } + anon = zone_nr_lru_pages(zone, sc, LRU_ACTIVE_ANON) + + zone_nr_lru_pages(zone, sc, LRU_INACTIVE_ANON); + file = zone_nr_lru_pages(zone, sc, LRU_ACTIVE_FILE) + + zone_nr_lru_pages(zone, sc, LRU_INACTIVE_FILE); + if (scanning_global_lru(sc)) { free = zone_page_state(zone, NR_FREE_PAGES); /* If we have very few page cache pages, @@ -1789,8 +1909,8 @@ static void get_scan_count(struct zone *zone, struct scan_control *sc, * With swappiness at 100, anonymous and file have the same priority. * This scanning priority is essentially the inverse of IO cost. */ - anon_prio = sc->swappiness; - file_prio = 200 - sc->swappiness; + anon_prio = vmscan_swappiness(sc); + file_prio = 200 - vmscan_swappiness(sc); /* * OK, so we have swap space and a fair amount of page cache @@ -1837,23 +1957,9 @@ out: scan = zone_nr_lru_pages(zone, sc, l); if (priority || noswap) { scan >>= priority; - scan = div64_u64(scan * fraction[file], denominator); - } - - /* - * If zone is small or memcg is small, nr[l] can be 0. - * This results no-scan on this priority and priority drop down. - * For global direct reclaim, it can visit next zone and tend - * not to have problems. For global kswapd, it's for zone - * balancing and it need to scan a small amounts. When using - * memcg, priority drop can cause big latency. So, it's better - * to scan small amount. See may_noscan above. - */ - if (!scan && force_scan) { - if (file) - scan = SWAP_CLUSTER_MAX; - else if (!noswap) + if (!scan && force_scan) scan = SWAP_CLUSTER_MAX; + scan = div64_u64(scan * fraction[file], denominator); } nr[l] = scan; } @@ -1933,12 +2039,14 @@ static void shrink_zone(int priority, struct zone *zone, enum lru_list l; unsigned long nr_reclaimed, nr_scanned; unsigned long nr_to_reclaim = sc->nr_to_reclaim; + struct blk_plug plug; restart: nr_reclaimed = 0; nr_scanned = sc->nr_scanned; get_scan_count(zone, sc, nr, priority); + blk_start_plug(&plug); while (nr[LRU_INACTIVE_ANON] || nr[LRU_ACTIVE_FILE] || nr[LRU_INACTIVE_FILE]) { for_each_evictable_lru(l) { @@ -1962,6 +2070,7 @@ restart: if (nr_reclaimed >= nr_to_reclaim && priority < DEF_PRIORITY) break; } + blk_finish_plug(&plug); sc->nr_reclaimed += nr_reclaimed; /* @@ -1994,14 +2103,19 @@ restart: * * If a zone is deemed to be full of pinned pages then just give it a light * scan then give up on it. + * + * This function returns true if a zone is being reclaimed for a costly + * high-order allocation and compaction is either ready to begin or deferred. + * This indicates to the caller that it should retry the allocation or fail. */ -static void shrink_zones(int priority, struct zonelist *zonelist, +static bool shrink_zones(int priority, struct zonelist *zonelist, struct scan_control *sc) { struct zoneref *z; struct zone *zone; unsigned long nr_soft_reclaimed; unsigned long nr_soft_scanned; + bool should_abort_reclaim = false; for_each_zone_zonelist_nodemask(zone, z, zonelist, gfp_zone(sc->gfp_mask), sc->nodemask) { @@ -2016,6 +2130,23 @@ static void shrink_zones(int priority, struct zonelist *zonelist, continue; if (zone->all_unreclaimable && priority != DEF_PRIORITY) continue; /* Let kswapd poll it */ + if (COMPACTION_BUILD) { + /* + * If we already have plenty of memory free for + * compaction in this zone, don't free any more. + * Even though compaction is invoked for any + * non-zero order, only frequent costly order + * reclamation is disruptive enough to become a + * noticable problem, like transparent huge page + * allocations. + */ + if (sc->order > PAGE_ALLOC_COSTLY_ORDER && + (compaction_suitable(zone, sc->order) || + compaction_deferred(zone))) { + should_abort_reclaim = true; + continue; + } + } /* * This steals pages from memory cgroups over softlimit * and returns the number of reclaimed pages and @@ -2033,6 +2164,8 @@ static void shrink_zones(int priority, struct zonelist *zonelist, shrink_zone(priority, zone, sc); } + + return should_abort_reclaim; } static bool zone_reclaimable(struct zone *zone) @@ -2097,7 +2230,9 @@ static unsigned long do_try_to_free_pages(struct zonelist *zonelist, sc->nr_scanned = 0; if (!priority) disable_swap_token(sc->mem_cgroup); - shrink_zones(priority, zonelist, sc); + if (shrink_zones(priority, zonelist, sc)) + break; + /* * Don't shrink slabs when reclaiming memory from * over limit cgroups @@ -2131,7 +2266,8 @@ static unsigned long do_try_to_free_pages(struct zonelist *zonelist, */ writeback_threshold = sc->nr_to_reclaim + sc->nr_to_reclaim / 2; if (total_scanned > writeback_threshold) { - wakeup_flusher_threads(laptop_mode ? 0 : total_scanned); + wakeup_flusher_threads(laptop_mode ? 0 : total_scanned, + WB_REASON_TRY_TO_FREE_PAGES); sc->may_writepage = 1; } @@ -2179,7 +2315,6 @@ unsigned long try_to_free_pages(struct zonelist *zonelist, int order, .nr_to_reclaim = SWAP_CLUSTER_MAX, .may_unmap = 1, .may_swap = 1, - .swappiness = vm_swappiness, .order = order, .mem_cgroup = NULL, .nodemask = nodemask, @@ -2203,7 +2338,6 @@ unsigned long try_to_free_pages(struct zonelist *zonelist, int order, unsigned long mem_cgroup_shrink_node_zone(struct mem_cgroup *mem, gfp_t gfp_mask, bool noswap, - unsigned int swappiness, struct zone *zone, unsigned long *nr_scanned) { @@ -2213,7 +2347,6 @@ unsigned long mem_cgroup_shrink_node_zone(struct mem_cgroup *mem, .may_writepage = !laptop_mode, .may_unmap = 1, .may_swap = !noswap, - .swappiness = swappiness, .order = 0, .mem_cgroup = mem, }; @@ -2242,8 +2375,7 @@ unsigned long mem_cgroup_shrink_node_zone(struct mem_cgroup *mem, unsigned long try_to_free_mem_cgroup_pages(struct mem_cgroup *mem_cont, gfp_t gfp_mask, - bool noswap, - unsigned int swappiness) + bool noswap) { struct zonelist *zonelist; unsigned long nr_reclaimed; @@ -2253,7 +2385,6 @@ unsigned long try_to_free_mem_cgroup_pages(struct mem_cgroup *mem_cont, .may_unmap = 1, .may_swap = !noswap, .nr_to_reclaim = SWAP_CLUSTER_MAX, - .swappiness = swappiness, .order = 0, .mem_cgroup = mem_cont, .nodemask = NULL, /* we don't care the placement */ @@ -2310,7 +2441,8 @@ static bool pgdat_balanced(pg_data_t *pgdat, unsigned long balanced_pages, for (i = 0; i <= classzone_idx; i++) present_pages += pgdat->node_zones[i].present_pages; - return balanced_pages > (present_pages >> 2); + /* A special case here: if zone has no page, we think it's balanced */ + return balanced_pages >= (present_pages >> 2); } /* is kswapd sleeping prematurely? */ @@ -2403,7 +2535,6 @@ static unsigned long balance_pgdat(pg_data_t *pgdat, int order, * we want to put equal scanning pressure on each zone. */ .nr_to_reclaim = ULONG_MAX, - .swappiness = vm_swappiness, .order = order, .mem_cgroup = NULL, }; @@ -2452,6 +2583,9 @@ loop_again: high_wmark_pages(zone), 0, 0)) { end_zone = i; break; + } else { + /* If balanced, clear the congested flag */ + zone_clear_flag(zone, ZONE_CONGESTED); } } if (i < 0) @@ -2642,6 +2776,8 @@ out: /* If balanced, clear the congested flag */ zone_clear_flag(zone, ZONE_CONGESTED); + if (i <= *classzone_idx) + balanced += zone->present_pages; } } @@ -2715,7 +2851,9 @@ static void kswapd_try_to_sleep(pg_data_t *pgdat, int order, int classzone_idx) static int kswapd(void *p) { unsigned long order, new_order; + unsigned balanced_order; int classzone_idx, new_classzone_idx; + int balanced_classzone_idx; pg_data_t *pgdat = (pg_data_t*)p; struct task_struct *tsk = current; @@ -2746,7 +2884,9 @@ static int kswapd(void *p) set_freezable(); order = new_order = 0; + balanced_order = 0; classzone_idx = new_classzone_idx = pgdat->nr_zones - 1; + balanced_classzone_idx = classzone_idx; for ( ; ; ) { int ret; @@ -2755,7 +2895,8 @@ static int kswapd(void *p) * new request of a similar or harder type will succeed soon * so consider going to sleep on the basis we reclaimed at */ - if (classzone_idx >= new_classzone_idx && order == new_order) { + if (balanced_classzone_idx >= new_classzone_idx && + balanced_order == new_order) { new_order = pgdat->kswapd_max_order; new_classzone_idx = pgdat->classzone_idx; pgdat->kswapd_max_order = 0; @@ -2770,9 +2911,12 @@ static int kswapd(void *p) order = new_order; classzone_idx = new_classzone_idx; } else { - kswapd_try_to_sleep(pgdat, order, classzone_idx); + kswapd_try_to_sleep(pgdat, balanced_order, + balanced_classzone_idx); order = pgdat->kswapd_max_order; classzone_idx = pgdat->classzone_idx; + new_order = order; + new_classzone_idx = classzone_idx; pgdat->kswapd_max_order = 0; pgdat->classzone_idx = pgdat->nr_zones - 1; } @@ -2787,7 +2931,9 @@ static int kswapd(void *p) */ if (!ret) { trace_mm_vmscan_kswapd_wake(pgdat->node_id, order); - order = balance_pgdat(pgdat, order, &classzone_idx); + balanced_classzone_idx = classzone_idx; + balanced_order = balance_pgdat(pgdat, order, + &balanced_classzone_idx); } } return 0; @@ -2873,7 +3019,6 @@ unsigned long shrink_all_memory(unsigned long nr_to_reclaim) .may_writepage = 1, .nr_to_reclaim = nr_to_reclaim, .hibernation_mode = 1, - .swappiness = vm_swappiness, .order = 0, }; struct shrink_control shrink = { @@ -3060,7 +3205,6 @@ static int __zone_reclaim(struct zone *zone, gfp_t gfp_mask, unsigned int order) .nr_to_reclaim = max_t(unsigned long, nr_pages, SWAP_CLUSTER_MAX), .gfp_mask = gfp_mask, - .swappiness = vm_swappiness, .order = order, }; struct shrink_control shrink = { @@ -3301,66 +3445,12 @@ void scan_mapping_unevictable_pages(struct address_space *mapping) } -/** - * scan_zone_unevictable_pages - check unevictable list for evictable pages - * @zone - zone of which to scan the unevictable list - * - * Scan @zone's unevictable LRU lists to check for pages that have become - * evictable. Move those that have to @zone's inactive list where they - * become candidates for reclaim, unless shrink_inactive_zone() decides - * to reactivate them. Pages that are still unevictable are rotated - * back onto @zone's unevictable list. - */ -#define SCAN_UNEVICTABLE_BATCH_SIZE 16UL /* arbitrary lock hold batch size */ -static void scan_zone_unevictable_pages(struct zone *zone) +static void warn_scan_unevictable_pages(void) { - struct list_head *l_unevictable = &zone->lru[LRU_UNEVICTABLE].list; - unsigned long scan; - unsigned long nr_to_scan = zone_page_state(zone, NR_UNEVICTABLE); - - while (nr_to_scan > 0) { - unsigned long batch_size = min(nr_to_scan, - SCAN_UNEVICTABLE_BATCH_SIZE); - - spin_lock_irq(&zone->lru_lock); - for (scan = 0; scan < batch_size; scan++) { - struct page *page = lru_to_page(l_unevictable); - - if (!trylock_page(page)) - continue; - - prefetchw_prev_lru_page(page, l_unevictable, flags); - - if (likely(PageLRU(page) && PageUnevictable(page))) - check_move_unevictable_page(page, zone); - - unlock_page(page); - } - spin_unlock_irq(&zone->lru_lock); - - nr_to_scan -= batch_size; - } -} - - -/** - * scan_all_zones_unevictable_pages - scan all unevictable lists for evictable pages - * - * A really big hammer: scan all zones' unevictable LRU lists to check for - * pages that have become evictable. Move those back to the zones' - * inactive list where they become candidates for reclaim. - * This occurs when, e.g., we have unswappable pages on the unevictable lists, - * and we add swap to the system. As such, it runs in the context of a task - * that has possibly/probably made some previously unevictable pages - * evictable. - */ -static void scan_all_zones_unevictable_pages(void) -{ - struct zone *zone; - - for_each_zone(zone) { - scan_zone_unevictable_pages(zone); - } + printk_once(KERN_WARNING + "The scan_unevictable_pages sysctl/node-interface has been " + "disabled for lack of a legitimate use case. If you have " + "one, please send an email to linux-mm@kvack.org.\n"); } /* @@ -3373,11 +3463,8 @@ int scan_unevictable_handler(struct ctl_table *table, int write, void __user *buffer, size_t *length, loff_t *ppos) { + warn_scan_unevictable_pages(); proc_doulongvec_minmax(table, write, buffer, length, ppos); - - if (write && *(unsigned long *)table->data) - scan_all_zones_unevictable_pages(); - scan_unevictable_pages = 0; return 0; } @@ -3392,6 +3479,7 @@ static ssize_t read_scan_unevictable_node(struct sys_device *dev, struct sysdev_attribute *attr, char *buf) { + warn_scan_unevictable_pages(); return sprintf(buf, "0\n"); /* always zero; should fit... */ } @@ -3399,19 +3487,7 @@ static ssize_t write_scan_unevictable_node(struct sys_device *dev, struct sysdev_attribute *attr, const char *buf, size_t count) { - struct zone *node_zones = NODE_DATA(dev->id)->node_zones; - struct zone *zone; - unsigned long res; - unsigned long req = strict_strtoul(buf, 10, &res); - - if (!req) - return 1; /* zero is no-op */ - - for (zone = node_zones; zone - node_zones < MAX_NR_ZONES; ++zone) { - if (!populated_zone(zone)) - continue; - scan_zone_unevictable_pages(zone); - } + warn_scan_unevictable_pages(); return 1; } diff --git a/mm/vmstat.c b/mm/vmstat.c index 20c18b7..8fd603b 100644 --- a/mm/vmstat.c +++ b/mm/vmstat.c @@ -78,7 +78,7 @@ void vm_events_fold_cpu(int cpu) * * vm_stat contains the global counters */ -atomic_long_t vm_stat[NR_VM_ZONE_STAT_ITEMS]; +atomic_long_t vm_stat[NR_VM_ZONE_STAT_ITEMS] __cacheline_aligned_in_smp; EXPORT_SYMBOL(vm_stat); #ifdef CONFIG_SMP @@ -659,7 +659,7 @@ static void walk_zones_in_node(struct seq_file *m, pg_data_t *pgdat, } #endif -#if defined(CONFIG_PROC_FS) || defined(CONFIG_SYSFS) +#if defined(CONFIG_PROC_FS) || defined(CONFIG_SYSFS) || defined(CONFIG_NUMA) #ifdef CONFIG_ZONE_DMA #define TEXT_FOR_DMA(xx) xx "_dma", #else @@ -702,6 +702,7 @@ const char * const vmstat_text[] = { "nr_unstable", "nr_bounce", "nr_vmscan_write", + "nr_vmscan_immediate_reclaim", "nr_writeback_temp", "nr_isolated_anon", "nr_isolated_file", @@ -788,7 +789,7 @@ const char * const vmstat_text[] = { #endif /* CONFIG_VM_EVENTS_COUNTERS */ }; -#endif /* CONFIG_PROC_FS || CONFIG_SYSFS */ +#endif /* CONFIG_PROC_FS || CONFIG_SYSFS || CONFIG_NUMA */ #ifdef CONFIG_PROC_FS |