diff options
Diffstat (limited to 'mm')
48 files changed, 3410 insertions, 1710 deletions
@@ -140,9 +140,13 @@ config ARCH_DISCARD_MEMBLOCK config NO_BOOTMEM boolean +config MEMORY_ISOLATION + boolean + # eventually, we can have this option just 'select SPARSEMEM' config MEMORY_HOTPLUG bool "Allow for memory hot-add" + select MEMORY_ISOLATION depends on SPARSEMEM || X86_64_ACPI_NUMA depends on HOTPLUG && ARCH_ENABLE_MEMORY_HOTPLUG depends on (IA64 || X86 || PPC_BOOK3S_64 || SUPERH || S390) @@ -272,6 +276,7 @@ config MEMORY_FAILURE depends on MMU depends on ARCH_SUPPORTS_MEMORY_FAILURE bool "Enable recovery from hardware memory errors" + select MEMORY_ISOLATION help Enables code to recover from some memory failures on systems with MCA recovery. This allows a system to continue running @@ -389,3 +394,20 @@ config CLEANCACHE in a negligible performance hit. If unsure, say Y to enable cleancache + +config FRONTSWAP + bool "Enable frontswap to cache swap pages if tmem is present" + depends on SWAP + default n + help + Frontswap is so named because it can be thought of as the opposite + of a "backing" store for a swap device. The data is stored into + "transcendent memory", memory that is not directly accessible or + addressable by the kernel and is of unknown and possibly + time-varying size. When space in transcendent memory is available, + a significant swap I/O reduction may be achieved. When none is + available, all frontswap calls are reduced to a single pointer- + compare-against-NULL resulting in a negligible performance hit + and swap data is stored as normal on the matching swap device. + + If unsure, say Y to enable frontswap. diff --git a/mm/Makefile b/mm/Makefile index a156285..92753e2 100644 --- a/mm/Makefile +++ b/mm/Makefile @@ -15,8 +15,9 @@ obj-y := filemap.o mempool.o oom_kill.o fadvise.o \ maccess.o page_alloc.o page-writeback.o \ readahead.o swap.o truncate.o vmscan.o shmem.o \ prio_tree.o util.o mmzone.o vmstat.o backing-dev.o \ - page_isolation.o mm_init.o mmu_context.o percpu.o \ + mm_init.o mmu_context.o percpu.o slab_common.o \ compaction.o $(mmu-y) + obj-y += init-mm.o ifdef CONFIG_NO_BOOTMEM @@ -29,6 +30,7 @@ obj-$(CONFIG_HAVE_MEMBLOCK) += memblock.o obj-$(CONFIG_BOUNCE) += bounce.o obj-$(CONFIG_SWAP) += page_io.o swap_state.o swapfile.o +obj-$(CONFIG_FRONTSWAP) += frontswap.o obj-$(CONFIG_HAS_DMA) += dmapool.o obj-$(CONFIG_HUGETLBFS) += hugetlb.o obj-$(CONFIG_NUMA) += mempolicy.o @@ -47,9 +49,11 @@ obj-$(CONFIG_FS_XIP) += filemap_xip.o obj-$(CONFIG_MIGRATION) += migrate.o obj-$(CONFIG_QUICKLIST) += quicklist.o obj-$(CONFIG_TRANSPARENT_HUGEPAGE) += huge_memory.o -obj-$(CONFIG_CGROUP_MEM_RES_CTLR) += memcontrol.o page_cgroup.o +obj-$(CONFIG_MEMCG) += memcontrol.o page_cgroup.o +obj-$(CONFIG_CGROUP_HUGETLB) += hugetlb_cgroup.o obj-$(CONFIG_MEMORY_FAILURE) += memory-failure.o obj-$(CONFIG_HWPOISON_INJECT) += hwpoison-inject.o obj-$(CONFIG_DEBUG_KMEMLEAK) += kmemleak.o obj-$(CONFIG_DEBUG_KMEMLEAK_TEST) += kmemleak-test.o obj-$(CONFIG_CLEANCACHE) += cleancache.o +obj-$(CONFIG_MEMORY_ISOLATION) += page_isolation.o diff --git a/mm/backing-dev.c b/mm/backing-dev.c index dd8e2aa..6b4718e 100644 --- a/mm/backing-dev.c +++ b/mm/backing-dev.c @@ -677,7 +677,7 @@ int bdi_init(struct backing_dev_info *bdi) bdi->min_ratio = 0; bdi->max_ratio = 100; - bdi->max_prop_frac = PROP_FRAC_BASE; + bdi->max_prop_frac = FPROP_FRAC_BASE; spin_lock_init(&bdi->wb_lock); INIT_LIST_HEAD(&bdi->bdi_list); INIT_LIST_HEAD(&bdi->work_list); @@ -700,7 +700,7 @@ int bdi_init(struct backing_dev_info *bdi) bdi->write_bandwidth = INIT_BW; bdi->avg_write_bandwidth = INIT_BW; - err = prop_local_init_percpu(&bdi->completions); + err = fprop_local_init_percpu(&bdi->completions); if (err) { err: @@ -744,7 +744,7 @@ void bdi_destroy(struct backing_dev_info *bdi) for (i = 0; i < NR_BDI_STAT_ITEMS; i++) percpu_counter_destroy(&bdi->bdi_stat[i]); - prop_local_destroy_percpu(&bdi->completions); + fprop_local_destroy_percpu(&bdi->completions); } EXPORT_SYMBOL(bdi_destroy); @@ -886,3 +886,23 @@ out: return ret; } EXPORT_SYMBOL(wait_iff_congested); + +int pdflush_proc_obsolete(struct ctl_table *table, int write, + void __user *buffer, size_t *lenp, loff_t *ppos) +{ + char kbuf[] = "0\n"; + + if (*ppos) { + *lenp = 0; + return 0; + } + + if (copy_to_user(buffer, kbuf, sizeof(kbuf))) + return -EFAULT; + printk_once(KERN_WARNING "%s exported in /proc is scheduled for removal\n", + table->procname); + + *lenp = 2; + *ppos += *lenp; + return 2; +} diff --git a/mm/bootmem.c b/mm/bootmem.c index ec4fcb7..bcb63ac 100644 --- a/mm/bootmem.c +++ b/mm/bootmem.c @@ -698,7 +698,7 @@ void * __init __alloc_bootmem(unsigned long size, unsigned long align, return ___alloc_bootmem(size, align, goal, limit); } -static void * __init ___alloc_bootmem_node_nopanic(pg_data_t *pgdat, +void * __init ___alloc_bootmem_node_nopanic(pg_data_t *pgdat, unsigned long size, unsigned long align, unsigned long goal, unsigned long limit) { @@ -710,6 +710,10 @@ again: if (ptr) return ptr; + /* do not panic in alloc_bootmem_bdata() */ + if (limit && goal + size > limit) + limit = 0; + ptr = alloc_bootmem_bdata(pgdat->bdata, size, align, goal, limit); if (ptr) return ptr; diff --git a/mm/bounce.c b/mm/bounce.c index d1be02c..0420867 100644 --- a/mm/bounce.c +++ b/mm/bounce.c @@ -24,23 +24,25 @@ static mempool_t *page_pool, *isa_page_pool; -#ifdef CONFIG_HIGHMEM +#if defined(CONFIG_HIGHMEM) || defined(CONFIG_NEED_BOUNCE_POOL) static __init int init_emergency_pool(void) { -#ifndef CONFIG_MEMORY_HOTPLUG +#if defined(CONFIG_HIGHMEM) && !defined(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); - printk("highmem bounce pool size: %d pages\n", POOL_SIZE); + printk("bounce pool size: %d pages\n", POOL_SIZE); return 0; } __initcall(init_emergency_pool); +#endif +#ifdef CONFIG_HIGHMEM /* * highmem version, map in to vec */ diff --git a/mm/compaction.c b/mm/compaction.c index 7ea259d..e78cb96 100644 --- a/mm/compaction.c +++ b/mm/compaction.c @@ -422,6 +422,17 @@ static void isolate_freepages(struct zone *zone, pfn -= pageblock_nr_pages) { unsigned long isolated; + /* + * Skip ahead if another thread is compacting in the area + * simultaneously. If we wrapped around, we can only skip + * ahead if zone->compact_cached_free_pfn also wrapped to + * above our starting point. + */ + if (cc->order > 0 && (!cc->wrapped || + zone->compact_cached_free_pfn > + cc->start_free_pfn)) + pfn = min(pfn, zone->compact_cached_free_pfn); + if (!pfn_valid(pfn)) continue; @@ -461,8 +472,11 @@ static void isolate_freepages(struct zone *zone, * looking for free pages, the search will restart here as * page migration may have returned some pages to the allocator */ - if (isolated) + if (isolated) { high_pfn = max(high_pfn, pfn); + if (cc->order > 0) + zone->compact_cached_free_pfn = high_pfn; + } } /* split_free_page does not map the pages */ @@ -556,6 +570,20 @@ static isolate_migrate_t isolate_migratepages(struct zone *zone, return ISOLATE_SUCCESS; } +/* + * Returns the start pfn of the last page block in a zone. This is the starting + * point for full compaction of a zone. Compaction searches for free pages from + * the end of each zone, while isolate_freepages_block scans forward inside each + * page block. + */ +static unsigned long start_free_pfn(struct zone *zone) +{ + unsigned long free_pfn; + free_pfn = zone->zone_start_pfn + zone->spanned_pages; + free_pfn &= ~(pageblock_nr_pages-1); + return free_pfn; +} + static int compact_finished(struct zone *zone, struct compact_control *cc) { @@ -565,8 +593,26 @@ static int compact_finished(struct zone *zone, if (fatal_signal_pending(current)) return COMPACT_PARTIAL; - /* Compaction run completes if the migrate and free scanner meet */ - if (cc->free_pfn <= cc->migrate_pfn) + /* + * A full (order == -1) compaction run starts at the beginning and + * end of a zone; it completes when the migrate and free scanner meet. + * A partial (order > 0) compaction can start with the free scanner + * at a random point in the zone, and may have to restart. + */ + if (cc->free_pfn <= cc->migrate_pfn) { + if (cc->order > 0 && !cc->wrapped) { + /* We started partway through; restart at the end. */ + unsigned long free_pfn = start_free_pfn(zone); + zone->compact_cached_free_pfn = free_pfn; + cc->free_pfn = free_pfn; + cc->wrapped = 1; + return COMPACT_CONTINUE; + } + return COMPACT_COMPLETE; + } + + /* We wrapped around and ended up where we started. */ + if (cc->wrapped && cc->free_pfn <= cc->start_free_pfn) return COMPACT_COMPLETE; /* @@ -664,8 +710,15 @@ static int compact_zone(struct zone *zone, struct compact_control *cc) /* Setup to move all movable pages to the end of the zone */ cc->migrate_pfn = zone->zone_start_pfn; - cc->free_pfn = cc->migrate_pfn + zone->spanned_pages; - cc->free_pfn &= ~(pageblock_nr_pages-1); + + if (cc->order > 0) { + /* Incremental compaction. Start where the last one stopped. */ + cc->free_pfn = zone->compact_cached_free_pfn; + cc->start_free_pfn = cc->free_pfn; + } else { + /* Order == -1 starts at the end of the zone. */ + cc->free_pfn = start_free_pfn(zone); + } migrate_prep_local(); @@ -701,8 +754,11 @@ static int compact_zone(struct zone *zone, struct compact_control *cc) if (err) { putback_lru_pages(&cc->migratepages); cc->nr_migratepages = 0; + if (err == -ENOMEM) { + ret = COMPACT_PARTIAL; + goto out; + } } - } out: diff --git a/mm/fadvise.c b/mm/fadvise.c index 469491e0..9b75a04 100644 --- a/mm/fadvise.c +++ b/mm/fadvise.c @@ -93,11 +93,6 @@ SYSCALL_DEFINE(fadvise64_64)(int fd, loff_t offset, loff_t len, int advice) spin_unlock(&file->f_lock); break; case POSIX_FADV_WILLNEED: - if (!mapping->a_ops->readpage) { - ret = -EINVAL; - break; - } - /* First and last PARTIAL page! */ start_index = offset >> PAGE_CACHE_SHIFT; end_index = endbyte >> PAGE_CACHE_SHIFT; @@ -106,12 +101,13 @@ SYSCALL_DEFINE(fadvise64_64)(int fd, loff_t offset, loff_t len, int advice) nrpages = end_index - start_index + 1; if (!nrpages) nrpages = ~0UL; - - ret = force_page_cache_readahead(mapping, file, - start_index, - nrpages); - if (ret > 0) - ret = 0; + + /* + * Ignore return value because fadvise() shall return + * success even if filesystem can't retrieve a hint, + */ + force_page_cache_readahead(mapping, file, start_index, + nrpages); break; case POSIX_FADV_NOREUSE: break; diff --git a/mm/frontswap.c b/mm/frontswap.c new file mode 100644 index 0000000..6b3e71a --- /dev/null +++ b/mm/frontswap.c @@ -0,0 +1,344 @@ +/* + * Frontswap frontend + * + * This code provides the generic "frontend" layer to call a matching + * "backend" driver implementation of frontswap. See + * Documentation/vm/frontswap.txt for more information. + * + * Copyright (C) 2009-2012 Oracle Corp. All rights reserved. + * Author: Dan Magenheimer + * + * This work is licensed under the terms of the GNU GPL, version 2. + */ + +#include <linux/mman.h> +#include <linux/swap.h> +#include <linux/swapops.h> +#include <linux/security.h> +#include <linux/module.h> +#include <linux/debugfs.h> +#include <linux/frontswap.h> +#include <linux/swapfile.h> + +/* + * frontswap_ops is set by frontswap_register_ops to contain the pointers + * to the frontswap "backend" implementation functions. + */ +static struct frontswap_ops frontswap_ops __read_mostly; + +/* + * This global enablement flag reduces overhead on systems where frontswap_ops + * has not been registered, so is preferred to the slower alternative: a + * function call that checks a non-global. + */ +bool frontswap_enabled __read_mostly; +EXPORT_SYMBOL(frontswap_enabled); + +/* + * If enabled, frontswap_store will return failure even on success. As + * a result, the swap subsystem will always write the page to swap, in + * effect converting frontswap into a writethrough cache. In this mode, + * there is no direct reduction in swap writes, but a frontswap backend + * can unilaterally "reclaim" any pages in use with no data loss, thus + * providing increases control over maximum memory usage due to frontswap. + */ +static bool frontswap_writethrough_enabled __read_mostly; + +#ifdef CONFIG_DEBUG_FS +/* + * Counters available via /sys/kernel/debug/frontswap (if debugfs is + * properly configured). These are for information only so are not protected + * against increment races. + */ +static u64 frontswap_loads; +static u64 frontswap_succ_stores; +static u64 frontswap_failed_stores; +static u64 frontswap_invalidates; + +static inline void inc_frontswap_loads(void) { + frontswap_loads++; +} +static inline void inc_frontswap_succ_stores(void) { + frontswap_succ_stores++; +} +static inline void inc_frontswap_failed_stores(void) { + frontswap_failed_stores++; +} +static inline void inc_frontswap_invalidates(void) { + frontswap_invalidates++; +} +#else +static inline void inc_frontswap_loads(void) { } +static inline void inc_frontswap_succ_stores(void) { } +static inline void inc_frontswap_failed_stores(void) { } +static inline void inc_frontswap_invalidates(void) { } +#endif +/* + * Register operations for frontswap, returning previous thus allowing + * detection of multiple backends and possible nesting. + */ +struct frontswap_ops frontswap_register_ops(struct frontswap_ops *ops) +{ + struct frontswap_ops old = frontswap_ops; + + frontswap_ops = *ops; + frontswap_enabled = true; + return old; +} +EXPORT_SYMBOL(frontswap_register_ops); + +/* + * Enable/disable frontswap writethrough (see above). + */ +void frontswap_writethrough(bool enable) +{ + frontswap_writethrough_enabled = enable; +} +EXPORT_SYMBOL(frontswap_writethrough); + +/* + * Called when a swap device is swapon'd. + */ +void __frontswap_init(unsigned type) +{ + struct swap_info_struct *sis = swap_info[type]; + + BUG_ON(sis == NULL); + if (sis->frontswap_map == NULL) + return; + frontswap_ops.init(type); +} +EXPORT_SYMBOL(__frontswap_init); + +static inline void __frontswap_clear(struct swap_info_struct *sis, pgoff_t offset) +{ + frontswap_clear(sis, offset); + atomic_dec(&sis->frontswap_pages); +} + +/* + * "Store" data from a page to frontswap and associate it with the page's + * swaptype and offset. Page must be locked and in the swap cache. + * If frontswap already contains a page with matching swaptype and + * offset, the frontswap implementation may either overwrite the data and + * return success or invalidate the page from frontswap and return failure. + */ +int __frontswap_store(struct page *page) +{ + int ret = -1, dup = 0; + swp_entry_t entry = { .val = page_private(page), }; + int type = swp_type(entry); + struct swap_info_struct *sis = swap_info[type]; + pgoff_t offset = swp_offset(entry); + + BUG_ON(!PageLocked(page)); + BUG_ON(sis == NULL); + if (frontswap_test(sis, offset)) + dup = 1; + ret = frontswap_ops.store(type, offset, page); + if (ret == 0) { + frontswap_set(sis, offset); + inc_frontswap_succ_stores(); + if (!dup) + atomic_inc(&sis->frontswap_pages); + } else { + /* + failed dup always results in automatic invalidate of + the (older) page from frontswap + */ + inc_frontswap_failed_stores(); + if (dup) + __frontswap_clear(sis, offset); + } + if (frontswap_writethrough_enabled) + /* report failure so swap also writes to swap device */ + ret = -1; + return ret; +} +EXPORT_SYMBOL(__frontswap_store); + +/* + * "Get" data from frontswap associated with swaptype and offset that were + * specified when the data was put to frontswap and use it to fill the + * specified page with data. Page must be locked and in the swap cache. + */ +int __frontswap_load(struct page *page) +{ + int ret = -1; + swp_entry_t entry = { .val = page_private(page), }; + int type = swp_type(entry); + struct swap_info_struct *sis = swap_info[type]; + pgoff_t offset = swp_offset(entry); + + BUG_ON(!PageLocked(page)); + BUG_ON(sis == NULL); + if (frontswap_test(sis, offset)) + ret = frontswap_ops.load(type, offset, page); + if (ret == 0) + inc_frontswap_loads(); + return ret; +} +EXPORT_SYMBOL(__frontswap_load); + +/* + * Invalidate any data from frontswap associated with the specified swaptype + * and offset so that a subsequent "get" will fail. + */ +void __frontswap_invalidate_page(unsigned type, pgoff_t offset) +{ + struct swap_info_struct *sis = swap_info[type]; + + BUG_ON(sis == NULL); + if (frontswap_test(sis, offset)) { + frontswap_ops.invalidate_page(type, offset); + __frontswap_clear(sis, offset); + inc_frontswap_invalidates(); + } +} +EXPORT_SYMBOL(__frontswap_invalidate_page); + +/* + * Invalidate all data from frontswap associated with all offsets for the + * specified swaptype. + */ +void __frontswap_invalidate_area(unsigned type) +{ + struct swap_info_struct *sis = swap_info[type]; + + BUG_ON(sis == NULL); + if (sis->frontswap_map == NULL) + return; + frontswap_ops.invalidate_area(type); + atomic_set(&sis->frontswap_pages, 0); + memset(sis->frontswap_map, 0, sis->max / sizeof(long)); +} +EXPORT_SYMBOL(__frontswap_invalidate_area); + +static unsigned long __frontswap_curr_pages(void) +{ + int type; + unsigned long totalpages = 0; + struct swap_info_struct *si = NULL; + + assert_spin_locked(&swap_lock); + for (type = swap_list.head; type >= 0; type = si->next) { + si = swap_info[type]; + totalpages += atomic_read(&si->frontswap_pages); + } + return totalpages; +} + +static int __frontswap_unuse_pages(unsigned long total, unsigned long *unused, + int *swapid) +{ + int ret = -EINVAL; + struct swap_info_struct *si = NULL; + int si_frontswap_pages; + unsigned long total_pages_to_unuse = total; + unsigned long pages = 0, pages_to_unuse = 0; + int type; + + assert_spin_locked(&swap_lock); + for (type = swap_list.head; type >= 0; type = si->next) { + si = swap_info[type]; + si_frontswap_pages = atomic_read(&si->frontswap_pages); + if (total_pages_to_unuse < si_frontswap_pages) { + pages = pages_to_unuse = total_pages_to_unuse; + } else { + pages = si_frontswap_pages; + pages_to_unuse = 0; /* unuse all */ + } + /* ensure there is enough RAM to fetch pages from frontswap */ + if (security_vm_enough_memory_mm(current->mm, pages)) { + ret = -ENOMEM; + continue; + } + vm_unacct_memory(pages); + *unused = pages_to_unuse; + *swapid = type; + ret = 0; + break; + } + + return ret; +} + +static int __frontswap_shrink(unsigned long target_pages, + unsigned long *pages_to_unuse, + int *type) +{ + unsigned long total_pages = 0, total_pages_to_unuse; + + assert_spin_locked(&swap_lock); + + total_pages = __frontswap_curr_pages(); + if (total_pages <= target_pages) { + /* Nothing to do */ + *pages_to_unuse = 0; + return 0; + } + total_pages_to_unuse = total_pages - target_pages; + return __frontswap_unuse_pages(total_pages_to_unuse, pages_to_unuse, type); +} + +/* + * Frontswap, like a true swap device, may unnecessarily retain pages + * under certain circumstances; "shrink" frontswap is essentially a + * "partial swapoff" and works by calling try_to_unuse to attempt to + * unuse enough frontswap pages to attempt to -- subject to memory + * constraints -- reduce the number of pages in frontswap to the + * number given in the parameter target_pages. + */ +void frontswap_shrink(unsigned long target_pages) +{ + unsigned long pages_to_unuse = 0; + int type, ret; + + /* + * we don't want to hold swap_lock while doing a very + * lengthy try_to_unuse, but swap_list may change + * so restart scan from swap_list.head each time + */ + spin_lock(&swap_lock); + ret = __frontswap_shrink(target_pages, &pages_to_unuse, &type); + spin_unlock(&swap_lock); + if (ret == 0 && pages_to_unuse) + try_to_unuse(type, true, pages_to_unuse); + return; +} +EXPORT_SYMBOL(frontswap_shrink); + +/* + * Count and return the number of frontswap pages across all + * swap devices. This is exported so that backend drivers can + * determine current usage without reading debugfs. + */ +unsigned long frontswap_curr_pages(void) +{ + unsigned long totalpages = 0; + + spin_lock(&swap_lock); + totalpages = __frontswap_curr_pages(); + spin_unlock(&swap_lock); + + return totalpages; +} +EXPORT_SYMBOL(frontswap_curr_pages); + +static int __init init_frontswap(void) +{ +#ifdef CONFIG_DEBUG_FS + struct dentry *root = debugfs_create_dir("frontswap", NULL); + if (root == NULL) + return -ENXIO; + debugfs_create_u64("loads", S_IRUGO, root, &frontswap_loads); + debugfs_create_u64("succ_stores", S_IRUGO, root, &frontswap_succ_stores); + debugfs_create_u64("failed_stores", S_IRUGO, root, + &frontswap_failed_stores); + debugfs_create_u64("invalidates", S_IRUGO, + root, &frontswap_invalidates); +#endif + return 0; +} + +module_init(init_frontswap); diff --git a/mm/highmem.c b/mm/highmem.c index 57d82c6..d517cd1 100644 --- a/mm/highmem.c +++ b/mm/highmem.c @@ -94,6 +94,18 @@ static DECLARE_WAIT_QUEUE_HEAD(pkmap_map_wait); do { spin_unlock(&kmap_lock); (void)(flags); } while (0) #endif +struct page *kmap_to_page(void *vaddr) +{ + unsigned long addr = (unsigned long)vaddr; + + if (addr >= PKMAP_ADDR(0) && addr <= PKMAP_ADDR(LAST_PKMAP)) { + int i = (addr - PKMAP_ADDR(0)) >> PAGE_SHIFT; + return pte_page(pkmap_page_table[i]); + } + + return virt_to_page(addr); +} + static void flush_all_zero_pkmaps(void) { int i; diff --git a/mm/hugetlb.c b/mm/hugetlb.c index e198831..bc72712 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -24,17 +24,20 @@ #include <asm/page.h> #include <asm/pgtable.h> -#include <linux/io.h> +#include <asm/tlb.h> +#include <linux/io.h> #include <linux/hugetlb.h> +#include <linux/hugetlb_cgroup.h> #include <linux/node.h> +#include <linux/hugetlb_cgroup.h> #include "internal.h" const unsigned long hugetlb_zero = 0, hugetlb_infinity = ~0UL; static gfp_t htlb_alloc_mask = GFP_HIGHUSER; unsigned long hugepages_treat_as_movable; -static int max_hstate; +int hugetlb_max_hstate __read_mostly; unsigned int default_hstate_idx; struct hstate hstates[HUGE_MAX_HSTATE]; @@ -45,13 +48,10 @@ static struct hstate * __initdata parsed_hstate; static unsigned long __initdata default_hstate_max_huge_pages; static unsigned long __initdata default_hstate_size; -#define for_each_hstate(h) \ - for ((h) = hstates; (h) < &hstates[max_hstate]; (h)++) - /* * Protects updates to hugepage_freelists, nr_huge_pages, and free_huge_pages */ -static DEFINE_SPINLOCK(hugetlb_lock); +DEFINE_SPINLOCK(hugetlb_lock); static inline void unlock_or_release_subpool(struct hugepage_subpool *spool) { @@ -509,7 +509,7 @@ void copy_huge_page(struct page *dst, struct page *src) static void enqueue_huge_page(struct hstate *h, struct page *page) { int nid = page_to_nid(page); - list_add(&page->lru, &h->hugepage_freelists[nid]); + list_move(&page->lru, &h->hugepage_freelists[nid]); h->free_huge_pages++; h->free_huge_pages_node[nid]++; } @@ -521,7 +521,7 @@ static struct page *dequeue_huge_page_node(struct hstate *h, int nid) if (list_empty(&h->hugepage_freelists[nid])) return NULL; page = list_entry(h->hugepage_freelists[nid].next, struct page, lru); - list_del(&page->lru); + list_move(&page->lru, &h->hugepage_activelist); set_page_refcounted(page); h->free_huge_pages--; h->free_huge_pages_node[nid]--; @@ -593,6 +593,7 @@ static void update_and_free_page(struct hstate *h, struct page *page) 1 << PG_active | 1 << PG_reserved | 1 << PG_private | 1 << PG_writeback); } + VM_BUG_ON(hugetlb_cgroup_from_page(page)); set_compound_page_dtor(page, NULL); set_page_refcounted(page); arch_release_hugepage(page); @@ -625,10 +626,13 @@ static void free_huge_page(struct page *page) page->mapping = NULL; BUG_ON(page_count(page)); BUG_ON(page_mapcount(page)); - INIT_LIST_HEAD(&page->lru); spin_lock(&hugetlb_lock); + hugetlb_cgroup_uncharge_page(hstate_index(h), + pages_per_huge_page(h), page); if (h->surplus_huge_pages_node[nid] && huge_page_order(h) < MAX_ORDER) { + /* remove the page from active list */ + list_del(&page->lru); update_and_free_page(h, page); h->surplus_huge_pages--; h->surplus_huge_pages_node[nid]--; @@ -641,8 +645,10 @@ static void free_huge_page(struct page *page) static void prep_new_huge_page(struct hstate *h, struct page *page, int nid) { + INIT_LIST_HEAD(&page->lru); set_compound_page_dtor(page, free_huge_page); spin_lock(&hugetlb_lock); + set_hugetlb_cgroup(page, NULL); h->nr_huge_pages++; h->nr_huge_pages_node[nid]++; spin_unlock(&hugetlb_lock); @@ -889,8 +895,10 @@ static struct page *alloc_buddy_huge_page(struct hstate *h, int nid) spin_lock(&hugetlb_lock); if (page) { + INIT_LIST_HEAD(&page->lru); r_nid = page_to_nid(page); set_compound_page_dtor(page, free_huge_page); + set_hugetlb_cgroup(page, NULL); /* * We incremented the global counters already */ @@ -993,7 +1001,6 @@ retry: list_for_each_entry_safe(page, tmp, &surplus_list, lru) { if ((--needed) < 0) break; - list_del(&page->lru); /* * This page is now managed by the hugetlb allocator and has * no users -- drop the buddy allocator's reference. @@ -1008,7 +1015,6 @@ free: /* Free unnecessary surplus pages to the buddy allocator */ if (!list_empty(&surplus_list)) { list_for_each_entry_safe(page, tmp, &surplus_list, lru) { - list_del(&page->lru); put_page(page); } } @@ -1112,7 +1118,10 @@ static struct page *alloc_huge_page(struct vm_area_struct *vma, struct hstate *h = hstate_vma(vma); struct page *page; long chg; + int ret, idx; + struct hugetlb_cgroup *h_cg; + idx = hstate_index(h); /* * Processes that did not create the mapping will have no * reserves and will not have accounted against subpool @@ -1123,27 +1132,43 @@ static struct page *alloc_huge_page(struct vm_area_struct *vma, */ chg = vma_needs_reservation(h, vma, addr); if (chg < 0) - return ERR_PTR(-VM_FAULT_OOM); + return ERR_PTR(-ENOMEM); if (chg) if (hugepage_subpool_get_pages(spool, chg)) - return ERR_PTR(-VM_FAULT_SIGBUS); + return ERR_PTR(-ENOSPC); + ret = hugetlb_cgroup_charge_cgroup(idx, pages_per_huge_page(h), &h_cg); + if (ret) { + hugepage_subpool_put_pages(spool, chg); + return ERR_PTR(-ENOSPC); + } spin_lock(&hugetlb_lock); page = dequeue_huge_page_vma(h, vma, addr, avoid_reserve); - spin_unlock(&hugetlb_lock); - - if (!page) { + if (page) { + /* update page cgroup details */ + hugetlb_cgroup_commit_charge(idx, pages_per_huge_page(h), + h_cg, page); + spin_unlock(&hugetlb_lock); + } else { + spin_unlock(&hugetlb_lock); page = alloc_buddy_huge_page(h, NUMA_NO_NODE); if (!page) { + hugetlb_cgroup_uncharge_cgroup(idx, + pages_per_huge_page(h), + h_cg); hugepage_subpool_put_pages(spool, chg); - return ERR_PTR(-VM_FAULT_SIGBUS); + return ERR_PTR(-ENOSPC); } + spin_lock(&hugetlb_lock); + hugetlb_cgroup_commit_charge(idx, pages_per_huge_page(h), + h_cg, page); + list_move(&page->lru, &h->hugepage_activelist); + spin_unlock(&hugetlb_lock); } set_page_private(page, (unsigned long)spool); vma_commit_reservation(h, vma, addr); - return page; } @@ -1646,7 +1671,7 @@ static int hugetlb_sysfs_add_hstate(struct hstate *h, struct kobject *parent, struct attribute_group *hstate_attr_group) { int retval; - int hi = h - hstates; + int hi = hstate_index(h); hstate_kobjs[hi] = kobject_create_and_add(h->name, parent); if (!hstate_kobjs[hi]) @@ -1741,11 +1766,13 @@ void hugetlb_unregister_node(struct node *node) if (!nhs->hugepages_kobj) return; /* no hstate attributes */ - for_each_hstate(h) - if (nhs->hstate_kobjs[h - hstates]) { - kobject_put(nhs->hstate_kobjs[h - hstates]); - nhs->hstate_kobjs[h - hstates] = NULL; + for_each_hstate(h) { + int idx = hstate_index(h); + if (nhs->hstate_kobjs[idx]) { + kobject_put(nhs->hstate_kobjs[idx]); + nhs->hstate_kobjs[idx] = NULL; } + } kobject_put(nhs->hugepages_kobj); nhs->hugepages_kobj = NULL; @@ -1848,7 +1875,7 @@ static void __exit hugetlb_exit(void) hugetlb_unregister_all_nodes(); for_each_hstate(h) { - kobject_put(hstate_kobjs[h - hstates]); + kobject_put(hstate_kobjs[hstate_index(h)]); } kobject_put(hugepages_kobj); @@ -1869,7 +1896,7 @@ static int __init hugetlb_init(void) if (!size_to_hstate(default_hstate_size)) hugetlb_add_hstate(HUGETLB_PAGE_ORDER); } - default_hstate_idx = size_to_hstate(default_hstate_size) - hstates; + default_hstate_idx = hstate_index(size_to_hstate(default_hstate_size)); if (default_hstate_max_huge_pages) default_hstate.max_huge_pages = default_hstate_max_huge_pages; @@ -1897,19 +1924,27 @@ void __init hugetlb_add_hstate(unsigned order) printk(KERN_WARNING "hugepagesz= specified twice, ignoring\n"); return; } - BUG_ON(max_hstate >= HUGE_MAX_HSTATE); + BUG_ON(hugetlb_max_hstate >= HUGE_MAX_HSTATE); BUG_ON(order == 0); - h = &hstates[max_hstate++]; + h = &hstates[hugetlb_max_hstate++]; h->order = order; h->mask = ~((1ULL << (order + PAGE_SHIFT)) - 1); h->nr_huge_pages = 0; h->free_huge_pages = 0; for (i = 0; i < MAX_NUMNODES; ++i) INIT_LIST_HEAD(&h->hugepage_freelists[i]); + INIT_LIST_HEAD(&h->hugepage_activelist); h->next_nid_to_alloc = first_node(node_states[N_HIGH_MEMORY]); h->next_nid_to_free = first_node(node_states[N_HIGH_MEMORY]); snprintf(h->name, HSTATE_NAME_LEN, "hugepages-%lukB", huge_page_size(h)/1024); + /* + * Add cgroup control files only if the huge page consists + * of more than two normal pages. This is because we use + * page[2].lru.next for storing cgoup details. + */ + if (order >= HUGETLB_CGROUP_MIN_ORDER) + hugetlb_cgroup_file_init(hugetlb_max_hstate - 1); parsed_hstate = h; } @@ -1920,10 +1955,10 @@ static int __init hugetlb_nrpages_setup(char *s) static unsigned long *last_mhp; /* - * !max_hstate means we haven't parsed a hugepagesz= parameter yet, + * !hugetlb_max_hstate means we haven't parsed a hugepagesz= parameter yet, * so this hugepages= parameter goes to the "default hstate". */ - if (!max_hstate) + if (!hugetlb_max_hstate) mhp = &default_hstate_max_huge_pages; else mhp = &parsed_hstate->max_huge_pages; @@ -1942,7 +1977,7 @@ static int __init hugetlb_nrpages_setup(char *s) * But we need to allocate >= MAX_ORDER hstates here early to still * use the bootmem allocator. */ - if (max_hstate && parsed_hstate->order >= MAX_ORDER) + if (hugetlb_max_hstate && parsed_hstate->order >= MAX_ORDER) hugetlb_hstate_alloc_pages(parsed_hstate); last_mhp = mhp; @@ -2308,30 +2343,26 @@ static int is_hugetlb_entry_hwpoisoned(pte_t pte) return 0; } -void __unmap_hugepage_range(struct vm_area_struct *vma, unsigned long start, - unsigned long end, struct page *ref_page) +void __unmap_hugepage_range(struct mmu_gather *tlb, struct vm_area_struct *vma, + unsigned long start, unsigned long end, + struct page *ref_page) { + int force_flush = 0; struct mm_struct *mm = vma->vm_mm; unsigned long address; pte_t *ptep; pte_t pte; struct page *page; - struct page *tmp; struct hstate *h = hstate_vma(vma); unsigned long sz = huge_page_size(h); - /* - * A page gathering list, protected by per file i_mmap_mutex. The - * lock is used to avoid list corruption from multiple unmapping - * of the same page since we are using page->lru. - */ - LIST_HEAD(page_list); - WARN_ON(!is_vm_hugetlb_page(vma)); BUG_ON(start & ~huge_page_mask(h)); BUG_ON(end & ~huge_page_mask(h)); + tlb_start_vma(tlb, vma); mmu_notifier_invalidate_range_start(mm, start, end); +again: spin_lock(&mm->page_table_lock); for (address = start; address < end; address += sz) { ptep = huge_pte_offset(mm, address); @@ -2370,30 +2401,64 @@ void __unmap_hugepage_range(struct vm_area_struct *vma, unsigned long start, } pte = huge_ptep_get_and_clear(mm, address, ptep); + tlb_remove_tlb_entry(tlb, ptep, address); if (pte_dirty(pte)) set_page_dirty(page); - list_add(&page->lru, &page_list); + page_remove_rmap(page); + force_flush = !__tlb_remove_page(tlb, page); + if (force_flush) + break; /* Bail out after unmapping reference page if supplied */ if (ref_page) break; } - flush_tlb_range(vma, start, end); spin_unlock(&mm->page_table_lock); - mmu_notifier_invalidate_range_end(mm, start, end); - list_for_each_entry_safe(page, tmp, &page_list, lru) { - page_remove_rmap(page); - list_del(&page->lru); - put_page(page); + /* + * mmu_gather ran out of room to batch pages, we break out of + * the PTE lock to avoid doing the potential expensive TLB invalidate + * and page-free while holding it. + */ + if (force_flush) { + force_flush = 0; + tlb_flush_mmu(tlb); + if (address < end && !ref_page) + goto again; } + mmu_notifier_invalidate_range_end(mm, start, end); + tlb_end_vma(tlb, vma); +} + +void __unmap_hugepage_range_final(struct mmu_gather *tlb, + struct vm_area_struct *vma, unsigned long start, + unsigned long end, struct page *ref_page) +{ + __unmap_hugepage_range(tlb, vma, start, end, ref_page); + + /* + * Clear this flag so that x86's huge_pmd_share page_table_shareable + * test will fail on a vma being torn down, and not grab a page table + * on its way out. We're lucky that the flag has such an appropriate + * name, and can in fact be safely cleared here. We could clear it + * before the __unmap_hugepage_range above, but all that's necessary + * is to clear it before releasing the i_mmap_mutex. This works + * because in the context this is called, the VMA is about to be + * destroyed and the i_mmap_mutex is held. + */ + vma->vm_flags &= ~VM_MAYSHARE; } void unmap_hugepage_range(struct vm_area_struct *vma, unsigned long start, unsigned long end, struct page *ref_page) { - mutex_lock(&vma->vm_file->f_mapping->i_mmap_mutex); - __unmap_hugepage_range(vma, start, end, ref_page); - mutex_unlock(&vma->vm_file->f_mapping->i_mmap_mutex); + struct mm_struct *mm; + struct mmu_gather tlb; + + mm = vma->vm_mm; + + tlb_gather_mmu(&tlb, mm, 0); + __unmap_hugepage_range(&tlb, vma, start, end, ref_page); + tlb_finish_mmu(&tlb, start, end); } /* @@ -2438,9 +2503,8 @@ static int unmap_ref_private(struct mm_struct *mm, struct vm_area_struct *vma, * from the time of fork. This would look like data corruption */ if (!is_vma_resv_set(iter_vma, HPAGE_RESV_OWNER)) - __unmap_hugepage_range(iter_vma, - address, address + huge_page_size(h), - page); + unmap_hugepage_range(iter_vma, address, + address + huge_page_size(h), page); } mutex_unlock(&mapping->i_mmap_mutex); @@ -2496,6 +2560,7 @@ retry_avoidcopy: new_page = alloc_huge_page(vma, address, outside_reserve); if (IS_ERR(new_page)) { + long err = PTR_ERR(new_page); page_cache_release(old_page); /* @@ -2524,7 +2589,10 @@ retry_avoidcopy: /* Caller expects lock to be held */ spin_lock(&mm->page_table_lock); - return -PTR_ERR(new_page); + if (err == -ENOMEM) + return VM_FAULT_OOM; + else + return VM_FAULT_SIGBUS; } /* @@ -2642,7 +2710,11 @@ retry: goto out; page = alloc_huge_page(vma, address, 0); if (IS_ERR(page)) { - ret = -PTR_ERR(page); + ret = PTR_ERR(page); + if (ret == -ENOMEM) + ret = VM_FAULT_OOM; + else + ret = VM_FAULT_SIGBUS; goto out; } clear_huge_page(page, address, pages_per_huge_page(h)); @@ -2679,7 +2751,7 @@ retry: */ if (unlikely(PageHWPoison(page))) { ret = VM_FAULT_HWPOISON | - VM_FAULT_SET_HINDEX(h - hstates); + VM_FAULT_SET_HINDEX(hstate_index(h)); goto backout_unlocked; } } @@ -2752,7 +2824,7 @@ int hugetlb_fault(struct mm_struct *mm, struct vm_area_struct *vma, return 0; } else if (unlikely(is_hugetlb_entry_hwpoisoned(entry))) return VM_FAULT_HWPOISON_LARGE | - VM_FAULT_SET_HINDEX(h - hstates); + VM_FAULT_SET_HINDEX(hstate_index(h)); } ptep = huge_pte_alloc(mm, address, huge_page_size(h)); @@ -2959,9 +3031,14 @@ void hugetlb_change_protection(struct vm_area_struct *vma, } } spin_unlock(&mm->page_table_lock); - mutex_unlock(&vma->vm_file->f_mapping->i_mmap_mutex); - + /* + * Must flush TLB before releasing i_mmap_mutex: x86's huge_pmd_unshare + * may have cleared our pud entry and done put_page on the page table: + * once we release i_mmap_mutex, another task can do the final put_page + * and that page table be reused and filled with junk. + */ flush_tlb_range(vma, start, end); + mutex_unlock(&vma->vm_file->f_mapping->i_mmap_mutex); } int hugetlb_reserve_pages(struct inode *inode, diff --git a/mm/hugetlb_cgroup.c b/mm/hugetlb_cgroup.c new file mode 100644 index 0000000..a3f358f --- /dev/null +++ b/mm/hugetlb_cgroup.c @@ -0,0 +1,418 @@ +/* + * + * Copyright IBM Corporation, 2012 + * Author Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com> + * + * This program is free software; you can redistribute it and/or modify it + * under the terms of version 2.1 of the GNU Lesser General Public License + * as published by the Free Software Foundation. + * + * This program is distributed in the hope that it would be useful, but + * WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. + * + */ + +#include <linux/cgroup.h> +#include <linux/slab.h> +#include <linux/hugetlb.h> +#include <linux/hugetlb_cgroup.h> + +struct hugetlb_cgroup { + struct cgroup_subsys_state css; + /* + * the counter to account for hugepages from hugetlb. + */ + struct res_counter hugepage[HUGE_MAX_HSTATE]; +}; + +#define MEMFILE_PRIVATE(x, val) (((x) << 16) | (val)) +#define MEMFILE_IDX(val) (((val) >> 16) & 0xffff) +#define MEMFILE_ATTR(val) ((val) & 0xffff) + +struct cgroup_subsys hugetlb_subsys __read_mostly; +static struct hugetlb_cgroup *root_h_cgroup __read_mostly; + +static inline +struct hugetlb_cgroup *hugetlb_cgroup_from_css(struct cgroup_subsys_state *s) +{ + return container_of(s, struct hugetlb_cgroup, css); +} + +static inline +struct hugetlb_cgroup *hugetlb_cgroup_from_cgroup(struct cgroup *cgroup) +{ + return hugetlb_cgroup_from_css(cgroup_subsys_state(cgroup, + hugetlb_subsys_id)); +} + +static inline +struct hugetlb_cgroup *hugetlb_cgroup_from_task(struct task_struct *task) +{ + return hugetlb_cgroup_from_css(task_subsys_state(task, + hugetlb_subsys_id)); +} + +static inline bool hugetlb_cgroup_is_root(struct hugetlb_cgroup *h_cg) +{ + return (h_cg == root_h_cgroup); +} + +static inline struct hugetlb_cgroup *parent_hugetlb_cgroup(struct cgroup *cg) +{ + if (!cg->parent) + return NULL; + return hugetlb_cgroup_from_cgroup(cg->parent); +} + +static inline bool hugetlb_cgroup_have_usage(struct cgroup *cg) +{ + int idx; + struct hugetlb_cgroup *h_cg = hugetlb_cgroup_from_cgroup(cg); + + for (idx = 0; idx < hugetlb_max_hstate; idx++) { + if ((res_counter_read_u64(&h_cg->hugepage[idx], RES_USAGE)) > 0) + return true; + } + return false; +} + +static struct cgroup_subsys_state *hugetlb_cgroup_create(struct cgroup *cgroup) +{ + int idx; + struct cgroup *parent_cgroup; + struct hugetlb_cgroup *h_cgroup, *parent_h_cgroup; + + h_cgroup = kzalloc(sizeof(*h_cgroup), GFP_KERNEL); + if (!h_cgroup) + return ERR_PTR(-ENOMEM); + + parent_cgroup = cgroup->parent; + if (parent_cgroup) { + parent_h_cgroup = hugetlb_cgroup_from_cgroup(parent_cgroup); + for (idx = 0; idx < HUGE_MAX_HSTATE; idx++) + res_counter_init(&h_cgroup->hugepage[idx], + &parent_h_cgroup->hugepage[idx]); + } else { + root_h_cgroup = h_cgroup; + for (idx = 0; idx < HUGE_MAX_HSTATE; idx++) + res_counter_init(&h_cgroup->hugepage[idx], NULL); + } + return &h_cgroup->css; +} + +static void hugetlb_cgroup_destroy(struct cgroup *cgroup) +{ + struct hugetlb_cgroup *h_cgroup; + + h_cgroup = hugetlb_cgroup_from_cgroup(cgroup); + kfree(h_cgroup); +} + + +/* + * Should be called with hugetlb_lock held. + * Since we are holding hugetlb_lock, pages cannot get moved from + * active list or uncharged from the cgroup, So no need to get + * page reference and test for page active here. This function + * cannot fail. + */ +static void hugetlb_cgroup_move_parent(int idx, struct cgroup *cgroup, + struct page *page) +{ + int csize; + struct res_counter *counter; + struct res_counter *fail_res; + struct hugetlb_cgroup *page_hcg; + struct hugetlb_cgroup *h_cg = hugetlb_cgroup_from_cgroup(cgroup); + struct hugetlb_cgroup *parent = parent_hugetlb_cgroup(cgroup); + + page_hcg = hugetlb_cgroup_from_page(page); + /* + * We can have pages in active list without any cgroup + * ie, hugepage with less than 3 pages. We can safely + * ignore those pages. + */ + if (!page_hcg || page_hcg != h_cg) + goto out; + + csize = PAGE_SIZE << compound_order(page); + if (!parent) { + parent = root_h_cgroup; + /* root has no limit */ + res_counter_charge_nofail(&parent->hugepage[idx], + csize, &fail_res); + } + counter = &h_cg->hugepage[idx]; + res_counter_uncharge_until(counter, counter->parent, csize); + + set_hugetlb_cgroup(page, parent); +out: + return; +} + +/* + * Force the hugetlb cgroup to empty the hugetlb resources by moving them to + * the parent cgroup. + */ +static int hugetlb_cgroup_pre_destroy(struct cgroup *cgroup) +{ + struct hstate *h; + struct page *page; + int ret = 0, idx = 0; + + do { + if (cgroup_task_count(cgroup) || + !list_empty(&cgroup->children)) { + ret = -EBUSY; + goto out; + } + for_each_hstate(h) { + spin_lock(&hugetlb_lock); + list_for_each_entry(page, &h->hugepage_activelist, lru) + hugetlb_cgroup_move_parent(idx, cgroup, page); + + spin_unlock(&hugetlb_lock); + idx++; + } + cond_resched(); + } while (hugetlb_cgroup_have_usage(cgroup)); +out: + return ret; +} + +int hugetlb_cgroup_charge_cgroup(int idx, unsigned long nr_pages, + struct hugetlb_cgroup **ptr) +{ + int ret = 0; + struct res_counter *fail_res; + struct hugetlb_cgroup *h_cg = NULL; + unsigned long csize = nr_pages * PAGE_SIZE; + + if (hugetlb_cgroup_disabled()) + goto done; + /* + * We don't charge any cgroup if the compound page have less + * than 3 pages. + */ + if (huge_page_order(&hstates[idx]) < HUGETLB_CGROUP_MIN_ORDER) + goto done; +again: + rcu_read_lock(); + h_cg = hugetlb_cgroup_from_task(current); + if (!css_tryget(&h_cg->css)) { + rcu_read_unlock(); + goto again; + } + rcu_read_unlock(); + + ret = res_counter_charge(&h_cg->hugepage[idx], csize, &fail_res); + css_put(&h_cg->css); +done: + *ptr = h_cg; + return ret; +} + +/* Should be called with hugetlb_lock held */ +void hugetlb_cgroup_commit_charge(int idx, unsigned long nr_pages, + struct hugetlb_cgroup *h_cg, + struct page *page) +{ + if (hugetlb_cgroup_disabled() || !h_cg) + return; + + set_hugetlb_cgroup(page, h_cg); + return; +} + +/* + * Should be called with hugetlb_lock held + */ +void hugetlb_cgroup_uncharge_page(int idx, unsigned long nr_pages, + struct page *page) +{ + struct hugetlb_cgroup *h_cg; + unsigned long csize = nr_pages * PAGE_SIZE; + + if (hugetlb_cgroup_disabled()) + return; + VM_BUG_ON(!spin_is_locked(&hugetlb_lock)); + h_cg = hugetlb_cgroup_from_page(page); + if (unlikely(!h_cg)) + return; + set_hugetlb_cgroup(page, NULL); + res_counter_uncharge(&h_cg->hugepage[idx], csize); + return; +} + +void hugetlb_cgroup_uncharge_cgroup(int idx, unsigned long nr_pages, + struct hugetlb_cgroup *h_cg) +{ + unsigned long csize = nr_pages * PAGE_SIZE; + + if (hugetlb_cgroup_disabled() || !h_cg) + return; + + if (huge_page_order(&hstates[idx]) < HUGETLB_CGROUP_MIN_ORDER) + return; + + res_counter_uncharge(&h_cg->hugepage[idx], csize); + return; +} + +static ssize_t hugetlb_cgroup_read(struct cgroup *cgroup, struct cftype *cft, + struct file *file, char __user *buf, + size_t nbytes, loff_t *ppos) +{ + u64 val; + char str[64]; + int idx, name, len; + struct hugetlb_cgroup *h_cg = hugetlb_cgroup_from_cgroup(cgroup); + + idx = MEMFILE_IDX(cft->private); + name = MEMFILE_ATTR(cft->private); + + val = res_counter_read_u64(&h_cg->hugepage[idx], name); + len = scnprintf(str, sizeof(str), "%llu\n", (unsigned long long)val); + return simple_read_from_buffer(buf, nbytes, ppos, str, len); +} + +static int hugetlb_cgroup_write(struct cgroup *cgroup, struct cftype *cft, + const char *buffer) +{ + int idx, name, ret; + unsigned long long val; + struct hugetlb_cgroup *h_cg = hugetlb_cgroup_from_cgroup(cgroup); + + idx = MEMFILE_IDX(cft->private); + name = MEMFILE_ATTR(cft->private); + + switch (name) { + case RES_LIMIT: + if (hugetlb_cgroup_is_root(h_cg)) { + /* Can't set limit on root */ + ret = -EINVAL; + break; + } + /* This function does all necessary parse...reuse it */ + ret = res_counter_memparse_write_strategy(buffer, &val); + if (ret) + break; + ret = res_counter_set_limit(&h_cg->hugepage[idx], val); + break; + default: + ret = -EINVAL; + break; + } + return ret; +} + +static int hugetlb_cgroup_reset(struct cgroup *cgroup, unsigned int event) +{ + int idx, name, ret = 0; + struct hugetlb_cgroup *h_cg = hugetlb_cgroup_from_cgroup(cgroup); + + idx = MEMFILE_IDX(event); + name = MEMFILE_ATTR(event); + + switch (name) { + case RES_MAX_USAGE: + res_counter_reset_max(&h_cg->hugepage[idx]); + break; + case RES_FAILCNT: + res_counter_reset_failcnt(&h_cg->hugepage[idx]); + break; + default: + ret = -EINVAL; + break; + } + return ret; +} + +static char *mem_fmt(char *buf, int size, unsigned long hsize) +{ + if (hsize >= (1UL << 30)) + snprintf(buf, size, "%luGB", hsize >> 30); + else if (hsize >= (1UL << 20)) + snprintf(buf, size, "%luMB", hsize >> 20); + else + snprintf(buf, size, "%luKB", hsize >> 10); + return buf; +} + +int __init hugetlb_cgroup_file_init(int idx) +{ + char buf[32]; + struct cftype *cft; + struct hstate *h = &hstates[idx]; + + /* format the size */ + mem_fmt(buf, 32, huge_page_size(h)); + + /* Add the limit file */ + cft = &h->cgroup_files[0]; + snprintf(cft->name, MAX_CFTYPE_NAME, "%s.limit_in_bytes", buf); + cft->private = MEMFILE_PRIVATE(idx, RES_LIMIT); + cft->read = hugetlb_cgroup_read; + cft->write_string = hugetlb_cgroup_write; + + /* Add the usage file */ + cft = &h->cgroup_files[1]; + snprintf(cft->name, MAX_CFTYPE_NAME, "%s.usage_in_bytes", buf); + cft->private = MEMFILE_PRIVATE(idx, RES_USAGE); + cft->read = hugetlb_cgroup_read; + + /* Add the MAX usage file */ + cft = &h->cgroup_files[2]; + snprintf(cft->name, MAX_CFTYPE_NAME, "%s.max_usage_in_bytes", buf); + cft->private = MEMFILE_PRIVATE(idx, RES_MAX_USAGE); + cft->trigger = hugetlb_cgroup_reset; + cft->read = hugetlb_cgroup_read; + + /* Add the failcntfile */ + cft = &h->cgroup_files[3]; + snprintf(cft->name, MAX_CFTYPE_NAME, "%s.failcnt", buf); + cft->private = MEMFILE_PRIVATE(idx, RES_FAILCNT); + cft->trigger = hugetlb_cgroup_reset; + cft->read = hugetlb_cgroup_read; + + /* NULL terminate the last cft */ + cft = &h->cgroup_files[4]; + memset(cft, 0, sizeof(*cft)); + + WARN_ON(cgroup_add_cftypes(&hugetlb_subsys, h->cgroup_files)); + + return 0; +} + +/* + * hugetlb_lock will make sure a parallel cgroup rmdir won't happen + * when we migrate hugepages + */ +void hugetlb_cgroup_migrate(struct page *oldhpage, struct page *newhpage) +{ + struct hugetlb_cgroup *h_cg; + struct hstate *h = page_hstate(oldhpage); + + if (hugetlb_cgroup_disabled()) + return; + + VM_BUG_ON(!PageHuge(oldhpage)); + spin_lock(&hugetlb_lock); + h_cg = hugetlb_cgroup_from_page(oldhpage); + set_hugetlb_cgroup(oldhpage, NULL); + + /* move the h_cg details to new cgroup */ + set_hugetlb_cgroup(newhpage, h_cg); + list_move(&newhpage->lru, &h->hugepage_activelist); + spin_unlock(&hugetlb_lock); + return; +} + +struct cgroup_subsys hugetlb_subsys = { + .name = "hugetlb", + .create = hugetlb_cgroup_create, + .pre_destroy = hugetlb_cgroup_pre_destroy, + .destroy = hugetlb_cgroup_destroy, + .subsys_id = hugetlb_subsys_id, +}; diff --git a/mm/hwpoison-inject.c b/mm/hwpoison-inject.c index cc448bb..3a61efc 100644 --- a/mm/hwpoison-inject.c +++ b/mm/hwpoison-inject.c @@ -123,7 +123,7 @@ static int pfn_inject_init(void) if (!dentry) goto fail; -#ifdef CONFIG_CGROUP_MEM_RES_CTLR_SWAP +#ifdef CONFIG_MEMCG_SWAP dentry = debugfs_create_u64("corrupt-filter-memcg", 0600, hwpoison_dir, &hwpoison_filter_memcg); if (!dentry) diff --git a/mm/internal.h b/mm/internal.h index 2ba87fb..3314f79 100644 --- a/mm/internal.h +++ b/mm/internal.h @@ -118,8 +118,14 @@ struct compact_control { unsigned long nr_freepages; /* Number of isolated free pages */ unsigned long nr_migratepages; /* Number of pages to migrate */ unsigned long free_pfn; /* isolate_freepages search base */ + unsigned long start_free_pfn; /* where we started the search */ unsigned long migrate_pfn; /* isolate_migratepages search base */ bool sync; /* Synchronous migration */ + bool wrapped; /* Order > 0 compactions are + incremental, once free_pfn + and migrate_pfn meet, we restart + from the top of the zone; + remember we wrapped around. */ int order; /* order a direct compactor needs */ int migratetype; /* MOVABLE, RECLAIMABLE etc */ @@ -347,3 +353,5 @@ extern u32 hwpoison_filter_enable; extern unsigned long vm_mmap_pgoff(struct file *, unsigned long, unsigned long, unsigned long, unsigned long, unsigned long); + +extern void set_pageblock_order(void); diff --git a/mm/madvise.c b/mm/madvise.c index deff1b6..14d260f 100644 --- a/mm/madvise.c +++ b/mm/madvise.c @@ -15,6 +15,7 @@ #include <linux/sched.h> #include <linux/ksm.h> #include <linux/fs.h> +#include <linux/file.h> /* * Any behaviour which results in changes to the vma->vm_flags needs to @@ -204,14 +205,16 @@ static long madvise_remove(struct vm_area_struct *vma, { loff_t offset; int error; + struct file *f; *prev = NULL; /* tell sys_madvise we drop mmap_sem */ if (vma->vm_flags & (VM_LOCKED|VM_NONLINEAR|VM_HUGETLB)) return -EINVAL; - if (!vma->vm_file || !vma->vm_file->f_mapping - || !vma->vm_file->f_mapping->host) { + f = vma->vm_file; + + if (!f || !f->f_mapping || !f->f_mapping->host) { return -EINVAL; } @@ -221,11 +224,18 @@ static long madvise_remove(struct vm_area_struct *vma, offset = (loff_t)(start - vma->vm_start) + ((loff_t)vma->vm_pgoff << PAGE_SHIFT); - /* filesystem's fallocate may need to take i_mutex */ + /* + * Filesystem's fallocate may need to take i_mutex. We need to + * explicitly grab a reference because the vma (and hence the + * vma's reference to the file) can go away as soon as we drop + * mmap_sem. + */ + get_file(f); up_read(¤t->mm->mmap_sem); - error = do_fallocate(vma->vm_file, + error = do_fallocate(f, FALLOC_FL_PUNCH_HOLE | FALLOC_FL_KEEP_SIZE, offset, end - start); + fput(f); down_read(¤t->mm->mmap_sem); return error; } diff --git a/mm/memblock.c b/mm/memblock.c index 952123e..4d9393c 100644 --- a/mm/memblock.c +++ b/mm/memblock.c @@ -143,30 +143,6 @@ phys_addr_t __init_memblock memblock_find_in_range(phys_addr_t start, MAX_NUMNODES); } -/* - * Free memblock.reserved.regions - */ -int __init_memblock memblock_free_reserved_regions(void) -{ - if (memblock.reserved.regions == memblock_reserved_init_regions) - return 0; - - return memblock_free(__pa(memblock.reserved.regions), - sizeof(struct memblock_region) * memblock.reserved.max); -} - -/* - * Reserve memblock.reserved.regions - */ -int __init_memblock memblock_reserve_reserved_regions(void) -{ - if (memblock.reserved.regions == memblock_reserved_init_regions) - return 0; - - return memblock_reserve(__pa(memblock.reserved.regions), - sizeof(struct memblock_region) * memblock.reserved.max); -} - static void __init_memblock memblock_remove_region(struct memblock_type *type, unsigned long r) { type->total_size -= type->regions[r].size; @@ -184,9 +160,39 @@ static void __init_memblock memblock_remove_region(struct memblock_type *type, u } } -static int __init_memblock memblock_double_array(struct memblock_type *type) +phys_addr_t __init_memblock get_allocated_memblock_reserved_regions_info( + phys_addr_t *addr) +{ + if (memblock.reserved.regions == memblock_reserved_init_regions) + return 0; + + *addr = __pa(memblock.reserved.regions); + + return PAGE_ALIGN(sizeof(struct memblock_region) * + memblock.reserved.max); +} + +/** + * memblock_double_array - double the size of the memblock regions array + * @type: memblock type of the regions array being doubled + * @new_area_start: starting address of memory range to avoid overlap with + * @new_area_size: size of memory range to avoid overlap with + * + * Double the size of the @type regions array. If memblock is being used to + * allocate memory for a new reserved regions array and there is a previously + * allocated memory range [@new_area_start,@new_area_start+@new_area_size] + * waiting to be reserved, ensure the memory used by the new array does + * not overlap. + * + * RETURNS: + * 0 on success, -1 on failure. + */ +static int __init_memblock memblock_double_array(struct memblock_type *type, + phys_addr_t new_area_start, + phys_addr_t new_area_size) { struct memblock_region *new_array, *old_array; + phys_addr_t old_alloc_size, new_alloc_size; phys_addr_t old_size, new_size, addr; int use_slab = slab_is_available(); int *in_slab; @@ -200,6 +206,12 @@ static int __init_memblock memblock_double_array(struct memblock_type *type) /* Calculate new doubled size */ old_size = type->max * sizeof(struct memblock_region); new_size = old_size << 1; + /* + * We need to allocated new one align to PAGE_SIZE, + * so we can free them completely later. + */ + old_alloc_size = PAGE_ALIGN(old_size); + new_alloc_size = PAGE_ALIGN(new_size); /* Retrieve the slab flag */ if (type == &memblock.memory) @@ -210,19 +222,30 @@ static int __init_memblock memblock_double_array(struct memblock_type *type) /* Try to find some space for it. * * WARNING: We assume that either slab_is_available() and we use it or - * we use MEMBLOCK for allocations. That means that this is unsafe to use - * when bootmem is currently active (unless bootmem itself is implemented - * on top of MEMBLOCK which isn't the case yet) + * we use MEMBLOCK for allocations. That means that this is unsafe to + * use when bootmem is currently active (unless bootmem itself is + * implemented on top of MEMBLOCK which isn't the case yet) * * This should however not be an issue for now, as we currently only - * call into MEMBLOCK while it's still active, or much later when slab is - * active for memory hotplug operations + * call into MEMBLOCK while it's still active, or much later when slab + * is active for memory hotplug operations */ if (use_slab) { new_array = kmalloc(new_size, GFP_KERNEL); addr = new_array ? __pa(new_array) : 0; } else { - addr = memblock_find_in_range(0, MEMBLOCK_ALLOC_ACCESSIBLE, new_size, sizeof(phys_addr_t)); + /* only exclude range when trying to double reserved.regions */ + if (type != &memblock.reserved) + new_area_start = new_area_size = 0; + + addr = memblock_find_in_range(new_area_start + new_area_size, + memblock.current_limit, + new_alloc_size, PAGE_SIZE); + if (!addr && new_area_size) + addr = memblock_find_in_range(0, + min(new_area_start, memblock.current_limit), + new_alloc_size, PAGE_SIZE); + new_array = addr ? __va(addr) : 0; } if (!addr) { @@ -231,12 +254,14 @@ static int __init_memblock memblock_double_array(struct memblock_type *type) return -1; } - memblock_dbg("memblock: %s array is doubled to %ld at [%#010llx-%#010llx]", - memblock_type_name(type), type->max * 2, (u64)addr, (u64)addr + new_size - 1); + memblock_dbg("memblock: %s is doubled to %ld at [%#010llx-%#010llx]", + memblock_type_name(type), type->max * 2, (u64)addr, + (u64)addr + new_size - 1); - /* Found space, we now need to move the array over before - * we add the reserved region since it may be our reserved - * array itself that is full. + /* + * Found space, we now need to move the array over before we add the + * reserved region since it may be our reserved array itself that is + * full. */ memcpy(new_array, type->regions, old_size); memset(new_array + type->max, 0, old_size); @@ -244,20 +269,19 @@ static int __init_memblock memblock_double_array(struct memblock_type *type) type->regions = new_array; type->max <<= 1; - /* Free old array. We needn't free it if the array is the - * static one - */ + /* Free old array. We needn't free it if the array is the static one */ if (*in_slab) kfree(old_array); else if (old_array != memblock_memory_init_regions && old_array != memblock_reserved_init_regions) - memblock_free(__pa(old_array), old_size); + memblock_free(__pa(old_array), old_alloc_size); - /* Reserve the new array if that comes from the memblock. - * Otherwise, we needn't do it + /* + * Reserve the new array if that comes from the memblock. Otherwise, we + * needn't do it */ if (!use_slab) - BUG_ON(memblock_reserve(addr, new_size)); + BUG_ON(memblock_reserve(addr, new_alloc_size)); /* Update slab flag */ *in_slab = use_slab; @@ -399,7 +423,7 @@ repeat: */ if (!insert) { while (type->cnt + nr_new > type->max) - if (memblock_double_array(type) < 0) + if (memblock_double_array(type, obase, size) < 0) return -ENOMEM; insert = true; goto repeat; @@ -450,7 +474,7 @@ static int __init_memblock memblock_isolate_range(struct memblock_type *type, /* we'll create at most two more regions */ while (type->cnt + 2 > type->max) - if (memblock_double_array(type) < 0) + if (memblock_double_array(type, base, size) < 0) return -ENOMEM; for (i = 0; i < type->cnt; i++) { @@ -540,9 +564,9 @@ int __init_memblock memblock_reserve(phys_addr_t base, phys_addr_t size) * __next_free_mem_range - next function for for_each_free_mem_range() * @idx: pointer to u64 loop variable * @nid: nid: node selector, %MAX_NUMNODES for all nodes - * @p_start: ptr to phys_addr_t for start address of the range, can be %NULL - * @p_end: ptr to phys_addr_t for end address of the range, can be %NULL - * @p_nid: ptr to int for nid of the range, can be %NULL + * @out_start: ptr to phys_addr_t for start address of the range, can be %NULL + * @out_end: ptr to phys_addr_t for end address of the range, can be %NULL + * @out_nid: ptr to int for nid of the range, can be %NULL * * Find the first free area from *@idx which matches @nid, fill the out * parameters, and update *@idx for the next iteration. The lower 32bit of @@ -616,9 +640,9 @@ void __init_memblock __next_free_mem_range(u64 *idx, int nid, * __next_free_mem_range_rev - next function for for_each_free_mem_range_reverse() * @idx: pointer to u64 loop variable * @nid: nid: node selector, %MAX_NUMNODES for all nodes - * @p_start: ptr to phys_addr_t for start address of the range, can be %NULL - * @p_end: ptr to phys_addr_t for end address of the range, can be %NULL - * @p_nid: ptr to int for nid of the range, can be %NULL + * @out_start: ptr to phys_addr_t for start address of the range, can be %NULL + * @out_end: ptr to phys_addr_t for end address of the range, can be %NULL + * @out_nid: ptr to int for nid of the range, can be %NULL * * Reverse of __next_free_mem_range(). */ @@ -867,6 +891,16 @@ int __init_memblock memblock_is_memory(phys_addr_t addr) return memblock_search(&memblock.memory, addr) != -1; } +/** + * memblock_is_region_memory - check if a region is a subset of memory + * @base: base of region to check + * @size: size of region to check + * + * Check if the region [@base, @base+@size) is a subset of a memory block. + * + * RETURNS: + * 0 if false, non-zero if true + */ int __init_memblock memblock_is_region_memory(phys_addr_t base, phys_addr_t size) { int idx = memblock_search(&memblock.memory, base); @@ -879,6 +913,16 @@ int __init_memblock memblock_is_region_memory(phys_addr_t base, phys_addr_t size memblock.memory.regions[idx].size) >= end; } +/** + * memblock_is_region_reserved - check if a region intersects reserved memory + * @base: base of region to check + * @size: size of region to check + * + * Check if the region [@base, @base+@size) intersects a reserved memory block. + * + * RETURNS: + * 0 if false, non-zero if true + */ int __init_memblock memblock_is_region_reserved(phys_addr_t base, phys_addr_t size) { memblock_cap_size(base, &size); diff --git a/mm/memcontrol.c b/mm/memcontrol.c index ac35bcc..795e525 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -61,12 +61,12 @@ struct cgroup_subsys mem_cgroup_subsys __read_mostly; #define MEM_CGROUP_RECLAIM_RETRIES 5 static struct mem_cgroup *root_mem_cgroup __read_mostly; -#ifdef CONFIG_CGROUP_MEM_RES_CTLR_SWAP +#ifdef CONFIG_MEMCG_SWAP /* Turned on only when memory cgroup is enabled && really_do_swap_account = 1 */ int do_swap_account __read_mostly; /* for remember boot option*/ -#ifdef CONFIG_CGROUP_MEM_RES_CTLR_SWAP_ENABLED +#ifdef CONFIG_MEMCG_SWAP_ENABLED static int really_do_swap_account __initdata = 1; #else static int really_do_swap_account __initdata = 0; @@ -87,7 +87,7 @@ enum mem_cgroup_stat_index { MEM_CGROUP_STAT_CACHE, /* # of pages charged as cache */ MEM_CGROUP_STAT_RSS, /* # of pages charged as anon rss */ MEM_CGROUP_STAT_FILE_MAPPED, /* # of pages charged as file rss */ - MEM_CGROUP_STAT_SWAPOUT, /* # of pages, swapped out */ + MEM_CGROUP_STAT_SWAP, /* # of pages, swapped out */ MEM_CGROUP_STAT_NSTATS, }; @@ -378,9 +378,7 @@ static bool move_file(void) enum charge_type { MEM_CGROUP_CHARGE_TYPE_CACHE = 0, - MEM_CGROUP_CHARGE_TYPE_MAPPED, - MEM_CGROUP_CHARGE_TYPE_SHMEM, /* used by page migration of shmem */ - MEM_CGROUP_CHARGE_TYPE_FORCE, /* used by force_empty */ + MEM_CGROUP_CHARGE_TYPE_ANON, MEM_CGROUP_CHARGE_TYPE_SWAPOUT, /* for accounting swapcache */ MEM_CGROUP_CHARGE_TYPE_DROP, /* a page was unused swap cache */ NR_CHARGE_TYPE, @@ -407,8 +405,14 @@ enum charge_type { static void mem_cgroup_get(struct mem_cgroup *memcg); static void mem_cgroup_put(struct mem_cgroup *memcg); +static inline +struct mem_cgroup *mem_cgroup_from_css(struct cgroup_subsys_state *s) +{ + return container_of(s, struct mem_cgroup, css); +} + /* Writing them here to avoid exposing memcg's inner layout */ -#ifdef CONFIG_CGROUP_MEM_RES_CTLR_KMEM +#ifdef CONFIG_MEMCG_KMEM #include <net/sock.h> #include <net/ip.h> @@ -467,9 +471,9 @@ struct cg_proto *tcp_proto_cgroup(struct mem_cgroup *memcg) } EXPORT_SYMBOL(tcp_proto_cgroup); #endif /* CONFIG_INET */ -#endif /* CONFIG_CGROUP_MEM_RES_CTLR_KMEM */ +#endif /* CONFIG_MEMCG_KMEM */ -#if defined(CONFIG_INET) && defined(CONFIG_CGROUP_MEM_RES_CTLR_KMEM) +#if defined(CONFIG_INET) && defined(CONFIG_MEMCG_KMEM) static void disarm_sock_keys(struct mem_cgroup *memcg) { if (!memcg_proto_activated(&memcg->tcp_mem.cg_proto)) @@ -703,7 +707,7 @@ static void mem_cgroup_swap_statistics(struct mem_cgroup *memcg, bool charge) { int val = (charge) ? 1 : -1; - this_cpu_add(memcg->stat->count[MEM_CGROUP_STAT_SWAPOUT], val); + this_cpu_add(memcg->stat->count[MEM_CGROUP_STAT_SWAP], val); } static unsigned long mem_cgroup_read_events(struct mem_cgroup *memcg, @@ -864,9 +868,8 @@ static void memcg_check_events(struct mem_cgroup *memcg, struct page *page) struct mem_cgroup *mem_cgroup_from_cont(struct cgroup *cont) { - return container_of(cgroup_subsys_state(cont, - mem_cgroup_subsys_id), struct mem_cgroup, - css); + return mem_cgroup_from_css( + cgroup_subsys_state(cont, mem_cgroup_subsys_id)); } struct mem_cgroup *mem_cgroup_from_task(struct task_struct *p) @@ -879,8 +882,7 @@ struct mem_cgroup *mem_cgroup_from_task(struct task_struct *p) if (unlikely(!p)) return NULL; - return container_of(task_subsys_state(p, mem_cgroup_subsys_id), - struct mem_cgroup, css); + return mem_cgroup_from_css(task_subsys_state(p, mem_cgroup_subsys_id)); } struct mem_cgroup *try_get_mem_cgroup_from_mm(struct mm_struct *mm) @@ -966,8 +968,7 @@ struct mem_cgroup *mem_cgroup_iter(struct mem_cgroup *root, css = css_get_next(&mem_cgroup_subsys, id + 1, &root->css, &id); if (css) { if (css == &root->css || css_tryget(css)) - memcg = container_of(css, - struct mem_cgroup, css); + memcg = mem_cgroup_from_css(css); } else id = 0; rcu_read_unlock(); @@ -1148,7 +1149,7 @@ bool __mem_cgroup_same_or_subtree(const struct mem_cgroup *root_memcg, { if (root_memcg == memcg) return true; - if (!root_memcg->use_hierarchy) + if (!root_memcg->use_hierarchy || !memcg) return false; return css_is_ancestor(&memcg->css, &root_memcg->css); } @@ -1234,7 +1235,7 @@ int mem_cgroup_inactive_file_is_low(struct lruvec *lruvec) /** * mem_cgroup_margin - calculate chargeable space of a memory cgroup - * @mem: the memory cgroup + * @memcg: the memory cgroup * * Returns the maximum amount of memory @mem can be charged with, in * pages. @@ -1454,7 +1455,7 @@ static int mem_cgroup_count_children(struct mem_cgroup *memcg) /* * Return the memory (and swap, if configured) limit for a memcg. */ -u64 mem_cgroup_get_limit(struct mem_cgroup *memcg) +static u64 mem_cgroup_get_limit(struct mem_cgroup *memcg) { u64 limit; u64 memsw; @@ -1470,6 +1471,73 @@ u64 mem_cgroup_get_limit(struct mem_cgroup *memcg) return min(limit, memsw); } +void mem_cgroup_out_of_memory(struct mem_cgroup *memcg, gfp_t gfp_mask, + int order) +{ + struct mem_cgroup *iter; + unsigned long chosen_points = 0; + unsigned long totalpages; + unsigned int points = 0; + struct task_struct *chosen = NULL; + + /* + * If current has a pending SIGKILL, then automatically select it. The + * goal is to allow it to allocate so that it may quickly exit and free + * its memory. + */ + if (fatal_signal_pending(current)) { + set_thread_flag(TIF_MEMDIE); + return; + } + + check_panic_on_oom(CONSTRAINT_MEMCG, gfp_mask, order, NULL); + totalpages = mem_cgroup_get_limit(memcg) >> PAGE_SHIFT ? : 1; + for_each_mem_cgroup_tree(iter, memcg) { + struct cgroup *cgroup = iter->css.cgroup; + struct cgroup_iter it; + struct task_struct *task; + + cgroup_iter_start(cgroup, &it); + while ((task = cgroup_iter_next(cgroup, &it))) { + switch (oom_scan_process_thread(task, totalpages, NULL, + false)) { + case OOM_SCAN_SELECT: + if (chosen) + put_task_struct(chosen); + chosen = task; + chosen_points = ULONG_MAX; + get_task_struct(chosen); + /* fall through */ + case OOM_SCAN_CONTINUE: + continue; + case OOM_SCAN_ABORT: + cgroup_iter_end(cgroup, &it); + mem_cgroup_iter_break(memcg, iter); + if (chosen) + put_task_struct(chosen); + return; + case OOM_SCAN_OK: + break; + }; + points = oom_badness(task, memcg, NULL, totalpages); + if (points > chosen_points) { + if (chosen) + put_task_struct(chosen); + chosen = task; + chosen_points = points; + get_task_struct(chosen); + } + } + cgroup_iter_end(cgroup, &it); + } + + if (!chosen) + return; + points = chosen_points * 1000 / totalpages; + oom_kill_process(chosen, gfp_mask, order, points, totalpages, memcg, + NULL, "Memory cgroup out of memory"); +} + static unsigned long mem_cgroup_reclaim(struct mem_cgroup *memcg, gfp_t gfp_mask, unsigned long flags) @@ -1508,7 +1576,7 @@ static unsigned long mem_cgroup_reclaim(struct mem_cgroup *memcg, /** * test_mem_cgroup_node_reclaimable - * @mem: the target memcg + * @memcg: the target memcg * @nid: the node ID to be checked. * @noswap : specify true here if the user wants flle only information. * @@ -1899,7 +1967,7 @@ again: return; /* * If this memory cgroup is not under account moving, we don't - * need to take move_lock_page_cgroup(). Because we already hold + * need to take move_lock_mem_cgroup(). Because we already hold * rcu_read_lock(), any calls to move_account will be delayed until * rcu_read_unlock() if mem_cgroup_stolen() == true. */ @@ -1921,7 +1989,7 @@ void __mem_cgroup_end_update_page_stat(struct page *page, unsigned long *flags) /* * It's guaranteed that pc->mem_cgroup never changes while * lock is held because a routine modifies pc->mem_cgroup - * should take move_lock_page_cgroup(). + * should take move_lock_mem_cgroup(). */ move_unlock_mem_cgroup(pc->mem_cgroup, flags); } @@ -2268,7 +2336,7 @@ static int __mem_cgroup_try_charge(struct mm_struct *mm, * We always charge the cgroup the mm_struct belongs to. * The mm_struct's mem_cgroup changes on task migration if the * thread group leader migrates. It's possible that mm is not - * set, if so charge the init_mm (happens for pagecache usage). + * set, if so charge the root memcg (happens for pagecache usage). */ if (!*ptr && !mm) *ptr = root_mem_cgroup; @@ -2429,7 +2497,7 @@ static struct mem_cgroup *mem_cgroup_lookup(unsigned short id) css = css_lookup(&mem_cgroup_subsys, id); if (!css) return NULL; - return container_of(css, struct mem_cgroup, css); + return mem_cgroup_from_css(css); } struct mem_cgroup *try_get_mem_cgroup_from_page(struct page *page) @@ -2473,11 +2541,7 @@ static void __mem_cgroup_commit_charge(struct mem_cgroup *memcg, bool anon; lock_page_cgroup(pc); - if (unlikely(PageCgroupUsed(pc))) { - unlock_page_cgroup(pc); - __mem_cgroup_cancel_charge(memcg, nr_pages); - return; - } + VM_BUG_ON(PageCgroupUsed(pc)); /* * we don't need page_cgroup_lock about tail pages, becase they are not * accessed by any other context at this point. @@ -2519,7 +2583,7 @@ static void __mem_cgroup_commit_charge(struct mem_cgroup *memcg, spin_unlock_irq(&zone->lru_lock); } - if (ctype == MEM_CGROUP_CHARGE_TYPE_MAPPED) + if (ctype == MEM_CGROUP_CHARGE_TYPE_ANON) anon = true; else anon = false; @@ -2644,8 +2708,7 @@ out: static int mem_cgroup_move_parent(struct page *page, struct page_cgroup *pc, - struct mem_cgroup *child, - gfp_t gfp_mask) + struct mem_cgroup *child) { struct mem_cgroup *parent; unsigned int nr_pages; @@ -2728,38 +2791,7 @@ int mem_cgroup_newpage_charge(struct page *page, VM_BUG_ON(page->mapping && !PageAnon(page)); VM_BUG_ON(!mm); return mem_cgroup_charge_common(page, mm, gfp_mask, - MEM_CGROUP_CHARGE_TYPE_MAPPED); -} - -static void -__mem_cgroup_commit_charge_swapin(struct page *page, struct mem_cgroup *ptr, - enum charge_type ctype); - -int mem_cgroup_cache_charge(struct page *page, struct mm_struct *mm, - gfp_t gfp_mask) -{ - struct mem_cgroup *memcg = NULL; - enum charge_type type = MEM_CGROUP_CHARGE_TYPE_CACHE; - int ret; - - if (mem_cgroup_disabled()) - return 0; - if (PageCompound(page)) - return 0; - - if (unlikely(!mm)) - mm = &init_mm; - if (!page_is_file_cache(page)) - type = MEM_CGROUP_CHARGE_TYPE_SHMEM; - - if (!PageSwapCache(page)) - ret = mem_cgroup_charge_common(page, mm, gfp_mask, type); - else { /* page is swapcache/shmem */ - ret = mem_cgroup_try_charge_swapin(mm, page, gfp_mask, &memcg); - if (!ret) - __mem_cgroup_commit_charge_swapin(page, memcg, type); - } - return ret; + MEM_CGROUP_CHARGE_TYPE_ANON); } /* @@ -2768,27 +2800,26 @@ int mem_cgroup_cache_charge(struct page *page, struct mm_struct *mm, * struct page_cgroup is acquired. This refcnt will be consumed by * "commit()" or removed by "cancel()" */ -int mem_cgroup_try_charge_swapin(struct mm_struct *mm, - struct page *page, - gfp_t mask, struct mem_cgroup **memcgp) +static int __mem_cgroup_try_charge_swapin(struct mm_struct *mm, + struct page *page, + gfp_t mask, + struct mem_cgroup **memcgp) { struct mem_cgroup *memcg; + struct page_cgroup *pc; int ret; - *memcgp = NULL; - - if (mem_cgroup_disabled()) - return 0; - - if (!do_swap_account) - goto charge_cur_mm; + pc = lookup_page_cgroup(page); /* - * A racing thread's fault, or swapoff, may have already updated - * the pte, and even removed page from swap cache: in those cases - * do_swap_page()'s pte_same() test will fail; but there's also a - * KSM case which does need to charge the page. + * Every swap fault against a single page tries to charge the + * page, bail as early as possible. shmem_unuse() encounters + * already charged pages, too. The USED bit is protected by + * the page lock, which serializes swap cache removal, which + * in turn serializes uncharging. */ - if (!PageSwapCache(page)) + if (PageCgroupUsed(pc)) + return 0; + if (!do_swap_account) goto charge_cur_mm; memcg = try_get_mem_cgroup_from_page(page); if (!memcg) @@ -2800,14 +2831,44 @@ int mem_cgroup_try_charge_swapin(struct mm_struct *mm, ret = 0; return ret; charge_cur_mm: - if (unlikely(!mm)) - mm = &init_mm; ret = __mem_cgroup_try_charge(mm, mask, 1, memcgp, true); if (ret == -EINTR) ret = 0; return ret; } +int mem_cgroup_try_charge_swapin(struct mm_struct *mm, struct page *page, + gfp_t gfp_mask, struct mem_cgroup **memcgp) +{ + *memcgp = NULL; + if (mem_cgroup_disabled()) + return 0; + /* + * A racing thread's fault, or swapoff, may have already + * updated the pte, and even removed page from swap cache: in + * those cases unuse_pte()'s pte_same() test will fail; but + * there's also a KSM case which does need to charge the page. + */ + if (!PageSwapCache(page)) { + int ret; + + ret = __mem_cgroup_try_charge(mm, gfp_mask, 1, memcgp, true); + if (ret == -EINTR) + ret = 0; + return ret; + } + return __mem_cgroup_try_charge_swapin(mm, page, gfp_mask, memcgp); +} + +void mem_cgroup_cancel_charge_swapin(struct mem_cgroup *memcg) +{ + if (mem_cgroup_disabled()) + return; + if (!memcg) + return; + __mem_cgroup_cancel_charge(memcg, 1); +} + static void __mem_cgroup_commit_charge_swapin(struct page *page, struct mem_cgroup *memcg, enum charge_type ctype) @@ -2842,16 +2903,30 @@ void mem_cgroup_commit_charge_swapin(struct page *page, struct mem_cgroup *memcg) { __mem_cgroup_commit_charge_swapin(page, memcg, - MEM_CGROUP_CHARGE_TYPE_MAPPED); + MEM_CGROUP_CHARGE_TYPE_ANON); } -void mem_cgroup_cancel_charge_swapin(struct mem_cgroup *memcg) +int mem_cgroup_cache_charge(struct page *page, struct mm_struct *mm, + gfp_t gfp_mask) { + struct mem_cgroup *memcg = NULL; + enum charge_type type = MEM_CGROUP_CHARGE_TYPE_CACHE; + int ret; + if (mem_cgroup_disabled()) - return; - if (!memcg) - return; - __mem_cgroup_cancel_charge(memcg, 1); + return 0; + if (PageCompound(page)) + return 0; + + if (!PageSwapCache(page)) + ret = mem_cgroup_charge_common(page, mm, gfp_mask, type); + else { /* page is swapcache/shmem */ + ret = __mem_cgroup_try_charge_swapin(mm, page, + gfp_mask, &memcg); + if (!ret) + __mem_cgroup_commit_charge_swapin(page, memcg, type); + } + return ret; } static void mem_cgroup_do_uncharge(struct mem_cgroup *memcg, @@ -2911,7 +2986,8 @@ direct_uncharge: * uncharge if !page_mapped(page) */ static struct mem_cgroup * -__mem_cgroup_uncharge_common(struct page *page, enum charge_type ctype) +__mem_cgroup_uncharge_common(struct page *page, enum charge_type ctype, + bool end_migration) { struct mem_cgroup *memcg = NULL; unsigned int nr_pages = 1; @@ -2921,8 +2997,7 @@ __mem_cgroup_uncharge_common(struct page *page, enum charge_type ctype) if (mem_cgroup_disabled()) return NULL; - if (PageSwapCache(page)) - return NULL; + VM_BUG_ON(PageSwapCache(page)); if (PageTransHuge(page)) { nr_pages <<= compound_order(page); @@ -2945,7 +3020,7 @@ __mem_cgroup_uncharge_common(struct page *page, enum charge_type ctype) anon = PageAnon(page); switch (ctype) { - case MEM_CGROUP_CHARGE_TYPE_MAPPED: + case MEM_CGROUP_CHARGE_TYPE_ANON: /* * Generally PageAnon tells if it's the anon statistics to be * updated; but sometimes e.g. mem_cgroup_uncharge_page() is @@ -2955,7 +3030,16 @@ __mem_cgroup_uncharge_common(struct page *page, enum charge_type ctype) /* fallthrough */ case MEM_CGROUP_CHARGE_TYPE_DROP: /* See mem_cgroup_prepare_migration() */ - if (page_mapped(page) || PageCgroupMigration(pc)) + if (page_mapped(page)) + goto unlock_out; + /* + * Pages under migration may not be uncharged. But + * end_migration() /must/ be the one uncharging the + * unused post-migration page and so it has to call + * here with the migration bit still set. See the + * res_counter handling below. + */ + if (!end_migration && PageCgroupMigration(pc)) goto unlock_out; break; case MEM_CGROUP_CHARGE_TYPE_SWAPOUT: @@ -2989,7 +3073,12 @@ __mem_cgroup_uncharge_common(struct page *page, enum charge_type ctype) mem_cgroup_swap_statistics(memcg, true); mem_cgroup_get(memcg); } - if (!mem_cgroup_is_root(memcg)) + /* + * Migration does not charge the res_counter for the + * replacement page, so leave it alone when phasing out the + * page that is unused after the migration. + */ + if (!end_migration && !mem_cgroup_is_root(memcg)) mem_cgroup_do_uncharge(memcg, nr_pages, ctype); return memcg; @@ -3005,14 +3094,16 @@ void mem_cgroup_uncharge_page(struct page *page) if (page_mapped(page)) return; VM_BUG_ON(page->mapping && !PageAnon(page)); - __mem_cgroup_uncharge_common(page, MEM_CGROUP_CHARGE_TYPE_MAPPED); + if (PageSwapCache(page)) + return; + __mem_cgroup_uncharge_common(page, MEM_CGROUP_CHARGE_TYPE_ANON, false); } void mem_cgroup_uncharge_cache_page(struct page *page) { VM_BUG_ON(page_mapped(page)); VM_BUG_ON(page->mapping); - __mem_cgroup_uncharge_common(page, MEM_CGROUP_CHARGE_TYPE_CACHE); + __mem_cgroup_uncharge_common(page, MEM_CGROUP_CHARGE_TYPE_CACHE, false); } /* @@ -3076,7 +3167,7 @@ mem_cgroup_uncharge_swapcache(struct page *page, swp_entry_t ent, bool swapout) if (!swapout) /* this was a swap cache but the swap is unused ! */ ctype = MEM_CGROUP_CHARGE_TYPE_DROP; - memcg = __mem_cgroup_uncharge_common(page, ctype); + memcg = __mem_cgroup_uncharge_common(page, ctype, false); /* * record memcg information, if swapout && memcg != NULL, @@ -3087,7 +3178,7 @@ mem_cgroup_uncharge_swapcache(struct page *page, swp_entry_t ent, bool swapout) } #endif -#ifdef CONFIG_CGROUP_MEM_RES_CTLR_SWAP +#ifdef CONFIG_MEMCG_SWAP /* * called from swap_entry_free(). remove record in swap_cgroup and * uncharge "memsw" account. @@ -3166,19 +3257,18 @@ static inline int mem_cgroup_move_swap_account(swp_entry_t entry, * Before starting migration, account PAGE_SIZE to mem_cgroup that the old * page belongs to. */ -int mem_cgroup_prepare_migration(struct page *page, - struct page *newpage, struct mem_cgroup **memcgp, gfp_t gfp_mask) +void mem_cgroup_prepare_migration(struct page *page, struct page *newpage, + struct mem_cgroup **memcgp) { struct mem_cgroup *memcg = NULL; struct page_cgroup *pc; enum charge_type ctype; - int ret = 0; *memcgp = NULL; VM_BUG_ON(PageTransHuge(page)); if (mem_cgroup_disabled()) - return 0; + return; pc = lookup_page_cgroup(page); lock_page_cgroup(pc); @@ -3223,24 +3313,9 @@ int mem_cgroup_prepare_migration(struct page *page, * we return here. */ if (!memcg) - return 0; + return; *memcgp = memcg; - ret = __mem_cgroup_try_charge(NULL, gfp_mask, 1, memcgp, false); - css_put(&memcg->css);/* drop extra refcnt */ - if (ret) { - if (PageAnon(page)) { - lock_page_cgroup(pc); - ClearPageCgroupMigration(pc); - unlock_page_cgroup(pc); - /* - * The old page may be fully unmapped while we kept it. - */ - mem_cgroup_uncharge_page(page); - } - /* we'll need to revisit this error code (we have -EINTR) */ - return -ENOMEM; - } /* * We charge new page before it's used/mapped. So, even if unlock_page() * is called before end_migration, we can catch all events on this new @@ -3248,13 +3323,15 @@ int mem_cgroup_prepare_migration(struct page *page, * mapcount will be finally 0 and we call uncharge in end_migration(). */ if (PageAnon(page)) - ctype = MEM_CGROUP_CHARGE_TYPE_MAPPED; - else if (page_is_file_cache(page)) - ctype = MEM_CGROUP_CHARGE_TYPE_CACHE; + ctype = MEM_CGROUP_CHARGE_TYPE_ANON; else - ctype = MEM_CGROUP_CHARGE_TYPE_SHMEM; + ctype = MEM_CGROUP_CHARGE_TYPE_CACHE; + /* + * The page is committed to the memcg, but it's not actually + * charged to the res_counter since we plan on replacing the + * old one and only one page is going to be left afterwards. + */ __mem_cgroup_commit_charge(memcg, newpage, 1, ctype, false); - return ret; } /* remove redundant charge if migration failed*/ @@ -3276,6 +3353,12 @@ void mem_cgroup_end_migration(struct mem_cgroup *memcg, used = newpage; unused = oldpage; } + anon = PageAnon(used); + __mem_cgroup_uncharge_common(unused, + anon ? MEM_CGROUP_CHARGE_TYPE_ANON + : MEM_CGROUP_CHARGE_TYPE_CACHE, + true); + css_put(&memcg->css); /* * We disallowed uncharge of pages under migration because mapcount * of the page goes down to zero, temporarly. @@ -3285,10 +3368,6 @@ void mem_cgroup_end_migration(struct mem_cgroup *memcg, lock_page_cgroup(pc); ClearPageCgroupMigration(pc); unlock_page_cgroup(pc); - anon = PageAnon(used); - __mem_cgroup_uncharge_common(unused, - anon ? MEM_CGROUP_CHARGE_TYPE_MAPPED - : MEM_CGROUP_CHARGE_TYPE_CACHE); /* * If a page is a file cache, radix-tree replacement is very atomic @@ -3340,10 +3419,6 @@ void mem_cgroup_replace_page_cache(struct page *oldpage, */ if (!memcg) return; - - if (PageSwapBacked(oldpage)) - type = MEM_CGROUP_CHARGE_TYPE_SHMEM; - /* * Even if newpage->mapping was NULL before starting replacement, * the newpage may be on LRU(or pagevec for LRU) already. We lock @@ -3418,7 +3493,7 @@ 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 memcg->res.limit < memcg->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); @@ -3479,7 +3554,7 @@ 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 memcg->res.limit < memcg->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); @@ -3611,10 +3686,12 @@ 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. + * Traverse a specified page_cgroup list and try to drop them all. This doesn't + * reclaim the pages page themselves - it just removes the page_cgroups. + * Returns true if some page_cgroups were not freed, indicating that the caller + * must retry this operation. */ -static int mem_cgroup_force_empty_list(struct mem_cgroup *memcg, +static bool mem_cgroup_force_empty_list(struct mem_cgroup *memcg, int node, int zid, enum lru_list lru) { struct mem_cgroup_per_zone *mz; @@ -3622,7 +3699,6 @@ static int mem_cgroup_force_empty_list(struct mem_cgroup *memcg, struct list_head *list; struct page *busy; struct zone *zone; - int ret = 0; zone = &NODE_DATA(node)->node_zones[zid]; mz = mem_cgroup_zoneinfo(memcg, node, zid); @@ -3636,7 +3712,6 @@ static int mem_cgroup_force_empty_list(struct mem_cgroup *memcg, struct page_cgroup *pc; struct page *page; - ret = 0; spin_lock_irqsave(&zone->lru_lock, flags); if (list_empty(list)) { spin_unlock_irqrestore(&zone->lru_lock, flags); @@ -3653,21 +3728,14 @@ static int mem_cgroup_force_empty_list(struct mem_cgroup *memcg, pc = lookup_page_cgroup(page); - ret = mem_cgroup_move_parent(page, pc, memcg, GFP_KERNEL); - if (ret == -ENOMEM || ret == -EINTR) - break; - - if (ret == -EBUSY || ret == -EINVAL) { + if (mem_cgroup_move_parent(page, pc, memcg)) { /* found lock contention or "pc" is obsolete. */ busy = page; cond_resched(); } else busy = NULL; } - - if (!ret && !list_empty(list)) - return -EBUSY; - return ret; + return !list_empty(list); } /* @@ -3692,9 +3760,6 @@ move_account: ret = -EBUSY; if (cgroup_task_count(cgrp) || !list_empty(&cgrp->children)) goto out; - ret = -EINTR; - if (signal_pending(current)) - goto out; /* This is for making all *used* pages to be on LRU. */ lru_add_drain_all(); drain_all_stock_sync(memcg); @@ -3715,9 +3780,6 @@ move_account: } 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 (res_counter_read_u64(&memcg->res, RES_USAGE) > 0 || ret); @@ -3779,6 +3841,10 @@ static int mem_cgroup_hierarchy_write(struct cgroup *cont, struct cftype *cft, parent_memcg = mem_cgroup_from_cont(parent); cgroup_lock(); + + if (memcg->use_hierarchy == val) + goto out; + /* * If parent's use_hierarchy is set, we can't make any modifications * in the child subtrees. If it is unset, then the change can @@ -3795,6 +3861,8 @@ static int mem_cgroup_hierarchy_write(struct cgroup *cont, struct cftype *cft, retval = -EBUSY; } else retval = -EINVAL; + +out: cgroup_unlock(); return retval; @@ -3831,7 +3899,7 @@ static inline u64 mem_cgroup_usage(struct mem_cgroup *memcg, bool swap) val += mem_cgroup_recursive_stat(memcg, MEM_CGROUP_STAT_RSS); if (swap) - val += mem_cgroup_recursive_stat(memcg, MEM_CGROUP_STAT_SWAPOUT); + val += mem_cgroup_recursive_stat(memcg, MEM_CGROUP_STAT_SWAP); return val << PAGE_SHIFT; } @@ -4015,7 +4083,7 @@ static int mem_cgroup_move_charge_write(struct cgroup *cgrp, #endif #ifdef CONFIG_NUMA -static int mem_control_numa_stat_show(struct cgroup *cont, struct cftype *cft, +static int memcg_numa_stat_show(struct cgroup *cont, struct cftype *cft, struct seq_file *m) { int nid; @@ -4074,7 +4142,7 @@ static inline void mem_cgroup_lru_names_not_uptodate(void) BUILD_BUG_ON(ARRAY_SIZE(mem_cgroup_lru_names) != NR_LRU_LISTS); } -static int mem_control_stat_show(struct cgroup *cont, struct cftype *cft, +static int memcg_stat_show(struct cgroup *cont, struct cftype *cft, struct seq_file *m) { struct mem_cgroup *memcg = mem_cgroup_from_cont(cont); @@ -4082,7 +4150,7 @@ static int mem_control_stat_show(struct cgroup *cont, struct cftype *cft, unsigned int i; for (i = 0; i < MEM_CGROUP_STAT_NSTATS; i++) { - if (i == MEM_CGROUP_STAT_SWAPOUT && !do_swap_account) + if (i == MEM_CGROUP_STAT_SWAP && !do_swap_account) continue; seq_printf(m, "%s %ld\n", mem_cgroup_stat_names[i], mem_cgroup_read_stat(memcg, i) * PAGE_SIZE); @@ -4109,7 +4177,7 @@ static int mem_control_stat_show(struct cgroup *cont, struct cftype *cft, for (i = 0; i < MEM_CGROUP_STAT_NSTATS; i++) { long long val = 0; - if (i == MEM_CGROUP_STAT_SWAPOUT && !do_swap_account) + if (i == MEM_CGROUP_STAT_SWAP && !do_swap_account) continue; for_each_mem_cgroup_tree(mi, memcg) val += mem_cgroup_read_stat(mi, i) * PAGE_SIZE; @@ -4533,7 +4601,7 @@ static int mem_cgroup_oom_control_write(struct cgroup *cgrp, return 0; } -#ifdef CONFIG_CGROUP_MEM_RES_CTLR_KMEM +#ifdef CONFIG_MEMCG_KMEM static int memcg_init_kmem(struct mem_cgroup *memcg, struct cgroup_subsys *ss) { return mem_cgroup_sockets_init(memcg, ss); @@ -4588,7 +4656,7 @@ static struct cftype mem_cgroup_files[] = { }, { .name = "stat", - .read_seq_string = mem_control_stat_show, + .read_seq_string = memcg_stat_show, }, { .name = "force_empty", @@ -4620,10 +4688,10 @@ static struct cftype mem_cgroup_files[] = { #ifdef CONFIG_NUMA { .name = "numa_stat", - .read_seq_string = mem_control_numa_stat_show, + .read_seq_string = memcg_numa_stat_show, }, #endif -#ifdef CONFIG_CGROUP_MEM_RES_CTLR_SWAP +#ifdef CONFIG_MEMCG_SWAP { .name = "memsw.usage_in_bytes", .private = MEMFILE_PRIVATE(_MEMSWAP, RES_USAGE), @@ -4810,7 +4878,7 @@ struct mem_cgroup *parent_mem_cgroup(struct mem_cgroup *memcg) } EXPORT_SYMBOL(parent_mem_cgroup); -#ifdef CONFIG_CGROUP_MEM_RES_CTLR_SWAP +#ifdef CONFIG_MEMCG_SWAP static void __init enable_swap_cgroup(void) { if (!mem_cgroup_disabled() && really_do_swap_account) @@ -5541,7 +5609,7 @@ struct cgroup_subsys mem_cgroup_subsys = { .__DEPRECATED_clear_css_refs = true, }; -#ifdef CONFIG_CGROUP_MEM_RES_CTLR_SWAP +#ifdef CONFIG_MEMCG_SWAP static int __init enable_swap_account(char *s) { /* consider enabled if no parameter or 1 is given */ diff --git a/mm/memory-failure.c b/mm/memory-failure.c index ab1e714..a6e2141 100644 --- a/mm/memory-failure.c +++ b/mm/memory-failure.c @@ -128,7 +128,7 @@ static int hwpoison_filter_flags(struct page *p) * can only guarantee that the page either belongs to the memcg tasks, or is * a freed page. */ -#ifdef CONFIG_CGROUP_MEM_RES_CTLR_SWAP +#ifdef CONFIG_MEMCG_SWAP u64 hwpoison_filter_memcg; EXPORT_SYMBOL_GPL(hwpoison_filter_memcg); static int hwpoison_filter_task(struct page *p) @@ -345,14 +345,14 @@ static void add_to_kill(struct task_struct *tsk, struct page *p, * Also when FAIL is set do a force kill because something went * wrong earlier. */ -static void kill_procs(struct list_head *to_kill, int doit, int trapno, +static void kill_procs(struct list_head *to_kill, int forcekill, int trapno, int fail, struct page *page, unsigned long pfn, int flags) { struct to_kill *tk, *next; list_for_each_entry_safe (tk, next, to_kill, nd) { - if (doit) { + if (forcekill) { /* * In case something went wrong with munmapping * make sure the process doesn't catch the @@ -858,7 +858,7 @@ static int hwpoison_user_mappings(struct page *p, unsigned long pfn, struct address_space *mapping; LIST_HEAD(tokill); int ret; - int kill = 1; + int kill = 1, forcekill; struct page *hpage = compound_head(p); struct page *ppage; @@ -888,7 +888,7 @@ static int hwpoison_user_mappings(struct page *p, unsigned long pfn, * be called inside page lock (it's recommended but not enforced). */ mapping = page_mapping(hpage); - if (!PageDirty(hpage) && mapping && + if (!(flags & MF_MUST_KILL) && !PageDirty(hpage) && mapping && mapping_cap_writeback_dirty(mapping)) { if (page_mkclean(hpage)) { SetPageDirty(hpage); @@ -965,12 +965,14 @@ static int hwpoison_user_mappings(struct page *p, unsigned long pfn, * Now that the dirty bit has been propagated to the * struct page and all unmaps done we can decide if * killing is needed or not. Only kill when the page - * was dirty, otherwise the tokill list is merely + * was dirty or the process is not restartable, + * otherwise the tokill list is merely * freed. When there was a problem unmapping earlier * use a more force-full uncatchable kill to prevent * any accesses to the poisoned memory. */ - kill_procs(&tokill, !!PageDirty(ppage), trapno, + forcekill = PageDirty(ppage) || (flags & MF_MUST_KILL); + kill_procs(&tokill, forcekill, trapno, ret != SWAP_SUCCESS, p, pfn, flags); return ret; @@ -1414,7 +1416,6 @@ static int soft_offline_huge_page(struct page *page, int flags) int ret; unsigned long pfn = page_to_pfn(page); struct page *hpage = compound_head(page); - LIST_HEAD(pagelist); ret = get_any_page(page, pfn, flags); if (ret < 0) @@ -1429,24 +1430,18 @@ static int soft_offline_huge_page(struct page *page, int flags) } /* Keep page count to indicate a given hugepage is isolated. */ - - list_add(&hpage->lru, &pagelist); - ret = migrate_huge_pages(&pagelist, new_page, MPOL_MF_MOVE_ALL, 0, - true); + ret = migrate_huge_page(hpage, new_page, MPOL_MF_MOVE_ALL, false, + MIGRATE_SYNC); + put_page(hpage); if (ret) { - struct page *page1, *page2; - list_for_each_entry_safe(page1, page2, &pagelist, lru) - put_page(page1); - pr_info("soft offline: %#lx: migration failed %d, type %lx\n", pfn, ret, page->flags); - if (ret > 0) - ret = -EIO; return ret; } done: if (!PageHWPoison(hpage)) - atomic_long_add(1 << compound_trans_order(hpage), &mce_bad_pages); + atomic_long_add(1 << compound_trans_order(hpage), + &mce_bad_pages); set_page_hwpoison_huge_page(hpage); dequeue_hwpoisoned_huge_page(hpage); /* keep elevated page count for bad page */ @@ -1561,7 +1556,7 @@ int soft_offline_page(struct page *page, int flags) page_is_file_cache(page)); list_add(&page->lru, &pagelist); ret = migrate_pages(&pagelist, new_page, MPOL_MF_MOVE_ALL, - 0, MIGRATE_SYNC); + false, MIGRATE_SYNC); if (ret) { putback_lru_pages(&pagelist); pr_info("soft offline: %#lx: migration failed %d, type %lx\n", diff --git a/mm/memory.c b/mm/memory.c index 1b7dc66..482f089 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -206,6 +206,8 @@ void tlb_gather_mmu(struct mmu_gather *tlb, struct mm_struct *mm, bool fullmm) tlb->mm = mm; tlb->fullmm = fullmm; + tlb->start = -1UL; + tlb->end = 0; tlb->need_flush = 0; tlb->fast_mode = (num_possible_cpus() == 1); tlb->local.next = NULL; @@ -248,6 +250,8 @@ void tlb_finish_mmu(struct mmu_gather *tlb, unsigned long start, unsigned long e { struct mmu_gather_batch *batch, *next; + tlb->start = start; + tlb->end = end; tlb_flush_mmu(tlb); /* keep the page table cache within bounds */ @@ -1204,6 +1208,11 @@ again: */ if (force_flush) { force_flush = 0; + +#ifdef HAVE_GENERIC_MMU_GATHER + tlb->start = addr; + tlb->end = end; +#endif tlb_flush_mmu(tlb); if (addr != end) goto again; @@ -1225,7 +1234,15 @@ static inline unsigned long zap_pmd_range(struct mmu_gather *tlb, next = pmd_addr_end(addr, end); if (pmd_trans_huge(*pmd)) { if (next - addr != HPAGE_PMD_SIZE) { - VM_BUG_ON(!rwsem_is_locked(&tlb->mm->mmap_sem)); +#ifdef CONFIG_DEBUG_VM + if (!rwsem_is_locked(&tlb->mm->mmap_sem)) { + pr_err("%s: mmap_sem is unlocked! addr=0x%lx end=0x%lx vma->vm_start=0x%lx vma->vm_end=0x%lx\n", + __func__, addr, end, + vma->vm_start, + vma->vm_end); + BUG(); + } +#endif split_huge_page_pmd(vma->vm_mm, pmd); } else if (zap_huge_pmd(tlb, vma, pmd, addr)) goto next; @@ -1326,8 +1343,11 @@ static void unmap_single_vma(struct mmu_gather *tlb, * Since no pte has actually been setup, it is * safe to do nothing in this case. */ - if (vma->vm_file) - unmap_hugepage_range(vma, start, end, NULL); + if (vma->vm_file) { + mutex_lock(&vma->vm_file->f_mapping->i_mmap_mutex); + __unmap_hugepage_range_final(tlb, vma, start, end, NULL); + mutex_unlock(&vma->vm_file->f_mapping->i_mmap_mutex); + } } else unmap_page_range(tlb, vma, start, end, details); } @@ -1366,7 +1386,7 @@ void unmap_vmas(struct mmu_gather *tlb, /** * zap_page_range - remove user pages in a given range * @vma: vm_area_struct holding the applicable pages - * @address: starting address of pages to zap + * @start: starting address of pages to zap * @size: number of bytes to zap * @details: details of nonlinear truncation or shared cache invalidation * @@ -3921,7 +3941,7 @@ void print_vma_addr(char *prefix, unsigned long ip) free_page((unsigned long)buf); } } - up_read(¤t->mm->mmap_sem); + up_read(&mm->mmap_sem); } #ifdef CONFIG_PROVE_LOCKING diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c index 0d7e3ec..3ad25f9 100644 --- a/mm/memory_hotplug.c +++ b/mm/memory_hotplug.c @@ -512,19 +512,20 @@ int __ref online_pages(unsigned long pfn, unsigned long nr_pages) zone->present_pages += onlined_pages; zone->zone_pgdat->node_present_pages += onlined_pages; - if (need_zonelists_rebuild) - build_all_zonelists(zone); - else - zone_pcp_update(zone); + if (onlined_pages) { + node_set_state(zone_to_nid(zone), N_HIGH_MEMORY); + if (need_zonelists_rebuild) + build_all_zonelists(NULL, zone); + else + zone_pcp_update(zone); + } mutex_unlock(&zonelists_mutex); init_per_zone_wmark_min(); - if (onlined_pages) { + if (onlined_pages) kswapd_run(zone_to_nid(zone)); - node_set_state(zone_to_nid(zone), N_HIGH_MEMORY); - } vm_total_pages = nr_free_pagecache_pages(); @@ -562,7 +563,7 @@ static pg_data_t __ref *hotadd_new_pgdat(int nid, u64 start) * to access not-initialized zonelist, build here. */ mutex_lock(&zonelists_mutex); - build_all_zonelists(NULL); + build_all_zonelists(pgdat, NULL); mutex_unlock(&zonelists_mutex); return pgdat; @@ -618,7 +619,7 @@ int __ref add_memory(int nid, u64 start, u64 size) pgdat = hotadd_new_pgdat(nid, start); ret = -ENOMEM; if (!pgdat) - goto out; + goto error; new_pgdat = 1; } @@ -965,6 +966,9 @@ repeat: init_per_zone_wmark_min(); + if (!populated_zone(zone)) + zone_pcp_reset(zone); + if (!node_present_pages(node)) { node_clear_state(node, N_HIGH_MEMORY); kswapd_stop(node); diff --git a/mm/mempolicy.c b/mm/mempolicy.c index f15c1b2..bd92431 100644 --- a/mm/mempolicy.c +++ b/mm/mempolicy.c @@ -1177,7 +1177,7 @@ static long do_mbind(unsigned long start, unsigned long len, if (!list_empty(&pagelist)) { nr_failed = migrate_pages(&pagelist, new_vma_page, (unsigned long)vma, - false, true); + false, MIGRATE_SYNC); if (nr_failed) putback_lru_pages(&pagelist); } @@ -1602,8 +1602,14 @@ static unsigned interleave_nodes(struct mempolicy *policy) * task can change it's policy. The system default policy requires no * such protection. */ -unsigned slab_node(struct mempolicy *policy) +unsigned slab_node(void) { + struct mempolicy *policy; + + if (in_interrupt()) + return numa_node_id(); + + policy = current->mempolicy; if (!policy || policy->flags & MPOL_F_LOCAL) return numa_node_id(); diff --git a/mm/migrate.c b/mm/migrate.c index be26d5c..77ed2d7 100644 --- a/mm/migrate.c +++ b/mm/migrate.c @@ -33,6 +33,7 @@ #include <linux/memcontrol.h> #include <linux/syscalls.h> #include <linux/hugetlb.h> +#include <linux/hugetlb_cgroup.h> #include <linux/gfp.h> #include <asm/tlbflush.h> @@ -682,7 +683,6 @@ static int __unmap_and_move(struct page *page, struct page *newpage, { int rc = -EAGAIN; int remap_swapcache = 1; - int charge = 0; struct mem_cgroup *mem; struct anon_vma *anon_vma = NULL; @@ -724,12 +724,7 @@ static int __unmap_and_move(struct page *page, struct page *newpage, } /* charge against new page */ - charge = mem_cgroup_prepare_migration(page, newpage, &mem, GFP_KERNEL); - if (charge == -ENOMEM) { - rc = -ENOMEM; - goto unlock; - } - BUG_ON(charge); + mem_cgroup_prepare_migration(page, newpage, &mem); if (PageWriteback(page)) { /* @@ -819,8 +814,7 @@ skip_unmap: put_anon_vma(anon_vma); uncharge: - if (!charge) - mem_cgroup_end_migration(mem, page, newpage, rc == 0); + mem_cgroup_end_migration(mem, page, newpage, rc == 0); unlock: unlock_page(page); out: @@ -931,16 +925,13 @@ static int unmap_and_move_huge_page(new_page_t get_new_page, if (anon_vma) put_anon_vma(anon_vma); - unlock_page(hpage); -out: - if (rc != -EAGAIN) { - list_del(&hpage->lru); - put_page(hpage); - } + if (!rc) + hugetlb_cgroup_migrate(hpage, new_hpage); + unlock_page(hpage); +out: put_page(new_hpage); - if (result) { if (rc) *result = rc; @@ -1016,48 +1007,32 @@ out: return nr_failed + retry; } -int migrate_huge_pages(struct list_head *from, - new_page_t get_new_page, unsigned long private, bool offlining, - enum migrate_mode mode) +int migrate_huge_page(struct page *hpage, new_page_t get_new_page, + unsigned long private, bool offlining, + enum migrate_mode mode) { - int retry = 1; - int nr_failed = 0; - int pass = 0; - struct page *page; - struct page *page2; - int rc; - - for (pass = 0; pass < 10 && retry; pass++) { - retry = 0; - - list_for_each_entry_safe(page, page2, from, lru) { + int pass, rc; + + for (pass = 0; pass < 10; pass++) { + rc = unmap_and_move_huge_page(get_new_page, + private, hpage, pass > 2, offlining, + mode); + switch (rc) { + case -ENOMEM: + goto out; + case -EAGAIN: + /* try again */ cond_resched(); - - rc = unmap_and_move_huge_page(get_new_page, - private, page, pass > 2, offlining, - mode); - - switch(rc) { - case -ENOMEM: - goto out; - case -EAGAIN: - retry++; - break; - case 0: - break; - default: - /* Permanent failure */ - nr_failed++; - break; - } + break; + case 0: + goto out; + default: + rc = -EIO; + goto out; } } - rc = 0; out: - if (rc) - return rc; - - return nr_failed + retry; + return rc; } #ifdef CONFIG_NUMA @@ -943,6 +943,8 @@ void vm_stat_account(struct mm_struct *mm, unsigned long flags, const unsigned long stack_flags = VM_STACK_FLAGS & (VM_GROWSUP|VM_GROWSDOWN); + mm->total_vm += pages; + if (file) { mm->shared_vm += pages; if ((flags & (VM_EXEC|VM_WRITE)) == VM_EXEC) @@ -1347,7 +1349,6 @@ munmap_back: out: perf_event_mmap(vma); - mm->total_vm += len >> PAGE_SHIFT; vm_stat_account(mm, vm_flags, file, len >> PAGE_SHIFT); if (vm_flags & VM_LOCKED) { if (!mlock_vma_pages_range(vma, addr, addr + len)) @@ -1707,7 +1708,6 @@ static int acct_stack_growth(struct vm_area_struct *vma, unsigned long size, uns return -ENOMEM; /* Ok, everything looks good - let it rip */ - mm->total_vm += grow; if (vma->vm_flags & VM_LOCKED) mm->locked_vm += grow; vm_stat_account(mm, vma->vm_flags, vma->vm_file, grow); @@ -1889,7 +1889,6 @@ static void remove_vma_list(struct mm_struct *mm, struct vm_area_struct *vma) if (vma->vm_flags & VM_ACCOUNT) nr_accounted += nrpages; - mm->total_vm -= nrpages; vm_stat_account(mm, vma->vm_flags, vma->vm_file, -nrpages); vma = remove_vma(vma); } while (vma); @@ -2345,9 +2344,6 @@ int insert_vm_struct(struct mm_struct * mm, struct vm_area_struct * vma) security_vm_enough_memory_mm(mm, vma_pages(vma))) return -ENOMEM; - if (vma->vm_file && uprobe_mmap(vma)) - return -EINVAL; - vma_link(mm, vma, prev, rb_link, rb_parent); return 0; } @@ -2418,9 +2414,6 @@ struct vm_area_struct *copy_vma(struct vm_area_struct **vmap, if (new_vma->vm_file) { get_file(new_vma->vm_file); - if (uprobe_mmap(new_vma)) - goto out_free_mempol; - if (vma->vm_flags & VM_EXECUTABLE) added_exe_file_vma(mm); } diff --git a/mm/mmu_notifier.c b/mm/mmu_notifier.c index 9a611d3..862b608 100644 --- a/mm/mmu_notifier.c +++ b/mm/mmu_notifier.c @@ -33,6 +33,24 @@ void __mmu_notifier_release(struct mm_struct *mm) { struct mmu_notifier *mn; + struct hlist_node *n; + + /* + * RCU here will block mmu_notifier_unregister until + * ->release returns. + */ + rcu_read_lock(); + hlist_for_each_entry_rcu(mn, n, &mm->mmu_notifier_mm->list, hlist) + /* + * if ->release runs before mmu_notifier_unregister it + * must be handled as it's the only way for the driver + * to flush all existing sptes and stop the driver + * from establishing any more sptes before all the + * pages in the mm are freed. + */ + if (mn->ops->release) + mn->ops->release(mn, mm); + rcu_read_unlock(); spin_lock(&mm->mmu_notifier_mm->lock); while (unlikely(!hlist_empty(&mm->mmu_notifier_mm->list))) { @@ -46,23 +64,6 @@ void __mmu_notifier_release(struct mm_struct *mm) * mmu_notifier_unregister to return. */ hlist_del_init_rcu(&mn->hlist); - /* - * RCU here will block mmu_notifier_unregister until - * ->release returns. - */ - rcu_read_lock(); - spin_unlock(&mm->mmu_notifier_mm->lock); - /* - * if ->release runs before mmu_notifier_unregister it - * must be handled as it's the only way for the driver - * to flush all existing sptes and stop the driver - * from establishing any more sptes before all the - * pages in the mm are freed. - */ - if (mn->ops->release) - mn->ops->release(mn, mm); - rcu_read_unlock(); - spin_lock(&mm->mmu_notifier_mm->lock); } spin_unlock(&mm->mmu_notifier_mm->lock); @@ -284,16 +285,13 @@ void mmu_notifier_unregister(struct mmu_notifier *mn, struct mm_struct *mm) { BUG_ON(atomic_read(&mm->mm_count) <= 0); - spin_lock(&mm->mmu_notifier_mm->lock); if (!hlist_unhashed(&mn->hlist)) { - hlist_del_rcu(&mn->hlist); - /* * RCU here will force exit_mmap to wait ->release to finish * before freeing the pages. */ rcu_read_lock(); - spin_unlock(&mm->mmu_notifier_mm->lock); + /* * exit_mmap will block in mmu_notifier_release to * guarantee ->release is called before freeing the @@ -302,8 +300,11 @@ void mmu_notifier_unregister(struct mmu_notifier *mn, struct mm_struct *mm) if (mn->ops->release) mn->ops->release(mn, mm); rcu_read_unlock(); - } else + + spin_lock(&mm->mmu_notifier_mm->lock); + hlist_del_rcu(&mn->hlist); spin_unlock(&mm->mmu_notifier_mm->lock); + } /* * Wait any running method to finish, of course including diff --git a/mm/mmzone.c b/mm/mmzone.c index 6830eab..3cef80f 100644 --- a/mm/mmzone.c +++ b/mm/mmzone.c @@ -96,7 +96,7 @@ void lruvec_init(struct lruvec *lruvec, struct zone *zone) for_each_lru(lru) INIT_LIST_HEAD(&lruvec->lists[lru]); -#ifdef CONFIG_CGROUP_MEM_RES_CTLR +#ifdef CONFIG_MEMCG lruvec->zone = zone; #endif } diff --git a/mm/mremap.c b/mm/mremap.c index 21fed20..cc06d0e 100644 --- a/mm/mremap.c +++ b/mm/mremap.c @@ -260,7 +260,6 @@ static unsigned long move_vma(struct vm_area_struct *vma, * If this were a serious issue, we'd add a flag to do_munmap(). */ hiwater_vm = mm->hiwater_vm; - mm->total_vm += new_len >> PAGE_SHIFT; vm_stat_account(mm, vma->vm_flags, vma->vm_file, new_len>>PAGE_SHIFT); if (do_munmap(mm, old_addr, old_len) < 0) { @@ -497,7 +496,6 @@ SYSCALL_DEFINE5(mremap, unsigned long, addr, unsigned long, old_len, goto out; } - mm->total_vm += pages; vm_stat_account(mm, vma->vm_flags, vma->vm_file, pages); if (vma->vm_flags & VM_LOCKED) { mm->locked_vm += pages; diff --git a/mm/nobootmem.c b/mm/nobootmem.c index d23415c..4055730 100644 --- a/mm/nobootmem.c +++ b/mm/nobootmem.c @@ -105,27 +105,35 @@ static void __init __free_pages_memory(unsigned long start, unsigned long end) __free_pages_bootmem(pfn_to_page(i), 0); } +static unsigned long __init __free_memory_core(phys_addr_t start, + phys_addr_t end) +{ + unsigned long start_pfn = PFN_UP(start); + unsigned long end_pfn = min_t(unsigned long, + PFN_DOWN(end), max_low_pfn); + + if (start_pfn > end_pfn) + return 0; + + __free_pages_memory(start_pfn, end_pfn); + + return end_pfn - start_pfn; +} + unsigned long __init free_low_memory_core_early(int nodeid) { unsigned long count = 0; - phys_addr_t start, end; + phys_addr_t start, end, size; u64 i; - /* free reserved array temporarily so that it's treated as free area */ - memblock_free_reserved_regions(); - - for_each_free_mem_range(i, MAX_NUMNODES, &start, &end, NULL) { - unsigned long start_pfn = PFN_UP(start); - unsigned long end_pfn = min_t(unsigned long, - PFN_DOWN(end), max_low_pfn); - if (start_pfn < end_pfn) { - __free_pages_memory(start_pfn, end_pfn); - count += end_pfn - start_pfn; - } - } + for_each_free_mem_range(i, MAX_NUMNODES, &start, &end, NULL) + count += __free_memory_core(start, end); + + /* free range that is used for reserved array if we allocate it */ + size = get_allocated_memblock_reserved_regions_info(&start); + if (size) + count += __free_memory_core(start, start + size); - /* put region array back? */ - memblock_reserve_reserved_regions(); return count; } @@ -274,7 +282,7 @@ void * __init __alloc_bootmem(unsigned long size, unsigned long align, return ___alloc_bootmem(size, align, goal, limit); } -static void * __init ___alloc_bootmem_node_nopanic(pg_data_t *pgdat, +void * __init ___alloc_bootmem_node_nopanic(pg_data_t *pgdat, unsigned long size, unsigned long align, unsigned long goal, @@ -1486,7 +1486,7 @@ SYSCALL_DEFINE6(mmap_pgoff, unsigned long, addr, unsigned long, len, flags &= ~(MAP_EXECUTABLE | MAP_DENYWRITE); - ret = vm_mmap_pgoff(file, addr, len, prot, flags, pgoff); + retval = vm_mmap_pgoff(file, addr, len, prot, flags, pgoff); if (file) fput(file); diff --git a/mm/oom_kill.c b/mm/oom_kill.c index ed0e196..1986008 100644 --- a/mm/oom_kill.c +++ b/mm/oom_kill.c @@ -183,7 +183,8 @@ static bool oom_unkillable_task(struct task_struct *p, unsigned long oom_badness(struct task_struct *p, struct mem_cgroup *memcg, const nodemask_t *nodemask, unsigned long totalpages) { - unsigned long points; + long points; + long adj; if (oom_unkillable_task(p, memcg, nodemask)) return 0; @@ -192,7 +193,8 @@ unsigned long oom_badness(struct task_struct *p, struct mem_cgroup *memcg, if (!p) return 0; - if (p->signal->oom_score_adj == OOM_SCORE_ADJ_MIN) { + adj = p->signal->oom_score_adj; + if (adj == OOM_SCORE_ADJ_MIN) { task_unlock(p); return 0; } @@ -210,20 +212,17 @@ unsigned long oom_badness(struct task_struct *p, struct mem_cgroup *memcg, * implementation used by LSMs. */ if (has_capability_noaudit(p, CAP_SYS_ADMIN)) - points -= 30 * totalpages / 1000; + adj -= 30; - /* - * /proc/pid/oom_score_adj ranges from -1000 to +1000 such that it may - * either completely disable oom killing or always prefer a certain - * task. - */ - points += p->signal->oom_score_adj * totalpages / 1000; + /* Normalize to oom_score_adj units */ + adj *= totalpages / 1000; + points += adj; /* * Never return 0 for an eligible task regardless of the root bonus and * oom_score_adj (oom_score_adj can't be OOM_SCORE_ADJ_MIN here). */ - return points ? points : 1; + return points > 0 ? points : 1; } /* @@ -289,76 +288,93 @@ static enum oom_constraint constrained_alloc(struct zonelist *zonelist, } #endif +enum oom_scan_t oom_scan_process_thread(struct task_struct *task, + unsigned long totalpages, const nodemask_t *nodemask, + bool force_kill) +{ + if (task->exit_state) + return OOM_SCAN_CONTINUE; + if (oom_unkillable_task(task, NULL, nodemask)) + return OOM_SCAN_CONTINUE; + + /* + * This task already has access to memory reserves and is being killed. + * Don't allow any other task to have access to the reserves. + */ + if (test_tsk_thread_flag(task, TIF_MEMDIE)) { + if (unlikely(frozen(task))) + __thaw_task(task); + if (!force_kill) + return OOM_SCAN_ABORT; + } + if (!task->mm) + return OOM_SCAN_CONTINUE; + + if (task->flags & PF_EXITING) { + /* + * If task is current and is in the process of releasing memory, + * allow the "kill" to set TIF_MEMDIE, which will allow it to + * access memory reserves. Otherwise, it may stall forever. + * + * The iteration isn't broken here, however, in case other + * threads are found to have already been oom killed. + */ + if (task == current) + return OOM_SCAN_SELECT; + else if (!force_kill) { + /* + * If this task is not being ptraced on exit, then wait + * for it to finish before killing some other task + * unnecessarily. + */ + if (!(task->group_leader->ptrace & PT_TRACE_EXIT)) + return OOM_SCAN_ABORT; + } + } + return OOM_SCAN_OK; +} + /* * Simple selection loop. We chose the process with the highest - * number of 'points'. We expect the caller will lock the tasklist. + * number of 'points'. * * (not docbooked, we don't want this one cluttering up the manual) */ static struct task_struct *select_bad_process(unsigned int *ppoints, - unsigned long totalpages, struct mem_cgroup *memcg, - const nodemask_t *nodemask, bool force_kill) + unsigned long totalpages, const nodemask_t *nodemask, + bool force_kill) { struct task_struct *g, *p; struct task_struct *chosen = NULL; unsigned long chosen_points = 0; + rcu_read_lock(); do_each_thread(g, p) { unsigned int points; - if (p->exit_state) - continue; - if (oom_unkillable_task(p, memcg, nodemask)) - continue; - - /* - * This task already has access to memory reserves and is - * being killed. Don't allow any other task access to the - * memory reserve. - * - * Note: this may have a chance of deadlock if it gets - * 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 (unlikely(frozen(p))) - __thaw_task(p); - if (!force_kill) - return ERR_PTR(-1UL); - } - if (!p->mm) + switch (oom_scan_process_thread(p, totalpages, nodemask, + force_kill)) { + case OOM_SCAN_SELECT: + chosen = p; + chosen_points = ULONG_MAX; + /* fall through */ + case OOM_SCAN_CONTINUE: continue; - - if (p->flags & PF_EXITING) { - /* - * If p is the current task and is in the process of - * releasing memory, we allow the "kill" to set - * TIF_MEMDIE, which will allow it to gain access to - * memory reserves. Otherwise, it may stall forever. - * - * The loop isn't broken here, however, in case other - * threads are found to have already been oom killed. - */ - if (p == current) { - chosen = p; - chosen_points = ULONG_MAX; - } else if (!force_kill) { - /* - * If this task is not being ptraced on exit, - * then wait for it to finish before killing - * some other task unnecessarily. - */ - if (!(p->group_leader->ptrace & PT_TRACE_EXIT)) - return ERR_PTR(-1UL); - } - } - - points = oom_badness(p, memcg, nodemask, totalpages); + case OOM_SCAN_ABORT: + rcu_read_unlock(); + return ERR_PTR(-1UL); + case OOM_SCAN_OK: + break; + }; + points = oom_badness(p, NULL, nodemask, totalpages); if (points > chosen_points) { chosen = p; chosen_points = points; } } while_each_thread(g, p); + if (chosen) + get_task_struct(chosen); + rcu_read_unlock(); *ppoints = chosen_points * 1000 / totalpages; return chosen; @@ -366,23 +382,22 @@ static struct task_struct *select_bad_process(unsigned int *ppoints, /** * dump_tasks - dump current memory state of all system tasks - * @mem: current's memory controller, if constrained + * @memcg: current's memory controller, if constrained * @nodemask: nodemask passed to page allocator for mempolicy ooms * * Dumps the current memory state of all eligible tasks. Tasks not in the same * memcg, not in the same cpuset, or bound to a disjoint set of mempolicy nodes * are not shown. - * State information includes task's pid, uid, tgid, vm size, rss, cpu, oom_adj - * value, oom_score_adj value, and name. - * - * Call with tasklist_lock read-locked. + * State information includes task's pid, uid, tgid, vm size, rss, nr_ptes, + * swapents, oom_score_adj value, and name. */ static void dump_tasks(const struct mem_cgroup *memcg, const nodemask_t *nodemask) { struct task_struct *p; struct task_struct *task; - pr_info("[ pid ] uid tgid total_vm rss cpu oom_adj oom_score_adj name\n"); + pr_info("[ pid ] uid tgid total_vm rss nr_ptes swapents oom_score_adj name\n"); + rcu_read_lock(); for_each_process(p) { if (oom_unkillable_task(p, memcg, nodemask)) continue; @@ -397,13 +412,15 @@ static void dump_tasks(const struct mem_cgroup *memcg, const nodemask_t *nodemas continue; } - pr_info("[%5d] %5d %5d %8lu %8lu %3u %3d %5d %s\n", + pr_info("[%5d] %5d %5d %8lu %8lu %7lu %8lu %5d %s\n", task->pid, from_kuid(&init_user_ns, task_uid(task)), task->tgid, task->mm->total_vm, get_mm_rss(task->mm), - task_cpu(task), task->signal->oom_adj, + task->mm->nr_ptes, + get_mm_counter(task->mm, MM_SWAPENTS), task->signal->oom_score_adj, task->comm); task_unlock(task); } + rcu_read_unlock(); } static void dump_header(struct task_struct *p, gfp_t gfp_mask, int order, @@ -424,10 +441,14 @@ static void dump_header(struct task_struct *p, gfp_t gfp_mask, int order, } #define K(x) ((x) << (PAGE_SHIFT-10)) -static void oom_kill_process(struct task_struct *p, gfp_t gfp_mask, int order, - unsigned int points, unsigned long totalpages, - struct mem_cgroup *memcg, nodemask_t *nodemask, - const char *message) +/* + * Must be called while holding a reference to p, which will be released upon + * returning. + */ +void oom_kill_process(struct task_struct *p, gfp_t gfp_mask, int order, + unsigned int points, unsigned long totalpages, + struct mem_cgroup *memcg, nodemask_t *nodemask, + const char *message) { struct task_struct *victim = p; struct task_struct *child; @@ -443,6 +464,7 @@ static void oom_kill_process(struct task_struct *p, gfp_t gfp_mask, int order, */ if (p->flags & PF_EXITING) { set_tsk_thread_flag(p, TIF_MEMDIE); + put_task_struct(p); return; } @@ -460,6 +482,7 @@ static void oom_kill_process(struct task_struct *p, gfp_t gfp_mask, int order, * parent. This attempts to lose the minimal amount of work done while * still freeing memory. */ + read_lock(&tasklist_lock); do { list_for_each_entry(child, &t->children, sibling) { unsigned int child_points; @@ -472,15 +495,26 @@ static void oom_kill_process(struct task_struct *p, gfp_t gfp_mask, int order, child_points = oom_badness(child, memcg, nodemask, totalpages); if (child_points > victim_points) { + put_task_struct(victim); victim = child; victim_points = child_points; + get_task_struct(victim); } } } while_each_thread(p, t); + read_unlock(&tasklist_lock); - victim = find_lock_task_mm(victim); - if (!victim) + rcu_read_lock(); + p = find_lock_task_mm(victim); + if (!p) { + rcu_read_unlock(); + put_task_struct(victim); return; + } else if (victim != p) { + get_task_struct(p); + put_task_struct(victim); + victim = p; + } /* mm cannot safely be dereferenced after task_unlock(victim) */ mm = victim->mm; @@ -511,17 +545,19 @@ static void oom_kill_process(struct task_struct *p, gfp_t gfp_mask, int order, task_unlock(p); do_send_sig_info(SIGKILL, SEND_SIG_FORCED, p, true); } + rcu_read_unlock(); set_tsk_thread_flag(victim, TIF_MEMDIE); do_send_sig_info(SIGKILL, SEND_SIG_FORCED, victim, true); + put_task_struct(victim); } #undef K /* * Determines whether the kernel must panic because of the panic_on_oom sysctl. */ -static void check_panic_on_oom(enum oom_constraint constraint, gfp_t gfp_mask, - int order, const nodemask_t *nodemask) +void check_panic_on_oom(enum oom_constraint constraint, gfp_t gfp_mask, + int order, const nodemask_t *nodemask) { if (likely(!sysctl_panic_on_oom)) return; @@ -534,42 +570,11 @@ static void check_panic_on_oom(enum oom_constraint constraint, gfp_t gfp_mask, if (constraint != CONSTRAINT_NONE) return; } - read_lock(&tasklist_lock); dump_header(NULL, gfp_mask, order, NULL, nodemask); - read_unlock(&tasklist_lock); panic("Out of memory: %s panic_on_oom is enabled\n", sysctl_panic_on_oom == 2 ? "compulsory" : "system-wide"); } -#ifdef CONFIG_CGROUP_MEM_RES_CTLR -void mem_cgroup_out_of_memory(struct mem_cgroup *memcg, gfp_t gfp_mask, - int order) -{ - unsigned long limit; - unsigned int points = 0; - struct task_struct *p; - - /* - * If current has a pending SIGKILL, then automatically select it. The - * goal is to allow it to allocate so that it may quickly exit and free - * its memory. - */ - if (fatal_signal_pending(current)) { - set_thread_flag(TIF_MEMDIE); - return; - } - - check_panic_on_oom(CONSTRAINT_MEMCG, gfp_mask, order, NULL); - limit = mem_cgroup_get_limit(memcg) >> PAGE_SHIFT ? : 1; - read_lock(&tasklist_lock); - p = select_bad_process(&points, limit, memcg, NULL, false); - if (p && PTR_ERR(p) != -1UL) - oom_kill_process(p, gfp_mask, order, points, limit, memcg, NULL, - "Memory cgroup out of memory"); - read_unlock(&tasklist_lock); -} -#endif - static BLOCKING_NOTIFIER_HEAD(oom_notify_list); int register_oom_notifier(struct notifier_block *nb) @@ -691,7 +696,7 @@ void out_of_memory(struct zonelist *zonelist, gfp_t gfp_mask, struct task_struct *p; unsigned long totalpages; unsigned long freed = 0; - unsigned int points; + unsigned int uninitialized_var(points); enum oom_constraint constraint = CONSTRAINT_NONE; int killed = 0; @@ -719,22 +724,20 @@ void out_of_memory(struct zonelist *zonelist, gfp_t gfp_mask, mpol_mask = (constraint == CONSTRAINT_MEMORY_POLICY) ? nodemask : NULL; check_panic_on_oom(constraint, gfp_mask, order, mpol_mask); - read_lock(&tasklist_lock); - if (sysctl_oom_kill_allocating_task && + if (sysctl_oom_kill_allocating_task && current->mm && !oom_unkillable_task(current, NULL, nodemask) && - current->mm) { + current->signal->oom_score_adj != OOM_SCORE_ADJ_MIN) { + get_task_struct(current); oom_kill_process(current, gfp_mask, order, 0, totalpages, NULL, nodemask, "Out of memory (oom_kill_allocating_task)"); goto out; } - p = select_bad_process(&points, totalpages, NULL, mpol_mask, - force_kill); + p = select_bad_process(&points, totalpages, mpol_mask, force_kill); /* Found nothing?!?! Either we hang forever, or we panic. */ if (!p) { dump_header(NULL, gfp_mask, order, NULL, mpol_mask); - read_unlock(&tasklist_lock); panic("Out of memory and no killable processes...\n"); } if (PTR_ERR(p) != -1UL) { @@ -743,14 +746,12 @@ void out_of_memory(struct zonelist *zonelist, gfp_t gfp_mask, killed = 1; } out: - read_unlock(&tasklist_lock); - /* - * Give "p" a good chance of killing itself before we - * retry to allocate memory unless "p" is current + * Give the killed threads a good chance of exiting before trying to + * allocate memory again. */ - if (killed && !test_thread_flag(TIF_MEMDIE)) - schedule_timeout_uninterruptible(1); + if (killed) + schedule_timeout_killable(1); } /* @@ -765,6 +766,5 @@ void pagefault_out_of_memory(void) out_of_memory(NULL, 0, 0, NULL, false); clear_system_oom(); } - if (!test_thread_flag(TIF_MEMDIE)) - schedule_timeout_uninterruptible(1); + schedule_timeout_killable(1); } diff --git a/mm/page-writeback.c b/mm/page-writeback.c index 93d8d2f..e5363f3 100644 --- a/mm/page-writeback.c +++ b/mm/page-writeback.c @@ -34,6 +34,7 @@ #include <linux/syscalls.h> #include <linux/buffer_head.h> /* __set_page_dirty_buffers */ #include <linux/pagevec.h> +#include <linux/timer.h> #include <trace/events/writeback.h> /* @@ -135,7 +136,20 @@ unsigned long global_dirty_limit; * measured in page writeback completions. * */ -static struct prop_descriptor vm_completions; +static struct fprop_global writeout_completions; + +static void writeout_period(unsigned long t); +/* Timer for aging of writeout_completions */ +static struct timer_list writeout_period_timer = + TIMER_DEFERRED_INITIALIZER(writeout_period, 0, 0); +static unsigned long writeout_period_time = 0; + +/* + * Length of period for aging writeout fractions of bdis. This is an + * arbitrarily chosen number. The longer the period, the slower fractions will + * reflect changes in current writeout rate. + */ +#define VM_COMPLETIONS_PERIOD_LEN (3*HZ) /* * Work out the current dirty-memory clamping and background writeout @@ -322,34 +336,6 @@ bool zone_dirty_ok(struct zone *zone) zone_page_state(zone, NR_WRITEBACK) <= limit; } -/* - * couple the period to the dirty_ratio: - * - * period/2 ~ roundup_pow_of_two(dirty limit) - */ -static int calc_period_shift(void) -{ - unsigned long dirty_total; - - if (vm_dirty_bytes) - dirty_total = vm_dirty_bytes / PAGE_SIZE; - else - dirty_total = (vm_dirty_ratio * global_dirtyable_memory()) / - 100; - return 2 + ilog2(dirty_total - 1); -} - -/* - * update the period when the dirty threshold changes. - */ -static void update_completion_period(void) -{ - int shift = calc_period_shift(); - prop_change_shift(&vm_completions, shift); - - writeback_set_ratelimit(); -} - int dirty_background_ratio_handler(struct ctl_table *table, int write, void __user *buffer, size_t *lenp, loff_t *ppos) @@ -383,7 +369,7 @@ int dirty_ratio_handler(struct ctl_table *table, int write, ret = proc_dointvec_minmax(table, write, buffer, lenp, ppos); if (ret == 0 && write && vm_dirty_ratio != old_ratio) { - update_completion_period(); + writeback_set_ratelimit(); vm_dirty_bytes = 0; } return ret; @@ -398,12 +384,21 @@ int dirty_bytes_handler(struct ctl_table *table, int write, ret = proc_doulongvec_minmax(table, write, buffer, lenp, ppos); if (ret == 0 && write && vm_dirty_bytes != old_bytes) { - update_completion_period(); + writeback_set_ratelimit(); vm_dirty_ratio = 0; } return ret; } +static unsigned long wp_next_time(unsigned long cur_time) +{ + cur_time += VM_COMPLETIONS_PERIOD_LEN; + /* 0 has a special meaning... */ + if (!cur_time) + return 1; + return cur_time; +} + /* * Increment the BDI's writeout completion count and the global writeout * completion count. Called from test_clear_page_writeback(). @@ -411,8 +406,19 @@ 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); + __fprop_inc_percpu_max(&writeout_completions, &bdi->completions, + bdi->max_prop_frac); + /* First event after period switching was turned off? */ + if (!unlikely(writeout_period_time)) { + /* + * We can race with other __bdi_writeout_inc calls here but + * it does not cause any harm since the resulting time when + * timer will fire and what is in writeout_period_time will be + * roughly the same. + */ + writeout_period_time = wp_next_time(jiffies); + mod_timer(&writeout_period_timer, writeout_period_time); + } } void bdi_writeout_inc(struct backing_dev_info *bdi) @@ -431,11 +437,33 @@ EXPORT_SYMBOL_GPL(bdi_writeout_inc); static void bdi_writeout_fraction(struct backing_dev_info *bdi, long *numerator, long *denominator) { - prop_fraction_percpu(&vm_completions, &bdi->completions, + fprop_fraction_percpu(&writeout_completions, &bdi->completions, numerator, denominator); } /* + * On idle system, we can be called long after we scheduled because we use + * deferred timers so count with missed periods. + */ +static void writeout_period(unsigned long t) +{ + int miss_periods = (jiffies - writeout_period_time) / + VM_COMPLETIONS_PERIOD_LEN; + + if (fprop_new_period(&writeout_completions, miss_periods + 1)) { + writeout_period_time = wp_next_time(writeout_period_time + + miss_periods * VM_COMPLETIONS_PERIOD_LEN); + mod_timer(&writeout_period_timer, writeout_period_time); + } else { + /* + * Aging has zeroed all fractions. Stop wasting CPU on period + * updates. + */ + writeout_period_time = 0; + } +} + +/* * bdi_min_ratio keeps the sum of the minimum dirty shares of all * registered backing devices, which, for obvious reasons, can not * exceed 100%. @@ -475,7 +503,7 @@ int bdi_set_max_ratio(struct backing_dev_info *bdi, unsigned max_ratio) ret = -EINVAL; } else { bdi->max_ratio = max_ratio; - bdi->max_prop_frac = (PROP_FRAC_BASE * max_ratio) / 100; + bdi->max_prop_frac = (FPROP_FRAC_BASE * max_ratio) / 100; } spin_unlock_bh(&bdi_lock); @@ -918,7 +946,7 @@ static void bdi_update_dirty_ratelimit(struct backing_dev_info *bdi, * 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 + * code makes use of task_ratelimit to filter out singular points and * limit the step size. * * The below code essentially only uses the relative value of @@ -941,7 +969,7 @@ static void bdi_update_dirty_ratelimit(struct backing_dev_info *bdi, * 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 + * and filter out the singular 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). @@ -1606,13 +1634,10 @@ static struct notifier_block __cpuinitdata ratelimit_nb = { */ void __init page_writeback_init(void) { - int shift; - writeback_set_ratelimit(); register_cpu_notifier(&ratelimit_nb); - shift = calc_period_shift(); - prop_descriptor_init(&vm_completions, shift); + fprop_global_init(&writeout_completions); } /** diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 4403009..889532b 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -51,7 +51,6 @@ #include <linux/page_cgroup.h> #include <linux/debugobjects.h> #include <linux/kmemleak.h> -#include <linux/memory.h> #include <linux/compaction.h> #include <trace/events/kmem.h> #include <linux/ftrace_event.h> @@ -219,7 +218,12 @@ EXPORT_SYMBOL(nr_online_nodes); int page_group_by_mobility_disabled __read_mostly; -static void set_pageblock_migratetype(struct page *page, int migratetype) +/* + * NOTE: + * Don't use set_pageblock_migratetype(page, MIGRATE_ISOLATE) directly. + * Instead, use {un}set_pageblock_isolate. + */ +void set_pageblock_migratetype(struct page *page, int migratetype) { if (unlikely(page_group_by_mobility_disabled)) @@ -954,7 +958,7 @@ static int move_freepages(struct zone *zone, return pages_moved; } -static int move_freepages_block(struct zone *zone, struct page *page, +int move_freepages_block(struct zone *zone, struct page *page, int migratetype) { unsigned long start_pfn, end_pfn; @@ -1158,8 +1162,10 @@ void drain_zone_pages(struct zone *zone, struct per_cpu_pages *pcp) to_drain = pcp->batch; else to_drain = pcp->count; - free_pcppages_bulk(zone, to_drain, pcp); - pcp->count -= to_drain; + if (to_drain > 0) { + free_pcppages_bulk(zone, to_drain, pcp); + pcp->count -= to_drain; + } local_irq_restore(flags); } #endif @@ -1529,16 +1535,16 @@ static int __init setup_fail_page_alloc(char *str) } __setup("fail_page_alloc=", setup_fail_page_alloc); -static int should_fail_alloc_page(gfp_t gfp_mask, unsigned int order) +static bool should_fail_alloc_page(gfp_t gfp_mask, unsigned int order) { if (order < fail_page_alloc.min_order) - return 0; + return false; if (gfp_mask & __GFP_NOFAIL) - return 0; + return false; if (fail_page_alloc.ignore_gfp_highmem && (gfp_mask & __GFP_HIGHMEM)) - return 0; + return false; if (fail_page_alloc.ignore_gfp_wait && (gfp_mask & __GFP_WAIT)) - return 0; + return false; return should_fail(&fail_page_alloc.attr, 1 << order); } @@ -1578,9 +1584,9 @@ late_initcall(fail_page_alloc_debugfs); #else /* CONFIG_FAIL_PAGE_ALLOC */ -static inline int should_fail_alloc_page(gfp_t gfp_mask, unsigned int order) +static inline bool should_fail_alloc_page(gfp_t gfp_mask, unsigned int order) { - return 0; + return false; } #endif /* CONFIG_FAIL_PAGE_ALLOC */ @@ -1594,6 +1600,7 @@ static bool __zone_watermark_ok(struct zone *z, int order, unsigned long mark, { /* free_pages my go negative - that's OK */ long min = mark; + long lowmem_reserve = z->lowmem_reserve[classzone_idx]; int o; free_pages -= (1 << order) - 1; @@ -1602,7 +1609,7 @@ static bool __zone_watermark_ok(struct zone *z, int order, unsigned long mark, if (alloc_flags & ALLOC_HARDER) min -= min / 4; - if (free_pages <= min + z->lowmem_reserve[classzone_idx]) + if (free_pages <= min + lowmem_reserve) return false; for (o = 0; o < order; o++) { /* At the next order, this order's pages become unavailable */ @@ -1617,6 +1624,20 @@ static bool __zone_watermark_ok(struct zone *z, int order, unsigned long mark, return true; } +#ifdef CONFIG_MEMORY_ISOLATION +static inline unsigned long nr_zone_isolate_freepages(struct zone *zone) +{ + if (unlikely(zone->nr_pageblock_isolate)) + return zone->nr_pageblock_isolate * pageblock_nr_pages; + return 0; +} +#else +static inline unsigned long nr_zone_isolate_freepages(struct zone *zone) +{ + return 0; +} +#endif + bool zone_watermark_ok(struct zone *z, int order, unsigned long mark, int classzone_idx, int alloc_flags) { @@ -1632,6 +1653,14 @@ bool zone_watermark_ok_safe(struct zone *z, int order, unsigned long mark, if (z->percpu_drift_mark && free_pages < z->percpu_drift_mark) free_pages = zone_page_state_snapshot(z, NR_FREE_PAGES); + /* + * If the zone has MIGRATE_ISOLATE type free pages, we should consider + * it. nr_zone_isolate_freepages is never accurate so kswapd might not + * sleep although it could do so. But this is more desirable for memory + * hotplug than sleeping which can cause a livelock in the direct + * reclaim path. + */ + free_pages -= nr_zone_isolate_freepages(z); return __zone_watermark_ok(z, order, mark, classzone_idx, alloc_flags, free_pages); } @@ -2087,8 +2116,8 @@ __alloc_pages_direct_compact(gfp_t gfp_mask, unsigned int order, page = get_page_from_freelist(gfp_mask, nodemask, order, zonelist, high_zoneidx, - alloc_flags, preferred_zone, - migratetype); + alloc_flags & ~ALLOC_NO_WATERMARKS, + preferred_zone, migratetype); if (page) { preferred_zone->compact_considered = 0; preferred_zone->compact_defer_shift = 0; @@ -2180,8 +2209,8 @@ __alloc_pages_direct_reclaim(gfp_t gfp_mask, unsigned int order, retry: page = get_page_from_freelist(gfp_mask, nodemask, order, zonelist, high_zoneidx, - alloc_flags, preferred_zone, - migratetype); + alloc_flags & ~ALLOC_NO_WATERMARKS, + preferred_zone, migratetype); /* * If an allocation failed after direct reclaim, it could be because @@ -2265,15 +2294,24 @@ gfp_to_alloc_flags(gfp_t gfp_mask) alloc_flags |= ALLOC_HARDER; if (likely(!(gfp_mask & __GFP_NOMEMALLOC))) { - if (!in_interrupt() && - ((current->flags & PF_MEMALLOC) || - unlikely(test_thread_flag(TIF_MEMDIE)))) + if (gfp_mask & __GFP_MEMALLOC) + alloc_flags |= ALLOC_NO_WATERMARKS; + else if (in_serving_softirq() && (current->flags & PF_MEMALLOC)) + alloc_flags |= ALLOC_NO_WATERMARKS; + else if (!in_interrupt() && + ((current->flags & PF_MEMALLOC) || + unlikely(test_thread_flag(TIF_MEMDIE)))) alloc_flags |= ALLOC_NO_WATERMARKS; } return alloc_flags; } +bool gfp_pfmemalloc_allowed(gfp_t gfp_mask) +{ + return !!(gfp_to_alloc_flags(gfp_mask) & ALLOC_NO_WATERMARKS); +} + static inline struct page * __alloc_pages_slowpath(gfp_t gfp_mask, unsigned int order, struct zonelist *zonelist, enum zone_type high_zoneidx, @@ -2340,11 +2378,27 @@ rebalance: /* Allocate without watermarks if the context allows */ if (alloc_flags & ALLOC_NO_WATERMARKS) { + /* + * Ignore mempolicies if ALLOC_NO_WATERMARKS on the grounds + * the allocation is high priority and these type of + * allocations are system rather than user orientated + */ + zonelist = node_zonelist(numa_node_id(), gfp_mask); + page = __alloc_pages_high_priority(gfp_mask, order, zonelist, high_zoneidx, nodemask, preferred_zone, migratetype); - if (page) + if (page) { + /* + * page->pfmemalloc is set when ALLOC_NO_WATERMARKS was + * necessary to allocate the page. The expectation is + * that the caller is taking steps that will free more + * memory. The caller should avoid the page being used + * for !PFMEMALLOC purposes. + */ + page->pfmemalloc = true; goto got_pg; + } } /* Atomic allocations - we can't balance anything */ @@ -2463,8 +2517,8 @@ nopage: got_pg: if (kmemcheck_enabled) kmemcheck_pagealloc_alloc(page, order, gfp_mask); - return page; + return page; } /* @@ -2515,6 +2569,8 @@ retry_cpuset: page = __alloc_pages_slowpath(gfp_mask, order, zonelist, high_zoneidx, nodemask, preferred_zone, migratetype); + else + page->pfmemalloc = false; trace_mm_page_alloc(page, order, gfp_mask, migratetype); @@ -3030,7 +3086,7 @@ int numa_zonelist_order_handler(ctl_table *table, int write, user_zonelist_order = oldval; } else if (oldval != user_zonelist_order) { mutex_lock(&zonelists_mutex); - build_all_zonelists(NULL); + build_all_zonelists(NULL, NULL); mutex_unlock(&zonelists_mutex); } } @@ -3409,14 +3465,21 @@ static void setup_zone_pageset(struct zone *zone); DEFINE_MUTEX(zonelists_mutex); /* return values int ....just for stop_machine() */ -static __init_refok int __build_all_zonelists(void *data) +static int __build_all_zonelists(void *data) { int nid; int cpu; + pg_data_t *self = data; #ifdef CONFIG_NUMA memset(node_load, 0, sizeof(node_load)); #endif + + if (self && !node_online(self->node_id)) { + build_zonelists(self); + build_zonelist_cache(self); + } + for_each_online_node(nid) { pg_data_t *pgdat = NODE_DATA(nid); @@ -3461,7 +3524,7 @@ static __init_refok int __build_all_zonelists(void *data) * Called with zonelists_mutex held always * unless system_state == SYSTEM_BOOTING. */ -void __ref build_all_zonelists(void *data) +void __ref build_all_zonelists(pg_data_t *pgdat, struct zone *zone) { set_zonelist_order(); @@ -3473,10 +3536,10 @@ void __ref build_all_zonelists(void *data) /* we have to stop all cpus to guarantee there is no user of zonelist */ #ifdef CONFIG_MEMORY_HOTPLUG - if (data) - setup_zone_pageset((struct zone *)data); + if (zone) + setup_zone_pageset(zone); #endif - stop_machine(__build_all_zonelists, NULL, NULL); + stop_machine(__build_all_zonelists, pgdat, NULL); /* cpuset refresh routine should be here */ } vm_total_pages = nr_free_pagecache_pages(); @@ -3746,7 +3809,7 @@ static void __meminit zone_init_free_lists(struct zone *zone) memmap_init_zone((size), (nid), (zone), (start_pfn), MEMMAP_EARLY) #endif -static int zone_batchsize(struct zone *zone) +static int __meminit zone_batchsize(struct zone *zone) { #ifdef CONFIG_MMU int batch; @@ -3828,7 +3891,7 @@ static void setup_pagelist_highmark(struct per_cpu_pageset *p, pcp->batch = PAGE_SHIFT * 8; } -static void setup_zone_pageset(struct zone *zone) +static void __meminit setup_zone_pageset(struct zone *zone) { int cpu; @@ -3901,32 +3964,6 @@ int zone_wait_table_init(struct zone *zone, unsigned long zone_size_pages) return 0; } -static int __zone_pcp_update(void *data) -{ - struct zone *zone = data; - int cpu; - unsigned long batch = zone_batchsize(zone), flags; - - for_each_possible_cpu(cpu) { - struct per_cpu_pageset *pset; - struct per_cpu_pages *pcp; - - pset = per_cpu_ptr(zone->pageset, cpu); - pcp = &pset->pcp; - - local_irq_save(flags); - free_pcppages_bulk(zone, pcp->count, pcp); - setup_pageset(pset, batch); - local_irq_restore(flags); - } - return 0; -} - -void zone_pcp_update(struct zone *zone) -{ - stop_machine(__zone_pcp_update, zone, NULL); -} - static __meminit void zone_pcp_init(struct zone *zone) { /* @@ -3942,7 +3979,7 @@ static __meminit void zone_pcp_init(struct zone *zone) zone_batchsize(zone)); } -__meminit int init_currently_empty_zone(struct zone *zone, +int __meminit init_currently_empty_zone(struct zone *zone, unsigned long zone_start_pfn, unsigned long size, enum memmap_context context) @@ -4301,7 +4338,7 @@ static inline void setup_usemap(struct pglist_data *pgdat, #ifdef CONFIG_HUGETLB_PAGE_SIZE_VARIABLE /* Initialise the number of pages represented by NR_PAGEBLOCK_BITS */ -static inline void __init set_pageblock_order(void) +void __init set_pageblock_order(void) { unsigned int order; @@ -4329,7 +4366,7 @@ static inline void __init set_pageblock_order(void) * include/linux/pageblock-flags.h for the values of pageblock_order based on * the kernel config */ -static inline void set_pageblock_order(void) +void __init set_pageblock_order(void) { } @@ -4340,6 +4377,8 @@ static inline void set_pageblock_order(void) * - mark all pages reserved * - mark all memory queues empty * - clear the memory bitmaps + * + * NOTE: pgdat should get zeroed by caller. */ static void __paginginit free_area_init_core(struct pglist_data *pgdat, unsigned long *zones_size, unsigned long *zholes_size) @@ -4350,9 +4389,8 @@ static void __paginginit free_area_init_core(struct pglist_data *pgdat, int ret; pgdat_resize_init(pgdat); - pgdat->nr_zones = 0; init_waitqueue_head(&pgdat->kswapd_wait); - pgdat->kswapd_max_order = 0; + init_waitqueue_head(&pgdat->pfmemalloc_wait); pgdat_page_cgroup_init(pgdat); for (j = 0; j < MAX_NR_ZONES; j++) { @@ -4394,6 +4432,11 @@ static void __paginginit free_area_init_core(struct pglist_data *pgdat, zone->spanned_pages = size; zone->present_pages = realsize; +#if defined CONFIG_COMPACTION || defined CONFIG_CMA + zone->compact_cached_free_pfn = zone->zone_start_pfn + + zone->spanned_pages; + zone->compact_cached_free_pfn &= ~(pageblock_nr_pages-1); +#endif #ifdef CONFIG_NUMA zone->node = nid; zone->min_unmapped_pages = (realsize*sysctl_min_unmapped_ratio) @@ -4408,8 +4451,6 @@ static void __paginginit free_area_init_core(struct pglist_data *pgdat, zone_pcp_init(zone); lruvec_init(&zone->lruvec, zone); - zap_zone_vm_stats(zone); - zone->flags = 0; if (!size) continue; @@ -4469,6 +4510,9 @@ void __paginginit free_area_init_node(int nid, unsigned long *zones_size, { pg_data_t *pgdat = NODE_DATA(nid); + /* pg_data_t should be reset to zero when it's allocated */ + WARN_ON(pgdat->nr_zones || pgdat->node_start_pfn || pgdat->classzone_idx); + pgdat->node_id = nid; pgdat->node_start_pfn = node_start_pfn; calculate_node_totalpages(pgdat, zones_size, zholes_size); @@ -4750,7 +4794,7 @@ out: } /* Any regular memory on that node ? */ -static void check_for_regular_memory(pg_data_t *pgdat) +static void __init check_for_regular_memory(pg_data_t *pgdat) { #ifdef CONFIG_HIGHMEM enum zone_type zone_type; @@ -5468,26 +5512,27 @@ void set_pageblock_flags_group(struct page *page, unsigned long flags, } /* - * This is designed as sub function...plz see page_isolation.c also. - * set/clear page block's type to be ISOLATE. - * page allocater never alloc memory from ISOLATE block. + * This function checks whether pageblock includes unmovable pages or not. + * If @count is not zero, it is okay to include less @count unmovable pages + * + * PageLRU check wihtout isolation or lru_lock could race so that + * MIGRATE_MOVABLE block might include unmovable pages. It means you can't + * expect this function should be exact. */ - -static int -__count_immobile_pages(struct zone *zone, struct page *page, int count) +bool has_unmovable_pages(struct zone *zone, struct page *page, int count) { unsigned long pfn, iter, found; int mt; /* * For avoiding noise data, lru_add_drain_all() should be called - * If ZONE_MOVABLE, the zone never contains immobile pages + * If ZONE_MOVABLE, the zone never contains unmovable pages */ if (zone_idx(zone) == ZONE_MOVABLE) - return true; + return false; mt = get_pageblock_migratetype(page); if (mt == MIGRATE_MOVABLE || is_migrate_cma(mt)) - return true; + return false; pfn = page_to_pfn(page); for (found = 0, iter = 0; iter < pageblock_nr_pages; iter++) { @@ -5497,11 +5542,18 @@ __count_immobile_pages(struct zone *zone, struct page *page, int count) continue; page = pfn_to_page(check); - if (!page_count(page)) { + /* + * We can't use page_count without pin a page + * because another CPU can free compound page. + * This check already skips compound tails of THP + * because their page->_count is zero at all time. + */ + if (!atomic_read(&page->_count)) { if (PageBuddy(page)) iter += (1 << page_order(page)) - 1; continue; } + if (!PageLRU(page)) found++; /* @@ -5518,9 +5570,9 @@ __count_immobile_pages(struct zone *zone, struct page *page, int count) * page at boot. */ if (found > count) - return false; + return true; } - return true; + return false; } bool is_pageblock_removable_nolock(struct page *page) @@ -5544,77 +5596,7 @@ bool is_pageblock_removable_nolock(struct page *page) zone->zone_start_pfn + zone->spanned_pages <= pfn) return false; - return __count_immobile_pages(zone, page, 0); -} - -int set_migratetype_isolate(struct page *page) -{ - struct zone *zone; - unsigned long flags, pfn; - struct memory_isolate_notify arg; - int notifier_ret; - int ret = -EBUSY; - - zone = page_zone(page); - - spin_lock_irqsave(&zone->lock, flags); - - pfn = page_to_pfn(page); - arg.start_pfn = pfn; - arg.nr_pages = pageblock_nr_pages; - arg.pages_found = 0; - - /* - * It may be possible to isolate a pageblock even if the - * migratetype is not MIGRATE_MOVABLE. The memory isolation - * notifier chain is used by balloon drivers to return the - * number of pages in a range that are held by the balloon - * driver to shrink memory. If all the pages are accounted for - * by balloons, are free, or on the LRU, isolation can continue. - * Later, for example, when memory hotplug notifier runs, these - * pages reported as "can be isolated" should be isolated(freed) - * by the balloon driver through the memory notifier chain. - */ - notifier_ret = memory_isolate_notify(MEM_ISOLATE_COUNT, &arg); - notifier_ret = notifier_to_errno(notifier_ret); - if (notifier_ret) - goto out; - /* - * FIXME: Now, memory hotplug doesn't call shrink_slab() by itself. - * We just check MOVABLE pages. - */ - if (__count_immobile_pages(zone, page, arg.pages_found)) - ret = 0; - - /* - * immobile means "not-on-lru" paes. If immobile is larger than - * removable-by-driver pages reported by notifier, we'll fail. - */ - -out: - if (!ret) { - set_pageblock_migratetype(page, MIGRATE_ISOLATE); - move_freepages_block(zone, page, MIGRATE_ISOLATE); - } - - spin_unlock_irqrestore(&zone->lock, flags); - if (!ret) - drain_all_pages(); - return ret; -} - -void unset_migratetype_isolate(struct page *page, unsigned migratetype) -{ - struct zone *zone; - unsigned long flags; - zone = page_zone(page); - spin_lock_irqsave(&zone->lock, flags); - if (get_pageblock_migratetype(page) != MIGRATE_ISOLATE) - goto out; - set_pageblock_migratetype(page, migratetype); - move_freepages_block(zone, page, migratetype); -out: - spin_unlock_irqrestore(&zone->lock, flags); + return !has_unmovable_pages(zone, page, 0); } #ifdef CONFIG_CMA @@ -5635,7 +5617,12 @@ static struct page * __alloc_contig_migrate_alloc(struct page *page, unsigned long private, int **resultp) { - return alloc_page(GFP_HIGHUSER_MOVABLE); + gfp_t gfp_mask = GFP_USER | __GFP_MOVABLE; + + if (PageHighMem(page)) + gfp_mask |= __GFP_HIGHMEM; + + return alloc_page(gfp_mask); } /* [start, end) must belong to a single zone. */ @@ -5864,7 +5851,49 @@ void free_contig_range(unsigned long pfn, unsigned nr_pages) } #endif +#ifdef CONFIG_MEMORY_HOTPLUG +static int __meminit __zone_pcp_update(void *data) +{ + struct zone *zone = data; + int cpu; + unsigned long batch = zone_batchsize(zone), flags; + + for_each_possible_cpu(cpu) { + struct per_cpu_pageset *pset; + struct per_cpu_pages *pcp; + + pset = per_cpu_ptr(zone->pageset, cpu); + pcp = &pset->pcp; + + local_irq_save(flags); + if (pcp->count > 0) + free_pcppages_bulk(zone, pcp->count, pcp); + setup_pageset(pset, batch); + local_irq_restore(flags); + } + return 0; +} + +void __meminit zone_pcp_update(struct zone *zone) +{ + stop_machine(__zone_pcp_update, zone, NULL); +} +#endif + #ifdef CONFIG_MEMORY_HOTREMOVE +void zone_pcp_reset(struct zone *zone) +{ + unsigned long flags; + + /* avoid races with drain_pages() */ + local_irq_save(flags); + if (zone->pageset != &boot_pageset) { + free_percpu(zone->pageset); + zone->pageset = &boot_pageset; + } + local_irq_restore(flags); +} + /* * All pages in the range must be isolated before calling this. */ diff --git a/mm/page_cgroup.c b/mm/page_cgroup.c index 1ccbd71..5ddad0c 100644 --- a/mm/page_cgroup.c +++ b/mm/page_cgroup.c @@ -317,7 +317,7 @@ void __meminit pgdat_page_cgroup_init(struct pglist_data *pgdat) #endif -#ifdef CONFIG_CGROUP_MEM_RES_CTLR_SWAP +#ifdef CONFIG_MEMCG_SWAP static DEFINE_MUTEX(swap_cgroup_mutex); struct swap_cgroup_ctrl { @@ -392,7 +392,7 @@ static struct swap_cgroup *lookup_swap_cgroup(swp_entry_t ent, /** * swap_cgroup_cmpxchg - cmpxchg mem_cgroup's id for this swp_entry. - * @end: swap entry to be cmpxchged + * @ent: swap entry to be cmpxchged * @old: old id * @new: new id * @@ -422,7 +422,7 @@ unsigned short swap_cgroup_cmpxchg(swp_entry_t ent, /** * swap_cgroup_record - record mem_cgroup for this swp_entry. * @ent: swap entry to be recorded into - * @mem: mem_cgroup to be recorded + * @id: mem_cgroup to be recorded * * Returns old value at success, 0 at failure. * (Of course, old value can be 0.) diff --git a/mm/page_io.c b/mm/page_io.c index dc76b4d..78eee32 100644 --- a/mm/page_io.c +++ b/mm/page_io.c @@ -17,7 +17,9 @@ #include <linux/swap.h> #include <linux/bio.h> #include <linux/swapops.h> +#include <linux/buffer_head.h> #include <linux/writeback.h> +#include <linux/frontswap.h> #include <asm/pgtable.h> static struct bio *get_swap_bio(gfp_t gfp_flags, @@ -85,6 +87,98 @@ void end_swap_bio_read(struct bio *bio, int err) bio_put(bio); } +int generic_swapfile_activate(struct swap_info_struct *sis, + struct file *swap_file, + sector_t *span) +{ + struct address_space *mapping = swap_file->f_mapping; + struct inode *inode = mapping->host; + unsigned blocks_per_page; + unsigned long page_no; + unsigned blkbits; + sector_t probe_block; + sector_t last_block; + sector_t lowest_block = -1; + sector_t highest_block = 0; + int nr_extents = 0; + int ret; + + blkbits = inode->i_blkbits; + blocks_per_page = PAGE_SIZE >> blkbits; + + /* + * Map all the blocks into the extent list. This code doesn't try + * to be very smart. + */ + probe_block = 0; + page_no = 0; + last_block = i_size_read(inode) >> blkbits; + while ((probe_block + blocks_per_page) <= last_block && + page_no < sis->max) { + unsigned block_in_page; + sector_t first_block; + + first_block = bmap(inode, probe_block); + if (first_block == 0) + goto bad_bmap; + + /* + * It must be PAGE_SIZE aligned on-disk + */ + if (first_block & (blocks_per_page - 1)) { + probe_block++; + goto reprobe; + } + + for (block_in_page = 1; block_in_page < blocks_per_page; + block_in_page++) { + sector_t block; + + block = bmap(inode, probe_block + block_in_page); + if (block == 0) + goto bad_bmap; + if (block != first_block + block_in_page) { + /* Discontiguity */ + probe_block++; + goto reprobe; + } + } + + first_block >>= (PAGE_SHIFT - blkbits); + if (page_no) { /* exclude the header page */ + if (first_block < lowest_block) + lowest_block = first_block; + if (first_block > highest_block) + highest_block = first_block; + } + + /* + * We found a PAGE_SIZE-length, PAGE_SIZE-aligned run of blocks + */ + ret = add_swap_extent(sis, page_no, 1, first_block); + if (ret < 0) + goto out; + nr_extents += ret; + page_no++; + probe_block += blocks_per_page; +reprobe: + continue; + } + ret = nr_extents; + *span = 1 + highest_block - lowest_block; + if (page_no == 0) + page_no = 1; /* force Empty message */ + sis->max = page_no; + sis->pages = page_no - 1; + sis->highest_bit = page_no - 1; +out: + return ret; +bad_bmap: + printk(KERN_ERR "swapon: swapfile has holes\n"); + ret = -EINVAL; + goto out; +} + /* * We may have stale swap cache pages in memory: notice * them here and get rid of the unnecessary final write. @@ -93,11 +187,45 @@ int swap_writepage(struct page *page, struct writeback_control *wbc) { struct bio *bio; int ret = 0, rw = WRITE; + struct swap_info_struct *sis = page_swap_info(page); if (try_to_free_swap(page)) { unlock_page(page); goto out; } + if (frontswap_store(page) == 0) { + set_page_writeback(page); + unlock_page(page); + end_page_writeback(page); + goto out; + } + + if (sis->flags & SWP_FILE) { + struct kiocb kiocb; + struct file *swap_file = sis->swap_file; + struct address_space *mapping = swap_file->f_mapping; + struct iovec iov = { + .iov_base = kmap(page), + .iov_len = PAGE_SIZE, + }; + + init_sync_kiocb(&kiocb, swap_file); + kiocb.ki_pos = page_file_offset(page); + kiocb.ki_left = PAGE_SIZE; + kiocb.ki_nbytes = PAGE_SIZE; + + unlock_page(page); + ret = mapping->a_ops->direct_IO(KERNEL_WRITE, + &kiocb, &iov, + kiocb.ki_pos, 1); + kunmap(page); + if (ret == PAGE_SIZE) { + count_vm_event(PSWPOUT); + ret = 0; + } + return ret; + } + bio = get_swap_bio(GFP_NOIO, page, end_swap_bio_write); if (bio == NULL) { set_page_dirty(page); @@ -119,9 +247,26 @@ int swap_readpage(struct page *page) { struct bio *bio; int ret = 0; + struct swap_info_struct *sis = page_swap_info(page); VM_BUG_ON(!PageLocked(page)); VM_BUG_ON(PageUptodate(page)); + if (frontswap_load(page) == 0) { + SetPageUptodate(page); + unlock_page(page); + goto out; + } + + if (sis->flags & SWP_FILE) { + struct file *swap_file = sis->swap_file; + struct address_space *mapping = swap_file->f_mapping; + + ret = mapping->a_ops->readpage(swap_file, page); + if (!ret) + count_vm_event(PSWPIN); + return ret; + } + bio = get_swap_bio(GFP_KERNEL, page, end_swap_bio_read); if (bio == NULL) { unlock_page(page); @@ -133,3 +278,15 @@ int swap_readpage(struct page *page) out: return ret; } + +int swap_set_page_dirty(struct page *page) +{ + struct swap_info_struct *sis = page_swap_info(page); + + if (sis->flags & SWP_FILE) { + struct address_space *mapping = sis->swap_file->f_mapping; + return mapping->a_ops->set_page_dirty(page); + } else { + return __set_page_dirty_no_writeback(page); + } +} diff --git a/mm/page_isolation.c b/mm/page_isolation.c index c9f0477..247d1f1 100644 --- a/mm/page_isolation.c +++ b/mm/page_isolation.c @@ -5,8 +5,101 @@ #include <linux/mm.h> #include <linux/page-isolation.h> #include <linux/pageblock-flags.h> +#include <linux/memory.h> #include "internal.h" +/* called while holding zone->lock */ +static void set_pageblock_isolate(struct page *page) +{ + if (get_pageblock_migratetype(page) == MIGRATE_ISOLATE) + return; + + set_pageblock_migratetype(page, MIGRATE_ISOLATE); + page_zone(page)->nr_pageblock_isolate++; +} + +/* called while holding zone->lock */ +static void restore_pageblock_isolate(struct page *page, int migratetype) +{ + struct zone *zone = page_zone(page); + if (WARN_ON(get_pageblock_migratetype(page) != MIGRATE_ISOLATE)) + return; + + BUG_ON(zone->nr_pageblock_isolate <= 0); + set_pageblock_migratetype(page, migratetype); + zone->nr_pageblock_isolate--; +} + +int set_migratetype_isolate(struct page *page) +{ + struct zone *zone; + unsigned long flags, pfn; + struct memory_isolate_notify arg; + int notifier_ret; + int ret = -EBUSY; + + zone = page_zone(page); + + spin_lock_irqsave(&zone->lock, flags); + + pfn = page_to_pfn(page); + arg.start_pfn = pfn; + arg.nr_pages = pageblock_nr_pages; + arg.pages_found = 0; + + /* + * It may be possible to isolate a pageblock even if the + * migratetype is not MIGRATE_MOVABLE. The memory isolation + * notifier chain is used by balloon drivers to return the + * number of pages in a range that are held by the balloon + * driver to shrink memory. If all the pages are accounted for + * by balloons, are free, or on the LRU, isolation can continue. + * Later, for example, when memory hotplug notifier runs, these + * pages reported as "can be isolated" should be isolated(freed) + * by the balloon driver through the memory notifier chain. + */ + notifier_ret = memory_isolate_notify(MEM_ISOLATE_COUNT, &arg); + notifier_ret = notifier_to_errno(notifier_ret); + if (notifier_ret) + goto out; + /* + * FIXME: Now, memory hotplug doesn't call shrink_slab() by itself. + * We just check MOVABLE pages. + */ + if (!has_unmovable_pages(zone, page, arg.pages_found)) + ret = 0; + + /* + * immobile means "not-on-lru" paes. If immobile is larger than + * removable-by-driver pages reported by notifier, we'll fail. + */ + +out: + if (!ret) { + set_pageblock_isolate(page); + move_freepages_block(zone, page, MIGRATE_ISOLATE); + } + + spin_unlock_irqrestore(&zone->lock, flags); + if (!ret) + drain_all_pages(); + return ret; +} + +void unset_migratetype_isolate(struct page *page, unsigned migratetype) +{ + struct zone *zone; + unsigned long flags; + zone = page_zone(page); + spin_lock_irqsave(&zone->lock, flags); + if (get_pageblock_migratetype(page) != MIGRATE_ISOLATE) + goto out; + move_freepages_block(zone, page, migratetype); + restore_pageblock_isolate(page, migratetype); +out: + spin_unlock_irqrestore(&zone->lock, flags); +} + static inline struct page * __first_valid_page(unsigned long pfn, unsigned long nr_pages) { diff --git a/mm/pagewalk.c b/mm/pagewalk.c index aa9701e..6c118d0 100644 --- a/mm/pagewalk.c +++ b/mm/pagewalk.c @@ -162,7 +162,6 @@ static int walk_hugetlb_range(struct vm_area_struct *vma, /** * walk_page_range - walk a memory map's page tables with a callback - * @mm: memory map to walk * @addr: starting address * @end: ending address * @walk: set of callbacks to invoke for each level of the tree diff --git a/mm/percpu-vm.c b/mm/percpu-vm.c index 405d331..3707c71 100644 --- a/mm/percpu-vm.c +++ b/mm/percpu-vm.c @@ -360,7 +360,6 @@ err_free: * @chunk: chunk to depopulate * @off: offset to the area to depopulate * @size: size of the area to depopulate in bytes - * @flush: whether to flush cache and tlb or not * * For each cpu, depopulate and unmap pages [@page_start,@page_end) * from @chunk. If @flush is true, vcache is flushed before unmapping @@ -264,46 +264,55 @@ static int shmem_radix_tree_replace(struct address_space *mapping, } /* + * Sometimes, before we decide whether to proceed or to fail, we must check + * that an entry was not already brought back from swap by a racing thread. + * + * Checking page is not enough: by the time a SwapCache page is locked, it + * might be reused, and again be SwapCache, using the same swap as before. + */ +static bool shmem_confirm_swap(struct address_space *mapping, + pgoff_t index, swp_entry_t swap) +{ + void *item; + + rcu_read_lock(); + item = radix_tree_lookup(&mapping->page_tree, index); + rcu_read_unlock(); + return item == swp_to_radix_entry(swap); +} + +/* * 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; + int error; VM_BUG_ON(!PageLocked(page)); VM_BUG_ON(!PageSwapBacked(page)); + page_cache_get(page); + page->mapping = mapping; + page->index = index; + + spin_lock_irq(&mapping->tree_lock); if (!expected) - error = radix_tree_preload(gfp & GFP_RECLAIM_MASK); + error = radix_tree_insert(&mapping->page_tree, index, page); + else + error = shmem_radix_tree_replace(mapping, index, expected, + page); 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); - } - if (!expected) - radix_tree_preload_end(); + 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); } - if (error) - mem_cgroup_uncharge_cache_page(page); return error; } @@ -683,10 +692,21 @@ static int shmem_unuse_inode(struct shmem_inode_info *info, mutex_lock(&shmem_swaplist_mutex); /* * We needed to drop mutex to make that restrictive page - * allocation; but the inode might already be freed by now, - * and we cannot refer to inode or mapping or info to check. - * However, we do hold page lock on the PageSwapCache page, - * so can check if that still has our reference remaining. + * allocation, but the inode might have been freed while we + * dropped it: although a racing shmem_evict_inode() cannot + * complete without emptying the radix_tree, our page lock + * on this swapcache page is not enough to prevent that - + * free_swap_and_cache() of our swap entry will only + * trylock_page(), removing swap from radix_tree whatever. + * + * We must not proceed to shmem_add_to_page_cache() if the + * inode has been freed, but of course we cannot rely on + * inode or mapping or info to check that. However, we can + * safely check if our swap entry is still in use (and here + * it can't have got reused for another page): if it's still + * in use, then the inode cannot have been freed yet, and we + * can safely proceed (if it's no longer in use, that tells + * nothing about the inode, but we don't need to unuse swap). */ if (!page_swapcount(*pagep)) error = -ENOENT; @@ -730,9 +750,9 @@ int shmem_unuse(swp_entry_t swap, struct page *page) /* * There's a faint possibility that swap page was replaced before - * caller locked it: it will come back later with the right page. + * caller locked it: caller will come back later with the right page. */ - if (unlikely(!PageSwapCache(page))) + if (unlikely(!PageSwapCache(page) || page_private(page) != swap.val)) goto out; /* @@ -909,7 +929,8 @@ static struct page *shmem_swapin(swp_entry_t swap, gfp_t gfp, /* Create a pseudo vma that just contains the policy */ pvma.vm_start = 0; - pvma.vm_pgoff = index; + /* Bias interleave by inode number to distribute better across nodes */ + pvma.vm_pgoff = index + info->vfs_inode.i_ino; pvma.vm_ops = NULL; pvma.vm_policy = spol; return swapin_readahead(swap, gfp, &pvma, 0); @@ -922,7 +943,8 @@ static struct page *shmem_alloc_page(gfp_t gfp, /* Create a pseudo vma that just contains the policy */ pvma.vm_start = 0; - pvma.vm_pgoff = index; + /* Bias interleave by inode number to distribute better across nodes */ + pvma.vm_pgoff = index + info->vfs_inode.i_ino; pvma.vm_ops = NULL; pvma.vm_policy = mpol_shared_policy_lookup(&info->policy, index); @@ -995,21 +1017,15 @@ static int shmem_replace_page(struct page **pagep, gfp_t gfp, newpage = shmem_alloc_page(gfp, info, index); if (!newpage) return -ENOMEM; - VM_BUG_ON(shmem_should_replace_page(newpage, gfp)); - *pagep = newpage; page_cache_get(newpage); copy_highpage(newpage, oldpage); + flush_dcache_page(newpage); - VM_BUG_ON(!PageLocked(oldpage)); __set_page_locked(newpage); - VM_BUG_ON(!PageUptodate(oldpage)); SetPageUptodate(newpage); - VM_BUG_ON(!PageSwapBacked(oldpage)); SetPageSwapBacked(newpage); - VM_BUG_ON(!swap_index); set_page_private(newpage, swap_index); - VM_BUG_ON(!PageSwapCache(oldpage)); SetPageSwapCache(newpage); /* @@ -1019,13 +1035,24 @@ static int shmem_replace_page(struct page **pagep, gfp_t gfp, spin_lock_irq(&swap_mapping->tree_lock); error = shmem_radix_tree_replace(swap_mapping, swap_index, oldpage, newpage); - __inc_zone_page_state(newpage, NR_FILE_PAGES); - __dec_zone_page_state(oldpage, NR_FILE_PAGES); + if (!error) { + __inc_zone_page_state(newpage, NR_FILE_PAGES); + __dec_zone_page_state(oldpage, NR_FILE_PAGES); + } spin_unlock_irq(&swap_mapping->tree_lock); - BUG_ON(error); - mem_cgroup_replace_page_cache(oldpage, newpage); - lru_cache_add_anon(newpage); + if (unlikely(error)) { + /* + * Is this possible? I think not, now that our callers check + * both PageSwapCache and page_private after getting page lock; + * but be defensive. Reverse old to newpage for clear and free. + */ + oldpage = newpage; + } else { + mem_cgroup_replace_page_cache(oldpage, newpage); + lru_cache_add_anon(newpage); + *pagep = newpage; + } ClearPageSwapCache(oldpage); set_page_private(oldpage, 0); @@ -1033,7 +1060,7 @@ static int shmem_replace_page(struct page **pagep, gfp_t gfp, unlock_page(oldpage); page_cache_release(oldpage); page_cache_release(oldpage); - return 0; + return error; } /* @@ -1107,9 +1134,10 @@ repeat: /* We have to do this with page locked to prevent races */ lock_page(page); - if (!PageSwapCache(page) || page->mapping) { + if (!PageSwapCache(page) || page_private(page) != swap.val || + !shmem_confirm_swap(mapping, index, swap)) { error = -EEXIST; /* try again */ - goto failed; + goto unlock; } if (!PageUptodate(page)) { error = -EIO; @@ -1125,9 +1153,12 @@ repeat: error = mem_cgroup_cache_charge(page, current->mm, gfp & GFP_RECLAIM_MASK); - if (!error) + if (!error) { error = shmem_add_to_page_cache(page, mapping, index, gfp, swp_to_radix_entry(swap)); + /* We already confirmed swap, and make no allocation */ + VM_BUG_ON(error); + } if (error) goto failed; @@ -1164,11 +1195,18 @@ repeat: __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; + error = radix_tree_preload(gfp & GFP_RECLAIM_MASK); + if (!error) { + error = shmem_add_to_page_cache(page, mapping, index, + gfp, NULL); + radix_tree_preload_end(); + } + if (error) { + mem_cgroup_uncharge_cache_page(page); + goto decused; + } lru_cache_add_anon(page); spin_lock(&info->lock); @@ -1228,14 +1266,10 @@ decused: unacct: shmem_unacct_blocks(info->flags, 1); failed: - 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; - } + if (swap.val && error != -EINVAL && + !shmem_confirm_swap(mapping, index, swap)) + error = -EEXIST; +unlock: if (page) { unlock_page(page); page_cache_release(page); @@ -1247,7 +1281,7 @@ failed: spin_unlock(&info->lock); goto repeat; } - if (error == -EEXIST) + if (error == -EEXIST) /* from above or from radix_tree_insert */ goto repeat; return error; } @@ -1675,98 +1709,6 @@ static ssize_t shmem_file_splice_read(struct file *in, loff_t *ppos, return error; } -/* - * llseek SEEK_DATA or SEEK_HOLE through the radix_tree. - */ -static pgoff_t shmem_seek_hole_data(struct address_space *mapping, - pgoff_t index, pgoff_t end, int origin) -{ - struct page *page; - struct pagevec pvec; - pgoff_t indices[PAGEVEC_SIZE]; - bool done = false; - int i; - - pagevec_init(&pvec, 0); - pvec.nr = 1; /* start small: we may be there already */ - while (!done) { - pvec.nr = shmem_find_get_pages_and_swap(mapping, index, - pvec.nr, pvec.pages, indices); - if (!pvec.nr) { - if (origin == SEEK_DATA) - index = end; - break; - } - for (i = 0; i < pvec.nr; i++, index++) { - if (index < indices[i]) { - if (origin == SEEK_HOLE) { - done = true; - break; - } - index = indices[i]; - } - page = pvec.pages[i]; - if (page && !radix_tree_exceptional_entry(page)) { - if (!PageUptodate(page)) - page = NULL; - } - if (index >= end || - (page && origin == SEEK_DATA) || - (!page && origin == SEEK_HOLE)) { - done = true; - break; - } - } - shmem_deswap_pagevec(&pvec); - pagevec_release(&pvec); - pvec.nr = PAGEVEC_SIZE; - cond_resched(); - } - return index; -} - -static loff_t shmem_file_llseek(struct file *file, loff_t offset, int origin) -{ - struct address_space *mapping; - struct inode *inode; - pgoff_t start, end; - loff_t new_offset; - - if (origin != SEEK_DATA && origin != SEEK_HOLE) - return generic_file_llseek_size(file, offset, origin, - MAX_LFS_FILESIZE); - mapping = file->f_mapping; - inode = mapping->host; - mutex_lock(&inode->i_mutex); - /* We're holding i_mutex so we can access i_size directly */ - - if (offset < 0) - offset = -EINVAL; - else if (offset >= inode->i_size) - offset = -ENXIO; - else { - start = offset >> PAGE_CACHE_SHIFT; - end = (inode->i_size + PAGE_CACHE_SIZE - 1) >> PAGE_CACHE_SHIFT; - new_offset = shmem_seek_hole_data(mapping, start, end, origin); - new_offset <<= PAGE_CACHE_SHIFT; - if (new_offset > offset) { - if (new_offset < inode->i_size) - offset = new_offset; - else if (origin == SEEK_DATA) - offset = -ENXIO; - else - offset = inode->i_size; - } - } - - if (offset >= 0 && offset != file->f_pos) { - file->f_pos = offset; - file->f_version = 0; - } - mutex_unlock(&inode->i_mutex); - return offset; -} - static long shmem_fallocate(struct file *file, int mode, loff_t offset, loff_t len) { @@ -1937,7 +1879,7 @@ static int shmem_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode) } static int shmem_create(struct inode *dir, struct dentry *dentry, umode_t mode, - struct nameidata *nd) + bool excl) { return shmem_mknod(dir, dentry, mode | S_IFREG, 0); } @@ -2770,7 +2712,7 @@ static const struct address_space_operations shmem_aops = { static const struct file_operations shmem_file_operations = { .mmap = shmem_mmap, #ifdef CONFIG_TMPFS - .llseek = shmem_file_llseek, + .llseek = generic_file_llseek, .read = do_sync_read, .write = do_sync_write, .aio_read = shmem_file_aio_read, @@ -68,7 +68,7 @@ * Further notes from the original documentation: * * 11 April '97. Started multi-threading - markhe - * The global cache-chain is protected by the mutex 'cache_chain_mutex'. + * The global cache-chain is protected by the mutex 'slab_mutex'. * The sem is only needed when accessing/extending the cache-chain, which * can never happen inside an interrupt (kmem_cache_create(), * kmem_cache_shrink() and kmem_cache_reap()). @@ -87,6 +87,7 @@ */ #include <linux/slab.h> +#include "slab.h" #include <linux/mm.h> #include <linux/poison.h> #include <linux/swap.h> @@ -117,12 +118,16 @@ #include <linux/memory.h> #include <linux/prefetch.h> +#include <net/sock.h> + #include <asm/cacheflush.h> #include <asm/tlbflush.h> #include <asm/page.h> #include <trace/events/kmem.h> +#include "internal.h" + /* * DEBUG - 1 for kmem_cache_create() to honour; SLAB_RED_ZONE & SLAB_POISON. * 0 for faster, smaller code (especially in the critical paths). @@ -151,6 +156,12 @@ #define ARCH_KMALLOC_FLAGS SLAB_HWCACHE_ALIGN #endif +/* + * true if a page was allocated from pfmemalloc reserves for network-based + * swap + */ +static bool pfmemalloc_active __read_mostly; + /* Legal flag mask for kmem_cache_create(). */ #if DEBUG # define CREATE_MASK (SLAB_RED_ZONE | \ @@ -256,9 +267,30 @@ struct array_cache { * Must have this definition in here for the proper * alignment of array_cache. Also simplifies accessing * the entries. + * + * Entries should not be directly dereferenced as + * entries belonging to slabs marked pfmemalloc will + * have the lower bits set SLAB_OBJ_PFMEMALLOC */ }; +#define SLAB_OBJ_PFMEMALLOC 1 +static inline bool is_obj_pfmemalloc(void *objp) +{ + return (unsigned long)objp & SLAB_OBJ_PFMEMALLOC; +} + +static inline void set_obj_pfmemalloc(void **objp) +{ + *objp = (void *)((unsigned long)*objp | SLAB_OBJ_PFMEMALLOC); + return; +} + +static inline void clear_obj_pfmemalloc(void **objp) +{ + *objp = (void *)((unsigned long)*objp & ~SLAB_OBJ_PFMEMALLOC); +} + /* * bootstrap: The caches do not work without cpuarrays anymore, but the * cpuarrays are allocated from the generic caches... @@ -424,8 +456,8 @@ static void kmem_list3_init(struct kmem_list3 *parent) * cachep->obj_offset - BYTES_PER_WORD .. cachep->obj_offset - 1: * redzone word. * cachep->obj_offset: The real object. - * cachep->buffer_size - 2* BYTES_PER_WORD: redzone word [BYTES_PER_WORD long] - * cachep->buffer_size - 1* BYTES_PER_WORD: last caller address + * cachep->size - 2* BYTES_PER_WORD: redzone word [BYTES_PER_WORD long] + * cachep->size - 1* BYTES_PER_WORD: last caller address * [BYTES_PER_WORD long] */ static int obj_offset(struct kmem_cache *cachep) @@ -433,11 +465,6 @@ static int obj_offset(struct kmem_cache *cachep) return cachep->obj_offset; } -static int obj_size(struct kmem_cache *cachep) -{ - return cachep->obj_size; -} - static unsigned long long *dbg_redzone1(struct kmem_cache *cachep, void *objp) { BUG_ON(!(cachep->flags & SLAB_RED_ZONE)); @@ -449,23 +476,22 @@ static unsigned long long *dbg_redzone2(struct kmem_cache *cachep, void *objp) { BUG_ON(!(cachep->flags & SLAB_RED_ZONE)); if (cachep->flags & SLAB_STORE_USER) - return (unsigned long long *)(objp + cachep->buffer_size - + return (unsigned long long *)(objp + cachep->size - sizeof(unsigned long long) - REDZONE_ALIGN); - return (unsigned long long *) (objp + cachep->buffer_size - + return (unsigned long long *) (objp + cachep->size - sizeof(unsigned long long)); } static void **dbg_userword(struct kmem_cache *cachep, void *objp) { BUG_ON(!(cachep->flags & SLAB_STORE_USER)); - return (void **)(objp + cachep->buffer_size - BYTES_PER_WORD); + return (void **)(objp + cachep->size - BYTES_PER_WORD); } #else #define obj_offset(x) 0 -#define obj_size(cachep) (cachep->buffer_size) #define dbg_redzone1(cachep, objp) ({BUG(); (unsigned long long *)NULL;}) #define dbg_redzone2(cachep, objp) ({BUG(); (unsigned long long *)NULL;}) #define dbg_userword(cachep, objp) ({BUG(); (void **)NULL;}) @@ -475,7 +501,7 @@ static void **dbg_userword(struct kmem_cache *cachep, void *objp) #ifdef CONFIG_TRACING size_t slab_buffer_size(struct kmem_cache *cachep) { - return cachep->buffer_size; + return cachep->size; } EXPORT_SYMBOL(slab_buffer_size); #endif @@ -489,56 +515,37 @@ EXPORT_SYMBOL(slab_buffer_size); static int slab_max_order = SLAB_MAX_ORDER_LO; static bool slab_max_order_set __initdata; -/* - * Functions for storing/retrieving the cachep and or slab from the page - * allocator. These are used to find the slab an obj belongs to. With kfree(), - * these are used to find the cache which an obj belongs to. - */ -static inline void page_set_cache(struct page *page, struct kmem_cache *cache) -{ - page->lru.next = (struct list_head *)cache; -} - static inline struct kmem_cache *page_get_cache(struct page *page) { page = compound_head(page); BUG_ON(!PageSlab(page)); - return (struct kmem_cache *)page->lru.next; -} - -static inline void page_set_slab(struct page *page, struct slab *slab) -{ - page->lru.prev = (struct list_head *)slab; -} - -static inline struct slab *page_get_slab(struct page *page) -{ - BUG_ON(!PageSlab(page)); - return (struct slab *)page->lru.prev; + return page->slab_cache; } static inline struct kmem_cache *virt_to_cache(const void *obj) { struct page *page = virt_to_head_page(obj); - return page_get_cache(page); + return page->slab_cache; } static inline struct slab *virt_to_slab(const void *obj) { struct page *page = virt_to_head_page(obj); - return page_get_slab(page); + + VM_BUG_ON(!PageSlab(page)); + return page->slab_page; } static inline void *index_to_obj(struct kmem_cache *cache, struct slab *slab, unsigned int idx) { - return slab->s_mem + cache->buffer_size * idx; + return slab->s_mem + cache->size * idx; } /* - * We want to avoid an expensive divide : (offset / cache->buffer_size) - * Using the fact that buffer_size is a constant for a particular cache, - * we can replace (offset / cache->buffer_size) by + * We want to avoid an expensive divide : (offset / cache->size) + * Using the fact that size is a constant for a particular cache, + * we can replace (offset / cache->size) by * reciprocal_divide(offset, cache->reciprocal_buffer_size) */ static inline unsigned int obj_to_index(const struct kmem_cache *cache, @@ -584,33 +591,12 @@ static struct kmem_cache cache_cache = { .batchcount = 1, .limit = BOOT_CPUCACHE_ENTRIES, .shared = 1, - .buffer_size = sizeof(struct kmem_cache), + .size = sizeof(struct kmem_cache), .name = "kmem_cache", }; #define BAD_ALIEN_MAGIC 0x01020304ul -/* - * chicken and egg problem: delay the per-cpu array allocation - * until the general caches are up. - */ -static enum { - NONE, - PARTIAL_AC, - PARTIAL_L3, - EARLY, - LATE, - FULL -} g_cpucache_up; - -/* - * used by boot code to determine if it can use slab based allocator - */ -int slab_is_available(void) -{ - return g_cpucache_up >= EARLY; -} - #ifdef CONFIG_LOCKDEP /* @@ -676,7 +662,7 @@ static void init_node_lock_keys(int q) { struct cache_sizes *s = malloc_sizes; - if (g_cpucache_up < LATE) + if (slab_state < UP) return; for (s = malloc_sizes; s->cs_size != ULONG_MAX; s++) { @@ -716,12 +702,6 @@ static void slab_set_debugobj_lock_classes(struct kmem_cache *cachep) } #endif -/* - * Guard access to the cache-chain. - */ -static DEFINE_MUTEX(cache_chain_mutex); -static struct list_head cache_chain; - static DEFINE_PER_CPU(struct delayed_work, slab_reap_work); static inline struct array_cache *cpu_cache_get(struct kmem_cache *cachep) @@ -951,6 +931,124 @@ static struct array_cache *alloc_arraycache(int node, int entries, return nc; } +static inline bool is_slab_pfmemalloc(struct slab *slabp) +{ + struct page *page = virt_to_page(slabp->s_mem); + + return PageSlabPfmemalloc(page); +} + +/* Clears pfmemalloc_active if no slabs have pfmalloc set */ +static void recheck_pfmemalloc_active(struct kmem_cache *cachep, + struct array_cache *ac) +{ + struct kmem_list3 *l3 = cachep->nodelists[numa_mem_id()]; + struct slab *slabp; + unsigned long flags; + + if (!pfmemalloc_active) + return; + + spin_lock_irqsave(&l3->list_lock, flags); + list_for_each_entry(slabp, &l3->slabs_full, list) + if (is_slab_pfmemalloc(slabp)) + goto out; + + list_for_each_entry(slabp, &l3->slabs_partial, list) + if (is_slab_pfmemalloc(slabp)) + goto out; + + list_for_each_entry(slabp, &l3->slabs_free, list) + if (is_slab_pfmemalloc(slabp)) + goto out; + + pfmemalloc_active = false; +out: + spin_unlock_irqrestore(&l3->list_lock, flags); +} + +static void *__ac_get_obj(struct kmem_cache *cachep, struct array_cache *ac, + gfp_t flags, bool force_refill) +{ + int i; + void *objp = ac->entry[--ac->avail]; + + /* Ensure the caller is allowed to use objects from PFMEMALLOC slab */ + if (unlikely(is_obj_pfmemalloc(objp))) { + struct kmem_list3 *l3; + + if (gfp_pfmemalloc_allowed(flags)) { + clear_obj_pfmemalloc(&objp); + return objp; + } + + /* The caller cannot use PFMEMALLOC objects, find another one */ + for (i = 1; i < ac->avail; i++) { + /* If a !PFMEMALLOC object is found, swap them */ + if (!is_obj_pfmemalloc(ac->entry[i])) { + objp = ac->entry[i]; + ac->entry[i] = ac->entry[ac->avail]; + ac->entry[ac->avail] = objp; + return objp; + } + } + + /* + * If there are empty slabs on the slabs_free list and we are + * being forced to refill the cache, mark this one !pfmemalloc. + */ + l3 = cachep->nodelists[numa_mem_id()]; + if (!list_empty(&l3->slabs_free) && force_refill) { + struct slab *slabp = virt_to_slab(objp); + ClearPageSlabPfmemalloc(virt_to_page(slabp->s_mem)); + clear_obj_pfmemalloc(&objp); + recheck_pfmemalloc_active(cachep, ac); + return objp; + } + + /* No !PFMEMALLOC objects available */ + ac->avail++; + objp = NULL; + } + + return objp; +} + +static inline void *ac_get_obj(struct kmem_cache *cachep, + struct array_cache *ac, gfp_t flags, bool force_refill) +{ + void *objp; + + if (unlikely(sk_memalloc_socks())) + objp = __ac_get_obj(cachep, ac, flags, force_refill); + else + objp = ac->entry[--ac->avail]; + + return objp; +} + +static void *__ac_put_obj(struct kmem_cache *cachep, struct array_cache *ac, + void *objp) +{ + if (unlikely(pfmemalloc_active)) { + /* Some pfmemalloc slabs exist, check if this is one */ + struct page *page = virt_to_page(objp); + if (PageSlabPfmemalloc(page)) + set_obj_pfmemalloc(&objp); + } + + return objp; +} + +static inline void ac_put_obj(struct kmem_cache *cachep, struct array_cache *ac, + void *objp) +{ + if (unlikely(sk_memalloc_socks())) + objp = __ac_put_obj(cachep, ac, objp); + + ac->entry[ac->avail++] = objp; +} + /* * Transfer objects in one arraycache to another. * Locking must be handled by the caller. @@ -1127,7 +1225,7 @@ static inline int cache_free_alien(struct kmem_cache *cachep, void *objp) STATS_INC_ACOVERFLOW(cachep); __drain_alien_cache(cachep, alien, nodeid); } - alien->entry[alien->avail++] = objp; + ac_put_obj(cachep, alien, objp); spin_unlock(&alien->lock); } else { spin_lock(&(cachep->nodelists[nodeid])->list_lock); @@ -1145,7 +1243,7 @@ static inline int cache_free_alien(struct kmem_cache *cachep, void *objp) * When hotplugging memory or a cpu, existing nodelists are not replaced if * already in use. * - * Must hold cache_chain_mutex. + * Must hold slab_mutex. */ static int init_cache_nodelists_node(int node) { @@ -1153,7 +1251,7 @@ static int init_cache_nodelists_node(int node) struct kmem_list3 *l3; const int memsize = sizeof(struct kmem_list3); - list_for_each_entry(cachep, &cache_chain, next) { + list_for_each_entry(cachep, &slab_caches, list) { /* * Set up the size64 kmemlist for cpu before we can * begin anything. Make sure some other cpu on this @@ -1169,7 +1267,7 @@ static int init_cache_nodelists_node(int node) /* * The l3s don't come and go as CPUs come and - * go. cache_chain_mutex is sufficient + * go. slab_mutex is sufficient * protection here. */ cachep->nodelists[node] = l3; @@ -1191,7 +1289,7 @@ static void __cpuinit cpuup_canceled(long cpu) int node = cpu_to_mem(cpu); const struct cpumask *mask = cpumask_of_node(node); - list_for_each_entry(cachep, &cache_chain, next) { + list_for_each_entry(cachep, &slab_caches, list) { struct array_cache *nc; struct array_cache *shared; struct array_cache **alien; @@ -1241,7 +1339,7 @@ free_array_cache: * the respective cache's slabs, now we can go ahead and * shrink each nodelist to its limit. */ - list_for_each_entry(cachep, &cache_chain, next) { + list_for_each_entry(cachep, &slab_caches, list) { l3 = cachep->nodelists[node]; if (!l3) continue; @@ -1270,7 +1368,7 @@ static int __cpuinit cpuup_prepare(long cpu) * Now we can go ahead with allocating the shared arrays and * array caches */ - list_for_each_entry(cachep, &cache_chain, next) { + list_for_each_entry(cachep, &slab_caches, list) { struct array_cache *nc; struct array_cache *shared = NULL; struct array_cache **alien = NULL; @@ -1338,9 +1436,9 @@ static int __cpuinit cpuup_callback(struct notifier_block *nfb, switch (action) { case CPU_UP_PREPARE: case CPU_UP_PREPARE_FROZEN: - mutex_lock(&cache_chain_mutex); + mutex_lock(&slab_mutex); err = cpuup_prepare(cpu); - mutex_unlock(&cache_chain_mutex); + mutex_unlock(&slab_mutex); break; case CPU_ONLINE: case CPU_ONLINE_FROZEN: @@ -1350,7 +1448,7 @@ static int __cpuinit cpuup_callback(struct notifier_block *nfb, case CPU_DOWN_PREPARE: case CPU_DOWN_PREPARE_FROZEN: /* - * Shutdown cache reaper. Note that the cache_chain_mutex is + * Shutdown cache reaper. Note that the slab_mutex is * held so that if cache_reap() is invoked it cannot do * anything expensive but will only modify reap_work * and reschedule the timer. @@ -1377,9 +1475,9 @@ static int __cpuinit cpuup_callback(struct notifier_block *nfb, #endif case CPU_UP_CANCELED: case CPU_UP_CANCELED_FROZEN: - mutex_lock(&cache_chain_mutex); + mutex_lock(&slab_mutex); cpuup_canceled(cpu); - mutex_unlock(&cache_chain_mutex); + mutex_unlock(&slab_mutex); break; } return notifier_from_errno(err); @@ -1395,14 +1493,14 @@ static struct notifier_block __cpuinitdata cpucache_notifier = { * Returns -EBUSY if all objects cannot be drained so that the node is not * removed. * - * Must hold cache_chain_mutex. + * Must hold slab_mutex. */ static int __meminit drain_cache_nodelists_node(int node) { struct kmem_cache *cachep; int ret = 0; - list_for_each_entry(cachep, &cache_chain, next) { + list_for_each_entry(cachep, &slab_caches, list) { struct kmem_list3 *l3; l3 = cachep->nodelists[node]; @@ -1433,14 +1531,14 @@ static int __meminit slab_memory_callback(struct notifier_block *self, switch (action) { case MEM_GOING_ONLINE: - mutex_lock(&cache_chain_mutex); + mutex_lock(&slab_mutex); ret = init_cache_nodelists_node(nid); - mutex_unlock(&cache_chain_mutex); + mutex_unlock(&slab_mutex); break; case MEM_GOING_OFFLINE: - mutex_lock(&cache_chain_mutex); + mutex_lock(&slab_mutex); ret = drain_cache_nodelists_node(nid); - mutex_unlock(&cache_chain_mutex); + mutex_unlock(&slab_mutex); break; case MEM_ONLINE: case MEM_OFFLINE: @@ -1544,8 +1642,8 @@ void __init kmem_cache_init(void) node = numa_mem_id(); /* 1) create the cache_cache */ - INIT_LIST_HEAD(&cache_chain); - list_add(&cache_cache.next, &cache_chain); + INIT_LIST_HEAD(&slab_caches); + list_add(&cache_cache.list, &slab_caches); cache_cache.colour_off = cache_line_size(); cache_cache.array[smp_processor_id()] = &initarray_cache.cache; cache_cache.nodelists[node] = &initkmem_list3[CACHE_CACHE + node]; @@ -1553,18 +1651,16 @@ void __init kmem_cache_init(void) /* * struct kmem_cache size depends on nr_node_ids & nr_cpu_ids */ - cache_cache.buffer_size = offsetof(struct kmem_cache, array[nr_cpu_ids]) + + cache_cache.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 - cache_cache.buffer_size = ALIGN(cache_cache.buffer_size, + cache_cache.object_size = cache_cache.size; + cache_cache.size = ALIGN(cache_cache.size, cache_line_size()); cache_cache.reciprocal_buffer_size = - reciprocal_value(cache_cache.buffer_size); + reciprocal_value(cache_cache.size); for (order = 0; order < MAX_ORDER; order++) { - cache_estimate(order, cache_cache.buffer_size, + cache_estimate(order, cache_cache.size, cache_line_size(), 0, &left_over, &cache_cache.num); if (cache_cache.num) break; @@ -1585,7 +1681,7 @@ void __init kmem_cache_init(void) * bug. */ - sizes[INDEX_AC].cs_cachep = kmem_cache_create(names[INDEX_AC].name, + sizes[INDEX_AC].cs_cachep = __kmem_cache_create(names[INDEX_AC].name, sizes[INDEX_AC].cs_size, ARCH_KMALLOC_MINALIGN, ARCH_KMALLOC_FLAGS|SLAB_PANIC, @@ -1593,7 +1689,7 @@ void __init kmem_cache_init(void) if (INDEX_AC != INDEX_L3) { sizes[INDEX_L3].cs_cachep = - kmem_cache_create(names[INDEX_L3].name, + __kmem_cache_create(names[INDEX_L3].name, sizes[INDEX_L3].cs_size, ARCH_KMALLOC_MINALIGN, ARCH_KMALLOC_FLAGS|SLAB_PANIC, @@ -1611,14 +1707,14 @@ void __init kmem_cache_init(void) * allow tighter packing of the smaller caches. */ if (!sizes->cs_cachep) { - sizes->cs_cachep = kmem_cache_create(names->name, + sizes->cs_cachep = __kmem_cache_create(names->name, sizes->cs_size, ARCH_KMALLOC_MINALIGN, ARCH_KMALLOC_FLAGS|SLAB_PANIC, NULL); } #ifdef CONFIG_ZONE_DMA - sizes->cs_dmacachep = kmem_cache_create( + sizes->cs_dmacachep = __kmem_cache_create( names->name_dma, sizes->cs_size, ARCH_KMALLOC_MINALIGN, @@ -1676,27 +1772,27 @@ void __init kmem_cache_init(void) } } - g_cpucache_up = EARLY; + slab_state = UP; } void __init kmem_cache_init_late(void) { struct kmem_cache *cachep; - g_cpucache_up = LATE; + slab_state = UP; /* 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) + mutex_lock(&slab_mutex); + list_for_each_entry(cachep, &slab_caches, list) if (enable_cpucache(cachep, GFP_NOWAIT)) BUG(); - mutex_unlock(&cache_chain_mutex); + mutex_unlock(&slab_mutex); /* Done! */ - g_cpucache_up = FULL; + slab_state = FULL; /* * Register a cpu startup notifier callback that initializes @@ -1727,6 +1823,9 @@ static int __init cpucache_init(void) */ for_each_online_cpu(cpu) start_cpu_timer(cpu); + + /* Done! */ + slab_state = FULL; return 0; } __initcall(cpucache_init); @@ -1743,7 +1842,7 @@ slab_out_of_memory(struct kmem_cache *cachep, gfp_t gfpflags, int nodeid) "SLAB: Unable to allocate memory on node %d (gfp=0x%x)\n", nodeid, gfpflags); printk(KERN_WARNING " cache: %s, object size: %d, order: %d\n", - cachep->name, cachep->buffer_size, cachep->gfporder); + cachep->name, cachep->size, cachep->gfporder); for_each_online_node(node) { unsigned long active_objs = 0, num_objs = 0, free_objects = 0; @@ -1798,7 +1897,7 @@ static void *kmem_getpages(struct kmem_cache *cachep, gfp_t flags, int nodeid) flags |= __GFP_COMP; #endif - flags |= cachep->gfpflags; + flags |= cachep->allocflags; if (cachep->flags & SLAB_RECLAIM_ACCOUNT) flags |= __GFP_RECLAIMABLE; @@ -1809,6 +1908,10 @@ static void *kmem_getpages(struct kmem_cache *cachep, gfp_t flags, int nodeid) return NULL; } + /* Record if ALLOC_NO_WATERMARKS was set when allocating the slab */ + if (unlikely(page->pfmemalloc)) + pfmemalloc_active = true; + nr_pages = (1 << cachep->gfporder); if (cachep->flags & SLAB_RECLAIM_ACCOUNT) add_zone_page_state(page_zone(page), @@ -1816,9 +1919,13 @@ static void *kmem_getpages(struct kmem_cache *cachep, gfp_t flags, int nodeid) else add_zone_page_state(page_zone(page), NR_SLAB_UNRECLAIMABLE, nr_pages); - for (i = 0; i < nr_pages; i++) + for (i = 0; i < nr_pages; i++) { __SetPageSlab(page + i); + if (page->pfmemalloc) + SetPageSlabPfmemalloc(page + i); + } + if (kmemcheck_enabled && !(cachep->flags & SLAB_NOTRACK)) { kmemcheck_alloc_shadow(page, cachep->gfporder, flags, nodeid); @@ -1850,6 +1957,7 @@ static void kmem_freepages(struct kmem_cache *cachep, void *addr) NR_SLAB_UNRECLAIMABLE, nr_freed); while (i--) { BUG_ON(!PageSlab(page)); + __ClearPageSlabPfmemalloc(page); __ClearPageSlab(page); page++; } @@ -1874,7 +1982,7 @@ static void kmem_rcu_free(struct rcu_head *head) static void store_stackinfo(struct kmem_cache *cachep, unsigned long *addr, unsigned long caller) { - int size = obj_size(cachep); + int size = cachep->object_size; addr = (unsigned long *)&((char *)addr)[obj_offset(cachep)]; @@ -1906,7 +2014,7 @@ static void store_stackinfo(struct kmem_cache *cachep, unsigned long *addr, static void poison_obj(struct kmem_cache *cachep, void *addr, unsigned char val) { - int size = obj_size(cachep); + int size = cachep->object_size; addr = &((char *)addr)[obj_offset(cachep)]; memset(addr, val, size); @@ -1966,7 +2074,7 @@ static void print_objinfo(struct kmem_cache *cachep, void *objp, int lines) printk("\n"); } realobj = (char *)objp + obj_offset(cachep); - size = obj_size(cachep); + size = cachep->object_size; for (i = 0; i < size && lines; i += 16, lines--) { int limit; limit = 16; @@ -1983,7 +2091,7 @@ static void check_poison_obj(struct kmem_cache *cachep, void *objp) int lines = 0; realobj = (char *)objp + obj_offset(cachep); - size = obj_size(cachep); + size = cachep->object_size; for (i = 0; i < size; i++) { char exp = POISON_FREE; @@ -2047,10 +2155,10 @@ static void slab_destroy_debugcheck(struct kmem_cache *cachep, struct slab *slab if (cachep->flags & SLAB_POISON) { #ifdef CONFIG_DEBUG_PAGEALLOC - if (cachep->buffer_size % PAGE_SIZE == 0 && + if (cachep->size % PAGE_SIZE == 0 && OFF_SLAB(cachep)) kernel_map_pages(virt_to_page(objp), - cachep->buffer_size / PAGE_SIZE, 1); + cachep->size / PAGE_SIZE, 1); else check_poison_obj(cachep, objp); #else @@ -2194,10 +2302,10 @@ static size_t calculate_slab_order(struct kmem_cache *cachep, static int __init_refok setup_cpu_cache(struct kmem_cache *cachep, gfp_t gfp) { - if (g_cpucache_up == FULL) + if (slab_state >= FULL) return enable_cpucache(cachep, gfp); - if (g_cpucache_up == NONE) { + if (slab_state == DOWN) { /* * Note: the first kmem_cache_create must create the cache * that's used by kmalloc(24), otherwise the creation of @@ -2212,16 +2320,16 @@ static int __init_refok setup_cpu_cache(struct kmem_cache *cachep, gfp_t gfp) */ set_up_list3s(cachep, SIZE_AC); if (INDEX_AC == INDEX_L3) - g_cpucache_up = PARTIAL_L3; + slab_state = PARTIAL_L3; else - g_cpucache_up = PARTIAL_AC; + slab_state = PARTIAL_ARRAYCACHE; } else { cachep->array[smp_processor_id()] = kmalloc(sizeof(struct arraycache_init), gfp); - if (g_cpucache_up == PARTIAL_AC) { + if (slab_state == PARTIAL_ARRAYCACHE) { set_up_list3s(cachep, SIZE_L3); - g_cpucache_up = PARTIAL_L3; + slab_state = PARTIAL_L3; } else { int node; for_each_online_node(node) { @@ -2247,7 +2355,7 @@ static int __init_refok setup_cpu_cache(struct kmem_cache *cachep, gfp_t gfp) } /** - * kmem_cache_create - Create a cache. + * __kmem_cache_create - Create a cache. * @name: A string which is used in /proc/slabinfo to identify this cache. * @size: The size of objects to be created in this cache. * @align: The required alignment for the objects. @@ -2274,59 +2382,14 @@ static int __init_refok setup_cpu_cache(struct kmem_cache *cachep, gfp_t gfp) * as davem. */ struct kmem_cache * -kmem_cache_create (const char *name, size_t size, size_t align, +__kmem_cache_create (const char *name, size_t size, size_t align, unsigned long flags, void (*ctor)(void *)) { size_t left_over, slab_size, ralign; - struct kmem_cache *cachep = NULL, *pc; + struct kmem_cache *cachep = NULL; gfp_t gfp; - /* - * Sanity checks... these are all serious usage bugs. - */ - if (!name || in_interrupt() || (size < BYTES_PER_WORD) || - size > KMALLOC_MAX_SIZE) { - printk(KERN_ERR "%s: Early error in slab %s\n", __func__, - name); - BUG(); - } - - /* - * We use cache_chain_mutex to ensure a consistent view of - * cpu_online_mask as well. Please see cpuup_callback - */ - if (slab_is_available()) { - get_online_cpus(); - mutex_lock(&cache_chain_mutex); - } - - list_for_each_entry(pc, &cache_chain, next) { - char tmp; - int res; - - /* - * This happens when the module gets unloaded and doesn't - * destroy its slab cache and no-one else reuses the vmalloc - * area of the module. Print a warning. - */ - res = probe_kernel_address(pc->name, tmp); - if (res) { - printk(KERN_ERR - "SLAB: cache with size %d has lost its name\n", - pc->buffer_size); - continue; - } - - if (!strcmp(pc->name, name)) { - printk(KERN_ERR - "kmem_cache_create: duplicate cache %s\n", name); - dump_stack(); - goto oops; - } - } - #if DEBUG - WARN_ON(strchr(name, ' ')); /* It confuses parsers */ #if FORCED_DEBUG /* * Enable redzoning and last user accounting, except for caches with @@ -2415,11 +2478,12 @@ kmem_cache_create (const char *name, size_t size, size_t align, /* Get cache's description obj. */ cachep = kmem_cache_zalloc(&cache_cache, gfp); if (!cachep) - goto oops; + return NULL; cachep->nodelists = (struct kmem_list3 **)&cachep->array[nr_cpu_ids]; + cachep->object_size = size; + cachep->align = align; #if DEBUG - cachep->obj_size = size; /* * Both debugging options require word-alignment which is calculated @@ -2442,7 +2506,7 @@ kmem_cache_create (const char *name, size_t size, size_t align, } #if FORCED_DEBUG && defined(CONFIG_DEBUG_PAGEALLOC) if (size >= malloc_sizes[INDEX_L3 + 1].cs_size - && cachep->obj_size > cache_line_size() && ALIGN(size, align) < PAGE_SIZE) { + && cachep->object_size > cache_line_size() && ALIGN(size, align) < PAGE_SIZE) { cachep->obj_offset += PAGE_SIZE - ALIGN(size, align); size = PAGE_SIZE; } @@ -2471,8 +2535,7 @@ kmem_cache_create (const char *name, size_t size, size_t align, printk(KERN_ERR "kmem_cache_create: couldn't create cache %s.\n", name); kmem_cache_free(&cache_cache, cachep); - cachep = NULL; - goto oops; + return NULL; } slab_size = ALIGN(cachep->num * sizeof(kmem_bufctl_t) + sizeof(struct slab), align); @@ -2508,10 +2571,10 @@ kmem_cache_create (const char *name, size_t size, size_t align, cachep->colour = left_over / cachep->colour_off; cachep->slab_size = slab_size; cachep->flags = flags; - cachep->gfpflags = 0; + cachep->allocflags = 0; if (CONFIG_ZONE_DMA_FLAG && (flags & SLAB_CACHE_DMA)) - cachep->gfpflags |= GFP_DMA; - cachep->buffer_size = size; + cachep->allocflags |= GFP_DMA; + cachep->size = size; cachep->reciprocal_buffer_size = reciprocal_value(size); if (flags & CFLGS_OFF_SLAB) { @@ -2530,8 +2593,7 @@ kmem_cache_create (const char *name, size_t size, size_t align, if (setup_cpu_cache(cachep, gfp)) { __kmem_cache_destroy(cachep); - cachep = NULL; - goto oops; + return NULL; } if (flags & SLAB_DEBUG_OBJECTS) { @@ -2545,18 +2607,9 @@ kmem_cache_create (const char *name, size_t size, size_t align, } /* cache setup completed, link it into the list */ - list_add(&cachep->next, &cache_chain); -oops: - if (!cachep && (flags & SLAB_PANIC)) - panic("kmem_cache_create(): failed to create slab `%s'\n", - name); - if (slab_is_available()) { - mutex_unlock(&cache_chain_mutex); - put_online_cpus(); - } + list_add(&cachep->list, &slab_caches); return cachep; } -EXPORT_SYMBOL(kmem_cache_create); #if DEBUG static void check_irq_off(void) @@ -2671,7 +2724,7 @@ out: return nr_freed; } -/* Called with cache_chain_mutex held to protect against cpu hotplug */ +/* Called with slab_mutex held to protect against cpu hotplug */ static int __cache_shrink(struct kmem_cache *cachep) { int ret = 0, i = 0; @@ -2706,9 +2759,9 @@ int kmem_cache_shrink(struct kmem_cache *cachep) BUG_ON(!cachep || in_interrupt()); get_online_cpus(); - mutex_lock(&cache_chain_mutex); + mutex_lock(&slab_mutex); ret = __cache_shrink(cachep); - mutex_unlock(&cache_chain_mutex); + mutex_unlock(&slab_mutex); put_online_cpus(); return ret; } @@ -2736,15 +2789,15 @@ void kmem_cache_destroy(struct kmem_cache *cachep) /* Find the cache in the chain of caches. */ get_online_cpus(); - mutex_lock(&cache_chain_mutex); + mutex_lock(&slab_mutex); /* * the chain is never empty, cache_cache is never destroyed */ - list_del(&cachep->next); + list_del(&cachep->list); if (__cache_shrink(cachep)) { slab_error(cachep, "Can't free all objects"); - list_add(&cachep->next, &cache_chain); - mutex_unlock(&cache_chain_mutex); + list_add(&cachep->list, &slab_caches); + mutex_unlock(&slab_mutex); put_online_cpus(); return; } @@ -2753,7 +2806,7 @@ void kmem_cache_destroy(struct kmem_cache *cachep) rcu_barrier(); __kmem_cache_destroy(cachep); - mutex_unlock(&cache_chain_mutex); + mutex_unlock(&slab_mutex); put_online_cpus(); } EXPORT_SYMBOL(kmem_cache_destroy); @@ -2840,10 +2893,10 @@ static void cache_init_objs(struct kmem_cache *cachep, slab_error(cachep, "constructor overwrote the" " start of an object"); } - if ((cachep->buffer_size % PAGE_SIZE) == 0 && + if ((cachep->size % PAGE_SIZE) == 0 && OFF_SLAB(cachep) && cachep->flags & SLAB_POISON) kernel_map_pages(virt_to_page(objp), - cachep->buffer_size / PAGE_SIZE, 0); + cachep->size / PAGE_SIZE, 0); #else if (cachep->ctor) cachep->ctor(objp); @@ -2857,9 +2910,9 @@ static void kmem_flagcheck(struct kmem_cache *cachep, gfp_t flags) { if (CONFIG_ZONE_DMA_FLAG) { if (flags & GFP_DMA) - BUG_ON(!(cachep->gfpflags & GFP_DMA)); + BUG_ON(!(cachep->allocflags & GFP_DMA)); else - BUG_ON(cachep->gfpflags & GFP_DMA); + BUG_ON(cachep->allocflags & GFP_DMA); } } @@ -2918,8 +2971,8 @@ static void slab_map_pages(struct kmem_cache *cache, struct slab *slab, nr_pages <<= cache->gfporder; do { - page_set_cache(page, cache); - page_set_slab(page, slab); + page->slab_cache = cache; + page->slab_page = slab; page++; } while (--nr_pages); } @@ -3057,7 +3110,7 @@ static void *cache_free_debugcheck(struct kmem_cache *cachep, void *objp, kfree_debugcheck(objp); page = virt_to_head_page(objp); - slabp = page_get_slab(page); + slabp = page->slab_page; if (cachep->flags & SLAB_RED_ZONE) { verify_redzone_free(cachep, objp); @@ -3077,10 +3130,10 @@ static void *cache_free_debugcheck(struct kmem_cache *cachep, void *objp, #endif if (cachep->flags & SLAB_POISON) { #ifdef CONFIG_DEBUG_PAGEALLOC - if ((cachep->buffer_size % PAGE_SIZE)==0 && OFF_SLAB(cachep)) { + if ((cachep->size % PAGE_SIZE)==0 && OFF_SLAB(cachep)) { store_stackinfo(cachep, objp, (unsigned long)caller); kernel_map_pages(virt_to_page(objp), - cachep->buffer_size / PAGE_SIZE, 0); + cachep->size / PAGE_SIZE, 0); } else { poison_obj(cachep, objp, POISON_FREE); } @@ -3120,16 +3173,19 @@ bad: #define check_slabp(x,y) do { } while(0) #endif -static void *cache_alloc_refill(struct kmem_cache *cachep, gfp_t flags) +static void *cache_alloc_refill(struct kmem_cache *cachep, gfp_t flags, + bool force_refill) { int batchcount; struct kmem_list3 *l3; struct array_cache *ac; int node; -retry: check_irq_off(); node = numa_mem_id(); + if (unlikely(force_refill)) + goto force_grow; +retry: ac = cpu_cache_get(cachep); batchcount = ac->batchcount; if (!ac->touched && batchcount > BATCHREFILL_LIMIT) { @@ -3179,8 +3235,8 @@ retry: STATS_INC_ACTIVE(cachep); STATS_SET_HIGH(cachep); - ac->entry[ac->avail++] = slab_get_obj(cachep, slabp, - node); + ac_put_obj(cachep, ac, slab_get_obj(cachep, slabp, + node)); } check_slabp(cachep, slabp); @@ -3199,18 +3255,22 @@ alloc_done: if (unlikely(!ac->avail)) { int x; +force_grow: x = cache_grow(cachep, flags | GFP_THISNODE, node, NULL); /* cache_grow can reenable interrupts, then ac could change. */ ac = cpu_cache_get(cachep); - if (!x && ac->avail == 0) /* no objects in sight? abort */ + + /* no objects in sight? abort */ + if (!x && (ac->avail == 0 || force_refill)) return NULL; if (!ac->avail) /* objects refilled by interrupt? */ goto retry; } ac->touched = 1; - return ac->entry[--ac->avail]; + + return ac_get_obj(cachep, ac, flags, force_refill); } static inline void cache_alloc_debugcheck_before(struct kmem_cache *cachep, @@ -3230,9 +3290,9 @@ static void *cache_alloc_debugcheck_after(struct kmem_cache *cachep, return objp; if (cachep->flags & SLAB_POISON) { #ifdef CONFIG_DEBUG_PAGEALLOC - if ((cachep->buffer_size % PAGE_SIZE) == 0 && OFF_SLAB(cachep)) + if ((cachep->size % PAGE_SIZE) == 0 && OFF_SLAB(cachep)) kernel_map_pages(virt_to_page(objp), - cachep->buffer_size / PAGE_SIZE, 1); + cachep->size / PAGE_SIZE, 1); else check_poison_obj(cachep, objp); #else @@ -3261,8 +3321,8 @@ static void *cache_alloc_debugcheck_after(struct kmem_cache *cachep, struct slab *slabp; unsigned objnr; - slabp = page_get_slab(virt_to_head_page(objp)); - objnr = (unsigned)(objp - slabp->s_mem) / cachep->buffer_size; + slabp = virt_to_head_page(objp)->slab_page; + objnr = (unsigned)(objp - slabp->s_mem) / cachep->size; slab_bufctl(slabp)[objnr] = BUFCTL_ACTIVE; } #endif @@ -3285,30 +3345,42 @@ static bool slab_should_failslab(struct kmem_cache *cachep, gfp_t flags) if (cachep == &cache_cache) return false; - return should_failslab(obj_size(cachep), flags, cachep->flags); + return should_failslab(cachep->object_size, flags, cachep->flags); } static inline void *____cache_alloc(struct kmem_cache *cachep, gfp_t flags) { void *objp; struct array_cache *ac; + bool force_refill = false; check_irq_off(); ac = cpu_cache_get(cachep); if (likely(ac->avail)) { - STATS_INC_ALLOCHIT(cachep); ac->touched = 1; - objp = ac->entry[--ac->avail]; - } else { - STATS_INC_ALLOCMISS(cachep); - objp = cache_alloc_refill(cachep, flags); + objp = ac_get_obj(cachep, ac, flags, false); + /* - * the 'ac' may be updated by cache_alloc_refill(), - * and kmemleak_erase() requires its correct value. + * Allow for the possibility all avail objects are not allowed + * by the current flags */ - ac = cpu_cache_get(cachep); + if (objp) { + STATS_INC_ALLOCHIT(cachep); + goto out; + } + force_refill = true; } + + STATS_INC_ALLOCMISS(cachep); + objp = cache_alloc_refill(cachep, flags, force_refill); + /* + * the 'ac' may be updated by cache_alloc_refill(), + * and kmemleak_erase() requires its correct value. + */ + ac = cpu_cache_get(cachep); + +out: /* * To avoid a false negative, if an object that is in one of the * per-CPU caches is leaked, we need to make sure kmemleak doesn't @@ -3336,7 +3408,7 @@ static void *alternate_node_alloc(struct kmem_cache *cachep, gfp_t flags) if (cpuset_do_slab_mem_spread() && (cachep->flags & SLAB_MEM_SPREAD)) nid_alloc = cpuset_slab_spread_node(); else if (current->mempolicy) - nid_alloc = slab_node(current->mempolicy); + nid_alloc = slab_node(); if (nid_alloc != nid_here) return ____cache_alloc_node(cachep, flags, nid_alloc); return NULL; @@ -3368,7 +3440,7 @@ static void *fallback_alloc(struct kmem_cache *cache, gfp_t flags) retry_cpuset: cpuset_mems_cookie = get_mems_allowed(); - zonelist = node_zonelist(slab_node(current->mempolicy), flags); + zonelist = node_zonelist(slab_node(), flags); retry: /* @@ -3545,14 +3617,14 @@ __cache_alloc_node(struct kmem_cache *cachep, gfp_t flags, int nodeid, out: local_irq_restore(save_flags); ptr = cache_alloc_debugcheck_after(cachep, flags, ptr, caller); - kmemleak_alloc_recursive(ptr, obj_size(cachep), 1, cachep->flags, + kmemleak_alloc_recursive(ptr, cachep->object_size, 1, cachep->flags, flags); if (likely(ptr)) - kmemcheck_slab_alloc(cachep, flags, ptr, obj_size(cachep)); + kmemcheck_slab_alloc(cachep, flags, ptr, cachep->object_size); if (unlikely((flags & __GFP_ZERO) && ptr)) - memset(ptr, 0, obj_size(cachep)); + memset(ptr, 0, cachep->object_size); return ptr; } @@ -3607,15 +3679,15 @@ __cache_alloc(struct kmem_cache *cachep, gfp_t flags, void *caller) objp = __do_cache_alloc(cachep, flags); local_irq_restore(save_flags); objp = cache_alloc_debugcheck_after(cachep, flags, objp, caller); - kmemleak_alloc_recursive(objp, obj_size(cachep), 1, cachep->flags, + kmemleak_alloc_recursive(objp, cachep->object_size, 1, cachep->flags, flags); prefetchw(objp); if (likely(objp)) - kmemcheck_slab_alloc(cachep, flags, objp, obj_size(cachep)); + kmemcheck_slab_alloc(cachep, flags, objp, cachep->object_size); if (unlikely((flags & __GFP_ZERO) && objp)) - memset(objp, 0, obj_size(cachep)); + memset(objp, 0, cachep->object_size); return objp; } @@ -3630,9 +3702,12 @@ static void free_block(struct kmem_cache *cachep, void **objpp, int nr_objects, struct kmem_list3 *l3; for (i = 0; i < nr_objects; i++) { - void *objp = objpp[i]; + void *objp; struct slab *slabp; + clear_obj_pfmemalloc(&objpp[i]); + objp = objpp[i]; + slabp = virt_to_slab(objp); l3 = cachep->nodelists[node]; list_del(&slabp->list); @@ -3731,7 +3806,7 @@ static inline void __cache_free(struct kmem_cache *cachep, void *objp, kmemleak_free_recursive(objp, cachep->flags); objp = cache_free_debugcheck(cachep, objp, caller); - kmemcheck_slab_free(cachep, objp, obj_size(cachep)); + kmemcheck_slab_free(cachep, objp, cachep->object_size); /* * Skip calling cache_free_alien() when the platform is not numa. @@ -3750,7 +3825,7 @@ static inline void __cache_free(struct kmem_cache *cachep, void *objp, cache_flusharray(cachep, ac); } - ac->entry[ac->avail++] = objp; + ac_put_obj(cachep, ac, objp); } /** @@ -3766,7 +3841,7 @@ void *kmem_cache_alloc(struct kmem_cache *cachep, gfp_t flags) void *ret = __cache_alloc(cachep, flags, __builtin_return_address(0)); trace_kmem_cache_alloc(_RET_IP_, ret, - obj_size(cachep), cachep->buffer_size, flags); + cachep->object_size, cachep->size, flags); return ret; } @@ -3794,7 +3869,7 @@ void *kmem_cache_alloc_node(struct kmem_cache *cachep, gfp_t flags, int nodeid) __builtin_return_address(0)); trace_kmem_cache_alloc_node(_RET_IP_, ret, - obj_size(cachep), cachep->buffer_size, + cachep->object_size, cachep->size, flags, nodeid); return ret; @@ -3876,7 +3951,7 @@ static __always_inline void *__do_kmalloc(size_t size, gfp_t flags, ret = __cache_alloc(cachep, flags, caller); trace_kmalloc((unsigned long) caller, ret, - size, cachep->buffer_size, flags); + size, cachep->size, flags); return ret; } @@ -3916,9 +3991,9 @@ void kmem_cache_free(struct kmem_cache *cachep, void *objp) unsigned long flags; local_irq_save(flags); - debug_check_no_locks_freed(objp, obj_size(cachep)); + debug_check_no_locks_freed(objp, cachep->object_size); if (!(cachep->flags & SLAB_DEBUG_OBJECTS)) - debug_check_no_obj_freed(objp, obj_size(cachep)); + debug_check_no_obj_freed(objp, cachep->object_size); __cache_free(cachep, objp, __builtin_return_address(0)); local_irq_restore(flags); @@ -3947,8 +4022,9 @@ void kfree(const void *objp) local_irq_save(flags); kfree_debugcheck(objp); c = virt_to_cache(objp); - debug_check_no_locks_freed(objp, obj_size(c)); - debug_check_no_obj_freed(objp, obj_size(c)); + debug_check_no_locks_freed(objp, c->object_size); + + debug_check_no_obj_freed(objp, c->object_size); __cache_free(c, (void *)objp, __builtin_return_address(0)); local_irq_restore(flags); } @@ -3956,7 +4032,7 @@ EXPORT_SYMBOL(kfree); unsigned int kmem_cache_size(struct kmem_cache *cachep) { - return obj_size(cachep); + return cachep->object_size; } EXPORT_SYMBOL(kmem_cache_size); @@ -4030,7 +4106,7 @@ static int alloc_kmemlist(struct kmem_cache *cachep, gfp_t gfp) return 0; fail: - if (!cachep->next.next) { + if (!cachep->list.next) { /* Cache is not active yet. Roll back what we did */ node--; while (node >= 0) { @@ -4065,7 +4141,7 @@ static void do_ccupdate_local(void *info) new->new[smp_processor_id()] = old; } -/* Always called with the cache_chain_mutex held */ +/* Always called with the slab_mutex held */ static int do_tune_cpucache(struct kmem_cache *cachep, int limit, int batchcount, int shared, gfp_t gfp) { @@ -4109,7 +4185,7 @@ static int do_tune_cpucache(struct kmem_cache *cachep, int limit, return alloc_kmemlist(cachep, gfp); } -/* Called with cache_chain_mutex held always */ +/* Called with slab_mutex held always */ static int enable_cpucache(struct kmem_cache *cachep, gfp_t gfp) { int err; @@ -4124,13 +4200,13 @@ static int enable_cpucache(struct kmem_cache *cachep, gfp_t gfp) * The numbers are guessed, we should auto-tune as described by * Bonwick. */ - if (cachep->buffer_size > 131072) + if (cachep->size > 131072) limit = 1; - else if (cachep->buffer_size > PAGE_SIZE) + else if (cachep->size > PAGE_SIZE) limit = 8; - else if (cachep->buffer_size > 1024) + else if (cachep->size > 1024) limit = 24; - else if (cachep->buffer_size > 256) + else if (cachep->size > 256) limit = 54; else limit = 120; @@ -4145,7 +4221,7 @@ static int enable_cpucache(struct kmem_cache *cachep, gfp_t gfp) * to a larger limit. Thus disabled by default. */ shared = 0; - if (cachep->buffer_size <= PAGE_SIZE && num_possible_cpus() > 1) + if (cachep->size <= PAGE_SIZE && num_possible_cpus() > 1) shared = 8; #if DEBUG @@ -4211,11 +4287,11 @@ static void cache_reap(struct work_struct *w) int node = numa_mem_id(); struct delayed_work *work = to_delayed_work(w); - if (!mutex_trylock(&cache_chain_mutex)) + if (!mutex_trylock(&slab_mutex)) /* Give up. Setup the next iteration. */ goto out; - list_for_each_entry(searchp, &cache_chain, next) { + list_for_each_entry(searchp, &slab_caches, list) { check_irq_on(); /* @@ -4253,7 +4329,7 @@ next: cond_resched(); } check_irq_on(); - mutex_unlock(&cache_chain_mutex); + mutex_unlock(&slab_mutex); next_reap_node(); out: /* Set up the next iteration */ @@ -4289,26 +4365,26 @@ static void *s_start(struct seq_file *m, loff_t *pos) { loff_t n = *pos; - mutex_lock(&cache_chain_mutex); + mutex_lock(&slab_mutex); if (!n) print_slabinfo_header(m); - return seq_list_start(&cache_chain, *pos); + return seq_list_start(&slab_caches, *pos); } static void *s_next(struct seq_file *m, void *p, loff_t *pos) { - return seq_list_next(p, &cache_chain, pos); + return seq_list_next(p, &slab_caches, pos); } static void s_stop(struct seq_file *m, void *p) { - mutex_unlock(&cache_chain_mutex); + mutex_unlock(&slab_mutex); } static int s_show(struct seq_file *m, void *p) { - struct kmem_cache *cachep = list_entry(p, struct kmem_cache, next); + struct kmem_cache *cachep = list_entry(p, struct kmem_cache, list); struct slab *slabp; unsigned long active_objs; unsigned long num_objs; @@ -4364,7 +4440,7 @@ static int s_show(struct seq_file *m, void *p) printk(KERN_ERR "slab: cache %s error: %s\n", name, error); seq_printf(m, "%-17s %6lu %6lu %6u %4u %4d", - name, active_objs, num_objs, cachep->buffer_size, + name, active_objs, num_objs, cachep->size, cachep->num, (1 << cachep->gfporder)); seq_printf(m, " : tunables %4u %4u %4u", cachep->limit, cachep->batchcount, cachep->shared); @@ -4454,9 +4530,9 @@ static ssize_t slabinfo_write(struct file *file, const char __user *buffer, return -EINVAL; /* Find the cache in the chain of caches. */ - mutex_lock(&cache_chain_mutex); + mutex_lock(&slab_mutex); res = -EINVAL; - list_for_each_entry(cachep, &cache_chain, next) { + list_for_each_entry(cachep, &slab_caches, list) { if (!strcmp(cachep->name, kbuf)) { if (limit < 1 || batchcount < 1 || batchcount > limit || shared < 0) { @@ -4469,7 +4545,7 @@ static ssize_t slabinfo_write(struct file *file, const char __user *buffer, break; } } - mutex_unlock(&cache_chain_mutex); + mutex_unlock(&slab_mutex); if (res >= 0) res = count; return res; @@ -4492,8 +4568,8 @@ static const struct file_operations proc_slabinfo_operations = { static void *leaks_start(struct seq_file *m, loff_t *pos) { - mutex_lock(&cache_chain_mutex); - return seq_list_start(&cache_chain, *pos); + mutex_lock(&slab_mutex); + return seq_list_start(&slab_caches, *pos); } static inline int add_caller(unsigned long *n, unsigned long v) @@ -4532,7 +4608,7 @@ static void handle_slab(unsigned long *n, struct kmem_cache *c, struct slab *s) int i; if (n[0] == n[1]) return; - for (i = 0, p = s->s_mem; i < c->num; i++, p += c->buffer_size) { + for (i = 0, p = s->s_mem; i < c->num; i++, p += c->size) { if (slab_bufctl(s)[i] != BUFCTL_ACTIVE) continue; if (!add_caller(n, (unsigned long)*dbg_userword(c, p))) @@ -4558,7 +4634,7 @@ static void show_symbol(struct seq_file *m, unsigned long address) static int leaks_show(struct seq_file *m, void *p) { - struct kmem_cache *cachep = list_entry(p, struct kmem_cache, next); + struct kmem_cache *cachep = list_entry(p, struct kmem_cache, list); struct slab *slabp; struct kmem_list3 *l3; const char *name; @@ -4592,17 +4668,17 @@ static int leaks_show(struct seq_file *m, void *p) name = cachep->name; if (n[0] == n[1]) { /* Increase the buffer size */ - mutex_unlock(&cache_chain_mutex); + mutex_unlock(&slab_mutex); m->private = kzalloc(n[0] * 4 * sizeof(unsigned long), GFP_KERNEL); if (!m->private) { /* Too bad, we are really out */ m->private = n; - mutex_lock(&cache_chain_mutex); + mutex_lock(&slab_mutex); return -ENOMEM; } *(unsigned long *)m->private = n[0] * 2; kfree(n); - mutex_lock(&cache_chain_mutex); + mutex_lock(&slab_mutex); /* Now make sure this entry will be retried */ m->count = m->size; return 0; @@ -4677,6 +4753,6 @@ size_t ksize(const void *objp) if (unlikely(objp == ZERO_SIZE_PTR)) return 0; - return obj_size(virt_to_cache(objp)); + return virt_to_cache(objp)->object_size; } EXPORT_SYMBOL(ksize); diff --git a/mm/slab.h b/mm/slab.h new file mode 100644 index 0000000..db7848c --- /dev/null +++ b/mm/slab.h @@ -0,0 +1,33 @@ +#ifndef MM_SLAB_H +#define MM_SLAB_H +/* + * Internal slab definitions + */ + +/* + * State of the slab allocator. + * + * This is used to describe the states of the allocator during bootup. + * Allocators use this to gradually bootstrap themselves. Most allocators + * have the problem that the structures used for managing slab caches are + * allocated from slab caches themselves. + */ +enum slab_state { + DOWN, /* No slab functionality yet */ + PARTIAL, /* SLUB: kmem_cache_node available */ + PARTIAL_ARRAYCACHE, /* SLAB: kmalloc size for arraycache available */ + PARTIAL_L3, /* SLAB: kmalloc size for l3 struct available */ + UP, /* Slab caches usable but not all extras yet */ + FULL /* Everything is working */ +}; + +extern enum slab_state slab_state; + +/* The slab cache mutex protects the management structures during changes */ +extern struct mutex slab_mutex; +extern struct list_head slab_caches; + +struct kmem_cache *__kmem_cache_create(const char *name, size_t size, + size_t align, unsigned long flags, void (*ctor)(void *)); + +#endif diff --git a/mm/slab_common.c b/mm/slab_common.c new file mode 100644 index 0000000..aa3ca5b --- /dev/null +++ b/mm/slab_common.c @@ -0,0 +1,120 @@ +/* + * Slab allocator functions that are independent of the allocator strategy + * + * (C) 2012 Christoph Lameter <cl@linux.com> + */ +#include <linux/slab.h> + +#include <linux/mm.h> +#include <linux/poison.h> +#include <linux/interrupt.h> +#include <linux/memory.h> +#include <linux/compiler.h> +#include <linux/module.h> +#include <linux/cpu.h> +#include <linux/uaccess.h> +#include <asm/cacheflush.h> +#include <asm/tlbflush.h> +#include <asm/page.h> + +#include "slab.h" + +enum slab_state slab_state; +LIST_HEAD(slab_caches); +DEFINE_MUTEX(slab_mutex); + +/* + * kmem_cache_create - Create a cache. + * @name: A string which is used in /proc/slabinfo to identify this cache. + * @size: The size of objects to be created in this cache. + * @align: The required alignment for the objects. + * @flags: SLAB flags + * @ctor: A constructor for the objects. + * + * Returns a ptr to the cache on success, NULL on failure. + * Cannot be called within a interrupt, but can be interrupted. + * The @ctor is run when new pages are allocated by the cache. + * + * The flags are + * + * %SLAB_POISON - Poison the slab with a known test pattern (a5a5a5a5) + * to catch references to uninitialised memory. + * + * %SLAB_RED_ZONE - Insert `Red' zones around the allocated memory to check + * for buffer overruns. + * + * %SLAB_HWCACHE_ALIGN - Align the objects in this cache to a hardware + * cacheline. This can be beneficial if you're counting cycles as closely + * as davem. + */ + +struct kmem_cache *kmem_cache_create(const char *name, size_t size, size_t align, + unsigned long flags, void (*ctor)(void *)) +{ + struct kmem_cache *s = NULL; + +#ifdef CONFIG_DEBUG_VM + if (!name || in_interrupt() || size < sizeof(void *) || + size > KMALLOC_MAX_SIZE) { + printk(KERN_ERR "kmem_cache_create(%s) integrity check" + " failed\n", name); + goto out; + } +#endif + + get_online_cpus(); + mutex_lock(&slab_mutex); + +#ifdef CONFIG_DEBUG_VM + list_for_each_entry(s, &slab_caches, list) { + char tmp; + int res; + + /* + * This happens when the module gets unloaded and doesn't + * destroy its slab cache and no-one else reuses the vmalloc + * area of the module. Print a warning. + */ + res = probe_kernel_address(s->name, tmp); + if (res) { + printk(KERN_ERR + "Slab cache with size %d has lost its name\n", + s->object_size); + continue; + } + + if (!strcmp(s->name, name)) { + printk(KERN_ERR "kmem_cache_create(%s): Cache name" + " already exists.\n", + name); + dump_stack(); + s = NULL; + goto oops; + } + } + + WARN_ON(strchr(name, ' ')); /* It confuses parsers */ +#endif + + s = __kmem_cache_create(name, size, align, flags, ctor); + +#ifdef CONFIG_DEBUG_VM +oops: +#endif + mutex_unlock(&slab_mutex); + put_online_cpus(); + +#ifdef CONFIG_DEBUG_VM +out: +#endif + if (!s && (flags & SLAB_PANIC)) + panic("kmem_cache_create: Failed to create slab '%s'\n", name); + + return s; +} +EXPORT_SYMBOL(kmem_cache_create); + +int slab_is_available(void) +{ + return slab_state >= UP; +} @@ -59,6 +59,8 @@ #include <linux/kernel.h> #include <linux/slab.h> +#include "slab.h" + #include <linux/mm.h> #include <linux/swap.h> /* struct reclaim_state */ #include <linux/cache.h> @@ -92,36 +94,6 @@ struct slob_block { typedef struct slob_block slob_t; /* - * We use struct page fields to manage some slob allocation aspects, - * however to avoid the horrible mess in include/linux/mm_types.h, we'll - * just define our own struct page type variant here. - */ -struct slob_page { - union { - struct { - unsigned long flags; /* mandatory */ - atomic_t _count; /* mandatory */ - slobidx_t units; /* free units left in page */ - unsigned long pad[2]; - slob_t *free; /* first free slob_t in page */ - struct list_head list; /* linked list of free pages */ - }; - struct page page; - }; -}; -static inline void struct_slob_page_wrong_size(void) -{ BUILD_BUG_ON(sizeof(struct slob_page) != sizeof(struct page)); } - -/* - * free_slob_page: call before a slob_page is returned to the page allocator. - */ -static inline void free_slob_page(struct slob_page *sp) -{ - reset_page_mapcount(&sp->page); - sp->page.mapping = NULL; -} - -/* * All partially free slob pages go on these lists. */ #define SLOB_BREAK1 256 @@ -131,46 +103,23 @@ static LIST_HEAD(free_slob_medium); static LIST_HEAD(free_slob_large); /* - * is_slob_page: True for all slob pages (false for bigblock pages) - */ -static inline int is_slob_page(struct slob_page *sp) -{ - return PageSlab((struct page *)sp); -} - -static inline void set_slob_page(struct slob_page *sp) -{ - __SetPageSlab((struct page *)sp); -} - -static inline void clear_slob_page(struct slob_page *sp) -{ - __ClearPageSlab((struct page *)sp); -} - -static inline struct slob_page *slob_page(const void *addr) -{ - return (struct slob_page *)virt_to_page(addr); -} - -/* * slob_page_free: true for pages on free_slob_pages list. */ -static inline int slob_page_free(struct slob_page *sp) +static inline int slob_page_free(struct page *sp) { - return PageSlobFree((struct page *)sp); + return PageSlobFree(sp); } -static void set_slob_page_free(struct slob_page *sp, struct list_head *list) +static void set_slob_page_free(struct page *sp, struct list_head *list) { list_add(&sp->list, list); - __SetPageSlobFree((struct page *)sp); + __SetPageSlobFree(sp); } -static inline void clear_slob_page_free(struct slob_page *sp) +static inline void clear_slob_page_free(struct page *sp) { list_del(&sp->list); - __ClearPageSlobFree((struct page *)sp); + __ClearPageSlobFree(sp); } #define SLOB_UNIT sizeof(slob_t) @@ -267,12 +216,12 @@ static void slob_free_pages(void *b, int order) /* * Allocate a slob block within a given slob_page sp. */ -static void *slob_page_alloc(struct slob_page *sp, size_t size, int align) +static void *slob_page_alloc(struct page *sp, size_t size, int align) { slob_t *prev, *cur, *aligned = NULL; int delta = 0, units = SLOB_UNITS(size); - for (prev = NULL, cur = sp->free; ; prev = cur, cur = slob_next(cur)) { + for (prev = NULL, cur = sp->freelist; ; prev = cur, cur = slob_next(cur)) { slobidx_t avail = slob_units(cur); if (align) { @@ -296,12 +245,12 @@ static void *slob_page_alloc(struct slob_page *sp, size_t size, int align) if (prev) set_slob(prev, slob_units(prev), next); else - sp->free = next; + sp->freelist = next; } else { /* fragment */ if (prev) set_slob(prev, slob_units(prev), cur + units); else - sp->free = cur + units; + sp->freelist = cur + units; set_slob(cur + units, avail - units, next); } @@ -320,7 +269,7 @@ static void *slob_page_alloc(struct slob_page *sp, size_t size, int align) */ static void *slob_alloc(size_t size, gfp_t gfp, int align, int node) { - struct slob_page *sp; + struct page *sp; struct list_head *prev; struct list_head *slob_list; slob_t *b = NULL; @@ -341,7 +290,7 @@ static void *slob_alloc(size_t size, gfp_t gfp, int align, int node) * If there's a node specification, search for a partial * page with a matching node id in the freelist. */ - if (node != -1 && page_to_nid(&sp->page) != node) + if (node != -1 && page_to_nid(sp) != node) continue; #endif /* Enough room on this page? */ @@ -369,12 +318,12 @@ static void *slob_alloc(size_t size, gfp_t gfp, int align, int node) b = slob_new_pages(gfp & ~__GFP_ZERO, 0, node); if (!b) return NULL; - sp = slob_page(b); - set_slob_page(sp); + sp = virt_to_page(b); + __SetPageSlab(sp); spin_lock_irqsave(&slob_lock, flags); sp->units = SLOB_UNITS(PAGE_SIZE); - sp->free = b; + sp->freelist = b; INIT_LIST_HEAD(&sp->list); set_slob(b, SLOB_UNITS(PAGE_SIZE), b + SLOB_UNITS(PAGE_SIZE)); set_slob_page_free(sp, slob_list); @@ -392,7 +341,7 @@ static void *slob_alloc(size_t size, gfp_t gfp, int align, int node) */ static void slob_free(void *block, int size) { - struct slob_page *sp; + struct page *sp; slob_t *prev, *next, *b = (slob_t *)block; slobidx_t units; unsigned long flags; @@ -402,7 +351,7 @@ static void slob_free(void *block, int size) return; BUG_ON(!size); - sp = slob_page(block); + sp = virt_to_page(block); units = SLOB_UNITS(size); spin_lock_irqsave(&slob_lock, flags); @@ -412,8 +361,8 @@ static void slob_free(void *block, int size) if (slob_page_free(sp)) clear_slob_page_free(sp); spin_unlock_irqrestore(&slob_lock, flags); - clear_slob_page(sp); - free_slob_page(sp); + __ClearPageSlab(sp); + reset_page_mapcount(sp); slob_free_pages(b, 0); return; } @@ -421,7 +370,7 @@ static void slob_free(void *block, int size) if (!slob_page_free(sp)) { /* This slob page is about to become partially free. Easy! */ sp->units = units; - sp->free = b; + sp->freelist = b; set_slob(b, units, (void *)((unsigned long)(b + SLOB_UNITS(PAGE_SIZE)) & PAGE_MASK)); @@ -441,15 +390,15 @@ static void slob_free(void *block, int size) */ sp->units += units; - if (b < sp->free) { - if (b + units == sp->free) { - units += slob_units(sp->free); - sp->free = slob_next(sp->free); + if (b < (slob_t *)sp->freelist) { + if (b + units == sp->freelist) { + units += slob_units(sp->freelist); + sp->freelist = slob_next(sp->freelist); } - set_slob(b, units, sp->free); - sp->free = b; + set_slob(b, units, sp->freelist); + sp->freelist = b; } else { - prev = sp->free; + prev = sp->freelist; next = slob_next(prev); while (b > next) { prev = next; @@ -522,7 +471,7 @@ EXPORT_SYMBOL(__kmalloc_node); void kfree(const void *block) { - struct slob_page *sp; + struct page *sp; trace_kfree(_RET_IP_, block); @@ -530,43 +479,36 @@ void kfree(const void *block) return; kmemleak_free(block); - sp = slob_page(block); - if (is_slob_page(sp)) { + sp = virt_to_page(block); + if (PageSlab(sp)) { int align = max(ARCH_KMALLOC_MINALIGN, ARCH_SLAB_MINALIGN); unsigned int *m = (unsigned int *)(block - align); slob_free(m, *m + align); } else - put_page(&sp->page); + put_page(sp); } EXPORT_SYMBOL(kfree); /* can't use ksize for kmem_cache_alloc memory, only kmalloc */ size_t ksize(const void *block) { - struct slob_page *sp; + struct page *sp; BUG_ON(!block); if (unlikely(block == ZERO_SIZE_PTR)) return 0; - sp = slob_page(block); - if (is_slob_page(sp)) { + sp = virt_to_page(block); + if (PageSlab(sp)) { int align = max(ARCH_KMALLOC_MINALIGN, ARCH_SLAB_MINALIGN); unsigned int *m = (unsigned int *)(block - align); return SLOB_UNITS(*m) * SLOB_UNIT; } else - return sp->page.private; + return sp->private; } EXPORT_SYMBOL(ksize); -struct kmem_cache { - unsigned int size, align; - unsigned long flags; - const char *name; - void (*ctor)(void *); -}; - -struct kmem_cache *kmem_cache_create(const char *name, size_t size, +struct kmem_cache *__kmem_cache_create(const char *name, size_t size, size_t align, unsigned long flags, void (*ctor)(void *)) { struct kmem_cache *c; @@ -589,13 +531,12 @@ struct kmem_cache *kmem_cache_create(const char *name, size_t size, c->align = ARCH_SLAB_MINALIGN; if (c->align < align) c->align = align; - } else if (flags & SLAB_PANIC) - panic("Cannot create slab cache %s\n", name); - kmemleak_alloc(c, sizeof(struct kmem_cache), 1, GFP_KERNEL); + kmemleak_alloc(c, sizeof(struct kmem_cache), 1, GFP_KERNEL); + c->refcount = 1; + } return c; } -EXPORT_SYMBOL(kmem_cache_create); void kmem_cache_destroy(struct kmem_cache *c) { @@ -678,19 +619,12 @@ int kmem_cache_shrink(struct kmem_cache *d) } EXPORT_SYMBOL(kmem_cache_shrink); -static unsigned int slob_ready __read_mostly; - -int slab_is_available(void) -{ - return slob_ready; -} - void __init kmem_cache_init(void) { - slob_ready = 1; + slab_state = UP; } void __init kmem_cache_init_late(void) { - /* Nothing to do */ + slab_state = FULL; } @@ -16,6 +16,7 @@ #include <linux/interrupt.h> #include <linux/bitops.h> #include <linux/slab.h> +#include "slab.h" #include <linux/proc_fs.h> #include <linux/seq_file.h> #include <linux/kmemcheck.h> @@ -33,15 +34,17 @@ #include <trace/events/kmem.h> +#include "internal.h" + /* * Lock order: - * 1. slub_lock (Global Semaphore) + * 1. slab_mutex (Global Mutex) * 2. node->list_lock * 3. slab_lock(page) (Only on some arches and for debugging) * - * slub_lock + * slab_mutex * - * The role of the slub_lock is to protect the list of all the slabs + * The role of the slab_mutex 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 @@ -182,17 +185,6 @@ static int kmem_size = sizeof(struct kmem_cache); static struct notifier_block slab_notifier; #endif -static enum { - DOWN, /* No slab functionality available */ - PARTIAL, /* Kmem_cache_node works */ - UP, /* Everything works but does not show up in sysfs */ - SYSFS /* Sysfs up */ -} slab_state = DOWN; - -/* A list of all slab caches on the system */ -static DECLARE_RWSEM(slub_lock); -static LIST_HEAD(slab_caches); - /* * Tracking user of a slab. */ @@ -237,11 +229,6 @@ static inline void stat(const struct kmem_cache *s, enum stat_item si) * Core slab cache functions *******************************************************************/ -int slab_is_available(void) -{ - return slab_state >= UP; -} - static inline struct kmem_cache_node *get_node(struct kmem_cache *s, int node) { return s->node[node]; @@ -311,7 +298,7 @@ static inline size_t slab_ksize(const struct kmem_cache *s) * and whatever may come after it. */ if (s->flags & (SLAB_RED_ZONE | SLAB_POISON)) - return s->objsize; + return s->object_size; #endif /* @@ -609,11 +596,11 @@ static void print_trailer(struct kmem_cache *s, struct page *page, u8 *p) if (p > addr + 16) print_section("Bytes b4 ", p - 16, 16); - print_section("Object ", p, min_t(unsigned long, s->objsize, + print_section("Object ", p, min_t(unsigned long, s->object_size, PAGE_SIZE)); if (s->flags & SLAB_RED_ZONE) - print_section("Redzone ", p + s->objsize, - s->inuse - s->objsize); + print_section("Redzone ", p + s->object_size, + s->inuse - s->object_size); if (s->offset) off = s->offset + sizeof(void *); @@ -655,12 +642,12 @@ static void init_object(struct kmem_cache *s, void *object, u8 val) u8 *p = object; if (s->flags & __OBJECT_POISON) { - memset(p, POISON_FREE, s->objsize - 1); - p[s->objsize - 1] = POISON_END; + memset(p, POISON_FREE, s->object_size - 1); + p[s->object_size - 1] = POISON_END; } if (s->flags & SLAB_RED_ZONE) - memset(p + s->objsize, val, s->inuse - s->objsize); + memset(p + s->object_size, val, s->inuse - s->object_size); } static void restore_bytes(struct kmem_cache *s, char *message, u8 data, @@ -705,10 +692,10 @@ static int check_bytes_and_report(struct kmem_cache *s, struct page *page, * Poisoning uses 0x6b (POISON_FREE) and the last byte is * 0xa5 (POISON_END) * - * object + s->objsize + * object + s->object_size * Padding to reach word boundary. This is also used for Redzoning. * Padding is extended by another word if Redzoning is enabled and - * objsize == inuse. + * object_size == inuse. * * We fill with 0xbb (RED_INACTIVE) for inactive objects and with * 0xcc (RED_ACTIVE) for objects in use. @@ -727,7 +714,7 @@ static int check_bytes_and_report(struct kmem_cache *s, struct page *page, * object + s->size * Nothing is used beyond s->size. * - * If slabcaches are merged then the objsize and inuse boundaries are mostly + * If slabcaches are merged then the object_size and inuse boundaries are mostly * ignored. And therefore no slab options that rely on these boundaries * may be used with merged slabcaches. */ @@ -787,25 +774,25 @@ static int check_object(struct kmem_cache *s, struct page *page, void *object, u8 val) { u8 *p = object; - u8 *endobject = object + s->objsize; + u8 *endobject = object + s->object_size; if (s->flags & SLAB_RED_ZONE) { if (!check_bytes_and_report(s, page, object, "Redzone", - endobject, val, s->inuse - s->objsize)) + endobject, val, s->inuse - s->object_size)) return 0; } else { - if ((s->flags & SLAB_POISON) && s->objsize < s->inuse) { + if ((s->flags & SLAB_POISON) && s->object_size < s->inuse) { check_bytes_and_report(s, page, p, "Alignment padding", - endobject, POISON_INUSE, s->inuse - s->objsize); + endobject, POISON_INUSE, s->inuse - s->object_size); } } if (s->flags & SLAB_POISON) { if (val != SLUB_RED_ACTIVE && (s->flags & __OBJECT_POISON) && (!check_bytes_and_report(s, page, p, "Poison", p, - POISON_FREE, s->objsize - 1) || + POISON_FREE, s->object_size - 1) || !check_bytes_and_report(s, page, p, "Poison", - p + s->objsize - 1, POISON_END, 1))) + p + s->object_size - 1, POISON_END, 1))) return 0; /* * check_pad_bytes cleans up on its own. @@ -926,7 +913,7 @@ 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->object_size); dump_stack(); } @@ -942,14 +929,14 @@ static inline int slab_pre_alloc_hook(struct kmem_cache *s, gfp_t flags) lockdep_trace_alloc(flags); might_sleep_if(flags & __GFP_WAIT); - return should_failslab(s->objsize, flags, s->flags); + return should_failslab(s->object_size, flags, s->flags); } static inline void slab_post_alloc_hook(struct kmem_cache *s, gfp_t flags, void *object) { flags &= gfp_allowed_mask; kmemcheck_slab_alloc(s, flags, object, slab_ksize(s)); - kmemleak_alloc_recursive(object, s->objsize, 1, s->flags, flags); + kmemleak_alloc_recursive(object, s->object_size, 1, s->flags, flags); } static inline void slab_free_hook(struct kmem_cache *s, void *x) @@ -966,13 +953,13 @@ static inline void slab_free_hook(struct kmem_cache *s, void *x) unsigned long flags; local_irq_save(flags); - kmemcheck_slab_free(s, x, s->objsize); - debug_check_no_locks_freed(x, s->objsize); + kmemcheck_slab_free(s, x, s->object_size); + debug_check_no_locks_freed(x, s->object_size); local_irq_restore(flags); } #endif if (!(s->flags & SLAB_DEBUG_OBJECTS)) - debug_check_no_obj_freed(x, s->objsize); + debug_check_no_obj_freed(x, s->object_size); } /* @@ -1207,7 +1194,7 @@ out: __setup("slub_debug", setup_slub_debug); -static unsigned long kmem_cache_flags(unsigned long objsize, +static unsigned long kmem_cache_flags(unsigned long object_size, unsigned long flags, const char *name, void (*ctor)(void *)) { @@ -1237,7 +1224,7 @@ static inline int check_object(struct kmem_cache *s, 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, +static inline unsigned long kmem_cache_flags(unsigned long object_size, unsigned long flags, const char *name, void (*ctor)(void *)) { @@ -1314,13 +1301,7 @@ static struct page *allocate_slab(struct kmem_cache *s, gfp_t flags, int node) stat(s, ORDER_FALLBACK); } - if (flags & __GFP_WAIT) - local_irq_disable(); - - if (!page) - return NULL; - - if (kmemcheck_enabled + if (kmemcheck_enabled && page && !(s->flags & (SLAB_NOTRACK | DEBUG_DEFAULT_FLAGS))) { int pages = 1 << oo_order(oo); @@ -1336,6 +1317,11 @@ static struct page *allocate_slab(struct kmem_cache *s, gfp_t flags, int node) kmemcheck_mark_unallocated_pages(page, pages); } + if (flags & __GFP_WAIT) + local_irq_disable(); + if (!page) + return NULL; + page->objects = oo_objects(oo); mod_zone_page_state(page_zone(page), (s->flags & SLAB_RECLAIM_ACCOUNT) ? @@ -1370,6 +1356,8 @@ static struct page *new_slab(struct kmem_cache *s, gfp_t flags, int node) inc_slabs_node(s, page_to_nid(page), page->objects); page->slab = s; __SetPageSlab(page); + if (page->pfmemalloc) + SetPageSlabPfmemalloc(page); start = page_address(page); @@ -1413,6 +1401,7 @@ static void __free_slab(struct kmem_cache *s, struct page *page) NR_SLAB_RECLAIMABLE : NR_SLAB_UNRECLAIMABLE, -pages); + __ClearPageSlabPfmemalloc(page); __ClearPageSlab(page); reset_page_mapcount(page); if (current->reclaim_state) @@ -1490,12 +1479,12 @@ static inline void remove_partial(struct kmem_cache_node *n, } /* - * Lock slab, remove from the partial list and put the object into the - * per cpu freelist. + * Remove slab from the partial list, freeze it and + * return the pointer to the freelist. * * Returns a list of objects or NULL if it fails. * - * Must hold list_lock. + * Must hold list_lock since we modify the partial list. */ static inline void *acquire_slab(struct kmem_cache *s, struct kmem_cache_node *n, struct page *page, @@ -1510,26 +1499,27 @@ static inline void *acquire_slab(struct kmem_cache *s, * 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; - new.freelist = NULL; - } else { - new.freelist = freelist; - } + freelist = page->freelist; + counters = page->counters; + new.counters = counters; + if (mode) { + new.inuse = page->objects; + new.freelist = NULL; + } else { + new.freelist = freelist; + } - VM_BUG_ON(new.frozen); - new.frozen = 1; + VM_BUG_ON(new.frozen); + new.frozen = 1; - } while (!__cmpxchg_double_slab(s, page, + if (!__cmpxchg_double_slab(s, page, freelist, counters, new.freelist, new.counters, - "lock and freeze")); + "acquire_slab")) + return NULL; remove_partial(n, page); + WARN_ON(!freelist); return freelist; } @@ -1563,7 +1553,6 @@ static void *get_partial_node(struct kmem_cache *s, if (!object) { c->page = page; - c->node = page_to_nid(page); stat(s, ALLOC_FROM_PARTIAL); object = t; available = page->objects - page->inuse; @@ -1617,7 +1606,7 @@ static void *get_any_partial(struct kmem_cache *s, gfp_t flags, do { cpuset_mems_cookie = get_mems_allowed(); - zonelist = node_zonelist(slab_node(current->mempolicy), flags); + zonelist = node_zonelist(slab_node(), flags); for_each_zone_zonelist(zone, z, zonelist, high_zoneidx) { struct kmem_cache_node *n; @@ -1731,14 +1720,12 @@ void init_kmem_cache_cpus(struct kmem_cache *s) /* * Remove the cpu slab */ -static void deactivate_slab(struct kmem_cache *s, struct kmem_cache_cpu *c) +static void deactivate_slab(struct kmem_cache *s, struct page *page, void *freelist) { enum slab_modes { M_NONE, M_PARTIAL, M_FULL, M_FREE }; - struct page *page = c->page; 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; @@ -1749,11 +1736,6 @@ static void deactivate_slab(struct kmem_cache *s, struct kmem_cache_cpu *c) 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 @@ -1879,21 +1861,31 @@ redo: } } -/* Unfreeze all the cpu partial slabs */ +/* + * Unfreeze all the cpu partial slabs. + * + * This function must be called with interrupt disabled. + */ static void unfreeze_partials(struct kmem_cache *s) { - struct kmem_cache_node *n = NULL; + struct kmem_cache_node *n = NULL, *n2 = NULL; struct kmem_cache_cpu *c = this_cpu_ptr(s->cpu_slab); struct page *page, *discard_page = NULL; 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; + + n2 = get_node(s, page_to_nid(page)); + if (n != n2) { + if (n) + spin_unlock(&n->list_lock); + + n = n2; + spin_lock(&n->list_lock); + } do { @@ -1906,43 +1898,17 @@ static void unfreeze_partials(struct kmem_cache *s) 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); - stat(s, FREE_REMOVE_PARTIAL); - } else { - add_partial(n, page, - DEACTIVATE_TO_TAIL); - stat(s, FREE_ADD_PARTIAL); - } - - l = m; - } - - } while (!cmpxchg_double_slab(s, page, + } while (!__cmpxchg_double_slab(s, page, old.freelist, old.counters, new.freelist, new.counters, "unfreezing slab")); - if (m == M_FREE) { + if (unlikely(!new.inuse && n->nr_partial > s->min_partial)) { page->next = discard_page; discard_page = page; + } else { + add_partial(n, page, DEACTIVATE_TO_TAIL); + stat(s, FREE_ADD_PARTIAL); } } @@ -2011,7 +1977,11 @@ int put_cpu_partial(struct kmem_cache *s, struct page *page, int drain) static inline void flush_slab(struct kmem_cache *s, struct kmem_cache_cpu *c) { stat(s, CPUSLAB_FLUSH); - deactivate_slab(s, c); + deactivate_slab(s, c->page, c->freelist); + + c->tid = next_tid(c->tid); + c->page = NULL; + c->freelist = NULL; } /* @@ -2055,10 +2025,10 @@ static void flush_all(struct kmem_cache *s) * Check if the objects in a per cpu structure fit numa * locality expectations. */ -static inline int node_match(struct kmem_cache_cpu *c, int node) +static inline int node_match(struct page *page, int node) { #ifdef CONFIG_NUMA - if (node != NUMA_NO_NODE && c->node != node) + if (node != NUMA_NO_NODE && page_to_nid(page) != node) return 0; #endif return 1; @@ -2101,10 +2071,10 @@ slab_out_of_memory(struct kmem_cache *s, gfp_t gfpflags, int nid) "SLUB: Unable to allocate memory on node %d (gfp=0x%x)\n", nid, gfpflags); printk(KERN_WARNING " cache: %s, object size: %d, buffer size: %d, " - "default order: %d, min order: %d\n", s->name, s->objsize, + "default order: %d, min order: %d\n", s->name, s->object_size, s->size, oo_order(s->oo), oo_order(s->min)); - if (oo_order(s->min) > get_order(s->objsize)) + if (oo_order(s->min) > get_order(s->object_size)) printk(KERN_WARNING " %s debugging increased min order, use " "slub_debug=O to disable.\n", s->name); @@ -2130,10 +2100,16 @@ 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); + void *freelist; + struct kmem_cache_cpu *c = *pc; + struct page *page; + freelist = get_partial(s, flags, node, c); + + if (freelist) + return freelist; + + page = new_slab(s, flags, node); if (page) { c = __this_cpu_ptr(s->cpu_slab); if (c->page) @@ -2143,17 +2119,24 @@ static inline void *new_slab_objects(struct kmem_cache *s, gfp_t flags, * No other reference to the page yet so we can * muck around with it freely without cmpxchg */ - object = page->freelist; + freelist = page->freelist; page->freelist = NULL; stat(s, ALLOC_SLAB); - c->node = page_to_nid(page); c->page = page; *pc = c; } else - object = NULL; + freelist = NULL; - return object; + return freelist; +} + +static inline bool pfmemalloc_match(struct page *page, gfp_t gfpflags) +{ + if (unlikely(PageSlabPfmemalloc(page))) + return gfp_pfmemalloc_allowed(gfpflags); + + return true; } /* @@ -2163,6 +2146,8 @@ static inline void *new_slab_objects(struct kmem_cache *s, gfp_t flags, * The page is still frozen if the return value is not NULL. * * If this function returns NULL then the page has been unfrozen. + * + * This function must be called with interrupt disabled. */ static inline void *get_freelist(struct kmem_cache *s, struct page *page) { @@ -2173,13 +2158,14 @@ static inline void *get_freelist(struct kmem_cache *s, struct page *page) do { freelist = page->freelist; counters = page->counters; + new.counters = counters; VM_BUG_ON(!new.frozen); new.inuse = page->objects; new.frozen = freelist != NULL; - } while (!cmpxchg_double_slab(s, page, + } while (!__cmpxchg_double_slab(s, page, freelist, counters, NULL, new.counters, "get_freelist")); @@ -2206,7 +2192,8 @@ static inline void *get_freelist(struct kmem_cache *s, struct page *page) static void *__slab_alloc(struct kmem_cache *s, gfp_t gfpflags, int node, unsigned long addr, struct kmem_cache_cpu *c) { - void **object; + void *freelist; + struct page *page; unsigned long flags; local_irq_save(flags); @@ -2219,25 +2206,41 @@ static void *__slab_alloc(struct kmem_cache *s, gfp_t gfpflags, int node, c = this_cpu_ptr(s->cpu_slab); #endif - if (!c->page) + page = c->page; + if (!page) goto new_slab; redo: - if (unlikely(!node_match(c, node))) { + + if (unlikely(!node_match(page, node))) { stat(s, ALLOC_NODE_MISMATCH); - deactivate_slab(s, c); + deactivate_slab(s, page, c->freelist); + c->page = NULL; + c->freelist = NULL; + goto new_slab; + } + + /* + * By rights, we should be searching for a slab page that was + * PFMEMALLOC but right now, we are losing the pfmemalloc + * information when the page leaves the per-cpu allocator + */ + if (unlikely(!pfmemalloc_match(page, gfpflags))) { + deactivate_slab(s, page, c->freelist); + c->page = NULL; + c->freelist = NULL; goto new_slab; } /* must check again c->freelist in case of cpu migration or IRQ */ - object = c->freelist; - if (object) + freelist = c->freelist; + if (freelist) goto load_freelist; stat(s, ALLOC_SLOWPATH); - object = get_freelist(s, c->page); + freelist = get_freelist(s, page); - if (!object) { + if (!freelist) { c->page = NULL; stat(s, DEACTIVATE_BYPASS); goto new_slab; @@ -2246,50 +2249,50 @@ redo: stat(s, ALLOC_REFILL); load_freelist: - c->freelist = get_freepointer(s, object); + /* + * freelist is pointing to the list of objects to be used. + * page is pointing to the page from which the objects are obtained. + * That page must be frozen for per cpu allocations to work. + */ + VM_BUG_ON(!c->page->frozen); + c->freelist = get_freepointer(s, freelist); c->tid = next_tid(c->tid); local_irq_restore(flags); - return object; + return freelist; new_slab: if (c->partial) { - c->page = c->partial; - c->partial = c->page->next; - c->node = page_to_nid(c->page); + page = c->page = c->partial; + c->partial = page->next; stat(s, CPU_PARTIAL_ALLOC); c->freelist = NULL; goto redo; } - /* Then do expensive stuff like retrieving pages from the partial lists */ - object = get_partial(s, gfpflags, node, c); - - if (unlikely(!object)) { + freelist = new_slab_objects(s, gfpflags, node, &c); - object = new_slab_objects(s, gfpflags, node, &c); + if (unlikely(!freelist)) { + if (!(gfpflags & __GFP_NOWARN) && printk_ratelimit()) + slab_out_of_memory(s, gfpflags, node); - if (unlikely(!object)) { - if (!(gfpflags & __GFP_NOWARN) && printk_ratelimit()) - slab_out_of_memory(s, gfpflags, node); - - local_irq_restore(flags); - return NULL; - } + local_irq_restore(flags); + return NULL; } - if (likely(!kmem_cache_debug(s))) + page = c->page; + if (likely(!kmem_cache_debug(s) && pfmemalloc_match(page, gfpflags))) goto load_freelist; /* Only entered in the debug case */ - if (!alloc_debug_processing(s, c->page, object, addr)) + if (kmem_cache_debug(s) && !alloc_debug_processing(s, page, freelist, addr)) goto new_slab; /* Slab failed checks. Next slab needed */ - c->freelist = get_freepointer(s, object); - deactivate_slab(s, c); - c->node = NUMA_NO_NODE; + deactivate_slab(s, page, get_freepointer(s, freelist)); + c->page = NULL; + c->freelist = NULL; local_irq_restore(flags); - return object; + return freelist; } /* @@ -2307,6 +2310,7 @@ static __always_inline void *slab_alloc(struct kmem_cache *s, { void **object; struct kmem_cache_cpu *c; + struct page *page; unsigned long tid; if (slab_pre_alloc_hook(s, gfpflags)) @@ -2332,8 +2336,8 @@ redo: barrier(); object = c->freelist; - if (unlikely(!object || !node_match(c, node))) - + page = c->page; + if (unlikely(!object || !node_match(page, node))) object = __slab_alloc(s, gfpflags, node, addr, c); else { @@ -2364,7 +2368,7 @@ redo: } if (unlikely(gfpflags & __GFP_ZERO) && object) - memset(object, 0, s->objsize); + memset(object, 0, s->object_size); slab_post_alloc_hook(s, gfpflags, object); @@ -2375,7 +2379,7 @@ void *kmem_cache_alloc(struct kmem_cache *s, gfp_t gfpflags) { void *ret = slab_alloc(s, gfpflags, NUMA_NO_NODE, _RET_IP_); - trace_kmem_cache_alloc(_RET_IP_, ret, s->objsize, s->size, gfpflags); + trace_kmem_cache_alloc(_RET_IP_, ret, s->object_size, s->size, gfpflags); return ret; } @@ -2405,7 +2409,7 @@ void *kmem_cache_alloc_node(struct kmem_cache *s, gfp_t gfpflags, int node) void *ret = slab_alloc(s, gfpflags, node, _RET_IP_); trace_kmem_cache_alloc_node(_RET_IP_, ret, - s->objsize, s->size, gfpflags, node); + s->object_size, s->size, gfpflags, node); return ret; } @@ -2900,7 +2904,7 @@ static void set_min_partial(struct kmem_cache *s, unsigned long min) static int calculate_sizes(struct kmem_cache *s, int forced_order) { unsigned long flags = s->flags; - unsigned long size = s->objsize; + unsigned long size = s->object_size; unsigned long align = s->align; int order; @@ -2929,7 +2933,7 @@ static int calculate_sizes(struct kmem_cache *s, int forced_order) * end of the object and the free pointer. If not then add an * additional word to have some bytes to store Redzone information. */ - if ((flags & SLAB_RED_ZONE) && size == s->objsize) + if ((flags & SLAB_RED_ZONE) && size == s->object_size) size += sizeof(void *); #endif @@ -2977,7 +2981,7 @@ static int calculate_sizes(struct kmem_cache *s, int forced_order) * user specified and the dynamic determination of cache line size * on bootup. */ - align = calculate_alignment(flags, align, s->objsize); + align = calculate_alignment(flags, align, s->object_size); s->align = align; /* @@ -3025,7 +3029,7 @@ static int kmem_cache_open(struct kmem_cache *s, memset(s, 0, kmem_size); s->name = name; s->ctor = ctor; - s->objsize = size; + s->object_size = size; s->align = align; s->flags = kmem_cache_flags(size, flags, name, ctor); s->reserved = 0; @@ -3040,7 +3044,7 @@ static int kmem_cache_open(struct kmem_cache *s, * Disable debugging flags that store metadata if the min slab * order increased. */ - if (get_order(s->size) > get_order(s->objsize)) { + if (get_order(s->size) > get_order(s->object_size)) { s->flags &= ~DEBUG_METADATA_FLAGS; s->offset = 0; if (!calculate_sizes(s, -1)) @@ -3114,7 +3118,7 @@ error: */ unsigned int kmem_cache_size(struct kmem_cache *s) { - return s->objsize; + return s->object_size; } EXPORT_SYMBOL(kmem_cache_size); @@ -3192,11 +3196,11 @@ static inline int kmem_cache_close(struct kmem_cache *s) */ void kmem_cache_destroy(struct kmem_cache *s) { - down_write(&slub_lock); + mutex_lock(&slab_mutex); s->refcount--; if (!s->refcount) { list_del(&s->list); - up_write(&slub_lock); + mutex_unlock(&slab_mutex); if (kmem_cache_close(s)) { printk(KERN_ERR "SLUB %s: %s called for cache that " "still has objects.\n", s->name, __func__); @@ -3206,7 +3210,7 @@ void kmem_cache_destroy(struct kmem_cache *s) rcu_barrier(); sysfs_slab_remove(s); } else - up_write(&slub_lock); + mutex_unlock(&slab_mutex); } EXPORT_SYMBOL(kmem_cache_destroy); @@ -3268,7 +3272,7 @@ static struct kmem_cache *__init create_kmalloc_cache(const char *name, /* * This function is called with IRQs disabled during early-boot on - * single CPU so there's no need to take slub_lock here. + * single CPU so there's no need to take slab_mutex here. */ if (!kmem_cache_open(s, name, size, ARCH_KMALLOC_MINALIGN, flags, NULL)) @@ -3553,10 +3557,10 @@ static int slab_mem_going_offline_callback(void *arg) { struct kmem_cache *s; - down_read(&slub_lock); + mutex_lock(&slab_mutex); list_for_each_entry(s, &slab_caches, list) kmem_cache_shrink(s); - up_read(&slub_lock); + mutex_unlock(&slab_mutex); return 0; } @@ -3577,7 +3581,7 @@ static void slab_mem_offline_callback(void *arg) if (offline_node < 0) return; - down_read(&slub_lock); + mutex_lock(&slab_mutex); list_for_each_entry(s, &slab_caches, list) { n = get_node(s, offline_node); if (n) { @@ -3593,7 +3597,7 @@ static void slab_mem_offline_callback(void *arg) kmem_cache_free(kmem_cache_node, n); } } - up_read(&slub_lock); + mutex_unlock(&slab_mutex); } static int slab_mem_going_online_callback(void *arg) @@ -3616,7 +3620,7 @@ static int slab_mem_going_online_callback(void *arg) * allocate a kmem_cache_node structure in order to bring the node * online. */ - down_read(&slub_lock); + mutex_lock(&slab_mutex); list_for_each_entry(s, &slab_caches, list) { /* * XXX: kmem_cache_alloc_node will fallback to other nodes @@ -3632,7 +3636,7 @@ static int slab_mem_going_online_callback(void *arg) s->node[nid] = n; } out: - up_read(&slub_lock); + mutex_unlock(&slab_mutex); return ret; } @@ -3843,11 +3847,11 @@ void __init kmem_cache_init(void) if (s && s->size) { char *name = kasprintf(GFP_NOWAIT, - "dma-kmalloc-%d", s->objsize); + "dma-kmalloc-%d", s->object_size); BUG_ON(!name); kmalloc_dma_caches[i] = create_kmalloc_cache(name, - s->objsize, SLAB_CACHE_DMA); + s->object_size, SLAB_CACHE_DMA); } } #endif @@ -3924,16 +3928,12 @@ static struct kmem_cache *find_mergeable(size_t size, return NULL; } -struct kmem_cache *kmem_cache_create(const char *name, size_t size, +struct kmem_cache *__kmem_cache_create(const char *name, size_t size, size_t align, unsigned long flags, void (*ctor)(void *)) { struct kmem_cache *s; char *n; - if (WARN_ON(!name)) - return NULL; - - down_write(&slub_lock); s = find_mergeable(size, align, flags, name, ctor); if (s) { s->refcount++; @@ -3941,49 +3941,42 @@ struct kmem_cache *kmem_cache_create(const char *name, size_t size, * Adjust the object sizes so that we clear * the complete object on kzalloc. */ - s->objsize = max(s->objsize, (int)size); + s->object_size = max(s->object_size, (int)size); s->inuse = max_t(int, s->inuse, ALIGN(size, sizeof(void *))); if (sysfs_slab_alias(s, name)) { s->refcount--; - goto err; + return NULL; } - up_write(&slub_lock); return s; } n = kstrdup(name, GFP_KERNEL); if (!n) - goto err; + return NULL; s = kmalloc(kmem_size, GFP_KERNEL); if (s) { if (kmem_cache_open(s, n, size, align, flags, ctor)) { + int r; + list_add(&s->list, &slab_caches); - up_write(&slub_lock); - if (sysfs_slab_add(s)) { - down_write(&slub_lock); - list_del(&s->list); - kfree(n); - kfree(s); - goto err; - } - return s; + mutex_unlock(&slab_mutex); + r = sysfs_slab_add(s); + mutex_lock(&slab_mutex); + + if (!r) + return s; + + list_del(&s->list); + kmem_cache_close(s); } kfree(s); } kfree(n); -err: - up_write(&slub_lock); - - if (flags & SLAB_PANIC) - panic("Cannot create slabcache %s\n", name); - else - s = NULL; - return s; + return NULL; } -EXPORT_SYMBOL(kmem_cache_create); #ifdef CONFIG_SMP /* @@ -4002,13 +3995,13 @@ static int __cpuinit slab_cpuup_callback(struct notifier_block *nfb, case CPU_UP_CANCELED_FROZEN: case CPU_DEAD: case CPU_DEAD_FROZEN: - down_read(&slub_lock); + mutex_lock(&slab_mutex); list_for_each_entry(s, &slab_caches, list) { local_irq_save(flags); __flush_cpu_slab(s, cpu); local_irq_restore(flags); } - up_read(&slub_lock); + mutex_unlock(&slab_mutex); break; default: break; @@ -4500,30 +4493,31 @@ 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); - int node = ACCESS_ONCE(c->node); + int node; struct page *page; - if (node < 0) - continue; page = ACCESS_ONCE(c->page); - if (page) { - if (flags & SO_TOTAL) - x = page->objects; - else if (flags & SO_OBJECTS) - x = page->inuse; - else - x = 1; + if (!page) + continue; - total += x; - nodes[node] += x; - } - page = c->partial; + node = page_to_nid(page); + if (flags & SO_TOTAL) + x = page->objects; + else if (flags & SO_OBJECTS) + x = page->inuse; + else + x = 1; + total += x; + nodes[node] += x; + + page = ACCESS_ONCE(c->partial); if (page) { x = page->pobjects; total += x; nodes[node] += x; } + per_cpu[node]++; } } @@ -4623,7 +4617,7 @@ SLAB_ATTR_RO(align); static ssize_t object_size_show(struct kmem_cache *s, char *buf) { - return sprintf(buf, "%d\n", s->objsize); + return sprintf(buf, "%d\n", s->object_size); } SLAB_ATTR_RO(object_size); @@ -5286,7 +5280,7 @@ static int sysfs_slab_add(struct kmem_cache *s) const char *name; int unmergeable; - if (slab_state < SYSFS) + if (slab_state < FULL) /* Defer until later */ return 0; @@ -5331,7 +5325,7 @@ static int sysfs_slab_add(struct kmem_cache *s) static void sysfs_slab_remove(struct kmem_cache *s) { - if (slab_state < SYSFS) + if (slab_state < FULL) /* * Sysfs has not been setup yet so no need to remove the * cache from sysfs. @@ -5359,7 +5353,7 @@ static int sysfs_slab_alias(struct kmem_cache *s, const char *name) { struct saved_alias *al; - if (slab_state == SYSFS) { + if (slab_state == FULL) { /* * If we have a leftover link then remove it. */ @@ -5383,16 +5377,16 @@ static int __init slab_sysfs_init(void) struct kmem_cache *s; int err; - down_write(&slub_lock); + mutex_lock(&slab_mutex); slab_kset = kset_create_and_add("slab", &slab_uevent_ops, kernel_kobj); if (!slab_kset) { - up_write(&slub_lock); + mutex_unlock(&slab_mutex); printk(KERN_ERR "Cannot register slab subsystem.\n"); return -ENOSYS; } - slab_state = SYSFS; + slab_state = FULL; list_for_each_entry(s, &slab_caches, list) { err = sysfs_slab_add(s); @@ -5408,11 +5402,11 @@ static int __init slab_sysfs_init(void) err = sysfs_slab_alias(al->s, al->name); if (err) printk(KERN_ERR "SLUB: Unable to add boot slab alias" - " %s to sysfs\n", s->name); + " %s to sysfs\n", al->name); kfree(al); } - up_write(&slub_lock); + mutex_unlock(&slab_mutex); resiliency_test(); return 0; } @@ -5427,7 +5421,7 @@ __initcall(slab_sysfs_init); static void print_slabinfo_header(struct seq_file *m) { seq_puts(m, "slabinfo - version: 2.1\n"); - seq_puts(m, "# name <active_objs> <num_objs> <objsize> " + seq_puts(m, "# name <active_objs> <num_objs> <object_size> " "<objperslab> <pagesperslab>"); seq_puts(m, " : tunables <limit> <batchcount> <sharedfactor>"); seq_puts(m, " : slabdata <active_slabs> <num_slabs> <sharedavail>"); @@ -5438,7 +5432,7 @@ static void *s_start(struct seq_file *m, loff_t *pos) { loff_t n = *pos; - down_read(&slub_lock); + mutex_lock(&slab_mutex); if (!n) print_slabinfo_header(m); @@ -5452,7 +5446,7 @@ static void *s_next(struct seq_file *m, void *p, loff_t *pos) static void s_stop(struct seq_file *m, void *p) { - up_read(&slub_lock); + mutex_unlock(&slab_mutex); } static int s_show(struct seq_file *m, void *p) diff --git a/mm/sparse.c b/mm/sparse.c index 6a4bf91..fac95f2 100644 --- a/mm/sparse.c +++ b/mm/sparse.c @@ -65,21 +65,18 @@ static struct mem_section noinline __init_refok *sparse_index_alloc(int nid) if (slab_is_available()) { if (node_state(nid, N_HIGH_MEMORY)) - section = kmalloc_node(array_size, GFP_KERNEL, nid); + section = kzalloc_node(array_size, GFP_KERNEL, nid); else - section = kmalloc(array_size, GFP_KERNEL); - } else + section = kzalloc(array_size, GFP_KERNEL); + } else { section = alloc_bootmem_node(NODE_DATA(nid), array_size); - - if (section) - memset(section, 0, array_size); + } return section; } static int __meminit sparse_index_init(unsigned long section_nr, int nid) { - static DEFINE_SPINLOCK(index_init_lock); unsigned long root = SECTION_NR_TO_ROOT(section_nr); struct mem_section *section; int ret = 0; @@ -90,20 +87,9 @@ static int __meminit sparse_index_init(unsigned long section_nr, int nid) section = sparse_index_alloc(nid); if (!section) return -ENOMEM; - /* - * This lock keeps two different sections from - * reallocating for the same index - */ - spin_lock(&index_init_lock); - - if (mem_section[root]) { - ret = -EEXIST; - goto out; - } mem_section[root] = section; -out: - spin_unlock(&index_init_lock); + return ret; } #else /* !SPARSEMEM_EXTREME */ @@ -132,6 +118,8 @@ int __section_nr(struct mem_section* ms) break; } + VM_BUG_ON(root_nr == NR_SECTION_ROOTS); + return (root_nr * SECTIONS_PER_ROOT) + (ms - root); } @@ -275,8 +263,9 @@ static unsigned long * __init sparse_early_usemaps_alloc_pgdat_section(struct pglist_data *pgdat, unsigned long size) { - pg_data_t *host_pgdat; - unsigned long goal; + unsigned long goal, limit; + unsigned long *p; + int nid; /* * A page may contain usemaps for other sections preventing the * page being freed and making a section unremovable while @@ -287,10 +276,17 @@ sparse_early_usemaps_alloc_pgdat_section(struct pglist_data *pgdat, * from the same section as the pgdat where possible to avoid * this problem. */ - goal = __pa(pgdat) & PAGE_SECTION_MASK; - host_pgdat = NODE_DATA(early_pfn_to_nid(goal >> PAGE_SHIFT)); - return __alloc_bootmem_node_nopanic(host_pgdat, size, - SMP_CACHE_BYTES, goal); + goal = __pa(pgdat) & (PAGE_SECTION_MASK << PAGE_SHIFT); + limit = goal + (1UL << PA_SECTION_SHIFT); + nid = early_pfn_to_nid(goal >> PAGE_SHIFT); +again: + p = ___alloc_bootmem_node_nopanic(NODE_DATA(nid), size, + SMP_CACHE_BYTES, goal, limit); + if (!p && limit) { + limit = 0; + goto again; + } + return p; } static void __init check_usemap_section_nr(int nid, unsigned long *usemap) @@ -485,6 +481,9 @@ void __init sparse_init(void) struct page **map_map; #endif + /* Setup pageblock_order for HUGETLB_PAGE_SIZE_VARIABLE */ + set_pageblock_order(); + /* * map is using big page (aka 2M in x86 64 bit) * usemap is less one page (aka 24 bytes) @@ -236,6 +236,58 @@ void put_pages_list(struct list_head *pages) } EXPORT_SYMBOL(put_pages_list); +/* + * get_kernel_pages() - pin kernel pages in memory + * @kiov: An array of struct kvec structures + * @nr_segs: number of segments to pin + * @write: pinning for read/write, currently ignored + * @pages: array that receives pointers to the pages pinned. + * Should be at least nr_segs long. + * + * Returns number of pages pinned. This may be fewer than the number + * requested. If nr_pages is 0 or negative, returns 0. If no pages + * were pinned, returns -errno. Each page returned must be released + * with a put_page() call when it is finished with. + */ +int get_kernel_pages(const struct kvec *kiov, int nr_segs, int write, + struct page **pages) +{ + int seg; + + for (seg = 0; seg < nr_segs; seg++) { + if (WARN_ON(kiov[seg].iov_len != PAGE_SIZE)) + return seg; + + pages[seg] = kmap_to_page(kiov[seg].iov_base); + page_cache_get(pages[seg]); + } + + return seg; +} +EXPORT_SYMBOL_GPL(get_kernel_pages); + +/* + * get_kernel_page() - pin a kernel page in memory + * @start: starting kernel address + * @write: pinning for read/write, currently ignored + * @pages: array that receives pointer to the page pinned. + * Must be at least nr_segs long. + * + * Returns 1 if page is pinned. If the page was not pinned, returns + * -errno. The page returned must be released with a put_page() call + * when it is finished with. + */ +int get_kernel_page(unsigned long start, int write, struct page **pages) +{ + const struct kvec kiov = { + .iov_base = (void *)start, + .iov_len = PAGE_SIZE + }; + + return get_kernel_pages(&kiov, 1, write, pages); +} +EXPORT_SYMBOL_GPL(get_kernel_page); + static void pagevec_lru_move_fn(struct pagevec *pvec, void (*move_fn)(struct page *page, struct lruvec *lruvec, void *arg), void *arg) diff --git a/mm/swap_state.c b/mm/swap_state.c index 4c5ff7f..0cb36fb 100644 --- a/mm/swap_state.c +++ b/mm/swap_state.c @@ -14,6 +14,7 @@ #include <linux/init.h> #include <linux/pagemap.h> #include <linux/backing-dev.h> +#include <linux/blkdev.h> #include <linux/pagevec.h> #include <linux/migrate.h> #include <linux/page_cgroup.h> @@ -26,7 +27,7 @@ */ static const struct address_space_operations swap_aops = { .writepage = swap_writepage, - .set_page_dirty = __set_page_dirty_no_writeback, + .set_page_dirty = swap_set_page_dirty, .migratepage = migrate_page, }; @@ -376,6 +377,7 @@ struct page *swapin_readahead(swp_entry_t entry, gfp_t gfp_mask, unsigned long offset = swp_offset(entry); unsigned long start_offset, end_offset; unsigned long mask = (1UL << page_cluster) - 1; + struct blk_plug plug; /* Read a page_cluster sized and aligned cluster around offset. */ start_offset = offset & ~mask; @@ -383,6 +385,7 @@ struct page *swapin_readahead(swp_entry_t entry, gfp_t gfp_mask, if (!start_offset) /* First page is swap header. */ start_offset++; + blk_start_plug(&plug); for (offset = start_offset; offset <= end_offset ; offset++) { /* Ok, do the async read-ahead now */ page = read_swap_cache_async(swp_entry(swp_type(entry), offset), @@ -391,6 +394,8 @@ struct page *swapin_readahead(swp_entry_t entry, gfp_t gfp_mask, continue; page_cache_release(page); } + blk_finish_plug(&plug); + lru_add_drain(); /* Push any new pages onto the LRU now */ return read_swap_cache_async(entry, gfp_mask, vma, addr); } diff --git a/mm/swapfile.c b/mm/swapfile.c index 457b10b..14e254c 100644 --- a/mm/swapfile.c +++ b/mm/swapfile.c @@ -31,6 +31,9 @@ #include <linux/memcontrol.h> #include <linux/poll.h> #include <linux/oom.h> +#include <linux/frontswap.h> +#include <linux/swapfile.h> +#include <linux/export.h> #include <asm/pgtable.h> #include <asm/tlbflush.h> @@ -42,7 +45,7 @@ static bool swap_count_continued(struct swap_info_struct *, pgoff_t, static void free_swap_count_continuations(struct swap_info_struct *); static sector_t map_swap_entry(swp_entry_t, struct block_device**); -static DEFINE_SPINLOCK(swap_lock); +DEFINE_SPINLOCK(swap_lock); static unsigned int nr_swapfiles; long nr_swap_pages; long total_swap_pages; @@ -53,9 +56,9 @@ static const char Unused_file[] = "Unused swap file entry "; static const char Bad_offset[] = "Bad swap offset entry "; static const char Unused_offset[] = "Unused swap offset entry "; -static struct swap_list_t swap_list = {-1, -1}; +struct swap_list_t swap_list = {-1, -1}; -static struct swap_info_struct *swap_info[MAX_SWAPFILES]; +struct swap_info_struct *swap_info[MAX_SWAPFILES]; static DEFINE_MUTEX(swapon_mutex); @@ -546,7 +549,6 @@ static unsigned char swap_entry_free(struct swap_info_struct *p, /* free if no reference */ if (!usage) { - struct gendisk *disk = p->bdev->bd_disk; if (offset < p->lowest_bit) p->lowest_bit = offset; if (offset > p->highest_bit) @@ -556,9 +558,13 @@ static unsigned char swap_entry_free(struct swap_info_struct *p, swap_list.next = p->type; nr_swap_pages++; p->inuse_pages--; - if ((p->flags & SWP_BLKDEV) && - disk->fops->swap_slot_free_notify) - disk->fops->swap_slot_free_notify(p->bdev, offset); + frontswap_invalidate_page(p->type, offset); + if (p->flags & SWP_BLKDEV) { + struct gendisk *disk = p->bdev->bd_disk; + if (disk->fops->swap_slot_free_notify) + disk->fops->swap_slot_free_notify(p->bdev, + offset); + } } return usage; @@ -829,8 +835,7 @@ static int unuse_pte(struct vm_area_struct *vma, pmd_t *pmd, pte = pte_offset_map_lock(vma->vm_mm, pmd, addr, &ptl); if (unlikely(!pte_same(*pte, swp_entry_to_pte(entry)))) { - if (ret > 0) - mem_cgroup_cancel_charge_swapin(memcg); + mem_cgroup_cancel_charge_swapin(memcg); ret = 0; goto out; } @@ -985,11 +990,12 @@ static int unuse_mm(struct mm_struct *mm, } /* - * Scan swap_map from current position to next entry still in use. + * Scan swap_map (or frontswap_map if frontswap parameter is true) + * from current position to next entry still in use. * Recycle to start on reaching the end, returning 0 when empty. */ static unsigned int find_next_to_unuse(struct swap_info_struct *si, - unsigned int prev) + unsigned int prev, bool frontswap) { unsigned int max = si->max; unsigned int i = prev; @@ -1015,6 +1021,12 @@ static unsigned int find_next_to_unuse(struct swap_info_struct *si, prev = 0; i = 1; } + if (frontswap) { + if (frontswap_test(si, i)) + break; + else + continue; + } count = si->swap_map[i]; if (count && swap_count(count) != SWAP_MAP_BAD) break; @@ -1026,8 +1038,12 @@ static unsigned int find_next_to_unuse(struct swap_info_struct *si, * We completely avoid races by reading each swap page in advance, * and then search for the process using it. All the necessary * page table adjustments can then be made atomically. + * + * if the boolean frontswap is true, only unuse pages_to_unuse pages; + * pages_to_unuse==0 means all pages; ignored if frontswap is false */ -static int try_to_unuse(unsigned int type) +int try_to_unuse(unsigned int type, bool frontswap, + unsigned long pages_to_unuse) { struct swap_info_struct *si = swap_info[type]; struct mm_struct *start_mm; @@ -1060,7 +1076,7 @@ static int try_to_unuse(unsigned int type) * one pass through swap_map is enough, but not necessarily: * there are races when an instance of an entry might be missed. */ - while ((i = find_next_to_unuse(si, i)) != 0) { + while ((i = find_next_to_unuse(si, i, frontswap)) != 0) { if (signal_pending(current)) { retval = -EINTR; break; @@ -1227,6 +1243,10 @@ static int try_to_unuse(unsigned int type) * interactive performance. */ cond_resched(); + if (frontswap && pages_to_unuse > 0) { + if (!--pages_to_unuse) + break; + } } mmput(start_mm); @@ -1310,6 +1330,14 @@ static void destroy_swap_extents(struct swap_info_struct *sis) list_del(&se->list); kfree(se); } + + if (sis->flags & SWP_FILE) { + struct file *swap_file = sis->swap_file; + struct address_space *mapping = swap_file->f_mapping; + + sis->flags &= ~SWP_FILE; + mapping->a_ops->swap_deactivate(swap_file); + } } /* @@ -1318,7 +1346,7 @@ static void destroy_swap_extents(struct swap_info_struct *sis) * * This function rather assumes that it is called in ascending page order. */ -static int +int add_swap_extent(struct swap_info_struct *sis, unsigned long start_page, unsigned long nr_pages, sector_t start_block) { @@ -1391,102 +1419,33 @@ add_swap_extent(struct swap_info_struct *sis, unsigned long start_page, */ static int setup_swap_extents(struct swap_info_struct *sis, sector_t *span) { - struct inode *inode; - unsigned blocks_per_page; - unsigned long page_no; - unsigned blkbits; - sector_t probe_block; - sector_t last_block; - sector_t lowest_block = -1; - sector_t highest_block = 0; - int nr_extents = 0; + struct file *swap_file = sis->swap_file; + struct address_space *mapping = swap_file->f_mapping; + struct inode *inode = mapping->host; int ret; - inode = sis->swap_file->f_mapping->host; if (S_ISBLK(inode->i_mode)) { ret = add_swap_extent(sis, 0, sis->max, 0); *span = sis->pages; - goto out; + return ret; } - blkbits = inode->i_blkbits; - blocks_per_page = PAGE_SIZE >> blkbits; - - /* - * Map all the blocks into the extent list. This code doesn't try - * to be very smart. - */ - probe_block = 0; - page_no = 0; - last_block = i_size_read(inode) >> blkbits; - while ((probe_block + blocks_per_page) <= last_block && - page_no < sis->max) { - unsigned block_in_page; - sector_t first_block; - - first_block = bmap(inode, probe_block); - if (first_block == 0) - goto bad_bmap; - - /* - * It must be PAGE_SIZE aligned on-disk - */ - if (first_block & (blocks_per_page - 1)) { - probe_block++; - goto reprobe; - } - - for (block_in_page = 1; block_in_page < blocks_per_page; - block_in_page++) { - sector_t block; - - block = bmap(inode, probe_block + block_in_page); - if (block == 0) - goto bad_bmap; - if (block != first_block + block_in_page) { - /* Discontiguity */ - probe_block++; - goto reprobe; - } - } - - first_block >>= (PAGE_SHIFT - blkbits); - if (page_no) { /* exclude the header page */ - if (first_block < lowest_block) - lowest_block = first_block; - if (first_block > highest_block) - highest_block = first_block; + if (mapping->a_ops->swap_activate) { + ret = mapping->a_ops->swap_activate(sis, swap_file, span); + if (!ret) { + sis->flags |= SWP_FILE; + ret = add_swap_extent(sis, 0, sis->max, 0); + *span = sis->pages; } + return ret; + } - /* - * We found a PAGE_SIZE-length, PAGE_SIZE-aligned run of blocks - */ - ret = add_swap_extent(sis, page_no, 1, first_block); - if (ret < 0) - goto out; - nr_extents += ret; - page_no++; - probe_block += blocks_per_page; -reprobe: - continue; - } - ret = nr_extents; - *span = 1 + highest_block - lowest_block; - if (page_no == 0) - page_no = 1; /* force Empty message */ - sis->max = page_no; - sis->pages = page_no - 1; - sis->highest_bit = page_no - 1; -out: - return ret; -bad_bmap: - printk(KERN_ERR "swapon: swapfile has holes\n"); - ret = -EINVAL; - goto out; + return generic_swapfile_activate(sis, swap_file, span); } static void enable_swap_info(struct swap_info_struct *p, int prio, - unsigned char *swap_map) + unsigned char *swap_map, + unsigned long *frontswap_map) { int i, prev; @@ -1496,6 +1455,7 @@ static void enable_swap_info(struct swap_info_struct *p, int prio, else p->prio = --least_priority; p->swap_map = swap_map; + frontswap_map_set(p, frontswap_map); p->flags |= SWP_WRITEOK; nr_swap_pages += p->pages; total_swap_pages += p->pages; @@ -1512,6 +1472,7 @@ static void enable_swap_info(struct swap_info_struct *p, int prio, swap_list.head = swap_list.next = p->type; else swap_info[prev]->next = p->type; + frontswap_init(p->type); spin_unlock(&swap_lock); } @@ -1585,7 +1546,7 @@ SYSCALL_DEFINE1(swapoff, const char __user *, specialfile) spin_unlock(&swap_lock); oom_score_adj = test_set_oom_score_adj(OOM_SCORE_ADJ_MAX); - err = try_to_unuse(type); + err = try_to_unuse(type, false, 0); /* force all pages to be unused */ compare_swap_oom_score_adj(OOM_SCORE_ADJ_MAX, oom_score_adj); if (err) { @@ -1596,7 +1557,7 @@ SYSCALL_DEFINE1(swapoff, const char __user *, specialfile) * sys_swapoff for this swap_info_struct at this point. */ /* re-insert swap space back into swap_list */ - enable_swap_info(p, p->prio, p->swap_map); + enable_swap_info(p, p->prio, p->swap_map, frontswap_map_get(p)); goto out_dput; } @@ -1622,9 +1583,11 @@ SYSCALL_DEFINE1(swapoff, const char __user *, specialfile) swap_map = p->swap_map; p->swap_map = NULL; p->flags = 0; + frontswap_invalidate_area(type); spin_unlock(&swap_lock); mutex_unlock(&swapon_mutex); vfree(swap_map); + vfree(frontswap_map_get(p)); /* Destroy swap account informatin */ swap_cgroup_swapoff(type); @@ -1893,24 +1856,20 @@ 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 three limiting factors: 1) the number + * 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 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 + * different architectures. 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 * 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. Then the same is done for a radix_tree entry. + * swap pte. */ maxpages = swp_offset(pte_to_swp_entry( - swp_entry_to_pte(swp_entry(0, ~0UL)))); - maxpages = swp_offset(radix_to_swp_entry( - swp_to_radix_entry(swp_entry(0, maxpages)))) + 1; - + swp_entry_to_pte(swp_entry(0, ~0UL)))) + 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 */ @@ -1988,6 +1947,7 @@ SYSCALL_DEFINE2(swapon, const char __user *, specialfile, int, swap_flags) sector_t span; unsigned long maxpages; unsigned char *swap_map = NULL; + unsigned long *frontswap_map = NULL; struct page *page = NULL; struct inode *inode = NULL; @@ -2071,6 +2031,9 @@ SYSCALL_DEFINE2(swapon, const char __user *, specialfile, int, swap_flags) error = nr_extents; goto bad_swap; } + /* frontswap enabled? set up bit-per-page map for frontswap */ + if (frontswap_enabled) + frontswap_map = vzalloc(maxpages / sizeof(long)); if (p->bdev) { if (blk_queue_nonrot(bdev_get_queue(p->bdev))) { @@ -2086,14 +2049,15 @@ SYSCALL_DEFINE2(swapon, const char __user *, specialfile, int, swap_flags) if (swap_flags & SWAP_FLAG_PREFER) prio = (swap_flags & SWAP_FLAG_PRIO_MASK) >> SWAP_FLAG_PRIO_SHIFT; - enable_swap_info(p, prio, swap_map); + enable_swap_info(p, prio, swap_map, frontswap_map); printk(KERN_INFO "Adding %uk swap on %s. " - "Priority:%d extents:%d across:%lluk %s%s\n", + "Priority:%d extents:%d across:%lluk %s%s%s\n", p->pages<<(PAGE_SHIFT-10), name, p->prio, nr_extents, (unsigned long long)span<<(PAGE_SHIFT-10), (p->flags & SWP_SOLIDSTATE) ? "SS" : "", - (p->flags & SWP_DISCARDABLE) ? "D" : ""); + (p->flags & SWP_DISCARDABLE) ? "D" : "", + (frontswap_map) ? "FS" : ""); mutex_unlock(&swapon_mutex); atomic_inc(&proc_poll_event); @@ -2261,6 +2225,31 @@ int swapcache_prepare(swp_entry_t entry) return __swap_duplicate(entry, SWAP_HAS_CACHE); } +struct swap_info_struct *page_swap_info(struct page *page) +{ + swp_entry_t swap = { .val = page_private(page) }; + BUG_ON(!PageSwapCache(page)); + return swap_info[swp_type(swap)]; +} + +/* + * out-of-line __page_file_ methods to avoid include hell. + */ +struct address_space *__page_file_mapping(struct page *page) +{ + VM_BUG_ON(!PageSwapCache(page)); + return page_swap_info(page)->swap_file->f_mapping; +} +EXPORT_SYMBOL_GPL(__page_file_mapping); + +pgoff_t __page_file_index(struct page *page) +{ + swp_entry_t swap = { .val = page_private(page) }; + VM_BUG_ON(!PageSwapCache(page)); + return swp_offset(swap); +} +EXPORT_SYMBOL_GPL(__page_file_index); + /* * add_swap_count_continuation - called when a swap count is duplicated * beyond SWAP_MAP_MAX, it allocates a new page and links that to the entry's diff --git a/mm/vmalloc.c b/mm/vmalloc.c index 2aad499..2bb90b1 100644 --- a/mm/vmalloc.c +++ b/mm/vmalloc.c @@ -413,11 +413,11 @@ nocache: if (addr + size - 1 < addr) goto overflow; - n = rb_next(&first->rb_node); - if (n) - first = rb_entry(n, struct vmap_area, rb_node); - else + if (list_is_last(&first->list, &vmap_area_list)) goto found; + + first = list_entry(first->list.next, + struct vmap_area, list); } found: @@ -904,6 +904,14 @@ static void *vb_alloc(unsigned long size, gfp_t gfp_mask) BUG_ON(size & ~PAGE_MASK); BUG_ON(size > PAGE_SIZE*VMAP_MAX_ALLOC); + if (WARN_ON(size == 0)) { + /* + * Allocating 0 bytes isn't what caller wants since + * get_order(0) returns funny result. Just warn and terminate + * early. + */ + return NULL; + } order = get_order(size); again: @@ -1280,7 +1288,7 @@ DEFINE_RWLOCK(vmlist_lock); struct vm_struct *vmlist; static void setup_vmalloc_vm(struct vm_struct *vm, struct vmap_area *va, - unsigned long flags, void *caller) + unsigned long flags, const void *caller) { vm->flags = flags; vm->addr = (void *)va->va_start; @@ -1306,7 +1314,7 @@ static void insert_vmalloc_vmlist(struct vm_struct *vm) } static void insert_vmalloc_vm(struct vm_struct *vm, struct vmap_area *va, - unsigned long flags, void *caller) + unsigned long flags, const void *caller) { setup_vmalloc_vm(vm, va, flags, caller); insert_vmalloc_vmlist(vm); @@ -1314,7 +1322,7 @@ static void insert_vmalloc_vm(struct vm_struct *vm, struct vmap_area *va, 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) + unsigned long end, int node, gfp_t gfp_mask, const void *caller) { struct vmap_area *va; struct vm_struct *area; @@ -1375,7 +1383,7 @@ EXPORT_SYMBOL_GPL(__get_vm_area); struct vm_struct *__get_vm_area_caller(unsigned long size, unsigned long flags, unsigned long start, unsigned long end, - void *caller) + const void *caller) { return __get_vm_area_node(size, 1, flags, start, end, -1, GFP_KERNEL, caller); @@ -1397,13 +1405,21 @@ struct vm_struct *get_vm_area(unsigned long size, unsigned long flags) } struct vm_struct *get_vm_area_caller(unsigned long size, unsigned long flags, - void *caller) + const void *caller) { return __get_vm_area_node(size, 1, flags, VMALLOC_START, VMALLOC_END, -1, GFP_KERNEL, caller); } -static struct vm_struct *find_vm_area(const void *addr) +/** + * find_vm_area - find a continuous kernel virtual area + * @addr: base address + * + * Search for the kernel VM area starting at @addr, and return it. + * It is up to the caller to do all required locking to keep the returned + * pointer valid. + */ +struct vm_struct *find_vm_area(const void *addr) { struct vmap_area *va; @@ -1568,9 +1584,9 @@ EXPORT_SYMBOL(vmap); static void *__vmalloc_node(unsigned long size, unsigned long align, gfp_t gfp_mask, pgprot_t prot, - int node, void *caller); + int node, const void *caller); static void *__vmalloc_area_node(struct vm_struct *area, gfp_t gfp_mask, - pgprot_t prot, int node, void *caller) + pgprot_t prot, int node, const void *caller) { const int order = 0; struct page **pages; @@ -1643,7 +1659,7 @@ fail: */ void *__vmalloc_node_range(unsigned long size, unsigned long align, unsigned long start, unsigned long end, gfp_t gfp_mask, - pgprot_t prot, int node, void *caller) + pgprot_t prot, int node, const void *caller) { struct vm_struct *area; void *addr; @@ -1699,7 +1715,7 @@ fail: */ static void *__vmalloc_node(unsigned long size, unsigned long align, gfp_t gfp_mask, pgprot_t prot, - int node, void *caller) + int node, const void *caller) { return __vmalloc_node_range(size, align, VMALLOC_START, VMALLOC_END, gfp_mask, prot, node, caller); @@ -1975,9 +1991,7 @@ static int aligned_vwrite(char *buf, char *addr, unsigned long count) * IOREMAP area is treated as memory hole and no copy is done. * * If [addr...addr+count) doesn't includes any intersects with alive - * vm_struct area, returns 0. - * @buf should be kernel's buffer. Because this function uses KM_USER0, - * the caller should guarantee KM_USER0 is not used. + * vm_struct area, returns 0. @buf should be kernel's buffer. * * Note: In usual ops, vread() is never necessary because the caller * should know vmalloc() area is valid and can use memcpy(). @@ -2051,9 +2065,7 @@ finished: * IOREMAP area is treated as memory hole and no copy is done. * * If [addr...addr+count) doesn't includes any intersects with alive - * vm_struct area, returns 0. - * @buf should be kernel's buffer. Because this function uses KM_USER0, - * the caller should guarantee KM_USER0 is not used. + * vm_struct area, returns 0. @buf should be kernel's buffer. * * Note: In usual ops, vwrite() is never necessary because the caller * should know vmalloc() area is valid and can use memcpy(). diff --git a/mm/vmscan.c b/mm/vmscan.c index eeb3bc9..8d01243 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -133,7 +133,7 @@ long vm_total_pages; /* The total number of pages which the VM controls */ static LIST_HEAD(shrinker_list); static DECLARE_RWSEM(shrinker_rwsem); -#ifdef CONFIG_CGROUP_MEM_RES_CTLR +#ifdef CONFIG_MEMCG static bool global_reclaim(struct scan_control *sc) { return !sc->target_mem_cgroup; @@ -687,6 +687,7 @@ static unsigned long shrink_page_list(struct list_head *page_list, cond_resched(); + mem_cgroup_uncharge_start(); while (!list_empty(page_list)) { enum page_references references; struct address_space *mapping; @@ -720,9 +721,41 @@ static unsigned long shrink_page_list(struct list_head *page_list, (PageSwapCache(page) && (sc->gfp_mask & __GFP_IO)); if (PageWriteback(page)) { - nr_writeback++; - unlock_page(page); - goto keep; + /* + * memcg doesn't have any dirty pages throttling so we + * could easily OOM just because too many pages are in + * writeback and there is nothing else to reclaim. + * + * Check __GFP_IO, certainly because a loop driver + * thread might enter reclaim, and deadlock if it waits + * on a page for which it is needed to do the write + * (loop masks off __GFP_IO|__GFP_FS for this reason); + * but more thought would probably show more reasons. + * + * Don't require __GFP_FS, since we're not going into + * the FS, just waiting on its writeback completion. + * Worryingly, ext4 gfs2 and xfs allocate pages with + * grab_cache_page_write_begin(,,AOP_FLAG_NOFS), so + * testing may_enter_fs here is liable to OOM on them. + */ + if (global_reclaim(sc) || + !PageReclaim(page) || !(sc->gfp_mask & __GFP_IO)) { + /* + * This is slightly racy - end_page_writeback() + * might have just cleared PageReclaim, then + * setting PageReclaim here end up interpreted + * as PageReadahead - but that does not matter + * enough to care. What we do want is for this + * page to have PageReclaim set next time memcg + * reclaim reaches the tests above, so it will + * then wait_on_page_writeback() to avoid OOM; + * and it's also appropriate in global reclaim. + */ + SetPageReclaim(page); + nr_writeback++; + goto keep_locked; + } + wait_on_page_writeback(page); } references = page_check_references(page, sc); @@ -921,6 +954,7 @@ keep: list_splice(&ret_pages, page_list); count_vm_events(PGACTIVATE, pgactivate); + mem_cgroup_uncharge_end(); *ret_nr_dirty += nr_dirty; *ret_nr_writeback += nr_writeback; return nr_reclaimed; @@ -1567,7 +1601,8 @@ static int vmscan_swappiness(struct scan_control *sc) * by looking at the fraction of the pages scanned we did rotate back * onto the active list instead of evict. * - * nr[0] = anon pages to scan; nr[1] = file pages to scan + * nr[0] = anon inactive pages to scan; nr[1] = anon active pages to scan + * nr[2] = file inactive pages to scan; nr[3] = file active pages to scan */ static void get_scan_count(struct lruvec *lruvec, struct scan_control *sc, unsigned long *nr) @@ -2111,6 +2146,83 @@ out: return 0; } +static bool pfmemalloc_watermark_ok(pg_data_t *pgdat) +{ + struct zone *zone; + unsigned long pfmemalloc_reserve = 0; + unsigned long free_pages = 0; + int i; + bool wmark_ok; + + for (i = 0; i <= ZONE_NORMAL; i++) { + zone = &pgdat->node_zones[i]; + pfmemalloc_reserve += min_wmark_pages(zone); + free_pages += zone_page_state(zone, NR_FREE_PAGES); + } + + wmark_ok = free_pages > pfmemalloc_reserve / 2; + + /* kswapd must be awake if processes are being throttled */ + if (!wmark_ok && waitqueue_active(&pgdat->kswapd_wait)) { + pgdat->classzone_idx = min(pgdat->classzone_idx, + (enum zone_type)ZONE_NORMAL); + wake_up_interruptible(&pgdat->kswapd_wait); + } + + return wmark_ok; +} + +/* + * Throttle direct reclaimers if backing storage is backed by the network + * and the PFMEMALLOC reserve for the preferred node is getting dangerously + * depleted. kswapd will continue to make progress and wake the processes + * when the low watermark is reached + */ +static void throttle_direct_reclaim(gfp_t gfp_mask, struct zonelist *zonelist, + nodemask_t *nodemask) +{ + struct zone *zone; + int high_zoneidx = gfp_zone(gfp_mask); + pg_data_t *pgdat; + + /* + * Kernel threads should not be throttled as they may be indirectly + * responsible for cleaning pages necessary for reclaim to make forward + * progress. kjournald for example may enter direct reclaim while + * committing a transaction where throttling it could forcing other + * processes to block on log_wait_commit(). + */ + if (current->flags & PF_KTHREAD) + return; + + /* Check if the pfmemalloc reserves are ok */ + first_zones_zonelist(zonelist, high_zoneidx, NULL, &zone); + pgdat = zone->zone_pgdat; + if (pfmemalloc_watermark_ok(pgdat)) + return; + + /* Account for the throttling */ + count_vm_event(PGSCAN_DIRECT_THROTTLE); + + /* + * If the caller cannot enter the filesystem, it's possible that it + * is due to the caller holding an FS lock or performing a journal + * transaction in the case of a filesystem like ext[3|4]. In this case, + * it is not safe to block on pfmemalloc_wait as kswapd could be + * blocked waiting on the same lock. Instead, throttle for up to a + * second before continuing. + */ + if (!(gfp_mask & __GFP_FS)) { + wait_event_interruptible_timeout(pgdat->pfmemalloc_wait, + pfmemalloc_watermark_ok(pgdat), HZ); + return; + } + + /* Throttle until kswapd wakes the process */ + wait_event_killable(zone->zone_pgdat->pfmemalloc_wait, + pfmemalloc_watermark_ok(pgdat)); +} + unsigned long try_to_free_pages(struct zonelist *zonelist, int order, gfp_t gfp_mask, nodemask_t *nodemask) { @@ -2130,6 +2242,15 @@ unsigned long try_to_free_pages(struct zonelist *zonelist, int order, .gfp_mask = sc.gfp_mask, }; + throttle_direct_reclaim(gfp_mask, zonelist, nodemask); + + /* + * Do not enter reclaim if fatal signal is pending. 1 is returned so + * that the page allocator does not consider triggering OOM + */ + if (fatal_signal_pending(current)) + return 1; + trace_mm_vmscan_direct_reclaim_begin(order, sc.may_writepage, gfp_mask); @@ -2141,7 +2262,7 @@ unsigned long try_to_free_pages(struct zonelist *zonelist, int order, return nr_reclaimed; } -#ifdef CONFIG_CGROUP_MEM_RES_CTLR +#ifdef CONFIG_MEMCG unsigned long mem_cgroup_shrink_node_zone(struct mem_cgroup *memcg, gfp_t gfp_mask, bool noswap, @@ -2274,8 +2395,13 @@ static bool pgdat_balanced(pg_data_t *pgdat, unsigned long balanced_pages, return balanced_pages >= (present_pages >> 2); } -/* is kswapd sleeping prematurely? */ -static bool sleeping_prematurely(pg_data_t *pgdat, int order, long remaining, +/* + * Prepare kswapd for sleeping. This verifies that there are no processes + * waiting in throttle_direct_reclaim() and that watermarks have been met. + * + * Returns true if kswapd is ready to sleep + */ +static bool prepare_kswapd_sleep(pg_data_t *pgdat, int order, long remaining, int classzone_idx) { int i; @@ -2284,7 +2410,21 @@ static bool sleeping_prematurely(pg_data_t *pgdat, int order, long remaining, /* If a direct reclaimer woke kswapd within HZ/10, it's premature */ if (remaining) - return true; + return false; + + /* + * There is a potential race between when kswapd checks its watermarks + * and a process gets throttled. There is also a potential race if + * processes get throttled, kswapd wakes, a large process exits therby + * balancing the zones that causes kswapd to miss a wakeup. If kswapd + * is going to sleep, no process should be sleeping on pfmemalloc_wait + * so wake them now if necessary. If necessary, processes will wake + * kswapd and get throttled again + */ + if (waitqueue_active(&pgdat->pfmemalloc_wait)) { + wake_up(&pgdat->pfmemalloc_wait); + return false; + } /* Check the watermark levels */ for (i = 0; i <= classzone_idx; i++) { @@ -2317,9 +2457,9 @@ static bool sleeping_prematurely(pg_data_t *pgdat, int order, long remaining, * must be balanced */ if (order) - return !pgdat_balanced(pgdat, balanced, classzone_idx); + return pgdat_balanced(pgdat, balanced, classzone_idx); else - return !all_zones_ok; + return all_zones_ok; } /* @@ -2537,7 +2677,7 @@ loop_again: * consider it to be no longer congested. It's * possible there are dirty pages backed by * congested BDIs but as pressure is relieved, - * spectulatively avoid congestion waits + * speculatively avoid congestion waits */ zone_clear_flag(zone, ZONE_CONGESTED); if (i <= *classzone_idx) @@ -2545,6 +2685,16 @@ loop_again: } } + + /* + * If the low watermark is met there is no need for processes + * to be throttled on pfmemalloc_wait as they should not be + * able to safely make forward progress. Wake them + */ + if (waitqueue_active(&pgdat->pfmemalloc_wait) && + pfmemalloc_watermark_ok(pgdat)) + wake_up(&pgdat->pfmemalloc_wait); + if (all_zones_ok || (order && pgdat_balanced(pgdat, balanced, *classzone_idx))) break; /* kswapd: all done */ /* @@ -2646,7 +2796,7 @@ out: } /* - * Return the order we were reclaiming at so sleeping_prematurely() + * Return the order we were reclaiming at so prepare_kswapd_sleep() * makes a decision on the order we were last reclaiming at. However, * if another caller entered the allocator slow path while kswapd * was awake, order will remain at the higher level @@ -2666,7 +2816,7 @@ static void kswapd_try_to_sleep(pg_data_t *pgdat, int order, int classzone_idx) prepare_to_wait(&pgdat->kswapd_wait, &wait, TASK_INTERRUPTIBLE); /* Try to sleep for a short interval */ - if (!sleeping_prematurely(pgdat, order, remaining, classzone_idx)) { + if (prepare_kswapd_sleep(pgdat, order, remaining, classzone_idx)) { remaining = schedule_timeout(HZ/10); finish_wait(&pgdat->kswapd_wait, &wait); prepare_to_wait(&pgdat->kswapd_wait, &wait, TASK_INTERRUPTIBLE); @@ -2676,7 +2826,7 @@ static void kswapd_try_to_sleep(pg_data_t *pgdat, int order, int classzone_idx) * After a short sleep, check if it was a premature sleep. If not, then * go fully to sleep until explicitly woken up. */ - if (!sleeping_prematurely(pgdat, order, remaining, classzone_idx)) { + if (prepare_kswapd_sleep(pgdat, order, remaining, classzone_idx)) { trace_mm_vmscan_kswapd_sleep(pgdat->node_id); /* @@ -2688,7 +2838,10 @@ static void kswapd_try_to_sleep(pg_data_t *pgdat, int order, int classzone_idx) * them before going back to sleep. */ set_pgdat_percpu_threshold(pgdat, calculate_normal_threshold); - schedule(); + + if (!kthread_should_stop()) + schedule(); + set_pgdat_percpu_threshold(pgdat, calculate_pressure_threshold); } else { if (remaining) @@ -2955,14 +3108,17 @@ int kswapd_run(int nid) } /* - * Called by memory hotplug when all memory in a node is offlined. + * Called by memory hotplug when all memory in a node is offlined. Caller must + * hold lock_memory_hotplug(). */ void kswapd_stop(int nid) { struct task_struct *kswapd = NODE_DATA(nid)->kswapd; - if (kswapd) + if (kswapd) { kthread_stop(kswapd); + NODE_DATA(nid)->kswapd = NULL; + } } static int __init kswapd_init(void) diff --git a/mm/vmstat.c b/mm/vmstat.c index 1bbbbd9..df7a674 100644 --- a/mm/vmstat.c +++ b/mm/vmstat.c @@ -745,6 +745,7 @@ const char * const vmstat_text[] = { TEXTS_FOR_ZONES("pgsteal_direct") TEXTS_FOR_ZONES("pgscan_kswapd") TEXTS_FOR_ZONES("pgscan_direct") + "pgscan_direct_throttle", #ifdef CONFIG_NUMA "zone_reclaim_failed", |
