diff options
Diffstat (limited to 'mm')
| -rw-r--r-- | mm/Kconfig | 6 | ||||
| -rw-r--r-- | mm/Makefile | 4 | ||||
| -rw-r--r-- | mm/cleancache.c | 276 | ||||
| -rw-r--r-- | mm/cma.c | 62 | ||||
| -rw-r--r-- | mm/cma.h | 24 | ||||
| -rw-r--r-- | mm/cma_debug.c | 205 | ||||
| -rw-r--r-- | mm/compaction.c | 75 | ||||
| -rw-r--r-- | mm/filemap.c | 130 | ||||
| -rw-r--r-- | mm/gup.c | 128 | ||||
| -rw-r--r-- | mm/huge_memory.c | 136 | ||||
| -rw-r--r-- | mm/hugetlb.c | 250 | ||||
| -rw-r--r-- | mm/internal.h | 8 | ||||
| -rw-r--r-- | mm/iov_iter.c | 753 | ||||
| -rw-r--r-- | mm/kasan/kasan.c | 27 | ||||
| -rw-r--r-- | mm/ksm.c | 10 | ||||
| -rw-r--r-- | mm/memblock.c | 22 | ||||
| -rw-r--r-- | mm/memcontrol.c | 245 | ||||
| -rw-r--r-- | mm/memory-failure.c | 122 | ||||
| -rw-r--r-- | mm/memory.c | 436 | ||||
| -rw-r--r-- | mm/memory_hotplug.c | 50 | ||||
| -rw-r--r-- | mm/mempolicy.c | 6 | ||||
| -rw-r--r-- | mm/mempool.c | 127 | ||||
| -rw-r--r-- | mm/memtest.c | 118 | ||||
| -rw-r--r-- | mm/migrate.c | 40 | ||||
| -rw-r--r-- | mm/mlock.c | 135 | ||||
| -rw-r--r-- | mm/mmap.c | 29 | ||||
| -rw-r--r-- | mm/mprotect.c | 3 | ||||
| -rw-r--r-- | mm/mremap.c | 35 | ||||
| -rw-r--r-- | mm/nommu.c | 5 | ||||
| -rw-r--r-- | mm/oom_kill.c | 9 | ||||
| -rw-r--r-- | mm/page-writeback.c | 29 | ||||
| -rw-r--r-- | mm/page_alloc.c | 256 | ||||
| -rw-r--r-- | mm/page_io.c | 7 | ||||
| -rw-r--r-- | mm/page_isolation.c | 1 | ||||
| -rw-r--r-- | mm/pagewalk.c | 9 | ||||
| -rw-r--r-- | mm/percpu.c | 4 | ||||
| -rw-r--r-- | mm/process_vm_access.c | 35 | ||||
| -rw-r--r-- | mm/rmap.c | 13 | ||||
| -rw-r--r-- | mm/shmem.c | 34 | ||||
| -rw-r--r-- | mm/slab.c | 22 | ||||
| -rw-r--r-- | mm/slob.c | 3 | ||||
| -rw-r--r-- | mm/slub.c | 38 | ||||
| -rw-r--r-- | mm/swap.c | 34 | ||||
| -rw-r--r-- | mm/swap_state.c | 2 | ||||
| -rw-r--r-- | mm/swapfile.c | 2 | ||||
| -rw-r--r-- | mm/truncate.c | 39 | ||||
| -rw-r--r-- | mm/util.c | 41 | ||||
| -rw-r--r-- | mm/vmalloc.c | 104 | ||||
| -rw-r--r-- | mm/zsmalloc.c | 971 |
49 files changed, 2807 insertions, 2313 deletions
diff --git a/mm/Kconfig b/mm/Kconfig index a03131b6ba8e..390214da4546 100644 --- a/mm/Kconfig +++ b/mm/Kconfig @@ -517,6 +517,12 @@ config CMA_DEBUG processing calls such as dma_alloc_from_contiguous(). This option does not affect warning and error messages. +config CMA_DEBUGFS + bool "CMA debugfs interface" + depends on CMA && DEBUG_FS + help + Turns on the DebugFS interface for CMA. + config CMA_AREAS int "Maximum count of the CMA areas" depends on CMA diff --git a/mm/Makefile b/mm/Makefile index 3c1caa2693bd..98c4eaeabdcb 100644 --- a/mm/Makefile +++ b/mm/Makefile @@ -21,7 +21,7 @@ obj-y := filemap.o mempool.o oom_kill.o \ mm_init.o mmu_context.o percpu.o slab_common.o \ compaction.o vmacache.o \ interval_tree.o list_lru.o workingset.o \ - iov_iter.o debug.o $(mmu-y) + debug.o $(mmu-y) obj-y += init-mm.o @@ -55,6 +55,7 @@ obj-$(CONFIG_KMEMCHECK) += kmemcheck.o obj-$(CONFIG_KASAN) += kasan/ obj-$(CONFIG_FAILSLAB) += failslab.o obj-$(CONFIG_MEMORY_HOTPLUG) += memory_hotplug.o +obj-$(CONFIG_MEMTEST) += memtest.o obj-$(CONFIG_MIGRATION) += migrate.o obj-$(CONFIG_QUICKLIST) += quicklist.o obj-$(CONFIG_TRANSPARENT_HUGEPAGE) += huge_memory.o @@ -76,3 +77,4 @@ obj-$(CONFIG_GENERIC_EARLY_IOREMAP) += early_ioremap.o obj-$(CONFIG_CMA) += cma.o obj-$(CONFIG_MEMORY_BALLOON) += balloon_compaction.o obj-$(CONFIG_PAGE_EXTENSION) += page_ext.o +obj-$(CONFIG_CMA_DEBUGFS) += cma_debug.o diff --git a/mm/cleancache.c b/mm/cleancache.c index 053bcd8f12fb..8fc50811119b 100644 --- a/mm/cleancache.c +++ b/mm/cleancache.c @@ -19,7 +19,7 @@ #include <linux/cleancache.h> /* - * cleancache_ops is set by cleancache_ops_register to contain the pointers + * cleancache_ops is set by cleancache_register_ops to contain the pointers * to the cleancache "backend" implementation functions. */ static struct cleancache_ops *cleancache_ops __read_mostly; @@ -34,145 +34,107 @@ static u64 cleancache_failed_gets; static u64 cleancache_puts; static u64 cleancache_invalidates; -/* - * When no backend is registered all calls to init_fs and init_shared_fs - * are registered and fake poolids (FAKE_FS_POOLID_OFFSET or - * FAKE_SHARED_FS_POOLID_OFFSET, plus offset in the respective array - * [shared_|]fs_poolid_map) are given to the respective super block - * (sb->cleancache_poolid) and no tmem_pools are created. When a backend - * registers with cleancache the previous calls to init_fs and init_shared_fs - * are executed to create tmem_pools and set the respective poolids. While no - * backend is registered all "puts", "gets" and "flushes" are ignored or failed. - */ -#define MAX_INITIALIZABLE_FS 32 -#define FAKE_FS_POOLID_OFFSET 1000 -#define FAKE_SHARED_FS_POOLID_OFFSET 2000 - -#define FS_NO_BACKEND (-1) -#define FS_UNKNOWN (-2) -static int fs_poolid_map[MAX_INITIALIZABLE_FS]; -static int shared_fs_poolid_map[MAX_INITIALIZABLE_FS]; -static char *uuids[MAX_INITIALIZABLE_FS]; -/* - * Mutex for the [shared_|]fs_poolid_map to guard against multiple threads - * invoking umount (and ending in __cleancache_invalidate_fs) and also multiple - * threads calling mount (and ending up in __cleancache_init_[shared|]fs). - */ -static DEFINE_MUTEX(poolid_mutex); -/* - * When set to false (default) all calls to the cleancache functions, except - * the __cleancache_invalidate_fs and __cleancache_init_[shared|]fs are guarded - * by the if (!cleancache_ops) return. This means multiple threads (from - * different filesystems) will be checking cleancache_ops. The usage of a - * bool instead of a atomic_t or a bool guarded by a spinlock is OK - we are - * OK if the time between the backend's have been initialized (and - * cleancache_ops has been set to not NULL) and when the filesystems start - * actually calling the backends. The inverse (when unloading) is obviously - * not good - but this shim does not do that (yet). - */ - -/* - * The backends and filesystems work all asynchronously. This is b/c the - * backends can be built as modules. - * The usual sequence of events is: - * a) mount / -> __cleancache_init_fs is called. We set the - * [shared_|]fs_poolid_map and uuids for. - * - * b). user does I/Os -> we call the rest of __cleancache_* functions - * which return immediately as cleancache_ops is false. - * - * c). modprobe zcache -> cleancache_register_ops. We init the backend - * and set cleancache_ops to true, and for any fs_poolid_map - * (which is set by __cleancache_init_fs) we initialize the poolid. - * - * d). user does I/Os -> now that cleancache_ops is true all the - * __cleancache_* functions can call the backend. They all check - * that fs_poolid_map is valid and if so invoke the backend. - * - * e). umount / -> __cleancache_invalidate_fs, the fs_poolid_map is - * reset (which is the second check in the __cleancache_* ops - * to call the backend). - * - * The sequence of event could also be c), followed by a), and d). and e). The - * c) would not happen anymore. There is also the chance of c), and one thread - * doing a) + d), and another doing e). For that case we depend on the - * filesystem calling __cleancache_invalidate_fs in the proper sequence (so - * that it handles all I/Os before it invalidates the fs (which is last part - * of unmounting process). - * - * Note: The acute reader will notice that there is no "rmmod zcache" case. - * This is b/c the functionality for that is not yet implemented and when - * done, will require some extra locking not yet devised. - */ +static void cleancache_register_ops_sb(struct super_block *sb, void *unused) +{ + switch (sb->cleancache_poolid) { + case CLEANCACHE_NO_BACKEND: + __cleancache_init_fs(sb); + break; + case CLEANCACHE_NO_BACKEND_SHARED: + __cleancache_init_shared_fs(sb); + break; + } +} /* - * Register operations for cleancache, returning previous thus allowing - * detection of multiple backends and possible nesting. + * Register operations for cleancache. Returns 0 on success. */ -struct cleancache_ops *cleancache_register_ops(struct cleancache_ops *ops) +int cleancache_register_ops(struct cleancache_ops *ops) { - struct cleancache_ops *old = cleancache_ops; - int i; + if (cmpxchg(&cleancache_ops, NULL, ops)) + return -EBUSY; - mutex_lock(&poolid_mutex); - for (i = 0; i < MAX_INITIALIZABLE_FS; i++) { - if (fs_poolid_map[i] == FS_NO_BACKEND) - fs_poolid_map[i] = ops->init_fs(PAGE_SIZE); - if (shared_fs_poolid_map[i] == FS_NO_BACKEND) - shared_fs_poolid_map[i] = ops->init_shared_fs - (uuids[i], PAGE_SIZE); - } /* - * We MUST set cleancache_ops _after_ we have called the backends - * init_fs or init_shared_fs functions. Otherwise the compiler might - * re-order where cleancache_ops is set in this function. + * A cleancache backend can be built as a module and hence loaded after + * a cleancache enabled filesystem has called cleancache_init_fs. To + * handle such a scenario, here we call ->init_fs or ->init_shared_fs + * for each active super block. To differentiate between local and + * shared filesystems, we temporarily initialize sb->cleancache_poolid + * to CLEANCACHE_NO_BACKEND or CLEANCACHE_NO_BACKEND_SHARED + * respectively in case there is no backend registered at the time + * cleancache_init_fs or cleancache_init_shared_fs is called. + * + * Since filesystems can be mounted concurrently with cleancache + * backend registration, we have to be careful to guarantee that all + * cleancache enabled filesystems that has been mounted by the time + * cleancache_register_ops is called has got and all mounted later will + * get cleancache_poolid. This is assured by the following statements + * tied together: + * + * a) iterate_supers skips only those super blocks that has started + * ->kill_sb + * + * b) if iterate_supers encounters a super block that has not finished + * ->mount yet, it waits until it is finished + * + * c) cleancache_init_fs is called from ->mount and + * cleancache_invalidate_fs is called from ->kill_sb + * + * d) we call iterate_supers after cleancache_ops has been set + * + * From a) it follows that if iterate_supers skips a super block, then + * either the super block is already dead, in which case we do not need + * to bother initializing cleancache for it, or it was mounted after we + * initiated iterate_supers. In the latter case, it must have seen + * cleancache_ops set according to d) and initialized cleancache from + * ->mount by itself according to c). This proves that we call + * ->init_fs at least once for each active super block. + * + * From b) and c) it follows that if iterate_supers encounters a super + * block that has already started ->init_fs, it will wait until ->mount + * and hence ->init_fs has finished, then check cleancache_poolid, see + * that it has already been set and therefore do nothing. This proves + * that we call ->init_fs no more than once for each super block. + * + * Combined together, the last two paragraphs prove the function + * correctness. + * + * Note that various cleancache callbacks may proceed before this + * function is called or even concurrently with it, but since + * CLEANCACHE_NO_BACKEND is negative, they will all result in a noop + * until the corresponding ->init_fs has been actually called and + * cleancache_ops has been set. */ - barrier(); - cleancache_ops = ops; - mutex_unlock(&poolid_mutex); - return old; + iterate_supers(cleancache_register_ops_sb, NULL); + return 0; } EXPORT_SYMBOL(cleancache_register_ops); /* Called by a cleancache-enabled filesystem at time of mount */ void __cleancache_init_fs(struct super_block *sb) { - int i; + int pool_id = CLEANCACHE_NO_BACKEND; - mutex_lock(&poolid_mutex); - for (i = 0; i < MAX_INITIALIZABLE_FS; i++) { - if (fs_poolid_map[i] == FS_UNKNOWN) { - sb->cleancache_poolid = i + FAKE_FS_POOLID_OFFSET; - if (cleancache_ops) - fs_poolid_map[i] = cleancache_ops->init_fs(PAGE_SIZE); - else - fs_poolid_map[i] = FS_NO_BACKEND; - break; - } + if (cleancache_ops) { + pool_id = cleancache_ops->init_fs(PAGE_SIZE); + if (pool_id < 0) + pool_id = CLEANCACHE_NO_POOL; } - mutex_unlock(&poolid_mutex); + sb->cleancache_poolid = pool_id; } EXPORT_SYMBOL(__cleancache_init_fs); /* Called by a cleancache-enabled clustered filesystem at time of mount */ -void __cleancache_init_shared_fs(char *uuid, struct super_block *sb) +void __cleancache_init_shared_fs(struct super_block *sb) { - int i; + int pool_id = CLEANCACHE_NO_BACKEND_SHARED; - mutex_lock(&poolid_mutex); - for (i = 0; i < MAX_INITIALIZABLE_FS; i++) { - if (shared_fs_poolid_map[i] == FS_UNKNOWN) { - sb->cleancache_poolid = i + FAKE_SHARED_FS_POOLID_OFFSET; - uuids[i] = uuid; - if (cleancache_ops) - shared_fs_poolid_map[i] = cleancache_ops->init_shared_fs - (uuid, PAGE_SIZE); - else - shared_fs_poolid_map[i] = FS_NO_BACKEND; - break; - } + if (cleancache_ops) { + pool_id = cleancache_ops->init_shared_fs(sb->s_uuid, PAGE_SIZE); + if (pool_id < 0) + pool_id = CLEANCACHE_NO_POOL; } - mutex_unlock(&poolid_mutex); + sb->cleancache_poolid = pool_id; } EXPORT_SYMBOL(__cleancache_init_shared_fs); @@ -202,19 +164,6 @@ static int cleancache_get_key(struct inode *inode, } /* - * Returns a pool_id that is associated with a given fake poolid. - */ -static int get_poolid_from_fake(int fake_pool_id) -{ - if (fake_pool_id >= FAKE_SHARED_FS_POOLID_OFFSET) - return shared_fs_poolid_map[fake_pool_id - - FAKE_SHARED_FS_POOLID_OFFSET]; - else if (fake_pool_id >= FAKE_FS_POOLID_OFFSET) - return fs_poolid_map[fake_pool_id - FAKE_FS_POOLID_OFFSET]; - return FS_NO_BACKEND; -} - -/* * "Get" data from cleancache associated with the poolid/inode/index * that were specified when the data was put to cleanache and, if * successful, use it to fill the specified page with data and return 0. @@ -229,7 +178,6 @@ int __cleancache_get_page(struct page *page) { int ret = -1; int pool_id; - int fake_pool_id; struct cleancache_filekey key = { .u.key = { 0 } }; if (!cleancache_ops) { @@ -238,17 +186,14 @@ int __cleancache_get_page(struct page *page) } VM_BUG_ON_PAGE(!PageLocked(page), page); - fake_pool_id = page->mapping->host->i_sb->cleancache_poolid; - if (fake_pool_id < 0) + pool_id = page->mapping->host->i_sb->cleancache_poolid; + if (pool_id < 0) goto out; - pool_id = get_poolid_from_fake(fake_pool_id); if (cleancache_get_key(page->mapping->host, &key) < 0) goto out; - if (pool_id >= 0) - ret = cleancache_ops->get_page(pool_id, - key, page->index, page); + ret = cleancache_ops->get_page(pool_id, key, page->index, page); if (ret == 0) cleancache_succ_gets++; else @@ -271,7 +216,6 @@ EXPORT_SYMBOL(__cleancache_get_page); void __cleancache_put_page(struct page *page) { int pool_id; - int fake_pool_id; struct cleancache_filekey key = { .u.key = { 0 } }; if (!cleancache_ops) { @@ -280,12 +224,7 @@ void __cleancache_put_page(struct page *page) } VM_BUG_ON_PAGE(!PageLocked(page), page); - fake_pool_id = page->mapping->host->i_sb->cleancache_poolid; - if (fake_pool_id < 0) - return; - - pool_id = get_poolid_from_fake(fake_pool_id); - + pool_id = page->mapping->host->i_sb->cleancache_poolid; if (pool_id >= 0 && cleancache_get_key(page->mapping->host, &key) >= 0) { cleancache_ops->put_page(pool_id, key, page->index, page); @@ -306,18 +245,13 @@ void __cleancache_invalidate_page(struct address_space *mapping, struct page *page) { /* careful... page->mapping is NULL sometimes when this is called */ - int pool_id; - int fake_pool_id = mapping->host->i_sb->cleancache_poolid; + int pool_id = mapping->host->i_sb->cleancache_poolid; struct cleancache_filekey key = { .u.key = { 0 } }; if (!cleancache_ops) return; - if (fake_pool_id >= 0) { - pool_id = get_poolid_from_fake(fake_pool_id); - if (pool_id < 0) - return; - + if (pool_id >= 0) { VM_BUG_ON_PAGE(!PageLocked(page), page); if (cleancache_get_key(mapping->host, &key) >= 0) { cleancache_ops->invalidate_page(pool_id, @@ -339,18 +273,12 @@ EXPORT_SYMBOL(__cleancache_invalidate_page); */ void __cleancache_invalidate_inode(struct address_space *mapping) { - int pool_id; - int fake_pool_id = mapping->host->i_sb->cleancache_poolid; + int pool_id = mapping->host->i_sb->cleancache_poolid; struct cleancache_filekey key = { .u.key = { 0 } }; if (!cleancache_ops) return; - if (fake_pool_id < 0) - return; - - pool_id = get_poolid_from_fake(fake_pool_id); - if (pool_id >= 0 && cleancache_get_key(mapping->host, &key) >= 0) cleancache_ops->invalidate_inode(pool_id, key); } @@ -363,32 +291,18 @@ EXPORT_SYMBOL(__cleancache_invalidate_inode); */ void __cleancache_invalidate_fs(struct super_block *sb) { - int index; - int fake_pool_id = sb->cleancache_poolid; - int old_poolid = fake_pool_id; + int pool_id; - mutex_lock(&poolid_mutex); - if (fake_pool_id >= FAKE_SHARED_FS_POOLID_OFFSET) { - index = fake_pool_id - FAKE_SHARED_FS_POOLID_OFFSET; - old_poolid = shared_fs_poolid_map[index]; - shared_fs_poolid_map[index] = FS_UNKNOWN; - uuids[index] = NULL; - } else if (fake_pool_id >= FAKE_FS_POOLID_OFFSET) { - index = fake_pool_id - FAKE_FS_POOLID_OFFSET; - old_poolid = fs_poolid_map[index]; - fs_poolid_map[index] = FS_UNKNOWN; - } - sb->cleancache_poolid = -1; - if (cleancache_ops) - cleancache_ops->invalidate_fs(old_poolid); - mutex_unlock(&poolid_mutex); + pool_id = sb->cleancache_poolid; + sb->cleancache_poolid = CLEANCACHE_NO_POOL; + + if (cleancache_ops && pool_id >= 0) + cleancache_ops->invalidate_fs(pool_id); } EXPORT_SYMBOL(__cleancache_invalidate_fs); static int __init init_cleancache(void) { - int i; - #ifdef CONFIG_DEBUG_FS struct dentry *root = debugfs_create_dir("cleancache", NULL); if (root == NULL) @@ -400,10 +314,6 @@ static int __init init_cleancache(void) debugfs_create_u64("invalidates", S_IRUGO, root, &cleancache_invalidates); #endif - for (i = 0; i < MAX_INITIALIZABLE_FS; i++) { - fs_poolid_map[i] = FS_UNKNOWN; - shared_fs_poolid_map[i] = FS_UNKNOWN; - } return 0; } module_init(init_cleancache) @@ -23,6 +23,7 @@ # define DEBUG #endif #endif +#define CREATE_TRACE_POINTS #include <linux/memblock.h> #include <linux/err.h> @@ -34,59 +35,54 @@ #include <linux/cma.h> #include <linux/highmem.h> #include <linux/io.h> +#include <trace/events/cma.h> -struct cma { - unsigned long base_pfn; - unsigned long count; - unsigned long *bitmap; - unsigned int order_per_bit; /* Order of pages represented by one bit */ - struct mutex lock; -}; +#include "cma.h" -static struct cma cma_areas[MAX_CMA_AREAS]; -static unsigned cma_area_count; +struct cma cma_areas[MAX_CMA_AREAS]; +unsigned cma_area_count; static DEFINE_MUTEX(cma_mutex); -phys_addr_t cma_get_base(struct cma *cma) +phys_addr_t cma_get_base(const struct cma *cma) { return PFN_PHYS(cma->base_pfn); } -unsigned long cma_get_size(struct cma *cma) +unsigned long cma_get_size(const struct cma *cma) { return cma->count << PAGE_SHIFT; } -static unsigned long cma_bitmap_aligned_mask(struct cma *cma, int align_order) +static unsigned long cma_bitmap_aligned_mask(const struct cma *cma, + int align_order) { if (align_order <= cma->order_per_bit) return 0; return (1UL << (align_order - cma->order_per_bit)) - 1; } -static unsigned long cma_bitmap_aligned_offset(struct cma *cma, int align_order) +/* + * Find a PFN aligned to the specified order and return an offset represented in + * order_per_bits. + */ +static unsigned long cma_bitmap_aligned_offset(const struct cma *cma, + int align_order) { - unsigned int alignment; - if (align_order <= cma->order_per_bit) return 0; - alignment = 1UL << (align_order - cma->order_per_bit); - return ALIGN(cma->base_pfn, alignment) - - (cma->base_pfn >> cma->order_per_bit); -} -static unsigned long cma_bitmap_maxno(struct cma *cma) -{ - return cma->count >> cma->order_per_bit; + return (ALIGN(cma->base_pfn, (1UL << align_order)) + - cma->base_pfn) >> cma->order_per_bit; } -static unsigned long cma_bitmap_pages_to_bits(struct cma *cma, - unsigned long pages) +static unsigned long cma_bitmap_pages_to_bits(const struct cma *cma, + unsigned long pages) { return ALIGN(pages, 1UL << cma->order_per_bit) >> cma->order_per_bit; } -static void cma_clear_bitmap(struct cma *cma, unsigned long pfn, int count) +static void cma_clear_bitmap(struct cma *cma, unsigned long pfn, + unsigned int count) { unsigned long bitmap_no, bitmap_count; @@ -132,6 +128,12 @@ static int __init cma_activate_area(struct cma *cma) } while (--i); mutex_init(&cma->lock); + +#ifdef CONFIG_CMA_DEBUGFS + INIT_HLIST_HEAD(&cma->mem_head); + spin_lock_init(&cma->mem_head_lock); +#endif + return 0; err: @@ -165,7 +167,8 @@ core_initcall(cma_init_reserved_areas); * This function creates custom contiguous area from already reserved memory. */ int __init cma_init_reserved_mem(phys_addr_t base, phys_addr_t size, - int order_per_bit, struct cma **res_cma) + unsigned int order_per_bit, + struct cma **res_cma) { struct cma *cma; phys_addr_t alignment; @@ -356,7 +359,7 @@ err: * This function allocates part of contiguous memory on specific * contiguous memory area. */ -struct page *cma_alloc(struct cma *cma, int count, unsigned int align) +struct page *cma_alloc(struct cma *cma, unsigned int count, unsigned int align) { unsigned long mask, offset, pfn, start = 0; unsigned long bitmap_maxno, bitmap_no, bitmap_count; @@ -413,6 +416,8 @@ struct page *cma_alloc(struct cma *cma, int count, unsigned int align) start = bitmap_no + mask + 1; } + trace_cma_alloc(page ? pfn : -1UL, page, count, align); + pr_debug("%s(): returned %p\n", __func__, page); return page; } @@ -427,7 +432,7 @@ struct page *cma_alloc(struct cma *cma, int count, unsigned int align) * It returns false when provided pages do not belong to contiguous area and * true otherwise. */ -bool cma_release(struct cma *cma, struct page *pages, int count) +bool cma_release(struct cma *cma, const struct page *pages, unsigned int count) { unsigned long pfn; @@ -445,6 +450,7 @@ bool cma_release(struct cma *cma, struct page *pages, int count) free_contig_range(pfn, count); cma_clear_bitmap(cma, pfn, count); + trace_cma_release(pfn, pages, count); return true; } diff --git a/mm/cma.h b/mm/cma.h new file mode 100644 index 000000000000..1132d733556d --- /dev/null +++ b/mm/cma.h @@ -0,0 +1,24 @@ +#ifndef __MM_CMA_H__ +#define __MM_CMA_H__ + +struct cma { + unsigned long base_pfn; + unsigned long count; + unsigned long *bitmap; + unsigned int order_per_bit; /* Order of pages represented by one bit */ + struct mutex lock; +#ifdef CONFIG_CMA_DEBUGFS + struct hlist_head mem_head; + spinlock_t mem_head_lock; +#endif +}; + +extern struct cma cma_areas[MAX_CMA_AREAS]; +extern unsigned cma_area_count; + +static unsigned long cma_bitmap_maxno(struct cma *cma) +{ + return cma->count >> cma->order_per_bit; +} + +#endif diff --git a/mm/cma_debug.c b/mm/cma_debug.c new file mode 100644 index 000000000000..7621ee34daa0 --- /dev/null +++ b/mm/cma_debug.c @@ -0,0 +1,205 @@ +/* + * CMA DebugFS Interface + * + * Copyright (c) 2015 Sasha Levin <sasha.levin@oracle.com> + */ + + +#include <linux/debugfs.h> +#include <linux/cma.h> +#include <linux/list.h> +#include <linux/kernel.h> +#include <linux/slab.h> +#include <linux/mm_types.h> + +#include "cma.h" + +struct cma_mem { + struct hlist_node node; + struct page *p; + unsigned long n; +}; + +static struct dentry *cma_debugfs_root; + +static int cma_debugfs_get(void *data, u64 *val) +{ + unsigned long *p = data; + + *val = *p; + + return 0; +} +DEFINE_SIMPLE_ATTRIBUTE(cma_debugfs_fops, cma_debugfs_get, NULL, "%llu\n"); + +static int cma_used_get(void *data, u64 *val) +{ + struct cma *cma = data; + unsigned long used; + + mutex_lock(&cma->lock); + /* pages counter is smaller than sizeof(int) */ + used = bitmap_weight(cma->bitmap, (int)cma->count); + mutex_unlock(&cma->lock); + *val = (u64)used << cma->order_per_bit; + + return 0; +} +DEFINE_SIMPLE_ATTRIBUTE(cma_used_fops, cma_used_get, NULL, "%llu\n"); + +static int cma_maxchunk_get(void *data, u64 *val) +{ + struct cma *cma = data; + unsigned long maxchunk = 0; + unsigned long start, end = 0; + + mutex_lock(&cma->lock); + for (;;) { + start = find_next_zero_bit(cma->bitmap, cma->count, end); + if (start >= cma->count) + break; + end = find_next_bit(cma->bitmap, cma->count, start); + maxchunk = max(end - start, maxchunk); + } + mutex_unlock(&cma->lock); + *val = (u64)maxchunk << cma->order_per_bit; + + return 0; +} +DEFINE_SIMPLE_ATTRIBUTE(cma_maxchunk_fops, cma_maxchunk_get, NULL, "%llu\n"); + +static void cma_add_to_cma_mem_list(struct cma *cma, struct cma_mem *mem) +{ + spin_lock(&cma->mem_head_lock); + hlist_add_head(&mem->node, &cma->mem_head); + spin_unlock(&cma->mem_head_lock); +} + +static struct cma_mem *cma_get_entry_from_list(struct cma *cma) +{ + struct cma_mem *mem = NULL; + + spin_lock(&cma->mem_head_lock); + if (!hlist_empty(&cma->mem_head)) { + mem = hlist_entry(cma->mem_head.first, struct cma_mem, node); + hlist_del_init(&mem->node); + } + spin_unlock(&cma->mem_head_lock); + + return mem; +} + +static int cma_free_mem(struct cma *cma, int count) +{ + struct cma_mem *mem = NULL; + + while (count) { + mem = cma_get_entry_from_list(cma); + if (mem == NULL) + return 0; + + if (mem->n <= count) { + cma_release(cma, mem->p, mem->n); + count -= mem->n; + kfree(mem); + } else if (cma->order_per_bit == 0) { + cma_release(cma, mem->p, count); + mem->p += count; + mem->n -= count; + count = 0; + cma_add_to_cma_mem_list(cma, mem); + } else { + pr_debug("cma: cannot release partial block when order_per_bit != 0\n"); + cma_add_to_cma_mem_list(cma, mem); + break; + } + } + + return 0; + +} + +static int cma_free_write(void *data, u64 val) +{ + int pages = val; + struct cma *cma = data; + + return cma_free_mem(cma, pages); +} +DEFINE_SIMPLE_ATTRIBUTE(cma_free_fops, NULL, cma_free_write, "%llu\n"); + +static int cma_alloc_mem(struct cma *cma, int count) +{ + struct cma_mem *mem; + struct page *p; + + mem = kzalloc(sizeof(*mem), GFP_KERNEL); + if (!mem) + return -ENOMEM; + + p = cma_alloc(cma, count, 0); + if (!p) { + kfree(mem); + return -ENOMEM; + } + + mem->p = p; + mem->n = count; + + cma_add_to_cma_mem_list(cma, mem); + + return 0; +} + +static int cma_alloc_write(void *data, u64 val) +{ + int pages = val; + struct cma *cma = data; + + return cma_alloc_mem(cma, pages); +} +DEFINE_SIMPLE_ATTRIBUTE(cma_alloc_fops, NULL, cma_alloc_write, "%llu\n"); + +static void cma_debugfs_add_one(struct cma *cma, int idx) +{ + struct dentry *tmp; + char name[16]; + int u32s; + + sprintf(name, "cma-%d", idx); + + tmp = debugfs_create_dir(name, cma_debugfs_root); + + debugfs_create_file("alloc", S_IWUSR, cma_debugfs_root, cma, + &cma_alloc_fops); + + debugfs_create_file("free", S_IWUSR, cma_debugfs_root, cma, + &cma_free_fops); + + debugfs_create_file("base_pfn", S_IRUGO, tmp, + &cma->base_pfn, &cma_debugfs_fops); + debugfs_create_file("count", S_IRUGO, tmp, + &cma->count, &cma_debugfs_fops); + debugfs_create_file("order_per_bit", S_IRUGO, tmp, + &cma->order_per_bit, &cma_debugfs_fops); + debugfs_create_file("used", S_IRUGO, tmp, cma, &cma_used_fops); + debugfs_create_file("maxchunk", S_IRUGO, tmp, cma, &cma_maxchunk_fops); + + u32s = DIV_ROUND_UP(cma_bitmap_maxno(cma), BITS_PER_BYTE * sizeof(u32)); + debugfs_create_u32_array("bitmap", S_IRUGO, tmp, (u32*)cma->bitmap, u32s); +} + +static int __init cma_debugfs_init(void) +{ + int i; + + cma_debugfs_root = debugfs_create_dir("cma", NULL); + if (!cma_debugfs_root) + return -ENOMEM; + + for (i = 0; i < cma_area_count; i++) + cma_debugfs_add_one(&cma_areas[i], i); + + return 0; +} +late_initcall(cma_debugfs_init); diff --git a/mm/compaction.c b/mm/compaction.c index 8c0d9459b54a..018f08da99a2 100644 --- a/mm/compaction.c +++ b/mm/compaction.c @@ -391,28 +391,6 @@ static inline bool compact_should_abort(struct compact_control *cc) return false; } -/* Returns true if the page is within a block suitable for migration to */ -static bool suitable_migration_target(struct page *page) -{ - /* If the page is a large free page, then disallow migration */ - if (PageBuddy(page)) { - /* - * We are checking page_order without zone->lock taken. But - * the only small danger is that we skip a potentially suitable - * pageblock, so it's not worth to check order for valid range. - */ - if (page_order_unsafe(page) >= pageblock_order) - return false; - } - - /* If the block is MIGRATE_MOVABLE or MIGRATE_CMA, allow migration */ - if (migrate_async_suitable(get_pageblock_migratetype(page))) - return true; - - /* Otherwise skip the block */ - return false; -} - /* * Isolate free pages onto a private freelist. If @strict is true, will abort * returning 0 on any invalid PFNs or non-free pages inside of the pageblock @@ -896,6 +874,29 @@ isolate_migratepages_range(struct compact_control *cc, unsigned long start_pfn, #endif /* CONFIG_COMPACTION || CONFIG_CMA */ #ifdef CONFIG_COMPACTION + +/* Returns true if the page is within a block suitable for migration to */ +static bool suitable_migration_target(struct page *page) +{ + /* If the page is a large free page, then disallow migration */ + if (PageBuddy(page)) { + /* + * We are checking page_order without zone->lock taken. But + * the only small danger is that we skip a potentially suitable + * pageblock, so it's not worth to check order for valid range. + */ + if (page_order_unsafe(page) >= pageblock_order) + return false; + } + + /* If the block is MIGRATE_MOVABLE or MIGRATE_CMA, allow migration */ + if (migrate_async_suitable(get_pageblock_migratetype(page))) + return true; + + /* Otherwise skip the block */ + return false; +} + /* * Based on information in the current compact_control, find blocks * suitable for isolating free pages from and then isolate them. @@ -1047,6 +1048,12 @@ typedef enum { } isolate_migrate_t; /* + * Allow userspace to control policy on scanning the unevictable LRU for + * compactable pages. + */ +int sysctl_compact_unevictable_allowed __read_mostly = 1; + +/* * Isolate all pages that can be migrated from the first suitable block, * starting at the block pointed to by the migrate scanner pfn within * compact_control. @@ -1057,6 +1064,7 @@ static isolate_migrate_t isolate_migratepages(struct zone *zone, unsigned long low_pfn, end_pfn; struct page *page; const isolate_mode_t isolate_mode = + (sysctl_compact_unevictable_allowed ? ISOLATE_UNEVICTABLE : 0) | (cc->mode == MIGRATE_ASYNC ? ISOLATE_ASYNC_MIGRATE : 0); /* @@ -1174,13 +1182,24 @@ static int __compact_finished(struct zone *zone, struct compact_control *cc, /* Direct compactor: Is a suitable page free? */ for (order = cc->order; order < MAX_ORDER; order++) { struct free_area *area = &zone->free_area[order]; + bool can_steal; /* Job done if page is free of the right migratetype */ if (!list_empty(&area->free_list[migratetype])) return COMPACT_PARTIAL; - /* Job done if allocation would set block type */ - if (order >= pageblock_order && area->nr_free) +#ifdef CONFIG_CMA + /* MIGRATE_MOVABLE can fallback on MIGRATE_CMA */ + if (migratetype == MIGRATE_MOVABLE && + !list_empty(&area->free_list[MIGRATE_CMA])) + return COMPACT_PARTIAL; +#endif + /* + * Job done if allocation would steal freepages from + * other migratetype buddy lists. + */ + if (find_suitable_fallback(area, order, migratetype, + true, &can_steal) != -1) return COMPACT_PARTIAL; } @@ -1587,6 +1606,14 @@ static void __compact_pgdat(pg_data_t *pgdat, struct compact_control *cc) INIT_LIST_HEAD(&cc->freepages); INIT_LIST_HEAD(&cc->migratepages); + /* + * When called via /proc/sys/vm/compact_memory + * this makes sure we compact the whole zone regardless of + * cached scanner positions. + */ + if (cc->order == -1) + __reset_isolation_suitable(zone); + if (cc->order == -1 || !compaction_deferred(zone, cc->order)) compact_zone(zone, cc); diff --git a/mm/filemap.c b/mm/filemap.c index ad7242043bdb..6bf5e42d560a 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -13,7 +13,6 @@ #include <linux/compiler.h> #include <linux/fs.h> #include <linux/uaccess.h> -#include <linux/aio.h> #include <linux/capability.h> #include <linux/kernel_stat.h> #include <linux/gfp.h> @@ -203,16 +202,15 @@ void __delete_from_page_cache(struct page *page, void *shadow) BUG_ON(page_mapped(page)); /* - * Some filesystems seem to re-dirty the page even after - * the VM has canceled the dirty bit (eg ext3 journaling). + * At this point page must be either written or cleaned by truncate. + * Dirty page here signals a bug and loss of unwritten data. * - * Fix it up by doing a final dirty accounting check after - * having removed the page entirely. + * This fixes dirty accounting after removing the page entirely but + * leaves PageDirty set: it has no effect for truncated page and + * anyway will be cleared before returning page into buddy allocator. */ - if (PageDirty(page) && mapping_cap_account_dirty(mapping)) { - dec_zone_page_state(page, NR_FILE_DIRTY); - dec_bdi_stat(inode_to_bdi(mapping->host), BDI_RECLAIMABLE); - } + if (WARN_ON_ONCE(PageDirty(page))) + account_page_cleaned(page, mapping); } /** @@ -1695,7 +1693,7 @@ generic_file_read_iter(struct kiocb *iocb, struct iov_iter *iter) loff_t *ppos = &iocb->ki_pos; loff_t pos = *ppos; - if (io_is_direct(file)) { + if (iocb->ki_flags & IOCB_DIRECT) { struct address_space *mapping = file->f_mapping; struct inode *inode = mapping->host; size_t count = iov_iter_count(iter); @@ -1708,7 +1706,7 @@ generic_file_read_iter(struct kiocb *iocb, struct iov_iter *iter) pos + count - 1); if (!retval) { struct iov_iter data = *iter; - retval = mapping->a_ops->direct_IO(READ, iocb, &data, pos); + retval = mapping->a_ops->direct_IO(iocb, &data, pos); } if (retval > 0) { @@ -2261,41 +2259,38 @@ EXPORT_SYMBOL(read_cache_page_gfp); * Returns appropriate error code that caller should return or * zero in case that write should be allowed. */ -inline int generic_write_checks(struct file *file, loff_t *pos, size_t *count, int isblk) +inline ssize_t generic_write_checks(struct kiocb *iocb, struct iov_iter *from) { + struct file *file = iocb->ki_filp; struct inode *inode = file->f_mapping->host; unsigned long limit = rlimit(RLIMIT_FSIZE); + loff_t pos; - if (unlikely(*pos < 0)) - return -EINVAL; + if (!iov_iter_count(from)) + return 0; - if (!isblk) { - /* FIXME: this is for backwards compatibility with 2.4 */ - if (file->f_flags & O_APPEND) - *pos = i_size_read(inode); + /* FIXME: this is for backwards compatibility with 2.4 */ + if (iocb->ki_flags & IOCB_APPEND) + iocb->ki_pos = i_size_read(inode); - if (limit != RLIM_INFINITY) { - if (*pos >= limit) { - send_sig(SIGXFSZ, current, 0); - return -EFBIG; - } - if (*count > limit - (typeof(limit))*pos) { - *count = limit - (typeof(limit))*pos; - } + pos = iocb->ki_pos; + + if (limit != RLIM_INFINITY) { + if (iocb->ki_pos >= limit) { + send_sig(SIGXFSZ, current, 0); + return -EFBIG; } + iov_iter_truncate(from, limit - (unsigned long)pos); } /* * LFS rule */ - if (unlikely(*pos + *count > MAX_NON_LFS && + if (unlikely(pos + iov_iter_count(from) > MAX_NON_LFS && !(file->f_flags & O_LARGEFILE))) { - if (*pos >= MAX_NON_LFS) { + if (pos >= MAX_NON_LFS) return -EFBIG; - } - if (*count > MAX_NON_LFS - (unsigned long)*pos) { - *count = MAX_NON_LFS - (unsigned long)*pos; - } + iov_iter_truncate(from, MAX_NON_LFS - (unsigned long)pos); } /* @@ -2305,34 +2300,11 @@ inline int generic_write_checks(struct file *file, loff_t *pos, size_t *count, i * exceeded without writing data we send a signal and return EFBIG. * Linus frestrict idea will clean these up nicely.. */ - if (likely(!isblk)) { - if (unlikely(*pos >= inode->i_sb->s_maxbytes)) { - if (*count || *pos > inode->i_sb->s_maxbytes) { - return -EFBIG; - } - /* zero-length writes at ->s_maxbytes are OK */ - } - - if (unlikely(*pos + *count > inode->i_sb->s_maxbytes)) - *count = inode->i_sb->s_maxbytes - *pos; - } else { -#ifdef CONFIG_BLOCK - loff_t isize; - if (bdev_read_only(I_BDEV(inode))) - return -EPERM; - isize = i_size_read(inode); - if (*pos >= isize) { - if (*count || *pos > isize) - return -ENOSPC; - } + if (unlikely(pos >= inode->i_sb->s_maxbytes)) + return -EFBIG; - if (*pos + *count > isize) - *count = isize - *pos; -#else - return -EPERM; -#endif - } - return 0; + iov_iter_truncate(from, inode->i_sb->s_maxbytes - pos); + return iov_iter_count(from); } EXPORT_SYMBOL(generic_write_checks); @@ -2396,7 +2368,7 @@ generic_file_direct_write(struct kiocb *iocb, struct iov_iter *from, loff_t pos) } data = *from; - written = mapping->a_ops->direct_IO(WRITE, iocb, &data, pos); + written = mapping->a_ops->direct_IO(iocb, &data, pos); /* * Finally, try again to invalidate clean pages which might have been @@ -2558,23 +2530,12 @@ ssize_t __generic_file_write_iter(struct kiocb *iocb, struct iov_iter *from) struct file *file = iocb->ki_filp; struct address_space * mapping = file->f_mapping; struct inode *inode = mapping->host; - loff_t pos = iocb->ki_pos; ssize_t written = 0; ssize_t err; ssize_t status; - size_t count = iov_iter_count(from); /* We can write back this queue in page reclaim */ current->backing_dev_info = inode_to_bdi(inode); - err = generic_write_checks(file, &pos, &count, S_ISBLK(inode->i_mode)); - if (err) - goto out; - - if (count == 0) - goto out; - - iov_iter_truncate(from, count); - err = file_remove_suid(file); if (err) goto out; @@ -2583,10 +2544,10 @@ ssize_t __generic_file_write_iter(struct kiocb *iocb, struct iov_iter *from) if (err) goto out; - if (io_is_direct(file)) { - loff_t endbyte; + if (iocb->ki_flags & IOCB_DIRECT) { + loff_t pos, endbyte; - written = generic_file_direct_write(iocb, from, pos); + written = generic_file_direct_write(iocb, from, iocb->ki_pos); /* * If the write stopped short of completing, fall back to * buffered writes. Some filesystems do this for writes to @@ -2594,13 +2555,10 @@ ssize_t __generic_file_write_iter(struct kiocb *iocb, struct iov_iter *from) * not succeed (even if it did, DAX does not handle dirty * page-cache pages correctly). */ - if (written < 0 || written == count || IS_DAX(inode)) + if (written < 0 || !iov_iter_count(from) || IS_DAX(inode)) goto out; - pos += written; - count -= written; - - status = generic_perform_write(file, from, pos); + status = generic_perform_write(file, from, pos = iocb->ki_pos); /* * If generic_perform_write() returned a synchronous error * then we want to return the number of bytes which were @@ -2612,15 +2570,15 @@ ssize_t __generic_file_write_iter(struct kiocb *iocb, struct iov_iter *from) err = status; goto out; } - iocb->ki_pos = pos + status; /* * We need to ensure that the page cache pages are written to * disk and invalidated to preserve the expected O_DIRECT * semantics. */ endbyte = pos + status - 1; - err = filemap_write_and_wait_range(file->f_mapping, pos, endbyte); + err = filemap_write_and_wait_range(mapping, pos, endbyte); if (err == 0) { + iocb->ki_pos = endbyte + 1; written += status; invalidate_mapping_pages(mapping, pos >> PAGE_CACHE_SHIFT, @@ -2632,9 +2590,9 @@ ssize_t __generic_file_write_iter(struct kiocb *iocb, struct iov_iter *from) */ } } else { - written = generic_perform_write(file, from, pos); - if (likely(written >= 0)) - iocb->ki_pos = pos + written; + written = generic_perform_write(file, from, iocb->ki_pos); + if (likely(written > 0)) + iocb->ki_pos += written; } out: current->backing_dev_info = NULL; @@ -2658,7 +2616,9 @@ ssize_t generic_file_write_iter(struct kiocb *iocb, struct iov_iter *from) ssize_t ret; mutex_lock(&inode->i_mutex); - ret = __generic_file_write_iter(iocb, from); + ret = generic_write_checks(iocb, from); + if (ret > 0) + ret = __generic_file_write_iter(iocb, from); mutex_unlock(&inode->i_mutex); if (ret > 0) { @@ -92,7 +92,7 @@ retry: */ mark_page_accessed(page); } - if ((flags & FOLL_MLOCK) && (vma->vm_flags & VM_LOCKED)) { + if ((flags & FOLL_POPULATE) && (vma->vm_flags & VM_LOCKED)) { /* * The preliminary mapping check is mainly to avoid the * pointless overhead of lock_page on the ZERO_PAGE @@ -265,8 +265,8 @@ static int faultin_page(struct task_struct *tsk, struct vm_area_struct *vma, unsigned int fault_flags = 0; int ret; - /* For mlock, just skip the stack guard page. */ - if ((*flags & FOLL_MLOCK) && + /* For mm_populate(), just skip the stack guard page. */ + if ((*flags & FOLL_POPULATE) && (stack_guard_page_start(vma, address) || stack_guard_page_end(vma, address + PAGE_SIZE))) return -ENOENT; @@ -819,6 +819,124 @@ long get_user_pages(struct task_struct *tsk, struct mm_struct *mm, EXPORT_SYMBOL(get_user_pages); /** + * populate_vma_page_range() - populate a range of pages in the vma. + * @vma: target vma + * @start: start address + * @end: end address + * @nonblocking: + * + * This takes care of mlocking the pages too if VM_LOCKED is set. + * + * return 0 on success, negative error code on error. + * + * vma->vm_mm->mmap_sem must be held. + * + * If @nonblocking is NULL, it may be held for read or write and will + * be unperturbed. + * + * If @nonblocking is non-NULL, it must held for read only and may be + * released. If it's released, *@nonblocking will be set to 0. + */ +long populate_vma_page_range(struct vm_area_struct *vma, + unsigned long start, unsigned long end, int *nonblocking) +{ + struct mm_struct *mm = vma->vm_mm; + unsigned long nr_pages = (end - start) / PAGE_SIZE; + int gup_flags; + + VM_BUG_ON(start & ~PAGE_MASK); + VM_BUG_ON(end & ~PAGE_MASK); + VM_BUG_ON_VMA(start < vma->vm_start, vma); + VM_BUG_ON_VMA(end > vma->vm_end, vma); + VM_BUG_ON_MM(!rwsem_is_locked(&mm->mmap_sem), mm); + + gup_flags = FOLL_TOUCH | FOLL_POPULATE; + /* + * We want to touch writable mappings with a write fault in order + * to break COW, except for shared mappings because these don't COW + * and we would not want to dirty them for nothing. + */ + if ((vma->vm_flags & (VM_WRITE | VM_SHARED)) == VM_WRITE) + gup_flags |= FOLL_WRITE; + + /* + * We want mlock to succeed for regions that have any permissions + * other than PROT_NONE. + */ + if (vma->vm_flags & (VM_READ | VM_WRITE | VM_EXEC)) + gup_flags |= FOLL_FORCE; + + /* + * We made sure addr is within a VMA, so the following will + * not result in a stack expansion that recurses back here. + */ + return __get_user_pages(current, mm, start, nr_pages, gup_flags, + NULL, NULL, nonblocking); +} + +/* + * __mm_populate - populate and/or mlock pages within a range of address space. + * + * This is used to implement mlock() and the MAP_POPULATE / MAP_LOCKED mmap + * flags. VMAs must be already marked with the desired vm_flags, and + * mmap_sem must not be held. + */ +int __mm_populate(unsigned long start, unsigned long len, int ignore_errors) +{ + struct mm_struct *mm = current->mm; + unsigned long end, nstart, nend; + struct vm_area_struct *vma = NULL; + int locked = 0; + long ret = 0; + + VM_BUG_ON(start & ~PAGE_MASK); + VM_BUG_ON(len != PAGE_ALIGN(len)); + end = start + len; + + for (nstart = start; nstart < end; nstart = nend) { + /* + * We want to fault in pages for [nstart; end) address range. + * Find first corresponding VMA. + */ + if (!locked) { + locked = 1; + down_read(&mm->mmap_sem); + vma = find_vma(mm, nstart); + } else if (nstart >= vma->vm_end) + vma = vma->vm_next; + if (!vma || vma->vm_start >= end) + break; + /* + * Set [nstart; nend) to intersection of desired address + * range with the first VMA. Also, skip undesirable VMA types. + */ + nend = min(end, vma->vm_end); + if (vma->vm_flags & (VM_IO | VM_PFNMAP)) + continue; + if (nstart < vma->vm_start) + nstart = vma->vm_start; + /* + * Now fault in a range of pages. populate_vma_page_range() + * double checks the vma flags, so that it won't mlock pages + * if the vma was already munlocked. + */ + ret = populate_vma_page_range(vma, nstart, nend, &locked); + if (ret < 0) { + if (ignore_errors) { + ret = 0; + continue; /* continue at next VMA */ + } + break; + } + nend = nstart + ret * PAGE_SIZE; + ret = 0; + } + if (locked) + up_read(&mm->mmap_sem); + return ret; /* 0 or negative error code */ +} + +/** * get_dump_page() - pin user page in memory while writing it to core dump * @addr: user address * @@ -901,7 +1019,7 @@ static int gup_pte_range(pmd_t pmd, unsigned long addr, unsigned long end, * * for an example see gup_get_pte in arch/x86/mm/gup.c */ - pte_t pte = ACCESS_ONCE(*ptep); + pte_t pte = READ_ONCE(*ptep); struct page *page; /* @@ -1191,7 +1309,7 @@ int __get_user_pages_fast(unsigned long start, int nr_pages, int write, local_irq_save(flags); pgdp = pgd_offset(mm, addr); do { - pgd_t pgd = ACCESS_ONCE(*pgdp); + pgd_t pgd = READ_ONCE(*pgdp); next = pgd_addr_end(addr, end); if (pgd_none(pgd)) diff --git a/mm/huge_memory.c b/mm/huge_memory.c index fc00c8cb5a82..078832cf3636 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -67,6 +67,7 @@ static unsigned int khugepaged_max_ptes_none __read_mostly = HPAGE_PMD_NR-1; static int khugepaged(void *none); static int khugepaged_slab_init(void); +static void khugepaged_slab_exit(void); #define MM_SLOTS_HASH_BITS 10 static __read_mostly DEFINE_HASHTABLE(mm_slots_hash, MM_SLOTS_HASH_BITS); @@ -109,9 +110,6 @@ static int set_recommended_min_free_kbytes(void) int nr_zones = 0; unsigned long recommended_min; - if (!khugepaged_enabled()) - return 0; - for_each_populated_zone(zone) nr_zones++; @@ -143,9 +141,8 @@ static int set_recommended_min_free_kbytes(void) setup_per_zone_wmarks(); return 0; } -late_initcall(set_recommended_min_free_kbytes); -static int start_khugepaged(void) +static int start_stop_khugepaged(void) { int err = 0; if (khugepaged_enabled()) { @@ -156,6 +153,7 @@ static int start_khugepaged(void) pr_err("khugepaged: kthread_run(khugepaged) failed\n"); err = PTR_ERR(khugepaged_thread); khugepaged_thread = NULL; + goto fail; } if (!list_empty(&khugepaged_scan.mm_head)) @@ -166,7 +164,7 @@ static int start_khugepaged(void) kthread_stop(khugepaged_thread); khugepaged_thread = NULL; } - +fail: return err; } @@ -183,7 +181,7 @@ static struct page *get_huge_zero_page(void) struct page *zero_page; retry: if (likely(atomic_inc_not_zero(&huge_zero_refcount))) - return ACCESS_ONCE(huge_zero_page); + return READ_ONCE(huge_zero_page); zero_page = alloc_pages((GFP_TRANSHUGE | __GFP_ZERO) & ~__GFP_MOVABLE, HPAGE_PMD_ORDER); @@ -202,7 +200,7 @@ retry: /* We take additional reference here. It will be put back by shrinker */ atomic_set(&huge_zero_refcount, 2); preempt_enable(); - return ACCESS_ONCE(huge_zero_page); + return READ_ONCE(huge_zero_page); } static void put_huge_zero_page(void) @@ -300,7 +298,7 @@ static ssize_t enabled_store(struct kobject *kobj, int err; mutex_lock(&khugepaged_mutex); - err = start_khugepaged(); + err = start_stop_khugepaged(); mutex_unlock(&khugepaged_mutex); if (err) @@ -634,27 +632,38 @@ static int __init hugepage_init(void) err = hugepage_init_sysfs(&hugepage_kobj); if (err) - return err; + goto err_sysfs; err = khugepaged_slab_init(); if (err) - goto out; + goto err_slab; - register_shrinker(&huge_zero_page_shrinker); + err = register_shrinker(&huge_zero_page_shrinker); + if (err) + goto err_hzp_shrinker; /* * By default disable transparent hugepages on smaller systems, * where the extra memory used could hurt more than TLB overhead * is likely to save. The admin can still enable it through /sys. */ - if (totalram_pages < (512 << (20 - PAGE_SHIFT))) + if (totalram_pages < (512 << (20 - PAGE_SHIFT))) { transparent_hugepage_flags = 0; + return 0; + } - start_khugepaged(); + err = start_stop_khugepaged(); + if (err) + goto err_khugepaged; return 0; -out: +err_khugepaged: + unregister_shrinker(&huge_zero_page_shrinker); +err_hzp_shrinker: + khugepaged_slab_exit(); +err_slab: hugepage_exit_sysfs(hugepage_kobj); +err_sysfs: return err; } subsys_initcall(hugepage_init); @@ -708,7 +717,7 @@ static inline pmd_t mk_huge_pmd(struct page *page, pgprot_t prot) static int __do_huge_pmd_anonymous_page(struct mm_struct *mm, struct vm_area_struct *vma, unsigned long haddr, pmd_t *pmd, - struct page *page) + struct page *page, gfp_t gfp) { struct mem_cgroup *memcg; pgtable_t pgtable; @@ -716,7 +725,7 @@ static int __do_huge_pmd_anonymous_page(struct mm_struct *mm, VM_BUG_ON_PAGE(!PageCompound(page), page); - if (mem_cgroup_try_charge(page, mm, GFP_TRANSHUGE, &memcg)) + if (mem_cgroup_try_charge(page, mm, gfp, &memcg)) return VM_FAULT_OOM; pgtable = pte_alloc_one(mm, haddr); @@ -822,7 +831,7 @@ int do_huge_pmd_anonymous_page(struct mm_struct *mm, struct vm_area_struct *vma, count_vm_event(THP_FAULT_FALLBACK); return VM_FAULT_FALLBACK; } - if (unlikely(__do_huge_pmd_anonymous_page(mm, vma, haddr, pmd, page))) { + if (unlikely(__do_huge_pmd_anonymous_page(mm, vma, haddr, pmd, page, gfp))) { put_page(page); count_vm_event(THP_FAULT_FALLBACK); return VM_FAULT_FALLBACK; @@ -1080,6 +1089,7 @@ int do_huge_pmd_wp_page(struct mm_struct *mm, struct vm_area_struct *vma, unsigned long haddr; unsigned long mmun_start; /* For mmu_notifiers */ unsigned long mmun_end; /* For mmu_notifiers */ + gfp_t huge_gfp; /* for allocation and charge */ ptl = pmd_lockptr(mm, pmd); VM_BUG_ON_VMA(!vma->anon_vma, vma); @@ -1106,10 +1116,8 @@ int do_huge_pmd_wp_page(struct mm_struct *mm, struct vm_area_struct *vma, alloc: if (transparent_hugepage_enabled(vma) && !transparent_hugepage_debug_cow()) { - gfp_t gfp; - - gfp = alloc_hugepage_gfpmask(transparent_hugepage_defrag(vma), 0); - new_page = alloc_hugepage_vma(gfp, vma, haddr, HPAGE_PMD_ORDER); + huge_gfp = alloc_hugepage_gfpmask(transparent_hugepage_defrag(vma), 0); + new_page = alloc_hugepage_vma(huge_gfp, vma, haddr, HPAGE_PMD_ORDER); } else new_page = NULL; @@ -1130,8 +1138,7 @@ alloc: goto out; } - if (unlikely(mem_cgroup_try_charge(new_page, mm, - GFP_TRANSHUGE, &memcg))) { + if (unlikely(mem_cgroup_try_charge(new_page, mm, huge_gfp, &memcg))) { put_page(new_page); if (page) { split_huge_page(page); @@ -1231,7 +1238,7 @@ struct page *follow_trans_huge_pmd(struct vm_area_struct *vma, pmd, _pmd, 1)) update_mmu_cache_pmd(vma, addr, pmd); } - if ((flags & FOLL_MLOCK) && (vma->vm_flags & VM_LOCKED)) { + if ((flags & FOLL_POPULATE) && (vma->vm_flags & VM_LOCKED)) { if (page->mapping && trylock_page(page)) { lru_add_drain(); if (page->mapping) @@ -1260,6 +1267,7 @@ int do_huge_pmd_numa_page(struct mm_struct *mm, struct vm_area_struct *vma, int target_nid, last_cpupid = -1; bool page_locked; bool migrated = false; + bool was_writable; int flags = 0; /* A PROT_NONE fault should not end up here */ @@ -1291,12 +1299,8 @@ int do_huge_pmd_numa_page(struct mm_struct *mm, struct vm_area_struct *vma, flags |= TNF_FAULT_LOCAL; } - /* - * Avoid grouping on DSO/COW pages in specific and RO pages - * in general, RO pages shouldn't hurt as much anyway since - * they can be in shared cache state. - */ - if (!pmd_write(pmd)) + /* See similar comment in do_numa_page for explanation */ + if (!(vma->vm_flags & VM_WRITE)) flags |= TNF_NO_GROUP; /* @@ -1353,12 +1357,17 @@ int do_huge_pmd_numa_page(struct mm_struct *mm, struct vm_area_struct *vma, if (migrated) { flags |= TNF_MIGRATED; page_nid = target_nid; - } + } else + flags |= TNF_MIGRATE_FAIL; goto out; clear_pmdnuma: BUG_ON(!PageLocked(page)); + was_writable = pmd_write(pmd); pmd = pmd_modify(pmd, vma->vm_page_prot); + pmd = pmd_mkyoung(pmd); + if (was_writable) + pmd = pmd_mkwrite(pmd); set_pmd_at(mm, haddr, pmdp, pmd); update_mmu_cache_pmd(vma, addr, pmdp); unlock_page(page); @@ -1482,6 +1491,8 @@ int change_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd, if (__pmd_trans_huge_lock(pmd, vma, &ptl) == 1) { pmd_t entry; + bool preserve_write = prot_numa && pmd_write(*pmd); + ret = 1; /* * Avoid trapping faults against the zero page. The read-only @@ -1490,16 +1501,17 @@ int change_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd, */ if (prot_numa && is_huge_zero_pmd(*pmd)) { spin_unlock(ptl); - return 0; + return ret; } if (!prot_numa || !pmd_protnone(*pmd)) { - ret = 1; entry = pmdp_get_and_clear_notify(mm, addr, pmd); entry = pmd_modify(entry, newprot); + if (preserve_write) + entry = pmd_mkwrite(entry); ret = HPAGE_PMD_NR; set_pmd_at(mm, addr, pmd, entry); - BUG_ON(pmd_write(entry)); + BUG_ON(!preserve_write && pmd_write(entry)); } spin_unlock(ptl); } @@ -1971,6 +1983,11 @@ static int __init khugepaged_slab_init(void) return 0; } +static void __init khugepaged_slab_exit(void) +{ + kmem_cache_destroy(mm_slot_cache); +} + static inline struct mm_slot *alloc_mm_slot(void) { if (!mm_slot_cache) /* initialization failed */ @@ -2104,7 +2121,7 @@ static void release_pte_pages(pte_t *pte, pte_t *_pte) { while (--_pte >= pte) { pte_t pteval = *_pte; - if (!pte_none(pteval)) + if (!pte_none(pteval) && !is_zero_pfn(pte_pfn(pteval))) release_pte_page(pte_page(pteval)); } } @@ -2115,13 +2132,13 @@ static int __collapse_huge_page_isolate(struct vm_area_struct *vma, { struct page *page; pte_t *_pte; - int none = 0; + int none_or_zero = 0; bool referenced = false, writable = false; for (_pte = pte; _pte < pte+HPAGE_PMD_NR; _pte++, address += PAGE_SIZE) { pte_t pteval = *_pte; - if (pte_none(pteval)) { - if (++none <= khugepaged_max_ptes_none) + if (pte_none(pteval) || is_zero_pfn(pte_pfn(pteval))) { + if (++none_or_zero <= khugepaged_max_ptes_none) continue; else goto out; @@ -2202,9 +2219,21 @@ static void __collapse_huge_page_copy(pte_t *pte, struct page *page, pte_t pteval = *_pte; struct page *src_page; - if (pte_none(pteval)) { + if (pte_none(pteval) || is_zero_pfn(pte_pfn(pteval))) { clear_user_highpage(page, address); add_mm_counter(vma->vm_mm, MM_ANONPAGES, 1); + if (is_zero_pfn(pte_pfn(pteval))) { + /* + * ptl mostly unnecessary. + */ + spin_lock(ptl); + /* + * paravirt calls inside pte_clear here are + * superfluous. + */ + pte_clear(vma->vm_mm, address, _pte); + spin_unlock(ptl); + } } else { src_page = pte_page(pteval); copy_user_highpage(page, src_page, address, vma); @@ -2306,8 +2335,8 @@ static bool khugepaged_prealloc_page(struct page **hpage, bool *wait) return true; } -static struct page -*khugepaged_alloc_page(struct page **hpage, struct mm_struct *mm, +static struct page * +khugepaged_alloc_page(struct page **hpage, gfp_t gfp, struct mm_struct *mm, struct vm_area_struct *vma, unsigned long address, int node) { @@ -2321,8 +2350,7 @@ static struct page */ up_read(&mm->mmap_sem); - *hpage = alloc_pages_exact_node(node, alloc_hugepage_gfpmask( - khugepaged_defrag(), __GFP_OTHER_NODE), HPAGE_PMD_ORDER); + *hpage = alloc_pages_exact_node(node, gfp, HPAGE_PMD_ORDER); if (unlikely(!*hpage)) { count_vm_event(THP_COLLAPSE_ALLOC_FAILED); *hpage = ERR_PTR(-ENOMEM); @@ -2375,13 +2403,14 @@ static bool khugepaged_prealloc_page(struct page **hpage, bool *wait) return true; } -static struct page -*khugepaged_alloc_page(struct page **hpage, struct mm_struct *mm, +static struct page * +khugepaged_alloc_page(struct page **hpage, gfp_t gfp, struct mm_struct *mm, struct vm_area_struct *vma, unsigned long address, int node) { up_read(&mm->mmap_sem); VM_BUG_ON(!*hpage); + return *hpage; } #endif @@ -2416,16 +2445,21 @@ static void collapse_huge_page(struct mm_struct *mm, struct mem_cgroup *memcg; unsigned long mmun_start; /* For mmu_notifiers */ unsigned long mmun_end; /* For mmu_notifiers */ + gfp_t gfp; VM_BUG_ON(address & ~HPAGE_PMD_MASK); + /* Only allocate from the target node */ + gfp = alloc_hugepage_gfpmask(khugepaged_defrag(), __GFP_OTHER_NODE) | + __GFP_THISNODE; + /* release the mmap_sem read lock. */ - new_page = khugepaged_alloc_page(hpage, mm, vma, address, node); + new_page = khugepaged_alloc_page(hpage, gfp, mm, vma, address, node); if (!new_page) return; if (unlikely(mem_cgroup_try_charge(new_page, mm, - GFP_TRANSHUGE, &memcg))) + gfp, &memcg))) return; /* @@ -2538,7 +2572,7 @@ static int khugepaged_scan_pmd(struct mm_struct *mm, { pmd_t *pmd; pte_t *pte, *_pte; - int ret = 0, none = 0; + int ret = 0, none_or_zero = 0; struct page *page; unsigned long _address; spinlock_t *ptl; @@ -2556,8 +2590,8 @@ static int khugepaged_scan_pmd(struct mm_struct *mm, for (_address = address, _pte = pte; _pte < pte+HPAGE_PMD_NR; _pte++, _address += PAGE_SIZE) { pte_t pteval = *_pte; - if (pte_none(pteval)) { - if (++none <= khugepaged_max_ptes_none) + if (pte_none(pteval) || is_zero_pfn(pte_pfn(pteval))) { + if (++none_or_zero <= khugepaged_max_ptes_none) continue; else goto out_unmap; diff --git a/mm/hugetlb.c b/mm/hugetlb.c index 0a9ac6c26832..271e4432734c 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -61,6 +61,9 @@ DEFINE_SPINLOCK(hugetlb_lock); static int num_fault_mutexes; static struct mutex *htlb_fault_mutex_table ____cacheline_aligned_in_smp; +/* Forward declaration */ +static int hugetlb_acct_memory(struct hstate *h, long delta); + static inline void unlock_or_release_subpool(struct hugepage_subpool *spool) { bool free = (spool->count == 0) && (spool->used_hpages == 0); @@ -68,23 +71,36 @@ static inline void unlock_or_release_subpool(struct hugepage_subpool *spool) spin_unlock(&spool->lock); /* If no pages are used, and no other handles to the subpool - * remain, free the subpool the subpool remain */ - if (free) + * remain, give up any reservations mased on minimum size and + * free the subpool */ + if (free) { + if (spool->min_hpages != -1) + hugetlb_acct_memory(spool->hstate, + -spool->min_hpages); kfree(spool); + } } -struct hugepage_subpool *hugepage_new_subpool(long nr_blocks) +struct hugepage_subpool *hugepage_new_subpool(struct hstate *h, long max_hpages, + long min_hpages) { struct hugepage_subpool *spool; - spool = kmalloc(sizeof(*spool), GFP_KERNEL); + spool = kzalloc(sizeof(*spool), GFP_KERNEL); if (!spool) return NULL; spin_lock_init(&spool->lock); spool->count = 1; - spool->max_hpages = nr_blocks; - spool->used_hpages = 0; + spool->max_hpages = max_hpages; + spool->hstate = h; + spool->min_hpages = min_hpages; + + if (min_hpages != -1 && hugetlb_acct_memory(h, min_hpages)) { + kfree(spool); + return NULL; + } + spool->rsv_hpages = min_hpages; return spool; } @@ -97,36 +113,89 @@ void hugepage_put_subpool(struct hugepage_subpool *spool) unlock_or_release_subpool(spool); } -static int hugepage_subpool_get_pages(struct hugepage_subpool *spool, +/* + * Subpool accounting for allocating and reserving pages. + * Return -ENOMEM if there are not enough resources to satisfy the + * the request. Otherwise, return the number of pages by which the + * global pools must be adjusted (upward). The returned value may + * only be different than the passed value (delta) in the case where + * a subpool minimum size must be manitained. + */ +static long hugepage_subpool_get_pages(struct hugepage_subpool *spool, long delta) { - int ret = 0; + long ret = delta; if (!spool) - return 0; + return ret; spin_lock(&spool->lock); - if ((spool->used_hpages + delta) <= spool->max_hpages) { - spool->used_hpages += delta; - } else { - ret = -ENOMEM; + + if (spool->max_hpages != -1) { /* maximum size accounting */ + if ((spool->used_hpages + delta) <= spool->max_hpages) + spool->used_hpages += delta; + else { + ret = -ENOMEM; + goto unlock_ret; + } } - spin_unlock(&spool->lock); + if (spool->min_hpages != -1) { /* minimum size accounting */ + if (delta > spool->rsv_hpages) { + /* + * Asking for more reserves than those already taken on + * behalf of subpool. Return difference. + */ + ret = delta - spool->rsv_hpages; + spool->rsv_hpages = 0; + } else { + ret = 0; /* reserves already accounted for */ + spool->rsv_hpages -= delta; + } + } + +unlock_ret: + spin_unlock(&spool->lock); return ret; } -static void hugepage_subpool_put_pages(struct hugepage_subpool *spool, +/* + * Subpool accounting for freeing and unreserving pages. + * Return the number of global page reservations that must be dropped. + * The return value may only be different than the passed value (delta) + * in the case where a subpool minimum size must be maintained. + */ +static long hugepage_subpool_put_pages(struct hugepage_subpool *spool, long delta) { + long ret = delta; + if (!spool) - return; + return delta; spin_lock(&spool->lock); - spool->used_hpages -= delta; - /* If hugetlbfs_put_super couldn't free spool due to - * an outstanding quota reference, free it now. */ + + if (spool->max_hpages != -1) /* maximum size accounting */ + spool->used_hpages -= delta; + + if (spool->min_hpages != -1) { /* minimum size accounting */ + if (spool->rsv_hpages + delta <= spool->min_hpages) + ret = 0; + else + ret = spool->rsv_hpages + delta - spool->min_hpages; + + spool->rsv_hpages += delta; + if (spool->rsv_hpages > spool->min_hpages) + spool->rsv_hpages = spool->min_hpages; + } + + /* + * If hugetlbfs_put_super couldn't free spool due to an outstanding + * quota reference, free it now. + */ unlock_or_release_subpool(spool); + + return ret; } static inline struct hugepage_subpool *subpool_inode(struct inode *inode) @@ -855,6 +924,31 @@ struct hstate *size_to_hstate(unsigned long size) return NULL; } +/* + * Test to determine whether the hugepage is "active/in-use" (i.e. being linked + * to hstate->hugepage_activelist.) + * + * This function can be called for tail pages, but never returns true for them. + */ +bool page_huge_active(struct page *page) +{ + VM_BUG_ON_PAGE(!PageHuge(page), page); + return PageHead(page) && PagePrivate(&page[1]); +} + +/* never called for tail page */ +static void set_page_huge_active(struct page *page) +{ + VM_BUG_ON_PAGE(!PageHeadHuge(page), page); + SetPagePrivate(&page[1]); +} + +static void clear_page_huge_active(struct page *page) +{ + VM_BUG_ON_PAGE(!PageHeadHuge(page), page); + ClearPagePrivate(&page[1]); +} + void free_huge_page(struct page *page) { /* @@ -874,7 +968,16 @@ void free_huge_page(struct page *page) restore_reserve = PagePrivate(page); ClearPagePrivate(page); + /* + * A return code of zero implies that the subpool will be under its + * minimum size if the reservation is not restored after page is free. + * Therefore, force restore_reserve operation. + */ + if (hugepage_subpool_put_pages(spool, 1) == 0) + restore_reserve = true; + spin_lock(&hugetlb_lock); + clear_page_huge_active(page); hugetlb_cgroup_uncharge_page(hstate_index(h), pages_per_huge_page(h), page); if (restore_reserve) @@ -891,7 +994,6 @@ void free_huge_page(struct page *page) enqueue_huge_page(h, page); } spin_unlock(&hugetlb_lock); - hugepage_subpool_put_pages(spool, 1); } static void prep_new_huge_page(struct hstate *h, struct page *page, int nid) @@ -917,7 +1019,6 @@ static void prep_compound_gigantic_page(struct page *page, unsigned long order) __SetPageHead(page); __ClearPageReserved(page); for (i = 1; i < nr_pages; i++, p = mem_map_next(p, page, i)) { - __SetPageTail(p); /* * For gigantic hugepages allocated through bootmem at * boot, it's safer to be consistent with the not-gigantic @@ -933,6 +1034,9 @@ static void prep_compound_gigantic_page(struct page *page, unsigned long order) __ClearPageReserved(p); set_page_count(p, 0); p->first_page = page; + /* Make sure p->first_page is always valid for PageTail() */ + smp_wmb(); + __SetPageTail(p); } } @@ -1384,7 +1488,7 @@ static struct page *alloc_huge_page(struct vm_area_struct *vma, if (chg < 0) return ERR_PTR(-ENOMEM); if (chg || avoid_reserve) - if (hugepage_subpool_get_pages(spool, 1)) + if (hugepage_subpool_get_pages(spool, 1) < 0) return ERR_PTR(-ENOSPC); ret = hugetlb_cgroup_charge_cgroup(idx, pages_per_huge_page(h), &h_cg); @@ -2452,6 +2556,7 @@ static void hugetlb_vm_op_close(struct vm_area_struct *vma) struct resv_map *resv = vma_resv_map(vma); struct hugepage_subpool *spool = subpool_vma(vma); unsigned long reserve, start, end; + long gbl_reserve; if (!resv || !is_vma_resv_set(vma, HPAGE_RESV_OWNER)) return; @@ -2464,8 +2569,12 @@ static void hugetlb_vm_op_close(struct vm_area_struct *vma) kref_put(&resv->refs, resv_map_release); if (reserve) { - hugetlb_acct_memory(h, -reserve); - hugepage_subpool_put_pages(spool, reserve); + /* + * Decrement reserve counts. The global reserve count may be + * adjusted if the subpool has a minimum size. + */ + gbl_reserve = hugepage_subpool_put_pages(spool, reserve); + hugetlb_acct_memory(h, -gbl_reserve); } } @@ -2889,6 +2998,7 @@ retry_avoidcopy: copy_user_huge_page(new_page, old_page, address, vma, pages_per_huge_page(h)); __SetPageUptodate(new_page); + set_page_huge_active(new_page); mmun_start = address & huge_page_mask(h); mmun_end = mmun_start + huge_page_size(h); @@ -3001,6 +3111,7 @@ retry: } clear_huge_page(page, address, pages_per_huge_page(h)); __SetPageUptodate(page); + set_page_huge_active(page); if (vma->vm_flags & VM_MAYSHARE) { int err; @@ -3276,6 +3387,15 @@ long follow_hugetlb_page(struct mm_struct *mm, struct vm_area_struct *vma, struct page *page; /* + * If we have a pending SIGKILL, don't keep faulting pages and + * potentially allocating memory. + */ + if (unlikely(fatal_signal_pending(current))) { + remainder = 0; + break; + } + + /* * Some archs (sparc64, sh*) have multiple pte_ts to * each hugepage. We have to make sure we get the * first, for the page indexing below to work. @@ -3436,6 +3556,7 @@ int hugetlb_reserve_pages(struct inode *inode, struct hstate *h = hstate_inode(inode); struct hugepage_subpool *spool = subpool_inode(inode); struct resv_map *resv_map; + long gbl_reserve; /* * Only apply hugepage reservation if asked. At fault time, an @@ -3472,8 +3593,13 @@ int hugetlb_reserve_pages(struct inode *inode, goto out_err; } - /* There must be enough pages in the subpool for the mapping */ - if (hugepage_subpool_get_pages(spool, chg)) { + /* + * There must be enough pages in the subpool for the mapping. If + * the subpool has a minimum size, there may be some global + * reservations already in place (gbl_reserve). + */ + gbl_reserve = hugepage_subpool_get_pages(spool, chg); + if (gbl_reserve < 0) { ret = -ENOSPC; goto out_err; } @@ -3482,9 +3608,10 @@ int hugetlb_reserve_pages(struct inode *inode, * Check enough hugepages are available for the reservation. * Hand the pages back to the subpool if there are not */ - ret = hugetlb_acct_memory(h, chg); + ret = hugetlb_acct_memory(h, gbl_reserve); if (ret < 0) { - hugepage_subpool_put_pages(spool, chg); + /* put back original number of pages, chg */ + (void)hugepage_subpool_put_pages(spool, chg); goto out_err; } @@ -3514,6 +3641,7 @@ void hugetlb_unreserve_pages(struct inode *inode, long offset, long freed) struct resv_map *resv_map = inode_resv_map(inode); long chg = 0; struct hugepage_subpool *spool = subpool_inode(inode); + long gbl_reserve; if (resv_map) chg = region_truncate(resv_map, offset); @@ -3521,8 +3649,12 @@ void hugetlb_unreserve_pages(struct inode *inode, long offset, long freed) inode->i_blocks -= (blocks_per_huge_page(h) * freed); spin_unlock(&inode->i_lock); - hugepage_subpool_put_pages(spool, (chg - freed)); - hugetlb_acct_memory(h, -(chg - freed)); + /* + * If the subpool has a minimum size, the number of global + * reservations to be released may be adjusted. + */ + gbl_reserve = hugepage_subpool_put_pages(spool, (chg - freed)); + hugetlb_acct_memory(h, -gbl_reserve); } #ifdef CONFIG_ARCH_WANT_HUGE_PMD_SHARE @@ -3733,8 +3865,7 @@ retry: if (!pmd_huge(*pmd)) goto out; if (pmd_present(*pmd)) { - page = pte_page(*(pte_t *)pmd) + - ((address & ~PMD_MASK) >> PAGE_SHIFT); + page = pmd_page(*pmd) + ((address & ~PMD_MASK) >> PAGE_SHIFT); if (flags & FOLL_GET) get_page(page); } else { @@ -3765,20 +3896,6 @@ follow_huge_pud(struct mm_struct *mm, unsigned long address, #ifdef CONFIG_MEMORY_FAILURE -/* Should be called in hugetlb_lock */ -static int is_hugepage_on_freelist(struct page *hpage) -{ - struct page *page; - struct page *tmp; - struct hstate *h = page_hstate(hpage); - int nid = page_to_nid(hpage); - - list_for_each_entry_safe(page, tmp, &h->hugepage_freelists[nid], lru) - if (page == hpage) - return 1; - return 0; -} - /* * This function is called from memory failure code. * Assume the caller holds page lock of the head page. @@ -3790,7 +3907,11 @@ int dequeue_hwpoisoned_huge_page(struct page *hpage) int ret = -EBUSY; spin_lock(&hugetlb_lock); - if (is_hugepage_on_freelist(hpage)) { + /* + * Just checking !page_huge_active is not enough, because that could be + * an isolated/hwpoisoned hugepage (which have >0 refcount). + */ + if (!page_huge_active(hpage) && !page_count(hpage)) { /* * Hwpoisoned hugepage isn't linked to activelist or freelist, * but dangling hpage->lru can trigger list-debug warnings @@ -3810,42 +3931,27 @@ int dequeue_hwpoisoned_huge_page(struct page *hpage) bool isolate_huge_page(struct page *page, struct list_head *list) { + bool ret = true; + VM_BUG_ON_PAGE(!PageHead(page), page); - if (!get_page_unless_zero(page)) - return false; spin_lock(&hugetlb_lock); + if (!page_huge_active(page) || !get_page_unless_zero(page)) { + ret = false; + goto unlock; + } + clear_page_huge_active(page); list_move_tail(&page->lru, list); +unlock: spin_unlock(&hugetlb_lock); - return true; + return ret; } void putback_active_hugepage(struct page *page) { VM_BUG_ON_PAGE(!PageHead(page), page); spin_lock(&hugetlb_lock); + set_page_huge_active(page); list_move_tail(&page->lru, &(page_hstate(page))->hugepage_activelist); spin_unlock(&hugetlb_lock); put_page(page); } - -bool is_hugepage_active(struct page *page) -{ - VM_BUG_ON_PAGE(!PageHuge(page), page); - /* - * This function can be called for a tail page because the caller, - * scan_movable_pages, scans through a given pfn-range which typically - * covers one memory block. In systems using gigantic hugepage (1GB - * for x86_64,) a hugepage is larger than a memory block, and we don't - * support migrating such large hugepages for now, so return false - * when called for tail pages. - */ - if (PageTail(page)) - return false; - /* - * Refcount of a hwpoisoned hugepages is 1, but they are not active, - * so we should return false for them. - */ - if (unlikely(PageHWPoison(page))) - return false; - return page_count(page) > 0; -} diff --git a/mm/internal.h b/mm/internal.h index a96da5b0029d..a25e359a4039 100644 --- a/mm/internal.h +++ b/mm/internal.h @@ -200,6 +200,8 @@ isolate_freepages_range(struct compact_control *cc, unsigned long isolate_migratepages_range(struct compact_control *cc, unsigned long low_pfn, unsigned long end_pfn); +int find_suitable_fallback(struct free_area *area, unsigned int order, + int migratetype, bool only_stealable, bool *can_steal); #endif @@ -222,13 +224,13 @@ static inline unsigned long page_order(struct page *page) * PageBuddy() should be checked first by the caller to minimize race window, * and invalid values must be handled gracefully. * - * ACCESS_ONCE is used so that if the caller assigns the result into a local + * READ_ONCE is used so that if the caller assigns the result into a local * variable and e.g. tests it for valid range before using, the compiler cannot * decide to remove the variable and inline the page_private(page) multiple * times, potentially observing different values in the tests and the actual * use of the result. */ -#define page_order_unsafe(page) ACCESS_ONCE(page_private(page)) +#define page_order_unsafe(page) READ_ONCE(page_private(page)) static inline bool is_cow_mapping(vm_flags_t flags) { @@ -240,7 +242,7 @@ void __vma_link_list(struct mm_struct *mm, struct vm_area_struct *vma, struct vm_area_struct *prev, struct rb_node *rb_parent); #ifdef CONFIG_MMU -extern long __mlock_vma_pages_range(struct vm_area_struct *vma, +extern long populate_vma_page_range(struct vm_area_struct *vma, unsigned long start, unsigned long end, int *nonblocking); extern void munlock_vma_pages_range(struct vm_area_struct *vma, unsigned long start, unsigned long end); diff --git a/mm/iov_iter.c b/mm/iov_iter.c deleted file mode 100644 index 827732047da1..000000000000 --- a/mm/iov_iter.c +++ /dev/null @@ -1,753 +0,0 @@ -#include <linux/export.h> -#include <linux/uio.h> -#include <linux/pagemap.h> -#include <linux/slab.h> -#include <linux/vmalloc.h> -#include <net/checksum.h> - -#define iterate_iovec(i, n, __v, __p, skip, STEP) { \ - size_t left; \ - size_t wanted = n; \ - __p = i->iov; \ - __v.iov_len = min(n, __p->iov_len - skip); \ - if (likely(__v.iov_len)) { \ - __v.iov_base = __p->iov_base + skip; \ - left = (STEP); \ - __v.iov_len -= left; \ - skip += __v.iov_len; \ - n -= __v.iov_len; \ - } else { \ - left = 0; \ - } \ - while (unlikely(!left && n)) { \ - __p++; \ - __v.iov_len = min(n, __p->iov_len); \ - if (unlikely(!__v.iov_len)) \ - continue; \ - __v.iov_base = __p->iov_base; \ - left = (STEP); \ - __v.iov_len -= left; \ - skip = __v.iov_len; \ - n -= __v.iov_len; \ - } \ - n = wanted - n; \ -} - -#define iterate_kvec(i, n, __v, __p, skip, STEP) { \ - size_t wanted = n; \ - __p = i->kvec; \ - __v.iov_len = min(n, __p->iov_len - skip); \ - if (likely(__v.iov_len)) { \ - __v.iov_base = __p->iov_base + skip; \ - (void)(STEP); \ - skip += __v.iov_len; \ - n -= __v.iov_len; \ - } \ - while (unlikely(n)) { \ - __p++; \ - __v.iov_len = min(n, __p->iov_len); \ - if (unlikely(!__v.iov_len)) \ - continue; \ - __v.iov_base = __p->iov_base; \ - (void)(STEP); \ - skip = __v.iov_len; \ - n -= __v.iov_len; \ - } \ - n = wanted; \ -} - -#define iterate_bvec(i, n, __v, __p, skip, STEP) { \ - size_t wanted = n; \ - __p = i->bvec; \ - __v.bv_len = min_t(size_t, n, __p->bv_len - skip); \ - if (likely(__v.bv_len)) { \ - __v.bv_page = __p->bv_page; \ - __v.bv_offset = __p->bv_offset + skip; \ - (void)(STEP); \ - skip += __v.bv_len; \ - n -= __v.bv_len; \ - } \ - while (unlikely(n)) { \ - __p++; \ - __v.bv_len = min_t(size_t, n, __p->bv_len); \ - if (unlikely(!__v.bv_len)) \ - continue; \ - __v.bv_page = __p->bv_page; \ - __v.bv_offset = __p->bv_offset; \ - (void)(STEP); \ - skip = __v.bv_len; \ - n -= __v.bv_len; \ - } \ - n = wanted; \ -} - -#define iterate_all_kinds(i, n, v, I, B, K) { \ - size_t skip = i->iov_offset; \ - if (unlikely(i->type & ITER_BVEC)) { \ - const struct bio_vec *bvec; \ - struct bio_vec v; \ - iterate_bvec(i, n, v, bvec, skip, (B)) \ - } else if (unlikely(i->type & ITER_KVEC)) { \ - const struct kvec *kvec; \ - struct kvec v; \ - iterate_kvec(i, n, v, kvec, skip, (K)) \ - } else { \ - const struct iovec *iov; \ - struct iovec v; \ - iterate_iovec(i, n, v, iov, skip, (I)) \ - } \ -} - -#define iterate_and_advance(i, n, v, I, B, K) { \ - size_t skip = i->iov_offset; \ - if (unlikely(i->type & ITER_BVEC)) { \ - const struct bio_vec *bvec; \ - struct bio_vec v; \ - iterate_bvec(i, n, v, bvec, skip, (B)) \ - if (skip == bvec->bv_len) { \ - bvec++; \ - skip = 0; \ - } \ - i->nr_segs -= bvec - i->bvec; \ - i->bvec = bvec; \ - } else if (unlikely(i->type & ITER_KVEC)) { \ - const struct kvec *kvec; \ - struct kvec v; \ - iterate_kvec(i, n, v, kvec, skip, (K)) \ - if (skip == kvec->iov_len) { \ - kvec++; \ - skip = 0; \ - } \ - i->nr_segs -= kvec - i->kvec; \ - i->kvec = kvec; \ - } else { \ - const struct iovec *iov; \ - struct iovec v; \ - iterate_iovec(i, n, v, iov, skip, (I)) \ - if (skip == iov->iov_len) { \ - iov++; \ - skip = 0; \ - } \ - i->nr_segs -= iov - i->iov; \ - i->iov = iov; \ - } \ - i->count -= n; \ - i->iov_offset = skip; \ -} - -static size_t copy_page_to_iter_iovec(struct page *page, size_t offset, size_t bytes, - struct iov_iter *i) -{ - size_t skip, copy, left, wanted; - const struct iovec *iov; - char __user *buf; - void *kaddr, *from; - - if (unlikely(bytes > i->count)) - bytes = i->count; - - if (unlikely(!bytes)) - return 0; - - wanted = bytes; - iov = i->iov; - skip = i->iov_offset; - buf = iov->iov_base + skip; - copy = min(bytes, iov->iov_len - skip); - - if (!fault_in_pages_writeable(buf, copy)) { - kaddr = kmap_atomic(page); - from = kaddr + offset; - - /* first chunk, usually the only one */ - left = __copy_to_user_inatomic(buf, from, copy); - copy -= left; - skip += copy; - from += copy; - bytes -= copy; - - while (unlikely(!left && bytes)) { - iov++; - buf = iov->iov_base; - copy = min(bytes, iov->iov_len); - left = __copy_to_user_inatomic(buf, from, copy); - copy -= left; - skip = copy; - from += copy; - bytes -= copy; - } - if (likely(!bytes)) { - kunmap_atomic(kaddr); - goto done; - } - offset = from - kaddr; - buf += copy; - kunmap_atomic(kaddr); - copy = min(bytes, iov->iov_len - skip); - } - /* Too bad - revert to non-atomic kmap */ - kaddr = kmap(page); - from = kaddr + offset; - left = __copy_to_user(buf, from, copy); - copy -= left; - skip += copy; - from += copy; - bytes -= copy; - while (unlikely(!left && bytes)) { - iov++; - buf = iov->iov_base; - copy = min(bytes, iov->iov_len); - left = __copy_to_user(buf, from, copy); - copy -= left; - skip = copy; - from += copy; - bytes -= copy; - } - kunmap(page); -done: - if (skip == iov->iov_len) { - iov++; - skip = 0; - } - i->count -= wanted - bytes; - i->nr_segs -= iov - i->iov; - i->iov = iov; - i->iov_offset = skip; - return wanted - bytes; -} - -static size_t copy_page_from_iter_iovec(struct page *page, size_t offset, size_t bytes, - struct iov_iter *i) -{ - size_t skip, copy, left, wanted; - const struct iovec *iov; - char __user *buf; - void *kaddr, *to; - - if (unlikely(bytes > i->count)) - bytes = i->count; - - if (unlikely(!bytes)) - return 0; - - wanted = bytes; - iov = i->iov; - skip = i->iov_offset; - buf = iov->iov_base + skip; - copy = min(bytes, iov->iov_len - skip); - - if (!fault_in_pages_readable(buf, copy)) { - kaddr = kmap_atomic(page); - to = kaddr + offset; - - /* first chunk, usually the only one */ - left = __copy_from_user_inatomic(to, buf, copy); - copy -= left; - skip += copy; - to += copy; - bytes -= copy; - - while (unlikely(!left && bytes)) { - iov++; - buf = iov->iov_base; - copy = min(bytes, iov->iov_len); - left = __copy_from_user_inatomic(to, buf, copy); - copy -= left; - skip = copy; - to += copy; - bytes -= copy; - } - if (likely(!bytes)) { - kunmap_atomic(kaddr); - goto done; - } - offset = to - kaddr; - buf += copy; - kunmap_atomic(kaddr); - copy = min(bytes, iov->iov_len - skip); - } - /* Too bad - revert to non-atomic kmap */ - kaddr = kmap(page); - to = kaddr + offset; - left = __copy_from_user(to, buf, copy); - copy -= left; - skip += copy; - to += copy; - bytes -= copy; - while (unlikely(!left && bytes)) { - iov++; - buf = iov->iov_base; - copy = min(bytes, iov->iov_len); - left = __copy_from_user(to, buf, copy); - copy -= left; - skip = copy; - to += copy; - bytes -= copy; - } - kunmap(page); -done: - if (skip == iov->iov_len) { - iov++; - skip = 0; - } - i->count -= wanted - bytes; - i->nr_segs -= iov - i->iov; - i->iov = iov; - i->iov_offset = skip; - return wanted - bytes; -} - -/* - * Fault in the first iovec of the given iov_iter, to a maximum length - * of bytes. Returns 0 on success, or non-zero if the memory could not be - * accessed (ie. because it is an invalid address). - * - * writev-intensive code may want this to prefault several iovecs -- that - * would be possible (callers must not rely on the fact that _only_ the - * first iovec will be faulted with the current implementation). - */ -int iov_iter_fault_in_readable(struct iov_iter *i, size_t bytes) -{ - if (!(i->type & (ITER_BVEC|ITER_KVEC))) { - char __user *buf = i->iov->iov_base + i->iov_offset; - bytes = min(bytes, i->iov->iov_len - i->iov_offset); - return fault_in_pages_readable(buf, bytes); - } - return 0; -} -EXPORT_SYMBOL(iov_iter_fault_in_readable); - -void iov_iter_init(struct iov_iter *i, int direction, - const struct iovec *iov, unsigned long nr_segs, - size_t count) -{ - /* It will get better. Eventually... */ - if (segment_eq(get_fs(), KERNEL_DS)) { - direction |= ITER_KVEC; - i->type = direction; - i->kvec = (struct kvec *)iov; - } else { - i->type = direction; - i->iov = iov; - } - i->nr_segs = nr_segs; - i->iov_offset = 0; - i->count = count; -} -EXPORT_SYMBOL(iov_iter_init); - -static void memcpy_from_page(char *to, struct page *page, size_t offset, size_t len) -{ - char *from = kmap_atomic(page); - memcpy(to, from + offset, len); - kunmap_atomic(from); -} - -static void memcpy_to_page(struct page *page, size_t offset, char *from, size_t len) -{ - char *to = kmap_atomic(page); - memcpy(to + offset, from, len); - kunmap_atomic(to); -} - -static void memzero_page(struct page *page, size_t offset, size_t len) -{ - char *addr = kmap_atomic(page); - memset(addr + offset, 0, len); - kunmap_atomic(addr); -} - -size_t copy_to_iter(void *addr, size_t bytes, struct iov_iter *i) -{ - char *from = addr; - if (unlikely(bytes > i->count)) - bytes = i->count; - - if (unlikely(!bytes)) - return 0; - - iterate_and_advance(i, bytes, v, - __copy_to_user(v.iov_base, (from += v.iov_len) - v.iov_len, - v.iov_len), - memcpy_to_page(v.bv_page, v.bv_offset, - (from += v.bv_len) - v.bv_len, v.bv_len), - memcpy(v.iov_base, (from += v.iov_len) - v.iov_len, v.iov_len) - ) - - return bytes; -} -EXPORT_SYMBOL(copy_to_iter); - -size_t copy_from_iter(void *addr, size_t bytes, struct iov_iter *i) -{ - char *to = addr; - if (unlikely(bytes > i->count)) - bytes = i->count; - - if (unlikely(!bytes)) - return 0; - - iterate_and_advance(i, bytes, v, - __copy_from_user((to += v.iov_len) - v.iov_len, v.iov_base, - v.iov_len), - memcpy_from_page((to += v.bv_len) - v.bv_len, v.bv_page, - v.bv_offset, v.bv_len), - memcpy((to += v.iov_len) - v.iov_len, v.iov_base, v.iov_len) - ) - - return bytes; -} -EXPORT_SYMBOL(copy_from_iter); - -size_t copy_from_iter_nocache(void *addr, size_t bytes, struct iov_iter *i) -{ - char *to = addr; - if (unlikely(bytes > i->count)) - bytes = i->count; - - if (unlikely(!bytes)) - return 0; - - iterate_and_advance(i, bytes, v, - __copy_from_user_nocache((to += v.iov_len) - v.iov_len, - v.iov_base, v.iov_len), - memcpy_from_page((to += v.bv_len) - v.bv_len, v.bv_page, - v.bv_offset, v.bv_len), - memcpy((to += v.iov_len) - v.iov_len, v.iov_base, v.iov_len) - ) - - return bytes; -} -EXPORT_SYMBOL(copy_from_iter_nocache); - -size_t copy_page_to_iter(struct page *page, size_t offset, size_t bytes, - struct iov_iter *i) -{ - if (i->type & (ITER_BVEC|ITER_KVEC)) { - void *kaddr = kmap_atomic(page); - size_t wanted = copy_to_iter(kaddr + offset, bytes, i); - kunmap_atomic(kaddr); - return wanted; - } else - return copy_page_to_iter_iovec(page, offset, bytes, i); -} -EXPORT_SYMBOL(copy_page_to_iter); - -size_t copy_page_from_iter(struct page *page, size_t offset, size_t bytes, - struct iov_iter *i) -{ - if (i->type & (ITER_BVEC|ITER_KVEC)) { - void *kaddr = kmap_atomic(page); - size_t wanted = copy_from_iter(kaddr + offset, bytes, i); - kunmap_atomic(kaddr); - return wanted; - } else - return copy_page_from_iter_iovec(page, offset, bytes, i); -} -EXPORT_SYMBOL(copy_page_from_iter); - -size_t iov_iter_zero(size_t bytes, struct iov_iter *i) -{ - if (unlikely(bytes > i->count)) - bytes = i->count; - - if (unlikely(!bytes)) - return 0; - - iterate_and_advance(i, bytes, v, - __clear_user(v.iov_base, v.iov_len), - memzero_page(v.bv_page, v.bv_offset, v.bv_len), - memset(v.iov_base, 0, v.iov_len) - ) - - return bytes; -} -EXPORT_SYMBOL(iov_iter_zero); - -size_t iov_iter_copy_from_user_atomic(struct page *page, - struct iov_iter *i, unsigned long offset, size_t bytes) -{ - char *kaddr = kmap_atomic(page), *p = kaddr + offset; - iterate_all_kinds(i, bytes, v, - __copy_from_user_inatomic((p += v.iov_len) - v.iov_len, - v.iov_base, v.iov_len), - memcpy_from_page((p += v.bv_len) - v.bv_len, v.bv_page, - v.bv_offset, v.bv_len), - memcpy((p += v.iov_len) - v.iov_len, v.iov_base, v.iov_len) - ) - kunmap_atomic(kaddr); - return bytes; -} -EXPORT_SYMBOL(iov_iter_copy_from_user_atomic); - -void iov_iter_advance(struct iov_iter *i, size_t size) -{ - iterate_and_advance(i, size, v, 0, 0, 0) -} -EXPORT_SYMBOL(iov_iter_advance); - -/* - * Return the count of just the current iov_iter segment. - */ -size_t iov_iter_single_seg_count(const struct iov_iter *i) -{ - if (i->nr_segs == 1) - return i->count; - else if (i->type & ITER_BVEC) - return min(i->count, i->bvec->bv_len - i->iov_offset); - else - return min(i->count, i->iov->iov_len - i->iov_offset); -} -EXPORT_SYMBOL(iov_iter_single_seg_count); - -void iov_iter_kvec(struct iov_iter *i, int direction, - const struct kvec *kvec, unsigned long nr_segs, - size_t count) -{ - BUG_ON(!(direction & ITER_KVEC)); - i->type = direction; - i->kvec = kvec; - i->nr_segs = nr_segs; - i->iov_offset = 0; - i->count = count; -} -EXPORT_SYMBOL(iov_iter_kvec); - -void iov_iter_bvec(struct iov_iter *i, int direction, - const struct bio_vec *bvec, unsigned long nr_segs, - size_t count) -{ - BUG_ON(!(direction & ITER_BVEC)); - i->type = direction; - i->bvec = bvec; - i->nr_segs = nr_segs; - i->iov_offset = 0; - i->count = count; -} -EXPORT_SYMBOL(iov_iter_bvec); - -unsigned long iov_iter_alignment(const struct iov_iter *i) -{ - unsigned long res = 0; - size_t size = i->count; - - if (!size) - return 0; - - iterate_all_kinds(i, size, v, - (res |= (unsigned long)v.iov_base | v.iov_len, 0), - res |= v.bv_offset | v.bv_len, - res |= (unsigned long)v.iov_base | v.iov_len - ) - return res; -} -EXPORT_SYMBOL(iov_iter_alignment); - -ssize_t iov_iter_get_pages(struct iov_iter *i, - struct page **pages, size_t maxsize, unsigned maxpages, - size_t *start) -{ - if (maxsize > i->count) - maxsize = i->count; - - if (!maxsize) - return 0; - - iterate_all_kinds(i, maxsize, v, ({ - unsigned long addr = (unsigned long)v.iov_base; - size_t len = v.iov_len + (*start = addr & (PAGE_SIZE - 1)); - int n; - int res; - - if (len > maxpages * PAGE_SIZE) - len = maxpages * PAGE_SIZE; - addr &= ~(PAGE_SIZE - 1); - n = DIV_ROUND_UP(len, PAGE_SIZE); - res = get_user_pages_fast(addr, n, (i->type & WRITE) != WRITE, pages); - if (unlikely(res < 0)) - return res; - return (res == n ? len : res * PAGE_SIZE) - *start; - 0;}),({ - /* can't be more than PAGE_SIZE */ - *start = v.bv_offset; - get_page(*pages = v.bv_page); - return v.bv_len; - }),({ - return -EFAULT; - }) - ) - return 0; -} -EXPORT_SYMBOL(iov_iter_get_pages); - -static struct page **get_pages_array(size_t n) -{ - struct page **p = kmalloc(n * sizeof(struct page *), GFP_KERNEL); - if (!p) - p = vmalloc(n * sizeof(struct page *)); - return p; -} - -ssize_t iov_iter_get_pages_alloc(struct iov_iter *i, - struct page ***pages, size_t maxsize, - size_t *start) -{ - struct page **p; - - if (maxsize > i->count) - maxsize = i->count; - - if (!maxsize) - return 0; - - iterate_all_kinds(i, maxsize, v, ({ - unsigned long addr = (unsigned long)v.iov_base; - size_t len = v.iov_len + (*start = addr & (PAGE_SIZE - 1)); - int n; - int res; - - addr &= ~(PAGE_SIZE - 1); - n = DIV_ROUND_UP(len, PAGE_SIZE); - p = get_pages_array(n); - if (!p) - return -ENOMEM; - res = get_user_pages_fast(addr, n, (i->type & WRITE) != WRITE, p); - if (unlikely(res < 0)) { - kvfree(p); - return res; - } - *pages = p; - return (res == n ? len : res * PAGE_SIZE) - *start; - 0;}),({ - /* can't be more than PAGE_SIZE */ - *start = v.bv_offset; - *pages = p = get_pages_array(1); - if (!p) - return -ENOMEM; - get_page(*p = v.bv_page); - return v.bv_len; - }),({ - return -EFAULT; - }) - ) - return 0; -} -EXPORT_SYMBOL(iov_iter_get_pages_alloc); - -size_t csum_and_copy_from_iter(void *addr, size_t bytes, __wsum *csum, - struct iov_iter *i) -{ - char *to = addr; - __wsum sum, next; - size_t off = 0; - if (unlikely(bytes > i->count)) - bytes = i->count; - - if (unlikely(!bytes)) - return 0; - - sum = *csum; - iterate_and_advance(i, bytes, v, ({ - int err = 0; - next = csum_and_copy_from_user(v.iov_base, - (to += v.iov_len) - v.iov_len, - v.iov_len, 0, &err); - if (!err) { - sum = csum_block_add(sum, next, off); - off += v.iov_len; - } - err ? v.iov_len : 0; - }), ({ - char *p = kmap_atomic(v.bv_page); - next = csum_partial_copy_nocheck(p + v.bv_offset, - (to += v.bv_len) - v.bv_len, - v.bv_len, 0); - kunmap_atomic(p); - sum = csum_block_add(sum, next, off); - off += v.bv_len; - }),({ - next = csum_partial_copy_nocheck(v.iov_base, - (to += v.iov_len) - v.iov_len, - v.iov_len, 0); - sum = csum_block_add(sum, next, off); - off += v.iov_len; - }) - ) - *csum = sum; - return bytes; -} -EXPORT_SYMBOL(csum_and_copy_from_iter); - -size_t csum_and_copy_to_iter(void *addr, size_t bytes, __wsum *csum, - struct iov_iter *i) -{ - char *from = addr; - __wsum sum, next; - size_t off = 0; - if (unlikely(bytes > i->count)) - bytes = i->count; - - if (unlikely(!bytes)) - return 0; - - sum = *csum; - iterate_and_advance(i, bytes, v, ({ - int err = 0; - next = csum_and_copy_to_user((from += v.iov_len) - v.iov_len, - v.iov_base, - v.iov_len, 0, &err); - if (!err) { - sum = csum_block_add(sum, next, off); - off += v.iov_len; - } - err ? v.iov_len : 0; - }), ({ - char *p = kmap_atomic(v.bv_page); - next = csum_partial_copy_nocheck((from += v.bv_len) - v.bv_len, - p + v.bv_offset, - v.bv_len, 0); - kunmap_atomic(p); - sum = csum_block_add(sum, next, off); - off += v.bv_len; - }),({ - next = csum_partial_copy_nocheck((from += v.iov_len) - v.iov_len, - v.iov_base, - v.iov_len, 0); - sum = csum_block_add(sum, next, off); - off += v.iov_len; - }) - ) - *csum = sum; - return bytes; -} -EXPORT_SYMBOL(csum_and_copy_to_iter); - -int iov_iter_npages(const struct iov_iter *i, int maxpages) -{ - size_t size = i->count; - int npages = 0; - - if (!size) - return 0; - - iterate_all_kinds(i, size, v, ({ - unsigned long p = (unsigned long)v.iov_base; - npages += DIV_ROUND_UP(p + v.iov_len, PAGE_SIZE) - - p / PAGE_SIZE; - if (npages >= maxpages) - return maxpages; - 0;}),({ - npages++; - if (npages >= maxpages) - return maxpages; - }),({ - unsigned long p = (unsigned long)v.iov_base; - npages += DIV_ROUND_UP(p + v.iov_len, PAGE_SIZE) - - p / PAGE_SIZE; - if (npages >= maxpages) - return maxpages; - }) - ) - return npages; -} -EXPORT_SYMBOL(iov_iter_npages); diff --git a/mm/kasan/kasan.c b/mm/kasan/kasan.c index 78fee632a7ee..6c513a63ea84 100644 --- a/mm/kasan/kasan.c +++ b/mm/kasan/kasan.c @@ -29,6 +29,7 @@ #include <linux/stacktrace.h> #include <linux/string.h> #include <linux/types.h> +#include <linux/vmalloc.h> #include <linux/kasan.h> #include "kasan.h" @@ -388,6 +389,19 @@ void kasan_krealloc(const void *object, size_t size) kasan_kmalloc(page->slab_cache, object, size); } +void kasan_kfree(void *ptr) +{ + struct page *page; + + page = virt_to_head_page(ptr); + + if (unlikely(!PageSlab(page))) + kasan_poison_shadow(ptr, PAGE_SIZE << compound_order(page), + KASAN_FREE_PAGE); + else + kasan_slab_free(page->slab_cache, ptr); +} + void kasan_kfree_large(const void *ptr) { struct page *page = virt_to_page(ptr); @@ -414,12 +428,19 @@ int kasan_module_alloc(void *addr, size_t size) GFP_KERNEL | __GFP_HIGHMEM | __GFP_ZERO, PAGE_KERNEL, VM_NO_GUARD, NUMA_NO_NODE, __builtin_return_address(0)); - return ret ? 0 : -ENOMEM; + + if (ret) { + find_vm_area(addr)->flags |= VM_KASAN; + return 0; + } + + return -ENOMEM; } -void kasan_module_free(void *addr) +void kasan_free_shadow(const struct vm_struct *vm) { - vfree(kasan_mem_to_shadow(addr)); + if (vm->flags & VM_KASAN) + vfree(kasan_mem_to_shadow(vm->addr)); } static void register_global(struct kasan_global *global) @@ -542,7 +542,7 @@ static struct page *get_ksm_page(struct stable_node *stable_node, bool lock_it) expected_mapping = (void *)stable_node + (PAGE_MAPPING_ANON | PAGE_MAPPING_KSM); again: - kpfn = ACCESS_ONCE(stable_node->kpfn); + kpfn = READ_ONCE(stable_node->kpfn); page = pfn_to_page(kpfn); /* @@ -551,7 +551,7 @@ again: * but on Alpha we need to be more careful. */ smp_read_barrier_depends(); - if (ACCESS_ONCE(page->mapping) != expected_mapping) + if (READ_ONCE(page->mapping) != expected_mapping) goto stale; /* @@ -577,14 +577,14 @@ again: cpu_relax(); } - if (ACCESS_ONCE(page->mapping) != expected_mapping) { + if (READ_ONCE(page->mapping) != expected_mapping) { put_page(page); goto stale; } if (lock_it) { lock_page(page); - if (ACCESS_ONCE(page->mapping) != expected_mapping) { + if (READ_ONCE(page->mapping) != expected_mapping) { unlock_page(page); put_page(page); goto stale; @@ -600,7 +600,7 @@ stale: * before checking whether node->kpfn has been changed. */ smp_rmb(); - if (ACCESS_ONCE(stable_node->kpfn) != kpfn) + if (READ_ONCE(stable_node->kpfn) != kpfn) goto again; remove_node_from_stable_tree(stable_node); return NULL; diff --git a/mm/memblock.c b/mm/memblock.c index 252b77bdf65e..9318b567ed79 100644 --- a/mm/memblock.c +++ b/mm/memblock.c @@ -580,10 +580,24 @@ int __init_memblock memblock_add_node(phys_addr_t base, phys_addr_t size, return memblock_add_range(&memblock.memory, base, size, nid, 0); } +static int __init_memblock memblock_add_region(phys_addr_t base, + phys_addr_t size, + int nid, + unsigned long flags) +{ + struct memblock_type *_rgn = &memblock.memory; + + memblock_dbg("memblock_add: [%#016llx-%#016llx] flags %#02lx %pF\n", + (unsigned long long)base, + (unsigned long long)base + size - 1, + flags, (void *)_RET_IP_); + + return memblock_add_range(_rgn, base, size, nid, flags); +} + int __init_memblock memblock_add(phys_addr_t base, phys_addr_t size) { - return memblock_add_range(&memblock.memory, base, size, - MAX_NUMNODES, 0); + return memblock_add_region(base, size, MAX_NUMNODES, 0); } /** @@ -699,14 +713,14 @@ static int __init_memblock memblock_reserve_region(phys_addr_t base, int nid, unsigned long flags) { - struct memblock_type *_rgn = &memblock.reserved; + struct memblock_type *type = &memblock.reserved; memblock_dbg("memblock_reserve: [%#016llx-%#016llx] flags %#02lx %pF\n", (unsigned long long)base, (unsigned long long)base + size - 1, flags, (void *)_RET_IP_); - return memblock_add_range(_rgn, base, size, nid, flags); + return memblock_add_range(type, base, size, nid, flags); } int __init_memblock memblock_reserve(phys_addr_t base, phys_addr_t size) diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 9fe07692eaad..14c2f2017e37 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -14,6 +14,12 @@ * Copyright (C) 2012 Parallels Inc. and Google Inc. * Authors: Glauber Costa and Suleiman Souhlal * + * Native page reclaim + * Charge lifetime sanitation + * Lockless page tracking & accounting + * Unified hierarchy configuration model + * Copyright (C) 2015 Red Hat, Inc., Johannes Weiner + * * This program is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License as published by * the Free Software Foundation; either version 2 of the License, or @@ -253,11 +259,6 @@ static void mem_cgroup_oom_notify(struct mem_cgroup *memcg); * page cache and RSS per cgroup. We would eventually like to provide * statistics based on the statistics developed by Rik Van Riel for clock-pro, * to help the administrator determine what knobs to tune. - * - * TODO: Add a water mark for the memory controller. Reclaim will begin when - * we hit the water mark. May be even add a low water mark, such that - * no reclaim occurs from a cgroup at it's low water mark, this is - * a feature that will be implemented much later in the future. */ struct mem_cgroup { struct cgroup_subsys_state css; @@ -454,6 +455,12 @@ static inline unsigned short mem_cgroup_id(struct mem_cgroup *memcg) return memcg->css.id; } +/* + * A helper function to get mem_cgroup from ID. must be called under + * rcu_read_lock(). The caller is responsible for calling + * css_tryget_online() if the mem_cgroup is used for charging. (dropping + * refcnt from swap can be called against removed memcg.) + */ static inline struct mem_cgroup *mem_cgroup_from_id(unsigned short id) { struct cgroup_subsys_state *css; @@ -667,7 +674,7 @@ static void mem_cgroup_remove_exceeded(struct mem_cgroup_per_zone *mz, static unsigned long soft_limit_excess(struct mem_cgroup *memcg) { unsigned long nr_pages = page_counter_read(&memcg->memory); - unsigned long soft_limit = ACCESS_ONCE(memcg->soft_limit); + unsigned long soft_limit = READ_ONCE(memcg->soft_limit); unsigned long excess = 0; if (nr_pages > soft_limit) @@ -1035,7 +1042,7 @@ struct mem_cgroup *mem_cgroup_iter(struct mem_cgroup *root, goto out_unlock; do { - pos = ACCESS_ONCE(iter->position); + pos = READ_ONCE(iter->position); /* * A racing update may change the position and * put the last reference, hence css_tryget(), @@ -1352,13 +1359,13 @@ static unsigned long mem_cgroup_margin(struct mem_cgroup *memcg) unsigned long limit; count = page_counter_read(&memcg->memory); - limit = ACCESS_ONCE(memcg->memory.limit); + limit = READ_ONCE(memcg->memory.limit); if (count < limit) margin = limit - count; if (do_swap_account) { count = page_counter_read(&memcg->memsw); - limit = ACCESS_ONCE(memcg->memsw.limit); + limit = READ_ONCE(memcg->memsw.limit); if (count <= limit) margin = min(margin, limit - count); } @@ -1436,15 +1443,17 @@ void mem_cgroup_print_oom_info(struct mem_cgroup *memcg, struct task_struct *p) struct mem_cgroup *iter; unsigned int i; - if (!p) - return; - mutex_lock(&oom_info_lock); rcu_read_lock(); - pr_info("Task in "); - pr_cont_cgroup_path(task_cgroup(p, memory_cgrp_id)); - pr_cont(" killed as a result of limit of "); + if (p) { + pr_info("Task in "); + pr_cont_cgroup_path(task_cgroup(p, memory_cgrp_id)); + pr_cont(" killed as a result of limit of "); + } else { + pr_info("Memory limit reached of cgroup "); + } + pr_cont_cgroup_path(memcg->css.cgroup); pr_cont("\n"); @@ -1531,7 +1540,7 @@ static void mem_cgroup_out_of_memory(struct mem_cgroup *memcg, gfp_t gfp_mask, return; } - check_panic_on_oom(CONSTRAINT_MEMCG, gfp_mask, order, NULL); + check_panic_on_oom(CONSTRAINT_MEMCG, gfp_mask, order, NULL, memcg); totalpages = mem_cgroup_get_limit(memcg) ? : 1; for_each_mem_cgroup_tree(iter, memcg) { struct css_task_iter it; @@ -2341,20 +2350,6 @@ static void cancel_charge(struct mem_cgroup *memcg, unsigned int nr_pages) } /* - * A helper function to get mem_cgroup from ID. must be called under - * rcu_read_lock(). The caller is responsible for calling - * css_tryget_online() if the mem_cgroup is used for charging. (dropping - * refcnt from swap can be called against removed memcg.) - */ -static struct mem_cgroup *mem_cgroup_lookup(unsigned short id) -{ - /* ID 0 is unused ID */ - if (!id) - return NULL; - return mem_cgroup_from_id(id); -} - -/* * try_get_mem_cgroup_from_page - look up page's memcg association * @page: the page * @@ -2380,7 +2375,7 @@ struct mem_cgroup *try_get_mem_cgroup_from_page(struct page *page) ent.val = page_private(page); id = lookup_swap_cgroup_id(ent); rcu_read_lock(); - memcg = mem_cgroup_lookup(id); + memcg = mem_cgroup_from_id(id); if (memcg && !css_tryget_online(&memcg->css)) memcg = NULL; rcu_read_unlock(); @@ -2642,7 +2637,7 @@ struct kmem_cache *__memcg_kmem_get_cache(struct kmem_cache *cachep) return cachep; memcg = get_mem_cgroup_from_mm(current->mm); - kmemcg_id = ACCESS_ONCE(memcg->kmemcg_id); + kmemcg_id = READ_ONCE(memcg->kmemcg_id); if (kmemcg_id < 0) goto out; @@ -2779,92 +2774,6 @@ void mem_cgroup_split_huge_fixup(struct page *head) } #endif /* CONFIG_TRANSPARENT_HUGEPAGE */ -/** - * mem_cgroup_move_account - move account of the page - * @page: the page - * @nr_pages: number of regular pages (>1 for huge pages) - * @from: mem_cgroup which the page is moved from. - * @to: mem_cgroup which the page is moved to. @from != @to. - * - * The caller must confirm following. - * - page is not on LRU (isolate_page() is useful.) - * - compound_lock is held when nr_pages > 1 - * - * This function doesn't do "charge" to new cgroup and doesn't do "uncharge" - * from old cgroup. - */ -static int mem_cgroup_move_account(struct page *page, - unsigned int nr_pages, - struct mem_cgroup *from, - struct mem_cgroup *to) -{ - unsigned long flags; - int ret; - - VM_BUG_ON(from == to); - VM_BUG_ON_PAGE(PageLRU(page), page); - /* - * The page is isolated from LRU. So, collapse function - * will not handle this page. But page splitting can happen. - * Do this check under compound_page_lock(). The caller should - * hold it. - */ - ret = -EBUSY; - if (nr_pages > 1 && !PageTransHuge(page)) - goto out; - - /* - * Prevent mem_cgroup_migrate() from looking at page->mem_cgroup - * of its source page while we change it: page migration takes - * both pages off the LRU, but page cache replacement doesn't. - */ - if (!trylock_page(page)) - goto out; - - ret = -EINVAL; - if (page->mem_cgroup != from) - goto out_unlock; - - spin_lock_irqsave(&from->move_lock, flags); - - if (!PageAnon(page) && page_mapped(page)) { - __this_cpu_sub(from->stat->count[MEM_CGROUP_STAT_FILE_MAPPED], - nr_pages); - __this_cpu_add(to->stat->count[MEM_CGROUP_STAT_FILE_MAPPED], - nr_pages); - } - - if (PageWriteback(page)) { - __this_cpu_sub(from->stat->count[MEM_CGROUP_STAT_WRITEBACK], - nr_pages); - __this_cpu_add(to->stat->count[MEM_CGROUP_STAT_WRITEBACK], - nr_pages); - } - - /* - * It is safe to change page->mem_cgroup here because the page - * is referenced, charged, and isolated - we can't race with - * uncharging, charging, migration, or LRU putback. - */ - - /* caller should have done css_get */ - page->mem_cgroup = to; - spin_unlock_irqrestore(&from->move_lock, flags); - - ret = 0; - - local_irq_disable(); - mem_cgroup_charge_statistics(to, page, nr_pages); - memcg_check_events(to, page); - mem_cgroup_charge_statistics(from, page, -nr_pages); - memcg_check_events(from, page); - local_irq_enable(); -out_unlock: - unlock_page(page); -out: - return ret; -} - #ifdef CONFIG_MEMCG_SWAP static void mem_cgroup_swap_statistics(struct mem_cgroup *memcg, bool charge) @@ -4816,6 +4725,92 @@ static struct page *mc_handle_file_pte(struct vm_area_struct *vma, return page; } +/** + * mem_cgroup_move_account - move account of the page + * @page: the page + * @nr_pages: number of regular pages (>1 for huge pages) + * @from: mem_cgroup which the page is moved from. + * @to: mem_cgroup which the page is moved to. @from != @to. + * + * The caller must confirm following. + * - page is not on LRU (isolate_page() is useful.) + * - compound_lock is held when nr_pages > 1 + * + * This function doesn't do "charge" to new cgroup and doesn't do "uncharge" + * from old cgroup. + */ +static int mem_cgroup_move_account(struct page *page, + unsigned int nr_pages, + struct mem_cgroup *from, + struct mem_cgroup *to) +{ + unsigned long flags; + int ret; + + VM_BUG_ON(from == to); + VM_BUG_ON_PAGE(PageLRU(page), page); + /* + * The page is isolated from LRU. So, collapse function + * will not handle this page. But page splitting can happen. + * Do this check under compound_page_lock(). The caller should + * hold it. + */ + ret = -EBUSY; + if (nr_pages > 1 && !PageTransHuge(page)) + goto out; + + /* + * Prevent mem_cgroup_migrate() from looking at page->mem_cgroup + * of its source page while we change it: page migration takes + * both pages off the LRU, but page cache replacement doesn't. + */ + if (!trylock_page(page)) + goto out; + + ret = -EINVAL; + if (page->mem_cgroup != from) + goto out_unlock; + + spin_lock_irqsave(&from->move_lock, flags); + + if (!PageAnon(page) && page_mapped(page)) { + __this_cpu_sub(from->stat->count[MEM_CGROUP_STAT_FILE_MAPPED], + nr_pages); + __this_cpu_add(to->stat->count[MEM_CGROUP_STAT_FILE_MAPPED], + nr_pages); + } + + if (PageWriteback(page)) { + __this_cpu_sub(from->stat->count[MEM_CGROUP_STAT_WRITEBACK], + nr_pages); + __this_cpu_add(to->stat->count[MEM_CGROUP_STAT_WRITEBACK], + nr_pages); + } + + /* + * It is safe to change page->mem_cgroup here because the page + * is referenced, charged, and isolated - we can't race with + * uncharging, charging, migration, or LRU putback. + */ + + /* caller should have done css_get */ + page->mem_cgroup = to; + spin_unlock_irqrestore(&from->move_lock, flags); + + ret = 0; + + local_irq_disable(); + mem_cgroup_charge_statistics(to, page, nr_pages); + memcg_check_events(to, page); + mem_cgroup_charge_statistics(from, page, -nr_pages); + memcg_check_events(from, page); + local_irq_enable(); +out_unlock: + unlock_page(page); +out: + return ret; +} + static enum mc_target_type get_mctgt_type(struct vm_area_struct *vma, unsigned long addr, pte_t ptent, union mc_target *target) { @@ -5012,7 +5007,7 @@ static int mem_cgroup_can_attach(struct cgroup_subsys_state *css, * tunable will only affect upcoming migrations, not the current one. * So we need to save it, and keep it going. */ - move_flags = ACCESS_ONCE(memcg->move_charge_at_immigrate); + move_flags = READ_ONCE(memcg->move_charge_at_immigrate); if (move_flags) { struct mm_struct *mm; struct mem_cgroup *from = mem_cgroup_from_task(p); @@ -5232,7 +5227,9 @@ static void mem_cgroup_bind(struct cgroup_subsys_state *root_css) * on for the root memcg is enough. */ if (cgroup_on_dfl(root_css->cgroup)) - mem_cgroup_from_css(root_css)->use_hierarchy = true; + root_mem_cgroup->use_hierarchy = true; + else + root_mem_cgroup->use_hierarchy = false; } static u64 memory_current_read(struct cgroup_subsys_state *css, @@ -5244,7 +5241,7 @@ static u64 memory_current_read(struct cgroup_subsys_state *css, static int memory_low_show(struct seq_file *m, void *v) { struct mem_cgroup *memcg = mem_cgroup_from_css(seq_css(m)); - unsigned long low = ACCESS_ONCE(memcg->low); + unsigned long low = READ_ONCE(memcg->low); if (low == PAGE_COUNTER_MAX) seq_puts(m, "max\n"); @@ -5274,7 +5271,7 @@ static ssize_t memory_low_write(struct kernfs_open_file *of, static int memory_high_show(struct seq_file *m, void *v) { struct mem_cgroup *memcg = mem_cgroup_from_css(seq_css(m)); - unsigned long high = ACCESS_ONCE(memcg->high); + unsigned long high = READ_ONCE(memcg->high); if (high == PAGE_COUNTER_MAX) seq_puts(m, "max\n"); @@ -5304,7 +5301,7 @@ static ssize_t memory_high_write(struct kernfs_open_file *of, static int memory_max_show(struct seq_file *m, void *v) { struct mem_cgroup *memcg = mem_cgroup_from_css(seq_css(m)); - unsigned long max = ACCESS_ONCE(memcg->memory.limit); + unsigned long max = READ_ONCE(memcg->memory.limit); if (max == PAGE_COUNTER_MAX) seq_puts(m, "max\n"); @@ -5859,7 +5856,7 @@ void mem_cgroup_uncharge_swap(swp_entry_t entry) id = swap_cgroup_record(entry, 0); rcu_read_lock(); - memcg = mem_cgroup_lookup(id); + memcg = mem_cgroup_from_id(id); if (memcg) { if (!mem_cgroup_is_root(memcg)) page_counter_uncharge(&memcg->memsw, 1); diff --git a/mm/memory-failure.c b/mm/memory-failure.c index d487f8dc6d39..d9359b770cd9 100644 --- a/mm/memory-failure.c +++ b/mm/memory-failure.c @@ -521,6 +521,52 @@ static const char *action_name[] = { [RECOVERED] = "Recovered", }; +enum action_page_type { + MSG_KERNEL, + MSG_KERNEL_HIGH_ORDER, + MSG_SLAB, + MSG_DIFFERENT_COMPOUND, + MSG_POISONED_HUGE, + MSG_HUGE, + MSG_FREE_HUGE, + MSG_UNMAP_FAILED, + MSG_DIRTY_SWAPCACHE, + MSG_CLEAN_SWAPCACHE, + MSG_DIRTY_MLOCKED_LRU, + MSG_CLEAN_MLOCKED_LRU, + MSG_DIRTY_UNEVICTABLE_LRU, + MSG_CLEAN_UNEVICTABLE_LRU, + MSG_DIRTY_LRU, + MSG_CLEAN_LRU, + MSG_TRUNCATED_LRU, + MSG_BUDDY, + MSG_BUDDY_2ND, + MSG_UNKNOWN, +}; + +static const char * const action_page_types[] = { + [MSG_KERNEL] = "reserved kernel page", + [MSG_KERNEL_HIGH_ORDER] = "high-order kernel page", + [MSG_SLAB] = "kernel slab page", + [MSG_DIFFERENT_COMPOUND] = "different compound page after locking", + [MSG_POISONED_HUGE] = "huge page already hardware poisoned", + [MSG_HUGE] = "huge page", + [MSG_FREE_HUGE] = "free huge page", + [MSG_UNMAP_FAILED] = "unmapping failed page", + [MSG_DIRTY_SWAPCACHE] = "dirty swapcache page", + [MSG_CLEAN_SWAPCACHE] = "clean swapcache page", + [MSG_DIRTY_MLOCKED_LRU] = "dirty mlocked LRU page", + [MSG_CLEAN_MLOCKED_LRU] = "clean mlocked LRU page", + [MSG_DIRTY_UNEVICTABLE_LRU] = "dirty unevictable LRU page", + [MSG_CLEAN_UNEVICTABLE_LRU] = "clean unevictable LRU page", + [MSG_DIRTY_LRU] = "dirty LRU page", + [MSG_CLEAN_LRU] = "clean LRU page", + [MSG_TRUNCATED_LRU] = "already truncated LRU page", + [MSG_BUDDY] = "free buddy page", + [MSG_BUDDY_2ND] = "free buddy page (2nd try)", + [MSG_UNKNOWN] = "unknown page", +}; + /* * XXX: It is possible that a page is isolated from LRU cache, * and then kept in swap cache or failed to remove from page cache. @@ -777,10 +823,10 @@ static int me_huge_page(struct page *p, unsigned long pfn) static struct page_state { unsigned long mask; unsigned long res; - char *msg; + enum action_page_type type; int (*action)(struct page *p, unsigned long pfn); } error_states[] = { - { reserved, reserved, "reserved kernel", me_kernel }, + { reserved, reserved, MSG_KERNEL, me_kernel }, /* * free pages are specially detected outside this table: * PG_buddy pages only make a small fraction of all free pages. @@ -791,31 +837,31 @@ static struct page_state { * currently unused objects without touching them. But just * treat it as standard kernel for now. */ - { slab, slab, "kernel slab", me_kernel }, + { slab, slab, MSG_SLAB, me_kernel }, #ifdef CONFIG_PAGEFLAGS_EXTENDED - { head, head, "huge", me_huge_page }, - { tail, tail, "huge", me_huge_page }, + { head, head, MSG_HUGE, me_huge_page }, + { tail, tail, MSG_HUGE, me_huge_page }, #else - { compound, compound, "huge", me_huge_page }, + { compound, compound, MSG_HUGE, me_huge_page }, #endif - { sc|dirty, sc|dirty, "dirty swapcache", me_swapcache_dirty }, - { sc|dirty, sc, "clean swapcache", me_swapcache_clean }, + { sc|dirty, sc|dirty, MSG_DIRTY_SWAPCACHE, me_swapcache_dirty }, + { sc|dirty, sc, MSG_CLEAN_SWAPCACHE, me_swapcache_clean }, - { mlock|dirty, mlock|dirty, "dirty mlocked LRU", me_pagecache_dirty }, - { mlock|dirty, mlock, "clean mlocked LRU", me_pagecache_clean }, + { mlock|dirty, mlock|dirty, MSG_DIRTY_MLOCKED_LRU, me_pagecache_dirty }, + { mlock|dirty, mlock, MSG_CLEAN_MLOCKED_LRU, me_pagecache_clean }, - { unevict|dirty, unevict|dirty, "dirty unevictable LRU", me_pagecache_dirty }, - { unevict|dirty, unevict, "clean unevictable LRU", me_pagecache_clean }, + { unevict|dirty, unevict|dirty, MSG_DIRTY_UNEVICTABLE_LRU, me_pagecache_dirty }, + { unevict|dirty, unevict, MSG_CLEAN_UNEVICTABLE_LRU, me_pagecache_clean }, - { lru|dirty, lru|dirty, "dirty LRU", me_pagecache_dirty }, - { lru|dirty, lru, "clean LRU", me_pagecache_clean }, + { lru|dirty, lru|dirty, MSG_DIRTY_LRU, me_pagecache_dirty }, + { lru|dirty, lru, MSG_CLEAN_LRU, me_pagecache_clean }, /* * Catchall entry: must be at end. */ - { 0, 0, "unknown page state", me_unknown }, + { 0, 0, MSG_UNKNOWN, me_unknown }, }; #undef dirty @@ -835,10 +881,10 @@ static struct page_state { * "Dirty/Clean" indication is not 100% accurate due to the possibility of * setting PG_dirty outside page lock. See also comment above set_page_dirty(). */ -static void action_result(unsigned long pfn, char *msg, int result) +static void action_result(unsigned long pfn, enum action_page_type type, int result) { - pr_err("MCE %#lx: %s page recovery: %s\n", - pfn, msg, action_name[result]); + pr_err("MCE %#lx: recovery action for %s: %s\n", + pfn, action_page_types[type], action_name[result]); } static int page_action(struct page_state *ps, struct page *p, @@ -854,11 +900,11 @@ static int page_action(struct page_state *ps, struct page *p, count--; if (count != 0) { printk(KERN_ERR - "MCE %#lx: %s page still referenced by %d users\n", - pfn, ps->msg, count); + "MCE %#lx: %s still referenced by %d users\n", + pfn, action_page_types[ps->type], count); result = FAILED; } - action_result(pfn, ps->msg, result); + action_result(pfn, ps->type, result); /* Could do more checks here if page looks ok */ /* @@ -1106,7 +1152,7 @@ int memory_failure(unsigned long pfn, int trapno, int flags) if (!(flags & MF_COUNT_INCREASED) && !get_page_unless_zero(hpage)) { if (is_free_buddy_page(p)) { - action_result(pfn, "free buddy", DELAYED); + action_result(pfn, MSG_BUDDY, DELAYED); return 0; } else if (PageHuge(hpage)) { /* @@ -1123,12 +1169,12 @@ int memory_failure(unsigned long pfn, int trapno, int flags) } set_page_hwpoison_huge_page(hpage); res = dequeue_hwpoisoned_huge_page(hpage); - action_result(pfn, "free huge", + action_result(pfn, MSG_FREE_HUGE, res ? IGNORED : DELAYED); unlock_page(hpage); return res; } else { - action_result(pfn, "high order kernel", IGNORED); + action_result(pfn, MSG_KERNEL_HIGH_ORDER, IGNORED); return -EBUSY; } } @@ -1150,9 +1196,10 @@ int memory_failure(unsigned long pfn, int trapno, int flags) */ if (is_free_buddy_page(p)) { if (flags & MF_COUNT_INCREASED) - action_result(pfn, "free buddy", DELAYED); + action_result(pfn, MSG_BUDDY, DELAYED); else - action_result(pfn, "free buddy, 2nd try", DELAYED); + action_result(pfn, MSG_BUDDY_2ND, + DELAYED); return 0; } } @@ -1165,7 +1212,7 @@ int memory_failure(unsigned long pfn, int trapno, int flags) * If this happens just bail out. */ if (compound_head(p) != hpage) { - action_result(pfn, "different compound page after locking", IGNORED); + action_result(pfn, MSG_DIFFERENT_COMPOUND, IGNORED); res = -EBUSY; goto out; } @@ -1205,8 +1252,7 @@ int memory_failure(unsigned long pfn, int trapno, int flags) * on the head page to show that the hugepage is hwpoisoned */ if (PageHuge(p) && PageTail(p) && TestSetPageHWPoison(hpage)) { - action_result(pfn, "hugepage already hardware poisoned", - IGNORED); + action_result(pfn, MSG_POISONED_HUGE, IGNORED); unlock_page(hpage); put_page(hpage); return 0; @@ -1235,7 +1281,7 @@ int memory_failure(unsigned long pfn, int trapno, int flags) */ if (hwpoison_user_mappings(p, pfn, trapno, flags, &hpage) != SWAP_SUCCESS) { - action_result(pfn, "unmapping failed", IGNORED); + action_result(pfn, MSG_UNMAP_FAILED, IGNORED); res = -EBUSY; goto out; } @@ -1244,7 +1290,7 @@ int memory_failure(unsigned long pfn, int trapno, int flags) * Torn down by someone else? */ if (PageLRU(p) && !PageSwapCache(p) && p->mapping == NULL) { - action_result(pfn, "already truncated LRU", IGNORED); + action_result(pfn, MSG_TRUNCATED_LRU, IGNORED); res = -EBUSY; goto out; } @@ -1540,8 +1586,18 @@ static int soft_offline_huge_page(struct page *page, int flags) } unlock_page(hpage); - /* Keep page count to indicate a given hugepage is isolated. */ - list_move(&hpage->lru, &pagelist); + ret = isolate_huge_page(hpage, &pagelist); + if (ret) { + /* + * get_any_page() and isolate_huge_page() takes a refcount each, + * so need to drop one here. + */ + put_page(hpage); + } else { + pr_info("soft offline: %#lx hugepage failed to isolate\n", pfn); + return -EBUSY; + } + ret = migrate_pages(&pagelist, new_page, NULL, MPOL_MF_MOVE_ALL, MIGRATE_SYNC, MR_MEMORY_FAILURE); if (ret) { diff --git a/mm/memory.c b/mm/memory.c index 8068893697bb..22e037e3364e 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -690,12 +690,11 @@ static void print_bad_pte(struct vm_area_struct *vma, unsigned long addr, /* * Choose text because data symbols depend on CONFIG_KALLSYMS_ALL=y */ - if (vma->vm_ops) - printk(KERN_ALERT "vma->vm_ops->fault: %pSR\n", - vma->vm_ops->fault); - if (vma->vm_file) - printk(KERN_ALERT "vma->vm_file->f_op->mmap: %pSR\n", - vma->vm_file->f_op->mmap); + pr_alert("file:%pD fault:%pf mmap:%pf readpage:%pf\n", + vma->vm_file, + vma->vm_ops ? vma->vm_ops->fault : NULL, + vma->vm_file ? vma->vm_file->f_op->mmap : NULL, + mapping ? mapping->a_ops->readpage : NULL); dump_stack(); add_taint(TAINT_BAD_PAGE, LOCKDEP_NOW_UNRELIABLE); } @@ -1983,167 +1982,91 @@ static int do_page_mkwrite(struct vm_area_struct *vma, struct page *page, } /* - * This routine handles present pages, when users try to write - * to a shared page. It is done by copying the page to a new address - * and decrementing the shared-page counter for the old page. + * Handle write page faults for pages that can be reused in the current vma * - * Note that this routine assumes that the protection checks have been - * done by the caller (the low-level page fault routine in most cases). - * Thus we can safely just mark it writable once we've done any necessary - * COW. - * - * We also mark the page dirty at this point even though the page will - * change only once the write actually happens. This avoids a few races, - * and potentially makes it more efficient. - * - * We enter with non-exclusive mmap_sem (to exclude vma changes, - * but allow concurrent faults), with pte both mapped and locked. - * We return with mmap_sem still held, but pte unmapped and unlocked. + * This can happen either due to the mapping being with the VM_SHARED flag, + * or due to us being the last reference standing to the page. In either + * case, all we need to do here is to mark the page as writable and update + * any related book-keeping. */ -static int do_wp_page(struct mm_struct *mm, struct vm_area_struct *vma, - unsigned long address, pte_t *page_table, pmd_t *pmd, - spinlock_t *ptl, pte_t orig_pte) +static inline int wp_page_reuse(struct mm_struct *mm, + struct vm_area_struct *vma, unsigned long address, + pte_t *page_table, spinlock_t *ptl, pte_t orig_pte, + struct page *page, int page_mkwrite, + int dirty_shared) __releases(ptl) { - struct page *old_page, *new_page = NULL; pte_t entry; - int ret = 0; - int page_mkwrite = 0; - bool dirty_shared = false; - unsigned long mmun_start = 0; /* For mmu_notifiers */ - unsigned long mmun_end = 0; /* For mmu_notifiers */ - struct mem_cgroup *memcg; - - old_page = vm_normal_page(vma, address, orig_pte); - if (!old_page) { - /* - * VM_MIXEDMAP !pfn_valid() case, or VM_SOFTDIRTY clear on a - * VM_PFNMAP VMA. - * - * We should not cow pages in a shared writeable mapping. - * Just mark the pages writable as we can't do any dirty - * accounting on raw pfn maps. - */ - if ((vma->vm_flags & (VM_WRITE|VM_SHARED)) == - (VM_WRITE|VM_SHARED)) - goto reuse; - goto gotten; - } - /* - * Take out anonymous pages first, anonymous shared vmas are - * not dirty accountable. + * Clear the pages cpupid information as the existing + * information potentially belongs to a now completely + * unrelated process. */ - if (PageAnon(old_page) && !PageKsm(old_page)) { - if (!trylock_page(old_page)) { - page_cache_get(old_page); - pte_unmap_unlock(page_table, ptl); - lock_page(old_page); - page_table = pte_offset_map_lock(mm, pmd, address, - &ptl); - if (!pte_same(*page_table, orig_pte)) { - unlock_page(old_page); - goto unlock; - } - page_cache_release(old_page); - } - if (reuse_swap_page(old_page)) { - /* - * The page is all ours. Move it to our anon_vma so - * the rmap code will not search our parent or siblings. - * Protected against the rmap code by the page lock. - */ - page_move_anon_rmap(old_page, vma, address); - unlock_page(old_page); - goto reuse; - } - unlock_page(old_page); - } else if (unlikely((vma->vm_flags & (VM_WRITE|VM_SHARED)) == - (VM_WRITE|VM_SHARED))) { - page_cache_get(old_page); - /* - * Only catch write-faults on shared writable pages, - * read-only shared pages can get COWed by - * get_user_pages(.write=1, .force=1). - */ - if (vma->vm_ops && vma->vm_ops->page_mkwrite) { - int tmp; - - pte_unmap_unlock(page_table, ptl); - tmp = do_page_mkwrite(vma, old_page, address); - if (unlikely(!tmp || (tmp & - (VM_FAULT_ERROR | VM_FAULT_NOPAGE)))) { - page_cache_release(old_page); - return tmp; - } - /* - * Since we dropped the lock we need to revalidate - * the PTE as someone else may have changed it. If - * they did, we just return, as we can count on the - * MMU to tell us if they didn't also make it writable. - */ - page_table = pte_offset_map_lock(mm, pmd, address, - &ptl); - if (!pte_same(*page_table, orig_pte)) { - unlock_page(old_page); - goto unlock; - } - page_mkwrite = 1; - } - - dirty_shared = true; - -reuse: - /* - * Clear the pages cpupid information as the existing - * information potentially belongs to a now completely - * unrelated process. - */ - if (old_page) - page_cpupid_xchg_last(old_page, (1 << LAST_CPUPID_SHIFT) - 1); - - flush_cache_page(vma, address, pte_pfn(orig_pte)); - entry = pte_mkyoung(orig_pte); - entry = maybe_mkwrite(pte_mkdirty(entry), vma); - if (ptep_set_access_flags(vma, address, page_table, entry,1)) - update_mmu_cache(vma, address, page_table); - pte_unmap_unlock(page_table, ptl); - ret |= VM_FAULT_WRITE; + if (page) + page_cpupid_xchg_last(page, (1 << LAST_CPUPID_SHIFT) - 1); - if (dirty_shared) { - struct address_space *mapping; - int dirtied; + flush_cache_page(vma, address, pte_pfn(orig_pte)); + entry = pte_mkyoung(orig_pte); + entry = maybe_mkwrite(pte_mkdirty(entry), vma); + if (ptep_set_access_flags(vma, address, page_table, entry, 1)) + update_mmu_cache(vma, address, page_table); + pte_unmap_unlock(page_table, ptl); - if (!page_mkwrite) - lock_page(old_page); + if (dirty_shared) { + struct address_space *mapping; + int dirtied; - dirtied = set_page_dirty(old_page); - VM_BUG_ON_PAGE(PageAnon(old_page), old_page); - mapping = old_page->mapping; - unlock_page(old_page); - page_cache_release(old_page); + if (!page_mkwrite) + lock_page(page); - if ((dirtied || page_mkwrite) && mapping) { - /* - * Some device drivers do not set page.mapping - * but still dirty their pages - */ - balance_dirty_pages_ratelimited(mapping); - } + dirtied = set_page_dirty(page); + VM_BUG_ON_PAGE(PageAnon(page), page); + mapping = page->mapping; + unlock_page(page); + page_cache_release(page); - if (!page_mkwrite) - file_update_time(vma->vm_file); + if ((dirtied || page_mkwrite) && mapping) { + /* + * Some device drivers do not set page.mapping + * but still dirty their pages + */ + balance_dirty_pages_ratelimited(mapping); } - return ret; + if (!page_mkwrite) + file_update_time(vma->vm_file); } - /* - * Ok, we need to copy. Oh, well.. - */ - page_cache_get(old_page); -gotten: - pte_unmap_unlock(page_table, ptl); + return VM_FAULT_WRITE; +} + +/* + * Handle the case of a page which we actually need to copy to a new page. + * + * Called with mmap_sem locked and the old page referenced, but + * without the ptl held. + * + * High level logic flow: + * + * - Allocate a page, copy the content of the old page to the new one. + * - Handle book keeping and accounting - cgroups, mmu-notifiers, etc. + * - Take the PTL. If the pte changed, bail out and release the allocated page + * - If the pte is still the way we remember it, update the page table and all + * relevant references. This includes dropping the reference the page-table + * held to the old page, as well as updating the rmap. + * - In any case, unlock the PTL and drop the reference we took to the old page. + */ +static int wp_page_copy(struct mm_struct *mm, struct vm_area_struct *vma, + unsigned long address, pte_t *page_table, pmd_t *pmd, + pte_t orig_pte, struct page *old_page) +{ + struct page *new_page = NULL; + spinlock_t *ptl = NULL; + pte_t entry; + int page_copied = 0; + const unsigned long mmun_start = address & PAGE_MASK; /* For mmu_notifiers */ + const unsigned long mmun_end = mmun_start + PAGE_SIZE; /* For mmu_notifiers */ + struct mem_cgroup *memcg; if (unlikely(anon_vma_prepare(vma))) goto oom; @@ -2163,8 +2086,6 @@ gotten: if (mem_cgroup_try_charge(new_page, mm, GFP_KERNEL, &memcg)) goto oom_free_new; - mmun_start = address & PAGE_MASK; - mmun_end = mmun_start + PAGE_SIZE; mmu_notifier_invalidate_range_start(mm, mmun_start, mmun_end); /* @@ -2177,8 +2098,9 @@ gotten: dec_mm_counter_fast(mm, MM_FILEPAGES); inc_mm_counter_fast(mm, MM_ANONPAGES); } - } else + } else { inc_mm_counter_fast(mm, MM_ANONPAGES); + } flush_cache_page(vma, address, pte_pfn(orig_pte)); entry = mk_pte(new_page, vma->vm_page_prot); entry = maybe_mkwrite(pte_mkdirty(entry), vma); @@ -2227,29 +2149,29 @@ gotten: /* Free the old page.. */ new_page = old_page; - ret |= VM_FAULT_WRITE; - } else + page_copied = 1; + } else { mem_cgroup_cancel_charge(new_page, memcg); + } if (new_page) page_cache_release(new_page); -unlock: + pte_unmap_unlock(page_table, ptl); - if (mmun_end > mmun_start) - mmu_notifier_invalidate_range_end(mm, mmun_start, mmun_end); + mmu_notifier_invalidate_range_end(mm, mmun_start, mmun_end); if (old_page) { /* * Don't let another task, with possibly unlocked vma, * keep the mlocked page. */ - if ((ret & VM_FAULT_WRITE) && (vma->vm_flags & VM_LOCKED)) { + if (page_copied && (vma->vm_flags & VM_LOCKED)) { lock_page(old_page); /* LRU manipulation */ munlock_vma_page(old_page); unlock_page(old_page); } page_cache_release(old_page); } - return ret; + return page_copied ? VM_FAULT_WRITE : 0; oom_free_new: page_cache_release(new_page); oom: @@ -2258,6 +2180,179 @@ oom: return VM_FAULT_OOM; } +/* + * Handle write page faults for VM_MIXEDMAP or VM_PFNMAP for a VM_SHARED + * mapping + */ +static int wp_pfn_shared(struct mm_struct *mm, + struct vm_area_struct *vma, unsigned long address, + pte_t *page_table, spinlock_t *ptl, pte_t orig_pte, + pmd_t *pmd) +{ + if (vma->vm_ops && vma->vm_ops->pfn_mkwrite) { + struct vm_fault vmf = { + .page = NULL, + .pgoff = linear_page_index(vma, address), + .virtual_address = (void __user *)(address & PAGE_MASK), + .flags = FAULT_FLAG_WRITE | FAULT_FLAG_MKWRITE, + }; + int ret; + + pte_unmap_unlock(page_table, ptl); + ret = vma->vm_ops->pfn_mkwrite(vma, &vmf); + if (ret & VM_FAULT_ERROR) + return ret; + page_table = pte_offset_map_lock(mm, pmd, address, &ptl); + /* + * We might have raced with another page fault while we + * released the pte_offset_map_lock. + */ + if (!pte_same(*page_table, orig_pte)) { + pte_unmap_unlock(page_table, ptl); + return 0; + } + } + return wp_page_reuse(mm, vma, address, page_table, ptl, orig_pte, + NULL, 0, 0); +} + +static int wp_page_shared(struct mm_struct *mm, struct vm_area_struct *vma, + unsigned long address, pte_t *page_table, + pmd_t *pmd, spinlock_t *ptl, pte_t orig_pte, + struct page *old_page) + __releases(ptl) +{ + int page_mkwrite = 0; + + page_cache_get(old_page); + + /* + * Only catch write-faults on shared writable pages, + * read-only shared pages can get COWed by + * get_user_pages(.write=1, .force=1). + */ + if (vma->vm_ops && vma->vm_ops->page_mkwrite) { + int tmp; + + pte_unmap_unlock(page_table, ptl); + tmp = do_page_mkwrite(vma, old_page, address); + if (unlikely(!tmp || (tmp & + (VM_FAULT_ERROR | VM_FAULT_NOPAGE)))) { + page_cache_release(old_page); + return tmp; + } + /* + * Since we dropped the lock we need to revalidate + * the PTE as someone else may have changed it. If + * they did, we just return, as we can count on the + * MMU to tell us if they didn't also make it writable. + */ + page_table = pte_offset_map_lock(mm, pmd, address, + &ptl); + if (!pte_same(*page_table, orig_pte)) { + unlock_page(old_page); + pte_unmap_unlock(page_table, ptl); + page_cache_release(old_page); + return 0; + } + page_mkwrite = 1; + } + + return wp_page_reuse(mm, vma, address, page_table, ptl, + orig_pte, old_page, page_mkwrite, 1); +} + +/* + * This routine handles present pages, when users try to write + * to a shared page. It is done by copying the page to a new address + * and decrementing the shared-page counter for the old page. + * + * Note that this routine assumes that the protection checks have been + * done by the caller (the low-level page fault routine in most cases). + * Thus we can safely just mark it writable once we've done any necessary + * COW. + * + * We also mark the page dirty at this point even though the page will + * change only once the write actually happens. This avoids a few races, + * and potentially makes it more efficient. + * + * We enter with non-exclusive mmap_sem (to exclude vma changes, + * but allow concurrent faults), with pte both mapped and locked. + * We return with mmap_sem still held, but pte unmapped and unlocked. + */ +static int do_wp_page(struct mm_struct *mm, struct vm_area_struct *vma, + unsigned long address, pte_t *page_table, pmd_t *pmd, + spinlock_t *ptl, pte_t orig_pte) + __releases(ptl) +{ + struct page *old_page; + + old_page = vm_normal_page(vma, address, orig_pte); + if (!old_page) { + /* + * VM_MIXEDMAP !pfn_valid() case, or VM_SOFTDIRTY clear on a + * VM_PFNMAP VMA. + * + * We should not cow pages in a shared writeable mapping. + * Just mark the pages writable and/or call ops->pfn_mkwrite. + */ + if ((vma->vm_flags & (VM_WRITE|VM_SHARED)) == + (VM_WRITE|VM_SHARED)) + return wp_pfn_shared(mm, vma, address, page_table, ptl, + orig_pte, pmd); + + pte_unmap_unlock(page_table, ptl); + return wp_page_copy(mm, vma, address, page_table, pmd, + orig_pte, old_page); + } + + /* + * Take out anonymous pages first, anonymous shared vmas are + * not dirty accountable. + */ + if (PageAnon(old_page) && !PageKsm(old_page)) { + if (!trylock_page(old_page)) { + page_cache_get(old_page); + pte_unmap_unlock(page_table, ptl); + lock_page(old_page); + page_table = pte_offset_map_lock(mm, pmd, address, + &ptl); + if (!pte_same(*page_table, orig_pte)) { + unlock_page(old_page); + pte_unmap_unlock(page_table, ptl); + page_cache_release(old_page); + return 0; + } + page_cache_release(old_page); + } + if (reuse_swap_page(old_page)) { + /* + * The page is all ours. Move it to our anon_vma so + * the rmap code will not search our parent or siblings. + * Protected against the rmap code by the page lock. + */ + page_move_anon_rmap(old_page, vma, address); + unlock_page(old_page); + return wp_page_reuse(mm, vma, address, page_table, ptl, + orig_pte, old_page, 0, 0); + } + unlock_page(old_page); + } else if (unlikely((vma->vm_flags & (VM_WRITE|VM_SHARED)) == + (VM_WRITE|VM_SHARED))) { + return wp_page_shared(mm, vma, address, page_table, pmd, + ptl, orig_pte, old_page); + } + + /* + * Ok, we need to copy. Oh, well.. + */ + page_cache_get(old_page); + + pte_unmap_unlock(page_table, ptl); + return wp_page_copy(mm, vma, address, page_table, pmd, + orig_pte, old_page); +} + static void unmap_mapping_range_vma(struct vm_area_struct *vma, unsigned long start_addr, unsigned long end_addr, struct zap_details *details) @@ -2784,7 +2879,7 @@ static void do_fault_around(struct vm_area_struct *vma, unsigned long address, struct vm_fault vmf; int off; - nr_pages = ACCESS_ONCE(fault_around_bytes) >> PAGE_SHIFT; + nr_pages = READ_ONCE(fault_around_bytes) >> PAGE_SHIFT; mask = ~(nr_pages * PAGE_SIZE - 1) & PAGE_MASK; start_addr = max(address & mask, vma->vm_start); @@ -3035,6 +3130,7 @@ static int do_numa_page(struct mm_struct *mm, struct vm_area_struct *vma, int last_cpupid; int target_nid; bool migrated = false; + bool was_writable = pte_write(pte); int flags = 0; /* A PROT_NONE fault should not end up here */ @@ -3059,6 +3155,8 @@ static int do_numa_page(struct mm_struct *mm, struct vm_area_struct *vma, /* Make it present again */ pte = pte_modify(pte, vma->vm_page_prot); pte = pte_mkyoung(pte); + if (was_writable) + pte = pte_mkwrite(pte); set_pte_at(mm, addr, ptep, pte); update_mmu_cache(vma, addr, ptep); @@ -3069,11 +3167,14 @@ static int do_numa_page(struct mm_struct *mm, struct vm_area_struct *vma, } /* - * Avoid grouping on DSO/COW pages in specific and RO pages - * in general, RO pages shouldn't hurt as much anyway since - * they can be in shared cache state. + * Avoid grouping on RO pages in general. RO pages shouldn't hurt as + * much anyway since they can be in shared cache state. This misses + * the case where a mapping is writable but the process never writes + * to it but pte_write gets cleared during protection updates and + * pte_dirty has unpredictable behaviour between PTE scan updates, + * background writeback, dirty balancing and application behaviour. */ - if (!pte_write(pte)) + if (!(vma->vm_flags & VM_WRITE)) flags |= TNF_NO_GROUP; /* @@ -3097,7 +3198,8 @@ static int do_numa_page(struct mm_struct *mm, struct vm_area_struct *vma, if (migrated) { page_nid = target_nid; flags |= TNF_MIGRATED; - } + } else + flags |= TNF_MIGRATE_FAIL; out: if (page_nid != -1) diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c index 9fab10795bea..457bde530cbe 100644 --- a/mm/memory_hotplug.c +++ b/mm/memory_hotplug.c @@ -104,7 +104,7 @@ void put_online_mems(void) } -static void mem_hotplug_begin(void) +void mem_hotplug_begin(void) { mem_hotplug.active_writer = current; @@ -119,7 +119,7 @@ static void mem_hotplug_begin(void) } } -static void mem_hotplug_done(void) +void mem_hotplug_done(void) { mem_hotplug.active_writer = NULL; mutex_unlock(&mem_hotplug.lock); @@ -502,7 +502,7 @@ int __ref __add_pages(int nid, struct zone *zone, unsigned long phys_start_pfn, end_sec = pfn_to_section_nr(phys_start_pfn + nr_pages - 1); for (i = start_sec; i <= end_sec; i++) { - err = __add_section(nid, zone, i << PFN_SECTION_SHIFT); + err = __add_section(nid, zone, section_nr_to_pfn(i)); /* * EEXIST is finally dealt with by ioresource collision @@ -959,6 +959,7 @@ static void node_states_set_node(int node, struct memory_notify *arg) } +/* Must be protected by mem_hotplug_begin() */ int __ref online_pages(unsigned long pfn, unsigned long nr_pages, int online_type) { unsigned long flags; @@ -969,7 +970,6 @@ int __ref online_pages(unsigned long pfn, unsigned long nr_pages, int online_typ int ret; struct memory_notify arg; - mem_hotplug_begin(); /* * This doesn't need a lock to do pfn_to_page(). * The section can't be removed here because of the @@ -977,21 +977,20 @@ int __ref online_pages(unsigned long pfn, unsigned long nr_pages, int online_typ */ zone = page_zone(pfn_to_page(pfn)); - ret = -EINVAL; if ((zone_idx(zone) > ZONE_NORMAL || online_type == MMOP_ONLINE_MOVABLE) && !can_online_high_movable(zone)) - goto out; + return -EINVAL; if (online_type == MMOP_ONLINE_KERNEL && zone_idx(zone) == ZONE_MOVABLE) { if (move_pfn_range_left(zone - 1, zone, pfn, pfn + nr_pages)) - goto out; + return -EINVAL; } if (online_type == MMOP_ONLINE_MOVABLE && zone_idx(zone) == ZONE_MOVABLE - 1) { if (move_pfn_range_right(zone, zone + 1, pfn, pfn + nr_pages)) - goto out; + return -EINVAL; } /* Previous code may changed the zone of the pfn range */ @@ -1007,7 +1006,7 @@ int __ref online_pages(unsigned long pfn, unsigned long nr_pages, int online_typ ret = notifier_to_errno(ret); if (ret) { memory_notify(MEM_CANCEL_ONLINE, &arg); - goto out; + return ret; } /* * If this zone is not populated, then it is not in zonelist. @@ -1031,7 +1030,7 @@ int __ref online_pages(unsigned long pfn, unsigned long nr_pages, int online_typ (((unsigned long long) pfn + nr_pages) << PAGE_SHIFT) - 1); memory_notify(MEM_CANCEL_ONLINE, &arg); - goto out; + return ret; } zone->present_pages += onlined_pages; @@ -1061,9 +1060,7 @@ int __ref online_pages(unsigned long pfn, unsigned long nr_pages, int online_typ if (onlined_pages) memory_notify(MEM_ONLINE, &arg); -out: - mem_hotplug_done(); - return ret; + return 0; } #endif /* CONFIG_MEMORY_HOTPLUG_SPARSE */ @@ -1092,6 +1089,10 @@ static pg_data_t __ref *hotadd_new_pgdat(int nid, u64 start) return NULL; arch_refresh_nodedata(nid, pgdat); + } else { + /* Reset the nr_zones and classzone_idx to 0 before reuse */ + pgdat->nr_zones = 0; + pgdat->classzone_idx = 0; } /* we can use NODE_DATA(nid) from here */ @@ -1372,7 +1373,7 @@ static unsigned long scan_movable_pages(unsigned long start, unsigned long end) if (PageLRU(page)) return pfn; if (PageHuge(page)) { - if (is_hugepage_active(page)) + if (page_huge_active(page)) return pfn; else pfn = round_up(pfn + 1, @@ -1684,21 +1685,18 @@ static int __ref __offline_pages(unsigned long start_pfn, if (!test_pages_in_a_zone(start_pfn, end_pfn)) return -EINVAL; - mem_hotplug_begin(); - zone = page_zone(pfn_to_page(start_pfn)); node = zone_to_nid(zone); nr_pages = end_pfn - start_pfn; - ret = -EINVAL; if (zone_idx(zone) <= ZONE_NORMAL && !can_offline_normal(zone, nr_pages)) - goto out; + return -EINVAL; /* set above range as isolated */ ret = start_isolate_page_range(start_pfn, end_pfn, MIGRATE_MOVABLE, true); if (ret) - goto out; + return ret; arg.start_pfn = start_pfn; arg.nr_pages = nr_pages; @@ -1791,7 +1789,6 @@ repeat: writeback_set_ratelimit(); memory_notify(MEM_OFFLINE, &arg); - mem_hotplug_done(); return 0; failed_removal: @@ -1801,12 +1798,10 @@ failed_removal: memory_notify(MEM_CANCEL_OFFLINE, &arg); /* pushback to free area */ undo_isolate_page_range(start_pfn, end_pfn, MIGRATE_MOVABLE); - -out: - mem_hotplug_done(); return ret; } +/* Must be protected by mem_hotplug_begin() */ int offline_pages(unsigned long start_pfn, unsigned long nr_pages) { return __offline_pages(start_pfn, start_pfn + nr_pages, 120 * HZ); @@ -1977,15 +1972,6 @@ void try_offline_node(int nid) if (is_vmalloc_addr(zone->wait_table)) vfree(zone->wait_table); } - - /* - * Since there is no way to guarentee the address of pgdat/zone is not - * on stack of any kernel threads or used by other kernel objects - * without reference counting or other symchronizing method, do not - * reset node_data and free pgdat here. Just reset it to 0 and reuse - * the memory when the node is online again. - */ - memset(pgdat, 0, sizeof(*pgdat)); } EXPORT_SYMBOL(try_offline_node); diff --git a/mm/mempolicy.c b/mm/mempolicy.c index 4721046a134a..ede26291d4aa 100644 --- a/mm/mempolicy.c +++ b/mm/mempolicy.c @@ -945,7 +945,8 @@ static struct page *new_node_page(struct page *page, unsigned long node, int **x return alloc_huge_page_node(page_hstate(compound_head(page)), node); else - return alloc_pages_exact_node(node, GFP_HIGHUSER_MOVABLE, 0); + return alloc_pages_exact_node(node, GFP_HIGHUSER_MOVABLE | + __GFP_THISNODE, 0); } /* @@ -1985,7 +1986,8 @@ retry_cpuset: nmask = policy_nodemask(gfp, pol); if (!nmask || node_isset(node, *nmask)) { mpol_cond_put(pol); - page = alloc_pages_exact_node(node, gfp, order); + page = alloc_pages_exact_node(node, + gfp | __GFP_THISNODE, order); goto out; } } diff --git a/mm/mempool.c b/mm/mempool.c index e209c98c7203..2cc08de8b1db 100644 --- a/mm/mempool.c +++ b/mm/mempool.c @@ -6,26 +6,138 @@ * extreme VM load. * * started by Ingo Molnar, Copyright (C) 2001 + * debugging by David Rientjes, Copyright (C) 2015 */ #include <linux/mm.h> #include <linux/slab.h> +#include <linux/highmem.h> +#include <linux/kasan.h> #include <linux/kmemleak.h> #include <linux/export.h> #include <linux/mempool.h> #include <linux/blkdev.h> #include <linux/writeback.h> +#include "slab.h" + +#if defined(CONFIG_DEBUG_SLAB) || defined(CONFIG_SLUB_DEBUG_ON) +static void poison_error(mempool_t *pool, void *element, size_t size, + size_t byte) +{ + const int nr = pool->curr_nr; + const int start = max_t(int, byte - (BITS_PER_LONG / 8), 0); + const int end = min_t(int, byte + (BITS_PER_LONG / 8), size); + int i; + + pr_err("BUG: mempool element poison mismatch\n"); + pr_err("Mempool %p size %zu\n", pool, size); + pr_err(" nr=%d @ %p: %s0x", nr, element, start > 0 ? "... " : ""); + for (i = start; i < end; i++) + pr_cont("%x ", *(u8 *)(element + i)); + pr_cont("%s\n", end < size ? "..." : ""); + dump_stack(); +} + +static void __check_element(mempool_t *pool, void *element, size_t size) +{ + u8 *obj = element; + size_t i; + + for (i = 0; i < size; i++) { + u8 exp = (i < size - 1) ? POISON_FREE : POISON_END; + + if (obj[i] != exp) { + poison_error(pool, element, size, i); + return; + } + } + memset(obj, POISON_INUSE, size); +} + +static void check_element(mempool_t *pool, void *element) +{ + /* Mempools backed by slab allocator */ + if (pool->free == mempool_free_slab || pool->free == mempool_kfree) + __check_element(pool, element, ksize(element)); + + /* Mempools backed by page allocator */ + if (pool->free == mempool_free_pages) { + int order = (int)(long)pool->pool_data; + void *addr = kmap_atomic((struct page *)element); + + __check_element(pool, addr, 1UL << (PAGE_SHIFT + order)); + kunmap_atomic(addr); + } +} + +static void __poison_element(void *element, size_t size) +{ + u8 *obj = element; + + memset(obj, POISON_FREE, size - 1); + obj[size - 1] = POISON_END; +} + +static void poison_element(mempool_t *pool, void *element) +{ + /* Mempools backed by slab allocator */ + if (pool->alloc == mempool_alloc_slab || pool->alloc == mempool_kmalloc) + __poison_element(element, ksize(element)); + + /* Mempools backed by page allocator */ + if (pool->alloc == mempool_alloc_pages) { + int order = (int)(long)pool->pool_data; + void *addr = kmap_atomic((struct page *)element); + + __poison_element(addr, 1UL << (PAGE_SHIFT + order)); + kunmap_atomic(addr); + } +} +#else /* CONFIG_DEBUG_SLAB || CONFIG_SLUB_DEBUG_ON */ +static inline void check_element(mempool_t *pool, void *element) +{ +} +static inline void poison_element(mempool_t *pool, void *element) +{ +} +#endif /* CONFIG_DEBUG_SLAB || CONFIG_SLUB_DEBUG_ON */ + +static void kasan_poison_element(mempool_t *pool, void *element) +{ + if (pool->alloc == mempool_alloc_slab) + kasan_slab_free(pool->pool_data, element); + if (pool->alloc == mempool_kmalloc) + kasan_kfree(element); + if (pool->alloc == mempool_alloc_pages) + kasan_free_pages(element, (unsigned long)pool->pool_data); +} + +static void kasan_unpoison_element(mempool_t *pool, void *element) +{ + if (pool->alloc == mempool_alloc_slab) + kasan_slab_alloc(pool->pool_data, element); + if (pool->alloc == mempool_kmalloc) + kasan_krealloc(element, (size_t)pool->pool_data); + if (pool->alloc == mempool_alloc_pages) + kasan_alloc_pages(element, (unsigned long)pool->pool_data); +} static void add_element(mempool_t *pool, void *element) { BUG_ON(pool->curr_nr >= pool->min_nr); + poison_element(pool, element); + kasan_poison_element(pool, element); pool->elements[pool->curr_nr++] = element; } static void *remove_element(mempool_t *pool) { - BUG_ON(pool->curr_nr <= 0); - return pool->elements[--pool->curr_nr]; + void *element = pool->elements[--pool->curr_nr]; + + BUG_ON(pool->curr_nr < 0); + check_element(pool, element); + kasan_unpoison_element(pool, element); + return element; } /** @@ -113,23 +225,24 @@ EXPORT_SYMBOL(mempool_create_node); * mempool_create(). * @new_min_nr: the new minimum number of elements guaranteed to be * allocated for this pool. - * @gfp_mask: the usual allocation bitmask. * * This function shrinks/grows the pool. In the case of growing, * it cannot be guaranteed that the pool will be grown to the new * size immediately, but new mempool_free() calls will refill it. + * This function may sleep. * * Note, the caller must guarantee that no mempool_destroy is called * while this function is running. mempool_alloc() & mempool_free() * might be called (eg. from IRQ contexts) while this function executes. */ -int mempool_resize(mempool_t *pool, int new_min_nr, gfp_t gfp_mask) +int mempool_resize(mempool_t *pool, int new_min_nr) { void *element; void **new_elements; unsigned long flags; BUG_ON(new_min_nr <= 0); + might_sleep(); spin_lock_irqsave(&pool->lock, flags); if (new_min_nr <= pool->min_nr) { @@ -145,7 +258,8 @@ int mempool_resize(mempool_t *pool, int new_min_nr, gfp_t gfp_mask) spin_unlock_irqrestore(&pool->lock, flags); /* Grow the pool */ - new_elements = kmalloc(new_min_nr * sizeof(*new_elements), gfp_mask); + new_elements = kmalloc_array(new_min_nr, sizeof(*new_elements), + GFP_KERNEL); if (!new_elements) return -ENOMEM; @@ -164,7 +278,7 @@ int mempool_resize(mempool_t *pool, int new_min_nr, gfp_t gfp_mask) while (pool->curr_nr < pool->min_nr) { spin_unlock_irqrestore(&pool->lock, flags); - element = pool->alloc(gfp_mask, pool->pool_data); + element = pool->alloc(GFP_KERNEL, pool->pool_data); if (!element) goto out; spin_lock_irqsave(&pool->lock, flags); @@ -332,6 +446,7 @@ EXPORT_SYMBOL(mempool_free); void *mempool_alloc_slab(gfp_t gfp_mask, void *pool_data) { struct kmem_cache *mem = pool_data; + VM_BUG_ON(mem->ctor); return kmem_cache_alloc(mem, gfp_mask); } EXPORT_SYMBOL(mempool_alloc_slab); diff --git a/mm/memtest.c b/mm/memtest.c new file mode 100644 index 000000000000..1997d934b13b --- /dev/null +++ b/mm/memtest.c @@ -0,0 +1,118 @@ +#include <linux/kernel.h> +#include <linux/errno.h> +#include <linux/string.h> +#include <linux/types.h> +#include <linux/mm.h> +#include <linux/smp.h> +#include <linux/init.h> +#include <linux/pfn.h> +#include <linux/memblock.h> + +static u64 patterns[] __initdata = { + /* The first entry has to be 0 to leave memtest with zeroed memory */ + 0, + 0xffffffffffffffffULL, + 0x5555555555555555ULL, + 0xaaaaaaaaaaaaaaaaULL, + 0x1111111111111111ULL, + 0x2222222222222222ULL, + 0x4444444444444444ULL, + 0x8888888888888888ULL, + 0x3333333333333333ULL, + 0x6666666666666666ULL, + 0x9999999999999999ULL, + 0xccccccccccccccccULL, + 0x7777777777777777ULL, + 0xbbbbbbbbbbbbbbbbULL, + 0xddddddddddddddddULL, + 0xeeeeeeeeeeeeeeeeULL, + 0x7a6c7258554e494cULL, /* yeah ;-) */ +}; + +static void __init reserve_bad_mem(u64 pattern, phys_addr_t start_bad, phys_addr_t end_bad) +{ + printk(KERN_INFO " %016llx bad mem addr %010llx - %010llx reserved\n", + (unsigned long long) pattern, + (unsigned long long) start_bad, + (unsigned long long) end_bad); + memblock_reserve(start_bad, end_bad - start_bad); +} + +static void __init memtest(u64 pattern, phys_addr_t start_phys, phys_addr_t size) +{ + u64 *p, *start, *end; + phys_addr_t start_bad, last_bad; + phys_addr_t start_phys_aligned; + const size_t incr = sizeof(pattern); + + start_phys_aligned = ALIGN(start_phys, incr); + start = __va(start_phys_aligned); + end = start + (size - (start_phys_aligned - start_phys)) / incr; + start_bad = 0; + last_bad = 0; + + for (p = start; p < end; p++) + *p = pattern; + + for (p = start; p < end; p++, start_phys_aligned += incr) { + if (*p == pattern) + continue; + if (start_phys_aligned == last_bad + incr) { + last_bad += incr; + continue; + } + if (start_bad) + reserve_bad_mem(pattern, start_bad, last_bad + incr); + start_bad = last_bad = start_phys_aligned; + } + if (start_bad) + reserve_bad_mem(pattern, start_bad, last_bad + incr); +} + +static void __init do_one_pass(u64 pattern, phys_addr_t start, phys_addr_t end) +{ + u64 i; + phys_addr_t this_start, this_end; + + for_each_free_mem_range(i, NUMA_NO_NODE, &this_start, &this_end, NULL) { + this_start = clamp(this_start, start, end); + this_end = clamp(this_end, start, end); + if (this_start < this_end) { + printk(KERN_INFO " %010llx - %010llx pattern %016llx\n", + (unsigned long long)this_start, + (unsigned long long)this_end, + (unsigned long long)cpu_to_be64(pattern)); + memtest(pattern, this_start, this_end - this_start); + } + } +} + +/* default is disabled */ +static int memtest_pattern __initdata; + +static int __init parse_memtest(char *arg) +{ + if (arg) + memtest_pattern = simple_strtoul(arg, NULL, 0); + else + memtest_pattern = ARRAY_SIZE(patterns); + + return 0; +} + +early_param("memtest", parse_memtest); + +void __init early_memtest(phys_addr_t start, phys_addr_t end) +{ + unsigned int i; + unsigned int idx = 0; + + if (!memtest_pattern) + return; + + printk(KERN_INFO "early_memtest: # of tests: %d\n", memtest_pattern); + for (i = memtest_pattern-1; i < UINT_MAX; --i) { + idx = i % ARRAY_SIZE(patterns); + do_one_pass(patterns[idx], start, end); + } +} diff --git a/mm/migrate.c b/mm/migrate.c index 85e042686031..f53838fe3dfe 100644 --- a/mm/migrate.c +++ b/mm/migrate.c @@ -537,7 +537,8 @@ void migrate_page_copy(struct page *newpage, struct page *page) * Please do not reorder this without considering how mm/ksm.c's * get_ksm_page() depends upon ksm_migrate_page() and PageSwapCache(). */ - ClearPageSwapCache(page); + if (PageSwapCache(page)) + ClearPageSwapCache(page); ClearPagePrivate(page); set_page_private(page, 0); @@ -901,12 +902,23 @@ out: } /* + * gcc 4.7 and 4.8 on arm get an ICEs when inlining unmap_and_move(). Work + * around it. + */ +#if (GCC_VERSION >= 40700 && GCC_VERSION < 40900) && defined(CONFIG_ARM) +#define ICE_noinline noinline +#else +#define ICE_noinline +#endif + +/* * Obtain the lock on page, remove all ptes and migrate the page * to the newly allocated page in newpage. */ -static int unmap_and_move(new_page_t get_new_page, free_page_t put_new_page, - unsigned long private, struct page *page, int force, - enum migrate_mode mode) +static ICE_noinline int unmap_and_move(new_page_t get_new_page, + free_page_t put_new_page, + unsigned long private, struct page *page, + int force, enum migrate_mode mode) { int rc = 0; int *result = NULL; @@ -1554,30 +1566,10 @@ static struct page *alloc_misplaced_dst_page(struct page *page, * page migration rate limiting control. * Do not migrate more than @pages_to_migrate in a @migrate_interval_millisecs * window of time. Default here says do not migrate more than 1280M per second. - * If a node is rate-limited then PTE NUMA updates are also rate-limited. However - * as it is faults that reset the window, pte updates will happen unconditionally - * if there has not been a fault since @pteupdate_interval_millisecs after the - * throttle window closed. */ static unsigned int migrate_interval_millisecs __read_mostly = 100; -static unsigned int pteupdate_interval_millisecs __read_mostly = 1000; static unsigned int ratelimit_pages __read_mostly = 128 << (20 - PAGE_SHIFT); -/* Returns true if NUMA migration is currently rate limited */ -bool migrate_ratelimited(int node) -{ - pg_data_t *pgdat = NODE_DATA(node); - - if (time_after(jiffies, pgdat->numabalancing_migrate_next_window + - msecs_to_jiffies(pteupdate_interval_millisecs))) - return false; - - if (pgdat->numabalancing_migrate_nr_pages < ratelimit_pages) - return false; - - return true; -} - /* Returns true if the node is migrate rate-limited after the update */ static bool numamigrate_update_ratelimit(pg_data_t *pgdat, unsigned long nr_pages) diff --git a/mm/mlock.c b/mm/mlock.c index 73cf0987088c..6fd2cf15e868 100644 --- a/mm/mlock.c +++ b/mm/mlock.c @@ -26,10 +26,10 @@ int can_do_mlock(void) { - if (capable(CAP_IPC_LOCK)) - return 1; if (rlimit(RLIMIT_MEMLOCK) != 0) return 1; + if (capable(CAP_IPC_LOCK)) + return 1; return 0; } EXPORT_SYMBOL(can_do_mlock); @@ -205,62 +205,6 @@ out: return nr_pages - 1; } -/** - * __mlock_vma_pages_range() - mlock a range of pages in the vma. - * @vma: target vma - * @start: start address - * @end: end address - * @nonblocking: - * - * This takes care of making the pages present too. - * - * return 0 on success, negative error code on error. - * - * vma->vm_mm->mmap_sem must be held. - * - * If @nonblocking is NULL, it may be held for read or write and will - * be unperturbed. - * - * If @nonblocking is non-NULL, it must held for read only and may be - * released. If it's released, *@nonblocking will be set to 0. - */ -long __mlock_vma_pages_range(struct vm_area_struct *vma, - unsigned long start, unsigned long end, int *nonblocking) -{ - struct mm_struct *mm = vma->vm_mm; - unsigned long nr_pages = (end - start) / PAGE_SIZE; - int gup_flags; - - VM_BUG_ON(start & ~PAGE_MASK); - VM_BUG_ON(end & ~PAGE_MASK); - VM_BUG_ON_VMA(start < vma->vm_start, vma); - VM_BUG_ON_VMA(end > vma->vm_end, vma); - VM_BUG_ON_MM(!rwsem_is_locked(&mm->mmap_sem), mm); - - gup_flags = FOLL_TOUCH | FOLL_MLOCK; - /* - * We want to touch writable mappings with a write fault in order - * to break COW, except for shared mappings because these don't COW - * and we would not want to dirty them for nothing. - */ - if ((vma->vm_flags & (VM_WRITE | VM_SHARED)) == VM_WRITE) - gup_flags |= FOLL_WRITE; - - /* - * We want mlock to succeed for regions that have any permissions - * other than PROT_NONE. - */ - if (vma->vm_flags & (VM_READ | VM_WRITE | VM_EXEC)) - gup_flags |= FOLL_FORCE; - - /* - * We made sure addr is within a VMA, so the following will - * not result in a stack expansion that recurses back here. - */ - return __get_user_pages(current, mm, start, nr_pages, gup_flags, - NULL, NULL, nonblocking); -} - /* * convert get_user_pages() return value to posix mlock() error */ @@ -596,7 +540,7 @@ success: /* * vm_flags is protected by the mmap_sem held in write mode. * It's okay if try_to_unmap_one unmaps a page just after we - * set VM_LOCKED, __mlock_vma_pages_range will bring it back. + * set VM_LOCKED, populate_vma_page_range will bring it back. */ if (lock) @@ -660,69 +604,6 @@ static int do_mlock(unsigned long start, size_t len, int on) return error; } -/* - * __mm_populate - populate and/or mlock pages within a range of address space. - * - * This is used to implement mlock() and the MAP_POPULATE / MAP_LOCKED mmap - * flags. VMAs must be already marked with the desired vm_flags, and - * mmap_sem must not be held. - */ -int __mm_populate(unsigned long start, unsigned long len, int ignore_errors) -{ - struct mm_struct *mm = current->mm; - unsigned long end, nstart, nend; - struct vm_area_struct *vma = NULL; - int locked = 0; - long ret = 0; - - VM_BUG_ON(start & ~PAGE_MASK); - VM_BUG_ON(len != PAGE_ALIGN(len)); - end = start + len; - - for (nstart = start; nstart < end; nstart = nend) { - /* - * We want to fault in pages for [nstart; end) address range. - * Find first corresponding VMA. - */ - if (!locked) { - locked = 1; - down_read(&mm->mmap_sem); - vma = find_vma(mm, nstart); - } else if (nstart >= vma->vm_end) - vma = vma->vm_next; - if (!vma || vma->vm_start >= end) - break; - /* - * Set [nstart; nend) to intersection of desired address - * range with the first VMA. Also, skip undesirable VMA types. - */ - nend = min(end, vma->vm_end); - if (vma->vm_flags & (VM_IO | VM_PFNMAP)) - continue; - if (nstart < vma->vm_start) - nstart = vma->vm_start; - /* - * Now fault in a range of pages. __mlock_vma_pages_range() - * double checks the vma flags, so that it won't mlock pages - * if the vma was already munlocked. - */ - ret = __mlock_vma_pages_range(vma, nstart, nend, &locked); - if (ret < 0) { - if (ignore_errors) { - ret = 0; - continue; /* continue at next VMA */ - } - ret = __mlock_posix_error_return(ret); - break; - } - nend = nstart + ret * PAGE_SIZE; - ret = 0; - } - if (locked) - up_read(&mm->mmap_sem); - return ret; /* 0 or negative error code */ -} - SYSCALL_DEFINE2(mlock, unsigned long, start, size_t, len) { unsigned long locked; @@ -750,9 +631,13 @@ SYSCALL_DEFINE2(mlock, unsigned long, start, size_t, len) error = do_mlock(start, len, 1); up_write(¤t->mm->mmap_sem); - if (!error) - error = __mm_populate(start, len, 0); - return error; + if (error) + return error; + + error = __mm_populate(start, len, 0); + if (error) + return __mlock_posix_error_return(error); + return 0; } SYSCALL_DEFINE2(munlock, unsigned long, start, size_t, len) diff --git a/mm/mmap.c b/mm/mmap.c index da9990acc08b..bb50cacc3ea5 100644 --- a/mm/mmap.c +++ b/mm/mmap.c @@ -774,10 +774,8 @@ again: remove_next = 1 + (end > next->vm_end); importer->anon_vma = exporter->anon_vma; error = anon_vma_clone(importer, exporter); - if (error) { - importer->anon_vma = NULL; + if (error) return error; - } } } @@ -1135,7 +1133,7 @@ static int anon_vma_compatible(struct vm_area_struct *a, struct vm_area_struct * * by another page fault trying to merge _that_. But that's ok: if it * is being set up, that automatically means that it will be a singleton * acceptable for merging, so we can do all of this optimistically. But - * we do that ACCESS_ONCE() to make sure that we never re-load the pointer. + * we do that READ_ONCE() to make sure that we never re-load the pointer. * * IOW: that the "list_is_singular()" test on the anon_vma_chain only * matters for the 'stable anon_vma' case (ie the thing we want to avoid @@ -1149,7 +1147,7 @@ static int anon_vma_compatible(struct vm_area_struct *a, struct vm_area_struct * static struct anon_vma *reusable_anon_vma(struct vm_area_struct *old, struct vm_area_struct *a, struct vm_area_struct *b) { if (anon_vma_compatible(a, b)) { - struct anon_vma *anon_vma = ACCESS_ONCE(old->anon_vma); + struct anon_vma *anon_vma = READ_ONCE(old->anon_vma); if (anon_vma && list_is_singular(&old->anon_vma_chain)) return anon_vma; @@ -1553,11 +1551,10 @@ unsigned long mmap_region(struct file *file, unsigned long addr, /* Clear old maps */ error = -ENOMEM; -munmap_back: - if (find_vma_links(mm, addr, addr + len, &prev, &rb_link, &rb_parent)) { + while (find_vma_links(mm, addr, addr + len, &prev, &rb_link, + &rb_parent)) { if (do_munmap(mm, addr, len)) return -ENOMEM; - goto munmap_back; } /* @@ -1573,7 +1570,8 @@ munmap_back: /* * Can we just expand an old mapping? */ - vma = vma_merge(mm, prev, addr, addr + len, vm_flags, NULL, file, pgoff, NULL); + vma = vma_merge(mm, prev, addr, addr + len, vm_flags, NULL, file, pgoff, + NULL); if (vma) goto out; @@ -2102,7 +2100,7 @@ static int acct_stack_growth(struct vm_area_struct *vma, unsigned long size, uns actual_size = size; if (size && (vma->vm_flags & (VM_GROWSUP | VM_GROWSDOWN))) actual_size -= PAGE_SIZE; - if (actual_size > ACCESS_ONCE(rlim[RLIMIT_STACK].rlim_cur)) + if (actual_size > READ_ONCE(rlim[RLIMIT_STACK].rlim_cur)) return -ENOMEM; /* mlock limit tests */ @@ -2110,7 +2108,7 @@ static int acct_stack_growth(struct vm_area_struct *vma, unsigned long size, uns unsigned long locked; unsigned long limit; locked = mm->locked_vm + grow; - limit = ACCESS_ONCE(rlim[RLIMIT_MEMLOCK].rlim_cur); + limit = READ_ONCE(rlim[RLIMIT_MEMLOCK].rlim_cur); limit >>= PAGE_SHIFT; if (locked > limit && !capable(CAP_IPC_LOCK)) return -ENOMEM; @@ -2318,7 +2316,7 @@ find_extend_vma(struct mm_struct *mm, unsigned long addr) if (!prev || expand_stack(prev, addr)) return NULL; if (prev->vm_flags & VM_LOCKED) - __mlock_vma_pages_range(prev, addr, prev->vm_end, NULL); + populate_vma_page_range(prev, addr, prev->vm_end, NULL); return prev; } #else @@ -2353,7 +2351,7 @@ find_extend_vma(struct mm_struct *mm, unsigned long addr) if (expand_stack(vma, addr)) return NULL; if (vma->vm_flags & VM_LOCKED) - __mlock_vma_pages_range(vma, addr, start, NULL); + populate_vma_page_range(vma, addr, start, NULL); return vma; } #endif @@ -2741,11 +2739,10 @@ static unsigned long do_brk(unsigned long addr, unsigned long len) /* * Clear old maps. this also does some error checking for us */ - munmap_back: - if (find_vma_links(mm, addr, addr + len, &prev, &rb_link, &rb_parent)) { + while (find_vma_links(mm, addr, addr + len, &prev, &rb_link, + &rb_parent)) { if (do_munmap(mm, addr, len)) return -ENOMEM; - goto munmap_back; } /* Check against address space limits *after* clearing old maps... */ diff --git a/mm/mprotect.c b/mm/mprotect.c index 44727811bf4c..88584838e704 100644 --- a/mm/mprotect.c +++ b/mm/mprotect.c @@ -75,6 +75,7 @@ static unsigned long change_pte_range(struct vm_area_struct *vma, pmd_t *pmd, oldpte = *pte; if (pte_present(oldpte)) { pte_t ptent; + bool preserve_write = prot_numa && pte_write(oldpte); /* * Avoid trapping faults against the zero or KSM @@ -94,6 +95,8 @@ static unsigned long change_pte_range(struct vm_area_struct *vma, pmd_t *pmd, ptent = ptep_modify_prot_start(mm, addr, pte); ptent = pte_modify(ptent, newprot); + if (preserve_write) + ptent = pte_mkwrite(ptent); /* Avoid taking write faults for known dirty pages */ if (dirty_accountable && pte_dirty(ptent) && diff --git a/mm/mremap.c b/mm/mremap.c index 57dadc025c64..034e2d360652 100644 --- a/mm/mremap.c +++ b/mm/mremap.c @@ -286,8 +286,14 @@ static unsigned long move_vma(struct vm_area_struct *vma, old_len = new_len; old_addr = new_addr; new_addr = -ENOMEM; - } else if (vma->vm_file && vma->vm_file->f_op->mremap) - vma->vm_file->f_op->mremap(vma->vm_file, new_vma); + } else if (vma->vm_file && vma->vm_file->f_op->mremap) { + err = vma->vm_file->f_op->mremap(vma->vm_file, new_vma); + if (err < 0) { + move_page_tables(new_vma, new_addr, vma, old_addr, + moved_len, true); + return err; + } + } /* Conceal VM_ACCOUNT so old reservation is not undone */ if (vm_flags & VM_ACCOUNT) { @@ -339,25 +345,25 @@ static struct vm_area_struct *vma_to_resize(unsigned long addr, struct vm_area_struct *vma = find_vma(mm, addr); if (!vma || vma->vm_start > addr) - goto Efault; + return ERR_PTR(-EFAULT); if (is_vm_hugetlb_page(vma)) - goto Einval; + return ERR_PTR(-EINVAL); /* We can't remap across vm area boundaries */ if (old_len > vma->vm_end - addr) - goto Efault; + return ERR_PTR(-EFAULT); /* Need to be careful about a growing mapping */ if (new_len > old_len) { unsigned long pgoff; if (vma->vm_flags & (VM_DONTEXPAND | VM_PFNMAP)) - goto Efault; + return ERR_PTR(-EFAULT); pgoff = (addr - vma->vm_start) >> PAGE_SHIFT; pgoff += vma->vm_pgoff; if (pgoff + (new_len >> PAGE_SHIFT) < pgoff) - goto Einval; + return ERR_PTR(-EINVAL); } if (vma->vm_flags & VM_LOCKED) { @@ -366,29 +372,20 @@ static struct vm_area_struct *vma_to_resize(unsigned long addr, lock_limit = rlimit(RLIMIT_MEMLOCK); locked += new_len - old_len; if (locked > lock_limit && !capable(CAP_IPC_LOCK)) - goto Eagain; + return ERR_PTR(-EAGAIN); } if (!may_expand_vm(mm, (new_len - old_len) >> PAGE_SHIFT)) - goto Enomem; + return ERR_PTR(-ENOMEM); if (vma->vm_flags & VM_ACCOUNT) { unsigned long charged = (new_len - old_len) >> PAGE_SHIFT; if (security_vm_enough_memory_mm(mm, charged)) - goto Efault; + return ERR_PTR(-ENOMEM); *p = charged; } return vma; - -Efault: /* very odd choice for most of the cases, but... */ - return ERR_PTR(-EFAULT); -Einval: - return ERR_PTR(-EINVAL); -Enomem: - return ERR_PTR(-ENOMEM); -Eagain: - return ERR_PTR(-EAGAIN); } static unsigned long mremap_to(unsigned long addr, unsigned long old_len, diff --git a/mm/nommu.c b/mm/nommu.c index 3e67e7538ecf..e544508e2a4b 100644 --- a/mm/nommu.c +++ b/mm/nommu.c @@ -62,6 +62,7 @@ void *high_memory; EXPORT_SYMBOL(high_memory); struct page *mem_map; unsigned long max_mapnr; +EXPORT_SYMBOL(max_mapnr); unsigned long highest_memmap_pfn; struct percpu_counter vm_committed_as; int sysctl_overcommit_memory = OVERCOMMIT_GUESS; /* heuristic overcommit */ @@ -1015,7 +1016,7 @@ static int validate_mmap_request(struct file *file, * device */ if (!file->f_op->get_unmapped_area) capabilities &= ~NOMMU_MAP_DIRECT; - if (!file->f_op->read) + if (!(file->f_mode & FMODE_CAN_READ)) capabilities &= ~NOMMU_MAP_COPY; /* The file shall have been opened with read permission. */ @@ -1239,7 +1240,7 @@ static int do_mmap_private(struct vm_area_struct *vma, old_fs = get_fs(); set_fs(KERNEL_DS); - ret = vma->vm_file->f_op->read(vma->vm_file, base, len, &fpos); + ret = __vfs_read(vma->vm_file, base, len, &fpos); set_fs(old_fs); if (ret < 0) diff --git a/mm/oom_kill.c b/mm/oom_kill.c index 642f38cb175a..2b665da1b3c9 100644 --- a/mm/oom_kill.c +++ b/mm/oom_kill.c @@ -408,7 +408,7 @@ bool oom_killer_disabled __read_mostly; static DECLARE_RWSEM(oom_sem); /** - * mark_tsk_oom_victim - marks the given taks as OOM victim. + * mark_tsk_oom_victim - marks the given task as OOM victim. * @tsk: task to mark * * Has to be called with oom_sem taken for read and never after @@ -612,7 +612,8 @@ void oom_kill_process(struct task_struct *p, gfp_t gfp_mask, int order, * Determines whether the kernel must panic because of the panic_on_oom sysctl. */ void check_panic_on_oom(enum oom_constraint constraint, gfp_t gfp_mask, - int order, const nodemask_t *nodemask) + int order, const nodemask_t *nodemask, + struct mem_cgroup *memcg) { if (likely(!sysctl_panic_on_oom)) return; @@ -625,7 +626,7 @@ void check_panic_on_oom(enum oom_constraint constraint, gfp_t gfp_mask, if (constraint != CONSTRAINT_NONE) return; } - dump_header(NULL, gfp_mask, order, NULL, nodemask); + dump_header(NULL, gfp_mask, order, memcg, nodemask); panic("Out of memory: %s panic_on_oom is enabled\n", sysctl_panic_on_oom == 2 ? "compulsory" : "system-wide"); } @@ -740,7 +741,7 @@ static void __out_of_memory(struct zonelist *zonelist, gfp_t gfp_mask, constraint = constrained_alloc(zonelist, gfp_mask, nodemask, &totalpages); mpol_mask = (constraint == CONSTRAINT_MEMORY_POLICY) ? nodemask : NULL; - check_panic_on_oom(constraint, gfp_mask, order, mpol_mask); + check_panic_on_oom(constraint, gfp_mask, order, mpol_mask, NULL); if (sysctl_oom_kill_allocating_task && current->mm && !oom_unkillable_task(current, NULL, nodemask) && diff --git a/mm/page-writeback.c b/mm/page-writeback.c index 45e187b2d971..5daf5568b9e1 100644 --- a/mm/page-writeback.c +++ b/mm/page-writeback.c @@ -857,8 +857,11 @@ static void bdi_update_write_bandwidth(struct backing_dev_info *bdi, * bw * elapsed + write_bandwidth * (period - elapsed) * write_bandwidth = --------------------------------------------------- * period + * + * @written may have decreased due to account_page_redirty(). + * Avoid underflowing @bw calculation. */ - bw = written - bdi->written_stamp; + bw = written - min(written, bdi->written_stamp); bw *= HZ; if (unlikely(elapsed > period)) { do_div(bw, elapsed); @@ -922,7 +925,7 @@ static void global_update_bandwidth(unsigned long thresh, unsigned long now) { static DEFINE_SPINLOCK(dirty_lock); - static unsigned long update_time; + static unsigned long update_time = INITIAL_JIFFIES; /* * check locklessly first to optimize away locking for the most time @@ -2108,6 +2111,25 @@ void account_page_dirtied(struct page *page, struct address_space *mapping) EXPORT_SYMBOL(account_page_dirtied); /* + * Helper function for deaccounting dirty page without writeback. + * + * Doing this should *normally* only ever be done when a page + * is truncated, and is not actually mapped anywhere at all. However, + * fs/buffer.c does this when it notices that somebody has cleaned + * out all the buffers on a page without actually doing it through + * the VM. Can you say "ext3 is horribly ugly"? Thought you could. + */ +void account_page_cleaned(struct page *page, struct address_space *mapping) +{ + if (mapping_cap_account_dirty(mapping)) { + dec_zone_page_state(page, NR_FILE_DIRTY); + dec_bdi_stat(inode_to_bdi(mapping->host), BDI_RECLAIMABLE); + task_io_account_cancelled_write(PAGE_CACHE_SIZE); + } +} +EXPORT_SYMBOL(account_page_cleaned); + +/* * For address_spaces which do not use buffers. Just tag the page as dirty in * its radix tree. * @@ -2206,7 +2228,8 @@ int set_page_dirty(struct page *page) * it will confuse readahead and make it restart the size rampup * process. But it's a trivial problem. */ - ClearPageReclaim(page); + if (PageReclaim(page)) + ClearPageReclaim(page); #ifdef CONFIG_BLOCK if (!spd) spd = __set_page_dirty_buffers; diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 7abfa70cdc1a..ebffa0e4a9c0 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -1032,11 +1032,9 @@ struct page *__rmqueue_smallest(struct zone *zone, unsigned int order, static int fallbacks[MIGRATE_TYPES][4] = { [MIGRATE_UNMOVABLE] = { MIGRATE_RECLAIMABLE, MIGRATE_MOVABLE, MIGRATE_RESERVE }, [MIGRATE_RECLAIMABLE] = { MIGRATE_UNMOVABLE, MIGRATE_MOVABLE, MIGRATE_RESERVE }, + [MIGRATE_MOVABLE] = { MIGRATE_RECLAIMABLE, MIGRATE_UNMOVABLE, MIGRATE_RESERVE }, #ifdef CONFIG_CMA - [MIGRATE_MOVABLE] = { MIGRATE_CMA, MIGRATE_RECLAIMABLE, MIGRATE_UNMOVABLE, MIGRATE_RESERVE }, [MIGRATE_CMA] = { MIGRATE_RESERVE }, /* Never used */ -#else - [MIGRATE_MOVABLE] = { MIGRATE_RECLAIMABLE, MIGRATE_UNMOVABLE, MIGRATE_RESERVE }, #endif [MIGRATE_RESERVE] = { MIGRATE_RESERVE }, /* Never used */ #ifdef CONFIG_MEMORY_ISOLATION @@ -1044,6 +1042,17 @@ static int fallbacks[MIGRATE_TYPES][4] = { #endif }; +#ifdef CONFIG_CMA +static struct page *__rmqueue_cma_fallback(struct zone *zone, + unsigned int order) +{ + return __rmqueue_smallest(zone, order, MIGRATE_CMA); +} +#else +static inline struct page *__rmqueue_cma_fallback(struct zone *zone, + unsigned int order) { return NULL; } +#endif + /* * Move the free pages in a range to the free lists of the requested type. * Note that start_page and end_pages are not aligned on a pageblock @@ -1136,14 +1145,40 @@ static void change_pageblock_range(struct page *pageblock_page, * as fragmentation caused by those allocations polluting movable pageblocks * is worse than movable allocations stealing from unmovable and reclaimable * pageblocks. - * - * If we claim more than half of the pageblock, change pageblock's migratetype - * as well. */ -static void try_to_steal_freepages(struct zone *zone, struct page *page, - int start_type, int fallback_type) +static bool can_steal_fallback(unsigned int order, int start_mt) +{ + /* + * Leaving this order check is intended, although there is + * relaxed order check in next check. The reason is that + * we can actually steal whole pageblock if this condition met, + * but, below check doesn't guarantee it and that is just heuristic + * so could be changed anytime. + */ + if (order >= pageblock_order) + return true; + + if (order >= pageblock_order / 2 || + start_mt == MIGRATE_RECLAIMABLE || + start_mt == MIGRATE_UNMOVABLE || + page_group_by_mobility_disabled) + return true; + + return false; +} + +/* + * This function implements actual steal behaviour. If order is large enough, + * we can steal whole pageblock. If not, we first move freepages in this + * pageblock and check whether half of pages are moved or not. If half of + * pages are moved, we can change migratetype of pageblock and permanently + * use it's pages as requested migratetype in the future. + */ +static void steal_suitable_fallback(struct zone *zone, struct page *page, + int start_type) { int current_order = page_order(page); + int pages; /* Take ownership for orders >= pageblock_order */ if (current_order >= pageblock_order) { @@ -1151,19 +1186,49 @@ static void try_to_steal_freepages(struct zone *zone, struct page *page, return; } - if (current_order >= pageblock_order / 2 || - start_type == MIGRATE_RECLAIMABLE || - start_type == MIGRATE_UNMOVABLE || - page_group_by_mobility_disabled) { - int pages; + pages = move_freepages_block(zone, page, start_type); + + /* Claim the whole block if over half of it is free */ + if (pages >= (1 << (pageblock_order-1)) || + page_group_by_mobility_disabled) + set_pageblock_migratetype(page, start_type); +} + +/* + * Check whether there is a suitable fallback freepage with requested order. + * If only_stealable is true, this function returns fallback_mt only if + * we can steal other freepages all together. This would help to reduce + * fragmentation due to mixed migratetype pages in one pageblock. + */ +int find_suitable_fallback(struct free_area *area, unsigned int order, + int migratetype, bool only_stealable, bool *can_steal) +{ + int i; + int fallback_mt; + + if (area->nr_free == 0) + return -1; + + *can_steal = false; + for (i = 0;; i++) { + fallback_mt = fallbacks[migratetype][i]; + if (fallback_mt == MIGRATE_RESERVE) + break; + + if (list_empty(&area->free_list[fallback_mt])) + continue; - pages = move_freepages_block(zone, page, start_type); + if (can_steal_fallback(order, migratetype)) + *can_steal = true; - /* Claim the whole block if over half of it is free */ - if (pages >= (1 << (pageblock_order-1)) || - page_group_by_mobility_disabled) - set_pageblock_migratetype(page, start_type); + if (!only_stealable) + return fallback_mt; + + if (*can_steal) + return fallback_mt; } + + return -1; } /* Remove an element from the buddy allocator from the fallback list */ @@ -1173,64 +1238,45 @@ __rmqueue_fallback(struct zone *zone, unsigned int order, int start_migratetype) struct free_area *area; unsigned int current_order; struct page *page; + int fallback_mt; + bool can_steal; /* Find the largest possible block of pages in the other list */ for (current_order = MAX_ORDER-1; current_order >= order && current_order <= MAX_ORDER-1; --current_order) { - int i; - for (i = 0;; i++) { - int migratetype = fallbacks[start_migratetype][i]; - int buddy_type = start_migratetype; - - /* MIGRATE_RESERVE handled later if necessary */ - if (migratetype == MIGRATE_RESERVE) - break; - - area = &(zone->free_area[current_order]); - if (list_empty(&area->free_list[migratetype])) - continue; - - page = list_entry(area->free_list[migratetype].next, - struct page, lru); - area->nr_free--; - - if (!is_migrate_cma(migratetype)) { - try_to_steal_freepages(zone, page, - start_migratetype, - migratetype); - } else { - /* - * When borrowing from MIGRATE_CMA, we need to - * release the excess buddy pages to CMA - * itself, and we do not try to steal extra - * free pages. - */ - buddy_type = migratetype; - } + area = &(zone->free_area[current_order]); + fallback_mt = find_suitable_fallback(area, current_order, + start_migratetype, false, &can_steal); + if (fallback_mt == -1) + continue; - /* Remove the page from the freelists */ - list_del(&page->lru); - rmv_page_order(page); + page = list_entry(area->free_list[fallback_mt].next, + struct page, lru); + if (can_steal) + steal_suitable_fallback(zone, page, start_migratetype); - expand(zone, page, order, current_order, area, - buddy_type); + /* Remove the page from the freelists */ + area->nr_free--; + list_del(&page->lru); + rmv_page_order(page); - /* - * The freepage_migratetype may differ from pageblock's - * migratetype depending on the decisions in - * try_to_steal_freepages(). This is OK as long as it - * does not differ for MIGRATE_CMA pageblocks. For CMA - * we need to make sure unallocated pages flushed from - * pcp lists are returned to the correct freelist. - */ - set_freepage_migratetype(page, buddy_type); + expand(zone, page, order, current_order, area, + start_migratetype); + /* + * The freepage_migratetype may differ from pageblock's + * migratetype depending on the decisions in + * try_to_steal_freepages(). This is OK as long as it + * does not differ for MIGRATE_CMA pageblocks. For CMA + * we need to make sure unallocated pages flushed from + * pcp lists are returned to the correct freelist. + */ + set_freepage_migratetype(page, start_migratetype); - trace_mm_page_alloc_extfrag(page, order, current_order, - start_migratetype, migratetype); + trace_mm_page_alloc_extfrag(page, order, current_order, + start_migratetype, fallback_mt); - return page; - } + return page; } return NULL; @@ -1249,7 +1295,11 @@ retry_reserve: page = __rmqueue_smallest(zone, order, migratetype); if (unlikely(!page) && migratetype != MIGRATE_RESERVE) { - page = __rmqueue_fallback(zone, order, migratetype); + if (migratetype == MIGRATE_MOVABLE) + page = __rmqueue_cma_fallback(zone, order); + + if (!page) + page = __rmqueue_fallback(zone, order, migratetype); /* * Use MIGRATE_RESERVE rather than fail an allocation. goto @@ -1321,7 +1371,7 @@ void drain_zone_pages(struct zone *zone, struct per_cpu_pages *pcp) int to_drain, batch; local_irq_save(flags); - batch = ACCESS_ONCE(pcp->batch); + batch = READ_ONCE(pcp->batch); to_drain = min(pcp->count, batch); if (to_drain > 0) { free_pcppages_bulk(zone, to_drain, pcp); @@ -1520,7 +1570,7 @@ void free_hot_cold_page(struct page *page, bool cold) list_add_tail(&page->lru, &pcp->lists[migratetype]); pcp->count++; if (pcp->count >= pcp->high) { - unsigned long batch = ACCESS_ONCE(pcp->batch); + unsigned long batch = READ_ONCE(pcp->batch); free_pcppages_bulk(zone, batch, pcp); pcp->count -= batch; } @@ -2362,18 +2412,13 @@ __alloc_pages_may_oom(gfp_t gfp_mask, unsigned int order, *did_some_progress = 1; goto out; } - /* - * GFP_THISNODE contains __GFP_NORETRY and we never hit this. - * Sanity check for bare calls of __GFP_THISNODE, not real OOM. - * The caller should handle page allocation failure by itself if - * it specifies __GFP_THISNODE. - * Note: Hugepage uses it but will hit PAGE_ALLOC_COSTLY_ORDER. - */ + /* The OOM killer may not free memory on a specific node */ if (gfp_mask & __GFP_THISNODE) goto out; } /* Exhausted what can be done so it's blamo time */ - if (out_of_memory(ac->zonelist, gfp_mask, order, ac->nodemask, false)) + if (out_of_memory(ac->zonelist, gfp_mask, order, ac->nodemask, false) + || WARN_ON_ONCE(gfp_mask & __GFP_NOFAIL)) *did_some_progress = 1; out: oom_zonelist_unlock(ac->zonelist, gfp_mask); @@ -2622,15 +2667,11 @@ __alloc_pages_slowpath(gfp_t gfp_mask, unsigned int order, } /* - * GFP_THISNODE (meaning __GFP_THISNODE, __GFP_NORETRY and - * __GFP_NOWARN set) should not cause reclaim since the subsystem - * (f.e. slab) using GFP_THISNODE may choose to trigger reclaim - * using a larger set of nodes after it has established that the - * allowed per node queues are empty and that nodes are - * over allocated. + * If this allocation cannot block and it is for a specific node, then + * fail early. There's no need to wakeup kswapd or retry for a + * speculative node-specific allocation. */ - if (IS_ENABLED(CONFIG_NUMA) && - (gfp_mask & GFP_THISNODE) == GFP_THISNODE) + if (IS_ENABLED(CONFIG_NUMA) && (gfp_mask & __GFP_THISNODE) && !wait) goto nopage; retry: @@ -2823,7 +2864,7 @@ __alloc_pages_nodemask(gfp_t gfp_mask, unsigned int order, /* * Check the zones suitable for the gfp_mask contain at least one * valid zone. It's possible to have an empty zonelist as a result - * of GFP_THISNODE and a memoryless node + * of __GFP_THISNODE and a memoryless node */ if (unlikely(!zonelist->_zonerefs->zone)) return NULL; @@ -3200,38 +3241,31 @@ static void show_migration_types(unsigned char type) * Show free area list (used inside shift_scroll-lock stuff) * We also calculate the percentage fragmentation. We do this by counting the * memory on each free list with the exception of the first item on the list. - * Suppresses nodes that are not allowed by current's cpuset if - * SHOW_MEM_FILTER_NODES is passed. + * + * Bits in @filter: + * SHOW_MEM_FILTER_NODES: suppress nodes that are not allowed by current's + * cpuset. */ void show_free_areas(unsigned int filter) { + unsigned long free_pcp = 0; int cpu; struct zone *zone; for_each_populated_zone(zone) { if (skip_free_areas_node(filter, zone_to_nid(zone))) continue; - show_node(zone); - printk("%s per-cpu:\n", zone->name); - for_each_online_cpu(cpu) { - struct per_cpu_pageset *pageset; - - pageset = per_cpu_ptr(zone->pageset, cpu); - - printk("CPU %4d: hi:%5d, btch:%4d usd:%4d\n", - cpu, pageset->pcp.high, - pageset->pcp.batch, pageset->pcp.count); - } + for_each_online_cpu(cpu) + free_pcp += per_cpu_ptr(zone->pageset, cpu)->pcp.count; } printk("active_anon:%lu inactive_anon:%lu isolated_anon:%lu\n" " active_file:%lu inactive_file:%lu isolated_file:%lu\n" - " unevictable:%lu" - " dirty:%lu writeback:%lu unstable:%lu\n" - " free:%lu slab_reclaimable:%lu slab_unreclaimable:%lu\n" + " unevictable:%lu dirty:%lu writeback:%lu unstable:%lu\n" + " slab_reclaimable:%lu slab_unreclaimable:%lu\n" " mapped:%lu shmem:%lu pagetables:%lu bounce:%lu\n" - " free_cma:%lu\n", + " free:%lu free_pcp:%lu free_cma:%lu\n", global_page_state(NR_ACTIVE_ANON), global_page_state(NR_INACTIVE_ANON), global_page_state(NR_ISOLATED_ANON), @@ -3242,13 +3276,14 @@ void show_free_areas(unsigned int filter) global_page_state(NR_FILE_DIRTY), global_page_state(NR_WRITEBACK), global_page_state(NR_UNSTABLE_NFS), - global_page_state(NR_FREE_PAGES), global_page_state(NR_SLAB_RECLAIMABLE), global_page_state(NR_SLAB_UNRECLAIMABLE), global_page_state(NR_FILE_MAPPED), global_page_state(NR_SHMEM), global_page_state(NR_PAGETABLE), global_page_state(NR_BOUNCE), + global_page_state(NR_FREE_PAGES), + free_pcp, global_page_state(NR_FREE_CMA_PAGES)); for_each_populated_zone(zone) { @@ -3256,6 +3291,11 @@ void show_free_areas(unsigned int filter) if (skip_free_areas_node(filter, zone_to_nid(zone))) continue; + + free_pcp = 0; + for_each_online_cpu(cpu) + free_pcp += per_cpu_ptr(zone->pageset, cpu)->pcp.count; + show_node(zone); printk("%s" " free:%lukB" @@ -3282,6 +3322,8 @@ void show_free_areas(unsigned int filter) " pagetables:%lukB" " unstable:%lukB" " bounce:%lukB" + " free_pcp:%lukB" + " local_pcp:%ukB" " free_cma:%lukB" " writeback_tmp:%lukB" " pages_scanned:%lu" @@ -3313,6 +3355,8 @@ void show_free_areas(unsigned int filter) K(zone_page_state(zone, NR_PAGETABLE)), K(zone_page_state(zone, NR_UNSTABLE_NFS)), K(zone_page_state(zone, NR_BOUNCE)), + K(free_pcp), + K(this_cpu_read(zone->pageset->pcp.count)), K(zone_page_state(zone, NR_FREE_CMA_PAGES)), K(zone_page_state(zone, NR_WRITEBACK_TEMP)), K(zone_page_state(zone, NR_PAGES_SCANNED)), @@ -5716,7 +5760,7 @@ static void __setup_per_zone_wmarks(void) * value here. * * The WMARK_HIGH-WMARK_LOW and (WMARK_LOW-WMARK_MIN) - * deltas controls asynch page reclaim, and so should + * deltas control asynch page reclaim, and so should * not be capped for highmem. */ unsigned long min_pages; @@ -6163,7 +6207,7 @@ void set_pfnblock_flags_mask(struct page *page, unsigned long flags, mask <<= (BITS_PER_LONG - bitidx - 1); flags <<= (BITS_PER_LONG - bitidx - 1); - word = ACCESS_ONCE(bitmap[word_bitidx]); + word = READ_ONCE(bitmap[word_bitidx]); for (;;) { old_word = cmpxchg(&bitmap[word_bitidx], word, (word & ~mask) | flags); if (word == old_word) diff --git a/mm/page_io.c b/mm/page_io.c index e6045804c8d8..6424869e275e 100644 --- a/mm/page_io.c +++ b/mm/page_io.c @@ -20,8 +20,8 @@ #include <linux/buffer_head.h> #include <linux/writeback.h> #include <linux/frontswap.h> -#include <linux/aio.h> #include <linux/blkdev.h> +#include <linux/uio.h> #include <asm/pgtable.h> static struct bio *get_swap_bio(gfp_t gfp_flags, @@ -274,13 +274,10 @@ int __swap_writepage(struct page *page, struct writeback_control *wbc, iov_iter_bvec(&from, ITER_BVEC | WRITE, &bv, 1, PAGE_SIZE); init_sync_kiocb(&kiocb, swap_file); kiocb.ki_pos = page_file_offset(page); - kiocb.ki_nbytes = PAGE_SIZE; set_page_writeback(page); unlock_page(page); - ret = mapping->a_ops->direct_IO(ITER_BVEC | WRITE, - &kiocb, &from, - kiocb.ki_pos); + ret = mapping->a_ops->direct_IO(&kiocb, &from, kiocb.ki_pos); if (ret == PAGE_SIZE) { count_vm_event(PSWPOUT); ret = 0; diff --git a/mm/page_isolation.c b/mm/page_isolation.c index 72f5ac381ab3..755a42c76eb4 100644 --- a/mm/page_isolation.c +++ b/mm/page_isolation.c @@ -103,6 +103,7 @@ void unset_migratetype_isolate(struct page *page, unsigned migratetype) if (!is_migrate_isolate_page(buddy)) { __isolate_free_page(page, order); + kernel_map_pages(page, (1 << order), 1); set_page_refcounted(page); isolated_page = page; } diff --git a/mm/pagewalk.c b/mm/pagewalk.c index 75c1f2878519..29f2f8b853ae 100644 --- a/mm/pagewalk.c +++ b/mm/pagewalk.c @@ -265,8 +265,15 @@ int walk_page_range(unsigned long start, unsigned long end, vma = vma->vm_next; err = walk_page_test(start, next, walk); - if (err > 0) + if (err > 0) { + /* + * positive return values are purely for + * controlling the pagewalk, so should never + * be passed to the callers. + */ + err = 0; continue; + } if (err < 0) break; } diff --git a/mm/percpu.c b/mm/percpu.c index 73c97a5f4495..dfd02484e8de 100644 --- a/mm/percpu.c +++ b/mm/percpu.c @@ -1310,7 +1310,7 @@ bool is_kernel_percpu_address(unsigned long addr) * and, from the second one, the backing allocator (currently either vm or * km) provides translation. * - * The addr can be tranlated simply without checking if it falls into the + * The addr can be translated simply without checking if it falls into the * first chunk. But the current code reflects better how percpu allocator * actually works, and the verification can discover both bugs in percpu * allocator itself and per_cpu_ptr_to_phys() callers. So we keep current @@ -1762,7 +1762,7 @@ early_param("percpu_alloc", percpu_alloc_setup); * and other parameters considering needed percpu size, allocation * atom size and distances between CPUs. * - * Groups are always mutliples of atom size and CPUs which are of + * Groups are always multiples of atom size and CPUs which are of * LOCAL_DISTANCE both ways are grouped together and share space for * units in the same group. The returned configuration is guaranteed * to have CPUs on different nodes on different groups and >=75% usage diff --git a/mm/process_vm_access.c b/mm/process_vm_access.c index b1597690530c..e88d071648c2 100644 --- a/mm/process_vm_access.c +++ b/mm/process_vm_access.c @@ -257,22 +257,18 @@ static ssize_t process_vm_rw(pid_t pid, struct iovec *iov_r = iovstack_r; struct iov_iter iter; ssize_t rc; + int dir = vm_write ? WRITE : READ; if (flags != 0) return -EINVAL; /* Check iovecs */ - if (vm_write) - rc = rw_copy_check_uvector(WRITE, lvec, liovcnt, UIO_FASTIOV, - iovstack_l, &iov_l); - else - rc = rw_copy_check_uvector(READ, lvec, liovcnt, UIO_FASTIOV, - iovstack_l, &iov_l); - if (rc <= 0) + rc = import_iovec(dir, lvec, liovcnt, UIO_FASTIOV, &iov_l, &iter); + if (rc < 0) + return rc; + if (!iov_iter_count(&iter)) goto free_iovecs; - iov_iter_init(&iter, vm_write ? WRITE : READ, iov_l, liovcnt, rc); - rc = rw_copy_check_uvector(CHECK_IOVEC_ONLY, rvec, riovcnt, UIO_FASTIOV, iovstack_r, &iov_r); if (rc <= 0) @@ -283,8 +279,7 @@ static ssize_t process_vm_rw(pid_t pid, free_iovecs: if (iov_r != iovstack_r) kfree(iov_r); - if (iov_l != iovstack_l) - kfree(iov_l); + kfree(iov_l); return rc; } @@ -320,21 +315,16 @@ compat_process_vm_rw(compat_pid_t pid, struct iovec *iov_r = iovstack_r; struct iov_iter iter; ssize_t rc = -EFAULT; + int dir = vm_write ? WRITE : READ; if (flags != 0) return -EINVAL; - if (vm_write) - rc = compat_rw_copy_check_uvector(WRITE, lvec, liovcnt, - UIO_FASTIOV, iovstack_l, - &iov_l); - else - rc = compat_rw_copy_check_uvector(READ, lvec, liovcnt, - UIO_FASTIOV, iovstack_l, - &iov_l); - if (rc <= 0) + rc = compat_import_iovec(dir, lvec, liovcnt, UIO_FASTIOV, &iov_l, &iter); + if (rc < 0) + return rc; + if (!iov_iter_count(&iter)) goto free_iovecs; - iov_iter_init(&iter, vm_write ? WRITE : READ, iov_l, liovcnt, rc); rc = compat_rw_copy_check_uvector(CHECK_IOVEC_ONLY, rvec, riovcnt, UIO_FASTIOV, iovstack_r, &iov_r); @@ -346,8 +336,7 @@ compat_process_vm_rw(compat_pid_t pid, free_iovecs: if (iov_r != iovstack_r) kfree(iov_r); - if (iov_l != iovstack_l) - kfree(iov_l); + kfree(iov_l); return rc; } diff --git a/mm/rmap.c b/mm/rmap.c index 5e3e09081164..24dd3f9fee27 100644 --- a/mm/rmap.c +++ b/mm/rmap.c @@ -287,6 +287,13 @@ int anon_vma_clone(struct vm_area_struct *dst, struct vm_area_struct *src) return 0; enomem_failure: + /* + * dst->anon_vma is dropped here otherwise its degree can be incorrectly + * decremented in unlink_anon_vmas(). + * We can safely do this because callers of anon_vma_clone() don't care + * about dst->anon_vma if anon_vma_clone() failed. + */ + dst->anon_vma = NULL; unlink_anon_vmas(dst); return -ENOMEM; } @@ -449,7 +456,7 @@ struct anon_vma *page_get_anon_vma(struct page *page) unsigned long anon_mapping; rcu_read_lock(); - anon_mapping = (unsigned long) ACCESS_ONCE(page->mapping); + anon_mapping = (unsigned long)READ_ONCE(page->mapping); if ((anon_mapping & PAGE_MAPPING_FLAGS) != PAGE_MAPPING_ANON) goto out; if (!page_mapped(page)) @@ -493,14 +500,14 @@ struct anon_vma *page_lock_anon_vma_read(struct page *page) unsigned long anon_mapping; rcu_read_lock(); - anon_mapping = (unsigned long) ACCESS_ONCE(page->mapping); + anon_mapping = (unsigned long)READ_ONCE(page->mapping); if ((anon_mapping & PAGE_MAPPING_FLAGS) != PAGE_MAPPING_ANON) goto out; if (!page_mapped(page)) goto out; anon_vma = (struct anon_vma *) (anon_mapping - PAGE_MAPPING_ANON); - root_anon_vma = ACCESS_ONCE(anon_vma->root); + root_anon_vma = READ_ONCE(anon_vma->root); if (down_read_trylock(&root_anon_vma->rwsem)) { /* * If the page is still mapped, then this anon_vma is still diff --git a/mm/shmem.c b/mm/shmem.c index cf2d0ca010bc..de981370fbc5 100644 --- a/mm/shmem.c +++ b/mm/shmem.c @@ -31,7 +31,7 @@ #include <linux/mm.h> #include <linux/export.h> #include <linux/swap.h> -#include <linux/aio.h> +#include <linux/uio.h> static struct vfsmount *shm_mnt; @@ -544,7 +544,7 @@ EXPORT_SYMBOL_GPL(shmem_truncate_range); static int shmem_setattr(struct dentry *dentry, struct iattr *attr) { - struct inode *inode = dentry->d_inode; + struct inode *inode = d_inode(dentry); struct shmem_inode_info *info = SHMEM_I(inode); int error; @@ -2274,7 +2274,7 @@ static int shmem_create(struct inode *dir, struct dentry *dentry, umode_t mode, */ static int shmem_link(struct dentry *old_dentry, struct inode *dir, struct dentry *dentry) { - struct inode *inode = old_dentry->d_inode; + struct inode *inode = d_inode(old_dentry); int ret; /* @@ -2298,7 +2298,7 @@ out: static int shmem_unlink(struct inode *dir, struct dentry *dentry) { - struct inode *inode = dentry->d_inode; + struct inode *inode = d_inode(dentry); if (inode->i_nlink > 1 && !S_ISDIR(inode->i_mode)) shmem_free_inode(inode->i_sb); @@ -2315,7 +2315,7 @@ static int shmem_rmdir(struct inode *dir, struct dentry *dentry) if (!simple_empty(dentry)) return -ENOTEMPTY; - drop_nlink(dentry->d_inode); + drop_nlink(d_inode(dentry)); drop_nlink(dir); return shmem_unlink(dir, dentry); } @@ -2336,8 +2336,8 @@ static int shmem_exchange(struct inode *old_dir, struct dentry *old_dentry, stru } old_dir->i_ctime = old_dir->i_mtime = new_dir->i_ctime = new_dir->i_mtime = - old_dentry->d_inode->i_ctime = - new_dentry->d_inode->i_ctime = CURRENT_TIME; + d_inode(old_dentry)->i_ctime = + d_inode(new_dentry)->i_ctime = CURRENT_TIME; return 0; } @@ -2376,7 +2376,7 @@ static int shmem_whiteout(struct inode *old_dir, struct dentry *old_dentry) */ static int shmem_rename2(struct inode *old_dir, struct dentry *old_dentry, struct inode *new_dir, struct dentry *new_dentry, unsigned int flags) { - struct inode *inode = old_dentry->d_inode; + struct inode *inode = d_inode(old_dentry); int they_are_dirs = S_ISDIR(inode->i_mode); if (flags & ~(RENAME_NOREPLACE | RENAME_EXCHANGE | RENAME_WHITEOUT)) @@ -2396,10 +2396,10 @@ static int shmem_rename2(struct inode *old_dir, struct dentry *old_dentry, struc return error; } - if (new_dentry->d_inode) { + if (d_really_is_positive(new_dentry)) { (void) shmem_unlink(new_dir, new_dentry); if (they_are_dirs) { - drop_nlink(new_dentry->d_inode); + drop_nlink(d_inode(new_dentry)); drop_nlink(old_dir); } } else if (they_are_dirs) { @@ -2476,14 +2476,14 @@ static int shmem_symlink(struct inode *dir, struct dentry *dentry, const char *s static void *shmem_follow_short_symlink(struct dentry *dentry, struct nameidata *nd) { - nd_set_link(nd, SHMEM_I(dentry->d_inode)->symlink); + nd_set_link(nd, SHMEM_I(d_inode(dentry))->symlink); return NULL; } static void *shmem_follow_link(struct dentry *dentry, struct nameidata *nd) { struct page *page = NULL; - int error = shmem_getpage(dentry->d_inode, 0, &page, SGP_READ, NULL); + int error = shmem_getpage(d_inode(dentry), 0, &page, SGP_READ, NULL); nd_set_link(nd, error ? ERR_PTR(error) : kmap(page)); if (page) unlock_page(page); @@ -2574,7 +2574,7 @@ static int shmem_xattr_validate(const char *name) static ssize_t shmem_getxattr(struct dentry *dentry, const char *name, void *buffer, size_t size) { - struct shmem_inode_info *info = SHMEM_I(dentry->d_inode); + struct shmem_inode_info *info = SHMEM_I(d_inode(dentry)); int err; /* @@ -2595,7 +2595,7 @@ static ssize_t shmem_getxattr(struct dentry *dentry, const char *name, static int shmem_setxattr(struct dentry *dentry, const char *name, const void *value, size_t size, int flags) { - struct shmem_inode_info *info = SHMEM_I(dentry->d_inode); + struct shmem_inode_info *info = SHMEM_I(d_inode(dentry)); int err; /* @@ -2615,7 +2615,7 @@ static int shmem_setxattr(struct dentry *dentry, const char *name, static int shmem_removexattr(struct dentry *dentry, const char *name) { - struct shmem_inode_info *info = SHMEM_I(dentry->d_inode); + struct shmem_inode_info *info = SHMEM_I(d_inode(dentry)); int err; /* @@ -2635,7 +2635,7 @@ static int shmem_removexattr(struct dentry *dentry, const char *name) static ssize_t shmem_listxattr(struct dentry *dentry, char *buffer, size_t size) { - struct shmem_inode_info *info = SHMEM_I(dentry->d_inode); + struct shmem_inode_info *info = SHMEM_I(d_inode(dentry)); return simple_xattr_list(&info->xattrs, buffer, size); } #endif /* CONFIG_TMPFS_XATTR */ @@ -3118,8 +3118,6 @@ static const struct file_operations shmem_file_operations = { .mmap = shmem_mmap, #ifdef CONFIG_TMPFS .llseek = shmem_file_llseek, - .read = new_sync_read, - .write = new_sync_write, .read_iter = shmem_file_read_iter, .write_iter = generic_file_write_iter, .fsync = noop_fsync, diff --git a/mm/slab.c b/mm/slab.c index c4b89eaf4c96..7eb38dd1cefa 100644 --- a/mm/slab.c +++ b/mm/slab.c @@ -857,6 +857,11 @@ static inline void *____cache_alloc_node(struct kmem_cache *cachep, return NULL; } +static inline gfp_t gfp_exact_node(gfp_t flags) +{ + return flags; +} + #else /* CONFIG_NUMA */ static void *____cache_alloc_node(struct kmem_cache *, gfp_t, int); @@ -1023,6 +1028,15 @@ static inline int cache_free_alien(struct kmem_cache *cachep, void *objp) return __cache_free_alien(cachep, objp, node, page_node); } + +/* + * Construct gfp mask to allocate from a specific node but do not invoke reclaim + * or warn about failures. + */ +static inline gfp_t gfp_exact_node(gfp_t flags) +{ + return (flags | __GFP_THISNODE | __GFP_NOWARN) & ~__GFP_WAIT; +} #endif /* @@ -2825,7 +2839,7 @@ alloc_done: if (unlikely(!ac->avail)) { int x; force_grow: - x = cache_grow(cachep, flags | GFP_THISNODE, node, NULL); + x = cache_grow(cachep, gfp_exact_node(flags), node, NULL); /* cache_grow can reenable interrupts, then ac could change. */ ac = cpu_cache_get(cachep); @@ -3019,7 +3033,7 @@ retry: get_node(cache, nid) && get_node(cache, nid)->free_objects) { obj = ____cache_alloc_node(cache, - flags | GFP_THISNODE, nid); + gfp_exact_node(flags), nid); if (obj) break; } @@ -3047,7 +3061,7 @@ retry: nid = page_to_nid(page); if (cache_grow(cache, flags, nid, page)) { obj = ____cache_alloc_node(cache, - flags | GFP_THISNODE, nid); + gfp_exact_node(flags), nid); if (!obj) /* * Another processor may allocate the @@ -3118,7 +3132,7 @@ retry: must_grow: spin_unlock(&n->list_lock); - x = cache_grow(cachep, flags | GFP_THISNODE, nodeid, NULL); + x = cache_grow(cachep, gfp_exact_node(flags), nodeid, NULL); if (x) goto retry; diff --git a/mm/slob.c b/mm/slob.c index 94a7fede6d48..4765f65019c7 100644 --- a/mm/slob.c +++ b/mm/slob.c @@ -532,7 +532,7 @@ int __kmem_cache_create(struct kmem_cache *c, unsigned long flags) return 0; } -void *slob_alloc_node(struct kmem_cache *c, gfp_t flags, int node) +static void *slob_alloc_node(struct kmem_cache *c, gfp_t flags, int node) { void *b; @@ -558,7 +558,6 @@ void *slob_alloc_node(struct kmem_cache *c, gfp_t flags, int node) kmemleak_alloc_recursive(b, c->size, 1, c->flags, flags); return b; } -EXPORT_SYMBOL(slob_alloc_node); void *kmem_cache_alloc(struct kmem_cache *cachep, gfp_t flags) { diff --git a/mm/slub.c b/mm/slub.c index 6832c4eab104..54c0876b43d5 100644 --- a/mm/slub.c +++ b/mm/slub.c @@ -374,7 +374,7 @@ static inline bool __cmpxchg_double_slab(struct kmem_cache *s, struct page *page if (cmpxchg_double(&page->freelist, &page->counters, freelist_old, counters_old, freelist_new, counters_new)) - return 1; + return true; } else #endif { @@ -384,7 +384,7 @@ static inline bool __cmpxchg_double_slab(struct kmem_cache *s, struct page *page page->freelist = freelist_new; set_page_slub_counters(page, counters_new); slab_unlock(page); - return 1; + return true; } slab_unlock(page); } @@ -396,7 +396,7 @@ static inline bool __cmpxchg_double_slab(struct kmem_cache *s, struct page *page pr_info("%s %s: cmpxchg double redo ", n, s->name); #endif - return 0; + return false; } static inline bool cmpxchg_double_slab(struct kmem_cache *s, struct page *page, @@ -410,7 +410,7 @@ static inline bool cmpxchg_double_slab(struct kmem_cache *s, struct page *page, if (cmpxchg_double(&page->freelist, &page->counters, freelist_old, counters_old, freelist_new, counters_new)) - return 1; + return true; } else #endif { @@ -424,7 +424,7 @@ static inline bool cmpxchg_double_slab(struct kmem_cache *s, struct page *page, set_page_slub_counters(page, counters_new); slab_unlock(page); local_irq_restore(flags); - return 1; + return true; } slab_unlock(page); local_irq_restore(flags); @@ -437,7 +437,7 @@ static inline bool cmpxchg_double_slab(struct kmem_cache *s, struct page *page, pr_info("%s %s: cmpxchg double redo ", n, s->name); #endif - return 0; + return false; } #ifdef CONFIG_SLUB_DEBUG @@ -1137,15 +1137,6 @@ static int __init setup_slub_debug(char *str) */ goto check_slabs; - if (tolower(*str) == 'o') { - /* - * Avoid enabling debugging on caches if its minimum order - * would increase as a result. - */ - disable_higher_order_debug = 1; - goto out; - } - slub_debug = 0; if (*str == '-') /* @@ -1176,6 +1167,13 @@ static int __init setup_slub_debug(char *str) case 'a': slub_debug |= SLAB_FAILSLAB; break; + case 'o': + /* + * Avoid enabling debugging on caches if its minimum + * order would increase as a result. + */ + disable_higher_order_debug = 1; + break; default: pr_err("slub_debug option '%c' unknown. skipped\n", *str); @@ -2449,7 +2447,8 @@ redo: do { tid = this_cpu_read(s->cpu_slab->tid); c = raw_cpu_ptr(s->cpu_slab); - } while (IS_ENABLED(CONFIG_PREEMPT) && unlikely(tid != c->tid)); + } while (IS_ENABLED(CONFIG_PREEMPT) && + unlikely(tid != READ_ONCE(c->tid))); /* * Irqless object alloc/free algorithm used here depends on sequence @@ -2718,7 +2717,8 @@ redo: do { tid = this_cpu_read(s->cpu_slab->tid); c = raw_cpu_ptr(s->cpu_slab); - } while (IS_ENABLED(CONFIG_PREEMPT) && unlikely(tid != c->tid)); + } while (IS_ENABLED(CONFIG_PREEMPT) && + unlikely(tid != READ_ONCE(c->tid))); /* Same with comment on barrier() in slab_alloc_node() */ barrier(); @@ -4277,7 +4277,7 @@ static ssize_t show_slab_objects(struct kmem_cache *s, int node; struct page *page; - page = ACCESS_ONCE(c->page); + page = READ_ONCE(c->page); if (!page) continue; @@ -4292,7 +4292,7 @@ static ssize_t show_slab_objects(struct kmem_cache *s, total += x; nodes[node] += x; - page = ACCESS_ONCE(c->partial); + page = READ_ONCE(c->partial); if (page) { node = page_to_nid(page); if (flags & SO_TOTAL) diff --git a/mm/swap.c b/mm/swap.c index cd3a5e64cea9..a7251a8ed532 100644 --- a/mm/swap.c +++ b/mm/swap.c @@ -31,6 +31,7 @@ #include <linux/memcontrol.h> #include <linux/gfp.h> #include <linux/uio.h> +#include <linux/hugetlb.h> #include "internal.h" @@ -42,7 +43,7 @@ int page_cluster; static DEFINE_PER_CPU(struct pagevec, lru_add_pvec); static DEFINE_PER_CPU(struct pagevec, lru_rotate_pvecs); -static DEFINE_PER_CPU(struct pagevec, lru_deactivate_pvecs); +static DEFINE_PER_CPU(struct pagevec, lru_deactivate_file_pvecs); /* * This path almost never happens for VM activity - pages are normally @@ -75,7 +76,14 @@ static void __put_compound_page(struct page *page) { compound_page_dtor *dtor; - __page_cache_release(page); + /* + * __page_cache_release() is supposed to be called for thp, not for + * hugetlb. This is because hugetlb page does never have PageLRU set + * (it's never listed to any LRU lists) and no memcg routines should + * be called for hugetlb (it has a separate hugetlb_cgroup.) + */ + if (!PageHuge(page)) + __page_cache_release(page); dtor = get_compound_page_dtor(page); (*dtor)(page); } @@ -743,7 +751,7 @@ void lru_cache_add_active_or_unevictable(struct page *page, * be write it out by flusher threads as this is much more effective * than the single-page writeout from reclaim. */ -static void lru_deactivate_fn(struct page *page, struct lruvec *lruvec, +static void lru_deactivate_file_fn(struct page *page, struct lruvec *lruvec, void *arg) { int lru, file; @@ -811,36 +819,36 @@ void lru_add_drain_cpu(int cpu) local_irq_restore(flags); } - pvec = &per_cpu(lru_deactivate_pvecs, cpu); + pvec = &per_cpu(lru_deactivate_file_pvecs, cpu); if (pagevec_count(pvec)) - pagevec_lru_move_fn(pvec, lru_deactivate_fn, NULL); + pagevec_lru_move_fn(pvec, lru_deactivate_file_fn, NULL); activate_page_drain(cpu); } /** - * deactivate_page - forcefully deactivate a page + * deactivate_file_page - forcefully deactivate a file page * @page: page to deactivate * * This function hints the VM that @page is a good reclaim candidate, * for example if its invalidation fails due to the page being dirty * or under writeback. */ -void deactivate_page(struct page *page) +void deactivate_file_page(struct page *page) { /* - * In a workload with many unevictable page such as mprotect, unevictable - * page deactivation for accelerating reclaim is pointless. + * In a workload with many unevictable page such as mprotect, + * unevictable page deactivation for accelerating reclaim is pointless. */ if (PageUnevictable(page)) return; if (likely(get_page_unless_zero(page))) { - struct pagevec *pvec = &get_cpu_var(lru_deactivate_pvecs); + struct pagevec *pvec = &get_cpu_var(lru_deactivate_file_pvecs); if (!pagevec_add(pvec, page)) - pagevec_lru_move_fn(pvec, lru_deactivate_fn, NULL); - put_cpu_var(lru_deactivate_pvecs); + pagevec_lru_move_fn(pvec, lru_deactivate_file_fn, NULL); + put_cpu_var(lru_deactivate_file_pvecs); } } @@ -872,7 +880,7 @@ void lru_add_drain_all(void) if (pagevec_count(&per_cpu(lru_add_pvec, cpu)) || pagevec_count(&per_cpu(lru_rotate_pvecs, cpu)) || - pagevec_count(&per_cpu(lru_deactivate_pvecs, cpu)) || + pagevec_count(&per_cpu(lru_deactivate_file_pvecs, cpu)) || need_activate_page_drain(cpu)) { INIT_WORK(work, lru_add_drain_per_cpu); schedule_work_on(cpu, work); diff --git a/mm/swap_state.c b/mm/swap_state.c index 405923f77334..8bc8e66138da 100644 --- a/mm/swap_state.c +++ b/mm/swap_state.c @@ -390,7 +390,7 @@ static unsigned long swapin_nr_pages(unsigned long offset) unsigned int pages, max_pages, last_ra; static atomic_t last_readahead_pages; - max_pages = 1 << ACCESS_ONCE(page_cluster); + max_pages = 1 << READ_ONCE(page_cluster); if (max_pages <= 1) return 1; diff --git a/mm/swapfile.c b/mm/swapfile.c index 63f55ccb9b26..a7e72103f23b 100644 --- a/mm/swapfile.c +++ b/mm/swapfile.c @@ -1312,7 +1312,7 @@ static unsigned int find_next_to_unuse(struct swap_info_struct *si, else continue; } - count = ACCESS_ONCE(si->swap_map[i]); + count = READ_ONCE(si->swap_map[i]); if (count && swap_count(count) != SWAP_MAP_BAD) break; } diff --git a/mm/truncate.c b/mm/truncate.c index ddec5a5966d7..66af9031fae8 100644 --- a/mm/truncate.c +++ b/mm/truncate.c @@ -93,35 +93,6 @@ void do_invalidatepage(struct page *page, unsigned int offset, } /* - * This cancels just the dirty bit on the kernel page itself, it - * does NOT actually remove dirty bits on any mmap's that may be - * around. It also leaves the page tagged dirty, so any sync - * activity will still find it on the dirty lists, and in particular, - * clear_page_dirty_for_io() will still look at the dirty bits in - * the VM. - * - * Doing this should *normally* only ever be done when a page - * is truncated, and is not actually mapped anywhere at all. However, - * fs/buffer.c does this when it notices that somebody has cleaned - * out all the buffers on a page without actually doing it through - * the VM. Can you say "ext3 is horribly ugly"? Tought you could. - */ -void cancel_dirty_page(struct page *page, unsigned int account_size) -{ - if (TestClearPageDirty(page)) { - struct address_space *mapping = page->mapping; - if (mapping && mapping_cap_account_dirty(mapping)) { - dec_zone_page_state(page, NR_FILE_DIRTY); - dec_bdi_stat(inode_to_bdi(mapping->host), - BDI_RECLAIMABLE); - if (account_size) - task_io_account_cancelled_write(account_size); - } - } -} -EXPORT_SYMBOL(cancel_dirty_page); - -/* * If truncate cannot remove the fs-private metadata from the page, the page * becomes orphaned. It will be left on the LRU and may even be mapped into * user pagetables if we're racing with filemap_fault(). @@ -140,7 +111,13 @@ truncate_complete_page(struct address_space *mapping, struct page *page) if (page_has_private(page)) do_invalidatepage(page, 0, PAGE_CACHE_SIZE); - cancel_dirty_page(page, PAGE_CACHE_SIZE); + /* + * Some filesystems seem to re-dirty the page even after + * the VM has canceled the dirty bit (eg ext3 journaling). + * Hence dirty accounting check is placed after invalidation. + */ + if (TestClearPageDirty(page)) + account_page_cleaned(page, mapping); ClearPageMappedToDisk(page); delete_from_page_cache(page); @@ -513,7 +490,7 @@ unsigned long invalidate_mapping_pages(struct address_space *mapping, * of interest and try to speed up its reclaim. */ if (!ret) - deactivate_page(page); + deactivate_file_page(page); count += ret; } pagevec_remove_exceptionals(&pvec); diff --git a/mm/util.c b/mm/util.c index 3981ae9d1b15..68ff8a5361e7 100644 --- a/mm/util.c +++ b/mm/util.c @@ -325,9 +325,37 @@ void kvfree(const void *addr) } EXPORT_SYMBOL(kvfree); +static inline void *__page_rmapping(struct page *page) +{ + unsigned long mapping; + + mapping = (unsigned long)page->mapping; + mapping &= ~PAGE_MAPPING_FLAGS; + + return (void *)mapping; +} + +/* Neutral page->mapping pointer to address_space or anon_vma or other */ +void *page_rmapping(struct page *page) +{ + page = compound_head(page); + return __page_rmapping(page); +} + +struct anon_vma *page_anon_vma(struct page *page) +{ + unsigned long mapping; + + page = compound_head(page); + mapping = (unsigned long)page->mapping; + if ((mapping & PAGE_MAPPING_FLAGS) != PAGE_MAPPING_ANON) + return NULL; + return __page_rmapping(page); +} + struct address_space *page_mapping(struct page *page) { - struct address_space *mapping = page->mapping; + unsigned long mapping; /* This happens if someone calls flush_dcache_page on slab page */ if (unlikely(PageSlab(page))) @@ -337,10 +365,13 @@ struct address_space *page_mapping(struct page *page) swp_entry_t entry; entry.val = page_private(page); - mapping = swap_address_space(entry); - } else if ((unsigned long)mapping & PAGE_MAPPING_ANON) - mapping = NULL; - return mapping; + return swap_address_space(entry); + } + + mapping = (unsigned long)page->mapping; + if (mapping & PAGE_MAPPING_FLAGS) + return NULL; + return page->mapping; } int overcommit_ratio_handler(struct ctl_table *table, int write, diff --git a/mm/vmalloc.c b/mm/vmalloc.c index 35b25e1340ca..2faaa2976447 100644 --- a/mm/vmalloc.c +++ b/mm/vmalloc.c @@ -29,6 +29,7 @@ #include <linux/atomic.h> #include <linux/compiler.h> #include <linux/llist.h> +#include <linux/bitops.h> #include <asm/uaccess.h> #include <asm/tlbflush.h> @@ -74,6 +75,8 @@ static void vunmap_pmd_range(pud_t *pud, unsigned long addr, unsigned long end) pmd = pmd_offset(pud, addr); do { next = pmd_addr_end(addr, end); + if (pmd_clear_huge(pmd)) + continue; if (pmd_none_or_clear_bad(pmd)) continue; vunmap_pte_range(pmd, addr, next); @@ -88,6 +91,8 @@ static void vunmap_pud_range(pgd_t *pgd, unsigned long addr, unsigned long end) pud = pud_offset(pgd, addr); do { next = pud_addr_end(addr, end); + if (pud_clear_huge(pud)) + continue; if (pud_none_or_clear_bad(pud)) continue; vunmap_pmd_range(pud, addr, next); @@ -760,7 +765,7 @@ struct vmap_block { spinlock_t lock; struct vmap_area *va; unsigned long free, dirty; - DECLARE_BITMAP(dirty_map, VMAP_BBMAP_BITS); + unsigned long dirty_min, dirty_max; /*< dirty range */ struct list_head free_list; struct rcu_head rcu_head; struct list_head purge; @@ -791,13 +796,31 @@ static unsigned long addr_to_vb_idx(unsigned long addr) return addr; } -static struct vmap_block *new_vmap_block(gfp_t gfp_mask) +static void *vmap_block_vaddr(unsigned long va_start, unsigned long pages_off) +{ + unsigned long addr; + + addr = va_start + (pages_off << PAGE_SHIFT); + BUG_ON(addr_to_vb_idx(addr) != addr_to_vb_idx(va_start)); + return (void *)addr; +} + +/** + * new_vmap_block - allocates new vmap_block and occupies 2^order pages in this + * block. Of course pages number can't exceed VMAP_BBMAP_BITS + * @order: how many 2^order pages should be occupied in newly allocated block + * @gfp_mask: flags for the page level allocator + * + * Returns: virtual address in a newly allocated block or ERR_PTR(-errno) + */ +static void *new_vmap_block(unsigned int order, gfp_t gfp_mask) { struct vmap_block_queue *vbq; struct vmap_block *vb; struct vmap_area *va; unsigned long vb_idx; int node, err; + void *vaddr; node = numa_node_id(); @@ -821,11 +844,15 @@ static struct vmap_block *new_vmap_block(gfp_t gfp_mask) return ERR_PTR(err); } + vaddr = vmap_block_vaddr(va->va_start, 0); spin_lock_init(&vb->lock); vb->va = va; - vb->free = VMAP_BBMAP_BITS; + /* At least something should be left free */ + BUG_ON(VMAP_BBMAP_BITS <= (1UL << order)); + vb->free = VMAP_BBMAP_BITS - (1UL << order); vb->dirty = 0; - bitmap_zero(vb->dirty_map, VMAP_BBMAP_BITS); + vb->dirty_min = VMAP_BBMAP_BITS; + vb->dirty_max = 0; INIT_LIST_HEAD(&vb->free_list); vb_idx = addr_to_vb_idx(va->va_start); @@ -837,11 +864,11 @@ static struct vmap_block *new_vmap_block(gfp_t gfp_mask) vbq = &get_cpu_var(vmap_block_queue); spin_lock(&vbq->lock); - list_add_rcu(&vb->free_list, &vbq->free); + list_add_tail_rcu(&vb->free_list, &vbq->free); spin_unlock(&vbq->lock); put_cpu_var(vmap_block_queue); - return vb; + return vaddr; } static void free_vmap_block(struct vmap_block *vb) @@ -876,7 +903,8 @@ static void purge_fragmented_blocks(int cpu) if (vb->free + vb->dirty == VMAP_BBMAP_BITS && vb->dirty != VMAP_BBMAP_BITS) { vb->free = 0; /* prevent further allocs after releasing lock */ vb->dirty = VMAP_BBMAP_BITS; /* prevent purging it again */ - bitmap_fill(vb->dirty_map, VMAP_BBMAP_BITS); + vb->dirty_min = 0; + vb->dirty_max = VMAP_BBMAP_BITS; spin_lock(&vbq->lock); list_del_rcu(&vb->free_list); spin_unlock(&vbq->lock); @@ -905,7 +933,7 @@ static void *vb_alloc(unsigned long size, gfp_t gfp_mask) { struct vmap_block_queue *vbq; struct vmap_block *vb; - unsigned long addr = 0; + void *vaddr = NULL; unsigned int order; BUG_ON(size & ~PAGE_MASK); @@ -920,43 +948,38 @@ static void *vb_alloc(unsigned long size, gfp_t gfp_mask) } order = get_order(size); -again: rcu_read_lock(); vbq = &get_cpu_var(vmap_block_queue); list_for_each_entry_rcu(vb, &vbq->free, free_list) { - int i; + unsigned long pages_off; spin_lock(&vb->lock); - if (vb->free < 1UL << order) - goto next; + if (vb->free < (1UL << order)) { + spin_unlock(&vb->lock); + continue; + } - i = VMAP_BBMAP_BITS - vb->free; - addr = vb->va->va_start + (i << PAGE_SHIFT); - BUG_ON(addr_to_vb_idx(addr) != - addr_to_vb_idx(vb->va->va_start)); + pages_off = VMAP_BBMAP_BITS - vb->free; + vaddr = vmap_block_vaddr(vb->va->va_start, pages_off); vb->free -= 1UL << order; if (vb->free == 0) { spin_lock(&vbq->lock); list_del_rcu(&vb->free_list); spin_unlock(&vbq->lock); } + spin_unlock(&vb->lock); break; -next: - spin_unlock(&vb->lock); } put_cpu_var(vmap_block_queue); rcu_read_unlock(); - if (!addr) { - vb = new_vmap_block(gfp_mask); - if (IS_ERR(vb)) - return vb; - goto again; - } + /* Allocate new block if nothing was found */ + if (!vaddr) + vaddr = new_vmap_block(order, gfp_mask); - return (void *)addr; + return vaddr; } static void vb_free(const void *addr, unsigned long size) @@ -974,6 +997,7 @@ static void vb_free(const void *addr, unsigned long size) order = get_order(size); offset = (unsigned long)addr & (VMAP_BLOCK_SIZE - 1); + offset >>= PAGE_SHIFT; vb_idx = addr_to_vb_idx((unsigned long)addr); rcu_read_lock(); @@ -984,7 +1008,10 @@ static void vb_free(const void *addr, unsigned long size) vunmap_page_range((unsigned long)addr, (unsigned long)addr + size); spin_lock(&vb->lock); - BUG_ON(bitmap_allocate_region(vb->dirty_map, offset >> PAGE_SHIFT, order)); + + /* Expand dirty range */ + vb->dirty_min = min(vb->dirty_min, offset); + vb->dirty_max = max(vb->dirty_max, offset + (1UL << order)); vb->dirty += 1UL << order; if (vb->dirty == VMAP_BBMAP_BITS) { @@ -1023,25 +1050,18 @@ void vm_unmap_aliases(void) rcu_read_lock(); list_for_each_entry_rcu(vb, &vbq->free, free_list) { - int i, j; - spin_lock(&vb->lock); - i = find_first_bit(vb->dirty_map, VMAP_BBMAP_BITS); - if (i < VMAP_BBMAP_BITS) { + if (vb->dirty) { + unsigned long va_start = vb->va->va_start; unsigned long s, e; - j = find_last_bit(vb->dirty_map, - VMAP_BBMAP_BITS); - j = j + 1; /* need exclusive index */ + s = va_start + (vb->dirty_min << PAGE_SHIFT); + e = va_start + (vb->dirty_max << PAGE_SHIFT); - s = vb->va->va_start + (i << PAGE_SHIFT); - e = vb->va->va_start + (j << PAGE_SHIFT); - flush = 1; + start = min(s, start); + end = max(e, end); - if (s < start) - start = s; - if (e > end) - end = e; + flush = 1; } spin_unlock(&vb->lock); } @@ -1314,7 +1334,8 @@ static struct vm_struct *__get_vm_area_node(unsigned long size, BUG_ON(in_interrupt()); if (flags & VM_IOREMAP) - align = 1ul << clamp(fls(size), PAGE_SHIFT, IOREMAP_MAX_ORDER); + align = 1ul << clamp_t(int, fls_long(size), + PAGE_SHIFT, IOREMAP_MAX_ORDER); size = PAGE_ALIGN(size); if (unlikely(!size)) @@ -1418,6 +1439,7 @@ struct vm_struct *remove_vm_area(const void *addr) spin_unlock(&vmap_area_lock); vmap_debug_free_range(va->va_start, va->va_end); + kasan_free_shadow(vm); free_unmap_vmap_area(va); vm->size -= PAGE_SIZE; diff --git a/mm/zsmalloc.c b/mm/zsmalloc.c index 0dec1fa5f656..08bd7a3d464a 100644 --- a/mm/zsmalloc.c +++ b/mm/zsmalloc.c @@ -12,35 +12,6 @@ */ /* - * This allocator is designed for use with zram. Thus, the allocator is - * supposed to work well under low memory conditions. In particular, it - * never attempts higher order page allocation which is very likely to - * fail under memory pressure. On the other hand, if we just use single - * (0-order) pages, it would suffer from very high fragmentation -- - * any object of size PAGE_SIZE/2 or larger would occupy an entire page. - * This was one of the major issues with its predecessor (xvmalloc). - * - * To overcome these issues, zsmalloc allocates a bunch of 0-order pages - * and links them together using various 'struct page' fields. These linked - * pages act as a single higher-order page i.e. an object can span 0-order - * page boundaries. The code refers to these linked pages as a single entity - * called zspage. - * - * For simplicity, zsmalloc can only allocate objects of size up to PAGE_SIZE - * since this satisfies the requirements of all its current users (in the - * worst case, page is incompressible and is thus stored "as-is" i.e. in - * uncompressed form). For allocation requests larger than this size, failure - * is returned (see zs_malloc). - * - * Additionally, zs_malloc() does not return a dereferenceable pointer. - * Instead, it returns an opaque handle (unsigned long) which encodes actual - * location of the allocated object. The reason for this indirection is that - * zsmalloc does not keep zspages permanently mapped since that would cause - * issues on 32-bit systems where the VA region for kernel space mappings - * is very small. So, before using the allocating memory, the object has to - * be mapped using zs_map_object() to get a usable pointer and subsequently - * unmapped using zs_unmap_object(). - * * Following is how we use various fields and flags of underlying * struct page(s) to form a zspage. * @@ -57,6 +28,8 @@ * * page->private (union with page->first_page): refers to the * component page after the first page + * If the page is first_page for huge object, it stores handle. + * Look at size_class->huge. * page->freelist: points to the first free object in zspage. * Free objects are linked together using in-place * metadata. @@ -78,6 +51,7 @@ #include <linux/module.h> #include <linux/kernel.h> +#include <linux/sched.h> #include <linux/bitops.h> #include <linux/errno.h> #include <linux/highmem.h> @@ -110,6 +84,8 @@ #define ZS_MAX_ZSPAGE_ORDER 2 #define ZS_MAX_PAGES_PER_ZSPAGE (_AC(1, UL) << ZS_MAX_ZSPAGE_ORDER) +#define ZS_HANDLE_SIZE (sizeof(unsigned long)) + /* * Object location (<PFN>, <obj_idx>) is encoded as * as single (unsigned long) handle value. @@ -133,13 +109,33 @@ #endif #endif #define _PFN_BITS (MAX_PHYSMEM_BITS - PAGE_SHIFT) -#define OBJ_INDEX_BITS (BITS_PER_LONG - _PFN_BITS) + +/* + * Memory for allocating for handle keeps object position by + * encoding <page, obj_idx> and the encoded value has a room + * in least bit(ie, look at obj_to_location). + * We use the bit to synchronize between object access by + * user and migration. + */ +#define HANDLE_PIN_BIT 0 + +/* + * Head in allocated object should have OBJ_ALLOCATED_TAG + * to identify the object was allocated or not. + * It's okay to add the status bit in the least bit because + * header keeps handle which is 4byte-aligned address so we + * have room for two bit at least. + */ +#define OBJ_ALLOCATED_TAG 1 +#define OBJ_TAG_BITS 1 +#define OBJ_INDEX_BITS (BITS_PER_LONG - _PFN_BITS - OBJ_TAG_BITS) #define OBJ_INDEX_MASK ((_AC(1, UL) << OBJ_INDEX_BITS) - 1) #define MAX(a, b) ((a) >= (b) ? (a) : (b)) /* ZS_MIN_ALLOC_SIZE must be multiple of ZS_ALIGN */ #define ZS_MIN_ALLOC_SIZE \ MAX(32, (ZS_MAX_PAGES_PER_ZSPAGE << PAGE_SHIFT >> OBJ_INDEX_BITS)) +/* each chunk includes extra space to keep handle */ #define ZS_MAX_ALLOC_SIZE PAGE_SIZE /* @@ -172,6 +168,8 @@ enum fullness_group { enum zs_stat_type { OBJ_ALLOCATED, OBJ_USED, + CLASS_ALMOST_FULL, + CLASS_ALMOST_EMPTY, NR_ZS_STAT_TYPE, }; @@ -216,6 +214,8 @@ struct size_class { /* Number of PAGE_SIZE sized pages to combine to form a 'zspage' */ int pages_per_zspage; + /* huge object: pages_per_zspage == 1 && maxobj_per_zspage == 1 */ + bool huge; #ifdef CONFIG_ZSMALLOC_STAT struct zs_size_stat stats; @@ -233,14 +233,24 @@ struct size_class { * This must be power of 2 and less than or equal to ZS_ALIGN */ struct link_free { - /* Handle of next free chunk (encodes <PFN, obj_idx>) */ - void *next; + union { + /* + * Position of next free chunk (encodes <PFN, obj_idx>) + * It's valid for non-allocated object + */ + void *next; + /* + * Handle of allocated object. + */ + unsigned long handle; + }; }; struct zs_pool { char *name; struct size_class **size_class; + struct kmem_cache *handle_cachep; gfp_t flags; /* allocation flags used when growing pool */ atomic_long_t pages_allocated; @@ -267,8 +277,37 @@ struct mapping_area { #endif char *vm_addr; /* address of kmap_atomic()'ed pages */ enum zs_mapmode vm_mm; /* mapping mode */ + bool huge; }; +static int create_handle_cache(struct zs_pool *pool) +{ + pool->handle_cachep = kmem_cache_create("zs_handle", ZS_HANDLE_SIZE, + 0, 0, NULL); + return pool->handle_cachep ? 0 : 1; +} + +static void destroy_handle_cache(struct zs_pool *pool) +{ + kmem_cache_destroy(pool->handle_cachep); +} + +static unsigned long alloc_handle(struct zs_pool *pool) +{ + return (unsigned long)kmem_cache_alloc(pool->handle_cachep, + pool->flags & ~__GFP_HIGHMEM); +} + +static void free_handle(struct zs_pool *pool, unsigned long handle) +{ + kmem_cache_free(pool->handle_cachep, (void *)handle); +} + +static void record_obj(unsigned long handle, unsigned long obj) +{ + *(unsigned long *)handle = obj; +} + /* zpool driver */ #ifdef CONFIG_ZPOOL @@ -346,6 +385,11 @@ static struct zpool_driver zs_zpool_driver = { MODULE_ALIAS("zpool-zsmalloc"); #endif /* CONFIG_ZPOOL */ +static unsigned int get_maxobj_per_zspage(int size, int pages_per_zspage) +{ + return pages_per_zspage * PAGE_SIZE / size; +} + /* per-cpu VM mapping areas for zspage accesses that cross page boundaries */ static DEFINE_PER_CPU(struct mapping_area, zs_map_area); @@ -396,9 +440,182 @@ static int get_size_class_index(int size) idx = DIV_ROUND_UP(size - ZS_MIN_ALLOC_SIZE, ZS_SIZE_CLASS_DELTA); - return idx; + return min(zs_size_classes - 1, idx); +} + +#ifdef CONFIG_ZSMALLOC_STAT + +static inline void zs_stat_inc(struct size_class *class, + enum zs_stat_type type, unsigned long cnt) +{ + class->stats.objs[type] += cnt; +} + +static inline void zs_stat_dec(struct size_class *class, + enum zs_stat_type type, unsigned long cnt) +{ + class->stats.objs[type] -= cnt; +} + +static inline unsigned long zs_stat_get(struct size_class *class, + enum zs_stat_type type) +{ + return class->stats.objs[type]; +} + +static int __init zs_stat_init(void) +{ + if (!debugfs_initialized()) + return -ENODEV; + + zs_stat_root = debugfs_create_dir("zsmalloc", NULL); + if (!zs_stat_root) + return -ENOMEM; + + return 0; +} + +static void __exit zs_stat_exit(void) +{ + debugfs_remove_recursive(zs_stat_root); +} + +static int zs_stats_size_show(struct seq_file *s, void *v) +{ + int i; + struct zs_pool *pool = s->private; + struct size_class *class; + int objs_per_zspage; + unsigned long class_almost_full, class_almost_empty; + unsigned long obj_allocated, obj_used, pages_used; + unsigned long total_class_almost_full = 0, total_class_almost_empty = 0; + unsigned long total_objs = 0, total_used_objs = 0, total_pages = 0; + + seq_printf(s, " %5s %5s %11s %12s %13s %10s %10s %16s\n", + "class", "size", "almost_full", "almost_empty", + "obj_allocated", "obj_used", "pages_used", + "pages_per_zspage"); + + for (i = 0; i < zs_size_classes; i++) { + class = pool->size_class[i]; + + if (class->index != i) + continue; + + spin_lock(&class->lock); + class_almost_full = zs_stat_get(class, CLASS_ALMOST_FULL); + class_almost_empty = zs_stat_get(class, CLASS_ALMOST_EMPTY); + obj_allocated = zs_stat_get(class, OBJ_ALLOCATED); + obj_used = zs_stat_get(class, OBJ_USED); + spin_unlock(&class->lock); + + objs_per_zspage = get_maxobj_per_zspage(class->size, + class->pages_per_zspage); + pages_used = obj_allocated / objs_per_zspage * + class->pages_per_zspage; + + seq_printf(s, " %5u %5u %11lu %12lu %13lu %10lu %10lu %16d\n", + i, class->size, class_almost_full, class_almost_empty, + obj_allocated, obj_used, pages_used, + class->pages_per_zspage); + + total_class_almost_full += class_almost_full; + total_class_almost_empty += class_almost_empty; + total_objs += obj_allocated; + total_used_objs += obj_used; + total_pages += pages_used; + } + + seq_puts(s, "\n"); + seq_printf(s, " %5s %5s %11lu %12lu %13lu %10lu %10lu\n", + "Total", "", total_class_almost_full, + total_class_almost_empty, total_objs, + total_used_objs, total_pages); + + return 0; +} + +static int zs_stats_size_open(struct inode *inode, struct file *file) +{ + return single_open(file, zs_stats_size_show, inode->i_private); +} + +static const struct file_operations zs_stat_size_ops = { + .open = zs_stats_size_open, + .read = seq_read, + .llseek = seq_lseek, + .release = single_release, +}; + +static int zs_pool_stat_create(char *name, struct zs_pool *pool) +{ + struct dentry *entry; + + if (!zs_stat_root) + return -ENODEV; + + entry = debugfs_create_dir(name, zs_stat_root); + if (!entry) { + pr_warn("debugfs dir <%s> creation failed\n", name); + return -ENOMEM; + } + pool->stat_dentry = entry; + + entry = debugfs_create_file("classes", S_IFREG | S_IRUGO, + pool->stat_dentry, pool, &zs_stat_size_ops); + if (!entry) { + pr_warn("%s: debugfs file entry <%s> creation failed\n", + name, "classes"); + return -ENOMEM; + } + + return 0; +} + +static void zs_pool_stat_destroy(struct zs_pool *pool) +{ + debugfs_remove_recursive(pool->stat_dentry); +} + +#else /* CONFIG_ZSMALLOC_STAT */ + +static inline void zs_stat_inc(struct size_class *class, + enum zs_stat_type type, unsigned long cnt) +{ +} + +static inline void zs_stat_dec(struct size_class *class, + enum zs_stat_type type, unsigned long cnt) +{ +} + +static inline unsigned long zs_stat_get(struct size_class *class, + enum zs_stat_type type) +{ + return 0; +} + +static int __init zs_stat_init(void) +{ + return 0; +} + +static void __exit zs_stat_exit(void) +{ +} + +static inline int zs_pool_stat_create(char *name, struct zs_pool *pool) +{ + return 0; +} + +static inline void zs_pool_stat_destroy(struct zs_pool *pool) +{ } +#endif + + /* * For each size class, zspages are divided into different groups * depending on how "full" they are. This was done so that we could @@ -419,7 +636,7 @@ static enum fullness_group get_fullness_group(struct page *page) fg = ZS_EMPTY; else if (inuse == max_objects) fg = ZS_FULL; - else if (inuse <= max_objects / fullness_threshold_frac) + else if (inuse <= 3 * max_objects / fullness_threshold_frac) fg = ZS_ALMOST_EMPTY; else fg = ZS_ALMOST_FULL; @@ -448,6 +665,8 @@ static void insert_zspage(struct page *page, struct size_class *class, list_add_tail(&page->lru, &(*head)->lru); *head = page; + zs_stat_inc(class, fullness == ZS_ALMOST_EMPTY ? + CLASS_ALMOST_EMPTY : CLASS_ALMOST_FULL, 1); } /* @@ -473,6 +692,8 @@ static void remove_zspage(struct page *page, struct size_class *class, struct page, lru); list_del_init(&page->lru); + zs_stat_dec(class, fullness == ZS_ALMOST_EMPTY ? + CLASS_ALMOST_EMPTY : CLASS_ALMOST_FULL, 1); } /* @@ -484,11 +705,10 @@ static void remove_zspage(struct page *page, struct size_class *class, * page from the freelist of the old fullness group to that of the new * fullness group. */ -static enum fullness_group fix_fullness_group(struct zs_pool *pool, +static enum fullness_group fix_fullness_group(struct size_class *class, struct page *page) { int class_idx; - struct size_class *class; enum fullness_group currfg, newfg; BUG_ON(!is_first_page(page)); @@ -498,7 +718,6 @@ static enum fullness_group fix_fullness_group(struct zs_pool *pool, if (newfg == currfg) goto out; - class = pool->size_class[class_idx]; remove_zspage(page, class, currfg); insert_zspage(page, class, newfg); set_zspage_mapping(page, class_idx, newfg); @@ -512,7 +731,8 @@ out: * to form a zspage for each size class. This is important * to reduce wastage due to unusable space left at end of * each zspage which is given as: - * wastage = Zp - Zp % size_class + * wastage = Zp % class_size + * usage = Zp - wastage * where Zp = zspage size = k * PAGE_SIZE where k = 1, 2, ... * * For example, for size class of 3/8 * PAGE_SIZE, we should @@ -571,35 +791,50 @@ static struct page *get_next_page(struct page *page) /* * Encode <page, obj_idx> as a single handle value. - * On hardware platforms with physical memory starting at 0x0 the pfn - * could be 0 so we ensure that the handle will never be 0 by adjusting the - * encoded obj_idx value before encoding. + * We use the least bit of handle for tagging. */ -static void *obj_location_to_handle(struct page *page, unsigned long obj_idx) +static void *location_to_obj(struct page *page, unsigned long obj_idx) { - unsigned long handle; + unsigned long obj; if (!page) { BUG_ON(obj_idx); return NULL; } - handle = page_to_pfn(page) << OBJ_INDEX_BITS; - handle |= ((obj_idx + 1) & OBJ_INDEX_MASK); + obj = page_to_pfn(page) << OBJ_INDEX_BITS; + obj |= ((obj_idx) & OBJ_INDEX_MASK); + obj <<= OBJ_TAG_BITS; - return (void *)handle; + return (void *)obj; } /* * Decode <page, obj_idx> pair from the given object handle. We adjust the * decoded obj_idx back to its original value since it was adjusted in - * obj_location_to_handle(). + * location_to_obj(). */ -static void obj_handle_to_location(unsigned long handle, struct page **page, +static void obj_to_location(unsigned long obj, struct page **page, unsigned long *obj_idx) { - *page = pfn_to_page(handle >> OBJ_INDEX_BITS); - *obj_idx = (handle & OBJ_INDEX_MASK) - 1; + obj >>= OBJ_TAG_BITS; + *page = pfn_to_page(obj >> OBJ_INDEX_BITS); + *obj_idx = (obj & OBJ_INDEX_MASK); +} + +static unsigned long handle_to_obj(unsigned long handle) +{ + return *(unsigned long *)handle; +} + +static unsigned long obj_to_head(struct size_class *class, struct page *page, + void *obj) +{ + if (class->huge) { + VM_BUG_ON(!is_first_page(page)); + return *(unsigned long *)page_private(page); + } else + return *(unsigned long *)obj; } static unsigned long obj_idx_to_offset(struct page *page, @@ -613,6 +848,25 @@ static unsigned long obj_idx_to_offset(struct page *page, return off + obj_idx * class_size; } +static inline int trypin_tag(unsigned long handle) +{ + unsigned long *ptr = (unsigned long *)handle; + + return !test_and_set_bit_lock(HANDLE_PIN_BIT, ptr); +} + +static void pin_tag(unsigned long handle) +{ + while (!trypin_tag(handle)); +} + +static void unpin_tag(unsigned long handle) +{ + unsigned long *ptr = (unsigned long *)handle; + + clear_bit_unlock(HANDLE_PIN_BIT, ptr); +} + static void reset_page(struct page *page) { clear_bit(PG_private, &page->flags); @@ -674,7 +928,7 @@ static void init_zspage(struct page *first_page, struct size_class *class) link = (struct link_free *)vaddr + off / sizeof(*link); while ((off += class->size) < PAGE_SIZE) { - link->next = obj_location_to_handle(page, i++); + link->next = location_to_obj(page, i++); link += class->size / sizeof(*link); } @@ -684,7 +938,7 @@ static void init_zspage(struct page *first_page, struct size_class *class) * page (if present) */ next_page = get_next_page(page); - link->next = obj_location_to_handle(next_page, 0); + link->next = location_to_obj(next_page, 0); kunmap_atomic(vaddr); page = next_page; off %= PAGE_SIZE; @@ -738,7 +992,7 @@ static struct page *alloc_zspage(struct size_class *class, gfp_t flags) init_zspage(first_page, class); - first_page->freelist = obj_location_to_handle(first_page, 0); + first_page->freelist = location_to_obj(first_page, 0); /* Maximum number of objects we can store in this zspage */ first_page->objects = class->pages_per_zspage * PAGE_SIZE / class->size; @@ -860,12 +1114,19 @@ static void __zs_unmap_object(struct mapping_area *area, { int sizes[2]; void *addr; - char *buf = area->vm_buf; + char *buf; /* no write fastpath */ if (area->vm_mm == ZS_MM_RO) goto out; + buf = area->vm_buf; + if (!area->huge) { + buf = buf + ZS_HANDLE_SIZE; + size -= ZS_HANDLE_SIZE; + off += ZS_HANDLE_SIZE; + } + sizes[0] = PAGE_SIZE - off; sizes[1] = size - sizes[0]; @@ -952,11 +1213,6 @@ static void init_zs_size_classes(void) zs_size_classes = nr; } -static unsigned int get_maxobj_per_zspage(int size, int pages_per_zspage) -{ - return pages_per_zspage * PAGE_SIZE / size; -} - static bool can_merge(struct size_class *prev, int size, int pages_per_zspage) { if (prev->pages_per_zspage != pages_per_zspage) @@ -969,166 +1225,13 @@ static bool can_merge(struct size_class *prev, int size, int pages_per_zspage) return true; } -#ifdef CONFIG_ZSMALLOC_STAT - -static inline void zs_stat_inc(struct size_class *class, - enum zs_stat_type type, unsigned long cnt) -{ - class->stats.objs[type] += cnt; -} - -static inline void zs_stat_dec(struct size_class *class, - enum zs_stat_type type, unsigned long cnt) -{ - class->stats.objs[type] -= cnt; -} - -static inline unsigned long zs_stat_get(struct size_class *class, - enum zs_stat_type type) -{ - return class->stats.objs[type]; -} - -static int __init zs_stat_init(void) -{ - if (!debugfs_initialized()) - return -ENODEV; - - zs_stat_root = debugfs_create_dir("zsmalloc", NULL); - if (!zs_stat_root) - return -ENOMEM; - - return 0; -} - -static void __exit zs_stat_exit(void) -{ - debugfs_remove_recursive(zs_stat_root); -} - -static int zs_stats_size_show(struct seq_file *s, void *v) +static bool zspage_full(struct page *page) { - int i; - struct zs_pool *pool = s->private; - struct size_class *class; - int objs_per_zspage; - unsigned long obj_allocated, obj_used, pages_used; - unsigned long total_objs = 0, total_used_objs = 0, total_pages = 0; - - seq_printf(s, " %5s %5s %13s %10s %10s\n", "class", "size", - "obj_allocated", "obj_used", "pages_used"); - - for (i = 0; i < zs_size_classes; i++) { - class = pool->size_class[i]; - - if (class->index != i) - continue; - - spin_lock(&class->lock); - obj_allocated = zs_stat_get(class, OBJ_ALLOCATED); - obj_used = zs_stat_get(class, OBJ_USED); - spin_unlock(&class->lock); - - objs_per_zspage = get_maxobj_per_zspage(class->size, - class->pages_per_zspage); - pages_used = obj_allocated / objs_per_zspage * - class->pages_per_zspage; - - seq_printf(s, " %5u %5u %10lu %10lu %10lu\n", i, - class->size, obj_allocated, obj_used, pages_used); - - total_objs += obj_allocated; - total_used_objs += obj_used; - total_pages += pages_used; - } - - seq_puts(s, "\n"); - seq_printf(s, " %5s %5s %10lu %10lu %10lu\n", "Total", "", - total_objs, total_used_objs, total_pages); - - return 0; -} - -static int zs_stats_size_open(struct inode *inode, struct file *file) -{ - return single_open(file, zs_stats_size_show, inode->i_private); -} - -static const struct file_operations zs_stat_size_ops = { - .open = zs_stats_size_open, - .read = seq_read, - .llseek = seq_lseek, - .release = single_release, -}; - -static int zs_pool_stat_create(char *name, struct zs_pool *pool) -{ - struct dentry *entry; - - if (!zs_stat_root) - return -ENODEV; - - entry = debugfs_create_dir(name, zs_stat_root); - if (!entry) { - pr_warn("debugfs dir <%s> creation failed\n", name); - return -ENOMEM; - } - pool->stat_dentry = entry; - - entry = debugfs_create_file("obj_in_classes", S_IFREG | S_IRUGO, - pool->stat_dentry, pool, &zs_stat_size_ops); - if (!entry) { - pr_warn("%s: debugfs file entry <%s> creation failed\n", - name, "obj_in_classes"); - return -ENOMEM; - } - - return 0; -} - -static void zs_pool_stat_destroy(struct zs_pool *pool) -{ - debugfs_remove_recursive(pool->stat_dentry); -} - -#else /* CONFIG_ZSMALLOC_STAT */ - -static inline void zs_stat_inc(struct size_class *class, - enum zs_stat_type type, unsigned long cnt) -{ -} - -static inline void zs_stat_dec(struct size_class *class, - enum zs_stat_type type, unsigned long cnt) -{ -} - -static inline unsigned long zs_stat_get(struct size_class *class, - enum zs_stat_type type) -{ - return 0; -} - -static int __init zs_stat_init(void) -{ - return 0; -} - -static void __exit zs_stat_exit(void) -{ -} - -static inline int zs_pool_stat_create(char *name, struct zs_pool *pool) -{ - return 0; -} + BUG_ON(!is_first_page(page)); -static inline void zs_pool_stat_destroy(struct zs_pool *pool) -{ + return page->inuse == page->objects; } -#endif - unsigned long zs_get_total_pages(struct zs_pool *pool) { return atomic_long_read(&pool->pages_allocated); @@ -1153,13 +1256,14 @@ void *zs_map_object(struct zs_pool *pool, unsigned long handle, enum zs_mapmode mm) { struct page *page; - unsigned long obj_idx, off; + unsigned long obj, obj_idx, off; unsigned int class_idx; enum fullness_group fg; struct size_class *class; struct mapping_area *area; struct page *pages[2]; + void *ret; BUG_ON(!handle); @@ -1170,7 +1274,11 @@ void *zs_map_object(struct zs_pool *pool, unsigned long handle, */ BUG_ON(in_interrupt()); - obj_handle_to_location(handle, &page, &obj_idx); + /* From now on, migration cannot move the object */ + pin_tag(handle); + + obj = handle_to_obj(handle); + obj_to_location(obj, &page, &obj_idx); get_zspage_mapping(get_first_page(page), &class_idx, &fg); class = pool->size_class[class_idx]; off = obj_idx_to_offset(page, obj_idx, class->size); @@ -1180,7 +1288,8 @@ void *zs_map_object(struct zs_pool *pool, unsigned long handle, if (off + class->size <= PAGE_SIZE) { /* this object is contained entirely within a page */ area->vm_addr = kmap_atomic(page); - return area->vm_addr + off; + ret = area->vm_addr + off; + goto out; } /* this object spans two pages */ @@ -1188,14 +1297,19 @@ void *zs_map_object(struct zs_pool *pool, unsigned long handle, pages[1] = get_next_page(page); BUG_ON(!pages[1]); - return __zs_map_object(area, pages, off, class->size); + ret = __zs_map_object(area, pages, off, class->size); +out: + if (!class->huge) + ret += ZS_HANDLE_SIZE; + + return ret; } EXPORT_SYMBOL_GPL(zs_map_object); void zs_unmap_object(struct zs_pool *pool, unsigned long handle) { struct page *page; - unsigned long obj_idx, off; + unsigned long obj, obj_idx, off; unsigned int class_idx; enum fullness_group fg; @@ -1204,7 +1318,8 @@ void zs_unmap_object(struct zs_pool *pool, unsigned long handle) BUG_ON(!handle); - obj_handle_to_location(handle, &page, &obj_idx); + obj = handle_to_obj(handle); + obj_to_location(obj, &page, &obj_idx); get_zspage_mapping(get_first_page(page), &class_idx, &fg); class = pool->size_class[class_idx]; off = obj_idx_to_offset(page, obj_idx, class->size); @@ -1222,9 +1337,42 @@ void zs_unmap_object(struct zs_pool *pool, unsigned long handle) __zs_unmap_object(area, pages, off, class->size); } put_cpu_var(zs_map_area); + unpin_tag(handle); } EXPORT_SYMBOL_GPL(zs_unmap_object); +static unsigned long obj_malloc(struct page *first_page, + struct size_class *class, unsigned long handle) +{ + unsigned long obj; + struct link_free *link; + + struct page *m_page; + unsigned long m_objidx, m_offset; + void *vaddr; + + handle |= OBJ_ALLOCATED_TAG; + obj = (unsigned long)first_page->freelist; + obj_to_location(obj, &m_page, &m_objidx); + m_offset = obj_idx_to_offset(m_page, m_objidx, class->size); + + vaddr = kmap_atomic(m_page); + link = (struct link_free *)vaddr + m_offset / sizeof(*link); + first_page->freelist = link->next; + if (!class->huge) + /* record handle in the header of allocated chunk */ + link->handle = handle; + else + /* record handle in first_page->private */ + set_page_private(first_page, handle); + kunmap_atomic(vaddr); + first_page->inuse++; + zs_stat_inc(class, OBJ_USED, 1); + + return obj; +} + + /** * zs_malloc - Allocate block of given size from pool. * @pool: pool to allocate from @@ -1236,17 +1384,19 @@ EXPORT_SYMBOL_GPL(zs_unmap_object); */ unsigned long zs_malloc(struct zs_pool *pool, size_t size) { - unsigned long obj; - struct link_free *link; + unsigned long handle, obj; struct size_class *class; - void *vaddr; - - struct page *first_page, *m_page; - unsigned long m_objidx, m_offset; + struct page *first_page; if (unlikely(!size || size > ZS_MAX_ALLOC_SIZE)) return 0; + handle = alloc_handle(pool); + if (!handle) + return 0; + + /* extra space in chunk to keep the handle */ + size += ZS_HANDLE_SIZE; class = pool->size_class[get_size_class_index(size)]; spin_lock(&class->lock); @@ -1255,8 +1405,10 @@ unsigned long zs_malloc(struct zs_pool *pool, size_t size) if (!first_page) { spin_unlock(&class->lock); first_page = alloc_zspage(class, pool->flags); - if (unlikely(!first_page)) + if (unlikely(!first_page)) { + free_handle(pool, handle); return 0; + } set_zspage_mapping(first_page, class->index, ZS_EMPTY); atomic_long_add(class->pages_per_zspage, @@ -1267,73 +1419,360 @@ unsigned long zs_malloc(struct zs_pool *pool, size_t size) class->size, class->pages_per_zspage)); } - obj = (unsigned long)first_page->freelist; - obj_handle_to_location(obj, &m_page, &m_objidx); - m_offset = obj_idx_to_offset(m_page, m_objidx, class->size); - - vaddr = kmap_atomic(m_page); - link = (struct link_free *)vaddr + m_offset / sizeof(*link); - first_page->freelist = link->next; - memset(link, POISON_INUSE, sizeof(*link)); - kunmap_atomic(vaddr); - - first_page->inuse++; - zs_stat_inc(class, OBJ_USED, 1); + obj = obj_malloc(first_page, class, handle); /* Now move the zspage to another fullness group, if required */ - fix_fullness_group(pool, first_page); + fix_fullness_group(class, first_page); + record_obj(handle, obj); spin_unlock(&class->lock); - return obj; + return handle; } EXPORT_SYMBOL_GPL(zs_malloc); -void zs_free(struct zs_pool *pool, unsigned long obj) +static void obj_free(struct zs_pool *pool, struct size_class *class, + unsigned long obj) { struct link_free *link; struct page *first_page, *f_page; unsigned long f_objidx, f_offset; void *vaddr; - int class_idx; - struct size_class *class; enum fullness_group fullness; - if (unlikely(!obj)) - return; + BUG_ON(!obj); - obj_handle_to_location(obj, &f_page, &f_objidx); + obj &= ~OBJ_ALLOCATED_TAG; + obj_to_location(obj, &f_page, &f_objidx); first_page = get_first_page(f_page); get_zspage_mapping(first_page, &class_idx, &fullness); - class = pool->size_class[class_idx]; f_offset = obj_idx_to_offset(f_page, f_objidx, class->size); - spin_lock(&class->lock); + vaddr = kmap_atomic(f_page); /* Insert this object in containing zspage's freelist */ - vaddr = kmap_atomic(f_page); link = (struct link_free *)(vaddr + f_offset); link->next = first_page->freelist; + if (class->huge) + set_page_private(first_page, 0); kunmap_atomic(vaddr); first_page->freelist = (void *)obj; - first_page->inuse--; - fullness = fix_fullness_group(pool, first_page); - zs_stat_dec(class, OBJ_USED, 1); - if (fullness == ZS_EMPTY) +} + +void zs_free(struct zs_pool *pool, unsigned long handle) +{ + struct page *first_page, *f_page; + unsigned long obj, f_objidx; + int class_idx; + struct size_class *class; + enum fullness_group fullness; + + if (unlikely(!handle)) + return; + + pin_tag(handle); + obj = handle_to_obj(handle); + obj_to_location(obj, &f_page, &f_objidx); + first_page = get_first_page(f_page); + + get_zspage_mapping(first_page, &class_idx, &fullness); + class = pool->size_class[class_idx]; + + spin_lock(&class->lock); + obj_free(pool, class, obj); + fullness = fix_fullness_group(class, first_page); + if (fullness == ZS_EMPTY) { zs_stat_dec(class, OBJ_ALLOCATED, get_maxobj_per_zspage( class->size, class->pages_per_zspage)); - + atomic_long_sub(class->pages_per_zspage, + &pool->pages_allocated); + free_zspage(first_page); + } spin_unlock(&class->lock); + unpin_tag(handle); + + free_handle(pool, handle); +} +EXPORT_SYMBOL_GPL(zs_free); + +static void zs_object_copy(unsigned long src, unsigned long dst, + struct size_class *class) +{ + struct page *s_page, *d_page; + unsigned long s_objidx, d_objidx; + unsigned long s_off, d_off; + void *s_addr, *d_addr; + int s_size, d_size, size; + int written = 0; + + s_size = d_size = class->size; + + obj_to_location(src, &s_page, &s_objidx); + obj_to_location(dst, &d_page, &d_objidx); + + s_off = obj_idx_to_offset(s_page, s_objidx, class->size); + d_off = obj_idx_to_offset(d_page, d_objidx, class->size); + + if (s_off + class->size > PAGE_SIZE) + s_size = PAGE_SIZE - s_off; + + if (d_off + class->size > PAGE_SIZE) + d_size = PAGE_SIZE - d_off; + + s_addr = kmap_atomic(s_page); + d_addr = kmap_atomic(d_page); + + while (1) { + size = min(s_size, d_size); + memcpy(d_addr + d_off, s_addr + s_off, size); + written += size; + + if (written == class->size) + break; + + s_off += size; + s_size -= size; + d_off += size; + d_size -= size; + + if (s_off >= PAGE_SIZE) { + kunmap_atomic(d_addr); + kunmap_atomic(s_addr); + s_page = get_next_page(s_page); + BUG_ON(!s_page); + s_addr = kmap_atomic(s_page); + d_addr = kmap_atomic(d_page); + s_size = class->size - written; + s_off = 0; + } + + if (d_off >= PAGE_SIZE) { + kunmap_atomic(d_addr); + d_page = get_next_page(d_page); + BUG_ON(!d_page); + d_addr = kmap_atomic(d_page); + d_size = class->size - written; + d_off = 0; + } + } + + kunmap_atomic(d_addr); + kunmap_atomic(s_addr); +} + +/* + * Find alloced object in zspage from index object and + * return handle. + */ +static unsigned long find_alloced_obj(struct page *page, int index, + struct size_class *class) +{ + unsigned long head; + int offset = 0; + unsigned long handle = 0; + void *addr = kmap_atomic(page); + + if (!is_first_page(page)) + offset = page->index; + offset += class->size * index; + + while (offset < PAGE_SIZE) { + head = obj_to_head(class, page, addr + offset); + if (head & OBJ_ALLOCATED_TAG) { + handle = head & ~OBJ_ALLOCATED_TAG; + if (trypin_tag(handle)) + break; + handle = 0; + } + + offset += class->size; + index++; + } + + kunmap_atomic(addr); + return handle; +} + +struct zs_compact_control { + /* Source page for migration which could be a subpage of zspage. */ + struct page *s_page; + /* Destination page for migration which should be a first page + * of zspage. */ + struct page *d_page; + /* Starting object index within @s_page which used for live object + * in the subpage. */ + int index; + /* how many of objects are migrated */ + int nr_migrated; +}; + +static int migrate_zspage(struct zs_pool *pool, struct size_class *class, + struct zs_compact_control *cc) +{ + unsigned long used_obj, free_obj; + unsigned long handle; + struct page *s_page = cc->s_page; + struct page *d_page = cc->d_page; + unsigned long index = cc->index; + int nr_migrated = 0; + int ret = 0; + + while (1) { + handle = find_alloced_obj(s_page, index, class); + if (!handle) { + s_page = get_next_page(s_page); + if (!s_page) + break; + index = 0; + continue; + } + + /* Stop if there is no more space */ + if (zspage_full(d_page)) { + unpin_tag(handle); + ret = -ENOMEM; + break; + } + + used_obj = handle_to_obj(handle); + free_obj = obj_malloc(d_page, class, handle); + zs_object_copy(used_obj, free_obj, class); + index++; + record_obj(handle, free_obj); + unpin_tag(handle); + obj_free(pool, class, used_obj); + nr_migrated++; + } + + /* Remember last position in this iteration */ + cc->s_page = s_page; + cc->index = index; + cc->nr_migrated = nr_migrated; + + return ret; +} + +static struct page *alloc_target_page(struct size_class *class) +{ + int i; + struct page *page; + + for (i = 0; i < _ZS_NR_FULLNESS_GROUPS; i++) { + page = class->fullness_list[i]; + if (page) { + remove_zspage(page, class, i); + break; + } + } + + return page; +} + +static void putback_zspage(struct zs_pool *pool, struct size_class *class, + struct page *first_page) +{ + enum fullness_group fullness; + + BUG_ON(!is_first_page(first_page)); + + fullness = get_fullness_group(first_page); + insert_zspage(first_page, class, fullness); + set_zspage_mapping(first_page, class->index, fullness); if (fullness == ZS_EMPTY) { + zs_stat_dec(class, OBJ_ALLOCATED, get_maxobj_per_zspage( + class->size, class->pages_per_zspage)); atomic_long_sub(class->pages_per_zspage, &pool->pages_allocated); + free_zspage(first_page); } } -EXPORT_SYMBOL_GPL(zs_free); + +static struct page *isolate_source_page(struct size_class *class) +{ + struct page *page; + + page = class->fullness_list[ZS_ALMOST_EMPTY]; + if (page) + remove_zspage(page, class, ZS_ALMOST_EMPTY); + + return page; +} + +static unsigned long __zs_compact(struct zs_pool *pool, + struct size_class *class) +{ + int nr_to_migrate; + struct zs_compact_control cc; + struct page *src_page; + struct page *dst_page = NULL; + unsigned long nr_total_migrated = 0; + + spin_lock(&class->lock); + while ((src_page = isolate_source_page(class))) { + + BUG_ON(!is_first_page(src_page)); + + /* The goal is to migrate all live objects in source page */ + nr_to_migrate = src_page->inuse; + cc.index = 0; + cc.s_page = src_page; + + while ((dst_page = alloc_target_page(class))) { + cc.d_page = dst_page; + /* + * If there is no more space in dst_page, try to + * allocate another zspage. + */ + if (!migrate_zspage(pool, class, &cc)) + break; + + putback_zspage(pool, class, dst_page); + nr_total_migrated += cc.nr_migrated; + nr_to_migrate -= cc.nr_migrated; + } + + /* Stop if we couldn't find slot */ + if (dst_page == NULL) + break; + + putback_zspage(pool, class, dst_page); + putback_zspage(pool, class, src_page); + spin_unlock(&class->lock); + nr_total_migrated += cc.nr_migrated; + cond_resched(); + spin_lock(&class->lock); + } + + if (src_page) + putback_zspage(pool, class, src_page); + + spin_unlock(&class->lock); + + return nr_total_migrated; +} + +unsigned long zs_compact(struct zs_pool *pool) +{ + int i; + unsigned long nr_migrated = 0; + struct size_class *class; + + for (i = zs_size_classes - 1; i >= 0; i--) { + class = pool->size_class[i]; + if (!class) + continue; + if (class->index != i) + continue; + nr_migrated += __zs_compact(pool, class); + } + + return nr_migrated; +} +EXPORT_SYMBOL_GPL(zs_compact); /** * zs_create_pool - Creates an allocation pool to work from. @@ -1355,20 +1794,20 @@ struct zs_pool *zs_create_pool(char *name, gfp_t flags) if (!pool) return NULL; - pool->name = kstrdup(name, GFP_KERNEL); - if (!pool->name) { - kfree(pool); - return NULL; - } - pool->size_class = kcalloc(zs_size_classes, sizeof(struct size_class *), GFP_KERNEL); if (!pool->size_class) { - kfree(pool->name); kfree(pool); return NULL; } + pool->name = kstrdup(name, GFP_KERNEL); + if (!pool->name) + goto err; + + if (create_handle_cache(pool)) + goto err; + /* * Iterate reversly, because, size of size_class that we want to use * for merging should be larger or equal to current size. @@ -1406,6 +1845,9 @@ struct zs_pool *zs_create_pool(char *name, gfp_t flags) class->size = size; class->index = i; class->pages_per_zspage = pages_per_zspage; + if (pages_per_zspage == 1 && + get_maxobj_per_zspage(size, pages_per_zspage) == 1) + class->huge = true; spin_lock_init(&class->lock); pool->size_class[i] = class; @@ -1450,6 +1892,7 @@ void zs_destroy_pool(struct zs_pool *pool) kfree(class); } + destroy_handle_cache(pool); kfree(pool->size_class); kfree(pool->name); kfree(pool); |