diff options
Diffstat (limited to 'mm/shmem.c')
| -rw-r--r-- | mm/shmem.c | 3409 |
1 files changed, 2103 insertions, 1306 deletions
diff --git a/mm/shmem.c b/mm/shmem.c index dc25565a61e..af68b15a8fc 100644 --- a/mm/shmem.c +++ b/mm/shmem.c @@ -6,7 +6,8 @@ * 2000-2001 Christoph Rohland * 2000-2001 SAP AG * 2002 Red Hat Inc. - * Copyright (C) 2002-2005 Hugh Dickins. + * Copyright (C) 2002-2011 Hugh Dickins. + * Copyright (C) 2011 Google Inc. * Copyright (C) 2002-2005 VERITAS Software Corporation. * Copyright (C) 2004 Andi Kleen, SuSE Labs * @@ -14,119 +15,115 @@ * Copyright (c) 2004, Luke Kenneth Casson Leighton <lkcl@lkcl.net> * Copyright (c) 2004 Red Hat, Inc., James Morris <jmorris@redhat.com> * + * tiny-shmem: + * Copyright (c) 2004, 2008 Matt Mackall <mpm@selenic.com> + * * This file is released under the GPL. */ +#include <linux/fs.h> +#include <linux/init.h> +#include <linux/vfs.h> +#include <linux/mount.h> +#include <linux/ramfs.h> +#include <linux/pagemap.h> +#include <linux/file.h> +#include <linux/mm.h> +#include <linux/export.h> +#include <linux/swap.h> +#include <linux/aio.h> + +static struct vfsmount *shm_mnt; + +#ifdef CONFIG_SHMEM /* * This virtual memory filesystem is heavily based on the ramfs. It * extends ramfs by the ability to use swap and honor resource limits * which makes it a completely usable filesystem. */ -#include <linux/config.h> -#include <linux/module.h> -#include <linux/init.h> -#include <linux/devfs_fs_kernel.h> -#include <linux/fs.h> -#include <linux/mm.h> +#include <linux/xattr.h> +#include <linux/exportfs.h> +#include <linux/posix_acl.h> +#include <linux/posix_acl_xattr.h> #include <linux/mman.h> -#include <linux/file.h> -#include <linux/swap.h> -#include <linux/pagemap.h> #include <linux/string.h> #include <linux/slab.h> #include <linux/backing-dev.h> #include <linux/shmem_fs.h> -#include <linux/mount.h> #include <linux/writeback.h> -#include <linux/vfs.h> #include <linux/blkdev.h> +#include <linux/pagevec.h> +#include <linux/percpu_counter.h> +#include <linux/falloc.h> +#include <linux/splice.h> #include <linux/security.h> #include <linux/swapops.h> #include <linux/mempolicy.h> #include <linux/namei.h> +#include <linux/ctype.h> +#include <linux/migrate.h> +#include <linux/highmem.h> +#include <linux/seq_file.h> +#include <linux/magic.h> + #include <asm/uaccess.h> -#include <asm/div64.h> #include <asm/pgtable.h> -/* This magic number is used in glibc for posix shared memory */ -#define TMPFS_MAGIC 0x01021994 - -#define ENTRIES_PER_PAGE (PAGE_CACHE_SIZE/sizeof(unsigned long)) -#define ENTRIES_PER_PAGEPAGE (ENTRIES_PER_PAGE*ENTRIES_PER_PAGE) #define BLOCKS_PER_PAGE (PAGE_CACHE_SIZE/512) - -#define SHMEM_MAX_INDEX (SHMEM_NR_DIRECT + (ENTRIES_PER_PAGEPAGE/2) * (ENTRIES_PER_PAGE+1)) -#define SHMEM_MAX_BYTES ((unsigned long long)SHMEM_MAX_INDEX << PAGE_CACHE_SHIFT) - #define VM_ACCT(size) (PAGE_CACHE_ALIGN(size) >> PAGE_SHIFT) -/* info->flags needs VM_flags to handle pagein/truncate races efficiently */ -#define SHMEM_PAGEIN VM_READ -#define SHMEM_TRUNCATE VM_WRITE - -/* Definition to limit shmem_truncate's steps between cond_rescheds */ -#define LATENCY_LIMIT 64 - /* Pretend that each entry is of this size in directory's i_size */ #define BOGO_DIRENT_SIZE 20 -/* Flag allocation requirements to shmem_getpage and shmem_swp_alloc */ +/* Symlink up to this size is kmalloc'ed instead of using a swappable page */ +#define SHORT_SYMLINK_LEN 128 + +/* + * shmem_fallocate communicates with shmem_fault or shmem_writepage via + * inode->i_private (with i_mutex making sure that it has only one user at + * a time): we would prefer not to enlarge the shmem inode just for that. + */ +struct shmem_falloc { + wait_queue_head_t *waitq; /* faults into hole wait for punch to end */ + pgoff_t start; /* start of range currently being fallocated */ + pgoff_t next; /* the next page offset to be fallocated */ + pgoff_t nr_falloced; /* how many new pages have been fallocated */ + pgoff_t nr_unswapped; /* how often writepage refused to swap out */ +}; + +/* Flag allocation requirements to shmem_getpage */ enum sgp_type { - SGP_QUICK, /* don't try more than file page cache lookup */ SGP_READ, /* don't exceed i_size, don't allocate page */ SGP_CACHE, /* don't exceed i_size, may allocate page */ - SGP_WRITE, /* may exceed i_size, may allocate page */ + SGP_DIRTY, /* like SGP_CACHE, but set new page dirty */ + SGP_WRITE, /* may exceed i_size, may allocate !Uptodate page */ + SGP_FALLOC, /* like SGP_WRITE, but make existing page Uptodate */ }; -static int shmem_getpage(struct inode *inode, unsigned long idx, - struct page **pagep, enum sgp_type sgp, int *type); - -static inline struct page *shmem_dir_alloc(gfp_t gfp_mask) -{ - /* - * The above definition of ENTRIES_PER_PAGE, and the use of - * BLOCKS_PER_PAGE on indirect pages, assume PAGE_CACHE_SIZE: - * might be reconsidered if it ever diverges from PAGE_SIZE. - */ - return alloc_pages(gfp_mask, PAGE_CACHE_SHIFT-PAGE_SHIFT); -} - -static inline void shmem_dir_free(struct page *page) -{ - __free_pages(page, PAGE_CACHE_SHIFT-PAGE_SHIFT); -} - -static struct page **shmem_dir_map(struct page *page) -{ - return (struct page **)kmap_atomic(page, KM_USER0); -} - -static inline void shmem_dir_unmap(struct page **dir) +#ifdef CONFIG_TMPFS +static unsigned long shmem_default_max_blocks(void) { - kunmap_atomic(dir, KM_USER0); + return totalram_pages / 2; } -static swp_entry_t *shmem_swp_map(struct page *page) +static unsigned long shmem_default_max_inodes(void) { - return (swp_entry_t *)kmap_atomic(page, KM_USER1); + return min(totalram_pages - totalhigh_pages, totalram_pages / 2); } +#endif -static inline void shmem_swp_balance_unmap(void) -{ - /* - * When passing a pointer to an i_direct entry, to code which - * also handles indirect entries and so will shmem_swp_unmap, - * we must arrange for the preempt count to remain in balance. - * What kmap_atomic of a lowmem page does depends on config - * and architecture, so pretend to kmap_atomic some lowmem page. - */ - (void) kmap_atomic(ZERO_PAGE(0), KM_USER1); -} +static bool shmem_should_replace_page(struct page *page, gfp_t gfp); +static int shmem_replace_page(struct page **pagep, gfp_t gfp, + struct shmem_inode_info *info, pgoff_t index); +static int shmem_getpage_gfp(struct inode *inode, pgoff_t index, + struct page **pagep, enum sgp_type sgp, gfp_t gfp, int *fault_type); -static inline void shmem_swp_unmap(swp_entry_t *entry) +static inline int shmem_getpage(struct inode *inode, pgoff_t index, + struct page **pagep, enum sgp_type sgp, int *fault_type) { - kunmap_atomic(entry, KM_USER1); + return shmem_getpage_gfp(inode, index, pagep, sgp, + mapping_gfp_mask(inode->i_mapping), fault_type); } static inline struct shmem_sb_info *SHMEM_SB(struct super_block *sb) @@ -142,13 +139,13 @@ static inline struct shmem_sb_info *SHMEM_SB(struct super_block *sb) */ static inline int shmem_acct_size(unsigned long flags, loff_t size) { - return (flags & VM_ACCOUNT)? - security_vm_enough_memory(VM_ACCT(size)): 0; + return (flags & VM_NORESERVE) ? + 0 : security_vm_enough_memory_mm(current->mm, VM_ACCT(size)); } static inline void shmem_unacct_size(unsigned long flags, loff_t size) { - if (flags & VM_ACCOUNT) + if (!(flags & VM_NORESERVE)) vm_unacct_memory(VM_ACCT(size)); } @@ -160,46 +157,59 @@ static inline void shmem_unacct_size(unsigned long flags, loff_t size) */ static inline int shmem_acct_block(unsigned long flags) { - return (flags & VM_ACCOUNT)? - 0: security_vm_enough_memory(VM_ACCT(PAGE_CACHE_SIZE)); + return (flags & VM_NORESERVE) ? + security_vm_enough_memory_mm(current->mm, VM_ACCT(PAGE_CACHE_SIZE)) : 0; } static inline void shmem_unacct_blocks(unsigned long flags, long pages) { - if (!(flags & VM_ACCOUNT)) + if (flags & VM_NORESERVE) vm_unacct_memory(pages * VM_ACCT(PAGE_CACHE_SIZE)); } -static struct super_operations shmem_ops; -static struct address_space_operations shmem_aops; -static struct file_operations shmem_file_operations; -static struct inode_operations shmem_inode_operations; -static struct inode_operations shmem_dir_inode_operations; -static struct vm_operations_struct shmem_vm_ops; +static const struct super_operations shmem_ops; +static const struct address_space_operations shmem_aops; +static const struct file_operations shmem_file_operations; +static const struct inode_operations shmem_inode_operations; +static const struct inode_operations shmem_dir_inode_operations; +static const struct inode_operations shmem_special_inode_operations; +static const struct vm_operations_struct shmem_vm_ops; static struct backing_dev_info shmem_backing_dev_info __read_mostly = { .ra_pages = 0, /* No readahead */ - .capabilities = BDI_CAP_NO_ACCT_DIRTY | BDI_CAP_NO_WRITEBACK, - .unplug_io_fn = default_unplug_io_fn, + .capabilities = BDI_CAP_NO_ACCT_AND_WRITEBACK | BDI_CAP_SWAP_BACKED, }; static LIST_HEAD(shmem_swaplist); -static DEFINE_SPINLOCK(shmem_swaplist_lock); +static DEFINE_MUTEX(shmem_swaplist_mutex); -static void shmem_free_blocks(struct inode *inode, long pages) +static int shmem_reserve_inode(struct super_block *sb) { - struct shmem_sb_info *sbinfo = SHMEM_SB(inode->i_sb); - if (sbinfo->max_blocks) { + struct shmem_sb_info *sbinfo = SHMEM_SB(sb); + if (sbinfo->max_inodes) { + spin_lock(&sbinfo->stat_lock); + if (!sbinfo->free_inodes) { + spin_unlock(&sbinfo->stat_lock); + return -ENOSPC; + } + sbinfo->free_inodes--; + spin_unlock(&sbinfo->stat_lock); + } + return 0; +} + +static void shmem_free_inode(struct super_block *sb) +{ + struct shmem_sb_info *sbinfo = SHMEM_SB(sb); + if (sbinfo->max_inodes) { spin_lock(&sbinfo->stat_lock); - sbinfo->free_blocks += pages; - inode->i_blocks -= pages*BLOCKS_PER_PAGE; + sbinfo->free_inodes++; spin_unlock(&sbinfo->stat_lock); } } -/* - * shmem_recalc_inode - recalculate the size of an inode - * +/** + * shmem_recalc_inode - recalculate the block usage of an inode * @inode: inode to recalc * * We have to calculate the free blocks since the mm can drop @@ -217,588 +227,493 @@ static void shmem_recalc_inode(struct inode *inode) freed = info->alloced - info->swapped - inode->i_mapping->nrpages; if (freed > 0) { + struct shmem_sb_info *sbinfo = SHMEM_SB(inode->i_sb); + if (sbinfo->max_blocks) + percpu_counter_add(&sbinfo->used_blocks, -freed); info->alloced -= freed; + inode->i_blocks -= freed * BLOCKS_PER_PAGE; shmem_unacct_blocks(info->flags, freed); - shmem_free_blocks(inode, freed); } } /* - * shmem_swp_entry - find the swap vector position in the info structure - * - * @info: info structure for the inode - * @index: index of the page to find - * @page: optional page to add to the structure. Has to be preset to - * all zeros - * - * If there is no space allocated yet it will return NULL when - * page is NULL, else it will use the page for the needed block, - * setting it to NULL on return to indicate that it has been used. - * - * The swap vector is organized the following way: - * - * There are SHMEM_NR_DIRECT entries directly stored in the - * shmem_inode_info structure. So small files do not need an addional - * allocation. - * - * For pages with index > SHMEM_NR_DIRECT there is the pointer - * i_indirect which points to a page which holds in the first half - * doubly indirect blocks, in the second half triple indirect blocks: - * - * For an artificial ENTRIES_PER_PAGE = 4 this would lead to the - * following layout (for SHMEM_NR_DIRECT == 16): + * Replace item expected in radix tree by a new item, while holding tree lock. + */ +static int shmem_radix_tree_replace(struct address_space *mapping, + pgoff_t index, void *expected, void *replacement) +{ + void **pslot; + void *item; + + VM_BUG_ON(!expected); + VM_BUG_ON(!replacement); + pslot = radix_tree_lookup_slot(&mapping->page_tree, index); + if (!pslot) + return -ENOENT; + item = radix_tree_deref_slot_protected(pslot, &mapping->tree_lock); + if (item != expected) + return -ENOENT; + radix_tree_replace_slot(pslot, replacement); + return 0; +} + +/* + * Sometimes, before we decide whether to proceed or to fail, we must check + * that an entry was not already brought back from swap by a racing thread. * - * i_indirect -> dir --> 16-19 - * | +-> 20-23 - * | - * +-->dir2 --> 24-27 - * | +-> 28-31 - * | +-> 32-35 - * | +-> 36-39 - * | - * +-->dir3 --> 40-43 - * +-> 44-47 - * +-> 48-51 - * +-> 52-55 + * Checking page is not enough: by the time a SwapCache page is locked, it + * might be reused, and again be SwapCache, using the same swap as before. */ -static swp_entry_t *shmem_swp_entry(struct shmem_inode_info *info, unsigned long index, struct page **page) +static bool shmem_confirm_swap(struct address_space *mapping, + pgoff_t index, swp_entry_t swap) { - unsigned long offset; - struct page **dir; - struct page *subdir; + void *item; - if (index < SHMEM_NR_DIRECT) { - shmem_swp_balance_unmap(); - return info->i_direct+index; - } - if (!info->i_indirect) { - if (page) { - info->i_indirect = *page; - *page = NULL; - } - return NULL; /* need another page */ - } + rcu_read_lock(); + item = radix_tree_lookup(&mapping->page_tree, index); + rcu_read_unlock(); + return item == swp_to_radix_entry(swap); +} - index -= SHMEM_NR_DIRECT; - offset = index % ENTRIES_PER_PAGE; - index /= ENTRIES_PER_PAGE; - dir = shmem_dir_map(info->i_indirect); - - if (index >= ENTRIES_PER_PAGE/2) { - index -= ENTRIES_PER_PAGE/2; - dir += ENTRIES_PER_PAGE/2 + index/ENTRIES_PER_PAGE; - index %= ENTRIES_PER_PAGE; - subdir = *dir; - if (!subdir) { - if (page) { - *dir = *page; - *page = NULL; - } - shmem_dir_unmap(dir); - return NULL; /* need another page */ - } - shmem_dir_unmap(dir); - dir = shmem_dir_map(subdir); - } +/* + * Like add_to_page_cache_locked, but error if expected item has gone. + */ +static int shmem_add_to_page_cache(struct page *page, + struct address_space *mapping, + pgoff_t index, gfp_t gfp, void *expected) +{ + int error; - dir += index; - subdir = *dir; - if (!subdir) { - if (!page || !(subdir = *page)) { - shmem_dir_unmap(dir); - return NULL; /* need a page */ - } - *dir = subdir; - *page = NULL; + VM_BUG_ON_PAGE(!PageLocked(page), page); + VM_BUG_ON_PAGE(!PageSwapBacked(page), page); + + page_cache_get(page); + page->mapping = mapping; + page->index = index; + + spin_lock_irq(&mapping->tree_lock); + if (!expected) + error = radix_tree_insert(&mapping->page_tree, index, page); + else + error = shmem_radix_tree_replace(mapping, index, expected, + page); + if (!error) { + mapping->nrpages++; + __inc_zone_page_state(page, NR_FILE_PAGES); + __inc_zone_page_state(page, NR_SHMEM); + spin_unlock_irq(&mapping->tree_lock); + } else { + page->mapping = NULL; + spin_unlock_irq(&mapping->tree_lock); + page_cache_release(page); } - shmem_dir_unmap(dir); - return shmem_swp_map(subdir) + offset; + return error; } -static void shmem_swp_set(struct shmem_inode_info *info, swp_entry_t *entry, unsigned long value) +/* + * Like delete_from_page_cache, but substitutes swap for page. + */ +static void shmem_delete_from_page_cache(struct page *page, void *radswap) { - long incdec = value? 1: -1; + struct address_space *mapping = page->mapping; + int error; - entry->val = value; - info->swapped += incdec; - if ((unsigned long)(entry - info->i_direct) >= SHMEM_NR_DIRECT) { - struct page *page = kmap_atomic_to_page(entry); - set_page_private(page, page_private(page) + incdec); - } + spin_lock_irq(&mapping->tree_lock); + error = shmem_radix_tree_replace(mapping, page->index, page, radswap); + page->mapping = NULL; + mapping->nrpages--; + __dec_zone_page_state(page, NR_FILE_PAGES); + __dec_zone_page_state(page, NR_SHMEM); + spin_unlock_irq(&mapping->tree_lock); + page_cache_release(page); + BUG_ON(error); } /* - * shmem_swp_alloc - get the position of the swap entry for the page. - * If it does not exist allocate the entry. - * - * @info: info structure for the inode - * @index: index of the page to find - * @sgp: check and recheck i_size? skip allocation? + * Remove swap entry from radix tree, free the swap and its page cache. */ -static swp_entry_t *shmem_swp_alloc(struct shmem_inode_info *info, unsigned long index, enum sgp_type sgp) +static int shmem_free_swap(struct address_space *mapping, + pgoff_t index, void *radswap) { - struct inode *inode = &info->vfs_inode; - struct shmem_sb_info *sbinfo = SHMEM_SB(inode->i_sb); - struct page *page = NULL; - swp_entry_t *entry; + void *old; - if (sgp != SGP_WRITE && - ((loff_t) index << PAGE_CACHE_SHIFT) >= i_size_read(inode)) - return ERR_PTR(-EINVAL); + spin_lock_irq(&mapping->tree_lock); + old = radix_tree_delete_item(&mapping->page_tree, index, radswap); + spin_unlock_irq(&mapping->tree_lock); + if (old != radswap) + return -ENOENT; + free_swap_and_cache(radix_to_swp_entry(radswap)); + return 0; +} - while (!(entry = shmem_swp_entry(info, index, &page))) { - if (sgp == SGP_READ) - return shmem_swp_map(ZERO_PAGE(0)); +/* + * SysV IPC SHM_UNLOCK restore Unevictable pages to their evictable lists. + */ +void shmem_unlock_mapping(struct address_space *mapping) +{ + struct pagevec pvec; + pgoff_t indices[PAGEVEC_SIZE]; + pgoff_t index = 0; + + pagevec_init(&pvec, 0); + /* + * Minor point, but we might as well stop if someone else SHM_LOCKs it. + */ + while (!mapping_unevictable(mapping)) { /* - * Test free_blocks against 1 not 0, since we have 1 data - * page (and perhaps indirect index pages) yet to allocate: - * a waste to allocate index if we cannot allocate data. + * Avoid pagevec_lookup(): find_get_pages() returns 0 as if it + * has finished, if it hits a row of PAGEVEC_SIZE swap entries. */ - if (sbinfo->max_blocks) { - spin_lock(&sbinfo->stat_lock); - if (sbinfo->free_blocks <= 1) { - spin_unlock(&sbinfo->stat_lock); - return ERR_PTR(-ENOSPC); - } - sbinfo->free_blocks--; - inode->i_blocks += BLOCKS_PER_PAGE; - spin_unlock(&sbinfo->stat_lock); - } - - spin_unlock(&info->lock); - page = shmem_dir_alloc(mapping_gfp_mask(inode->i_mapping) | __GFP_ZERO); - if (page) - set_page_private(page, 0); - spin_lock(&info->lock); - - if (!page) { - shmem_free_blocks(inode, 1); - return ERR_PTR(-ENOMEM); - } - if (sgp != SGP_WRITE && - ((loff_t) index << PAGE_CACHE_SHIFT) >= i_size_read(inode)) { - entry = ERR_PTR(-EINVAL); + pvec.nr = find_get_entries(mapping, index, + PAGEVEC_SIZE, pvec.pages, indices); + if (!pvec.nr) break; - } - if (info->next_index <= index) - info->next_index = index + 1; - } - if (page) { - /* another task gave its page, or truncated the file */ - shmem_free_blocks(inode, 1); - shmem_dir_free(page); + index = indices[pvec.nr - 1] + 1; + pagevec_remove_exceptionals(&pvec); + check_move_unevictable_pages(pvec.pages, pvec.nr); + pagevec_release(&pvec); + cond_resched(); } - if (info->next_index <= index && !IS_ERR(entry)) - info->next_index = index + 1; - return entry; } /* - * shmem_free_swp - free some swap entries in a directory - * - * @dir: pointer to the directory - * @edir: pointer after last entry of the directory + * Remove range of pages and swap entries from radix tree, and free them. + * If !unfalloc, truncate or punch hole; if unfalloc, undo failed fallocate. */ -static int shmem_free_swp(swp_entry_t *dir, swp_entry_t *edir) +static void shmem_undo_range(struct inode *inode, loff_t lstart, loff_t lend, + bool unfalloc) { - swp_entry_t *ptr; - int freed = 0; + struct address_space *mapping = inode->i_mapping; + struct shmem_inode_info *info = SHMEM_I(inode); + pgoff_t start = (lstart + PAGE_CACHE_SIZE - 1) >> PAGE_CACHE_SHIFT; + pgoff_t end = (lend + 1) >> PAGE_CACHE_SHIFT; + unsigned int partial_start = lstart & (PAGE_CACHE_SIZE - 1); + unsigned int partial_end = (lend + 1) & (PAGE_CACHE_SIZE - 1); + struct pagevec pvec; + pgoff_t indices[PAGEVEC_SIZE]; + long nr_swaps_freed = 0; + pgoff_t index; + int i; + + if (lend == -1) + end = -1; /* unsigned, so actually very big */ + + pagevec_init(&pvec, 0); + index = start; + while (index < end) { + pvec.nr = find_get_entries(mapping, index, + min(end - index, (pgoff_t)PAGEVEC_SIZE), + pvec.pages, indices); + if (!pvec.nr) + break; + mem_cgroup_uncharge_start(); + for (i = 0; i < pagevec_count(&pvec); i++) { + struct page *page = pvec.pages[i]; + + index = indices[i]; + if (index >= end) + break; + + if (radix_tree_exceptional_entry(page)) { + if (unfalloc) + continue; + nr_swaps_freed += !shmem_free_swap(mapping, + index, page); + continue; + } - for (ptr = dir; ptr < edir; ptr++) { - if (ptr->val) { - free_swap_and_cache(*ptr); - *ptr = (swp_entry_t){0}; - freed++; + if (!trylock_page(page)) + continue; + if (!unfalloc || !PageUptodate(page)) { + if (page->mapping == mapping) { + VM_BUG_ON_PAGE(PageWriteback(page), page); + truncate_inode_page(mapping, page); + } + } + unlock_page(page); } + pagevec_remove_exceptionals(&pvec); + pagevec_release(&pvec); + mem_cgroup_uncharge_end(); + cond_resched(); + index++; } - return freed; -} - -static int shmem_map_and_free_swp(struct page *subdir, - int offset, int limit, struct page ***dir) -{ - swp_entry_t *ptr; - int freed = 0; - - ptr = shmem_swp_map(subdir); - for (; offset < limit; offset += LATENCY_LIMIT) { - int size = limit - offset; - if (size > LATENCY_LIMIT) - size = LATENCY_LIMIT; - freed += shmem_free_swp(ptr+offset, ptr+offset+size); - if (need_resched()) { - shmem_swp_unmap(ptr); - if (*dir) { - shmem_dir_unmap(*dir); - *dir = NULL; + + if (partial_start) { + struct page *page = NULL; + shmem_getpage(inode, start - 1, &page, SGP_READ, NULL); + if (page) { + unsigned int top = PAGE_CACHE_SIZE; + if (start > end) { + top = partial_end; + partial_end = 0; } - cond_resched(); - ptr = shmem_swp_map(subdir); + zero_user_segment(page, partial_start, top); + set_page_dirty(page); + unlock_page(page); + page_cache_release(page); } } - shmem_swp_unmap(ptr); - return freed; -} - -static void shmem_free_pages(struct list_head *next) -{ - struct page *page; - int freed = 0; - - do { - page = container_of(next, struct page, lru); - next = next->next; - shmem_dir_free(page); - freed++; - if (freed >= LATENCY_LIMIT) { - cond_resched(); - freed = 0; + if (partial_end) { + struct page *page = NULL; + shmem_getpage(inode, end, &page, SGP_READ, NULL); + if (page) { + zero_user_segment(page, 0, partial_end); + set_page_dirty(page); + unlock_page(page); + page_cache_release(page); } - } while (next); -} + } + if (start >= end) + return; -static void shmem_truncate(struct inode *inode) -{ - struct shmem_inode_info *info = SHMEM_I(inode); - unsigned long idx; - unsigned long size; - unsigned long limit; - unsigned long stage; - unsigned long diroff; - struct page **dir; - struct page *topdir; - struct page *middir; - struct page *subdir; - swp_entry_t *ptr; - LIST_HEAD(pages_to_free); - long nr_pages_to_free = 0; - long nr_swaps_freed = 0; - int offset; - int freed; + index = start; + while (index < end) { + cond_resched(); - inode->i_ctime = inode->i_mtime = CURRENT_TIME; - idx = (inode->i_size + PAGE_CACHE_SIZE - 1) >> PAGE_CACHE_SHIFT; - if (idx >= info->next_index) - return; + pvec.nr = find_get_entries(mapping, index, + min(end - index, (pgoff_t)PAGEVEC_SIZE), + pvec.pages, indices); + if (!pvec.nr) { + /* If all gone or hole-punch or unfalloc, we're done */ + if (index == start || end != -1) + break; + /* But if truncating, restart to make sure all gone */ + index = start; + continue; + } + mem_cgroup_uncharge_start(); + for (i = 0; i < pagevec_count(&pvec); i++) { + struct page *page = pvec.pages[i]; - spin_lock(&info->lock); - info->flags |= SHMEM_TRUNCATE; - limit = info->next_index; - info->next_index = idx; - topdir = info->i_indirect; - if (topdir && idx <= SHMEM_NR_DIRECT) { - info->i_indirect = NULL; - nr_pages_to_free++; - list_add(&topdir->lru, &pages_to_free); - } - spin_unlock(&info->lock); + index = indices[i]; + if (index >= end) + break; - if (info->swapped && idx < SHMEM_NR_DIRECT) { - ptr = info->i_direct; - size = limit; - if (size > SHMEM_NR_DIRECT) - size = SHMEM_NR_DIRECT; - nr_swaps_freed = shmem_free_swp(ptr+idx, ptr+size); - } - if (!topdir) - goto done2; - - BUG_ON(limit <= SHMEM_NR_DIRECT); - limit -= SHMEM_NR_DIRECT; - idx = (idx > SHMEM_NR_DIRECT)? (idx - SHMEM_NR_DIRECT): 0; - offset = idx % ENTRIES_PER_PAGE; - idx -= offset; - - dir = shmem_dir_map(topdir); - stage = ENTRIES_PER_PAGEPAGE/2; - if (idx < ENTRIES_PER_PAGEPAGE/2) { - middir = topdir; - diroff = idx/ENTRIES_PER_PAGE; - } else { - dir += ENTRIES_PER_PAGE/2; - dir += (idx - ENTRIES_PER_PAGEPAGE/2)/ENTRIES_PER_PAGEPAGE; - while (stage <= idx) - stage += ENTRIES_PER_PAGEPAGE; - middir = *dir; - if (*dir) { - diroff = ((idx - ENTRIES_PER_PAGEPAGE/2) % - ENTRIES_PER_PAGEPAGE) / ENTRIES_PER_PAGE; - if (!diroff && !offset) { - *dir = NULL; - nr_pages_to_free++; - list_add(&middir->lru, &pages_to_free); + if (radix_tree_exceptional_entry(page)) { + if (unfalloc) + continue; + if (shmem_free_swap(mapping, index, page)) { + /* Swap was replaced by page: retry */ + index--; + break; + } + nr_swaps_freed++; + continue; } - shmem_dir_unmap(dir); - dir = shmem_dir_map(middir); - } else { - diroff = 0; - offset = 0; - idx = stage; - } - } - for (; idx < limit; idx += ENTRIES_PER_PAGE, diroff++) { - if (unlikely(idx == stage)) { - shmem_dir_unmap(dir); - dir = shmem_dir_map(topdir) + - ENTRIES_PER_PAGE/2 + idx/ENTRIES_PER_PAGEPAGE; - while (!*dir) { - dir++; - idx += ENTRIES_PER_PAGEPAGE; - if (idx >= limit) - goto done1; + lock_page(page); + if (!unfalloc || !PageUptodate(page)) { + if (page->mapping == mapping) { + VM_BUG_ON_PAGE(PageWriteback(page), page); + truncate_inode_page(mapping, page); + } else { + /* Page was replaced by swap: retry */ + unlock_page(page); + index--; + break; + } } - stage = idx + ENTRIES_PER_PAGEPAGE; - middir = *dir; - *dir = NULL; - nr_pages_to_free++; - list_add(&middir->lru, &pages_to_free); - shmem_dir_unmap(dir); - cond_resched(); - dir = shmem_dir_map(middir); - diroff = 0; - } - subdir = dir[diroff]; - if (subdir && page_private(subdir)) { - size = limit - idx; - if (size > ENTRIES_PER_PAGE) - size = ENTRIES_PER_PAGE; - freed = shmem_map_and_free_swp(subdir, - offset, size, &dir); - if (!dir) - dir = shmem_dir_map(middir); - nr_swaps_freed += freed; - if (offset) - spin_lock(&info->lock); - set_page_private(subdir, page_private(subdir) - freed); - if (offset) - spin_unlock(&info->lock); - BUG_ON(page_private(subdir) > offset); + unlock_page(page); } - if (offset) - offset = 0; - else if (subdir) { - dir[diroff] = NULL; - nr_pages_to_free++; - list_add(&subdir->lru, &pages_to_free); - } - } -done1: - shmem_dir_unmap(dir); -done2: - if (inode->i_mapping->nrpages && (info->flags & SHMEM_PAGEIN)) { - /* - * Call truncate_inode_pages again: racing shmem_unuse_inode - * may have swizzled a page in from swap since vmtruncate or - * generic_delete_inode did it, before we lowered next_index. - * Also, though shmem_getpage checks i_size before adding to - * cache, no recheck after: so fix the narrow window there too. - */ - truncate_inode_pages(inode->i_mapping, inode->i_size); + pagevec_remove_exceptionals(&pvec); + pagevec_release(&pvec); + mem_cgroup_uncharge_end(); + index++; } spin_lock(&info->lock); - info->flags &= ~SHMEM_TRUNCATE; info->swapped -= nr_swaps_freed; - if (nr_pages_to_free) - shmem_free_blocks(inode, nr_pages_to_free); shmem_recalc_inode(inode); spin_unlock(&info->lock); +} - /* - * Empty swap vector directory pages to be freed? - */ - if (!list_empty(&pages_to_free)) { - pages_to_free.prev->next = NULL; - shmem_free_pages(pages_to_free.next); - } +void shmem_truncate_range(struct inode *inode, loff_t lstart, loff_t lend) +{ + shmem_undo_range(inode, lstart, lend, false); + inode->i_ctime = inode->i_mtime = CURRENT_TIME; } +EXPORT_SYMBOL_GPL(shmem_truncate_range); -static int shmem_notify_change(struct dentry *dentry, struct iattr *attr) +static int shmem_setattr(struct dentry *dentry, struct iattr *attr) { struct inode *inode = dentry->d_inode; - struct page *page = NULL; int error; - if (attr->ia_valid & ATTR_SIZE) { - if (attr->ia_size < inode->i_size) { - /* - * If truncating down to a partial page, then - * if that page is already allocated, hold it - * in memory until the truncation is over, so - * truncate_partial_page cannnot miss it were - * it assigned to swap. - */ - if (attr->ia_size & (PAGE_CACHE_SIZE-1)) { - (void) shmem_getpage(inode, - attr->ia_size>>PAGE_CACHE_SHIFT, - &page, SGP_READ, NULL); - } - /* - * Reset SHMEM_PAGEIN flag so that shmem_truncate can - * detect if any pages might have been added to cache - * after truncate_inode_pages. But we needn't bother - * if it's being fully truncated to zero-length: the - * nrpages check is efficient enough in that case. - */ - if (attr->ia_size) { - struct shmem_inode_info *info = SHMEM_I(inode); - spin_lock(&info->lock); - info->flags &= ~SHMEM_PAGEIN; - spin_unlock(&info->lock); - } + error = inode_change_ok(inode, attr); + if (error) + return error; + + if (S_ISREG(inode->i_mode) && (attr->ia_valid & ATTR_SIZE)) { + loff_t oldsize = inode->i_size; + loff_t newsize = attr->ia_size; + + if (newsize != oldsize) { + i_size_write(inode, newsize); + inode->i_ctime = inode->i_mtime = CURRENT_TIME; + } + if (newsize < oldsize) { + loff_t holebegin = round_up(newsize, PAGE_SIZE); + unmap_mapping_range(inode->i_mapping, holebegin, 0, 1); + shmem_truncate_range(inode, newsize, (loff_t)-1); + /* unmap again to remove racily COWed private pages */ + unmap_mapping_range(inode->i_mapping, holebegin, 0, 1); } } - error = inode_change_ok(inode, attr); - if (!error) - error = inode_setattr(inode, attr); - if (page) - page_cache_release(page); + setattr_copy(inode, attr); + if (attr->ia_valid & ATTR_MODE) + error = posix_acl_chmod(inode, inode->i_mode); return error; } -static void shmem_delete_inode(struct inode *inode) +static void shmem_evict_inode(struct inode *inode) { - struct shmem_sb_info *sbinfo = SHMEM_SB(inode->i_sb); struct shmem_inode_info *info = SHMEM_I(inode); - if (inode->i_op->truncate == shmem_truncate) { - truncate_inode_pages(inode->i_mapping, 0); + if (inode->i_mapping->a_ops == &shmem_aops) { shmem_unacct_size(info->flags, inode->i_size); inode->i_size = 0; - shmem_truncate(inode); + shmem_truncate_range(inode, 0, (loff_t)-1); if (!list_empty(&info->swaplist)) { - spin_lock(&shmem_swaplist_lock); + mutex_lock(&shmem_swaplist_mutex); list_del_init(&info->swaplist); - spin_unlock(&shmem_swaplist_lock); + mutex_unlock(&shmem_swaplist_mutex); } - } - BUG_ON(inode->i_blocks); - if (sbinfo->max_inodes) { - spin_lock(&sbinfo->stat_lock); - sbinfo->free_inodes++; - spin_unlock(&sbinfo->stat_lock); - } + } else + kfree(info->symlink); + + simple_xattrs_free(&info->xattrs); + WARN_ON(inode->i_blocks); + shmem_free_inode(inode->i_sb); clear_inode(inode); } -static inline int shmem_find_swp(swp_entry_t entry, swp_entry_t *dir, swp_entry_t *edir) -{ - swp_entry_t *ptr; +/* + * If swap found in inode, free it and move page from swapcache to filecache. + */ +static int shmem_unuse_inode(struct shmem_inode_info *info, + swp_entry_t swap, struct page **pagep) +{ + struct address_space *mapping = info->vfs_inode.i_mapping; + void *radswap; + pgoff_t index; + gfp_t gfp; + int error = 0; + + radswap = swp_to_radix_entry(swap); + index = radix_tree_locate_item(&mapping->page_tree, radswap); + if (index == -1) + return 0; - for (ptr = dir; ptr < edir; ptr++) { - if (ptr->val == entry.val) - return ptr - dir; + /* + * Move _head_ to start search for next from here. + * But be careful: shmem_evict_inode checks list_empty without taking + * mutex, and there's an instant in list_move_tail when info->swaplist + * would appear empty, if it were the only one on shmem_swaplist. + */ + if (shmem_swaplist.next != &info->swaplist) + list_move_tail(&shmem_swaplist, &info->swaplist); + + gfp = mapping_gfp_mask(mapping); + if (shmem_should_replace_page(*pagep, gfp)) { + mutex_unlock(&shmem_swaplist_mutex); + error = shmem_replace_page(pagep, gfp, info, index); + mutex_lock(&shmem_swaplist_mutex); + /* + * We needed to drop mutex to make that restrictive page + * allocation, but the inode might have been freed while we + * dropped it: although a racing shmem_evict_inode() cannot + * complete without emptying the radix_tree, our page lock + * on this swapcache page is not enough to prevent that - + * free_swap_and_cache() of our swap entry will only + * trylock_page(), removing swap from radix_tree whatever. + * + * We must not proceed to shmem_add_to_page_cache() if the + * inode has been freed, but of course we cannot rely on + * inode or mapping or info to check that. However, we can + * safely check if our swap entry is still in use (and here + * it can't have got reused for another page): if it's still + * in use, then the inode cannot have been freed yet, and we + * can safely proceed (if it's no longer in use, that tells + * nothing about the inode, but we don't need to unuse swap). + */ + if (!page_swapcount(*pagep)) + error = -ENOENT; } - return -1; -} -static int shmem_unuse_inode(struct shmem_inode_info *info, swp_entry_t entry, struct page *page) -{ - struct inode *inode; - unsigned long idx; - unsigned long size; - unsigned long limit; - unsigned long stage; - struct page **dir; - struct page *subdir; - swp_entry_t *ptr; - int offset; - - idx = 0; - ptr = info->i_direct; - spin_lock(&info->lock); - limit = info->next_index; - size = limit; - if (size > SHMEM_NR_DIRECT) - size = SHMEM_NR_DIRECT; - offset = shmem_find_swp(entry, ptr, ptr+size); - if (offset >= 0) { - shmem_swp_balance_unmap(); - goto found; - } - if (!info->i_indirect) - goto lost2; - - dir = shmem_dir_map(info->i_indirect); - stage = SHMEM_NR_DIRECT + ENTRIES_PER_PAGEPAGE/2; - - for (idx = SHMEM_NR_DIRECT; idx < limit; idx += ENTRIES_PER_PAGE, dir++) { - if (unlikely(idx == stage)) { - shmem_dir_unmap(dir-1); - dir = shmem_dir_map(info->i_indirect) + - ENTRIES_PER_PAGE/2 + idx/ENTRIES_PER_PAGEPAGE; - while (!*dir) { - dir++; - idx += ENTRIES_PER_PAGEPAGE; - if (idx >= limit) - goto lost1; - } - stage = idx + ENTRIES_PER_PAGEPAGE; - subdir = *dir; - shmem_dir_unmap(dir); - dir = shmem_dir_map(subdir); - } - subdir = *dir; - if (subdir && page_private(subdir)) { - ptr = shmem_swp_map(subdir); - size = limit - idx; - if (size > ENTRIES_PER_PAGE) - size = ENTRIES_PER_PAGE; - offset = shmem_find_swp(entry, ptr, ptr+size); - if (offset >= 0) { - shmem_dir_unmap(dir); - goto found; - } - shmem_swp_unmap(ptr); - } - } -lost1: - shmem_dir_unmap(dir-1); -lost2: - spin_unlock(&info->lock); - return 0; -found: - idx += offset; - inode = &info->vfs_inode; - if (move_from_swap_cache(page, idx, inode->i_mapping) == 0) { - info->flags |= SHMEM_PAGEIN; - shmem_swp_set(info, ptr + offset, 0); - } - shmem_swp_unmap(ptr); - spin_unlock(&info->lock); /* - * Decrement swap count even when the entry is left behind: - * try_to_unuse will skip over mms, then reincrement count. + * We rely on shmem_swaplist_mutex, not only to protect the swaplist, + * but also to hold up shmem_evict_inode(): so inode cannot be freed + * beneath us (pagelock doesn't help until the page is in pagecache). */ - swap_free(entry); - return 1; + if (!error) + error = shmem_add_to_page_cache(*pagep, mapping, index, + GFP_NOWAIT, radswap); + if (error != -ENOMEM) { + /* + * Truncation and eviction use free_swap_and_cache(), which + * only does trylock page: if we raced, best clean up here. + */ + delete_from_swap_cache(*pagep); + set_page_dirty(*pagep); + if (!error) { + spin_lock(&info->lock); + info->swapped--; + spin_unlock(&info->lock); + swap_free(swap); + } + error = 1; /* not an error, but entry was found */ + } + return error; } /* - * shmem_unuse() search for an eventually swapped out shmem page. + * Search through swapped inodes to find and replace swap by page. */ -int shmem_unuse(swp_entry_t entry, struct page *page) +int shmem_unuse(swp_entry_t swap, struct page *page) { - struct list_head *p, *next; + struct list_head *this, *next; struct shmem_inode_info *info; int found = 0; + int error = 0; + + /* + * There's a faint possibility that swap page was replaced before + * caller locked it: caller will come back later with the right page. + */ + if (unlikely(!PageSwapCache(page) || page_private(page) != swap.val)) + goto out; - spin_lock(&shmem_swaplist_lock); - list_for_each_safe(p, next, &shmem_swaplist) { - info = list_entry(p, struct shmem_inode_info, swaplist); - if (!info->swapped) + /* + * Charge page using GFP_KERNEL while we can wait, before taking + * the shmem_swaplist_mutex which might hold up shmem_writepage(). + * Charged back to the user (not to caller) when swap account is used. + */ + error = mem_cgroup_charge_file(page, current->mm, GFP_KERNEL); + if (error) + goto out; + /* No radix_tree_preload: swap entry keeps a place for page in tree */ + + mutex_lock(&shmem_swaplist_mutex); + list_for_each_safe(this, next, &shmem_swaplist) { + info = list_entry(this, struct shmem_inode_info, swaplist); + if (info->swapped) + found = shmem_unuse_inode(info, swap, &page); + else list_del_init(&info->swaplist); - else if (shmem_unuse_inode(info, entry, page)) { - /* move head to start search for next from here */ - list_move_tail(&shmem_swaplist, &info->swaplist); - found = 1; + cond_resched(); + if (found) break; - } } - spin_unlock(&shmem_swaplist_lock); - return found; + mutex_unlock(&shmem_swaplist_mutex); + + if (found < 0) + error = found; +out: + unlock_page(page); + page_cache_release(page); + return error; } /* @@ -807,435 +722,624 @@ int shmem_unuse(swp_entry_t entry, struct page *page) static int shmem_writepage(struct page *page, struct writeback_control *wbc) { struct shmem_inode_info *info; - swp_entry_t *entry, swap; struct address_space *mapping; - unsigned long index; struct inode *inode; + swp_entry_t swap; + pgoff_t index; BUG_ON(!PageLocked(page)); - BUG_ON(page_mapped(page)); - mapping = page->mapping; index = page->index; inode = mapping->host; info = SHMEM_I(inode); if (info->flags & VM_LOCKED) goto redirty; + if (!total_swap_pages) + goto redirty; + + /* + * shmem_backing_dev_info's capabilities prevent regular writeback or + * sync from ever calling shmem_writepage; but a stacking filesystem + * might use ->writepage of its underlying filesystem, in which case + * tmpfs should write out to swap only in response to memory pressure, + * and not for the writeback threads or sync. + */ + if (!wbc->for_reclaim) { + WARN_ON_ONCE(1); /* Still happens? Tell us about it! */ + goto redirty; + } + + /* + * This is somewhat ridiculous, but without plumbing a SWAP_MAP_FALLOC + * value into swapfile.c, the only way we can correctly account for a + * fallocated page arriving here is now to initialize it and write it. + * + * That's okay for a page already fallocated earlier, but if we have + * not yet completed the fallocation, then (a) we want to keep track + * of this page in case we have to undo it, and (b) it may not be a + * good idea to continue anyway, once we're pushing into swap. So + * reactivate the page, and let shmem_fallocate() quit when too many. + */ + if (!PageUptodate(page)) { + if (inode->i_private) { + struct shmem_falloc *shmem_falloc; + spin_lock(&inode->i_lock); + shmem_falloc = inode->i_private; + if (shmem_falloc && + !shmem_falloc->waitq && + index >= shmem_falloc->start && + index < shmem_falloc->next) + shmem_falloc->nr_unswapped++; + else + shmem_falloc = NULL; + spin_unlock(&inode->i_lock); + if (shmem_falloc) + goto redirty; + } + clear_highpage(page); + flush_dcache_page(page); + SetPageUptodate(page); + } + swap = get_swap_page(); if (!swap.val) goto redirty; - spin_lock(&info->lock); - shmem_recalc_inode(inode); - if (index >= info->next_index) { - BUG_ON(!(info->flags & SHMEM_TRUNCATE)); - goto unlock; - } - entry = shmem_swp_entry(info, index, NULL); - BUG_ON(!entry); - BUG_ON(entry->val); + /* + * Add inode to shmem_unuse()'s list of swapped-out inodes, + * if it's not already there. Do it now before the page is + * moved to swap cache, when its pagelock no longer protects + * the inode from eviction. But don't unlock the mutex until + * we've incremented swapped, because shmem_unuse_inode() will + * prune a !swapped inode from the swaplist under this mutex. + */ + mutex_lock(&shmem_swaplist_mutex); + if (list_empty(&info->swaplist)) + list_add_tail(&info->swaplist, &shmem_swaplist); - if (move_to_swap_cache(page, swap) == 0) { - shmem_swp_set(info, entry, swap.val); - shmem_swp_unmap(entry); + if (add_to_swap_cache(page, swap, GFP_ATOMIC) == 0) { + swap_shmem_alloc(swap); + shmem_delete_from_page_cache(page, swp_to_radix_entry(swap)); + + spin_lock(&info->lock); + info->swapped++; + shmem_recalc_inode(inode); spin_unlock(&info->lock); - if (list_empty(&info->swaplist)) { - spin_lock(&shmem_swaplist_lock); - /* move instead of add in case we're racing */ - list_move_tail(&info->swaplist, &shmem_swaplist); - spin_unlock(&shmem_swaplist_lock); - } - unlock_page(page); + + mutex_unlock(&shmem_swaplist_mutex); + BUG_ON(page_mapped(page)); + swap_writepage(page, wbc); return 0; } - shmem_swp_unmap(entry); -unlock: - spin_unlock(&info->lock); - swap_free(swap); + mutex_unlock(&shmem_swaplist_mutex); + swapcache_free(swap, NULL); redirty: set_page_dirty(page); - return WRITEPAGE_ACTIVATE; /* Return with the page locked */ + if (wbc->for_reclaim) + return AOP_WRITEPAGE_ACTIVATE; /* Return with page locked */ + unlock_page(page); + return 0; } #ifdef CONFIG_NUMA -static struct page *shmem_swapin_async(struct shared_policy *p, - swp_entry_t entry, unsigned long idx) +#ifdef CONFIG_TMPFS +static void shmem_show_mpol(struct seq_file *seq, struct mempolicy *mpol) { - struct page *page; - struct vm_area_struct pvma; + char buffer[64]; - /* Create a pseudo vma that just contains the policy */ - memset(&pvma, 0, sizeof(struct vm_area_struct)); - pvma.vm_end = PAGE_SIZE; - pvma.vm_pgoff = idx; - pvma.vm_policy = mpol_shared_policy_lookup(p, idx); - page = read_swap_cache_async(entry, &pvma, 0); - mpol_free(pvma.vm_policy); - return page; + if (!mpol || mpol->mode == MPOL_DEFAULT) + return; /* show nothing */ + + mpol_to_str(buffer, sizeof(buffer), mpol); + + seq_printf(seq, ",mpol=%s", buffer); +} + +static struct mempolicy *shmem_get_sbmpol(struct shmem_sb_info *sbinfo) +{ + struct mempolicy *mpol = NULL; + if (sbinfo->mpol) { + spin_lock(&sbinfo->stat_lock); /* prevent replace/use races */ + mpol = sbinfo->mpol; + mpol_get(mpol); + spin_unlock(&sbinfo->stat_lock); + } + return mpol; } +#endif /* CONFIG_TMPFS */ -struct page *shmem_swapin(struct shmem_inode_info *info, swp_entry_t entry, - unsigned long idx) +static struct page *shmem_swapin(swp_entry_t swap, gfp_t gfp, + struct shmem_inode_info *info, pgoff_t index) { - struct shared_policy *p = &info->policy; - int i, num; + struct vm_area_struct pvma; struct page *page; - unsigned long offset; - num = valid_swaphandles(entry, &offset); - for (i = 0; i < num; offset++, i++) { - page = shmem_swapin_async(p, - swp_entry(swp_type(entry), offset), idx); - if (!page) - break; - page_cache_release(page); - } - lru_add_drain(); /* Push any new pages onto the LRU now */ - return shmem_swapin_async(p, entry, idx); + /* Create a pseudo vma that just contains the policy */ + pvma.vm_start = 0; + /* Bias interleave by inode number to distribute better across nodes */ + pvma.vm_pgoff = index + info->vfs_inode.i_ino; + pvma.vm_ops = NULL; + pvma.vm_policy = mpol_shared_policy_lookup(&info->policy, index); + + page = swapin_readahead(swap, gfp, &pvma, 0); + + /* Drop reference taken by mpol_shared_policy_lookup() */ + mpol_cond_put(pvma.vm_policy); + + return page; } -static struct page * -shmem_alloc_page(gfp_t gfp, struct shmem_inode_info *info, - unsigned long idx) +static struct page *shmem_alloc_page(gfp_t gfp, + struct shmem_inode_info *info, pgoff_t index) { struct vm_area_struct pvma; struct page *page; - memset(&pvma, 0, sizeof(struct vm_area_struct)); - pvma.vm_policy = mpol_shared_policy_lookup(&info->policy, idx); - pvma.vm_pgoff = idx; - pvma.vm_end = PAGE_SIZE; - page = alloc_page_vma(gfp | __GFP_ZERO, &pvma, 0); - mpol_free(pvma.vm_policy); + /* Create a pseudo vma that just contains the policy */ + pvma.vm_start = 0; + /* Bias interleave by inode number to distribute better across nodes */ + pvma.vm_pgoff = index + info->vfs_inode.i_ino; + pvma.vm_ops = NULL; + pvma.vm_policy = mpol_shared_policy_lookup(&info->policy, index); + + page = alloc_page_vma(gfp, &pvma, 0); + + /* Drop reference taken by mpol_shared_policy_lookup() */ + mpol_cond_put(pvma.vm_policy); + return page; } -#else -static inline struct page * -shmem_swapin(struct shmem_inode_info *info,swp_entry_t entry,unsigned long idx) +#else /* !CONFIG_NUMA */ +#ifdef CONFIG_TMPFS +static inline void shmem_show_mpol(struct seq_file *seq, struct mempolicy *mpol) +{ +} +#endif /* CONFIG_TMPFS */ + +static inline struct page *shmem_swapin(swp_entry_t swap, gfp_t gfp, + struct shmem_inode_info *info, pgoff_t index) +{ + return swapin_readahead(swap, gfp, NULL, 0); +} + +static inline struct page *shmem_alloc_page(gfp_t gfp, + struct shmem_inode_info *info, pgoff_t index) { - swapin_readahead(entry, 0, NULL); - return read_swap_cache_async(entry, NULL, 0); + return alloc_page(gfp); } +#endif /* CONFIG_NUMA */ -static inline struct page * -shmem_alloc_page(gfp_t gfp,struct shmem_inode_info *info, unsigned long idx) +#if !defined(CONFIG_NUMA) || !defined(CONFIG_TMPFS) +static inline struct mempolicy *shmem_get_sbmpol(struct shmem_sb_info *sbinfo) { - return alloc_page(gfp | __GFP_ZERO); + return NULL; } #endif /* - * shmem_getpage - either get the page from swap or allocate a new one + * When a page is moved from swapcache to shmem filecache (either by the + * usual swapin of shmem_getpage_gfp(), or by the less common swapoff of + * shmem_unuse_inode()), it may have been read in earlier from swap, in + * ignorance of the mapping it belongs to. If that mapping has special + * constraints (like the gma500 GEM driver, which requires RAM below 4GB), + * we may need to copy to a suitable page before moving to filecache. + * + * In a future release, this may well be extended to respect cpuset and + * NUMA mempolicy, and applied also to anonymous pages in do_swap_page(); + * but for now it is a simple matter of zone. + */ +static bool shmem_should_replace_page(struct page *page, gfp_t gfp) +{ + return page_zonenum(page) > gfp_zone(gfp); +} + +static int shmem_replace_page(struct page **pagep, gfp_t gfp, + struct shmem_inode_info *info, pgoff_t index) +{ + struct page *oldpage, *newpage; + struct address_space *swap_mapping; + pgoff_t swap_index; + int error; + + oldpage = *pagep; + swap_index = page_private(oldpage); + swap_mapping = page_mapping(oldpage); + + /* + * We have arrived here because our zones are constrained, so don't + * limit chance of success by further cpuset and node constraints. + */ + gfp &= ~GFP_CONSTRAINT_MASK; + newpage = shmem_alloc_page(gfp, info, index); + if (!newpage) + return -ENOMEM; + + page_cache_get(newpage); + copy_highpage(newpage, oldpage); + flush_dcache_page(newpage); + + __set_page_locked(newpage); + SetPageUptodate(newpage); + SetPageSwapBacked(newpage); + set_page_private(newpage, swap_index); + SetPageSwapCache(newpage); + + /* + * Our caller will very soon move newpage out of swapcache, but it's + * a nice clean interface for us to replace oldpage by newpage there. + */ + spin_lock_irq(&swap_mapping->tree_lock); + error = shmem_radix_tree_replace(swap_mapping, swap_index, oldpage, + newpage); + if (!error) { + __inc_zone_page_state(newpage, NR_FILE_PAGES); + __dec_zone_page_state(oldpage, NR_FILE_PAGES); + } + spin_unlock_irq(&swap_mapping->tree_lock); + + if (unlikely(error)) { + /* + * Is this possible? I think not, now that our callers check + * both PageSwapCache and page_private after getting page lock; + * but be defensive. Reverse old to newpage for clear and free. + */ + oldpage = newpage; + } else { + mem_cgroup_replace_page_cache(oldpage, newpage); + lru_cache_add_anon(newpage); + *pagep = newpage; + } + + ClearPageSwapCache(oldpage); + set_page_private(oldpage, 0); + + unlock_page(oldpage); + page_cache_release(oldpage); + page_cache_release(oldpage); + return error; +} + +/* + * shmem_getpage_gfp - find page in cache, or get from swap, or allocate * * If we allocate a new one we do not mark it dirty. That's up to the * vm. If we swap it in we mark it dirty since we also free the swap * entry since a page cannot live in both the swap and page cache */ -static int shmem_getpage(struct inode *inode, unsigned long idx, - struct page **pagep, enum sgp_type sgp, int *type) +static int shmem_getpage_gfp(struct inode *inode, pgoff_t index, + struct page **pagep, enum sgp_type sgp, gfp_t gfp, int *fault_type) { struct address_space *mapping = inode->i_mapping; - struct shmem_inode_info *info = SHMEM_I(inode); + struct shmem_inode_info *info; struct shmem_sb_info *sbinfo; - struct page *filepage = *pagep; - struct page *swappage; - swp_entry_t *entry; + struct page *page; swp_entry_t swap; int error; + int once = 0; + int alloced = 0; - if (idx >= SHMEM_MAX_INDEX) + if (index > (MAX_LFS_FILESIZE >> PAGE_CACHE_SHIFT)) return -EFBIG; - /* - * Normally, filepage is NULL on entry, and either found - * uptodate immediately, or allocated and zeroed, or read - * in under swappage, which is then assigned to filepage. - * But shmem_prepare_write passes in a locked filepage, - * which may be found not uptodate by other callers too, - * and may need to be copied from the swappage read in. - */ repeat: - if (!filepage) - filepage = find_lock_page(mapping, idx); - if (filepage && PageUptodate(filepage)) - goto done; - error = 0; - if (sgp == SGP_QUICK) - goto failed; + swap.val = 0; + page = find_lock_entry(mapping, index); + if (radix_tree_exceptional_entry(page)) { + swap = radix_to_swp_entry(page); + page = NULL; + } - spin_lock(&info->lock); - shmem_recalc_inode(inode); - entry = shmem_swp_alloc(info, idx, sgp); - if (IS_ERR(entry)) { - spin_unlock(&info->lock); - error = PTR_ERR(entry); + if (sgp != SGP_WRITE && sgp != SGP_FALLOC && + ((loff_t)index << PAGE_CACHE_SHIFT) >= i_size_read(inode)) { + error = -EINVAL; goto failed; } - swap = *entry; + + if (page && sgp == SGP_WRITE) + mark_page_accessed(page); + + /* fallocated page? */ + if (page && !PageUptodate(page)) { + if (sgp != SGP_READ) + goto clear; + unlock_page(page); + page_cache_release(page); + page = NULL; + } + if (page || (sgp == SGP_READ && !swap.val)) { + *pagep = page; + return 0; + } + + /* + * Fast cache lookup did not find it: + * bring it back from swap or allocate. + */ + info = SHMEM_I(inode); + sbinfo = SHMEM_SB(inode->i_sb); if (swap.val) { /* Look it up and read it in.. */ - swappage = lookup_swap_cache(swap); - if (!swappage) { - shmem_swp_unmap(entry); - spin_unlock(&info->lock); + page = lookup_swap_cache(swap); + if (!page) { /* here we actually do the io */ - if (type && *type == VM_FAULT_MINOR) { - inc_page_state(pgmajfault); - *type = VM_FAULT_MAJOR; - } - swappage = shmem_swapin(info, swap, idx); - if (!swappage) { - spin_lock(&info->lock); - entry = shmem_swp_alloc(info, idx, sgp); - if (IS_ERR(entry)) - error = PTR_ERR(entry); - else { - if (entry->val == swap.val) - error = -ENOMEM; - shmem_swp_unmap(entry); - } - spin_unlock(&info->lock); - if (error) - goto failed; - goto repeat; + if (fault_type) + *fault_type |= VM_FAULT_MAJOR; + page = shmem_swapin(swap, gfp, info, index); + if (!page) { + error = -ENOMEM; + goto failed; } - wait_on_page_locked(swappage); - page_cache_release(swappage); - goto repeat; } /* We have to do this with page locked to prevent races */ - if (TestSetPageLocked(swappage)) { - shmem_swp_unmap(entry); - spin_unlock(&info->lock); - wait_on_page_locked(swappage); - page_cache_release(swappage); - goto repeat; + lock_page(page); + if (!PageSwapCache(page) || page_private(page) != swap.val || + !shmem_confirm_swap(mapping, index, swap)) { + error = -EEXIST; /* try again */ + goto unlock; } - if (PageWriteback(swappage)) { - shmem_swp_unmap(entry); - spin_unlock(&info->lock); - wait_on_page_writeback(swappage); - unlock_page(swappage); - page_cache_release(swappage); - goto repeat; - } - if (!PageUptodate(swappage)) { - shmem_swp_unmap(entry); - spin_unlock(&info->lock); - unlock_page(swappage); - page_cache_release(swappage); + if (!PageUptodate(page)) { error = -EIO; goto failed; } + wait_on_page_writeback(page); - if (filepage) { - shmem_swp_set(info, entry, 0); - shmem_swp_unmap(entry); - delete_from_swap_cache(swappage); - spin_unlock(&info->lock); - copy_highpage(filepage, swappage); - unlock_page(swappage); - page_cache_release(swappage); - flush_dcache_page(filepage); - SetPageUptodate(filepage); - set_page_dirty(filepage); - swap_free(swap); - } else if (!(error = move_from_swap_cache( - swappage, idx, mapping))) { - info->flags |= SHMEM_PAGEIN; - shmem_swp_set(info, entry, 0); - shmem_swp_unmap(entry); - spin_unlock(&info->lock); - filepage = swappage; - swap_free(swap); - } else { - shmem_swp_unmap(entry); - spin_unlock(&info->lock); - unlock_page(swappage); - page_cache_release(swappage); - if (error == -ENOMEM) { - /* let kswapd refresh zone for GFP_ATOMICs */ - blk_congestion_wait(WRITE, HZ/50); - } - goto repeat; + if (shmem_should_replace_page(page, gfp)) { + error = shmem_replace_page(&page, gfp, info, index); + if (error) + goto failed; } - } else if (sgp == SGP_READ && !filepage) { - shmem_swp_unmap(entry); - filepage = find_get_page(mapping, idx); - if (filepage && - (!PageUptodate(filepage) || TestSetPageLocked(filepage))) { - spin_unlock(&info->lock); - wait_on_page_locked(filepage); - page_cache_release(filepage); - filepage = NULL; - goto repeat; + + error = mem_cgroup_charge_file(page, current->mm, + gfp & GFP_RECLAIM_MASK); + if (!error) { + error = shmem_add_to_page_cache(page, mapping, index, + gfp, swp_to_radix_entry(swap)); + /* + * We already confirmed swap under page lock, and make + * no memory allocation here, so usually no possibility + * of error; but free_swap_and_cache() only trylocks a + * page, so it is just possible that the entry has been + * truncated or holepunched since swap was confirmed. + * shmem_undo_range() will have done some of the + * unaccounting, now delete_from_swap_cache() will do + * the rest (including mem_cgroup_uncharge_swapcache). + * Reset swap.val? No, leave it so "failed" goes back to + * "repeat": reading a hole and writing should succeed. + */ + if (error) + delete_from_swap_cache(page); } + if (error) + goto failed; + + spin_lock(&info->lock); + info->swapped--; + shmem_recalc_inode(inode); spin_unlock(&info->lock); + + if (sgp == SGP_WRITE) + mark_page_accessed(page); + + delete_from_swap_cache(page); + set_page_dirty(page); + swap_free(swap); + } else { - shmem_swp_unmap(entry); - sbinfo = SHMEM_SB(inode->i_sb); + if (shmem_acct_block(info->flags)) { + error = -ENOSPC; + goto failed; + } if (sbinfo->max_blocks) { - spin_lock(&sbinfo->stat_lock); - if (sbinfo->free_blocks == 0 || - shmem_acct_block(info->flags)) { - spin_unlock(&sbinfo->stat_lock); - spin_unlock(&info->lock); + if (percpu_counter_compare(&sbinfo->used_blocks, + sbinfo->max_blocks) >= 0) { error = -ENOSPC; - goto failed; + goto unacct; } - sbinfo->free_blocks--; - inode->i_blocks += BLOCKS_PER_PAGE; - spin_unlock(&sbinfo->stat_lock); - } else if (shmem_acct_block(info->flags)) { - spin_unlock(&info->lock); - error = -ENOSPC; - goto failed; + percpu_counter_inc(&sbinfo->used_blocks); } - if (!filepage) { - spin_unlock(&info->lock); - filepage = shmem_alloc_page(mapping_gfp_mask(mapping), - info, - idx); - if (!filepage) { - shmem_unacct_blocks(info->flags, 1); - shmem_free_blocks(inode, 1); - error = -ENOMEM; - goto failed; - } + page = shmem_alloc_page(gfp, info, index); + if (!page) { + error = -ENOMEM; + goto decused; + } - spin_lock(&info->lock); - entry = shmem_swp_alloc(info, idx, sgp); - if (IS_ERR(entry)) - error = PTR_ERR(entry); - else { - swap = *entry; - shmem_swp_unmap(entry); - } - if (error || swap.val || 0 != add_to_page_cache_lru( - filepage, mapping, idx, GFP_ATOMIC)) { - spin_unlock(&info->lock); - page_cache_release(filepage); - shmem_unacct_blocks(info->flags, 1); - shmem_free_blocks(inode, 1); - filepage = NULL; - if (error) - goto failed; - goto repeat; - } - info->flags |= SHMEM_PAGEIN; + __SetPageSwapBacked(page); + __set_page_locked(page); + if (sgp == SGP_WRITE) + init_page_accessed(page); + + error = mem_cgroup_charge_file(page, current->mm, + gfp & GFP_RECLAIM_MASK); + if (error) + goto decused; + error = radix_tree_maybe_preload(gfp & GFP_RECLAIM_MASK); + if (!error) { + error = shmem_add_to_page_cache(page, mapping, index, + gfp, NULL); + radix_tree_preload_end(); + } + if (error) { + mem_cgroup_uncharge_cache_page(page); + goto decused; } + lru_cache_add_anon(page); + spin_lock(&info->lock); info->alloced++; + inode->i_blocks += BLOCKS_PER_PAGE; + shmem_recalc_inode(inode); spin_unlock(&info->lock); - flush_dcache_page(filepage); - SetPageUptodate(filepage); + alloced = true; + + /* + * Let SGP_FALLOC use the SGP_WRITE optimization on a new page. + */ + if (sgp == SGP_FALLOC) + sgp = SGP_WRITE; +clear: + /* + * Let SGP_WRITE caller clear ends if write does not fill page; + * but SGP_FALLOC on a page fallocated earlier must initialize + * it now, lest undo on failure cancel our earlier guarantee. + */ + if (sgp != SGP_WRITE) { + clear_highpage(page); + flush_dcache_page(page); + SetPageUptodate(page); + } + if (sgp == SGP_DIRTY) + set_page_dirty(page); } -done: - if (*pagep != filepage) { - unlock_page(filepage); - *pagep = filepage; + + /* Perhaps the file has been truncated since we checked */ + if (sgp != SGP_WRITE && sgp != SGP_FALLOC && + ((loff_t)index << PAGE_CACHE_SHIFT) >= i_size_read(inode)) { + error = -EINVAL; + if (alloced) + goto trunc; + else + goto failed; } + *pagep = page; return 0; + /* + * Error recovery. + */ +trunc: + info = SHMEM_I(inode); + ClearPageDirty(page); + delete_from_page_cache(page); + spin_lock(&info->lock); + info->alloced--; + inode->i_blocks -= BLOCKS_PER_PAGE; + spin_unlock(&info->lock); +decused: + sbinfo = SHMEM_SB(inode->i_sb); + if (sbinfo->max_blocks) + percpu_counter_add(&sbinfo->used_blocks, -1); +unacct: + shmem_unacct_blocks(info->flags, 1); failed: - if (*pagep != filepage) { - unlock_page(filepage); - page_cache_release(filepage); + if (swap.val && error != -EINVAL && + !shmem_confirm_swap(mapping, index, swap)) + error = -EEXIST; +unlock: + if (page) { + unlock_page(page); + page_cache_release(page); } + if (error == -ENOSPC && !once++) { + info = SHMEM_I(inode); + spin_lock(&info->lock); + shmem_recalc_inode(inode); + spin_unlock(&info->lock); + goto repeat; + } + if (error == -EEXIST) /* from above or from radix_tree_insert */ + goto repeat; return error; } -struct page *shmem_nopage(struct vm_area_struct *vma, unsigned long address, int *type) +static int shmem_fault(struct vm_area_struct *vma, struct vm_fault *vmf) { - struct inode *inode = vma->vm_file->f_dentry->d_inode; - struct page *page = NULL; - unsigned long idx; + struct inode *inode = file_inode(vma->vm_file); int error; + int ret = VM_FAULT_LOCKED; - idx = (address - vma->vm_start) >> PAGE_SHIFT; - idx += vma->vm_pgoff; - idx >>= PAGE_CACHE_SHIFT - PAGE_SHIFT; - if (((loff_t) idx << PAGE_CACHE_SHIFT) >= i_size_read(inode)) - return NOPAGE_SIGBUS; - - error = shmem_getpage(inode, idx, &page, SGP_CACHE, type); - if (error) - return (error == -ENOMEM)? NOPAGE_OOM: NOPAGE_SIGBUS; - - mark_page_accessed(page); - return page; -} - -static int shmem_populate(struct vm_area_struct *vma, - unsigned long addr, unsigned long len, - pgprot_t prot, unsigned long pgoff, int nonblock) -{ - struct inode *inode = vma->vm_file->f_dentry->d_inode; - struct mm_struct *mm = vma->vm_mm; - enum sgp_type sgp = nonblock? SGP_QUICK: SGP_CACHE; - unsigned long size; + /* + * Trinity finds that probing a hole which tmpfs is punching can + * prevent the hole-punch from ever completing: which in turn + * locks writers out with its hold on i_mutex. So refrain from + * faulting pages into the hole while it's being punched. Although + * shmem_undo_range() does remove the additions, it may be unable to + * keep up, as each new page needs its own unmap_mapping_range() call, + * and the i_mmap tree grows ever slower to scan if new vmas are added. + * + * It does not matter if we sometimes reach this check just before the + * hole-punch begins, so that one fault then races with the punch: + * we just need to make racing faults a rare case. + * + * The implementation below would be much simpler if we just used a + * standard mutex or completion: but we cannot take i_mutex in fault, + * and bloating every shmem inode for this unlikely case would be sad. + */ + if (unlikely(inode->i_private)) { + struct shmem_falloc *shmem_falloc; + + spin_lock(&inode->i_lock); + shmem_falloc = inode->i_private; + if (shmem_falloc && + shmem_falloc->waitq && + vmf->pgoff >= shmem_falloc->start && + vmf->pgoff < shmem_falloc->next) { + wait_queue_head_t *shmem_falloc_waitq; + DEFINE_WAIT(shmem_fault_wait); + + ret = VM_FAULT_NOPAGE; + if ((vmf->flags & FAULT_FLAG_ALLOW_RETRY) && + !(vmf->flags & FAULT_FLAG_RETRY_NOWAIT)) { + /* It's polite to up mmap_sem if we can */ + up_read(&vma->vm_mm->mmap_sem); + ret = VM_FAULT_RETRY; + } - size = (i_size_read(inode) + PAGE_SIZE - 1) >> PAGE_SHIFT; - if (pgoff >= size || pgoff + (len >> PAGE_SHIFT) > size) - return -EINVAL; + shmem_falloc_waitq = shmem_falloc->waitq; + prepare_to_wait(shmem_falloc_waitq, &shmem_fault_wait, + TASK_UNINTERRUPTIBLE); + spin_unlock(&inode->i_lock); + schedule(); - while ((long) len > 0) { - struct page *page = NULL; - int err; - /* - * Will need changing if PAGE_CACHE_SIZE != PAGE_SIZE - */ - err = shmem_getpage(inode, pgoff, &page, sgp, NULL); - if (err) - return err; - /* Page may still be null, but only if nonblock was set. */ - if (page) { - mark_page_accessed(page); - err = install_page(mm, vma, addr, page, prot); - if (err) { - page_cache_release(page); - return err; - } - } else if (vma->vm_flags & VM_NONLINEAR) { - /* No page was found just because we can't read it in - * now (being here implies nonblock != 0), but the page - * may exist, so set the PTE to fault it in later. */ - err = install_file_pte(mm, vma, addr, pgoff, prot); - if (err) - return err; + /* + * shmem_falloc_waitq points into the shmem_fallocate() + * stack of the hole-punching task: shmem_falloc_waitq + * is usually invalid by the time we reach here, but + * finish_wait() does not dereference it in that case; + * though i_lock needed lest racing with wake_up_all(). + */ + spin_lock(&inode->i_lock); + finish_wait(shmem_falloc_waitq, &shmem_fault_wait); + spin_unlock(&inode->i_lock); + return ret; } + spin_unlock(&inode->i_lock); + } - len -= PAGE_SIZE; - addr += PAGE_SIZE; - pgoff++; + error = shmem_getpage(inode, vmf->pgoff, &vmf->page, SGP_CACHE, &ret); + if (error) + return ((error == -ENOMEM) ? VM_FAULT_OOM : VM_FAULT_SIGBUS); + + if (ret & VM_FAULT_MAJOR) { + count_vm_event(PGMAJFAULT); + mem_cgroup_count_vm_event(vma->vm_mm, PGMAJFAULT); } - return 0; + return ret; } #ifdef CONFIG_NUMA -int shmem_set_policy(struct vm_area_struct *vma, struct mempolicy *new) +static int shmem_set_policy(struct vm_area_struct *vma, struct mempolicy *mpol) { - struct inode *i = vma->vm_file->f_dentry->d_inode; - return mpol_set_shared_policy(&SHMEM_I(i)->policy, vma, new); + struct inode *inode = file_inode(vma->vm_file); + return mpol_set_shared_policy(&SHMEM_I(inode)->policy, vma, mpol); } -struct mempolicy * -shmem_get_policy(struct vm_area_struct *vma, unsigned long addr) +static struct mempolicy *shmem_get_policy(struct vm_area_struct *vma, + unsigned long addr) { - struct inode *i = vma->vm_file->f_dentry->d_inode; - unsigned long idx; + struct inode *inode = file_inode(vma->vm_file); + pgoff_t index; - idx = ((addr - vma->vm_start) >> PAGE_SHIFT) + vma->vm_pgoff; - return mpol_shared_policy_lookup(&SHMEM_I(i)->policy, idx); + index = ((addr - vma->vm_start) >> PAGE_SHIFT) + vma->vm_pgoff; + return mpol_shared_policy_lookup(&SHMEM_I(inode)->policy, index); } #endif int shmem_lock(struct file *file, int lock, struct user_struct *user) { - struct inode *inode = file->f_dentry->d_inode; + struct inode *inode = file_inode(file); struct shmem_inode_info *info = SHMEM_I(inode); int retval = -ENOMEM; @@ -1244,12 +1348,15 @@ int shmem_lock(struct file *file, int lock, struct user_struct *user) if (!user_shm_lock(inode->i_size, user)) goto out_nomem; info->flags |= VM_LOCKED; + mapping_set_unevictable(file->f_mapping); } if (!lock && (info->flags & VM_LOCKED) && user) { user_shm_unlock(inode->i_size, user); info->flags &= ~VM_LOCKED; + mapping_clear_unevictable(file->f_mapping); } retval = 0; + out_nomem: spin_unlock(&info->lock); return retval; @@ -1262,49 +1369,46 @@ static int shmem_mmap(struct file *file, struct vm_area_struct *vma) return 0; } -static struct inode * -shmem_get_inode(struct super_block *sb, int mode, dev_t dev) +static struct inode *shmem_get_inode(struct super_block *sb, const struct inode *dir, + umode_t mode, dev_t dev, unsigned long flags) { struct inode *inode; struct shmem_inode_info *info; struct shmem_sb_info *sbinfo = SHMEM_SB(sb); - if (sbinfo->max_inodes) { - spin_lock(&sbinfo->stat_lock); - if (!sbinfo->free_inodes) { - spin_unlock(&sbinfo->stat_lock); - return NULL; - } - sbinfo->free_inodes--; - spin_unlock(&sbinfo->stat_lock); - } + if (shmem_reserve_inode(sb)) + return NULL; inode = new_inode(sb); if (inode) { - inode->i_mode = mode; - inode->i_uid = current->fsuid; - inode->i_gid = current->fsgid; - inode->i_blksize = PAGE_CACHE_SIZE; + inode->i_ino = get_next_ino(); + inode_init_owner(inode, dir, mode); inode->i_blocks = 0; - inode->i_mapping->a_ops = &shmem_aops; inode->i_mapping->backing_dev_info = &shmem_backing_dev_info; inode->i_atime = inode->i_mtime = inode->i_ctime = CURRENT_TIME; + inode->i_generation = get_seconds(); info = SHMEM_I(inode); memset(info, 0, (char *)inode - (char *)info); spin_lock_init(&info->lock); + info->flags = flags & VM_NORESERVE; INIT_LIST_HEAD(&info->swaplist); + simple_xattrs_init(&info->xattrs); + cache_no_acl(inode); switch (mode & S_IFMT) { default: + inode->i_op = &shmem_special_inode_operations; init_special_inode(inode, mode, dev); break; case S_IFREG: + inode->i_mapping->a_ops = &shmem_aops; inode->i_op = &shmem_inode_operations; inode->i_fop = &shmem_file_operations; - mpol_shared_policy_init(&info->policy); + mpol_shared_policy_init(&info->policy, + shmem_get_sbmpol(sbinfo)); break; case S_IFDIR: - inode->i_nlink++; + inc_nlink(inode); /* Some things misbehave if size == 0 on a directory */ inode->i_size = 2 * BOGO_DIRENT_SIZE; inode->i_op = &shmem_dir_inode_operations; @@ -1315,147 +1419,91 @@ shmem_get_inode(struct super_block *sb, int mode, dev_t dev) * Must not load anything in the rbtree, * mpol_free_shared_policy will not be called. */ - mpol_shared_policy_init(&info->policy); + mpol_shared_policy_init(&info->policy, NULL); break; } - } else if (sbinfo->max_inodes) { - spin_lock(&sbinfo->stat_lock); - sbinfo->free_inodes++; - spin_unlock(&sbinfo->stat_lock); - } + } else + shmem_free_inode(sb); return inode; } +bool shmem_mapping(struct address_space *mapping) +{ + return mapping->backing_dev_info == &shmem_backing_dev_info; +} + #ifdef CONFIG_TMPFS -static struct inode_operations shmem_symlink_inode_operations; -static struct inode_operations shmem_symlink_inline_operations; +static const struct inode_operations shmem_symlink_inode_operations; +static const struct inode_operations shmem_short_symlink_operations; + +#ifdef CONFIG_TMPFS_XATTR +static int shmem_initxattrs(struct inode *, const struct xattr *, void *); +#else +#define shmem_initxattrs NULL +#endif -/* - * Normally tmpfs makes no use of shmem_prepare_write, but it - * lets a tmpfs file be used read-write below the loop driver. - */ static int -shmem_prepare_write(struct file *file, struct page *page, unsigned offset, unsigned to) +shmem_write_begin(struct file *file, struct address_space *mapping, + loff_t pos, unsigned len, unsigned flags, + struct page **pagep, void **fsdata) { - struct inode *inode = page->mapping->host; - return shmem_getpage(inode, page->index, &page, SGP_WRITE, NULL); + struct inode *inode = mapping->host; + pgoff_t index = pos >> PAGE_CACHE_SHIFT; + return shmem_getpage(inode, index, pagep, SGP_WRITE, NULL); } -static ssize_t -shmem_file_write(struct file *file, const char __user *buf, size_t count, loff_t *ppos) +static int +shmem_write_end(struct file *file, struct address_space *mapping, + loff_t pos, unsigned len, unsigned copied, + struct page *page, void *fsdata) { - struct inode *inode = file->f_dentry->d_inode; - loff_t pos; - unsigned long written; - ssize_t err; - - if ((ssize_t) count < 0) - return -EINVAL; - - if (!access_ok(VERIFY_READ, buf, count)) - return -EFAULT; - - down(&inode->i_sem); - - pos = *ppos; - written = 0; - - err = generic_write_checks(file, &pos, &count, 0); - if (err || !count) - goto out; - - err = remove_suid(file->f_dentry); - if (err) - goto out; - - inode->i_ctime = inode->i_mtime = CURRENT_TIME; - - do { - struct page *page = NULL; - unsigned long bytes, index, offset; - char *kaddr; - int left; - - offset = (pos & (PAGE_CACHE_SIZE -1)); /* Within page */ - index = pos >> PAGE_CACHE_SHIFT; - bytes = PAGE_CACHE_SIZE - offset; - if (bytes > count) - bytes = count; - - /* - * We don't hold page lock across copy from user - - * what would it guard against? - so no deadlock here. - * But it still may be a good idea to prefault below. - */ - - err = shmem_getpage(inode, index, &page, SGP_WRITE, NULL); - if (err) - break; + struct inode *inode = mapping->host; - left = bytes; - if (PageHighMem(page)) { - volatile unsigned char dummy; - __get_user(dummy, buf); - __get_user(dummy, buf + bytes - 1); + if (pos + copied > inode->i_size) + i_size_write(inode, pos + copied); - kaddr = kmap_atomic(page, KM_USER0); - left = __copy_from_user_inatomic(kaddr + offset, - buf, bytes); - kunmap_atomic(kaddr, KM_USER0); + if (!PageUptodate(page)) { + if (copied < PAGE_CACHE_SIZE) { + unsigned from = pos & (PAGE_CACHE_SIZE - 1); + zero_user_segments(page, 0, from, + from + copied, PAGE_CACHE_SIZE); } - if (left) { - kaddr = kmap(page); - left = __copy_from_user(kaddr + offset, buf, bytes); - kunmap(page); - } - - written += bytes; - count -= bytes; - pos += bytes; - buf += bytes; - if (pos > inode->i_size) - i_size_write(inode, pos); - - flush_dcache_page(page); - set_page_dirty(page); - mark_page_accessed(page); - page_cache_release(page); - - if (left) { - pos -= left; - written -= left; - err = -EFAULT; - break; - } - - /* - * Our dirty pages are not counted in nr_dirty, - * and we do not attempt to balance dirty pages. - */ - - cond_resched(); - } while (count); + SetPageUptodate(page); + } + set_page_dirty(page); + unlock_page(page); + page_cache_release(page); - *ppos = pos; - if (written) - err = written; -out: - up(&inode->i_sem); - return err; + return copied; } -static void do_shmem_file_read(struct file *filp, loff_t *ppos, read_descriptor_t *desc, read_actor_t actor) +static ssize_t shmem_file_read_iter(struct kiocb *iocb, struct iov_iter *to) { - struct inode *inode = filp->f_dentry->d_inode; + struct file *file = iocb->ki_filp; + struct inode *inode = file_inode(file); struct address_space *mapping = inode->i_mapping; - unsigned long index, offset; + pgoff_t index; + unsigned long offset; + enum sgp_type sgp = SGP_READ; + int error = 0; + ssize_t retval = 0; + loff_t *ppos = &iocb->ki_pos; + + /* + * Might this read be for a stacking filesystem? Then when reading + * holes of a sparse file, we actually need to allocate those pages, + * and even mark them dirty, so it cannot exceed the max_blocks limit. + */ + if (segment_eq(get_fs(), KERNEL_DS)) + sgp = SGP_DIRTY; index = *ppos >> PAGE_CACHE_SHIFT; offset = *ppos & ~PAGE_CACHE_MASK; for (;;) { struct page *page = NULL; - unsigned long end_index, nr, ret; + pgoff_t end_index; + unsigned long nr, ret; loff_t i_size = i_size_read(inode); end_index = i_size >> PAGE_CACHE_SHIFT; @@ -1467,16 +1515,18 @@ static void do_shmem_file_read(struct file *filp, loff_t *ppos, read_descriptor_ break; } - desc->error = shmem_getpage(inode, index, &page, SGP_READ, NULL); - if (desc->error) { - if (desc->error == -EINVAL) - desc->error = 0; + error = shmem_getpage(inode, index, &page, sgp, NULL); + if (error) { + if (error == -EINVAL) + error = 0; break; } + if (page) + unlock_page(page); /* * We must evaluate after, since reads (unlike writes) - * are called without i_sem protection against truncate + * are called without i_mutex protection against truncate */ nr = PAGE_CACHE_SIZE; i_size = i_size_read(inode); @@ -1512,88 +1562,366 @@ static void do_shmem_file_read(struct file *filp, loff_t *ppos, read_descriptor_ /* * Ok, we have the page, and it's up-to-date, so * now we can copy it to user space... - * - * The actor routine returns how many bytes were actually used.. - * NOTE! This may not be the same as how much of a user buffer - * we filled up (we may be padding etc), so we can only update - * "pos" here (the actor routine has to update the user buffer - * pointers and the remaining count). */ - ret = actor(desc, page, offset, nr); + ret = copy_page_to_iter(page, offset, nr, to); + retval += ret; offset += ret; index += offset >> PAGE_CACHE_SHIFT; offset &= ~PAGE_CACHE_MASK; page_cache_release(page); - if (ret != nr || !desc->count) + if (!iov_iter_count(to)) break; - + if (ret < nr) { + error = -EFAULT; + break; + } cond_resched(); } *ppos = ((loff_t) index << PAGE_CACHE_SHIFT) + offset; - file_accessed(filp); + file_accessed(file); + return retval ? retval : error; } -static ssize_t shmem_file_read(struct file *filp, char __user *buf, size_t count, loff_t *ppos) +static ssize_t shmem_file_splice_read(struct file *in, loff_t *ppos, + struct pipe_inode_info *pipe, size_t len, + unsigned int flags) { - read_descriptor_t desc; - - if ((ssize_t) count < 0) - return -EINVAL; - if (!access_ok(VERIFY_WRITE, buf, count)) - return -EFAULT; - if (!count) + struct address_space *mapping = in->f_mapping; + struct inode *inode = mapping->host; + unsigned int loff, nr_pages, req_pages; + struct page *pages[PIPE_DEF_BUFFERS]; + struct partial_page partial[PIPE_DEF_BUFFERS]; + struct page *page; + pgoff_t index, end_index; + loff_t isize, left; + int error, page_nr; + struct splice_pipe_desc spd = { + .pages = pages, + .partial = partial, + .nr_pages_max = PIPE_DEF_BUFFERS, + .flags = flags, + .ops = &page_cache_pipe_buf_ops, + .spd_release = spd_release_page, + }; + + isize = i_size_read(inode); + if (unlikely(*ppos >= isize)) return 0; - desc.written = 0; - desc.count = count; - desc.arg.buf = buf; - desc.error = 0; + left = isize - *ppos; + if (unlikely(left < len)) + len = left; + + if (splice_grow_spd(pipe, &spd)) + return -ENOMEM; + + index = *ppos >> PAGE_CACHE_SHIFT; + loff = *ppos & ~PAGE_CACHE_MASK; + req_pages = (len + loff + PAGE_CACHE_SIZE - 1) >> PAGE_CACHE_SHIFT; + nr_pages = min(req_pages, spd.nr_pages_max); + + spd.nr_pages = find_get_pages_contig(mapping, index, + nr_pages, spd.pages); + index += spd.nr_pages; + error = 0; + + while (spd.nr_pages < nr_pages) { + error = shmem_getpage(inode, index, &page, SGP_CACHE, NULL); + if (error) + break; + unlock_page(page); + spd.pages[spd.nr_pages++] = page; + index++; + } + + index = *ppos >> PAGE_CACHE_SHIFT; + nr_pages = spd.nr_pages; + spd.nr_pages = 0; + + for (page_nr = 0; page_nr < nr_pages; page_nr++) { + unsigned int this_len; + + if (!len) + break; + + this_len = min_t(unsigned long, len, PAGE_CACHE_SIZE - loff); + page = spd.pages[page_nr]; + + if (!PageUptodate(page) || page->mapping != mapping) { + error = shmem_getpage(inode, index, &page, + SGP_CACHE, NULL); + if (error) + break; + unlock_page(page); + page_cache_release(spd.pages[page_nr]); + spd.pages[page_nr] = page; + } + + isize = i_size_read(inode); + end_index = (isize - 1) >> PAGE_CACHE_SHIFT; + if (unlikely(!isize || index > end_index)) + break; + + if (end_index == index) { + unsigned int plen; - do_shmem_file_read(filp, ppos, &desc, file_read_actor); - if (desc.written) - return desc.written; - return desc.error; + plen = ((isize - 1) & ~PAGE_CACHE_MASK) + 1; + if (plen <= loff) + break; + + this_len = min(this_len, plen - loff); + len = this_len; + } + + spd.partial[page_nr].offset = loff; + spd.partial[page_nr].len = this_len; + len -= this_len; + loff = 0; + spd.nr_pages++; + index++; + } + + while (page_nr < nr_pages) + page_cache_release(spd.pages[page_nr++]); + + if (spd.nr_pages) + error = splice_to_pipe(pipe, &spd); + + splice_shrink_spd(&spd); + + if (error > 0) { + *ppos += error; + file_accessed(in); + } + return error; } -static ssize_t shmem_file_sendfile(struct file *in_file, loff_t *ppos, - size_t count, read_actor_t actor, void *target) +/* + * llseek SEEK_DATA or SEEK_HOLE through the radix_tree. + */ +static pgoff_t shmem_seek_hole_data(struct address_space *mapping, + pgoff_t index, pgoff_t end, int whence) { - read_descriptor_t desc; + struct page *page; + struct pagevec pvec; + pgoff_t indices[PAGEVEC_SIZE]; + bool done = false; + int i; + + pagevec_init(&pvec, 0); + pvec.nr = 1; /* start small: we may be there already */ + while (!done) { + pvec.nr = find_get_entries(mapping, index, + pvec.nr, pvec.pages, indices); + if (!pvec.nr) { + if (whence == SEEK_DATA) + index = end; + break; + } + for (i = 0; i < pvec.nr; i++, index++) { + if (index < indices[i]) { + if (whence == SEEK_HOLE) { + done = true; + break; + } + index = indices[i]; + } + page = pvec.pages[i]; + if (page && !radix_tree_exceptional_entry(page)) { + if (!PageUptodate(page)) + page = NULL; + } + if (index >= end || + (page && whence == SEEK_DATA) || + (!page && whence == SEEK_HOLE)) { + done = true; + break; + } + } + pagevec_remove_exceptionals(&pvec); + pagevec_release(&pvec); + pvec.nr = PAGEVEC_SIZE; + cond_resched(); + } + return index; +} + +static loff_t shmem_file_llseek(struct file *file, loff_t offset, int whence) +{ + struct address_space *mapping = file->f_mapping; + struct inode *inode = mapping->host; + pgoff_t start, end; + loff_t new_offset; + + if (whence != SEEK_DATA && whence != SEEK_HOLE) + return generic_file_llseek_size(file, offset, whence, + MAX_LFS_FILESIZE, i_size_read(inode)); + mutex_lock(&inode->i_mutex); + /* We're holding i_mutex so we can access i_size directly */ + + if (offset < 0) + offset = -EINVAL; + else if (offset >= inode->i_size) + offset = -ENXIO; + else { + start = offset >> PAGE_CACHE_SHIFT; + end = (inode->i_size + PAGE_CACHE_SIZE - 1) >> PAGE_CACHE_SHIFT; + new_offset = shmem_seek_hole_data(mapping, start, end, whence); + new_offset <<= PAGE_CACHE_SHIFT; + if (new_offset > offset) { + if (new_offset < inode->i_size) + offset = new_offset; + else if (whence == SEEK_DATA) + offset = -ENXIO; + else + offset = inode->i_size; + } + } - if (!count) - return 0; + if (offset >= 0) + offset = vfs_setpos(file, offset, MAX_LFS_FILESIZE); + mutex_unlock(&inode->i_mutex); + return offset; +} - desc.written = 0; - desc.count = count; - desc.arg.data = target; - desc.error = 0; +static long shmem_fallocate(struct file *file, int mode, loff_t offset, + loff_t len) +{ + struct inode *inode = file_inode(file); + struct shmem_sb_info *sbinfo = SHMEM_SB(inode->i_sb); + struct shmem_falloc shmem_falloc; + pgoff_t start, index, end; + int error; - do_shmem_file_read(in_file, ppos, &desc, actor); - if (desc.written) - return desc.written; - return desc.error; + if (mode & ~(FALLOC_FL_KEEP_SIZE | FALLOC_FL_PUNCH_HOLE)) + return -EOPNOTSUPP; + + mutex_lock(&inode->i_mutex); + + if (mode & FALLOC_FL_PUNCH_HOLE) { + struct address_space *mapping = file->f_mapping; + loff_t unmap_start = round_up(offset, PAGE_SIZE); + loff_t unmap_end = round_down(offset + len, PAGE_SIZE) - 1; + DECLARE_WAIT_QUEUE_HEAD_ONSTACK(shmem_falloc_waitq); + + shmem_falloc.waitq = &shmem_falloc_waitq; + shmem_falloc.start = unmap_start >> PAGE_SHIFT; + shmem_falloc.next = (unmap_end + 1) >> PAGE_SHIFT; + spin_lock(&inode->i_lock); + inode->i_private = &shmem_falloc; + spin_unlock(&inode->i_lock); + + if ((u64)unmap_end > (u64)unmap_start) + unmap_mapping_range(mapping, unmap_start, + 1 + unmap_end - unmap_start, 0); + shmem_truncate_range(inode, offset, offset + len - 1); + /* No need to unmap again: hole-punching leaves COWed pages */ + + spin_lock(&inode->i_lock); + inode->i_private = NULL; + wake_up_all(&shmem_falloc_waitq); + spin_unlock(&inode->i_lock); + error = 0; + goto out; + } + + /* We need to check rlimit even when FALLOC_FL_KEEP_SIZE */ + error = inode_newsize_ok(inode, offset + len); + if (error) + goto out; + + start = offset >> PAGE_CACHE_SHIFT; + end = (offset + len + PAGE_CACHE_SIZE - 1) >> PAGE_CACHE_SHIFT; + /* Try to avoid a swapstorm if len is impossible to satisfy */ + if (sbinfo->max_blocks && end - start > sbinfo->max_blocks) { + error = -ENOSPC; + goto out; + } + + shmem_falloc.waitq = NULL; + shmem_falloc.start = start; + shmem_falloc.next = start; + shmem_falloc.nr_falloced = 0; + shmem_falloc.nr_unswapped = 0; + spin_lock(&inode->i_lock); + inode->i_private = &shmem_falloc; + spin_unlock(&inode->i_lock); + + for (index = start; index < end; index++) { + struct page *page; + + /* + * Good, the fallocate(2) manpage permits EINTR: we may have + * been interrupted because we are using up too much memory. + */ + if (signal_pending(current)) + error = -EINTR; + else if (shmem_falloc.nr_unswapped > shmem_falloc.nr_falloced) + error = -ENOMEM; + else + error = shmem_getpage(inode, index, &page, SGP_FALLOC, + NULL); + if (error) { + /* Remove the !PageUptodate pages we added */ + shmem_undo_range(inode, + (loff_t)start << PAGE_CACHE_SHIFT, + (loff_t)index << PAGE_CACHE_SHIFT, true); + goto undone; + } + + /* + * Inform shmem_writepage() how far we have reached. + * No need for lock or barrier: we have the page lock. + */ + shmem_falloc.next++; + if (!PageUptodate(page)) + shmem_falloc.nr_falloced++; + + /* + * If !PageUptodate, leave it that way so that freeable pages + * can be recognized if we need to rollback on error later. + * But set_page_dirty so that memory pressure will swap rather + * than free the pages we are allocating (and SGP_CACHE pages + * might still be clean: we now need to mark those dirty too). + */ + set_page_dirty(page); + unlock_page(page); + page_cache_release(page); + cond_resched(); + } + + if (!(mode & FALLOC_FL_KEEP_SIZE) && offset + len > inode->i_size) + i_size_write(inode, offset + len); + inode->i_ctime = CURRENT_TIME; +undone: + spin_lock(&inode->i_lock); + inode->i_private = NULL; + spin_unlock(&inode->i_lock); +out: + mutex_unlock(&inode->i_mutex); + return error; } -static int shmem_statfs(struct super_block *sb, struct kstatfs *buf) +static int shmem_statfs(struct dentry *dentry, struct kstatfs *buf) { - struct shmem_sb_info *sbinfo = SHMEM_SB(sb); + struct shmem_sb_info *sbinfo = SHMEM_SB(dentry->d_sb); buf->f_type = TMPFS_MAGIC; buf->f_bsize = PAGE_CACHE_SIZE; buf->f_namelen = NAME_MAX; - spin_lock(&sbinfo->stat_lock); if (sbinfo->max_blocks) { buf->f_blocks = sbinfo->max_blocks; - buf->f_bavail = buf->f_bfree = sbinfo->free_blocks; + buf->f_bavail = + buf->f_bfree = sbinfo->max_blocks - + percpu_counter_sum(&sbinfo->used_blocks); } if (sbinfo->max_inodes) { buf->f_files = sbinfo->max_inodes; buf->f_ffree = sbinfo->free_inodes; } /* else leave those fields 0 like simple_statfs */ - spin_unlock(&sbinfo->stat_lock); return 0; } @@ -1601,46 +1929,70 @@ static int shmem_statfs(struct super_block *sb, struct kstatfs *buf) * File creation. Allocate an inode, and we're done.. */ static int -shmem_mknod(struct inode *dir, struct dentry *dentry, int mode, dev_t dev) +shmem_mknod(struct inode *dir, struct dentry *dentry, umode_t mode, dev_t dev) { - struct inode *inode = shmem_get_inode(dir->i_sb, mode, dev); + struct inode *inode; int error = -ENOSPC; + inode = shmem_get_inode(dir->i_sb, dir, mode, dev, VM_NORESERVE); if (inode) { - error = security_inode_init_security(inode, dir, NULL, NULL, - NULL); - if (error) { - if (error != -EOPNOTSUPP) { - iput(inode); - return error; - } - error = 0; - } - if (dir->i_mode & S_ISGID) { - inode->i_gid = dir->i_gid; - if (S_ISDIR(mode)) - inode->i_mode |= S_ISGID; - } + error = simple_acl_create(dir, inode); + if (error) + goto out_iput; + error = security_inode_init_security(inode, dir, + &dentry->d_name, + shmem_initxattrs, NULL); + if (error && error != -EOPNOTSUPP) + goto out_iput; + + error = 0; dir->i_size += BOGO_DIRENT_SIZE; dir->i_ctime = dir->i_mtime = CURRENT_TIME; d_instantiate(dentry, inode); dget(dentry); /* Extra count - pin the dentry in core */ } return error; +out_iput: + iput(inode); + return error; +} + +static int +shmem_tmpfile(struct inode *dir, struct dentry *dentry, umode_t mode) +{ + struct inode *inode; + int error = -ENOSPC; + + inode = shmem_get_inode(dir->i_sb, dir, mode, 0, VM_NORESERVE); + if (inode) { + error = security_inode_init_security(inode, dir, + NULL, + shmem_initxattrs, NULL); + if (error && error != -EOPNOTSUPP) + goto out_iput; + error = simple_acl_create(dir, inode); + if (error) + goto out_iput; + d_tmpfile(dentry, inode); + } + return error; +out_iput: + iput(inode); + return error; } -static int shmem_mkdir(struct inode *dir, struct dentry *dentry, int mode) +static int shmem_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode) { int error; if ((error = shmem_mknod(dir, dentry, mode | S_IFDIR, 0))) return error; - dir->i_nlink++; + inc_nlink(dir); return 0; } -static int shmem_create(struct inode *dir, struct dentry *dentry, int mode, - struct nameidata *nd) +static int shmem_create(struct inode *dir, struct dentry *dentry, umode_t mode, + bool excl) { return shmem_mknod(dir, dentry, mode | S_IFREG, 0); } @@ -1651,48 +2003,37 @@ static int shmem_create(struct inode *dir, struct dentry *dentry, int mode, static int shmem_link(struct dentry *old_dentry, struct inode *dir, struct dentry *dentry) { struct inode *inode = old_dentry->d_inode; - struct shmem_sb_info *sbinfo = SHMEM_SB(inode->i_sb); + int ret; /* * No ordinary (disk based) filesystem counts links as inodes; * but each new link needs a new dentry, pinning lowmem, and * tmpfs dentries cannot be pruned until they are unlinked. */ - if (sbinfo->max_inodes) { - spin_lock(&sbinfo->stat_lock); - if (!sbinfo->free_inodes) { - spin_unlock(&sbinfo->stat_lock); - return -ENOSPC; - } - sbinfo->free_inodes--; - spin_unlock(&sbinfo->stat_lock); - } + ret = shmem_reserve_inode(inode->i_sb); + if (ret) + goto out; dir->i_size += BOGO_DIRENT_SIZE; inode->i_ctime = dir->i_ctime = dir->i_mtime = CURRENT_TIME; - inode->i_nlink++; - atomic_inc(&inode->i_count); /* New dentry reference */ + inc_nlink(inode); + ihold(inode); /* New dentry reference */ dget(dentry); /* Extra pinning count for the created dentry */ d_instantiate(dentry, inode); - return 0; +out: + return ret; } static int shmem_unlink(struct inode *dir, struct dentry *dentry) { struct inode *inode = dentry->d_inode; - if (inode->i_nlink > 1 && !S_ISDIR(inode->i_mode)) { - struct shmem_sb_info *sbinfo = SHMEM_SB(inode->i_sb); - if (sbinfo->max_inodes) { - spin_lock(&sbinfo->stat_lock); - sbinfo->free_inodes++; - spin_unlock(&sbinfo->stat_lock); - } - } + if (inode->i_nlink > 1 && !S_ISDIR(inode->i_mode)) + shmem_free_inode(inode->i_sb); dir->i_size -= BOGO_DIRENT_SIZE; inode->i_ctime = dir->i_ctime = dir->i_mtime = CURRENT_TIME; - inode->i_nlink--; + drop_nlink(inode); dput(dentry); /* Undo the count from "create" - this does all the work */ return 0; } @@ -1702,7 +2043,8 @@ static int shmem_rmdir(struct inode *dir, struct dentry *dentry) if (!simple_empty(dentry)) return -ENOTEMPTY; - dir->i_nlink--; + drop_nlink(dentry->d_inode); + drop_nlink(dir); return shmem_unlink(dir, dentry); } @@ -1723,10 +2065,10 @@ static int shmem_rename(struct inode *old_dir, struct dentry *old_dentry, struct if (new_dentry->d_inode) { (void) shmem_unlink(new_dir, new_dentry); if (they_are_dirs) - old_dir->i_nlink--; + drop_nlink(old_dir); } else if (they_are_dirs) { - old_dir->i_nlink--; - new_dir->i_nlink++; + drop_nlink(old_dir); + inc_nlink(new_dir); } old_dir->i_size -= BOGO_DIRENT_SIZE; @@ -1742,7 +2084,7 @@ static int shmem_symlink(struct inode *dir, struct dentry *dentry, const char *s int error; int len; struct inode *inode; - struct page *page = NULL; + struct page *page; char *kaddr; struct shmem_inode_info *info; @@ -1750,12 +2092,12 @@ static int shmem_symlink(struct inode *dir, struct dentry *dentry, const char *s if (len > PAGE_CACHE_SIZE) return -ENAMETOOLONG; - inode = shmem_get_inode(dir->i_sb, S_IFLNK|S_IRWXUGO, 0); + inode = shmem_get_inode(dir->i_sb, dir, S_IFLNK|S_IRWXUGO, 0, VM_NORESERVE); if (!inode) return -ENOSPC; - error = security_inode_init_security(inode, dir, NULL, NULL, - NULL); + error = security_inode_init_security(inode, dir, &dentry->d_name, + shmem_initxattrs, NULL); if (error) { if (error != -EOPNOTSUPP) { iput(inode); @@ -1766,25 +2108,29 @@ static int shmem_symlink(struct inode *dir, struct dentry *dentry, const char *s info = SHMEM_I(inode); inode->i_size = len-1; - if (len <= (char *)inode - (char *)info) { - /* do it inline */ - memcpy(info, symname, len); - inode->i_op = &shmem_symlink_inline_operations; + if (len <= SHORT_SYMLINK_LEN) { + info->symlink = kmemdup(symname, len, GFP_KERNEL); + if (!info->symlink) { + iput(inode); + return -ENOMEM; + } + inode->i_op = &shmem_short_symlink_operations; } else { error = shmem_getpage(inode, 0, &page, SGP_WRITE, NULL); if (error) { iput(inode); return error; } + inode->i_mapping->a_ops = &shmem_aops; inode->i_op = &shmem_symlink_inode_operations; - kaddr = kmap_atomic(page, KM_USER0); + kaddr = kmap_atomic(page); memcpy(kaddr, symname, len); - kunmap_atomic(kaddr, KM_USER0); + kunmap_atomic(kaddr); + SetPageUptodate(page); set_page_dirty(page); + unlock_page(page); page_cache_release(page); } - if (dir->i_mode & S_ISGID) - inode->i_gid = dir->i_gid; dir->i_size += BOGO_DIRENT_SIZE; dir->i_ctime = dir->i_mtime = CURRENT_TIME; d_instantiate(dentry, inode); @@ -1792,17 +2138,19 @@ static int shmem_symlink(struct inode *dir, struct dentry *dentry, const char *s return 0; } -static void *shmem_follow_link_inline(struct dentry *dentry, struct nameidata *nd) +static void *shmem_follow_short_symlink(struct dentry *dentry, struct nameidata *nd) { - nd_set_link(nd, (char *)SHMEM_I(dentry->d_inode)); + nd_set_link(nd, SHMEM_I(dentry->d_inode)->symlink); return NULL; } static void *shmem_follow_link(struct dentry *dentry, struct nameidata *nd) { struct page *page = NULL; - int res = shmem_getpage(dentry->d_inode, 0, &page, SGP_READ, NULL); - nd_set_link(nd, res ? ERR_PTR(res) : kmap(page)); + int error = shmem_getpage(dentry->d_inode, 0, &page, SGP_READ, NULL); + nd_set_link(nd, error ? ERR_PTR(error) : kmap(page)); + if (page) + unlock_page(page); return page; } @@ -1816,23 +2164,266 @@ static void shmem_put_link(struct dentry *dentry, struct nameidata *nd, void *co } } -static struct inode_operations shmem_symlink_inline_operations = { +#ifdef CONFIG_TMPFS_XATTR +/* + * Superblocks without xattr inode operations may get some security.* xattr + * support from the LSM "for free". As soon as we have any other xattrs + * like ACLs, we also need to implement the security.* handlers at + * filesystem level, though. + */ + +/* + * Callback for security_inode_init_security() for acquiring xattrs. + */ +static int shmem_initxattrs(struct inode *inode, + const struct xattr *xattr_array, + void *fs_info) +{ + struct shmem_inode_info *info = SHMEM_I(inode); + const struct xattr *xattr; + struct simple_xattr *new_xattr; + size_t len; + + for (xattr = xattr_array; xattr->name != NULL; xattr++) { + new_xattr = simple_xattr_alloc(xattr->value, xattr->value_len); + if (!new_xattr) + return -ENOMEM; + + len = strlen(xattr->name) + 1; + new_xattr->name = kmalloc(XATTR_SECURITY_PREFIX_LEN + len, + GFP_KERNEL); + if (!new_xattr->name) { + kfree(new_xattr); + return -ENOMEM; + } + + memcpy(new_xattr->name, XATTR_SECURITY_PREFIX, + XATTR_SECURITY_PREFIX_LEN); + memcpy(new_xattr->name + XATTR_SECURITY_PREFIX_LEN, + xattr->name, len); + + simple_xattr_list_add(&info->xattrs, new_xattr); + } + + return 0; +} + +static const struct xattr_handler *shmem_xattr_handlers[] = { +#ifdef CONFIG_TMPFS_POSIX_ACL + &posix_acl_access_xattr_handler, + &posix_acl_default_xattr_handler, +#endif + NULL +}; + +static int shmem_xattr_validate(const char *name) +{ + struct { const char *prefix; size_t len; } arr[] = { + { XATTR_SECURITY_PREFIX, XATTR_SECURITY_PREFIX_LEN }, + { XATTR_TRUSTED_PREFIX, XATTR_TRUSTED_PREFIX_LEN } + }; + int i; + + for (i = 0; i < ARRAY_SIZE(arr); i++) { + size_t preflen = arr[i].len; + if (strncmp(name, arr[i].prefix, preflen) == 0) { + if (!name[preflen]) + return -EINVAL; + return 0; + } + } + return -EOPNOTSUPP; +} + +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); + int err; + + /* + * If this is a request for a synthetic attribute in the system.* + * namespace use the generic infrastructure to resolve a handler + * for it via sb->s_xattr. + */ + if (!strncmp(name, XATTR_SYSTEM_PREFIX, XATTR_SYSTEM_PREFIX_LEN)) + return generic_getxattr(dentry, name, buffer, size); + + err = shmem_xattr_validate(name); + if (err) + return err; + + return simple_xattr_get(&info->xattrs, name, buffer, size); +} + +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); + int err; + + /* + * If this is a request for a synthetic attribute in the system.* + * namespace use the generic infrastructure to resolve a handler + * for it via sb->s_xattr. + */ + if (!strncmp(name, XATTR_SYSTEM_PREFIX, XATTR_SYSTEM_PREFIX_LEN)) + return generic_setxattr(dentry, name, value, size, flags); + + err = shmem_xattr_validate(name); + if (err) + return err; + + return simple_xattr_set(&info->xattrs, name, value, size, flags); +} + +static int shmem_removexattr(struct dentry *dentry, const char *name) +{ + struct shmem_inode_info *info = SHMEM_I(dentry->d_inode); + int err; + + /* + * If this is a request for a synthetic attribute in the system.* + * namespace use the generic infrastructure to resolve a handler + * for it via sb->s_xattr. + */ + if (!strncmp(name, XATTR_SYSTEM_PREFIX, XATTR_SYSTEM_PREFIX_LEN)) + return generic_removexattr(dentry, name); + + err = shmem_xattr_validate(name); + if (err) + return err; + + return simple_xattr_remove(&info->xattrs, name); +} + +static ssize_t shmem_listxattr(struct dentry *dentry, char *buffer, size_t size) +{ + struct shmem_inode_info *info = SHMEM_I(dentry->d_inode); + return simple_xattr_list(&info->xattrs, buffer, size); +} +#endif /* CONFIG_TMPFS_XATTR */ + +static const struct inode_operations shmem_short_symlink_operations = { .readlink = generic_readlink, - .follow_link = shmem_follow_link_inline, + .follow_link = shmem_follow_short_symlink, +#ifdef CONFIG_TMPFS_XATTR + .setxattr = shmem_setxattr, + .getxattr = shmem_getxattr, + .listxattr = shmem_listxattr, + .removexattr = shmem_removexattr, +#endif }; -static struct inode_operations shmem_symlink_inode_operations = { - .truncate = shmem_truncate, +static const struct inode_operations shmem_symlink_inode_operations = { .readlink = generic_readlink, .follow_link = shmem_follow_link, .put_link = shmem_put_link, +#ifdef CONFIG_TMPFS_XATTR + .setxattr = shmem_setxattr, + .getxattr = shmem_getxattr, + .listxattr = shmem_listxattr, + .removexattr = shmem_removexattr, +#endif }; -static int shmem_parse_options(char *options, int *mode, uid_t *uid, gid_t *gid, unsigned long *blocks, unsigned long *inodes) +static struct dentry *shmem_get_parent(struct dentry *child) +{ + return ERR_PTR(-ESTALE); +} + +static int shmem_match(struct inode *ino, void *vfh) +{ + __u32 *fh = vfh; + __u64 inum = fh[2]; + inum = (inum << 32) | fh[1]; + return ino->i_ino == inum && fh[0] == ino->i_generation; +} + +static struct dentry *shmem_fh_to_dentry(struct super_block *sb, + struct fid *fid, int fh_len, int fh_type) +{ + struct inode *inode; + struct dentry *dentry = NULL; + u64 inum; + + if (fh_len < 3) + return NULL; + + inum = fid->raw[2]; + inum = (inum << 32) | fid->raw[1]; + + inode = ilookup5(sb, (unsigned long)(inum + fid->raw[0]), + shmem_match, fid->raw); + if (inode) { + dentry = d_find_alias(inode); + iput(inode); + } + + return dentry; +} + +static int shmem_encode_fh(struct inode *inode, __u32 *fh, int *len, + struct inode *parent) +{ + if (*len < 3) { + *len = 3; + return FILEID_INVALID; + } + + if (inode_unhashed(inode)) { + /* Unfortunately insert_inode_hash is not idempotent, + * so as we hash inodes here rather than at creation + * time, we need a lock to ensure we only try + * to do it once + */ + static DEFINE_SPINLOCK(lock); + spin_lock(&lock); + if (inode_unhashed(inode)) + __insert_inode_hash(inode, + inode->i_ino + inode->i_generation); + spin_unlock(&lock); + } + + fh[0] = inode->i_generation; + fh[1] = inode->i_ino; + fh[2] = ((__u64)inode->i_ino) >> 32; + + *len = 3; + return 1; +} + +static const struct export_operations shmem_export_ops = { + .get_parent = shmem_get_parent, + .encode_fh = shmem_encode_fh, + .fh_to_dentry = shmem_fh_to_dentry, +}; + +static int shmem_parse_options(char *options, struct shmem_sb_info *sbinfo, + bool remount) { char *this_char, *value, *rest; + struct mempolicy *mpol = NULL; + uid_t uid; + gid_t gid; - while ((this_char = strsep(&options, ",")) != NULL) { + while (options != NULL) { + this_char = options; + for (;;) { + /* + * NUL-terminate this option: unfortunately, + * mount options form a comma-separated list, + * but mpol's nodelist may also contain commas. + */ + options = strchr(options, ','); + if (options == NULL) + break; + options++; + if (!isdigit(*options)) { + options[-1] = '\0'; + break; + } + } if (!*this_char) continue; if ((value = strchr(this_char,'=')) != NULL) { @@ -1841,7 +2432,7 @@ static int shmem_parse_options(char *options, int *mode, uid_t *uid, gid_t *gid, printk(KERN_ERR "tmpfs: No value for mount option '%s'\n", this_char); - return 1; + goto error; } if (!strcmp(this_char,"size")) { @@ -1855,44 +2446,59 @@ static int shmem_parse_options(char *options, int *mode, uid_t *uid, gid_t *gid, } if (*rest) goto bad_val; - *blocks = size >> PAGE_CACHE_SHIFT; + sbinfo->max_blocks = + DIV_ROUND_UP(size, PAGE_CACHE_SIZE); } else if (!strcmp(this_char,"nr_blocks")) { - *blocks = memparse(value,&rest); + sbinfo->max_blocks = memparse(value, &rest); if (*rest) goto bad_val; } else if (!strcmp(this_char,"nr_inodes")) { - *inodes = memparse(value,&rest); + sbinfo->max_inodes = memparse(value, &rest); if (*rest) goto bad_val; } else if (!strcmp(this_char,"mode")) { - if (!mode) + if (remount) continue; - *mode = simple_strtoul(value,&rest,8); + sbinfo->mode = simple_strtoul(value, &rest, 8) & 07777; if (*rest) goto bad_val; } else if (!strcmp(this_char,"uid")) { - if (!uid) + if (remount) continue; - *uid = simple_strtoul(value,&rest,0); + uid = simple_strtoul(value, &rest, 0); if (*rest) goto bad_val; + sbinfo->uid = make_kuid(current_user_ns(), uid); + if (!uid_valid(sbinfo->uid)) + goto bad_val; } else if (!strcmp(this_char,"gid")) { - if (!gid) + if (remount) continue; - *gid = simple_strtoul(value,&rest,0); + gid = simple_strtoul(value, &rest, 0); if (*rest) goto bad_val; + sbinfo->gid = make_kgid(current_user_ns(), gid); + if (!gid_valid(sbinfo->gid)) + goto bad_val; + } else if (!strcmp(this_char,"mpol")) { + mpol_put(mpol); + mpol = NULL; + if (mpol_parse_str(value, &mpol)) + goto bad_val; } else { printk(KERN_ERR "tmpfs: Bad mount option %s\n", this_char); - return 1; + goto error; } } + sbinfo->mpol = mpol; return 0; bad_val: printk(KERN_ERR "tmpfs: Bad value '%s' for mount option '%s'\n", value, this_char); +error: + mpol_put(mpol); return 1; } @@ -1900,63 +2506,95 @@ bad_val: static int shmem_remount_fs(struct super_block *sb, int *flags, char *data) { struct shmem_sb_info *sbinfo = SHMEM_SB(sb); - unsigned long max_blocks = sbinfo->max_blocks; - unsigned long max_inodes = sbinfo->max_inodes; - unsigned long blocks; + struct shmem_sb_info config = *sbinfo; unsigned long inodes; int error = -EINVAL; - if (shmem_parse_options(data, NULL, NULL, NULL, - &max_blocks, &max_inodes)) + config.mpol = NULL; + if (shmem_parse_options(data, &config, true)) return error; spin_lock(&sbinfo->stat_lock); - blocks = sbinfo->max_blocks - sbinfo->free_blocks; inodes = sbinfo->max_inodes - sbinfo->free_inodes; - if (max_blocks < blocks) + if (percpu_counter_compare(&sbinfo->used_blocks, config.max_blocks) > 0) goto out; - if (max_inodes < inodes) + if (config.max_inodes < inodes) goto out; /* - * Those tests also disallow limited->unlimited while any are in - * use, so i_blocks will always be zero when max_blocks is zero; + * Those tests disallow limited->unlimited while any are in use; * but we must separately disallow unlimited->limited, because * in that case we have no record of how much is already in use. */ - if (max_blocks && !sbinfo->max_blocks) + if (config.max_blocks && !sbinfo->max_blocks) goto out; - if (max_inodes && !sbinfo->max_inodes) + if (config.max_inodes && !sbinfo->max_inodes) goto out; error = 0; - sbinfo->max_blocks = max_blocks; - sbinfo->free_blocks = max_blocks - blocks; - sbinfo->max_inodes = max_inodes; - sbinfo->free_inodes = max_inodes - inodes; + sbinfo->max_blocks = config.max_blocks; + sbinfo->max_inodes = config.max_inodes; + sbinfo->free_inodes = config.max_inodes - inodes; + + /* + * Preserve previous mempolicy unless mpol remount option was specified. + */ + if (config.mpol) { + mpol_put(sbinfo->mpol); + sbinfo->mpol = config.mpol; /* transfers initial ref */ + } out: spin_unlock(&sbinfo->stat_lock); return error; } -#endif + +static int shmem_show_options(struct seq_file *seq, struct dentry *root) +{ + struct shmem_sb_info *sbinfo = SHMEM_SB(root->d_sb); + + if (sbinfo->max_blocks != shmem_default_max_blocks()) + seq_printf(seq, ",size=%luk", + sbinfo->max_blocks << (PAGE_CACHE_SHIFT - 10)); + if (sbinfo->max_inodes != shmem_default_max_inodes()) + seq_printf(seq, ",nr_inodes=%lu", sbinfo->max_inodes); + if (sbinfo->mode != (S_IRWXUGO | S_ISVTX)) + seq_printf(seq, ",mode=%03ho", sbinfo->mode); + if (!uid_eq(sbinfo->uid, GLOBAL_ROOT_UID)) + seq_printf(seq, ",uid=%u", + from_kuid_munged(&init_user_ns, sbinfo->uid)); + if (!gid_eq(sbinfo->gid, GLOBAL_ROOT_GID)) + seq_printf(seq, ",gid=%u", + from_kgid_munged(&init_user_ns, sbinfo->gid)); + shmem_show_mpol(seq, sbinfo->mpol); + return 0; +} +#endif /* CONFIG_TMPFS */ static void shmem_put_super(struct super_block *sb) { - kfree(sb->s_fs_info); + struct shmem_sb_info *sbinfo = SHMEM_SB(sb); + + percpu_counter_destroy(&sbinfo->used_blocks); + mpol_put(sbinfo->mpol); + kfree(sbinfo); sb->s_fs_info = NULL; } -static int shmem_fill_super(struct super_block *sb, - void *data, int silent) +int shmem_fill_super(struct super_block *sb, void *data, int silent) { struct inode *inode; - struct dentry *root; - int mode = S_IRWXUGO | S_ISVTX; - uid_t uid = current->fsuid; - gid_t gid = current->fsgid; - int err = -ENOMEM; struct shmem_sb_info *sbinfo; - unsigned long blocks = 0; - unsigned long inodes = 0; + int err = -ENOMEM; + + /* Round up to L1_CACHE_BYTES to resist false sharing */ + sbinfo = kzalloc(max((int)sizeof(struct shmem_sb_info), + L1_CACHE_BYTES), GFP_KERNEL); + if (!sbinfo) + return -ENOMEM; + + sbinfo->mode = S_IRWXUGO | S_ISVTX; + sbinfo->uid = current_fsuid(); + sbinfo->gid = current_fsgid(); + sb->s_fs_info = sbinfo; #ifdef CONFIG_TMPFS /* @@ -1964,128 +2602,136 @@ static int shmem_fill_super(struct super_block *sb, * tmpfs instance, limiting inodes to one per page of lowmem; * but the internal instance is left unlimited. */ - if (!(sb->s_flags & MS_NOUSER)) { - blocks = totalram_pages / 2; - inodes = totalram_pages - totalhigh_pages; - if (inodes > blocks) - inodes = blocks; - if (shmem_parse_options(data, &mode, &uid, &gid, - &blocks, &inodes)) - return -EINVAL; + if (!(sb->s_flags & MS_KERNMOUNT)) { + sbinfo->max_blocks = shmem_default_max_blocks(); + sbinfo->max_inodes = shmem_default_max_inodes(); + if (shmem_parse_options(data, sbinfo, false)) { + err = -EINVAL; + goto failed; + } + } else { + sb->s_flags |= MS_NOUSER; } + sb->s_export_op = &shmem_export_ops; + sb->s_flags |= MS_NOSEC; #else sb->s_flags |= MS_NOUSER; #endif - /* Round up to L1_CACHE_BYTES to resist false sharing */ - sbinfo = kmalloc(max((int)sizeof(struct shmem_sb_info), - L1_CACHE_BYTES), GFP_KERNEL); - if (!sbinfo) - return -ENOMEM; - spin_lock_init(&sbinfo->stat_lock); - sbinfo->max_blocks = blocks; - sbinfo->free_blocks = blocks; - sbinfo->max_inodes = inodes; - sbinfo->free_inodes = inodes; + if (percpu_counter_init(&sbinfo->used_blocks, 0)) + goto failed; + sbinfo->free_inodes = sbinfo->max_inodes; - sb->s_fs_info = sbinfo; - sb->s_maxbytes = SHMEM_MAX_BYTES; + sb->s_maxbytes = MAX_LFS_FILESIZE; sb->s_blocksize = PAGE_CACHE_SIZE; sb->s_blocksize_bits = PAGE_CACHE_SHIFT; sb->s_magic = TMPFS_MAGIC; sb->s_op = &shmem_ops; + sb->s_time_gran = 1; +#ifdef CONFIG_TMPFS_XATTR + sb->s_xattr = shmem_xattr_handlers; +#endif +#ifdef CONFIG_TMPFS_POSIX_ACL + sb->s_flags |= MS_POSIXACL; +#endif - inode = shmem_get_inode(sb, S_IFDIR | mode, 0); + inode = shmem_get_inode(sb, NULL, S_IFDIR | sbinfo->mode, 0, VM_NORESERVE); if (!inode) goto failed; - inode->i_uid = uid; - inode->i_gid = gid; - root = d_alloc_root(inode); - if (!root) - goto failed_iput; - sb->s_root = root; + inode->i_uid = sbinfo->uid; + inode->i_gid = sbinfo->gid; + sb->s_root = d_make_root(inode); + if (!sb->s_root) + goto failed; return 0; -failed_iput: - iput(inode); failed: shmem_put_super(sb); return err; } -static kmem_cache_t *shmem_inode_cachep; +static struct kmem_cache *shmem_inode_cachep; static struct inode *shmem_alloc_inode(struct super_block *sb) { - struct shmem_inode_info *p; - p = (struct shmem_inode_info *)kmem_cache_alloc(shmem_inode_cachep, SLAB_KERNEL); - if (!p) + struct shmem_inode_info *info; + info = kmem_cache_alloc(shmem_inode_cachep, GFP_KERNEL); + if (!info) return NULL; - return &p->vfs_inode; + return &info->vfs_inode; } -static void shmem_destroy_inode(struct inode *inode) +static void shmem_destroy_callback(struct rcu_head *head) { - if ((inode->i_mode & S_IFMT) == S_IFREG) { - /* only struct inode is valid if it's an inline symlink */ - mpol_free_shared_policy(&SHMEM_I(inode)->policy); - } + struct inode *inode = container_of(head, struct inode, i_rcu); kmem_cache_free(shmem_inode_cachep, SHMEM_I(inode)); } -static void init_once(void *foo, kmem_cache_t *cachep, unsigned long flags) +static void shmem_destroy_inode(struct inode *inode) { - struct shmem_inode_info *p = (struct shmem_inode_info *) foo; + if (S_ISREG(inode->i_mode)) + mpol_free_shared_policy(&SHMEM_I(inode)->policy); + call_rcu(&inode->i_rcu, shmem_destroy_callback); +} - if ((flags & (SLAB_CTOR_VERIFY|SLAB_CTOR_CONSTRUCTOR)) == - SLAB_CTOR_CONSTRUCTOR) { - inode_init_once(&p->vfs_inode); - } +static void shmem_init_inode(void *foo) +{ + struct shmem_inode_info *info = foo; + inode_init_once(&info->vfs_inode); } -static int init_inodecache(void) +static int shmem_init_inodecache(void) { shmem_inode_cachep = kmem_cache_create("shmem_inode_cache", sizeof(struct shmem_inode_info), - 0, 0, init_once, NULL); - if (shmem_inode_cachep == NULL) - return -ENOMEM; + 0, SLAB_PANIC, shmem_init_inode); return 0; } -static void destroy_inodecache(void) +static void shmem_destroy_inodecache(void) { - if (kmem_cache_destroy(shmem_inode_cachep)) - printk(KERN_INFO "shmem_inode_cache: not all structures were freed\n"); + kmem_cache_destroy(shmem_inode_cachep); } -static struct address_space_operations shmem_aops = { +static const struct address_space_operations shmem_aops = { .writepage = shmem_writepage, - .set_page_dirty = __set_page_dirty_nobuffers, + .set_page_dirty = __set_page_dirty_no_writeback, #ifdef CONFIG_TMPFS - .prepare_write = shmem_prepare_write, - .commit_write = simple_commit_write, + .write_begin = shmem_write_begin, + .write_end = shmem_write_end, #endif + .migratepage = migrate_page, + .error_remove_page = generic_error_remove_page, }; -static struct file_operations shmem_file_operations = { +static const struct file_operations shmem_file_operations = { .mmap = shmem_mmap, #ifdef CONFIG_TMPFS - .llseek = generic_file_llseek, - .read = shmem_file_read, - .write = shmem_file_write, - .fsync = simple_sync_file, - .sendfile = shmem_file_sendfile, + .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, + .splice_read = shmem_file_splice_read, + .splice_write = iter_file_splice_write, + .fallocate = shmem_fallocate, #endif }; -static struct inode_operations shmem_inode_operations = { - .truncate = shmem_truncate, - .setattr = shmem_notify_change, +static const struct inode_operations shmem_inode_operations = { + .setattr = shmem_setattr, +#ifdef CONFIG_TMPFS_XATTR + .setxattr = shmem_setxattr, + .getxattr = shmem_getxattr, + .listxattr = shmem_listxattr, + .removexattr = shmem_removexattr, + .set_acl = simple_set_acl, +#endif }; -static struct inode_operations shmem_dir_inode_operations = { +static const struct inode_operations shmem_dir_inode_operations = { #ifdef CONFIG_TMPFS .create = shmem_create, .lookup = simple_lookup, @@ -2096,63 +2742,93 @@ static struct inode_operations shmem_dir_inode_operations = { .rmdir = shmem_rmdir, .mknod = shmem_mknod, .rename = shmem_rename, + .tmpfile = shmem_tmpfile, +#endif +#ifdef CONFIG_TMPFS_XATTR + .setxattr = shmem_setxattr, + .getxattr = shmem_getxattr, + .listxattr = shmem_listxattr, + .removexattr = shmem_removexattr, +#endif +#ifdef CONFIG_TMPFS_POSIX_ACL + .setattr = shmem_setattr, + .set_acl = simple_set_acl, #endif }; -static struct super_operations shmem_ops = { +static const struct inode_operations shmem_special_inode_operations = { +#ifdef CONFIG_TMPFS_XATTR + .setxattr = shmem_setxattr, + .getxattr = shmem_getxattr, + .listxattr = shmem_listxattr, + .removexattr = shmem_removexattr, +#endif +#ifdef CONFIG_TMPFS_POSIX_ACL + .setattr = shmem_setattr, + .set_acl = simple_set_acl, +#endif +}; + +static const struct super_operations shmem_ops = { .alloc_inode = shmem_alloc_inode, .destroy_inode = shmem_destroy_inode, #ifdef CONFIG_TMPFS .statfs = shmem_statfs, .remount_fs = shmem_remount_fs, + .show_options = shmem_show_options, #endif - .delete_inode = shmem_delete_inode, + .evict_inode = shmem_evict_inode, .drop_inode = generic_delete_inode, .put_super = shmem_put_super, }; -static struct vm_operations_struct shmem_vm_ops = { - .nopage = shmem_nopage, - .populate = shmem_populate, +static const struct vm_operations_struct shmem_vm_ops = { + .fault = shmem_fault, + .map_pages = filemap_map_pages, #ifdef CONFIG_NUMA .set_policy = shmem_set_policy, .get_policy = shmem_get_policy, #endif + .remap_pages = generic_file_remap_pages, }; - -static struct super_block *shmem_get_sb(struct file_system_type *fs_type, +static struct dentry *shmem_mount(struct file_system_type *fs_type, int flags, const char *dev_name, void *data) { - return get_sb_nodev(fs_type, flags, data, shmem_fill_super); + return mount_nodev(fs_type, flags, data, shmem_fill_super); } -static struct file_system_type tmpfs_fs_type = { +static struct file_system_type shmem_fs_type = { .owner = THIS_MODULE, .name = "tmpfs", - .get_sb = shmem_get_sb, + .mount = shmem_mount, .kill_sb = kill_litter_super, + .fs_flags = FS_USERNS_MOUNT, }; -static struct vfsmount *shm_mnt; -static int __init init_tmpfs(void) +int __init shmem_init(void) { int error; - error = init_inodecache(); + /* If rootfs called this, don't re-init */ + if (shmem_inode_cachep) + return 0; + + error = bdi_init(&shmem_backing_dev_info); + if (error) + goto out4; + + error = shmem_init_inodecache(); if (error) goto out3; - error = register_filesystem(&tmpfs_fs_type); + error = register_filesystem(&shmem_fs_type); if (error) { printk(KERN_ERR "Could not register tmpfs\n"); goto out2; } -#ifdef CONFIG_TMPFS - devfs_mk_dir("shm"); -#endif - shm_mnt = do_kern_mount(tmpfs_fs_type.name, MS_NOUSER, - tmpfs_fs_type.name, NULL); + + shm_mnt = kern_mount(&shmem_fs_type); if (IS_ERR(shm_mnt)) { error = PTR_ERR(shm_mnt); printk(KERN_ERR "Could not kern_mount tmpfs\n"); @@ -2161,81 +2837,163 @@ static int __init init_tmpfs(void) return 0; out1: - unregister_filesystem(&tmpfs_fs_type); + unregister_filesystem(&shmem_fs_type); out2: - destroy_inodecache(); + shmem_destroy_inodecache(); out3: + bdi_destroy(&shmem_backing_dev_info); +out4: shm_mnt = ERR_PTR(error); return error; } -module_init(init_tmpfs) + +#else /* !CONFIG_SHMEM */ /* - * shmem_file_setup - get an unlinked file living in tmpfs - * - * @name: name for dentry (to be seen in /proc/<pid>/maps - * @size: size to be set for the file + * tiny-shmem: simple shmemfs and tmpfs using ramfs code * + * This is intended for small system where the benefits of the full + * shmem code (swap-backed and resource-limited) are outweighed by + * their complexity. On systems without swap this code should be + * effectively equivalent, but much lighter weight. */ -struct file *shmem_file_setup(char *name, loff_t size, unsigned long flags) + +static struct file_system_type shmem_fs_type = { + .name = "tmpfs", + .mount = ramfs_mount, + .kill_sb = kill_litter_super, + .fs_flags = FS_USERNS_MOUNT, +}; + +int __init shmem_init(void) { - int error; - struct file *file; + BUG_ON(register_filesystem(&shmem_fs_type) != 0); + + shm_mnt = kern_mount(&shmem_fs_type); + BUG_ON(IS_ERR(shm_mnt)); + + return 0; +} + +int shmem_unuse(swp_entry_t swap, struct page *page) +{ + return 0; +} + +int shmem_lock(struct file *file, int lock, struct user_struct *user) +{ + return 0; +} + +void shmem_unlock_mapping(struct address_space *mapping) +{ +} + +void shmem_truncate_range(struct inode *inode, loff_t lstart, loff_t lend) +{ + truncate_inode_pages_range(inode->i_mapping, lstart, lend); +} +EXPORT_SYMBOL_GPL(shmem_truncate_range); + +#define shmem_vm_ops generic_file_vm_ops +#define shmem_file_operations ramfs_file_operations +#define shmem_get_inode(sb, dir, mode, dev, flags) ramfs_get_inode(sb, dir, mode, dev) +#define shmem_acct_size(flags, size) 0 +#define shmem_unacct_size(flags, size) do {} while (0) + +#endif /* CONFIG_SHMEM */ + +/* common code */ + +static struct dentry_operations anon_ops = { + .d_dname = simple_dname +}; + +static struct file *__shmem_file_setup(const char *name, loff_t size, + unsigned long flags, unsigned int i_flags) +{ + struct file *res; struct inode *inode; - struct dentry *dentry, *root; + struct path path; + struct super_block *sb; struct qstr this; if (IS_ERR(shm_mnt)) - return (void *)shm_mnt; + return ERR_CAST(shm_mnt); - if (size < 0 || size > SHMEM_MAX_BYTES) + if (size < 0 || size > MAX_LFS_FILESIZE) return ERR_PTR(-EINVAL); if (shmem_acct_size(flags, size)) return ERR_PTR(-ENOMEM); - error = -ENOMEM; + res = ERR_PTR(-ENOMEM); this.name = name; this.len = strlen(name); this.hash = 0; /* will go */ - root = shm_mnt->mnt_root; - dentry = d_alloc(root, &this); - if (!dentry) + sb = shm_mnt->mnt_sb; + path.dentry = d_alloc_pseudo(sb, &this); + if (!path.dentry) goto put_memory; + d_set_d_op(path.dentry, &anon_ops); + path.mnt = mntget(shm_mnt); - error = -ENFILE; - file = get_empty_filp(); - if (!file) - goto put_dentry; - - error = -ENOSPC; - inode = shmem_get_inode(root->d_sb, S_IFREG | S_IRWXUGO, 0); + res = ERR_PTR(-ENOSPC); + inode = shmem_get_inode(sb, NULL, S_IFREG | S_IRWXUGO, 0, flags); if (!inode) - goto close_file; + goto put_dentry; - SHMEM_I(inode)->flags = flags & VM_ACCOUNT; - d_instantiate(dentry, inode); + inode->i_flags |= i_flags; + d_instantiate(path.dentry, inode); inode->i_size = size; - inode->i_nlink = 0; /* It is unlinked */ - file->f_vfsmnt = mntget(shm_mnt); - file->f_dentry = dentry; - file->f_mapping = inode->i_mapping; - file->f_op = &shmem_file_operations; - file->f_mode = FMODE_WRITE | FMODE_READ; - return file; - -close_file: - put_filp(file); + clear_nlink(inode); /* It is unlinked */ + res = ERR_PTR(ramfs_nommu_expand_for_mapping(inode, size)); + if (IS_ERR(res)) + goto put_dentry; + + res = alloc_file(&path, FMODE_WRITE | FMODE_READ, + &shmem_file_operations); + if (IS_ERR(res)) + goto put_dentry; + + return res; + put_dentry: - dput(dentry); + path_put(&path); put_memory: shmem_unacct_size(flags, size); - return ERR_PTR(error); + return res; } -/* +/** + * shmem_kernel_file_setup - get an unlinked file living in tmpfs which must be + * kernel internal. There will be NO LSM permission checks against the + * underlying inode. So users of this interface must do LSM checks at a + * higher layer. The one user is the big_key implementation. LSM checks + * are provided at the key level rather than the inode level. + * @name: name for dentry (to be seen in /proc/<pid>/maps + * @size: size to be set for the file + * @flags: VM_NORESERVE suppresses pre-accounting of the entire object size + */ +struct file *shmem_kernel_file_setup(const char *name, loff_t size, unsigned long flags) +{ + return __shmem_file_setup(name, size, flags, S_PRIVATE); +} + +/** + * shmem_file_setup - get an unlinked file living in tmpfs + * @name: name for dentry (to be seen in /proc/<pid>/maps + * @size: size to be set for the file + * @flags: VM_NORESERVE suppresses pre-accounting of the entire object size + */ +struct file *shmem_file_setup(const char *name, loff_t size, unsigned long flags) +{ + return __shmem_file_setup(name, size, flags, 0); +} +EXPORT_SYMBOL_GPL(shmem_file_setup); + +/** * shmem_zero_setup - setup a shared anonymous mapping - * * @vma: the vma to be mmapped is prepared by do_mmap_pgoff */ int shmem_zero_setup(struct vm_area_struct *vma) @@ -2253,3 +3011,42 @@ int shmem_zero_setup(struct vm_area_struct *vma) vma->vm_ops = &shmem_vm_ops; return 0; } + +/** + * shmem_read_mapping_page_gfp - read into page cache, using specified page allocation flags. + * @mapping: the page's address_space + * @index: the page index + * @gfp: the page allocator flags to use if allocating + * + * This behaves as a tmpfs "read_cache_page_gfp(mapping, index, gfp)", + * with any new page allocations done using the specified allocation flags. + * But read_cache_page_gfp() uses the ->readpage() method: which does not + * suit tmpfs, since it may have pages in swapcache, and needs to find those + * for itself; although drivers/gpu/drm i915 and ttm rely upon this support. + * + * i915_gem_object_get_pages_gtt() mixes __GFP_NORETRY | __GFP_NOWARN in + * with the mapping_gfp_mask(), to avoid OOMing the machine unnecessarily. + */ +struct page *shmem_read_mapping_page_gfp(struct address_space *mapping, + pgoff_t index, gfp_t gfp) +{ +#ifdef CONFIG_SHMEM + struct inode *inode = mapping->host; + struct page *page; + int error; + + BUG_ON(mapping->a_ops != &shmem_aops); + error = shmem_getpage_gfp(inode, index, &page, SGP_CACHE, gfp, NULL); + if (error) + page = ERR_PTR(error); + else + unlock_page(page); + return page; +#else + /* + * The tiny !SHMEM case uses ramfs without swap + */ + return read_cache_page_gfp(mapping, index, gfp); +#endif +} +EXPORT_SYMBOL_GPL(shmem_read_mapping_page_gfp); |