X-Git-Url: http://ftp.safe.ca/?a=blobdiff_plain;f=mm%2Fshmem.c;h=4ef9797bd430a9b0b79ebd7bffc1a3fcb3a1ee1f;hb=70764a905785ebacc8d44fed7a12fba3db267ae6;hp=37777f4c11f86074ce9d5cd81bd9cafb0dd6e233;hpb=b5810039a54e5babf428e9a1e89fc1940fabff11;p=safe%2Fjmp%2Flinux-2.6 diff --git a/mm/shmem.c b/mm/shmem.c index 37777f4..4ef9797 100644 --- a/mm/shmem.c +++ b/mm/shmem.c @@ -14,51 +14,78 @@ * Copyright (c) 2004, Luke Kenneth Casson Leighton * Copyright (c) 2004 Red Hat, Inc., James Morris * + * tiny-shmem: + * Copyright (c) 2004, 2008 Matt Mackall + * * This file is released under the GPL. */ +#include +#include +#include +#include +#include +#include +#include +#include +#include + +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 -#include -#include -#include -#include -#include +#include +#include +#include +#include #include -#include -#include -#include #include #include #include #include -#include #include -#include #include #include #include #include #include +#include +#include +#include +#include +#include + #include #include #include -/* This magic number is used in glibc for posix shared memory */ -#define TMPFS_MAGIC 0x01021994 - +/* + * The maximum size of a shmem/tmpfs file is limited by the maximum size of + * its triple-indirect swap vector - see illustration at shmem_swp_entry(). + * + * With 4kB page size, maximum file size is just over 2TB on a 32-bit kernel, + * but one eighth of that on a 64-bit kernel. With 8kB page size, maximum + * file size is just over 4TB on a 64-bit kernel, but 16TB on a 32-bit kernel, + * MAX_LFS_FILESIZE being then more restrictive than swap vector layout. + * + * We use / and * instead of shifts in the definitions below, so that the swap + * vector can be tested with small even values (e.g. 20) for ENTRIES_PER_PAGE. + */ #define ENTRIES_PER_PAGE (PAGE_CACHE_SIZE/sizeof(unsigned long)) -#define ENTRIES_PER_PAGEPAGE (ENTRIES_PER_PAGE*ENTRIES_PER_PAGE) -#define BLOCKS_PER_PAGE (PAGE_CACHE_SIZE/512) +#define ENTRIES_PER_PAGEPAGE ((unsigned long long)ENTRIES_PER_PAGE*ENTRIES_PER_PAGE) + +#define SHMSWP_MAX_INDEX (SHMEM_NR_DIRECT + (ENTRIES_PER_PAGEPAGE/2) * (ENTRIES_PER_PAGE+1)) +#define SHMSWP_MAX_BYTES (SHMSWP_MAX_INDEX << PAGE_CACHE_SHIFT) -#define SHMEM_MAX_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 SHMEM_MAX_BYTES min_t(unsigned long long, SHMSWP_MAX_BYTES, MAX_LFS_FILESIZE) +#define SHMEM_MAX_INDEX ((unsigned long)((SHMEM_MAX_BYTES+1) >> PAGE_CACHE_SHIFT)) +#define BLOCKS_PER_PAGE (PAGE_CACHE_SIZE/512) #define VM_ACCT(size) (PAGE_CACHE_ALIGN(size) >> PAGE_SHIFT) /* info->flags needs VM_flags to handle pagein/truncate races efficiently */ @@ -71,17 +98,26 @@ /* Pretend that each entry is of this size in directory's i_size */ #define BOGO_DIRENT_SIZE 20 -/* Keep swapped page count in private field of indirect struct page */ -#define nr_swapped private - /* Flag allocation requirements to shmem_getpage and shmem_swp_alloc */ 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_DIRTY, /* like SGP_CACHE, but set new page dirty */ SGP_WRITE, /* may exceed i_size, may allocate page */ }; +#ifdef CONFIG_TMPFS +static unsigned long shmem_default_max_blocks(void) +{ + return totalram_pages / 2; +} + +static unsigned long shmem_default_max_inodes(void) +{ + return min(totalram_pages - totalhigh_pages, totalram_pages / 2); +} +#endif + static int shmem_getpage(struct inode *inode, unsigned long idx, struct page **pagep, enum sgp_type sgp, int *type); @@ -91,8 +127,11 @@ static inline struct page *shmem_dir_alloc(gfp_t gfp_mask) * The above definition of ENTRIES_PER_PAGE, and the use of * BLOCKS_PER_PAGE on indirect pages, assume PAGE_CACHE_SIZE: * might be reconsidered if it ever diverges from PAGE_SIZE. + * + * Mobility flags are masked out as swap vectors cannot move */ - return alloc_pages(gfp_mask, PAGE_CACHE_SHIFT-PAGE_SHIFT); + return alloc_pages((gfp_mask & ~GFP_MOVABLE_MASK) | __GFP_ZERO, + PAGE_CACHE_SHIFT-PAGE_SHIFT); } static inline void shmem_dir_free(struct page *page) @@ -145,13 +184,13 @@ 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_kern(VM_ACCT(size)); } static inline void shmem_unacct_size(unsigned long flags, loff_t size) { - if (flags & VM_ACCOUNT) + if (!(flags & VM_NORESERVE)) vm_unacct_memory(VM_ACCT(size)); } @@ -163,31 +202,32 @@ 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_kern(VM_ACCT(PAGE_CACHE_SIZE)) : 0; } static inline void shmem_unacct_blocks(unsigned long flags, long pages) { - if (!(flags & VM_ACCOUNT)) + if (flags & VM_NORESERVE) vm_unacct_memory(pages * VM_ACCT(PAGE_CACHE_SIZE)); } -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, + .capabilities = BDI_CAP_NO_ACCT_AND_WRITEBACK | BDI_CAP_SWAP_BACKED, .unplug_io_fn = default_unplug_io_fn, }; 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) { @@ -200,9 +240,33 @@ 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(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_inodes++; + spin_unlock(&sbinfo->stat_lock); + } +} + +/** * shmem_recalc_inode - recalculate the size of an inode - * * @inode: inode to recalc * * We have to calculate the free blocks since the mm can drop @@ -226,9 +290,8 @@ static void shmem_recalc_inode(struct inode *inode) } } -/* +/** * 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 @@ -324,17 +387,19 @@ static void shmem_swp_set(struct shmem_inode_info *info, swp_entry_t *entry, uns entry->val = value; info->swapped += incdec; - if ((unsigned long)(entry - info->i_direct) >= SHMEM_NR_DIRECT) - kmap_atomic_to_page(entry)->nr_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); + } } -/* +/** * 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? + * + * If the entry does not exist, allocate it. */ static swp_entry_t *shmem_swp_alloc(struct shmem_inode_info *info, unsigned long index, enum sgp_type sgp) { @@ -367,10 +432,7 @@ static swp_entry_t *shmem_swp_alloc(struct shmem_inode_info *info, unsigned long } spin_unlock(&info->lock); - page = shmem_dir_alloc(mapping_gfp_mask(inode->i_mapping) | __GFP_ZERO); - if (page) { - page->nr_swapped = 0; - } + page = shmem_dir_alloc(mapping_gfp_mask(inode->i_mapping)); spin_lock(&info->lock); if (!page) { @@ -395,29 +457,40 @@ static swp_entry_t *shmem_swp_alloc(struct shmem_inode_info *info, unsigned long 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 + * @dir: pointer to the directory + * @edir: pointer after last entry of the directory + * @punch_lock: pointer to spinlock when needed for the holepunch case */ -static int shmem_free_swp(swp_entry_t *dir, swp_entry_t *edir) +static int shmem_free_swp(swp_entry_t *dir, swp_entry_t *edir, + spinlock_t *punch_lock) { + spinlock_t *punch_unlock = NULL; swp_entry_t *ptr; int freed = 0; for (ptr = dir; ptr < edir; ptr++) { if (ptr->val) { + if (unlikely(punch_lock)) { + punch_unlock = punch_lock; + punch_lock = NULL; + spin_lock(punch_unlock); + if (!ptr->val) + continue; + } free_swap_and_cache(*ptr); *ptr = (swp_entry_t){0}; freed++; } } + if (punch_unlock) + spin_unlock(punch_unlock); return freed; } -static int shmem_map_and_free_swp(struct page *subdir, - int offset, int limit, struct page ***dir) +static int shmem_map_and_free_swp(struct page *subdir, int offset, + int limit, struct page ***dir, spinlock_t *punch_lock) { swp_entry_t *ptr; int freed = 0; @@ -427,7 +500,8 @@ static int shmem_map_and_free_swp(struct page *subdir, int size = limit - offset; if (size > LATENCY_LIMIT) size = LATENCY_LIMIT; - freed += shmem_free_swp(ptr+offset, ptr+offset+size); + freed += shmem_free_swp(ptr+offset, ptr+offset+size, + punch_lock); if (need_resched()) { shmem_swp_unmap(ptr); if (*dir) { @@ -459,7 +533,7 @@ static void shmem_free_pages(struct list_head *next) } while (next); } -static void shmem_truncate(struct inode *inode) +static void shmem_truncate_range(struct inode *inode, loff_t start, loff_t end) { struct shmem_inode_info *info = SHMEM_I(inode); unsigned long idx; @@ -477,18 +551,39 @@ static void shmem_truncate(struct inode *inode) long nr_swaps_freed = 0; int offset; int freed; + int punch_hole; + spinlock_t *needs_lock; + spinlock_t *punch_lock; + unsigned long upper_limit; inode->i_ctime = inode->i_mtime = CURRENT_TIME; - idx = (inode->i_size + PAGE_CACHE_SIZE - 1) >> PAGE_CACHE_SHIFT; + idx = (start + PAGE_CACHE_SIZE - 1) >> PAGE_CACHE_SHIFT; if (idx >= info->next_index) return; spin_lock(&info->lock); info->flags |= SHMEM_TRUNCATE; - limit = info->next_index; - info->next_index = idx; + if (likely(end == (loff_t) -1)) { + limit = info->next_index; + upper_limit = SHMEM_MAX_INDEX; + info->next_index = idx; + needs_lock = NULL; + punch_hole = 0; + } else { + if (end + 1 >= inode->i_size) { /* we may free a little more */ + limit = (inode->i_size + PAGE_CACHE_SIZE - 1) >> + PAGE_CACHE_SHIFT; + upper_limit = SHMEM_MAX_INDEX; + } else { + limit = (end + 1) >> PAGE_CACHE_SHIFT; + upper_limit = limit; + } + needs_lock = &info->lock; + punch_hole = 1; + } + topdir = info->i_indirect; - if (topdir && idx <= SHMEM_NR_DIRECT) { + if (topdir && idx <= SHMEM_NR_DIRECT && !punch_hole) { info->i_indirect = NULL; nr_pages_to_free++; list_add(&topdir->lru, &pages_to_free); @@ -500,12 +595,30 @@ static void shmem_truncate(struct inode *inode) size = limit; if (size > SHMEM_NR_DIRECT) size = SHMEM_NR_DIRECT; - nr_swaps_freed = shmem_free_swp(ptr+idx, ptr+size); + nr_swaps_freed = shmem_free_swp(ptr+idx, ptr+size, needs_lock); } - if (!topdir) + + /* + * If there are no indirect blocks or we are punching a hole + * below indirect blocks, nothing to be done. + */ + if (!topdir || limit <= SHMEM_NR_DIRECT) goto done2; - BUG_ON(limit <= SHMEM_NR_DIRECT); + /* + * The truncation case has already dropped info->lock, and we're safe + * because i_size and next_index have already been lowered, preventing + * access beyond. But in the punch_hole case, we still need to take + * the lock when updating the swap directory, because there might be + * racing accesses by shmem_getpage(SGP_CACHE), shmem_unuse_inode or + * shmem_writepage. However, whenever we find we can remove a whole + * directory page (not at the misaligned start or end of the range), + * we first NULLify its pointer in the level above, and then have no + * need to take the lock when updating its contents: needs_lock and + * punch_lock (either pointing to info->lock or NULL) manage this. + */ + + upper_limit -= SHMEM_NR_DIRECT; limit -= SHMEM_NR_DIRECT; idx = (idx > SHMEM_NR_DIRECT)? (idx - SHMEM_NR_DIRECT): 0; offset = idx % ENTRIES_PER_PAGE; @@ -525,8 +638,14 @@ static void shmem_truncate(struct inode *inode) if (*dir) { diroff = ((idx - ENTRIES_PER_PAGEPAGE/2) % ENTRIES_PER_PAGEPAGE) / ENTRIES_PER_PAGE; - if (!diroff && !offset) { - *dir = NULL; + if (!diroff && !offset && upper_limit >= stage) { + if (needs_lock) { + spin_lock(needs_lock); + *dir = NULL; + spin_unlock(needs_lock); + needs_lock = NULL; + } else + *dir = NULL; nr_pages_to_free++; list_add(&middir->lru, &pages_to_free); } @@ -552,38 +671,55 @@ static void shmem_truncate(struct inode *inode) } stage = idx + ENTRIES_PER_PAGEPAGE; middir = *dir; - *dir = NULL; - nr_pages_to_free++; - list_add(&middir->lru, &pages_to_free); + if (punch_hole) + needs_lock = &info->lock; + if (upper_limit >= stage) { + if (needs_lock) { + spin_lock(needs_lock); + *dir = NULL; + spin_unlock(needs_lock); + needs_lock = NULL; + } else + *dir = NULL; + nr_pages_to_free++; + list_add(&middir->lru, &pages_to_free); + } shmem_dir_unmap(dir); cond_resched(); dir = shmem_dir_map(middir); diroff = 0; } + punch_lock = needs_lock; subdir = dir[diroff]; - if (subdir && subdir->nr_swapped) { + if (subdir && !offset && upper_limit-idx >= ENTRIES_PER_PAGE) { + if (needs_lock) { + spin_lock(needs_lock); + dir[diroff] = NULL; + spin_unlock(needs_lock); + punch_lock = NULL; + } else + dir[diroff] = NULL; + nr_pages_to_free++; + list_add(&subdir->lru, &pages_to_free); + } + if (subdir && page_private(subdir) /* has swap entries */) { size = limit - idx; if (size > ENTRIES_PER_PAGE) size = ENTRIES_PER_PAGE; freed = shmem_map_and_free_swp(subdir, - offset, size, &dir); + offset, size, &dir, punch_lock); if (!dir) dir = shmem_dir_map(middir); nr_swaps_freed += freed; - if (offset) + if (offset || punch_lock) { spin_lock(&info->lock); - subdir->nr_swapped -= freed; - if (offset) + set_page_private(subdir, + page_private(subdir) - freed); spin_unlock(&info->lock); - BUG_ON(subdir->nr_swapped > offset); - } - if (offset) - offset = 0; - else if (subdir) { - dir[diroff] = NULL; - nr_pages_to_free++; - list_add(&subdir->lru, &pages_to_free); + } else + BUG_ON(page_private(subdir) != freed); } + offset = 0; } done1: shmem_dir_unmap(dir); @@ -595,8 +731,16 @@ done2: * 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. + * + * Recalling truncate_inode_pages_range and unmap_mapping_range + * every time for punch_hole (which never got a chance to clear + * SHMEM_PAGEIN at the start of vmtruncate_range) is expensive, + * yet hardly ever necessary: try to optimize them out later. */ - truncate_inode_pages(inode->i_mapping, inode->i_size); + truncate_inode_pages_range(inode->i_mapping, start, end); + if (punch_hole) + unmap_mapping_range(inode->i_mapping, start, + end - start, 1); } spin_lock(&info->lock); @@ -616,13 +760,18 @@ done2: } } +static void shmem_truncate(struct inode *inode) +{ + shmem_truncate_range(inode, inode->i_size, (loff_t)-1); +} + static int shmem_notify_change(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 (S_ISREG(inode->i_mode) && (attr->ia_valid & ATTR_SIZE)) { if (attr->ia_size < inode->i_size) { /* * If truncating down to a partial page, then @@ -635,6 +784,8 @@ static int shmem_notify_change(struct dentry *dentry, struct iattr *attr) (void) shmem_getpage(inode, attr->ia_size>>PAGE_CACHE_SHIFT, &page, SGP_READ, NULL); + if (page) + unlock_page(page); } /* * Reset SHMEM_PAGEIN flag so that shmem_truncate can @@ -655,6 +806,10 @@ static int shmem_notify_change(struct dentry *dentry, struct iattr *attr) error = inode_change_ok(inode, attr); if (!error) error = inode_setattr(inode, attr); +#ifdef CONFIG_TMPFS_POSIX_ACL + if (!error && (attr->ia_valid & ATTR_MODE)) + error = generic_acl_chmod(inode); +#endif if (page) page_cache_release(page); return error; @@ -662,7 +817,6 @@ static int shmem_notify_change(struct dentry *dentry, struct iattr *attr) static void shmem_delete_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) { @@ -671,17 +825,13 @@ static void shmem_delete_inode(struct inode *inode) inode->i_size = 0; shmem_truncate(inode); 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); - } + shmem_free_inode(inode->i_sb); clear_inode(inode); } @@ -707,19 +857,22 @@ static int shmem_unuse_inode(struct shmem_inode_info *info, swp_entry_t entry, s struct page *subdir; swp_entry_t *ptr; int offset; + int error; idx = 0; ptr = info->i_direct; spin_lock(&info->lock); + if (!info->swapped) { + list_del_init(&info->swaplist); + goto lost2; + } limit = info->next_index; size = limit; if (size > SHMEM_NR_DIRECT) size = SHMEM_NR_DIRECT; offset = shmem_find_swp(entry, ptr, ptr+size); - if (offset >= 0) { - shmem_swp_balance_unmap(); + if (offset >= 0) goto found; - } if (!info->i_indirect) goto lost2; @@ -729,6 +882,14 @@ static int shmem_unuse_inode(struct shmem_inode_info *info, swp_entry_t entry, s for (idx = SHMEM_NR_DIRECT; idx < limit; idx += ENTRIES_PER_PAGE, dir++) { if (unlikely(idx == stage)) { shmem_dir_unmap(dir-1); + if (cond_resched_lock(&info->lock)) { + /* check it has not been truncated */ + if (limit > info->next_index) { + limit = info->next_index; + if (idx >= limit) + goto lost2; + } + } dir = shmem_dir_map(info->i_indirect) + ENTRIES_PER_PAGE/2 + idx/ENTRIES_PER_PAGEPAGE; while (!*dir) { @@ -743,17 +904,17 @@ static int shmem_unuse_inode(struct shmem_inode_info *info, swp_entry_t entry, s dir = shmem_dir_map(subdir); } subdir = *dir; - if (subdir && subdir->nr_swapped) { + if (subdir && page_private(subdir)) { ptr = shmem_swp_map(subdir); size = limit - idx; if (size > ENTRIES_PER_PAGE) size = ENTRIES_PER_PAGE; offset = shmem_find_swp(entry, ptr, ptr+size); + shmem_swp_unmap(ptr); if (offset >= 0) { shmem_dir_unmap(dir); goto found; } - shmem_swp_unmap(ptr); } } lost1: @@ -763,19 +924,77 @@ lost2: 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); + inode = igrab(&info->vfs_inode); spin_unlock(&info->lock); + /* - * Decrement swap count even when the entry is left behind: - * try_to_unuse will skip over mms, then reincrement count. + * Move _head_ to start search for next from here. + * But be careful: shmem_delete_inode checks list_empty without taking + * mutex, and there's an instant in list_move_tail when info->swaplist + * would appear empty, if it were the only one on shmem_swaplist. We + * could avoid doing it if inode NULL; or use this minor optimization. */ - swap_free(entry); - return 1; + if (shmem_swaplist.next != &info->swaplist) + list_move_tail(&shmem_swaplist, &info->swaplist); + mutex_unlock(&shmem_swaplist_mutex); + + error = 1; + if (!inode) + goto out; + /* + * Charge page using GFP_KERNEL while we can wait. + * Charged back to the user(not to caller) when swap account is used. + * add_to_page_cache() will be called with GFP_NOWAIT. + */ + error = mem_cgroup_cache_charge(page, current->mm, GFP_KERNEL); + if (error) + goto out; + error = radix_tree_preload(GFP_KERNEL); + if (error) { + mem_cgroup_uncharge_cache_page(page); + goto out; + } + error = 1; + + spin_lock(&info->lock); + ptr = shmem_swp_entry(info, idx, NULL); + if (ptr && ptr->val == entry.val) { + error = add_to_page_cache_locked(page, inode->i_mapping, + idx, GFP_NOWAIT); + /* does mem_cgroup_uncharge_cache_page on error */ + } else /* we must compensate for our precharge above */ + mem_cgroup_uncharge_cache_page(page); + + if (error == -EEXIST) { + struct page *filepage = find_get_page(inode->i_mapping, idx); + error = 1; + if (filepage) { + /* + * There might be a more uptodate page coming down + * from a stacked writepage: forget our swappage if so. + */ + if (PageUptodate(filepage)) + error = 0; + page_cache_release(filepage); + } + } + if (!error) { + delete_from_swap_cache(page); + set_page_dirty(page); + info->flags |= SHMEM_PAGEIN; + shmem_swp_set(info, ptr, 0); + swap_free(entry); + error = 1; /* not an error, but entry was found */ + } + if (ptr) + shmem_swp_unmap(ptr); + spin_unlock(&info->lock); + radix_tree_preload_end(); +out: + unlock_page(page); + page_cache_release(page); + iput(inode); /* allows for NULL */ + return error; } /* @@ -787,20 +1006,23 @@ int shmem_unuse(swp_entry_t entry, struct page *page) struct shmem_inode_info *info; int found = 0; - spin_lock(&shmem_swaplist_lock); + mutex_lock(&shmem_swaplist_mutex); list_for_each_safe(p, next, &shmem_swaplist) { info = list_entry(p, struct shmem_inode_info, swaplist); - if (!info->swapped) - 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; - break; - } + found = shmem_unuse_inode(info, entry, page); + cond_resched(); + if (found) + goto out; } - spin_unlock(&shmem_swaplist_lock); - return found; + mutex_unlock(&shmem_swaplist_mutex); + /* + * Can some race bring us here? We've been holding page lock, + * so I think not; but would rather try again later than BUG() + */ + unlock_page(page); + page_cache_release(page); +out: + return (found < 0) ? found : 0; } /* @@ -815,115 +1037,170 @@ static int shmem_writepage(struct page *page, struct writeback_control *wbc) struct inode *inode; 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; - swap = get_swap_page(); - if (!swap.val) + 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 + * may use the ->writepage of its underlying filesystem, in which case + * tmpfs should write out to swap only in response to memory pressure, + * and not for the writeback threads or sync. However, in those cases, + * we do still want to check if there's a redundant swappage to be + * discarded. + */ + if (wbc->for_reclaim) + swap = get_swap_page(); + else + swap.val = 0; + 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); + if (entry->val) { + /* + * The more uptodate page coming down from a stacked + * writepage should replace our old swappage. + */ + free_swap_and_cache(*entry); + shmem_swp_set(info, entry, 0); + } + shmem_recalc_inode(inode); - if (move_to_swap_cache(page, swap) == 0) { + if (swap.val && add_to_swap_cache(page, swap, GFP_ATOMIC) == 0) { + remove_from_page_cache(page); shmem_swp_set(info, entry, swap.val); shmem_swp_unmap(entry); + if (list_empty(&info->swaplist)) + inode = igrab(inode); + else + inode = NULL; spin_unlock(&info->lock); - if (list_empty(&info->swaplist)) { - spin_lock(&shmem_swaplist_lock); + swap_shmem_alloc(swap); + BUG_ON(page_mapped(page)); + page_cache_release(page); /* pagecache ref */ + swap_writepage(page, wbc); + if (inode) { + mutex_lock(&shmem_swaplist_mutex); /* move instead of add in case we're racing */ list_move_tail(&info->swaplist, &shmem_swaplist); - spin_unlock(&shmem_swaplist_lock); + mutex_unlock(&shmem_swaplist_mutex); + iput(inode); } - unlock_page(page); return 0; } shmem_swp_unmap(entry); unlock: spin_unlock(&info->lock); - swap_free(swap); + /* + * add_to_swap_cache() doesn't return -EEXIST, so we can safely + * clear SWAP_HAS_CACHE flag. + */ + 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, 1); + + seq_printf(seq, ",mpol=%s", buffer); } -struct page *shmem_swapin(struct shmem_inode_info *info, swp_entry_t entry, - unsigned long idx) +static struct mempolicy *shmem_get_sbmpol(struct shmem_sb_info *sbinfo) { - struct shared_policy *p = &info->policy; - int i, num; - 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); + 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); } - lru_add_drain(); /* Push any new pages onto the LRU now */ - return shmem_swapin_async(p, entry, idx); + return mpol; } +#endif /* CONFIG_TMPFS */ -static struct page * -shmem_alloc_page(gfp_t gfp, struct shmem_inode_info *info, - unsigned long idx) +static struct page *shmem_swapin(swp_entry_t entry, gfp_t gfp, + struct shmem_inode_info *info, unsigned long idx) { + struct mempolicy mpol, *spol; 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); + spol = mpol_cond_copy(&mpol, + mpol_shared_policy_lookup(&info->policy, idx)); + + /* Create a pseudo vma that just contains the policy */ + pvma.vm_start = 0; pvma.vm_pgoff = idx; - pvma.vm_end = PAGE_SIZE; - page = alloc_page_vma(gfp | __GFP_ZERO, &pvma, 0); - mpol_free(pvma.vm_policy); + pvma.vm_ops = NULL; + pvma.vm_policy = spol; + page = swapin_readahead(entry, gfp, &pvma, 0); return page; } -#else -static inline struct page * -shmem_swapin(struct shmem_inode_info *info,swp_entry_t entry,unsigned long idx) + +static struct page *shmem_alloc_page(gfp_t gfp, + struct shmem_inode_info *info, unsigned long idx) { - swapin_readahead(entry, 0, NULL); - return read_swap_cache_async(entry, NULL, 0); + struct vm_area_struct pvma; + + /* Create a pseudo vma that just contains the policy */ + pvma.vm_start = 0; + pvma.vm_pgoff = idx; + pvma.vm_ops = NULL; + pvma.vm_policy = mpol_shared_policy_lookup(&info->policy, idx); + + /* + * alloc_page_vma() will drop the shared policy reference + */ + return alloc_page_vma(gfp, &pvma, 0); +} +#else /* !CONFIG_NUMA */ +#ifdef CONFIG_TMPFS +static inline void shmem_show_mpol(struct seq_file *seq, struct mempolicy *p) +{ +} +#endif /* CONFIG_TMPFS */ + +static inline struct page *shmem_swapin(swp_entry_t entry, gfp_t gfp, + struct shmem_inode_info *info, unsigned long idx) +{ + return swapin_readahead(entry, gfp, NULL, 0); +} + +static inline struct page *shmem_alloc_page(gfp_t gfp, + struct shmem_inode_info *info, unsigned long idx) +{ + 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 @@ -944,17 +1221,22 @@ static int shmem_getpage(struct inode *inode, unsigned long idx, struct page *swappage; swp_entry_t *entry; swp_entry_t swap; + gfp_t gfp; int error; if (idx >= SHMEM_MAX_INDEX) return -EFBIG; + + if (type) + *type = 0; + /* * 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. + * But shmem_readpage (required for splice) passes in a locked + * filepage, which may be found not uptodate by other callers + * too, and may need to be copied from the swappage read in. */ repeat: if (!filepage) @@ -962,8 +1244,17 @@ repeat: if (filepage && PageUptodate(filepage)) goto done; error = 0; - if (sgp == SGP_QUICK) - goto failed; + gfp = mapping_gfp_mask(mapping); + if (!filepage) { + /* + * Try to preload while we can wait, to not make a habit of + * draining atomic reserves; but don't latch on to this cpu. + */ + error = radix_tree_preload(gfp & ~__GFP_HIGHMEM); + if (error) + goto failed; + radix_tree_preload_end(); + } spin_lock(&info->lock); shmem_recalc_inode(inode); @@ -980,13 +1271,13 @@ repeat: swappage = lookup_swap_cache(swap); if (!swappage) { shmem_swp_unmap(entry); - spin_unlock(&info->lock); /* here we actually do the io */ - if (type && *type == VM_FAULT_MINOR) { - inc_page_state(pgmajfault); - *type = VM_FAULT_MAJOR; + if (type && !(*type & VM_FAULT_MAJOR)) { + __count_vm_event(PGMAJFAULT); + *type |= VM_FAULT_MAJOR; } - swappage = shmem_swapin(info, swap, idx); + spin_unlock(&info->lock); + swappage = shmem_swapin(swap, gfp, info, idx); if (!swappage) { spin_lock(&info->lock); entry = shmem_swp_alloc(info, idx, sgp); @@ -1008,7 +1299,7 @@ repeat: } /* We have to do this with page locked to prevent races */ - if (TestSetPageLocked(swappage)) { + if (!trylock_page(swappage)) { shmem_swp_unmap(entry); spin_unlock(&info->lock); wait_on_page_locked(swappage); @@ -1044,30 +1335,43 @@ repeat: SetPageUptodate(filepage); set_page_dirty(filepage); swap_free(swap); - } else if (!(error = move_from_swap_cache( - swappage, idx, mapping))) { + } else if (!(error = add_to_page_cache_locked(swappage, mapping, + idx, GFP_NOWAIT))) { info->flags |= SHMEM_PAGEIN; shmem_swp_set(info, entry, 0); shmem_swp_unmap(entry); + delete_from_swap_cache(swappage); spin_unlock(&info->lock); filepage = swappage; + set_page_dirty(filepage); swap_free(swap); } else { shmem_swp_unmap(entry); spin_unlock(&info->lock); - unlock_page(swappage); - page_cache_release(swappage); if (error == -ENOMEM) { - /* let kswapd refresh zone for GFP_ATOMICs */ - blk_congestion_wait(WRITE, HZ/50); + /* + * reclaim from proper memory cgroup and + * call memcg's OOM if needed. + */ + error = mem_cgroup_shmem_charge_fallback( + swappage, + current->mm, + gfp); + if (error) { + unlock_page(swappage); + page_cache_release(swappage); + goto failed; + } } + unlock_page(swappage); + page_cache_release(swappage); goto repeat; } } else if (sgp == SGP_READ && !filepage) { shmem_swp_unmap(entry); filepage = find_get_page(mapping, idx); if (filepage && - (!PageUptodate(filepage) || TestSetPageLocked(filepage))) { + (!PageUptodate(filepage) || !trylock_page(filepage))) { spin_unlock(&info->lock); wait_on_page_locked(filepage); page_cache_release(filepage); @@ -1097,16 +1401,28 @@ repeat: } if (!filepage) { + int ret; + spin_unlock(&info->lock); - filepage = shmem_alloc_page(mapping_gfp_mask(mapping), - info, - idx); + filepage = shmem_alloc_page(gfp, info, idx); if (!filepage) { shmem_unacct_blocks(info->flags, 1); shmem_free_blocks(inode, 1); error = -ENOMEM; goto failed; } + SetPageSwapBacked(filepage); + + /* Precharge page while we can wait, compensate after */ + error = mem_cgroup_cache_charge(filepage, current->mm, + GFP_KERNEL); + if (error) { + page_cache_release(filepage); + shmem_unacct_blocks(info->flags, 1); + shmem_free_blocks(inode, 1); + filepage = NULL; + goto failed; + } spin_lock(&info->lock); entry = shmem_swp_alloc(info, idx, sgp); @@ -1116,8 +1432,17 @@ repeat: swap = *entry; shmem_swp_unmap(entry); } - if (error || swap.val || 0 != add_to_page_cache_lru( - filepage, mapping, idx, GFP_ATOMIC)) { + ret = error || swap.val; + if (ret) + mem_cgroup_uncharge_cache_page(filepage); + else + ret = add_to_page_cache_lru(filepage, mapping, + idx, GFP_NOWAIT); + /* + * At add_to_page_cache_lru() failure, uncharge will + * be done automatically. + */ + if (ret) { spin_unlock(&info->lock); page_cache_release(filepage); shmem_unacct_blocks(info->flags, 1); @@ -1132,14 +1457,14 @@ repeat: info->alloced++; spin_unlock(&info->lock); + clear_highpage(filepage); flush_dcache_page(filepage); SetPageUptodate(filepage); + if (sgp == SGP_DIRTY) + set_page_dirty(filepage); } done: - if (*pagep != filepage) { - unlock_page(filepage); - *pagep = filepage; - } + *pagep = filepage; return 0; failed: @@ -1150,84 +1475,33 @@ failed: 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 = vma->vm_file->f_path.dentry->d_inode; int error; + int ret; - 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; + if (((loff_t)vmf->pgoff << PAGE_CACHE_SHIFT) >= i_size_read(inode)) + return VM_FAULT_SIGBUS; - error = shmem_getpage(inode, idx, &page, SGP_CACHE, type); + error = shmem_getpage(inode, vmf->pgoff, &vmf->page, SGP_CACHE, &ret); if (error) - return (error == -ENOMEM)? NOPAGE_OOM: NOPAGE_SIGBUS; + return ((error == -ENOMEM) ? VM_FAULT_OOM : VM_FAULT_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; - - size = (i_size_read(inode) + PAGE_SIZE - 1) >> PAGE_SHIFT; - if (pgoff >= size || pgoff + (len >> PAGE_SHIFT) > size) - return -EINVAL; - - 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; - } - - len -= PAGE_SIZE; - addr += PAGE_SIZE; - pgoff++; - } - return 0; + return ret | VM_FAULT_LOCKED; } #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 *new) { - struct inode *i = vma->vm_file->f_dentry->d_inode; + struct inode *i = vma->vm_file->f_path.dentry->d_inode; return mpol_set_shared_policy(&SHMEM_I(i)->policy, vma, new); } -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; + struct inode *i = vma->vm_file->f_path.dentry->d_inode; unsigned long idx; idx = ((addr - vma->vm_start) >> PAGE_SHIFT) + vma->vm_pgoff; @@ -1237,7 +1511,7 @@ shmem_get_policy(struct vm_area_struct *vma, unsigned long addr) int shmem_lock(struct file *file, int lock, struct user_struct *user) { - struct inode *inode = file->f_dentry->d_inode; + struct inode *inode = file->f_path.dentry->d_inode; struct shmem_inode_info *info = SHMEM_I(inode); int retval = -ENOMEM; @@ -1246,12 +1520,16 @@ 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); + scan_mapping_unevictable_pages(file->f_mapping); } retval = 0; + out_nomem: spin_unlock(&info->lock); return retval; @@ -1261,52 +1539,48 @@ static int shmem_mmap(struct file *file, struct vm_area_struct *vma) { file_accessed(file); vma->vm_ops = &shmem_vm_ops; + vma->vm_flags |= VM_CAN_NONLINEAR; 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, + int 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_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); + 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; @@ -1317,140 +1591,73 @@ 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; } #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_symlink_inline_operations; /* - * Normally tmpfs makes no use of shmem_prepare_write, but it - * lets a tmpfs file be used read-write below the loop driver. + * Normally tmpfs avoids the use of shmem_readpage and shmem_write_begin; + * but providing them allows a tmpfs file to be used for splice, sendfile, and + * below the loop driver, in the generic fashion that many filesystems support. */ -static int -shmem_prepare_write(struct file *file, struct page *page, unsigned offset, unsigned to) +static int shmem_readpage(struct file *file, struct page *page) { struct inode *inode = page->mapping->host; - return shmem_getpage(inode, page->index, &page, SGP_WRITE, NULL); + int error = shmem_getpage(inode, page->index, &page, SGP_CACHE, NULL); + unlock_page(page); + return error; } -static ssize_t -shmem_file_write(struct file *file, const char __user *buf, size_t count, loff_t *ppos) +static int +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 = 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; - - left = bytes; - if (PageHighMem(page)) { - volatile unsigned char dummy; - __get_user(dummy, buf); - __get_user(dummy, buf + bytes - 1); - - kaddr = kmap_atomic(page, KM_USER0); - left = __copy_from_user_inatomic(kaddr + offset, - buf, bytes); - kunmap_atomic(kaddr, KM_USER0); - } - 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); + struct inode *inode = mapping->host; + pgoff_t index = pos >> PAGE_CACHE_SHIFT; + *pagep = NULL; + return shmem_getpage(inode, index, pagep, SGP_WRITE, NULL); +} - if (left) { - pos -= left; - written -= left; - err = -EFAULT; - break; - } +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 = mapping->host; - /* - * Our dirty pages are not counted in nr_dirty, - * and we do not attempt to balance dirty pages. - */ + if (pos + copied > inode->i_size) + i_size_write(inode, pos + copied); - cond_resched(); - } while (count); + 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) { - struct inode *inode = filp->f_dentry->d_inode; + struct inode *inode = filp->f_path.dentry->d_inode; struct address_space *mapping = inode->i_mapping; unsigned long index, offset; + enum sgp_type sgp = SGP_READ; + + /* + * 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; @@ -1469,16 +1676,18 @@ 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); + desc->error = shmem_getpage(inode, index, &page, sgp, NULL); if (desc->error) { if (desc->error == -EINVAL) desc->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); @@ -1537,50 +1746,43 @@ static void do_shmem_file_read(struct file *filp, loff_t *ppos, read_descriptor_ file_accessed(filp); } -static ssize_t shmem_file_read(struct file *filp, char __user *buf, size_t count, loff_t *ppos) -{ - read_descriptor_t desc; - - if ((ssize_t) count < 0) - return -EINVAL; - if (!access_ok(VERIFY_WRITE, buf, count)) - return -EFAULT; - if (!count) - return 0; - - desc.written = 0; - desc.count = count; - desc.arg.buf = buf; - desc.error = 0; - - do_shmem_file_read(filp, ppos, &desc, file_read_actor); - if (desc.written) - return desc.written; - return desc.error; -} - -static ssize_t shmem_file_sendfile(struct file *in_file, loff_t *ppos, - size_t count, read_actor_t actor, void *target) +static ssize_t shmem_file_aio_read(struct kiocb *iocb, + const struct iovec *iov, unsigned long nr_segs, loff_t pos) { - read_descriptor_t desc; + struct file *filp = iocb->ki_filp; + ssize_t retval; + unsigned long seg; + size_t count; + loff_t *ppos = &iocb->ki_pos; - if (!count) - return 0; + retval = generic_segment_checks(iov, &nr_segs, &count, VERIFY_WRITE); + if (retval) + return retval; - desc.written = 0; - desc.count = count; - desc.arg.data = target; - desc.error = 0; + for (seg = 0; seg < nr_segs; seg++) { + read_descriptor_t desc; - do_shmem_file_read(in_file, ppos, &desc, actor); - if (desc.written) - return desc.written; - return desc.error; + desc.written = 0; + desc.arg.buf = iov[seg].iov_base; + desc.count = iov[seg].iov_len; + if (desc.count == 0) + continue; + desc.error = 0; + do_shmem_file_read(filp, ppos, &desc, file_read_actor); + retval += desc.written; + if (desc.error) { + retval = retval ?: desc.error; + break; + } + if (desc.count > 0) + break; + } + return retval; } -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; @@ -1605,9 +1807,10 @@ static int shmem_statfs(struct super_block *sb, struct kstatfs *buf) static int shmem_mknod(struct inode *dir, struct dentry *dentry, int mode, dev_t dev) { - struct inode *inode = shmem_get_inode(dir->i_sb, mode, dev); + struct inode *inode; int error = -ENOSPC; + inode = shmem_get_inode(dir->i_sb, dir, mode, dev, VM_NORESERVE); if (inode) { error = security_inode_init_security(inode, dir, NULL, NULL, NULL); @@ -1616,13 +1819,16 @@ shmem_mknod(struct inode *dir, struct dentry *dentry, int mode, dev_t dev) 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; +#ifdef CONFIG_TMPFS_POSIX_ACL + error = generic_acl_init(inode, dir); + if (error) { + iput(inode); + return error; } +#else + error = 0; +#endif dir->i_size += BOGO_DIRENT_SIZE; dir->i_ctime = dir->i_mtime = CURRENT_TIME; d_instantiate(dentry, inode); @@ -1637,7 +1843,7 @@ static int shmem_mkdir(struct inode *dir, struct dentry *dentry, int mode) if ((error = shmem_mknod(dir, dentry, mode | S_IFDIR, 0))) return error; - dir->i_nlink++; + inc_nlink(dir); return 0; } @@ -1653,48 +1859,37 @@ 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++; + inc_nlink(inode); atomic_inc(&inode->i_count); /* 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; } @@ -1704,7 +1899,8 @@ 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); } @@ -1725,10 +1921,10 @@ 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; @@ -1752,7 +1948,7 @@ static int shmem_symlink(struct inode *dir, struct dentry *dentry, const char *s if (len > PAGE_CACHE_SIZE) return -ENAMETOOLONG; - inode = shmem_get_inode(dir->i_sb, S_IFLNK|S_IRWXUGO, 0); + inode = shmem_get_inode(dir->i_sb, dir, S_IFLNK|S_IRWXUGO, 0, VM_NORESERVE); if (!inode) return -ENOSPC; @@ -1778,15 +1974,15 @@ static int shmem_symlink(struct inode *dir, struct dentry *dentry, const char *s iput(inode); return error; } + inode->i_mapping->a_ops = &shmem_aops; inode->i_op = &shmem_symlink_inode_operations; kaddr = kmap_atomic(page, KM_USER0); memcpy(kaddr, symname, len); kunmap_atomic(kaddr, KM_USER0); 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); @@ -1805,6 +2001,8 @@ 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)); + if (page) + unlock_page(page); return page; } @@ -1818,23 +2016,157 @@ static void shmem_put_link(struct dentry *dentry, struct nameidata *nd, void *co } } -static struct inode_operations shmem_symlink_inline_operations = { +static const struct inode_operations shmem_symlink_inline_operations = { .readlink = generic_readlink, .follow_link = shmem_follow_link_inline, }; -static struct inode_operations shmem_symlink_inode_operations = { +static const struct inode_operations shmem_symlink_inode_operations = { .truncate = shmem_truncate, .readlink = generic_readlink, .follow_link = shmem_follow_link, .put_link = shmem_put_link, }; -static int shmem_parse_options(char *options, int *mode, uid_t *uid, gid_t *gid, unsigned long *blocks, unsigned long *inodes) +#ifdef CONFIG_TMPFS_POSIX_ACL +/* + * Superblocks without xattr inode operations will get security.* xattr + * support from the VFS "for free". As soon as we have any other xattrs + * like ACLs, we also need to implement the security.* handlers at + * filesystem level, though. + */ + +static size_t shmem_xattr_security_list(struct dentry *dentry, char *list, + size_t list_len, const char *name, + size_t name_len, int handler_flags) +{ + return security_inode_listsecurity(dentry->d_inode, list, list_len); +} + +static int shmem_xattr_security_get(struct dentry *dentry, const char *name, + void *buffer, size_t size, int handler_flags) +{ + if (strcmp(name, "") == 0) + return -EINVAL; + return xattr_getsecurity(dentry->d_inode, name, buffer, size); +} + +static int shmem_xattr_security_set(struct dentry *dentry, const char *name, + const void *value, size_t size, int flags, int handler_flags) +{ + if (strcmp(name, "") == 0) + return -EINVAL; + return security_inode_setsecurity(dentry->d_inode, name, value, + size, flags); +} + +static const struct xattr_handler shmem_xattr_security_handler = { + .prefix = XATTR_SECURITY_PREFIX, + .list = shmem_xattr_security_list, + .get = shmem_xattr_security_get, + .set = shmem_xattr_security_set, +}; + +static const struct xattr_handler *shmem_xattr_handlers[] = { + &generic_acl_access_handler, + &generic_acl_default_handler, + &shmem_xattr_security_handler, + NULL +}; +#endif + +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 = fid->raw[2]; + inum = (inum << 32) | fid->raw[1]; + + if (fh_len < 3) + return NULL; + + 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 dentry *dentry, __u32 *fh, int *len, + int connectable) +{ + struct inode *inode = dentry->d_inode; + + if (*len < 3) + return 255; + + if (hlist_unhashed(&inode->i_hash)) { + /* 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 (hlist_unhashed(&inode->i_hash)) + __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; - 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) { @@ -1857,33 +2189,37 @@ 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); + sbinfo->uid = simple_strtoul(value, &rest, 0); if (*rest) goto bad_val; } else if (!strcmp(this_char,"gid")) { - if (!gid) + if (remount) continue; - *gid = simple_strtoul(value,&rest,0); + sbinfo->gid = simple_strtoul(value, &rest, 0); if (*rest) goto bad_val; + } else if (!strcmp(this_char,"mpol")) { + if (mpol_parse_str(value, &sbinfo->mpol, 1)) + goto bad_val; } else { printk(KERN_ERR "tmpfs: Bad mount option %s\n", this_char); @@ -1902,22 +2238,20 @@ 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; + struct shmem_sb_info config = *sbinfo; unsigned long blocks; unsigned long inodes; int error = -EINVAL; - if (shmem_parse_options(data, NULL, NULL, NULL, - &max_blocks, &max_inodes)) + 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 (config.max_blocks < blocks) goto out; - if (max_inodes < inodes) + if (config.max_inodes < inodes) goto out; /* * Those tests also disallow limited->unlimited while any are in @@ -1925,21 +2259,43 @@ static int shmem_remount_fs(struct super_block *sb, int *flags, char *data) * 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->free_blocks = config.max_blocks - blocks; + sbinfo->max_inodes = config.max_inodes; + sbinfo->free_inodes = config.max_inodes - inodes; + + 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 vfsmount *vfs) +{ + struct shmem_sb_info *sbinfo = SHMEM_SB(vfs->mnt_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=%03o", sbinfo->mode); + if (sbinfo->uid != 0) + seq_printf(seq, ",uid=%u", sbinfo->uid); + if (sbinfo->gid != 0) + seq_printf(seq, ",gid=%u", sbinfo->gid); + shmem_show_mpol(seq, sbinfo->mpol); + return 0; +} +#endif /* CONFIG_TMPFS */ static void shmem_put_super(struct super_block *sb) { @@ -1947,18 +2303,23 @@ static void shmem_put_super(struct super_block *sb) 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 /* @@ -1967,42 +2328,38 @@ static int shmem_fill_super(struct super_block *sb, * 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; + 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; + } } + sb->s_export_op = &shmem_export_ops; #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; + sbinfo->free_blocks = sbinfo->max_blocks; + sbinfo->free_inodes = sbinfo->max_inodes; - sb->s_fs_info = sbinfo; sb->s_maxbytes = SHMEM_MAX_BYTES; 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_POSIX_ACL + sb->s_xattr = shmem_xattr_handlers; + 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; + inode->i_uid = sbinfo->uid; + inode->i_gid = sbinfo->gid; root = d_alloc_root(inode); if (!root) goto failed_iput; @@ -2016,12 +2373,12 @@ failed: 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); + p = (struct shmem_inode_info *)kmem_cache_alloc(shmem_inode_cachep, GFP_KERNEL); if (!p) return NULL; return &p->vfs_inode; @@ -2036,58 +2393,67 @@ static void shmem_destroy_inode(struct inode *inode) kmem_cache_free(shmem_inode_cachep, SHMEM_I(inode)); } -static void init_once(void *foo, kmem_cache_t *cachep, unsigned long flags) +static void init_once(void *foo) { struct shmem_inode_info *p = (struct shmem_inode_info *) foo; - if ((flags & (SLAB_CTOR_VERIFY|SLAB_CTOR_CONSTRUCTOR)) == - SLAB_CTOR_CONSTRUCTOR) { - inode_init_once(&p->vfs_inode); - } + inode_init_once(&p->vfs_inode); } static int 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, init_once); return 0; } static void 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, + .readpage = shmem_readpage, + .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, + .read = do_sync_read, + .write = do_sync_write, + .aio_read = shmem_file_aio_read, + .aio_write = generic_file_aio_write, .fsync = simple_sync_file, - .sendfile = shmem_file_sendfile, + .splice_read = generic_file_splice_read, + .splice_write = generic_file_splice_write, #endif }; -static struct inode_operations shmem_inode_operations = { +static const struct inode_operations shmem_inode_operations = { .truncate = shmem_truncate, .setattr = shmem_notify_change, + .truncate_range = shmem_truncate_range, +#ifdef CONFIG_TMPFS_POSIX_ACL + .setxattr = generic_setxattr, + .getxattr = generic_getxattr, + .listxattr = generic_listxattr, + .removexattr = generic_removexattr, + .check_acl = generic_check_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, @@ -2099,23 +2465,42 @@ static struct inode_operations shmem_dir_inode_operations = { .mknod = shmem_mknod, .rename = shmem_rename, #endif +#ifdef CONFIG_TMPFS_POSIX_ACL + .setattr = shmem_notify_change, + .setxattr = generic_setxattr, + .getxattr = generic_getxattr, + .listxattr = generic_listxattr, + .removexattr = generic_removexattr, + .check_acl = generic_check_acl, +#endif +}; + +static const struct inode_operations shmem_special_inode_operations = { +#ifdef CONFIG_TMPFS_POSIX_ACL + .setattr = shmem_notify_change, + .setxattr = generic_setxattr, + .getxattr = generic_getxattr, + .listxattr = generic_listxattr, + .removexattr = generic_removexattr, + .check_acl = generic_check_acl, +#endif }; -static struct super_operations shmem_ops = { +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, .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, #ifdef CONFIG_NUMA .set_policy = shmem_set_policy, .get_policy = shmem_get_policy, @@ -2123,10 +2508,10 @@ static struct vm_operations_struct shmem_vm_ops = { }; -static struct super_block *shmem_get_sb(struct file_system_type *fs_type, - int flags, const char *dev_name, void *data) +static int shmem_get_sb(struct file_system_type *fs_type, + int flags, const char *dev_name, void *data, struct vfsmount *mnt) { - return get_sb_nodev(fs_type, flags, data, shmem_fill_super); + return get_sb_nodev(fs_type, flags, data, shmem_fill_super, mnt); } static struct file_system_type tmpfs_fs_type = { @@ -2135,12 +2520,15 @@ static struct file_system_type tmpfs_fs_type = { .get_sb = shmem_get_sb, .kill_sb = kill_litter_super, }; -static struct vfsmount *shm_mnt; -static int __init init_tmpfs(void) +int __init init_tmpfs(void) { int error; + error = bdi_init(&shmem_backing_dev_info); + if (error) + goto out4; + error = init_inodecache(); if (error) goto out3; @@ -2150,10 +2538,8 @@ static int __init init_tmpfs(void) 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, + + shm_mnt = vfs_kern_mount(&tmpfs_fs_type, MS_NOUSER, tmpfs_fs_type.name, NULL); if (IS_ERR(shm_mnt)) { error = PTR_ERR(shm_mnt); @@ -2167,24 +2553,75 @@ out1: out2: 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 + * 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. + */ + +#include + +static struct file_system_type tmpfs_fs_type = { + .name = "tmpfs", + .get_sb = ramfs_get_sb, + .kill_sb = kill_litter_super, +}; + +int __init init_tmpfs(void) +{ + BUG_ON(register_filesystem(&tmpfs_fs_type) != 0); + + shm_mnt = kern_mount(&tmpfs_fs_type); + BUG_ON(IS_ERR(shm_mnt)); + + return 0; +} + +int shmem_unuse(swp_entry_t entry, struct page *page) +{ + return 0; +} + +int shmem_lock(struct file *file, int lock, struct user_struct *user) +{ + return 0; +} + +#define shmem_vm_ops generic_file_vm_ops +#define shmem_file_operations ramfs_file_operations +#define shmem_get_inode(sb, dir, mode, dev, flags) ramfs_get_inode(sb, dir, mode, dev) +#define shmem_acct_size(flags, size) 0 +#define shmem_unacct_size(flags, size) do {} while (0) +#define SHMEM_MAX_BYTES MAX_LFS_FILESIZE + +#endif /* CONFIG_SHMEM */ + +/* common code */ + +/** + * shmem_file_setup - get an unlinked file living in tmpfs * @name: name for dentry (to be seen in /proc//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(char *name, loff_t size, unsigned long flags) +struct file *shmem_file_setup(const char *name, loff_t size, unsigned long flags) { int error; struct file *file; struct inode *inode; - struct dentry *dentry, *root; + struct path path; + struct dentry *root; struct qstr this; if (IS_ERR(shm_mnt)) @@ -2201,43 +2638,43 @@ struct file *shmem_file_setup(char *name, loff_t size, unsigned long flags) this.len = strlen(name); this.hash = 0; /* will go */ root = shm_mnt->mnt_root; - dentry = d_alloc(root, &this); - if (!dentry) + path.dentry = d_alloc(root, &this); + if (!path.dentry) goto put_memory; - - error = -ENFILE; - file = get_empty_filp(); - if (!file) - goto put_dentry; + path.mnt = mntget(shm_mnt); error = -ENOSPC; - inode = shmem_get_inode(root->d_sb, S_IFREG | S_IRWXUGO, 0); + inode = shmem_get_inode(root->d_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); + 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; +#ifndef CONFIG_MMU + error = ramfs_nommu_expand_for_mapping(inode, size); + if (error) + goto put_dentry; +#endif + + error = -ENFILE; + file = alloc_file(&path, FMODE_WRITE | FMODE_READ, + &shmem_file_operations); + if (!file) + goto put_dentry; + return file; -close_file: - put_filp(file); put_dentry: - dput(dentry); + path_put(&path); put_memory: shmem_unacct_size(flags, size); return ERR_PTR(error); } +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)