X-Git-Url: http://git.onelab.eu/?a=blobdiff_plain;f=mm%2Fshmem.c;h=aa4d8378a6b86ddfff95f396f8e345e82a3324d0;hb=d2536f29c05742d0bc509969bb9708b49203e159;hp=ada4f735c7d95c4fe70ab495b8e142354d089cf4;hpb=8fe849edaaabd915f060b3744165ff7f95a2b34e;p=linux-2.6.git diff --git a/mm/shmem.c b/mm/shmem.c index ada4f735c..aa4d8378a 100644 --- a/mm/shmem.c +++ b/mm/shmem.c @@ -6,10 +6,14 @@ * 2000-2001 Christoph Rohland * 2000-2001 SAP AG * 2002 Red Hat Inc. - * Copyright (C) 2002-2003 Hugh Dickins. - * Copyright (C) 2002-2003 VERITAS Software Corporation. + * Copyright (C) 2002-2005 Hugh Dickins. + * Copyright (C) 2002-2005 VERITAS Software Corporation. * Copyright (C) 2004 Andi Kleen, SuSE Labs * + * Extended attribute support for tmpfs: + * Copyright (c) 2004, Luke Kenneth Casson Leighton + * Copyright (c) 2004 Red Hat, Inc., James Morris + * * This file is released under the GPL. */ @@ -19,11 +23,11 @@ * which makes it a completely usable filesystem. */ -#include #include #include -#include #include +#include +#include #include #include #include @@ -40,12 +44,17 @@ #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 #define ENTRIES_PER_PAGE (PAGE_CACHE_SIZE/sizeof(unsigned long)) #define ENTRIES_PER_PAGEPAGE (ENTRIES_PER_PAGE*ENTRIES_PER_PAGE) @@ -60,12 +69,12 @@ #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 -/* 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 */ @@ -77,7 +86,7 @@ enum sgp_type { 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(unsigned int gfp_mask) +static inline struct page *shmem_dir_alloc(gfp_t gfp_mask) { /* * The above definition of ENTRIES_PER_PAGE, and the use of @@ -103,23 +112,25 @@ static inline void shmem_dir_unmap(struct page **dir) } static swp_entry_t *shmem_swp_map(struct page *page) +{ + return (swp_entry_t *)kmap_atomic(page, KM_USER1); +} + +static inline void shmem_swp_balance_unmap(void) { /* - * We have to avoid the unconditional inc_preempt_count() - * in kmap_atomic(), since shmem_swp_unmap() will also be - * applied to the low memory addresses within i_direct[]. - * PageHighMem and high_memory tests are good for all arches - * and configs: highmem_start_page and FIXADDR_START are not. + * 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. */ - return PageHighMem(page)? - (swp_entry_t *)kmap_atomic(page, KM_USER1): - (swp_entry_t *)page_address(page); + (void) kmap_atomic(ZERO_PAGE(0), KM_USER1); } static inline void shmem_swp_unmap(swp_entry_t *entry) { - if (entry >= (swp_entry_t *)high_memory) - kunmap_atomic(entry, KM_USER1); + kunmap_atomic(entry, KM_USER1); } static inline struct shmem_sb_info *SHMEM_SB(struct super_block *sb) @@ -164,28 +175,31 @@ static inline void shmem_unacct_blocks(unsigned long flags, long pages) } static struct super_operations shmem_ops; -static struct address_space_operations shmem_aops; -static struct file_operations shmem_file_operations; +static const struct address_space_operations shmem_aops; +static const struct file_operations shmem_file_operations; static struct inode_operations shmem_inode_operations; static struct inode_operations shmem_dir_inode_operations; +static struct inode_operations shmem_special_inode_operations; static struct vm_operations_struct shmem_vm_ops; -static struct backing_dev_info shmem_backing_dev_info = { +static struct backing_dev_info shmem_backing_dev_info __read_mostly = { .ra_pages = 0, /* No readahead */ - .memory_backed = 1, /* Does not contribute to dirty memory */ - .unplug_io_fn = default_unplug_io_fn, + .capabilities = BDI_CAP_NO_ACCT_DIRTY | BDI_CAP_NO_WRITEBACK, + .unplug_io_fn = default_unplug_io_fn, }; -LIST_HEAD(shmem_inodes); -static spinlock_t shmem_ilock = SPIN_LOCK_UNLOCKED; +static LIST_HEAD(shmem_swaplist); +static DEFINE_SPINLOCK(shmem_swaplist_lock); -static void shmem_free_block(struct inode *inode) +static void shmem_free_blocks(struct inode *inode, long pages) { struct shmem_sb_info *sbinfo = SHMEM_SB(inode->i_sb); - spin_lock(&sbinfo->stat_lock); - sbinfo->free_blocks++; - inode->i_blocks -= BLOCKS_PER_PAGE; - spin_unlock(&sbinfo->stat_lock); + if (sbinfo->max_blocks) { + spin_lock(&sbinfo->stat_lock); + sbinfo->free_blocks += pages; + inode->i_blocks -= pages*BLOCKS_PER_PAGE; + spin_unlock(&sbinfo->stat_lock); + } } /* @@ -208,13 +222,9 @@ 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); info->alloced -= freed; - spin_lock(&sbinfo->stat_lock); - sbinfo->free_blocks += freed; - inode->i_blocks -= freed*BLOCKS_PER_PAGE; - spin_unlock(&sbinfo->stat_lock); shmem_unacct_blocks(info->flags, freed); + shmem_free_blocks(inode, freed); } } @@ -262,8 +272,10 @@ static swp_entry_t *shmem_swp_entry(struct shmem_inode_info *info, unsigned long struct page **dir; struct page *subdir; - if (index < SHMEM_NR_DIRECT) + if (index < SHMEM_NR_DIRECT) { + shmem_swp_balance_unmap(); return info->i_direct+index; + } if (!info->i_indirect) { if (page) { info->i_indirect = *page; @@ -305,17 +317,7 @@ static swp_entry_t *shmem_swp_entry(struct shmem_inode_info *info, unsigned long *page = NULL; } shmem_dir_unmap(dir); - - /* - * With apologies... caller shmem_swp_alloc passes non-NULL - * page (though perhaps NULL *page); and now we know that this - * indirect page has been allocated, we can shortcut the final - * kmap if we know it contains no swap entries, as is commonly - * the case: return pointer to a 0 which doesn't need kmapping. - */ - return (page && !subdir->nr_swapped)? - (swp_entry_t *)&subdir->nr_swapped: - shmem_swp_map(subdir) + offset; + return shmem_swp_map(subdir) + offset; } static void shmem_swp_set(struct shmem_inode_info *info, swp_entry_t *entry, unsigned long value) @@ -324,8 +326,10 @@ 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); + } } /* @@ -342,7 +346,6 @@ static swp_entry_t *shmem_swp_alloc(struct shmem_inode_info *info, unsigned long struct shmem_sb_info *sbinfo = SHMEM_SB(inode->i_sb); struct page *page = NULL; swp_entry_t *entry; - static const swp_entry_t unswapped = { 0 }; if (sgp != SGP_WRITE && ((loff_t) index << PAGE_CACHE_SHIFT) >= i_size_read(inode)) @@ -350,31 +353,31 @@ static swp_entry_t *shmem_swp_alloc(struct shmem_inode_info *info, unsigned long while (!(entry = shmem_swp_entry(info, index, &page))) { if (sgp == SGP_READ) - return (swp_entry_t *) &unswapped; + return shmem_swp_map(ZERO_PAGE(0)); /* * 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. */ - spin_lock(&sbinfo->stat_lock); - if (sbinfo->free_blocks <= 1) { + 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); - 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)); - if (page) { - clear_highpage(page); - page->nr_swapped = 0; - } + 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_block(inode); + shmem_free_blocks(inode, 1); return ERR_PTR(-ENOMEM); } if (sgp != SGP_WRITE && @@ -387,7 +390,7 @@ static swp_entry_t *shmem_swp_alloc(struct shmem_inode_info *info, unsigned long } if (page) { /* another task gave its page, or truncated the file */ - shmem_free_block(inode); + shmem_free_blocks(inode, 1); shmem_dir_free(page); } if (info->next_index <= index && !IS_ERR(entry)) @@ -398,93 +401,209 @@ static swp_entry_t *shmem_swp_alloc(struct shmem_inode_info *info, unsigned long /* * 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 void shmem_truncate(struct inode *inode) +static int shmem_map_and_free_swp(struct page *subdir, int offset, + int limit, struct page ***dir, spinlock_t *punch_lock) +{ + swp_entry_t *ptr; + int freed = 0; + + ptr = shmem_swp_map(subdir); + for (; offset < limit; offset += LATENCY_LIMIT) { + int size = limit - offset; + if (size > LATENCY_LIMIT) + size = LATENCY_LIMIT; + freed += shmem_free_swp(ptr+offset, ptr+offset+size, + punch_lock); + if (need_resched()) { + shmem_swp_unmap(ptr); + if (*dir) { + shmem_dir_unmap(*dir); + *dir = NULL; + } + cond_resched(); + ptr = shmem_swp_map(subdir); + } + } + shmem_swp_unmap(ptr); + return freed; +} + +static 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; + } + } while (next); +} + +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; unsigned long size; unsigned long limit; unsigned long stage; + unsigned long diroff; struct page **dir; + struct page *topdir; + struct page *middir; struct page *subdir; - struct page *empty; swp_entry_t *ptr; + LIST_HEAD(pages_to_free); + long nr_pages_to_free = 0; + 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 && !punch_hole) { + info->i_indirect = NULL; + nr_pages_to_free++; + list_add(&topdir->lru, &pages_to_free); + } + spin_unlock(&info->lock); + if (info->swapped && idx < SHMEM_NR_DIRECT) { ptr = info->i_direct; size = limit; if (size > SHMEM_NR_DIRECT) size = SHMEM_NR_DIRECT; - info->swapped -= shmem_free_swp(ptr+idx, ptr+size); + nr_swaps_freed = shmem_free_swp(ptr+idx, ptr+size, needs_lock); } - if (!info->i_indirect) + + /* + * 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; idx -= offset; - empty = NULL; - dir = shmem_dir_map(info->i_indirect); + dir = shmem_dir_map(topdir); stage = ENTRIES_PER_PAGEPAGE/2; - if (idx < ENTRIES_PER_PAGEPAGE/2) - dir += idx/ENTRIES_PER_PAGE; - else { + 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) { - subdir = *dir; - size = ((idx - ENTRIES_PER_PAGEPAGE/2) % + diroff = ((idx - ENTRIES_PER_PAGEPAGE/2) % ENTRIES_PER_PAGEPAGE) / ENTRIES_PER_PAGE; - if (!size && !offset) { - empty = subdir; - *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); } shmem_dir_unmap(dir); - dir = shmem_dir_map(subdir) + size; + dir = shmem_dir_map(middir); } else { + diroff = 0; offset = 0; idx = stage; } } - for (; idx < limit; idx += ENTRIES_PER_PAGE, dir++) { + for (; idx < limit; idx += ENTRIES_PER_PAGE, diroff++) { if (unlikely(idx == stage)) { - shmem_dir_unmap(dir-1); - dir = shmem_dir_map(info->i_indirect) + + shmem_dir_unmap(dir); + dir = shmem_dir_map(topdir) + ENTRIES_PER_PAGE/2 + idx/ENTRIES_PER_PAGEPAGE; while (!*dir) { dir++; @@ -493,50 +612,60 @@ static void shmem_truncate(struct inode *inode) goto done1; } stage = idx + ENTRIES_PER_PAGEPAGE; - subdir = *dir; - *dir = NULL; - shmem_dir_unmap(dir); - if (empty) { - shmem_dir_free(empty); - shmem_free_block(inode); + middir = *dir; + if (punch_hole) + needs_lock = &info->lock; + if (upper_limit >= stage) { + if (needs_lock) { + spin_lock(needs_lock); + *dir = NULL; + spin_unlock(needs_lock); + needs_lock = NULL; + } else + *dir = NULL; + nr_pages_to_free++; + list_add(&middir->lru, &pages_to_free); } - empty = subdir; - cond_resched_lock(&info->lock); - dir = shmem_dir_map(subdir); + shmem_dir_unmap(dir); + cond_resched(); + dir = shmem_dir_map(middir); + diroff = 0; } - subdir = *dir; - if (subdir && subdir->nr_swapped) { - ptr = shmem_swp_map(subdir); + punch_lock = needs_lock; + subdir = dir[diroff]; + if (subdir && !offset && upper_limit-idx >= ENTRIES_PER_PAGE) { + if (needs_lock) { + spin_lock(needs_lock); + dir[diroff] = NULL; + spin_unlock(needs_lock); + punch_lock = NULL; + } else + dir[diroff] = NULL; + nr_pages_to_free++; + list_add(&subdir->lru, &pages_to_free); + } + if (subdir && page_private(subdir) /* has swap entries */) { size = limit - idx; if (size > ENTRIES_PER_PAGE) size = ENTRIES_PER_PAGE; - freed = shmem_free_swp(ptr+offset, ptr+size); - shmem_swp_unmap(ptr); - info->swapped -= freed; - subdir->nr_swapped -= freed; - BUG_ON(subdir->nr_swapped > offset); - } - if (offset) - offset = 0; - else if (subdir) { - *dir = NULL; - shmem_dir_free(subdir); - shmem_free_block(inode); + freed = shmem_map_and_free_swp(subdir, + offset, size, &dir, punch_lock); + if (!dir) + dir = shmem_dir_map(middir); + nr_swaps_freed += freed; + if (offset || punch_lock) { + spin_lock(&info->lock); + set_page_private(subdir, + page_private(subdir) - freed); + spin_unlock(&info->lock); + } else + BUG_ON(page_private(subdir) != freed); } + offset = 0; } done1: - shmem_dir_unmap(dir-1); - if (empty) { - shmem_dir_free(empty); - shmem_free_block(inode); - } - if (info->next_index <= SHMEM_NR_DIRECT) { - shmem_dir_free(info->i_indirect); - info->i_indirect = NULL; - shmem_free_block(inode); - } + shmem_dir_unmap(dir); done2: - BUG_ON(info->swapped > info->next_index); if (inode->i_mapping->nrpages && (info->flags & SHMEM_PAGEIN)) { /* * Call truncate_inode_pages again: racing shmem_unuse_inode @@ -544,14 +673,38 @@ 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. */ - spin_unlock(&info->lock); - truncate_inode_pages(inode->i_mapping, inode->i_size); - spin_lock(&info->lock); + 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); 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); + } +} + +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) @@ -560,7 +713,7 @@ static int shmem_notify_change(struct dentry *dentry, struct iattr *attr) 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 @@ -593,6 +746,10 @@ 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, &shmem_acl_ops); +#endif if (page) page_cache_release(page); return error; @@ -604,17 +761,22 @@ static void shmem_delete_inode(struct inode *inode) struct shmem_inode_info *info = SHMEM_I(inode); if (inode->i_op->truncate == shmem_truncate) { - spin_lock(&shmem_ilock); - list_del(&info->list); - spin_unlock(&shmem_ilock); + truncate_inode_pages(inode->i_mapping, 0); shmem_unacct_size(info->flags, inode->i_size); inode->i_size = 0; shmem_truncate(inode); + if (!list_empty(&info->swaplist)) { + spin_lock(&shmem_swaplist_lock); + list_del_init(&info->swaplist); + spin_unlock(&shmem_swaplist_lock); + } } BUG_ON(inode->i_blocks); - spin_lock(&sbinfo->stat_lock); - sbinfo->free_inodes++; - spin_unlock(&sbinfo->stat_lock); + if (sbinfo->max_inodes) { + spin_lock(&sbinfo->stat_lock); + sbinfo->free_inodes++; + spin_unlock(&sbinfo->stat_lock); + } clear_inode(inode); } @@ -649,13 +811,12 @@ static int shmem_unuse_inode(struct shmem_inode_info *info, swp_entry_t entry, s if (size > SHMEM_NR_DIRECT) size = SHMEM_NR_DIRECT; offset = shmem_find_swp(entry, ptr, ptr+size); - if (offset >= 0) + if (offset >= 0) { + shmem_swp_balance_unmap(); goto found; + } if (!info->i_indirect) goto lost2; - /* we might be racing with shmem_truncate */ - if (limit <= SHMEM_NR_DIRECT) - goto lost2; dir = shmem_dir_map(info->i_indirect); stage = SHMEM_NR_DIRECT + ENTRIES_PER_PAGEPAGE/2; @@ -677,7 +838,7 @@ 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) @@ -717,22 +878,23 @@ found: */ int shmem_unuse(swp_entry_t entry, struct page *page) { - struct list_head *p; + struct list_head *p, *next; struct shmem_inode_info *info; int found = 0; - spin_lock(&shmem_ilock); - list_for_each(p, &shmem_inodes) { - info = list_entry(p, struct shmem_inode_info, list); - - if (info->swapped && shmem_unuse_inode(info, entry, page)) { + 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) + 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_inodes, &info->list); + list_move_tail(&shmem_swaplist, &info->swaplist); found = 1; break; } } - spin_unlock(&shmem_ilock); + spin_unlock(&shmem_swaplist_lock); return found; } @@ -774,6 +936,12 @@ static int shmem_writepage(struct page *page, struct writeback_control *wbc) shmem_swp_set(info, entry, swap.val); shmem_swp_unmap(entry); 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); return 0; } @@ -784,10 +952,55 @@ unlock: swap_free(swap); redirty: set_page_dirty(page); - return WRITEPAGE_ACTIVATE; /* Return with the page locked */ + return AOP_WRITEPAGE_ACTIVATE; /* Return with the page locked */ } #ifdef CONFIG_NUMA +static inline int shmem_parse_mpol(char *value, int *policy, nodemask_t *policy_nodes) +{ + char *nodelist = strchr(value, ':'); + int err = 1; + + if (nodelist) { + /* NUL-terminate policy string */ + *nodelist++ = '\0'; + if (nodelist_parse(nodelist, *policy_nodes)) + goto out; + } + if (!strcmp(value, "default")) { + *policy = MPOL_DEFAULT; + /* Don't allow a nodelist */ + if (!nodelist) + err = 0; + } else if (!strcmp(value, "prefer")) { + *policy = MPOL_PREFERRED; + /* Insist on a nodelist of one node only */ + if (nodelist) { + char *rest = nodelist; + while (isdigit(*rest)) + rest++; + if (!*rest) + err = 0; + } + } else if (!strcmp(value, "bind")) { + *policy = MPOL_BIND; + /* Insist on a nodelist */ + if (nodelist) + err = 0; + } else if (!strcmp(value, "interleave")) { + *policy = MPOL_INTERLEAVE; + /* Default to nodes online if no nodelist */ + if (!nodelist) + *policy_nodes = node_online_map; + err = 0; + } +out: + /* Restore string for error message */ + if (nodelist) + *--nodelist = ':'; + return err; +} + static struct page *shmem_swapin_async(struct shared_policy *p, swp_entry_t entry, unsigned long idx) { @@ -825,7 +1038,7 @@ struct page *shmem_swapin(struct shmem_inode_info *info, swp_entry_t entry, } static struct page * -shmem_alloc_page(unsigned long gfp, struct shmem_inode_info *info, +shmem_alloc_page(gfp_t gfp, struct shmem_inode_info *info, unsigned long idx) { struct vm_area_struct pvma; @@ -835,11 +1048,16 @@ shmem_alloc_page(unsigned long gfp, struct shmem_inode_info *info, pvma.vm_policy = mpol_shared_policy_lookup(&info->policy, idx); pvma.vm_pgoff = idx; pvma.vm_end = PAGE_SIZE; - page = alloc_page_vma(gfp, &pvma, 0); + page = alloc_page_vma(gfp | __GFP_ZERO, &pvma, 0); mpol_free(pvma.vm_policy); return page; } #else +static inline int shmem_parse_mpol(char *value, int *policy, nodemask_t *policy_nodes) +{ + return 1; +} + static inline struct page * shmem_swapin(struct shmem_inode_info *info,swp_entry_t entry,unsigned long idx) { @@ -848,10 +1066,9 @@ shmem_swapin(struct shmem_inode_info *info,swp_entry_t entry,unsigned long idx) } static inline struct page * -shmem_alloc_page(unsigned long gfp,struct shmem_inode_info *info, - unsigned long idx) +shmem_alloc_page(gfp_t gfp,struct shmem_inode_info *info, unsigned long idx) { - return alloc_page(gfp); + return alloc_page(gfp | __GFP_ZERO); } #endif @@ -872,7 +1089,7 @@ static int shmem_getpage(struct inode *inode, unsigned long idx, struct page *swappage; swp_entry_t *entry; swp_entry_t swap; - int error, majmin = VM_FAULT_MINOR; + int error; if (idx >= SHMEM_MAX_INDEX) return -EFBIG; @@ -908,11 +1125,12 @@ repeat: swappage = lookup_swap_cache(swap); if (!swappage) { shmem_swp_unmap(entry); - spin_unlock(&info->lock); /* here we actually do the io */ - if (majmin == VM_FAULT_MINOR && type) - inc_page_state(pgmajfault); - majmin = VM_FAULT_MAJOR; + if (type && *type == VM_FAULT_MINOR) { + __count_vm_event(PGMAJFAULT); + *type = VM_FAULT_MAJOR; + } + spin_unlock(&info->lock); swappage = shmem_swapin(info, swap, idx); if (!swappage) { spin_lock(&info->lock); @@ -986,7 +1204,7 @@ repeat: page_cache_release(swappage); if (error == -ENOMEM) { /* let kswapd refresh zone for GFP_ATOMICs */ - blk_congestion_wait(WRITE, HZ/50); + congestion_wait(WRITE, HZ/50); } goto repeat; } @@ -1005,16 +1223,23 @@ repeat: } else { shmem_swp_unmap(entry); sbinfo = SHMEM_SB(inode->i_sb); - spin_lock(&sbinfo->stat_lock); - if (sbinfo->free_blocks == 0 || shmem_acct_block(info->flags)) { + 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); + error = -ENOSPC; + goto failed; + } + 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; } - sbinfo->free_blocks--; - inode->i_blocks += BLOCKS_PER_PAGE; - spin_unlock(&sbinfo->stat_lock); if (!filepage) { spin_unlock(&info->lock); @@ -1023,7 +1248,7 @@ repeat: idx); if (!filepage) { shmem_unacct_blocks(info->flags, 1); - shmem_free_block(inode); + shmem_free_blocks(inode, 1); error = -ENOMEM; goto failed; } @@ -1041,7 +1266,7 @@ repeat: spin_unlock(&info->lock); page_cache_release(filepage); shmem_unacct_blocks(info->flags, 1); - shmem_free_block(inode); + shmem_free_blocks(inode, 1); filepage = NULL; if (error) goto failed; @@ -1052,20 +1277,14 @@ repeat: info->alloced++; spin_unlock(&info->lock); - clear_highpage(filepage); flush_dcache_page(filepage); SetPageUptodate(filepage); } done: - if (!*pagep) { - if (filepage) { - unlock_page(filepage); - *pagep = filepage; - } else - *pagep = ZERO_PAGE(0); + if (*pagep != filepage) { + unlock_page(filepage); + *pagep = filepage; } - if (type) - *type = majmin; return 0; failed: @@ -1078,7 +1297,7 @@ failed: struct page *shmem_nopage(struct vm_area_struct *vma, unsigned long address, int *type) { - struct inode *inode = vma->vm_file->f_dentry->d_inode; + struct inode *inode = vma->vm_file->f_path.dentry->d_inode; struct page *page = NULL; unsigned long idx; int error; @@ -1086,6 +1305,8 @@ struct page *shmem_nopage(struct vm_area_struct *vma, unsigned long address, int 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) @@ -1099,7 +1320,7 @@ 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 inode *inode = vma->vm_file->f_path.dentry->d_inode; struct mm_struct *mm = vma->vm_mm; enum sgp_type sgp = nonblock? SGP_QUICK: SGP_CACHE; unsigned long size; @@ -1117,6 +1338,7 @@ static int shmem_populate(struct vm_area_struct *vma, 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); @@ -1124,16 +1346,13 @@ static int shmem_populate(struct vm_area_struct *vma, page_cache_release(page); return err; } - } else if (nonblock) { - /* - * If a nonlinear mapping then store the file page - * offset in the pte. - */ - if (pgoff != linear_page_index(vma, addr)) { - err = install_file_pte(mm, vma, addr, pgoff, prot); - if (err) - 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; @@ -1146,14 +1365,14 @@ static int shmem_populate(struct vm_area_struct *vma, #ifdef CONFIG_NUMA 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) { - 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; @@ -1161,39 +1380,29 @@ shmem_get_policy(struct vm_area_struct *vma, unsigned long addr) } #endif -int shmem_lock(struct file *file, int lock) +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); - struct mm_struct *mm = current->mm; - unsigned long lock_limit, locked; int retval = -ENOMEM; spin_lock(&info->lock); if (lock && !(info->flags & VM_LOCKED)) { - locked = inode->i_size >> PAGE_SHIFT; - locked += mm->locked_vm; - lock_limit = current->rlim[RLIMIT_MEMLOCK].rlim_cur; - lock_limit >>= PAGE_SHIFT; - if ((locked > lock_limit) && !capable(CAP_IPC_LOCK)) + if (!user_shm_lock(inode->i_size, user)) goto out_nomem; - mm->locked_vm = locked; - } - if (!lock && (info->flags & VM_LOCKED) && mm) { - locked = inode->i_size >> PAGE_SHIFT; - mm->locked_vm -= locked; - } - if (lock) info->flags |= VM_LOCKED; - else + } + if (!lock && (info->flags & VM_LOCKED) && user) { + user_shm_unlock(inode->i_size, user); info->flags &= ~VM_LOCKED; + } retval = 0; out_nomem: spin_unlock(&info->lock); return retval; } -static int shmem_mmap(struct file *file, struct vm_area_struct *vma) +int shmem_mmap(struct file *file, struct vm_area_struct *vma) { file_accessed(file); vma->vm_ops = &shmem_vm_ops; @@ -1207,79 +1416,67 @@ shmem_get_inode(struct super_block *sb, int mode, dev_t dev) struct shmem_inode_info *info; struct shmem_sb_info *sbinfo = SHMEM_SB(sb); - spin_lock(&sbinfo->stat_lock); - if (!sbinfo->free_inodes) { + 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); - return NULL; } - sbinfo->free_inodes--; - spin_unlock(&sbinfo->stat_lock); 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_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); - mpol_shared_policy_init(&info->policy); + INIT_LIST_HEAD(&info->swaplist); + switch (mode & S_IFMT) { default: + inode->i_op = &shmem_special_inode_operations; init_special_inode(inode, mode, dev); break; case S_IFREG: inode->i_op = &shmem_inode_operations; inode->i_fop = &shmem_file_operations; - spin_lock(&shmem_ilock); - list_add_tail(&info->list, &shmem_inodes); - spin_unlock(&shmem_ilock); + mpol_shared_policy_init(&info->policy, sbinfo->policy, + &sbinfo->policy_nodes); 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; inode->i_fop = &simple_dir_operations; break; case S_IFLNK: + /* + * Must not load anything in the rbtree, + * mpol_free_shared_policy will not be called. + */ + mpol_shared_policy_init(&info->policy, MPOL_DEFAULT, + NULL); break; } + } else if (sbinfo->max_inodes) { + spin_lock(&sbinfo->stat_lock); + sbinfo->free_inodes++; + spin_unlock(&sbinfo->stat_lock); } return inode; } -static int shmem_set_size(struct shmem_sb_info *info, - unsigned long max_blocks, unsigned long max_inodes) -{ - int error; - unsigned long blocks, inodes; - - spin_lock(&info->stat_lock); - blocks = info->max_blocks - info->free_blocks; - inodes = info->max_inodes - info->free_inodes; - error = -EINVAL; - if (max_blocks < blocks) - goto out; - if (max_inodes < inodes) - goto out; - error = 0; - info->max_blocks = max_blocks; - info->free_blocks = max_blocks - blocks; - info->max_inodes = max_inodes; - info->free_inodes = max_inodes - inodes; -out: - spin_unlock(&info->stat_lock); - return error; -} - #ifdef CONFIG_TMPFS - static struct inode_operations shmem_symlink_inode_operations; static struct inode_operations shmem_symlink_inline_operations; @@ -1297,10 +1494,10 @@ shmem_prepare_write(struct file *file, struct page *page, unsigned offset, unsig static ssize_t shmem_file_write(struct file *file, const char __user *buf, size_t count, loff_t *ppos) { - struct inode *inode = file->f_dentry->d_inode; + struct inode *inode = file->f_path.dentry->d_inode; loff_t pos; unsigned long written; - int err; + ssize_t err; if ((ssize_t) count < 0) return -EINVAL; @@ -1308,7 +1505,7 @@ shmem_file_write(struct file *file, const char __user *buf, size_t count, loff_t if (!access_ok(VERIFY_READ, buf, count)) return -EFAULT; - down(&inode->i_sem); + mutex_lock(&inode->i_mutex); pos = *ppos; written = 0; @@ -1317,7 +1514,7 @@ shmem_file_write(struct file *file, const char __user *buf, size_t count, loff_t if (err || !count) goto out; - err = remove_suid(file->f_dentry); + err = remove_suid(file->f_path.dentry); if (err) goto out; @@ -1352,7 +1549,8 @@ shmem_file_write(struct file *file, const char __user *buf, size_t count, loff_t __get_user(dummy, buf + bytes - 1); kaddr = kmap_atomic(page, KM_USER0); - left = __copy_from_user(kaddr + offset, buf, bytes); + left = __copy_from_user_inatomic(kaddr + offset, + buf, bytes); kunmap_atomic(kaddr, KM_USER0); } if (left) { @@ -1392,13 +1590,13 @@ shmem_file_write(struct file *file, const char __user *buf, size_t count, loff_t if (written) err = written; out: - up(&inode->i_sem); + mutex_unlock(&inode->i_mutex); return err; } 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; @@ -1428,7 +1626,7 @@ static void do_shmem_file_read(struct file *filp, loff_t *ppos, read_descriptor_ /* * 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); @@ -1436,13 +1634,14 @@ static void do_shmem_file_read(struct file *filp, loff_t *ppos, read_descriptor_ if (index == end_index) { nr = i_size & ~PAGE_CACHE_MASK; if (nr <= offset) { - page_cache_release(page); + if (page) + page_cache_release(page); break; } } nr -= offset; - if (page != ZERO_PAGE(0)) { + if (page) { /* * If users can be writing to this page using arbitrary * virtual addresses, take care about potential aliasing @@ -1455,6 +1654,9 @@ static void do_shmem_file_read(struct file *filp, loff_t *ppos, read_descriptor_ */ if (!offset) mark_page_accessed(page); + } else { + page = ZERO_PAGE(0); + page_cache_get(page); } /* @@ -1496,7 +1698,7 @@ static ssize_t shmem_file_read(struct file *filp, char __user *buf, size_t count desc.written = 0; desc.count = count; - desc.buf = buf; + desc.arg.buf = buf; desc.error = 0; do_shmem_file_read(filp, ppos, &desc, file_read_actor); @@ -1506,7 +1708,7 @@ static ssize_t shmem_file_read(struct file *filp, char __user *buf, size_t count } static ssize_t shmem_file_sendfile(struct file *in_file, loff_t *ppos, - size_t count, read_actor_t actor, void __user *target) + size_t count, read_actor_t actor, void *target) { read_descriptor_t desc; @@ -1515,7 +1717,7 @@ static ssize_t shmem_file_sendfile(struct file *in_file, loff_t *ppos, desc.written = 0; desc.count = count; - desc.buf = target; + desc.arg.data = target; desc.error = 0; do_shmem_file_read(in_file, ppos, &desc, actor); @@ -1524,19 +1726,24 @@ static ssize_t shmem_file_sendfile(struct file *in_file, loff_t *ppos, return desc.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_type = TMPFS_SUPER_MAGIC; buf->f_bsize = PAGE_CACHE_SIZE; + buf->f_namelen = NAME_MAX; spin_lock(&sbinfo->stat_lock); - buf->f_blocks = sbinfo->max_blocks; - buf->f_bavail = buf->f_bfree = sbinfo->free_blocks; - buf->f_files = sbinfo->max_inodes; - buf->f_ffree = sbinfo->free_inodes; + if (sbinfo->max_blocks) { + buf->f_blocks = sbinfo->max_blocks; + buf->f_bavail = buf->f_bfree = sbinfo->free_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); - buf->f_namelen = NAME_MAX; return 0; } @@ -1550,6 +1757,19 @@ shmem_mknod(struct inode *dir, struct dentry *dentry, int mode, dev_t dev) int error = -ENOSPC; if (inode) { + error = security_inode_init_security(inode, dir, NULL, NULL, + NULL); + if (error) { + if (error != -EOPNOTSUPP) { + iput(inode); + return error; + } + } + error = shmem_acl_init(inode, dir); + if (error) { + iput(inode); + return error; + } if (dir->i_mode & S_ISGID) { inode->i_gid = dir->i_gid; if (S_ISDIR(mode)) @@ -1559,7 +1779,6 @@ shmem_mknod(struct inode *dir, struct dentry *dentry, int mode, dev_t dev) dir->i_ctime = dir->i_mtime = CURRENT_TIME; d_instantiate(dentry, inode); dget(dentry); /* Extra count - pin the dentry in core */ - error = 0; } return error; } @@ -1570,7 +1789,7 @@ 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; } @@ -1586,10 +1805,26 @@ 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); + + /* + * 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); + } 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); @@ -1600,9 +1835,18 @@ 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); + } + } + 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; } @@ -1612,7 +1856,8 @@ 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); } @@ -1633,10 +1878,10 @@ 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; @@ -1664,6 +1909,16 @@ static int shmem_symlink(struct inode *dir, struct dentry *dentry, const char *s if (!inode) return -ENOSPC; + error = security_inode_init_security(inode, dir, NULL, NULL, + NULL); + if (error) { + if (error != -EOPNOTSUPP) { + iput(inode); + return error; + } + error = 0; + } + info = SHMEM_I(inode); inode->i_size = len-1; if (len <= (char *)inode - (char *)info) { @@ -1677,9 +1932,6 @@ static int shmem_symlink(struct inode *dir, struct dentry *dentry, const char *s return error; } inode->i_op = &shmem_symlink_inode_operations; - spin_lock(&shmem_ilock); - list_add_tail(&info->list, &shmem_inodes); - spin_unlock(&shmem_ilock); kaddr = kmap_atomic(page, KM_USER0); memcpy(kaddr, symname, len); kunmap_atomic(kaddr, KM_USER0); @@ -1695,32 +1947,27 @@ static int shmem_symlink(struct inode *dir, struct dentry *dentry, const char *s return 0; } -static int shmem_follow_link_inline(struct dentry *dentry, struct nameidata *nd) +static void *shmem_follow_link_inline(struct dentry *dentry, struct nameidata *nd) { nd_set_link(nd, (char *)SHMEM_I(dentry->d_inode)); - return 0; + return NULL; } -static int shmem_follow_link(struct dentry *dentry, struct nameidata *nd) +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)); - return 0; + return page; } -static void shmem_put_link(struct dentry *dentry, struct nameidata *nd) +static void shmem_put_link(struct dentry *dentry, struct nameidata *nd, void *cookie) { if (!IS_ERR(nd_get_link(nd))) { - struct page *page; - - page = find_get_page(dentry->d_inode->i_mapping, 0); - if (!page) - BUG(); + struct page *page = cookie; kunmap(page); mark_page_accessed(page); page_cache_release(page); - page_cache_release(page); } } @@ -1736,11 +1983,155 @@ static struct inode_operations shmem_symlink_inode_operations = { .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 inode *inode, char *list, + size_t list_len, const char *name, + size_t name_len) +{ + return security_inode_listsecurity(inode, list, list_len); +} + +static int shmem_xattr_security_get(struct inode *inode, const char *name, + void *buffer, size_t size) +{ + if (strcmp(name, "") == 0) + return -EINVAL; + return security_inode_getsecurity(inode, name, buffer, size, + -EOPNOTSUPP); +} + +static int shmem_xattr_security_set(struct inode *inode, const char *name, + const void *value, size_t size, int flags) +{ + if (strcmp(name, "") == 0) + return -EINVAL; + return security_inode_setsecurity(inode, name, value, size, flags); +} + +static 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 struct xattr_handler *shmem_xattr_handlers[] = { + &shmem_xattr_acl_access_handler, + &shmem_xattr_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_get_dentry(struct super_block *sb, void *vfh) +{ + struct dentry *de = NULL; + struct inode *inode; + __u32 *fh = vfh; + __u64 inum = fh[2]; + inum = (inum << 32) | fh[1]; + + inode = ilookup5(sb, (unsigned long)(inum+fh[0]), shmem_match, vfh); + if (inode) { + de = d_find_alias(inode); + iput(inode); + } + + return de? de: ERR_PTR(-ESTALE); +} + +static struct dentry *shmem_decode_fh(struct super_block *sb, __u32 *fh, + int len, int type, + int (*acceptable)(void *context, struct dentry *de), + void *context) +{ + if (len < 3) + return ERR_PTR(-ESTALE); + + return sb->s_export_op->find_exported_dentry(sb, fh, NULL, acceptable, + context); +} + +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 struct export_operations shmem_export_ops = { + .get_parent = shmem_get_parent, + .get_dentry = shmem_get_dentry, + .encode_fh = shmem_encode_fh, + .decode_fh = shmem_decode_fh, +}; + +static int shmem_parse_options(char *options, int *mode, uid_t *uid, + gid_t *gid, unsigned long *blocks, unsigned long *inodes, + int *policy, nodemask_t *policy_nodes) { 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) { @@ -1790,6 +2181,9 @@ static int shmem_parse_options(char *options, int *mode, uid_t *uid, gid_t *gid, *gid = simple_strtoul(value,&rest,0); if (*rest) goto bad_val; + } else if (!strcmp(this_char,"mpol")) { + if (shmem_parse_mpol(value,policy,policy_nodes)) + goto bad_val; } else { printk(KERN_ERR "tmpfs: Bad mount option %s\n", this_char); @@ -1810,56 +2204,114 @@ 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; + int policy = sbinfo->policy; + nodemask_t policy_nodes = sbinfo->policy_nodes; + unsigned long blocks; + unsigned long inodes; + int error = -EINVAL; + + if (shmem_parse_options(data, NULL, NULL, NULL, &max_blocks, + &max_inodes, &policy, &policy_nodes)) + return error; - if (shmem_parse_options(data, NULL, NULL, NULL, &max_blocks, &max_inodes)) - return -EINVAL; - return shmem_set_size(sbinfo, max_blocks, max_inodes); + spin_lock(&sbinfo->stat_lock); + blocks = sbinfo->max_blocks - sbinfo->free_blocks; + inodes = sbinfo->max_inodes - sbinfo->free_inodes; + if (max_blocks < blocks) + goto out; + if (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; + * 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) + goto out; + if (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->policy = policy; + sbinfo->policy_nodes = policy_nodes; +out: + spin_unlock(&sbinfo->stat_lock); + return error; } #endif +static void shmem_put_super(struct super_block *sb) +{ + kfree(sb->s_fs_info); + sb->s_fs_info = NULL; +} + static int shmem_fill_super(struct super_block *sb, void *data, int silent) { struct inode *inode; struct dentry *root; - unsigned long blocks, inodes; int mode = S_IRWXUGO | S_ISVTX; uid_t uid = current->fsuid; gid_t gid = current->fsgid; - struct shmem_sb_info *sbinfo; int err = -ENOMEM; + struct shmem_sb_info *sbinfo; + unsigned long blocks = 0; + unsigned long inodes = 0; + int policy = MPOL_DEFAULT; + nodemask_t policy_nodes = node_online_map; - sbinfo = kmalloc(sizeof(struct shmem_sb_info), GFP_KERNEL); - if (!sbinfo) - return -ENOMEM; - sb->s_fs_info = sbinfo; - memset(sbinfo, 0, sizeof(struct shmem_sb_info)); - +#ifdef CONFIG_TMPFS /* * Per default we only allow half of the physical ram per - * tmpfs instance + * tmpfs instance, limiting inodes to one per page of lowmem; + * but the internal instance is left unlimited. */ - blocks = inodes = totalram_pages / 2; - -#ifdef CONFIG_TMPFS - if (shmem_parse_options(data, &mode, &uid, &gid, &blocks, &inodes)) { - err = -EINVAL; - goto failed; + 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, &policy, &policy_nodes)) + return -EINVAL; } + 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->policy = policy; + sbinfo->policy_nodes = policy_nodes; + + 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_magic = TMPFS_SUPER_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); if (!inode) goto failed; @@ -1874,23 +2326,16 @@ static int shmem_fill_super(struct super_block *sb, failed_iput: iput(inode); failed: - kfree(sbinfo); - sb->s_fs_info = NULL; + shmem_put_super(sb); return err; } -static void shmem_put_super(struct super_block *sb) -{ - kfree(sb->s_fs_info); - sb->s_fs_info = NULL; -} - -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; @@ -1898,17 +2343,26 @@ static struct inode *shmem_alloc_inode(struct super_block *sb) static void shmem_destroy_inode(struct inode *inode) { - mpol_free_shared_policy(&SHMEM_I(inode)->policy); + 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); + } + shmem_acl_destroy_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 kmem_cache *cachep, + unsigned long flags) { 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); +#ifdef CONFIG_TMPFS_POSIX_ACL + p->i_acl = NULL; + p->i_default_acl = NULL; +#endif } } @@ -1916,8 +2370,7 @@ static int init_inodecache(void) { shmem_inode_cachep = kmem_cache_create("shmem_inode_cache", sizeof(struct shmem_inode_info), - 0, SLAB_HWCACHE_ALIGN|SLAB_RECLAIM_ACCOUNT, - init_once, NULL); + 0, 0, init_once, NULL); if (shmem_inode_cachep == NULL) return -ENOMEM; return 0; @@ -1925,20 +2378,20 @@ static int init_inodecache(void) 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, #ifdef CONFIG_TMPFS .prepare_write = shmem_prepare_write, .commit_write = simple_commit_write, #endif + .migratepage = migrate_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, @@ -1952,6 +2405,15 @@ static struct file_operations shmem_file_operations = { static 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, + .permission = shmem_permission, +#endif + }; static struct inode_operations shmem_dir_inode_operations = { @@ -1966,6 +2428,25 @@ 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, + .permission = shmem_permission, +#endif +}; + +static 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, + .permission = shmem_permission, +#endif }; static struct super_operations shmem_ops = { @@ -1989,10 +2470,11 @@ static struct vm_operations_struct shmem_vm_ops = { #endif }; -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 = { @@ -2016,18 +2498,14 @@ 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 = kern_mount(&tmpfs_fs_type); + + 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); printk(KERN_ERR "Could not kern_mount tmpfs\n"); goto out1; } - - /* The internal instance should not do size checking */ - shmem_set_size(SHMEM_SB(shm_mnt->mnt_sb), ULONG_MAX, ULONG_MAX); return 0; out1: @@ -2058,7 +2536,7 @@ struct file *shmem_file_setup(char *name, loff_t size, unsigned long flags) if (IS_ERR(shm_mnt)) return (void *)shm_mnt; - if (size > SHMEM_MAX_BYTES) + if (size < 0 || size > SHMEM_MAX_BYTES) return ERR_PTR(-EINVAL); if (shmem_acct_size(flags, size)) @@ -2087,12 +2565,12 @@ struct file *shmem_file_setup(char *name, loff_t size, unsigned long flags) d_instantiate(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_path.mnt = mntget(shm_mnt); + file->f_path.dentry = dentry; file->f_mapping = inode->i_mapping; file->f_op = &shmem_file_operations; file->f_mode = FMODE_WRITE | FMODE_READ; - return(file); + return file; close_file: put_filp(file); @@ -2123,5 +2601,3 @@ int shmem_zero_setup(struct vm_area_struct *vma) vma->vm_ops = &shmem_vm_ops; return 0; } - -EXPORT_SYMBOL(shmem_file_setup);