X-Git-Url: http://ftp.safe.ca/?a=blobdiff_plain;f=fs%2Fbuffer.c;h=9f697419ed8e34ec041c92d8f6794c8b4b06ab33;hb=620565ef5f35f4196e5081417db381c16b0ae791;hp=9ece6c2086d0588c4a1e9f5bf276c5ca20df443d;hpb=637aff46f94a754207c80c8c64bf1b74f24b967d;p=safe%2Fjmp%2Flinux-2.6 diff --git a/fs/buffer.c b/fs/buffer.c index 9ece6c2..9f69741 100644 --- a/fs/buffer.c +++ b/fs/buffer.c @@ -67,17 +67,16 @@ static int sync_buffer(void *word) return 0; } -void fastcall __lock_buffer(struct buffer_head *bh) +void __lock_buffer(struct buffer_head *bh) { wait_on_bit_lock(&bh->b_state, BH_Lock, sync_buffer, TASK_UNINTERRUPTIBLE); } EXPORT_SYMBOL(__lock_buffer); -void fastcall unlock_buffer(struct buffer_head *bh) +void unlock_buffer(struct buffer_head *bh) { - smp_mb__before_clear_bit(); - clear_buffer_locked(bh); + clear_bit_unlock(BH_Lock, &bh->b_state); smp_mb__after_clear_bit(); wake_up_bit(&bh->b_state, BH_Lock); } @@ -100,10 +99,18 @@ __clear_page_buffers(struct page *page) page_cache_release(page); } + +static int quiet_error(struct buffer_head *bh) +{ + if (!test_bit(BH_Quiet, &bh->b_state) && printk_ratelimit()) + return 0; + return 1; +} + + static void buffer_io_error(struct buffer_head *bh) { char b[BDEVNAME_SIZE]; - printk(KERN_ERR "Buffer I/O error on device %s, logical block %Lu\n", bdevname(bh->b_bdev, b), (unsigned long long)bh->b_blocknr); @@ -145,7 +152,7 @@ void end_buffer_write_sync(struct buffer_head *bh, int uptodate) if (uptodate) { set_buffer_uptodate(bh); } else { - if (!buffer_eopnotsupp(bh) && printk_ratelimit()) { + if (!buffer_eopnotsupp(bh) && !quiet_error(bh)) { buffer_io_error(bh); printk(KERN_WARNING "lost page write due to " "I/O error on %s\n", @@ -196,10 +203,25 @@ int fsync_bdev(struct block_device *bdev) * happen on bdev until thaw_bdev() is called. * If a superblock is found on this device, we take the s_umount semaphore * on it to make sure nobody unmounts until the snapshot creation is done. + * The reference counter (bd_fsfreeze_count) guarantees that only the last + * unfreeze process can unfreeze the frozen filesystem actually when multiple + * freeze requests arrive simultaneously. It counts up in freeze_bdev() and + * count down in thaw_bdev(). When it becomes 0, thaw_bdev() will unfreeze + * actually. */ struct super_block *freeze_bdev(struct block_device *bdev) { struct super_block *sb; + int error = 0; + + mutex_lock(&bdev->bd_fsfreeze_mutex); + if (bdev->bd_fsfreeze_count > 0) { + bdev->bd_fsfreeze_count++; + sb = get_super(bdev); + mutex_unlock(&bdev->bd_fsfreeze_mutex); + return sb; + } + bdev->bd_fsfreeze_count++; down(&bdev->bd_mount_sem); sb = get_super(bdev); @@ -214,11 +236,24 @@ struct super_block *freeze_bdev(struct block_device *bdev) sync_blockdev(sb->s_bdev); - if (sb->s_op->write_super_lockfs) - sb->s_op->write_super_lockfs(sb); + if (sb->s_op->freeze_fs) { + error = sb->s_op->freeze_fs(sb); + if (error) { + printk(KERN_ERR + "VFS:Filesystem freeze failed\n"); + sb->s_frozen = SB_UNFROZEN; + drop_super(sb); + up(&bdev->bd_mount_sem); + bdev->bd_fsfreeze_count--; + mutex_unlock(&bdev->bd_fsfreeze_mutex); + return ERR_PTR(error); + } + } } sync_blockdev(bdev); + mutex_unlock(&bdev->bd_fsfreeze_mutex); + return sb; /* thaw_bdev releases s->s_umount and bd_mount_sem */ } EXPORT_SYMBOL(freeze_bdev); @@ -230,20 +265,48 @@ EXPORT_SYMBOL(freeze_bdev); * * Unlocks the filesystem and marks it writeable again after freeze_bdev(). */ -void thaw_bdev(struct block_device *bdev, struct super_block *sb) +int thaw_bdev(struct block_device *bdev, struct super_block *sb) { + int error = 0; + + mutex_lock(&bdev->bd_fsfreeze_mutex); + if (!bdev->bd_fsfreeze_count) { + mutex_unlock(&bdev->bd_fsfreeze_mutex); + return -EINVAL; + } + + bdev->bd_fsfreeze_count--; + if (bdev->bd_fsfreeze_count > 0) { + if (sb) + drop_super(sb); + mutex_unlock(&bdev->bd_fsfreeze_mutex); + return 0; + } + if (sb) { BUG_ON(sb->s_bdev != bdev); - - if (sb->s_op->unlockfs) - sb->s_op->unlockfs(sb); - sb->s_frozen = SB_UNFROZEN; - smp_wmb(); - wake_up(&sb->s_wait_unfrozen); + if (!(sb->s_flags & MS_RDONLY)) { + if (sb->s_op->unfreeze_fs) { + error = sb->s_op->unfreeze_fs(sb); + if (error) { + printk(KERN_ERR + "VFS:Filesystem thaw failed\n"); + sb->s_frozen = SB_FREEZE_TRANS; + bdev->bd_fsfreeze_count++; + mutex_unlock(&bdev->bd_fsfreeze_mutex); + return error; + } + } + sb->s_frozen = SB_UNFROZEN; + smp_wmb(); + wake_up(&sb->s_wait_unfrozen); + } drop_super(sb); } up(&bdev->bd_mount_sem); + mutex_unlock(&bdev->bd_fsfreeze_mutex); + return 0; } EXPORT_SYMBOL(thaw_bdev); @@ -360,16 +423,19 @@ void invalidate_bdev(struct block_device *bdev) */ static void free_more_memory(void) { - struct zone **zones; - pg_data_t *pgdat; + struct zone *zone; + int nid; wakeup_pdflush(1024); yield(); - for_each_online_pgdat(pgdat) { - zones = pgdat->node_zonelists[gfp_zone(GFP_NOFS)].zones; - if (*zones) - try_to_free_pages(zones, 0, GFP_NOFS); + for_each_online_node(nid) { + (void)first_zones_zonelist(node_zonelist(nid, GFP_NOFS), + gfp_zone(GFP_NOFS), NULL, + &zone); + if (zone) + try_to_free_pages(node_zonelist(nid, GFP_NOFS), 0, + GFP_NOFS); } } @@ -392,7 +458,7 @@ static void end_buffer_async_read(struct buffer_head *bh, int uptodate) set_buffer_uptodate(bh); } else { clear_buffer_uptodate(bh); - if (printk_ratelimit()) + if (!quiet_error(bh)) buffer_io_error(bh); SetPageError(page); } @@ -453,7 +519,7 @@ static void end_buffer_async_write(struct buffer_head *bh, int uptodate) if (uptodate) { set_buffer_uptodate(bh); } else { - if (printk_ratelimit()) { + if (!quiet_error(bh)) { buffer_io_error(bh); printk(KERN_WARNING "lost page write due to " "I/O error on %s\n", @@ -577,7 +643,7 @@ EXPORT_SYMBOL(mark_buffer_async_write); /* * The buffer's backing address_space's private_lock must be held */ -static inline void __remove_assoc_queue(struct buffer_head *bh) +static void __remove_assoc_queue(struct buffer_head *bh) { list_del_init(&bh->b_assoc_buffers); WARN_ON(!bh->b_assoc_map); @@ -627,8 +693,7 @@ repeat: } /** - * sync_mapping_buffers - write out and wait upon a mapping's "associated" - * buffers + * sync_mapping_buffers - write out & wait upon a mapping's "associated" buffers * @mapping: the mapping which wants those buffers written * * Starts I/O against the buffers at mapping->private_list, and waits upon @@ -678,7 +743,7 @@ void mark_buffer_dirty_inode(struct buffer_head *bh, struct inode *inode) } else { BUG_ON(mapping->assoc_mapping != buffer_mapping); } - if (list_empty(&bh->b_assoc_buffers)) { + if (!bh->b_assoc_map) { spin_lock(&buffer_mapping->private_lock); list_move_tail(&bh->b_assoc_buffers, &mapping->private_list); @@ -704,18 +769,21 @@ static int __set_page_dirty(struct page *page, if (TestSetPageDirty(page)) return 0; - write_lock_irq(&mapping->tree_lock); + spin_lock_irq(&mapping->tree_lock); if (page->mapping) { /* Race with truncate? */ WARN_ON_ONCE(warn && !PageUptodate(page)); if (mapping_cap_account_dirty(mapping)) { __inc_zone_page_state(page, NR_FILE_DIRTY); + __inc_bdi_stat(mapping->backing_dev_info, + BDI_RECLAIMABLE); + task_dirty_inc(current); task_io_account_write(PAGE_CACHE_SIZE); } radix_tree_tag_set(&mapping->page_tree, page_index(page), PAGECACHE_TAG_DIRTY); } - write_unlock_irq(&mapping->tree_lock); + spin_unlock_irq(&mapping->tree_lock); __mark_inode_dirty(mapping->host, I_DIRTY_PAGES); return 1; @@ -792,6 +860,7 @@ static int fsync_buffers_list(spinlock_t *lock, struct list_head *list) { struct buffer_head *bh; struct list_head tmp; + struct address_space *mapping; int err = 0, err2; INIT_LIST_HEAD(&tmp); @@ -799,9 +868,14 @@ static int fsync_buffers_list(spinlock_t *lock, struct list_head *list) spin_lock(lock); while (!list_empty(list)) { bh = BH_ENTRY(list->next); + mapping = bh->b_assoc_map; __remove_assoc_queue(bh); + /* Avoid race with mark_buffer_dirty_inode() which does + * a lockless check and we rely on seeing the dirty bit */ + smp_mb(); if (buffer_dirty(bh) || buffer_locked(bh)) { list_add(&bh->b_assoc_buffers, &tmp); + bh->b_assoc_map = mapping; if (buffer_dirty(bh)) { get_bh(bh); spin_unlock(lock); @@ -811,7 +885,7 @@ static int fsync_buffers_list(spinlock_t *lock, struct list_head *list) * contents - it is a noop if I/O is still in * flight on potentially older contents. */ - ll_rw_block(SWRITE, 1, &bh); + ll_rw_block(SWRITE_SYNC, 1, &bh); brelse(bh); spin_lock(lock); } @@ -820,8 +894,17 @@ static int fsync_buffers_list(spinlock_t *lock, struct list_head *list) while (!list_empty(&tmp)) { bh = BH_ENTRY(tmp.prev); - list_del_init(&bh->b_assoc_buffers); get_bh(bh); + mapping = bh->b_assoc_map; + __remove_assoc_queue(bh); + /* Avoid race with mark_buffer_dirty_inode() which does + * a lockless check and we rely on seeing the dirty bit */ + smp_mb(); + if (buffer_dirty(bh)) { + list_add(&bh->b_assoc_buffers, + &mapping->private_list); + bh->b_assoc_map = mapping; + } spin_unlock(lock); wait_on_buffer(bh); if (!buffer_uptodate(bh)) @@ -860,6 +943,7 @@ void invalidate_inode_buffers(struct inode *inode) spin_unlock(&buffer_mapping->private_lock); } } +EXPORT_SYMBOL(invalidate_inode_buffers); /* * Remove any clean buffers from the inode's buffer list. This is called @@ -1082,7 +1166,7 @@ grow_buffers(struct block_device *bdev, sector_t block, int size) printk(KERN_ERR "%s: requested out-of-range block %llu for " "device %s\n", - __FUNCTION__, (unsigned long long)block, + __func__, (unsigned long long)block, bdevname(bdev, b)); return -EIO; } @@ -1162,10 +1246,23 @@ __getblk_slow(struct block_device *bdev, sector_t block, int size) * mark_buffer_dirty() is atomic. It takes bh->b_page->mapping->private_lock, * mapping->tree_lock and the global inode_lock. */ -void fastcall mark_buffer_dirty(struct buffer_head *bh) +void mark_buffer_dirty(struct buffer_head *bh) { WARN_ON_ONCE(!buffer_uptodate(bh)); - if (!buffer_dirty(bh) && !test_set_buffer_dirty(bh)) + + /* + * Very *carefully* optimize the it-is-already-dirty case. + * + * Don't let the final "is it dirty" escape to before we + * perhaps modified the buffer. + */ + if (buffer_dirty(bh)) { + smp_mb(); + if (buffer_dirty(bh)) + return; + } + + if (!test_set_buffer_dirty(bh)) __set_page_dirty(bh->b_page, page_mapping(bh->b_page), 0); } @@ -1182,8 +1279,7 @@ void __brelse(struct buffer_head * buf) put_bh(buf); return; } - printk(KERN_ERR "VFS: brelse: Trying to free free buffer\n"); - WARN_ON(1); + WARN(1, KERN_ERR "VFS: brelse: Trying to free free buffer\n"); } /* @@ -1193,7 +1289,7 @@ void __brelse(struct buffer_head * buf) void __bforget(struct buffer_head *bh) { clear_buffer_dirty(bh); - if (!list_empty(&bh->b_assoc_buffers)) { + if (bh->b_assoc_map) { struct address_space *buffer_mapping = bh->b_page->mapping; spin_lock(&buffer_mapping->private_lock); @@ -1432,8 +1528,9 @@ static void invalidate_bh_lru(void *arg) void invalidate_bh_lrus(void) { - on_each_cpu(invalidate_bh_lru, NULL, 1, 1); + on_each_cpu(invalidate_bh_lru, NULL, 1); } +EXPORT_SYMBOL_GPL(invalidate_bh_lrus); void set_bh_page(struct buffer_head *bh, struct page *page, unsigned long offset) @@ -1658,11 +1755,13 @@ static int __block_write_full_page(struct inode *inode, struct page *page, */ clear_buffer_dirty(bh); set_buffer_uptodate(bh); - } else if (!buffer_mapped(bh) && buffer_dirty(bh)) { + } else if ((!buffer_mapped(bh) || buffer_delay(bh)) && + buffer_dirty(bh)) { WARN_ON(bh->b_size != blocksize); err = get_block(inode, block, bh, 1); if (err) goto recover; + clear_buffer_delay(bh); if (buffer_new(bh)) { /* blockdev mappings never come here */ clear_buffer_new(bh); @@ -1686,7 +1785,7 @@ static int __block_write_full_page(struct inode *inode, struct page *page, */ if (wbc->sync_mode != WB_SYNC_NONE || !wbc->nonblocking) { lock_buffer(bh); - } else if (test_set_buffer_locked(bh)) { + } else if (!trylock_buffer(bh)) { redirty_page_for_writepage(wbc, page); continue; } @@ -1728,7 +1827,6 @@ done: * The page and buffer_heads can be released at any time from * here on. */ - wbc->pages_skipped++; /* We didn't write this page */ } return err; @@ -1742,7 +1840,8 @@ recover: bh = head; /* Recovery: lock and submit the mapped buffers */ do { - if (buffer_mapped(bh) && buffer_dirty(bh)) { + if (buffer_mapped(bh) && buffer_dirty(bh) && + !buffer_delay(bh)) { lock_buffer(bh); mark_buffer_async_write(bh); } else { @@ -1770,6 +1869,48 @@ recover: goto done; } +/* + * If a page has any new buffers, zero them out here, and mark them uptodate + * and dirty so they'll be written out (in order to prevent uninitialised + * block data from leaking). And clear the new bit. + */ +void page_zero_new_buffers(struct page *page, unsigned from, unsigned to) +{ + unsigned int block_start, block_end; + struct buffer_head *head, *bh; + + BUG_ON(!PageLocked(page)); + if (!page_has_buffers(page)) + return; + + bh = head = page_buffers(page); + block_start = 0; + do { + block_end = block_start + bh->b_size; + + if (buffer_new(bh)) { + if (block_end > from && block_start < to) { + if (!PageUptodate(page)) { + unsigned start, size; + + start = max(from, block_start); + size = min(to, block_end) - start; + + zero_user(page, start, size); + set_buffer_uptodate(bh); + } + + clear_buffer_new(bh); + mark_buffer_dirty(bh); + } + } + + block_start = block_end; + bh = bh->b_this_page; + } while (bh != head); +} +EXPORT_SYMBOL(page_zero_new_buffers); + static int __block_prepare_write(struct inode *inode, struct page *page, unsigned from, unsigned to, get_block_t *get_block) { @@ -1818,19 +1959,10 @@ static int __block_prepare_write(struct inode *inode, struct page *page, mark_buffer_dirty(bh); continue; } - if (block_end > to || block_start < from) { - void *kaddr; - - kaddr = kmap_atomic(page, KM_USER0); - if (block_end > to) - memset(kaddr+to, 0, - block_end-to); - if (block_start < from) - memset(kaddr+block_start, - 0, from-block_start); - flush_dcache_page(page); - kunmap_atomic(kaddr, KM_USER0); - } + if (block_end > to || block_start < from) + zero_user_segments(page, + to, block_end, + block_start, from); continue; } } @@ -1854,38 +1986,8 @@ static int __block_prepare_write(struct inode *inode, struct page *page, if (!buffer_uptodate(*wait_bh)) err = -EIO; } - if (!err) { - bh = head; - do { - if (buffer_new(bh)) - clear_buffer_new(bh); - } while ((bh = bh->b_this_page) != head); - return 0; - } - /* Error case: */ - /* - * Zero out any newly allocated blocks to avoid exposing stale - * data. If BH_New is set, we know that the block was newly - * allocated in the above loop. - */ - bh = head; - block_start = 0; - do { - block_end = block_start+blocksize; - if (block_end <= from) - goto next_bh; - if (block_start >= to) - break; - if (buffer_new(bh)) { - clear_buffer_new(bh); - zero_user_page(page, block_start, bh->b_size, KM_USER0); - set_buffer_uptodate(bh); - mark_buffer_dirty(bh); - } -next_bh: - block_start = block_end; - bh = bh->b_this_page; - } while (bh != head); + if (unlikely(err)) + page_zero_new_buffers(page, from, to); return err; } @@ -1910,6 +2012,7 @@ static int __block_commit_write(struct inode *inode, struct page *page, set_buffer_uptodate(bh); mark_buffer_dirty(bh); } + clear_buffer_new(bh); } /* @@ -1924,6 +2027,185 @@ static int __block_commit_write(struct inode *inode, struct page *page, } /* + * block_write_begin takes care of the basic task of block allocation and + * bringing partial write blocks uptodate first. + * + * If *pagep is not NULL, then block_write_begin uses the locked page + * at *pagep rather than allocating its own. In this case, the page will + * not be unlocked or deallocated on failure. + */ +int block_write_begin(struct file *file, struct address_space *mapping, + loff_t pos, unsigned len, unsigned flags, + struct page **pagep, void **fsdata, + get_block_t *get_block) +{ + struct inode *inode = mapping->host; + int status = 0; + struct page *page; + pgoff_t index; + unsigned start, end; + int ownpage = 0; + + index = pos >> PAGE_CACHE_SHIFT; + start = pos & (PAGE_CACHE_SIZE - 1); + end = start + len; + + page = *pagep; + if (page == NULL) { + ownpage = 1; + page = grab_cache_page_write_begin(mapping, index, flags); + if (!page) { + status = -ENOMEM; + goto out; + } + *pagep = page; + } else + BUG_ON(!PageLocked(page)); + + status = __block_prepare_write(inode, page, start, end, get_block); + if (unlikely(status)) { + ClearPageUptodate(page); + + if (ownpage) { + unlock_page(page); + page_cache_release(page); + *pagep = NULL; + + /* + * prepare_write() may have instantiated a few blocks + * outside i_size. Trim these off again. Don't need + * i_size_read because we hold i_mutex. + */ + if (pos + len > inode->i_size) + vmtruncate(inode, inode->i_size); + } + } + +out: + return status; +} +EXPORT_SYMBOL(block_write_begin); + +int block_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; + unsigned start; + + start = pos & (PAGE_CACHE_SIZE - 1); + + if (unlikely(copied < len)) { + /* + * The buffers that were written will now be uptodate, so we + * don't have to worry about a readpage reading them and + * overwriting a partial write. However if we have encountered + * a short write and only partially written into a buffer, it + * will not be marked uptodate, so a readpage might come in and + * destroy our partial write. + * + * Do the simplest thing, and just treat any short write to a + * non uptodate page as a zero-length write, and force the + * caller to redo the whole thing. + */ + if (!PageUptodate(page)) + copied = 0; + + page_zero_new_buffers(page, start+copied, start+len); + } + flush_dcache_page(page); + + /* This could be a short (even 0-length) commit */ + __block_commit_write(inode, page, start, start+copied); + + return copied; +} +EXPORT_SYMBOL(block_write_end); + +int generic_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; + int i_size_changed = 0; + + copied = block_write_end(file, mapping, pos, len, copied, page, fsdata); + + /* + * No need to use i_size_read() here, the i_size + * cannot change under us because we hold i_mutex. + * + * But it's important to update i_size while still holding page lock: + * page writeout could otherwise come in and zero beyond i_size. + */ + if (pos+copied > inode->i_size) { + i_size_write(inode, pos+copied); + i_size_changed = 1; + } + + unlock_page(page); + page_cache_release(page); + + /* + * Don't mark the inode dirty under page lock. First, it unnecessarily + * makes the holding time of page lock longer. Second, it forces lock + * ordering of page lock and transaction start for journaling + * filesystems. + */ + if (i_size_changed) + mark_inode_dirty(inode); + + return copied; +} +EXPORT_SYMBOL(generic_write_end); + +/* + * block_is_partially_uptodate checks whether buffers within a page are + * uptodate or not. + * + * Returns true if all buffers which correspond to a file portion + * we want to read are uptodate. + */ +int block_is_partially_uptodate(struct page *page, read_descriptor_t *desc, + unsigned long from) +{ + struct inode *inode = page->mapping->host; + unsigned block_start, block_end, blocksize; + unsigned to; + struct buffer_head *bh, *head; + int ret = 1; + + if (!page_has_buffers(page)) + return 0; + + blocksize = 1 << inode->i_blkbits; + to = min_t(unsigned, PAGE_CACHE_SIZE - from, desc->count); + to = from + to; + if (from < blocksize && to > PAGE_CACHE_SIZE - blocksize) + return 0; + + head = page_buffers(page); + bh = head; + block_start = 0; + do { + block_end = block_start + blocksize; + if (block_end > from && block_start < to) { + if (!buffer_uptodate(bh)) { + ret = 0; + break; + } + if (block_end >= to) + break; + } + block_start = block_end; + bh = bh->b_this_page; + } while (bh != head); + + return ret; +} +EXPORT_SYMBOL(block_is_partially_uptodate); + +/* * Generic "read page" function for block devices that have the normal * get_block functionality. This is most of the block device filesystems. * Reads the page asynchronously --- the unlock_buffer() and @@ -1966,8 +2248,7 @@ int block_read_full_page(struct page *page, get_block_t *get_block) SetPageError(page); } if (!buffer_mapped(bh)) { - zero_user_page(page, i * blocksize, blocksize, - KM_USER0); + zero_user(page, i * blocksize, blocksize); if (!err) set_buffer_uptodate(bh); continue; @@ -2019,14 +2300,14 @@ int block_read_full_page(struct page *page, get_block_t *get_block) } /* utility function for filesystems that need to do work on expanding - * truncates. Uses prepare/commit_write to allow the filesystem to + * truncates. Uses filesystem pagecache writes to allow the filesystem to * deal with the hole. */ -static int __generic_cont_expand(struct inode *inode, loff_t size, - pgoff_t index, unsigned int offset) +int generic_cont_expand_simple(struct inode *inode, loff_t size) { struct address_space *mapping = inode->i_mapping; struct page *page; + void *fsdata; unsigned long limit; int err; @@ -2039,140 +2320,117 @@ static int __generic_cont_expand(struct inode *inode, loff_t size, if (size > inode->i_sb->s_maxbytes) goto out; - err = -ENOMEM; - page = grab_cache_page(mapping, index); - if (!page) - goto out; - err = mapping->a_ops->prepare_write(NULL, page, offset, offset); - if (err) { - /* - * ->prepare_write() may have instantiated a few blocks - * outside i_size. Trim these off again. - */ - unlock_page(page); - page_cache_release(page); - vmtruncate(inode, inode->i_size); + err = pagecache_write_begin(NULL, mapping, size, 0, + AOP_FLAG_UNINTERRUPTIBLE|AOP_FLAG_CONT_EXPAND, + &page, &fsdata); + if (err) goto out; - } - err = mapping->a_ops->commit_write(NULL, page, offset, offset); + err = pagecache_write_end(NULL, mapping, size, 0, 0, page, fsdata); + BUG_ON(err > 0); - unlock_page(page); - page_cache_release(page); - if (err > 0) - err = 0; out: return err; } -int generic_cont_expand(struct inode *inode, loff_t size) +static int cont_expand_zero(struct file *file, struct address_space *mapping, + loff_t pos, loff_t *bytes) { - pgoff_t index; - unsigned int offset; + struct inode *inode = mapping->host; + unsigned blocksize = 1 << inode->i_blkbits; + struct page *page; + void *fsdata; + pgoff_t index, curidx; + loff_t curpos; + unsigned zerofrom, offset, len; + int err = 0; - offset = (size & (PAGE_CACHE_SIZE - 1)); /* Within page */ + index = pos >> PAGE_CACHE_SHIFT; + offset = pos & ~PAGE_CACHE_MASK; - /* ugh. in prepare/commit_write, if from==to==start of block, we - ** skip the prepare. make sure we never send an offset for the start - ** of a block - */ - if ((offset & (inode->i_sb->s_blocksize - 1)) == 0) { - /* caller must handle this extra byte. */ - offset++; - } - index = size >> PAGE_CACHE_SHIFT; + while (index > (curidx = (curpos = *bytes)>>PAGE_CACHE_SHIFT)) { + zerofrom = curpos & ~PAGE_CACHE_MASK; + if (zerofrom & (blocksize-1)) { + *bytes |= (blocksize-1); + (*bytes)++; + } + len = PAGE_CACHE_SIZE - zerofrom; - return __generic_cont_expand(inode, size, index, offset); -} + err = pagecache_write_begin(file, mapping, curpos, len, + AOP_FLAG_UNINTERRUPTIBLE, + &page, &fsdata); + if (err) + goto out; + zero_user(page, zerofrom, len); + err = pagecache_write_end(file, mapping, curpos, len, len, + page, fsdata); + if (err < 0) + goto out; + BUG_ON(err != len); + err = 0; -int generic_cont_expand_simple(struct inode *inode, loff_t size) -{ - loff_t pos = size - 1; - pgoff_t index = pos >> PAGE_CACHE_SHIFT; - unsigned int offset = (pos & (PAGE_CACHE_SIZE - 1)) + 1; + balance_dirty_pages_ratelimited(mapping); + } + + /* page covers the boundary, find the boundary offset */ + if (index == curidx) { + zerofrom = curpos & ~PAGE_CACHE_MASK; + /* if we will expand the thing last block will be filled */ + if (offset <= zerofrom) { + goto out; + } + if (zerofrom & (blocksize-1)) { + *bytes |= (blocksize-1); + (*bytes)++; + } + len = offset - zerofrom; - /* prepare/commit_write can handle even if from==to==start of block. */ - return __generic_cont_expand(inode, size, index, offset); + err = pagecache_write_begin(file, mapping, curpos, len, + AOP_FLAG_UNINTERRUPTIBLE, + &page, &fsdata); + if (err) + goto out; + zero_user(page, zerofrom, len); + err = pagecache_write_end(file, mapping, curpos, len, len, + page, fsdata); + if (err < 0) + goto out; + BUG_ON(err != len); + err = 0; + } +out: + return err; } /* * For moronic filesystems that do not allow holes in file. * We may have to extend the file. */ - -int cont_prepare_write(struct page *page, unsigned offset, - unsigned to, get_block_t *get_block, loff_t *bytes) +int cont_write_begin(struct file *file, struct address_space *mapping, + loff_t pos, unsigned len, unsigned flags, + struct page **pagep, void **fsdata, + get_block_t *get_block, loff_t *bytes) { - struct address_space *mapping = page->mapping; struct inode *inode = mapping->host; - struct page *new_page; - pgoff_t pgpos; - long status; - unsigned zerofrom; unsigned blocksize = 1 << inode->i_blkbits; + unsigned zerofrom; + int err; - while(page->index > (pgpos = *bytes>>PAGE_CACHE_SHIFT)) { - status = -ENOMEM; - new_page = grab_cache_page(mapping, pgpos); - if (!new_page) - goto out; - /* we might sleep */ - if (*bytes>>PAGE_CACHE_SHIFT != pgpos) { - unlock_page(new_page); - page_cache_release(new_page); - continue; - } - zerofrom = *bytes & ~PAGE_CACHE_MASK; - if (zerofrom & (blocksize-1)) { - *bytes |= (blocksize-1); - (*bytes)++; - } - status = __block_prepare_write(inode, new_page, zerofrom, - PAGE_CACHE_SIZE, get_block); - if (status) - goto out_unmap; - zero_user_page(new_page, zerofrom, PAGE_CACHE_SIZE - zerofrom, - KM_USER0); - generic_commit_write(NULL, new_page, zerofrom, PAGE_CACHE_SIZE); - unlock_page(new_page); - page_cache_release(new_page); - } - - if (page->index < pgpos) { - /* completely inside the area */ - zerofrom = offset; - } else { - /* page covers the boundary, find the boundary offset */ - zerofrom = *bytes & ~PAGE_CACHE_MASK; - - /* if we will expand the thing last block will be filled */ - if (to > zerofrom && (zerofrom & (blocksize-1))) { - *bytes |= (blocksize-1); - (*bytes)++; - } + err = cont_expand_zero(file, mapping, pos, bytes); + if (err) + goto out; - /* starting below the boundary? Nothing to zero out */ - if (offset <= zerofrom) - zerofrom = offset; + zerofrom = *bytes & ~PAGE_CACHE_MASK; + if (pos+len > *bytes && zerofrom & (blocksize-1)) { + *bytes |= (blocksize-1); + (*bytes)++; } - status = __block_prepare_write(inode, page, zerofrom, to, get_block); - if (status) - goto out1; - if (zerofrom < offset) { - zero_user_page(page, zerofrom, offset - zerofrom, KM_USER0); - __block_commit_write(inode, page, zerofrom, offset); - } - return 0; -out1: - ClearPageUptodate(page); - return status; -out_unmap: - ClearPageUptodate(new_page); - unlock_page(new_page); - page_cache_release(new_page); + *pagep = NULL; + err = block_write_begin(file, mapping, pos, len, + flags, pagep, fsdata, get_block); out: - return status; + return err; } int block_prepare_write(struct page *page, unsigned from, unsigned to, @@ -2192,23 +2450,6 @@ int block_commit_write(struct page *page, unsigned from, unsigned to) return 0; } -int generic_commit_write(struct file *file, struct page *page, - unsigned from, unsigned to) -{ - struct inode *inode = page->mapping->host; - loff_t pos = ((loff_t)page->index << PAGE_CACHE_SHIFT) + to; - __block_commit_write(inode,page,from,to); - /* - * No need to use i_size_read() here, the i_size - * cannot change under us because we hold i_mutex. - */ - if (pos > inode->i_size) { - i_size_write(inode, pos); - mark_inode_dirty(inode); - } - return 0; -} - /* * block_page_mkwrite() is not allowed to change the file size as it gets * called from a page fault handler when a page is first dirtied. Hence we must @@ -2257,7 +2498,7 @@ out_unlock: } /* - * nobh_prepare_write()'s prereads are special: the buffer_heads are freed + * nobh_write_begin()'s prereads are special: the buffer_heads are freed * immediately, while under the page lock. So it needs a special end_io * handler which does not touch the bh after unlocking it. */ @@ -2267,26 +2508,69 @@ static void end_buffer_read_nobh(struct buffer_head *bh, int uptodate) } /* + * Attach the singly-linked list of buffers created by nobh_write_begin, to + * the page (converting it to circular linked list and taking care of page + * dirty races). + */ +static void attach_nobh_buffers(struct page *page, struct buffer_head *head) +{ + struct buffer_head *bh; + + BUG_ON(!PageLocked(page)); + + spin_lock(&page->mapping->private_lock); + bh = head; + do { + if (PageDirty(page)) + set_buffer_dirty(bh); + if (!bh->b_this_page) + bh->b_this_page = head; + bh = bh->b_this_page; + } while (bh != head); + attach_page_buffers(page, head); + spin_unlock(&page->mapping->private_lock); +} + +/* * On entry, the page is fully not uptodate. * On exit the page is fully uptodate in the areas outside (from,to) */ -int nobh_prepare_write(struct page *page, unsigned from, unsigned to, +int nobh_write_begin(struct file *file, struct address_space *mapping, + loff_t pos, unsigned len, unsigned flags, + struct page **pagep, void **fsdata, get_block_t *get_block) { - struct inode *inode = page->mapping->host; + struct inode *inode = mapping->host; const unsigned blkbits = inode->i_blkbits; const unsigned blocksize = 1 << blkbits; struct buffer_head *head, *bh; + struct page *page; + pgoff_t index; + unsigned from, to; unsigned block_in_page; unsigned block_start, block_end; sector_t block_in_file; - char *kaddr; int nr_reads = 0; int ret = 0; int is_mapped_to_disk = 1; - if (page_has_buffers(page)) - return block_prepare_write(page, from, to, get_block); + index = pos >> PAGE_CACHE_SHIFT; + from = pos & (PAGE_CACHE_SIZE - 1); + to = from + len; + + page = grab_cache_page_write_begin(mapping, index, flags); + if (!page) + return -ENOMEM; + *pagep = page; + *fsdata = NULL; + + if (page_has_buffers(page)) { + unlock_page(page); + page_cache_release(page); + *pagep = NULL; + return block_write_begin(file, mapping, pos, len, flags, pagep, + fsdata, get_block); + } if (PageMappedToDisk(page)) return 0; @@ -2301,8 +2585,10 @@ int nobh_prepare_write(struct page *page, unsigned from, unsigned to, * than the circular one we're used to. */ head = alloc_page_buffers(page, blocksize, 0); - if (!head) - return -ENOMEM; + if (!head) { + ret = -ENOMEM; + goto out_release; + } block_in_file = (sector_t)page->index << (PAGE_CACHE_SHIFT - blkbits); @@ -2334,13 +2620,8 @@ int nobh_prepare_write(struct page *page, unsigned from, unsigned to, continue; } if (buffer_new(bh) || !buffer_mapped(bh)) { - kaddr = kmap_atomic(page, KM_USER0); - if (block_start < from) - memset(kaddr+block_start, 0, from-block_start); - if (block_end > to) - memset(kaddr + to, 0, block_end - to); - flush_dcache_page(page); - kunmap_atomic(kaddr, KM_USER0); + zero_user_segments(page, block_start, from, + to, block_end); continue; } if (buffer_uptodate(bh)) @@ -2371,15 +2652,12 @@ int nobh_prepare_write(struct page *page, unsigned from, unsigned to, if (is_mapped_to_disk) SetPageMappedToDisk(page); - do { - bh = head; - head = head->b_this_page; - free_buffer_head(bh); - } while (head); + *fsdata = head; /* to be released by nobh_write_end */ return 0; failed: + BUG_ON(!ret); /* * Error recovery is a bit difficult. We need to zero out blocks that * were newly allocated, and dirty them to ensure they get written out. @@ -2387,64 +2665,55 @@ failed: * the handling of potential IO errors during writeout would be hard * (could try doing synchronous writeout, but what if that fails too?) */ - spin_lock(&page->mapping->private_lock); - bh = head; - block_start = 0; - do { - if (PageUptodate(page)) - set_buffer_uptodate(bh); - if (PageDirty(page)) - set_buffer_dirty(bh); + attach_nobh_buffers(page, head); + page_zero_new_buffers(page, from, to); - block_end = block_start+blocksize; - if (block_end <= from) - goto next; - if (block_start >= to) - goto next; +out_release: + unlock_page(page); + page_cache_release(page); + *pagep = NULL; - if (buffer_new(bh)) { - clear_buffer_new(bh); - if (!buffer_uptodate(bh)) { - zero_user_page(page, block_start, bh->b_size, KM_USER0); - set_buffer_uptodate(bh); - } - mark_buffer_dirty(bh); - } -next: - block_start = block_end; - if (!bh->b_this_page) - bh->b_this_page = head; - bh = bh->b_this_page; - } while (bh != head); - attach_page_buffers(page, head); - spin_unlock(&page->mapping->private_lock); + if (pos + len > inode->i_size) + vmtruncate(inode, inode->i_size); return ret; } -EXPORT_SYMBOL(nobh_prepare_write); +EXPORT_SYMBOL(nobh_write_begin); -/* - * Make sure any changes to nobh_commit_write() are reflected in - * nobh_truncate_page(), since it doesn't call commit_write(). - */ -int nobh_commit_write(struct file *file, struct page *page, - unsigned from, unsigned to) +int nobh_write_end(struct file *file, struct address_space *mapping, + loff_t pos, unsigned len, unsigned copied, + struct page *page, void *fsdata) { struct inode *inode = page->mapping->host; - loff_t pos = ((loff_t)page->index << PAGE_CACHE_SHIFT) + to; + struct buffer_head *head = fsdata; + struct buffer_head *bh; + BUG_ON(fsdata != NULL && page_has_buffers(page)); + if (unlikely(copied < len) && head) + attach_nobh_buffers(page, head); if (page_has_buffers(page)) - return generic_commit_write(file, page, from, to); + return generic_write_end(file, mapping, pos, len, + copied, page, fsdata); SetPageUptodate(page); set_page_dirty(page); - if (pos > inode->i_size) { - i_size_write(inode, pos); + if (pos+copied > inode->i_size) { + i_size_write(inode, pos+copied); mark_inode_dirty(inode); } - return 0; + + unlock_page(page); + page_cache_release(page); + + while (head) { + bh = head; + head = head->b_this_page; + free_buffer_head(bh); + } + + return copied; } -EXPORT_SYMBOL(nobh_commit_write); +EXPORT_SYMBOL(nobh_write_end); /* * nobh_writepage() - based on block_full_write_page() except @@ -2488,7 +2757,7 @@ int nobh_writepage(struct page *page, get_block_t *get_block, * the page size, the remaining memory is zeroed when mapped, and * writes to that region are not written out to the file." */ - zero_user_page(page, offset, PAGE_CACHE_SIZE - offset, KM_USER0); + zero_user_segment(page, offset, PAGE_CACHE_SIZE); out: ret = mpage_writepage(page, get_block, wbc); if (ret == -EAGAIN) @@ -2497,44 +2766,79 @@ out: } EXPORT_SYMBOL(nobh_writepage); -/* - * This function assumes that ->prepare_write() uses nobh_prepare_write(). - */ -int nobh_truncate_page(struct address_space *mapping, loff_t from) +int nobh_truncate_page(struct address_space *mapping, + loff_t from, get_block_t *get_block) { - struct inode *inode = mapping->host; - unsigned blocksize = 1 << inode->i_blkbits; pgoff_t index = from >> PAGE_CACHE_SHIFT; unsigned offset = from & (PAGE_CACHE_SIZE-1); - unsigned to; + unsigned blocksize; + sector_t iblock; + unsigned length, pos; + struct inode *inode = mapping->host; struct page *page; - const struct address_space_operations *a_ops = mapping->a_ops; - int ret = 0; + struct buffer_head map_bh; + int err; - if ((offset & (blocksize - 1)) == 0) - goto out; + blocksize = 1 << inode->i_blkbits; + length = offset & (blocksize - 1); + + /* Block boundary? Nothing to do */ + if (!length) + return 0; + + length = blocksize - length; + iblock = (sector_t)index << (PAGE_CACHE_SHIFT - inode->i_blkbits); - ret = -ENOMEM; page = grab_cache_page(mapping, index); + err = -ENOMEM; if (!page) goto out; - to = (offset + blocksize) & ~(blocksize - 1); - ret = a_ops->prepare_write(NULL, page, offset, to); - if (ret == 0) { - zero_user_page(page, offset, PAGE_CACHE_SIZE - offset, - KM_USER0); - /* - * It would be more correct to call aops->commit_write() - * here, but this is more efficient. - */ - SetPageUptodate(page); - set_page_dirty(page); + if (page_has_buffers(page)) { +has_buffers: + unlock_page(page); + page_cache_release(page); + return block_truncate_page(mapping, from, get_block); } + + /* Find the buffer that contains "offset" */ + pos = blocksize; + while (offset >= pos) { + iblock++; + pos += blocksize; + } + + err = get_block(inode, iblock, &map_bh, 0); + if (err) + goto unlock; + /* unmapped? It's a hole - nothing to do */ + if (!buffer_mapped(&map_bh)) + goto unlock; + + /* Ok, it's mapped. Make sure it's up-to-date */ + if (!PageUptodate(page)) { + err = mapping->a_ops->readpage(NULL, page); + if (err) { + page_cache_release(page); + goto out; + } + lock_page(page); + if (!PageUptodate(page)) { + err = -EIO; + goto unlock; + } + if (page_has_buffers(page)) + goto has_buffers; + } + zero_user(page, offset, length); + set_page_dirty(page); + err = 0; + +unlock: unlock_page(page); page_cache_release(page); out: - return ret; + return err; } EXPORT_SYMBOL(nobh_truncate_page); @@ -2602,7 +2906,7 @@ int block_truncate_page(struct address_space *mapping, goto unlock; } - zero_user_page(page, offset, length, KM_USER0); + zero_user(page, offset, length); mark_buffer_dirty(bh); err = 0; @@ -2648,7 +2952,7 @@ int block_write_full_page(struct page *page, get_block_t *get_block, * the page size, the remaining memory is zeroed when mapped, and * writes to that region are not written out to the file." */ - zero_user_page(page, offset, PAGE_CACHE_SIZE - offset, KM_USER0); + zero_user_segment(page, offset, PAGE_CACHE_SIZE); return __block_write_full_page(inode, page, get_block, wbc); } @@ -2673,6 +2977,9 @@ static void end_bio_bh_io_sync(struct bio *bio, int err) set_bit(BH_Eopnotsupp, &bh->b_state); } + if (unlikely (test_bit(BIO_QUIET,&bio->bi_flags))) + set_bit(BH_Quiet, &bh->b_state); + bh->b_end_io(bh, test_bit(BIO_UPTODATE, &bio->bi_flags)); bio_put(bio); } @@ -2686,14 +2993,17 @@ int submit_bh(int rw, struct buffer_head * bh) BUG_ON(!buffer_mapped(bh)); BUG_ON(!bh->b_end_io); - if (buffer_ordered(bh) && (rw == WRITE)) - rw = WRITE_BARRIER; + /* + * Mask in barrier bit for a write (could be either a WRITE or a + * WRITE_SYNC + */ + if (buffer_ordered(bh) && (rw & WRITE)) + rw |= WRITE_BARRIER; /* - * Only clear out a write error when rewriting, should this - * include WRITE_SYNC as well? + * Only clear out a write error when rewriting */ - if (test_set_buffer_req(bh) && (rw == WRITE || rw == WRITE_BARRIER)) + if (test_set_buffer_req(bh) && (rw & WRITE)) clear_buffer_write_io_error(bh); /* @@ -2758,16 +3068,19 @@ void ll_rw_block(int rw, int nr, struct buffer_head *bhs[]) for (i = 0; i < nr; i++) { struct buffer_head *bh = bhs[i]; - if (rw == SWRITE) + if (rw == SWRITE || rw == SWRITE_SYNC) lock_buffer(bh); - else if (test_set_buffer_locked(bh)) + else if (!trylock_buffer(bh)) continue; - if (rw == WRITE || rw == SWRITE) { + if (rw == WRITE || rw == SWRITE || rw == SWRITE_SYNC) { if (test_clear_buffer_dirty(bh)) { bh->b_end_io = end_buffer_write_sync; get_bh(bh); - submit_bh(WRITE, bh); + if (rw == SWRITE_SYNC) + submit_bh(WRITE_SYNC, bh); + else + submit_bh(WRITE, bh); continue; } } else { @@ -2854,7 +3167,7 @@ drop_buffers(struct page *page, struct buffer_head **buffers_to_free) do { struct buffer_head *next = bh->b_this_page; - if (!list_empty(&bh->b_assoc_buffers)) + if (bh->b_assoc_map) __remove_assoc_queue(bh); bh = next; } while (bh != head); @@ -2931,7 +3244,7 @@ void block_sync_page(struct page *page) * Use of bdflush() is deprecated and will be removed in a future kernel. * The `pdflush' kernel threads fully replace bdflush daemons and this call. */ -asmlinkage long sys_bdflush(int func, long data) +SYSCALL_DEFINE2(bdflush, int, func, long, data) { static int msg_count; @@ -2986,7 +3299,7 @@ static void recalc_bh_state(void) struct buffer_head *alloc_buffer_head(gfp_t gfp_flags) { - struct buffer_head *ret = kmem_cache_zalloc(bh_cachep, gfp_flags); + struct buffer_head *ret = kmem_cache_alloc(bh_cachep, gfp_flags); if (ret) { INIT_LIST_HEAD(&ret->b_assoc_buffers); get_cpu_var(bh_accounting).nr++; @@ -3029,12 +3342,68 @@ static int buffer_cpu_notify(struct notifier_block *self, return NOTIFY_OK; } +/** + * bh_uptodate_or_lock - Test whether the buffer is uptodate + * @bh: struct buffer_head + * + * Return true if the buffer is up-to-date and false, + * with the buffer locked, if not. + */ +int bh_uptodate_or_lock(struct buffer_head *bh) +{ + if (!buffer_uptodate(bh)) { + lock_buffer(bh); + if (!buffer_uptodate(bh)) + return 0; + unlock_buffer(bh); + } + return 1; +} +EXPORT_SYMBOL(bh_uptodate_or_lock); + +/** + * bh_submit_read - Submit a locked buffer for reading + * @bh: struct buffer_head + * + * Returns zero on success and -EIO on error. + */ +int bh_submit_read(struct buffer_head *bh) +{ + BUG_ON(!buffer_locked(bh)); + + if (buffer_uptodate(bh)) { + unlock_buffer(bh); + return 0; + } + + get_bh(bh); + bh->b_end_io = end_buffer_read_sync; + submit_bh(READ, bh); + wait_on_buffer(bh); + if (buffer_uptodate(bh)) + return 0; + return -EIO; +} +EXPORT_SYMBOL(bh_submit_read); + +static void +init_buffer_head(void *data) +{ + struct buffer_head *bh = data; + + memset(bh, 0, sizeof(*bh)); + INIT_LIST_HEAD(&bh->b_assoc_buffers); +} + void __init buffer_init(void) { int nrpages; - bh_cachep = KMEM_CACHE(buffer_head, - SLAB_RECLAIM_ACCOUNT|SLAB_PANIC|SLAB_MEM_SPREAD); + bh_cachep = kmem_cache_create("buffer_head", + sizeof(struct buffer_head), 0, + (SLAB_RECLAIM_ACCOUNT|SLAB_PANIC| + SLAB_MEM_SPREAD), + init_buffer_head); /* * Limit the bh occupancy to 10% of ZONE_NORMAL @@ -3054,14 +3423,12 @@ EXPORT_SYMBOL(block_read_full_page); EXPORT_SYMBOL(block_sync_page); EXPORT_SYMBOL(block_truncate_page); EXPORT_SYMBOL(block_write_full_page); -EXPORT_SYMBOL(cont_prepare_write); +EXPORT_SYMBOL(cont_write_begin); EXPORT_SYMBOL(end_buffer_read_sync); EXPORT_SYMBOL(end_buffer_write_sync); EXPORT_SYMBOL(file_fsync); EXPORT_SYMBOL(fsync_bdev); EXPORT_SYMBOL(generic_block_bmap); -EXPORT_SYMBOL(generic_commit_write); -EXPORT_SYMBOL(generic_cont_expand); EXPORT_SYMBOL(generic_cont_expand_simple); EXPORT_SYMBOL(init_buffer); EXPORT_SYMBOL(invalidate_bdev);