diff options
Diffstat (limited to 'fs/buffer.c')
| -rw-r--r-- | fs/buffer.c | 1141 |
1 files changed, 630 insertions, 511 deletions
diff --git a/fs/buffer.c b/fs/buffer.c index 39ff14403d1..eba6e4f621c 100644 --- a/fs/buffer.c +++ b/fs/buffer.c @@ -29,7 +29,7 @@ #include <linux/file.h> #include <linux/quotaops.h> #include <linux/highmem.h> -#include <linux/module.h> +#include <linux/export.h> #include <linux/writeback.h> #include <linux/hash.h> #include <linux/suspend.h> @@ -41,46 +41,80 @@ #include <linux/bitops.h> #include <linux/mpage.h> #include <linux/bit_spinlock.h> +#include <trace/events/block.h> static int fsync_buffers_list(spinlock_t *lock, struct list_head *list); #define BH_ENTRY(list) list_entry((list), struct buffer_head, b_assoc_buffers) -inline void -init_buffer(struct buffer_head *bh, bh_end_io_t *handler, void *private) +void init_buffer(struct buffer_head *bh, bh_end_io_t *handler, void *private) { bh->b_end_io = handler; bh->b_private = private; } +EXPORT_SYMBOL(init_buffer); -static int sync_buffer(void *word) +inline void touch_buffer(struct buffer_head *bh) { - struct block_device *bd; - struct buffer_head *bh - = container_of(word, struct buffer_head, b_state); + trace_block_touch_buffer(bh); + mark_page_accessed(bh->b_page); +} +EXPORT_SYMBOL(touch_buffer); - smp_mb(); - bd = bh->b_bdev; - if (bd) - blk_run_address_space(bd->bd_inode->i_mapping); +static int sleep_on_buffer(void *word) +{ io_schedule(); return 0; } void __lock_buffer(struct buffer_head *bh) { - wait_on_bit_lock(&bh->b_state, BH_Lock, sync_buffer, + wait_on_bit_lock(&bh->b_state, BH_Lock, sleep_on_buffer, TASK_UNINTERRUPTIBLE); } EXPORT_SYMBOL(__lock_buffer); void unlock_buffer(struct buffer_head *bh) { - smp_mb__before_clear_bit(); - clear_buffer_locked(bh); - smp_mb__after_clear_bit(); + clear_bit_unlock(BH_Lock, &bh->b_state); + smp_mb__after_atomic(); wake_up_bit(&bh->b_state, BH_Lock); } +EXPORT_SYMBOL(unlock_buffer); + +/* + * Returns if the page has dirty or writeback buffers. If all the buffers + * are unlocked and clean then the PageDirty information is stale. If + * any of the pages are locked, it is assumed they are locked for IO. + */ +void buffer_check_dirty_writeback(struct page *page, + bool *dirty, bool *writeback) +{ + struct buffer_head *head, *bh; + *dirty = false; + *writeback = false; + + BUG_ON(!PageLocked(page)); + + if (!page_has_buffers(page)) + return; + + if (PageWriteback(page)) + *writeback = true; + + head = page_buffers(page); + bh = head; + do { + if (buffer_locked(bh)) + *writeback = true; + + if (buffer_dirty(bh)) + *dirty = true; + + bh = bh->b_this_page; + } while (bh != head); +} +EXPORT_SYMBOL(buffer_check_dirty_writeback); /* * Block until a buffer comes unlocked. This doesn't stop it @@ -89,8 +123,9 @@ void unlock_buffer(struct buffer_head *bh) */ void __wait_on_buffer(struct buffer_head * bh) { - wait_on_bit(&bh->b_state, BH_Lock, sync_buffer, TASK_UNINTERRUPTIBLE); + wait_on_bit(&bh->b_state, BH_Lock, sleep_on_buffer, TASK_UNINTERRUPTIBLE); } +EXPORT_SYMBOL(__wait_on_buffer); static void __clear_page_buffers(struct page *page) @@ -100,10 +135,18 @@ __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); @@ -137,6 +180,7 @@ void end_buffer_read_sync(struct buffer_head *bh, int uptodate) __end_buffer_read_notouch(bh, uptodate); put_bh(bh); } +EXPORT_SYMBOL(end_buffer_read_sync); void end_buffer_write_sync(struct buffer_head *bh, int uptodate) { @@ -145,7 +189,7 @@ 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 (!quiet_error(bh)) { buffer_io_error(bh); printk(KERN_WARNING "lost page write due to " "I/O error on %s\n", @@ -157,95 +201,7 @@ void end_buffer_write_sync(struct buffer_head *bh, int uptodate) unlock_buffer(bh); put_bh(bh); } - -/* - * Write out and wait upon all the dirty data associated with a block - * device via its mapping. Does not take the superblock lock. - */ -int sync_blockdev(struct block_device *bdev) -{ - int ret = 0; - - if (bdev) - ret = filemap_write_and_wait(bdev->bd_inode->i_mapping); - return ret; -} -EXPORT_SYMBOL(sync_blockdev); - -/* - * Write out and wait upon all dirty data associated with this - * device. Filesystem data as well as the underlying block - * device. Takes the superblock lock. - */ -int fsync_bdev(struct block_device *bdev) -{ - struct super_block *sb = get_super(bdev); - if (sb) { - int res = fsync_super(sb); - drop_super(sb); - return res; - } - return sync_blockdev(bdev); -} - -/** - * freeze_bdev -- lock a filesystem and force it into a consistent state - * @bdev: blockdevice to lock - * - * This takes the block device bd_mount_sem to make sure no new mounts - * 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. - */ -struct super_block *freeze_bdev(struct block_device *bdev) -{ - struct super_block *sb; - - down(&bdev->bd_mount_sem); - sb = get_super(bdev); - if (sb && !(sb->s_flags & MS_RDONLY)) { - sb->s_frozen = SB_FREEZE_WRITE; - smp_wmb(); - - __fsync_super(sb); - - sb->s_frozen = SB_FREEZE_TRANS; - smp_wmb(); - - sync_blockdev(sb->s_bdev); - - if (sb->s_op->write_super_lockfs) - sb->s_op->write_super_lockfs(sb); - } - - sync_blockdev(bdev); - return sb; /* thaw_bdev releases s->s_umount and bd_mount_sem */ -} -EXPORT_SYMBOL(freeze_bdev); - -/** - * thaw_bdev -- unlock filesystem - * @bdev: blockdevice to unlock - * @sb: associated superblock - * - * Unlocks the filesystem and marks it writeable again after freeze_bdev(). - */ -void thaw_bdev(struct block_device *bdev, struct super_block *sb) -{ - 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); - drop_super(sb); - } - - up(&bdev->bd_mount_sem); -} -EXPORT_SYMBOL(thaw_bdev); +EXPORT_SYMBOL(end_buffer_write_sync); /* * Various filesystems appear to want __find_get_block to be non-blocking. @@ -271,7 +227,7 @@ __find_get_block_slow(struct block_device *bdev, sector_t block) int all_mapped = 1; index = block >> (PAGE_CACHE_SHIFT - bd_inode->i_blkbits); - page = find_get_page(bd_mapping, index); + page = find_get_page_flags(bd_mapping, index, FGP_ACCESSED); if (!page) goto out; @@ -281,13 +237,13 @@ __find_get_block_slow(struct block_device *bdev, sector_t block) head = page_buffers(page); bh = head; do { - if (bh->b_blocknr == block) { + if (!buffer_mapped(bh)) + all_mapped = 0; + else if (bh->b_blocknr == block) { ret = bh; get_bh(bh); goto out_unlock; } - if (!buffer_mapped(bh)) - all_mapped = 0; bh = bh->b_this_page; } while (bh != head); @@ -297,13 +253,16 @@ __find_get_block_slow(struct block_device *bdev, sector_t block) * elsewhere, don't buffer_error if we had some unmapped buffers */ if (all_mapped) { + char b[BDEVNAME_SIZE]; + printk("__find_get_block_slow() failed. " "block=%llu, b_blocknr=%llu\n", (unsigned long long)block, (unsigned long long)bh->b_blocknr); printk("b_state=0x%08lx, b_size=%zu\n", bh->b_state, bh->b_size); - printk("device blocksize: %d\n", 1 << bd_inode->i_blkbits); + printk("device %s blocksize: %d\n", bdevname(bdev, b), + 1 << bd_inode->i_blkbits); } out_unlock: spin_unlock(&bd_mapping->private_lock); @@ -312,64 +271,24 @@ out: return ret; } -/* If invalidate_buffers() will trash dirty buffers, it means some kind - of fs corruption is going on. Trashing dirty data always imply losing - information that was supposed to be just stored on the physical layer - by the user. - - Thus invalidate_buffers in general usage is not allwowed to trash - dirty buffers. For example ioctl(FLSBLKBUF) expects dirty data to - be preserved. These buffers are simply skipped. - - We also skip buffers which are still in use. For example this can - happen if a userspace program is reading the block device. - - NOTE: In the case where the user removed a removable-media-disk even if - there's still dirty data not synced on disk (due a bug in the device driver - or due an error of the user), by not destroying the dirty buffers we could - generate corruption also on the next media inserted, thus a parameter is - necessary to handle this case in the most safe way possible (trying - to not corrupt also the new disk inserted with the data belonging to - the old now corrupted disk). Also for the ramdisk the natural thing - to do in order to release the ramdisk memory is to destroy dirty buffers. - - These are two special cases. Normal usage imply the device driver - to issue a sync on the device (without waiting I/O completion) and - then an invalidate_buffers call that doesn't trash dirty buffers. - - For handling cache coherency with the blkdev pagecache the 'update' case - is been introduced. It is needed to re-read from disk any pinned - buffer. NOTE: re-reading from disk is destructive so we can do it only - when we assume nobody is changing the buffercache under our I/O and when - we think the disk contains more recent information than the buffercache. - The update == 1 pass marks the buffers we need to update, the update == 2 - pass does the actual I/O. */ -void invalidate_bdev(struct block_device *bdev) -{ - struct address_space *mapping = bdev->bd_inode->i_mapping; - - if (mapping->nrpages == 0) - return; - - invalidate_bh_lrus(); - invalidate_mapping_pages(mapping, 0, -1); -} - /* - * Kick pdflush then try to free up some ZONE_NORMAL memory. + * Kick the writeback threads then try to free up some ZONE_NORMAL memory. */ static void free_more_memory(void) { - struct zone **zones; - pg_data_t *pgdat; + struct zone *zone; + int nid; - wakeup_pdflush(1024); + wakeup_flusher_threads(1024, WB_REASON_FREE_MORE_MEM); 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, NULL); } } @@ -392,7 +311,7 @@ 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); } @@ -439,7 +358,7 @@ still_busy: * Completion handler for block_write_full_page() - pages which are unlocked * during I/O, and which have PageWriteback cleared upon I/O completion. */ -static void end_buffer_async_write(struct buffer_head *bh, int uptodate) +void end_buffer_async_write(struct buffer_head *bh, int uptodate) { char b[BDEVNAME_SIZE]; unsigned long flags; @@ -453,7 +372,7 @@ 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", @@ -489,6 +408,7 @@ still_busy: local_irq_restore(flags); return; } +EXPORT_SYMBOL(end_buffer_async_write); /* * If a page's buffers are under async readin (end_buffer_async_read @@ -517,11 +437,17 @@ static void mark_buffer_async_read(struct buffer_head *bh) set_buffer_async_read(bh); } -void mark_buffer_async_write(struct buffer_head *bh) +static void mark_buffer_async_write_endio(struct buffer_head *bh, + bh_end_io_t *handler) { - bh->b_end_io = end_buffer_async_write; + bh->b_end_io = handler; set_buffer_async_write(bh); } + +void mark_buffer_async_write(struct buffer_head *bh) +{ + mark_buffer_async_write_endio(bh, end_buffer_async_write); +} EXPORT_SYMBOL(mark_buffer_async_write); @@ -577,7 +503,7 @@ 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); @@ -626,6 +552,37 @@ repeat: return err; } +static void do_thaw_one(struct super_block *sb, void *unused) +{ + char b[BDEVNAME_SIZE]; + while (sb->s_bdev && !thaw_bdev(sb->s_bdev, sb)) + printk(KERN_WARNING "Emergency Thaw on %s\n", + bdevname(sb->s_bdev, b)); +} + +static void do_thaw_all(struct work_struct *work) +{ + iterate_supers(do_thaw_one, NULL); + kfree(work); + printk(KERN_WARNING "Emergency Thaw complete\n"); +} + +/** + * emergency_thaw_all -- forcibly thaw every frozen filesystem + * + * Used for emergency unfreeze of all filesystems via SysRq + */ +void emergency_thaw_all(void) +{ + struct work_struct *work; + + work = kmalloc(sizeof(*work), GFP_ATOMIC); + if (work) { + INIT_WORK(work, do_thaw_all); + schedule_work(work); + } +} + /** * sync_mapping_buffers - write out & wait upon a mapping's "associated" buffers * @mapping: the mapping which wants those buffers written @@ -639,7 +596,7 @@ repeat: */ int sync_mapping_buffers(struct address_space *mapping) { - struct address_space *buffer_mapping = mapping->assoc_mapping; + struct address_space *buffer_mapping = mapping->private_data; if (buffer_mapping == NULL || list_empty(&mapping->private_list)) return 0; @@ -672,10 +629,10 @@ void mark_buffer_dirty_inode(struct buffer_head *bh, struct inode *inode) struct address_space *buffer_mapping = bh->b_page->mapping; mark_buffer_dirty(bh); - if (!mapping->assoc_mapping) { - mapping->assoc_mapping = buffer_mapping; + if (!mapping->private_data) { + mapping->private_data = buffer_mapping; } else { - BUG_ON(mapping->assoc_mapping != buffer_mapping); + BUG_ON(mapping->private_data != buffer_mapping); } if (!bh->b_assoc_map) { spin_lock(&buffer_mapping->private_lock); @@ -694,32 +651,20 @@ EXPORT_SYMBOL(mark_buffer_dirty_inode); * If warn is true, then emit a warning if the page is not uptodate and has * not been truncated. */ -static int __set_page_dirty(struct page *page, +static void __set_page_dirty(struct page *page, struct address_space *mapping, int warn) { - if (unlikely(!mapping)) - return !TestSetPageDirty(page); - - if (TestSetPageDirty(page)) - return 0; + unsigned long flags; - write_lock_irq(&mapping->tree_lock); + spin_lock_irqsave(&mapping->tree_lock, flags); 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_io_account_write(PAGE_CACHE_SIZE); - } + account_page_dirtied(page, mapping); radix_tree_tag_set(&mapping->page_tree, page_index(page), PAGECACHE_TAG_DIRTY); } - write_unlock_irq(&mapping->tree_lock); + spin_unlock_irqrestore(&mapping->tree_lock, flags); __mark_inode_dirty(mapping->host, I_DIRTY_PAGES); - - return 1; } /* @@ -749,6 +694,7 @@ static int __set_page_dirty(struct page *page, */ int __set_page_dirty_buffers(struct page *page) { + int newly_dirty; struct address_space *mapping = page_mapping(page); if (unlikely(!mapping)) @@ -764,9 +710,12 @@ int __set_page_dirty_buffers(struct page *page) bh = bh->b_this_page; } while (bh != head); } + newly_dirty = !TestSetPageDirty(page); spin_unlock(&mapping->private_lock); - return __set_page_dirty(page, mapping, 1); + if (newly_dirty) + __set_page_dirty(page, mapping, 1); + return newly_dirty; } EXPORT_SYMBOL(__set_page_dirty_buffers); @@ -795,8 +744,10 @@ static int fsync_buffers_list(spinlock_t *lock, struct list_head *list) struct list_head tmp; struct address_space *mapping; int err = 0, err2; + struct blk_plug plug; INIT_LIST_HEAD(&tmp); + blk_start_plug(&plug); spin_lock(lock); while (!list_empty(list)) { @@ -814,17 +765,29 @@ static int fsync_buffers_list(spinlock_t *lock, struct list_head *list) spin_unlock(lock); /* * Ensure any pending I/O completes so that - * ll_rw_block() actually writes the current - * contents - it is a noop if I/O is still in - * flight on potentially older contents. + * write_dirty_buffer() actually writes the + * current contents - it is a noop if I/O is + * still in flight on potentially older + * contents. + */ + write_dirty_buffer(bh, WRITE_SYNC); + + /* + * Kick off IO for the previous mapping. Note + * that we will not run the very last mapping, + * wait_on_buffer() will do that for us + * through sync_buffer(). */ - ll_rw_block(SWRITE, 1, &bh); brelse(bh); spin_lock(lock); } } } + spin_unlock(lock); + blk_finish_plug(&plug); + spin_lock(lock); + while (!list_empty(&tmp)) { bh = BH_ENTRY(tmp.prev); get_bh(bh); @@ -868,7 +831,7 @@ void invalidate_inode_buffers(struct inode *inode) if (inode_has_buffers(inode)) { struct address_space *mapping = &inode->i_data; struct list_head *list = &mapping->private_list; - struct address_space *buffer_mapping = mapping->assoc_mapping; + struct address_space *buffer_mapping = mapping->private_data; spin_lock(&buffer_mapping->private_lock); while (!list_empty(list)) @@ -876,6 +839,7 @@ 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 @@ -890,7 +854,7 @@ int remove_inode_buffers(struct inode *inode) if (inode_has_buffers(inode)) { struct address_space *mapping = &inode->i_data; struct list_head *list = &mapping->private_list; - struct address_space *buffer_mapping = mapping->assoc_mapping; + struct address_space *buffer_mapping = mapping->private_data; spin_lock(&buffer_mapping->private_lock); while (!list_empty(list)) { @@ -929,20 +893,14 @@ try_again: if (!bh) goto no_grow; - bh->b_bdev = NULL; bh->b_this_page = head; bh->b_blocknr = -1; head = bh; - bh->b_state = 0; - atomic_set(&bh->b_count, 0); - bh->b_private = NULL; bh->b_size = size; /* Link the buffer to its page */ set_bh_page(bh, page, offset); - - init_buffer(bh, NULL, NULL); } return head; /* @@ -991,16 +949,29 @@ link_dev_buffers(struct page *page, struct buffer_head *head) attach_page_buffers(page, head); } +static sector_t blkdev_max_block(struct block_device *bdev, unsigned int size) +{ + sector_t retval = ~((sector_t)0); + loff_t sz = i_size_read(bdev->bd_inode); + + if (sz) { + unsigned int sizebits = blksize_bits(size); + retval = (sz >> sizebits); + } + return retval; +} + /* * Initialise the state of a blockdev page's buffers. */ -static void +static sector_t init_page_buffers(struct page *page, struct block_device *bdev, sector_t block, int size) { struct buffer_head *head = page_buffers(page); struct buffer_head *bh = head; int uptodate = PageUptodate(page); + sector_t end_block = blkdev_max_block(I_BDEV(bdev->bd_inode), size); do { if (!buffer_mapped(bh)) { @@ -1009,38 +980,57 @@ init_page_buffers(struct page *page, struct block_device *bdev, bh->b_blocknr = block; if (uptodate) set_buffer_uptodate(bh); - set_buffer_mapped(bh); + if (block < end_block) + set_buffer_mapped(bh); } block++; bh = bh->b_this_page; } while (bh != head); + + /* + * Caller needs to validate requested block against end of device. + */ + return end_block; } /* * Create the page-cache page that contains the requested block. * - * This is user purely for blockdev mappings. + * This is used purely for blockdev mappings. */ -static struct page * +static int grow_dev_page(struct block_device *bdev, sector_t block, - pgoff_t index, int size) + pgoff_t index, int size, int sizebits) { struct inode *inode = bdev->bd_inode; struct page *page; struct buffer_head *bh; + sector_t end_block; + int ret = 0; /* Will call free_more_memory() */ + gfp_t gfp_mask; - page = find_or_create_page(inode->i_mapping, index, - (mapping_gfp_mask(inode->i_mapping) & ~__GFP_FS)|__GFP_MOVABLE); + gfp_mask = mapping_gfp_mask(inode->i_mapping) & ~__GFP_FS; + gfp_mask |= __GFP_MOVABLE; + /* + * XXX: __getblk_slow() can not really deal with failure and + * will endlessly loop on improvised global reclaim. Prefer + * looping in the allocator rather than here, at least that + * code knows what it's doing. + */ + gfp_mask |= __GFP_NOFAIL; + + page = find_or_create_page(inode->i_mapping, index, gfp_mask); if (!page) - return NULL; + return ret; BUG_ON(!PageLocked(page)); if (page_has_buffers(page)) { bh = page_buffers(page); if (bh->b_size == size) { - init_page_buffers(page, bdev, block, size); - return page; + end_block = init_page_buffers(page, bdev, + index << sizebits, size); + goto done; } if (!try_to_free_buffers(page)) goto failed; @@ -1060,15 +1050,14 @@ grow_dev_page(struct block_device *bdev, sector_t block, */ spin_lock(&inode->i_mapping->private_lock); link_dev_buffers(page, bh); - init_page_buffers(page, bdev, block, size); + end_block = init_page_buffers(page, bdev, index << sizebits, size); spin_unlock(&inode->i_mapping->private_lock); - return page; - +done: + ret = (block < end_block) ? 1 : -ENXIO; failed: - BUG(); unlock_page(page); page_cache_release(page); - return NULL; + return ret; } /* @@ -1078,7 +1067,6 @@ failed: static int grow_buffers(struct block_device *bdev, sector_t block, int size) { - struct page *page; pgoff_t index; int sizebits; @@ -1098,37 +1086,32 @@ 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; } - block = index << sizebits; + /* Create a page with the proper size buffers.. */ - page = grow_dev_page(bdev, block, index, size); - if (!page) - return 0; - unlock_page(page); - page_cache_release(page); - return 1; + return grow_dev_page(bdev, block, index, size, sizebits); } static struct buffer_head * __getblk_slow(struct block_device *bdev, sector_t block, int size) { /* Size must be multiple of hard sectorsize */ - if (unlikely(size & (bdev_hardsect_size(bdev)-1) || + if (unlikely(size & (bdev_logical_block_size(bdev)-1) || (size < 512 || size > PAGE_SIZE))) { printk(KERN_ERR "getblk(): invalid block size %d requested\n", size); - printk(KERN_ERR "hardsect size: %d\n", - bdev_hardsect_size(bdev)); + printk(KERN_ERR "logical block size: %d\n", + bdev_logical_block_size(bdev)); dump_stack(); return NULL; } for (;;) { - struct buffer_head * bh; + struct buffer_head *bh; int ret; bh = __find_get_block(bdev, block, size); @@ -1176,12 +1159,14 @@ __getblk_slow(struct block_device *bdev, sector_t block, int size) * inode list. * * mark_buffer_dirty() is atomic. It takes bh->b_page->mapping->private_lock, - * mapping->tree_lock and the global inode_lock. + * mapping->tree_lock and mapping->host->i_lock. */ void mark_buffer_dirty(struct buffer_head *bh) { WARN_ON_ONCE(!buffer_uptodate(bh)); + trace_block_dirty_buffer(bh); + /* * Very *carefully* optimize the it-is-already-dirty case. * @@ -1194,9 +1179,16 @@ void mark_buffer_dirty(struct buffer_head *bh) return; } - if (!test_set_buffer_dirty(bh)) - __set_page_dirty(bh->b_page, page_mapping(bh->b_page), 0); + if (!test_set_buffer_dirty(bh)) { + struct page *page = bh->b_page; + if (!TestSetPageDirty(page)) { + struct address_space *mapping = page_mapping(page); + if (mapping) + __set_page_dirty(page, mapping, 0); + } + } } +EXPORT_SYMBOL(mark_buffer_dirty); /* * Decrement a buffer_head's reference count. If all buffers against a page @@ -1211,9 +1203,9 @@ 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"); } +EXPORT_SYMBOL(__brelse); /* * bforget() is like brelse(), except it discards any @@ -1232,6 +1224,7 @@ void __bforget(struct buffer_head *bh) } __brelse(bh); } +EXPORT_SYMBOL(__bforget); static struct buffer_head *__bread_slow(struct buffer_head *bh) { @@ -1294,12 +1287,10 @@ static inline void check_irqs_on(void) static void bh_lru_install(struct buffer_head *bh) { struct buffer_head *evictee = NULL; - struct bh_lru *lru; check_irqs_on(); bh_lru_lock(); - lru = &__get_cpu_var(bh_lrus); - if (lru->bhs[0] != bh) { + if (__this_cpu_read(bh_lrus.bhs[0]) != bh) { struct buffer_head *bhs[BH_LRU_SIZE]; int in; int out = 0; @@ -1307,7 +1298,8 @@ static void bh_lru_install(struct buffer_head *bh) get_bh(bh); bhs[out++] = bh; for (in = 0; in < BH_LRU_SIZE; in++) { - struct buffer_head *bh2 = lru->bhs[in]; + struct buffer_head *bh2 = + __this_cpu_read(bh_lrus.bhs[in]); if (bh2 == bh) { __brelse(bh2); @@ -1322,7 +1314,7 @@ static void bh_lru_install(struct buffer_head *bh) } while (out < BH_LRU_SIZE) bhs[out++] = NULL; - memcpy(lru->bhs, bhs, sizeof(bhs)); + memcpy(this_cpu_ptr(&bh_lrus.bhs), bhs, sizeof(bhs)); } bh_lru_unlock(); @@ -1337,23 +1329,22 @@ static struct buffer_head * lookup_bh_lru(struct block_device *bdev, sector_t block, unsigned size) { struct buffer_head *ret = NULL; - struct bh_lru *lru; unsigned int i; check_irqs_on(); bh_lru_lock(); - lru = &__get_cpu_var(bh_lrus); for (i = 0; i < BH_LRU_SIZE; i++) { - struct buffer_head *bh = lru->bhs[i]; + struct buffer_head *bh = __this_cpu_read(bh_lrus.bhs[i]); if (bh && bh->b_bdev == bdev && bh->b_blocknr == block && bh->b_size == size) { if (i) { while (i) { - lru->bhs[i] = lru->bhs[i - 1]; + __this_cpu_write(bh_lrus.bhs[i], + __this_cpu_read(bh_lrus.bhs[i - 1])); i--; } - lru->bhs[0] = bh; + __this_cpu_write(bh_lrus.bhs[0], bh); } get_bh(bh); ret = bh; @@ -1375,12 +1366,13 @@ __find_get_block(struct block_device *bdev, sector_t block, unsigned size) struct buffer_head *bh = lookup_bh_lru(bdev, block, size); if (bh == NULL) { + /* __find_get_block_slow will mark the page accessed */ bh = __find_get_block_slow(bdev, block); if (bh) bh_lru_install(bh); - } - if (bh) + } else touch_buffer(bh); + return bh; } EXPORT_SYMBOL(__find_get_block); @@ -1390,10 +1382,6 @@ EXPORT_SYMBOL(__find_get_block); * which corresponds to the passed block_device, block and size. The * returned buffer has its reference count incremented. * - * __getblk() cannot fail - it just keeps trying. If you pass it an - * illegal block number, __getblk() will happily return a buffer_head - * which represents the non-existent block. Very weird. - * * __getblk() will lock up the machine if grow_dev_page's try_to_free_buffers() * attempt is failing. FIXME, perhaps? */ @@ -1458,10 +1446,23 @@ static void invalidate_bh_lru(void *arg) } put_cpu_var(bh_lrus); } + +static bool has_bh_in_lru(int cpu, void *dummy) +{ + struct bh_lru *b = per_cpu_ptr(&bh_lrus, cpu); + int i; + for (i = 0; i < BH_LRU_SIZE; i++) { + if (b->bhs[i]) + return 1; + } + + return 0; +} + void invalidate_bh_lrus(void) { - on_each_cpu(invalidate_bh_lru, NULL, 1, 1); + on_each_cpu_cond(has_bh_in_lru, invalidate_bh_lru, NULL, 1, GFP_KERNEL); } EXPORT_SYMBOL_GPL(invalidate_bh_lrus); @@ -1483,27 +1484,39 @@ EXPORT_SYMBOL(set_bh_page); /* * Called when truncating a buffer on a page completely. */ + +/* Bits that are cleared during an invalidate */ +#define BUFFER_FLAGS_DISCARD \ + (1 << BH_Mapped | 1 << BH_New | 1 << BH_Req | \ + 1 << BH_Delay | 1 << BH_Unwritten) + static void discard_buffer(struct buffer_head * bh) { + unsigned long b_state, b_state_old; + lock_buffer(bh); clear_buffer_dirty(bh); bh->b_bdev = NULL; - clear_buffer_mapped(bh); - clear_buffer_req(bh); - clear_buffer_new(bh); - clear_buffer_delay(bh); - clear_buffer_unwritten(bh); + b_state = bh->b_state; + for (;;) { + b_state_old = cmpxchg(&bh->b_state, b_state, + (b_state & ~BUFFER_FLAGS_DISCARD)); + if (b_state_old == b_state) + break; + b_state = b_state_old; + } unlock_buffer(bh); } /** - * block_invalidatepage - invalidate part of all of a buffer-backed page + * block_invalidatepage - invalidate part or all of a buffer-backed page * * @page: the page which is affected - * @offset: the index of the truncation point + * @offset: start of the range to invalidate + * @length: length of the range to invalidate * * block_invalidatepage() is called when all or part of the page has become - * invalidatedby a truncate operation. + * invalidated by a truncate operation. * * block_invalidatepage() does not have to release all buffers, but it must * ensure that no dirty buffer is left outside @offset and that no I/O @@ -1511,15 +1524,22 @@ static void discard_buffer(struct buffer_head * bh) * point. Because the caller is about to free (and possibly reuse) those * blocks on-disk. */ -void block_invalidatepage(struct page *page, unsigned long offset) +void block_invalidatepage(struct page *page, unsigned int offset, + unsigned int length) { struct buffer_head *head, *bh, *next; unsigned int curr_off = 0; + unsigned int stop = length + offset; BUG_ON(!PageLocked(page)); if (!page_has_buffers(page)) goto out; + /* + * Check for overflow + */ + BUG_ON(stop > PAGE_CACHE_SIZE || stop < length); + head = page_buffers(page); bh = head; do { @@ -1527,6 +1547,12 @@ void block_invalidatepage(struct page *page, unsigned long offset) next = bh->b_this_page; /* + * Are we still fully in range ? + */ + if (next_off > stop) + goto out; + + /* * is this block fully invalidated? */ if (offset <= curr_off) @@ -1547,6 +1573,7 @@ out: } EXPORT_SYMBOL(block_invalidatepage); + /* * We attach and possibly dirty the buffers atomically wrt * __set_page_dirty_buffers() via private_lock. try_to_free_buffers @@ -1615,6 +1642,28 @@ void unmap_underlying_metadata(struct block_device *bdev, sector_t block) EXPORT_SYMBOL(unmap_underlying_metadata); /* + * Size is a power-of-two in the range 512..PAGE_SIZE, + * and the case we care about most is PAGE_SIZE. + * + * So this *could* possibly be written with those + * constraints in mind (relevant mostly if some + * architecture has a slow bit-scan instruction) + */ +static inline int block_size_bits(unsigned int blocksize) +{ + return ilog2(blocksize); +} + +static struct buffer_head *create_page_buffers(struct page *page, struct inode *inode, unsigned int b_state) +{ + BUG_ON(!PageLocked(page)); + + if (!page_has_buffers(page)) + create_empty_buffers(page, 1 << ACCESS_ONCE(inode->i_blkbits), b_state); + return page_buffers(page); +} + +/* * NOTE! All mapped/uptodate combinations are valid: * * Mapped Uptodate Meaning @@ -1638,25 +1687,26 @@ EXPORT_SYMBOL(unmap_underlying_metadata); * locked buffer. This only can happen if someone has written the buffer * directly, with submit_bh(). At the address_space level PageWriteback * prevents this contention from occurring. + * + * If block_write_full_page() is called with wbc->sync_mode == + * WB_SYNC_ALL, the writes are posted using WRITE_SYNC; this + * causes the writes to be flagged as synchronous writes. */ static int __block_write_full_page(struct inode *inode, struct page *page, - get_block_t *get_block, struct writeback_control *wbc) + get_block_t *get_block, struct writeback_control *wbc, + bh_end_io_t *handler) { int err; sector_t block; sector_t last_block; struct buffer_head *bh, *head; - const unsigned blocksize = 1 << inode->i_blkbits; + unsigned int blocksize, bbits; int nr_underway = 0; + int write_op = (wbc->sync_mode == WB_SYNC_ALL ? + WRITE_SYNC : WRITE); - BUG_ON(!PageLocked(page)); - - last_block = (i_size_read(inode) - 1) >> inode->i_blkbits; - - if (!page_has_buffers(page)) { - create_empty_buffers(page, blocksize, + head = create_page_buffers(page, inode, (1 << BH_Dirty)|(1 << BH_Uptodate)); - } /* * Be very careful. We have no exclusion from __set_page_dirty_buffers @@ -1668,9 +1718,12 @@ static int __block_write_full_page(struct inode *inode, struct page *page, * handle that here by just cleaning them. */ - block = (sector_t)page->index << (PAGE_CACHE_SHIFT - inode->i_blkbits); - head = page_buffers(page); bh = head; + blocksize = bh->b_size; + bbits = block_size_bits(blocksize); + + block = (sector_t)page->index << (PAGE_CACHE_SHIFT - bbits); + last_block = (i_size_read(inode) - 1) >> bbits; /* * Get all the dirty buffers mapped to disk addresses and @@ -1688,11 +1741,13 @@ 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); @@ -1710,18 +1765,18 @@ static int __block_write_full_page(struct inode *inode, struct page *page, /* * If it's a fully non-blocking write attempt and we cannot * lock the buffer then redirty the page. Note that this can - * potentially cause a busy-wait loop from pdflush and kswapd - * activity, but those code paths have their own higher-level - * throttling. + * potentially cause a busy-wait loop from writeback threads + * and kswapd activity, but those code paths have their own + * higher-level throttling. */ - if (wbc->sync_mode != WB_SYNC_NONE || !wbc->nonblocking) { + if (wbc->sync_mode != WB_SYNC_NONE) { lock_buffer(bh); - } else if (test_set_buffer_locked(bh)) { + } else if (!trylock_buffer(bh)) { redirty_page_for_writepage(wbc, page); continue; } if (test_clear_buffer_dirty(bh)) { - mark_buffer_async_write(bh); + mark_buffer_async_write_endio(bh, handler); } else { unlock_buffer(bh); } @@ -1737,7 +1792,7 @@ static int __block_write_full_page(struct inode *inode, struct page *page, do { struct buffer_head *next = bh->b_this_page; if (buffer_async_write(bh)) { - submit_bh(WRITE, bh); + submit_bh(write_op, bh); nr_underway++; } bh = next; @@ -1771,9 +1826,10 @@ 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); + mark_buffer_async_write_endio(bh, handler); } else { /* * The buffer may have been set dirty during @@ -1790,7 +1846,7 @@ recover: struct buffer_head *next = bh->b_this_page; if (buffer_async_write(bh)) { clear_buffer_dirty(bh); - submit_bh(WRITE, bh); + submit_bh(write_op, bh); nr_underway++; } bh = next; @@ -1841,9 +1897,12 @@ void page_zero_new_buffers(struct page *page, unsigned from, unsigned to) } 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) +int __block_write_begin(struct page *page, loff_t pos, unsigned len, + get_block_t *get_block) { + unsigned from = pos & (PAGE_CACHE_SIZE - 1); + unsigned to = from + len; + struct inode *inode = page->mapping->host; unsigned block_start, block_end; sector_t block; int err = 0; @@ -1855,12 +1914,10 @@ static int __block_prepare_write(struct inode *inode, struct page *page, BUG_ON(to > PAGE_CACHE_SIZE); BUG_ON(from > to); - blocksize = 1 << inode->i_blkbits; - if (!page_has_buffers(page)) - create_empty_buffers(page, blocksize, 0); - head = page_buffers(page); + head = create_page_buffers(page, inode, 0); + blocksize = head->b_size; + bbits = block_size_bits(blocksize); - bbits = inode->i_blkbits; block = (sector_t)page->index << (PAGE_CACHE_SHIFT - bbits); for(bh = head, block_start = 0; bh != head || !block_start; @@ -1920,6 +1977,7 @@ static int __block_prepare_write(struct inode *inode, struct page *page, page_zero_new_buffers(page, from, to); return err; } +EXPORT_SYMBOL(__block_write_begin); static int __block_commit_write(struct inode *inode, struct page *page, unsigned from, unsigned to) @@ -1929,11 +1987,11 @@ static int __block_commit_write(struct inode *inode, struct page *page, unsigned blocksize; struct buffer_head *bh, *head; - blocksize = 1 << inode->i_blkbits; + bh = head = page_buffers(page); + blocksize = bh->b_size; - for(bh = head = page_buffers(page), block_start = 0; - bh != head || !block_start; - block_start=block_end, bh = bh->b_this_page) { + block_start = 0; + do { block_end = block_start + blocksize; if (block_end <= from || block_start >= to) { if (!buffer_uptodate(bh)) @@ -1943,7 +2001,10 @@ static int __block_commit_write(struct inode *inode, struct page *page, mark_buffer_dirty(bh); } clear_buffer_new(bh); - } + + block_start = block_end; + bh = bh->b_this_page; + } while (bh != head); /* * If this is a partial write which happened to make all buffers @@ -1960,59 +2021,27 @@ 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. + * The filesystem needs to handle block truncation upon 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) +int block_write_begin(struct address_space *mapping, loff_t pos, unsigned len, + unsigned flags, struct page **pagep, get_block_t *get_block) { - struct inode *inode = mapping->host; - int status = 0; + pgoff_t index = pos >> PAGE_CACHE_SHIFT; struct page *page; - pgoff_t index; - unsigned start, end; - int ownpage = 0; + int status; - 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(mapping, index); - if (!page) { - status = -ENOMEM; - goto out; - } - *pagep = page; - } else - BUG_ON(!PageLocked(page)); + page = grab_cache_page_write_begin(mapping, index, flags); + if (!page) + return -ENOMEM; - status = __block_prepare_write(inode, page, start, end, get_block); + status = __block_write_begin(page, pos, len, 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); - } - goto out; + unlock_page(page); + page_cache_release(page); + page = NULL; } -out: + *pagep = page; return status; } EXPORT_SYMBOL(block_write_begin); @@ -2058,6 +2087,7 @@ int generic_write_end(struct file *file, struct address_space *mapping, 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); @@ -2070,17 +2100,71 @@ int generic_write_end(struct file *file, struct address_space *mapping, */ if (pos+copied > inode->i_size) { i_size_write(inode, pos+copied); - mark_inode_dirty(inode); + 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, unsigned long from, + unsigned long count) +{ + unsigned block_start, block_end, blocksize; + unsigned to; + struct buffer_head *bh, *head; + int ret = 1; + + if (!page_has_buffers(page)) + return 0; + + head = page_buffers(page); + blocksize = head->b_size; + to = min_t(unsigned, PAGE_CACHE_SIZE - from, count); + to = from + to; + if (from < blocksize && to > PAGE_CACHE_SIZE - blocksize) + return 0; + + 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 @@ -2092,18 +2176,16 @@ int block_read_full_page(struct page *page, get_block_t *get_block) struct inode *inode = page->mapping->host; sector_t iblock, lblock; struct buffer_head *bh, *head, *arr[MAX_BUF_PER_PAGE]; - unsigned int blocksize; + unsigned int blocksize, bbits; int nr, i; int fully_mapped = 1; - BUG_ON(!PageLocked(page)); - blocksize = 1 << inode->i_blkbits; - if (!page_has_buffers(page)) - create_empty_buffers(page, blocksize, 0); - head = page_buffers(page); + head = create_page_buffers(page, inode, 0); + blocksize = head->b_size; + bbits = block_size_bits(blocksize); - iblock = (sector_t)page->index << (PAGE_CACHE_SHIFT - inode->i_blkbits); - lblock = (i_size_read(inode)+blocksize-1) >> inode->i_blkbits; + iblock = (sector_t)page->index << (PAGE_CACHE_SHIFT - bbits); + lblock = (i_size_read(inode)+blocksize-1) >> bbits; bh = head; nr = 0; i = 0; @@ -2173,6 +2255,7 @@ int block_read_full_page(struct page *page, get_block_t *get_block) } return 0; } +EXPORT_SYMBOL(block_read_full_page); /* utility function for filesystems that need to do work on expanding * truncates. Uses filesystem pagecache writes to allow the filesystem to @@ -2183,16 +2266,10 @@ 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; - err = -EFBIG; - limit = current->signal->rlim[RLIMIT_FSIZE].rlim_cur; - if (limit != RLIM_INFINITY && size > (loff_t)limit) { - send_sig(SIGXFSZ, current, 0); - goto out; - } - if (size > inode->i_sb->s_maxbytes) + err = inode_newsize_ok(inode, size); + if (err) goto out; err = pagecache_write_begin(NULL, mapping, size, 0, @@ -2207,9 +2284,10 @@ int generic_cont_expand_simple(struct inode *inode, loff_t size) out: return err; } +EXPORT_SYMBOL(generic_cont_expand_simple); -int cont_expand_zero(struct file *file, struct address_space *mapping, - loff_t pos, loff_t *bytes) +static int cont_expand_zero(struct file *file, struct address_space *mapping, + loff_t pos, loff_t *bytes) { struct inode *inode = mapping->host; unsigned blocksize = 1 << inode->i_blkbits; @@ -2243,6 +2321,8 @@ int cont_expand_zero(struct file *file, struct address_space *mapping, goto out; BUG_ON(err != len); err = 0; + + balance_dirty_pages_ratelimited(mapping); } /* page covers the boundary, find the boundary offset */ @@ -2291,7 +2371,7 @@ int cont_write_begin(struct file *file, struct address_space *mapping, err = cont_expand_zero(file, mapping, pos, bytes); if (err) - goto out; + return err; zerofrom = *bytes & ~PAGE_CACHE_MASK; if (pos+len > *bytes && zerofrom & (blocksize-1)) { @@ -2299,22 +2379,9 @@ int cont_write_begin(struct file *file, struct address_space *mapping, (*bytes)++; } - *pagep = NULL; - err = block_write_begin(file, mapping, pos, len, - flags, pagep, fsdata, get_block); -out: - return err; -} - -int block_prepare_write(struct page *page, unsigned from, unsigned to, - get_block_t *get_block) -{ - struct inode *inode = page->mapping->host; - int err = __block_prepare_write(inode, page, from, to, get_block); - if (err) - ClearPageUptodate(page); - return err; + return block_write_begin(mapping, pos, len, flags, pagep, get_block); } +EXPORT_SYMBOL(cont_write_begin); int block_commit_write(struct page *page, unsigned from, unsigned to) { @@ -2322,23 +2389,7 @@ int block_commit_write(struct page *page, unsigned from, unsigned to) __block_commit_write(inode,page,from,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; -} +EXPORT_SYMBOL(block_commit_write); /* * block_page_mkwrite() is not allowed to change the file size as it gets @@ -2350,25 +2401,29 @@ int generic_commit_write(struct file *file, struct page *page, * * We are not allowed to take the i_mutex here so we have to play games to * protect against truncate races as the page could now be beyond EOF. Because - * vmtruncate() writes the inode size before removing pages, once we have the + * truncate writes the inode size before removing pages, once we have the * page lock we can determine safely if the page is beyond EOF. If it is not * beyond EOF, then the page is guaranteed safe against truncation until we * unlock the page. + * + * Direct callers of this function should protect against filesystem freezing + * using sb_start_write() - sb_end_write() functions. */ -int -block_page_mkwrite(struct vm_area_struct *vma, struct page *page, - get_block_t get_block) +int __block_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf, + get_block_t get_block) { - struct inode *inode = vma->vm_file->f_path.dentry->d_inode; + struct page *page = vmf->page; + struct inode *inode = file_inode(vma->vm_file); unsigned long end; loff_t size; - int ret = -EINVAL; + int ret; lock_page(page); size = i_size_read(inode); if ((page->mapping != inode->i_mapping) || (page_offset(page) > size)) { - /* page got truncated out from underneath us */ + /* We overload EFAULT to mean page got truncated */ + ret = -EFAULT; goto out_unlock; } @@ -2378,14 +2433,40 @@ block_page_mkwrite(struct vm_area_struct *vma, struct page *page, else end = PAGE_CACHE_SIZE; - ret = block_prepare_write(page, 0, end, get_block); + ret = __block_write_begin(page, 0, end, get_block); if (!ret) ret = block_commit_write(page, 0, end); + if (unlikely(ret < 0)) + goto out_unlock; + set_page_dirty(page); + wait_for_stable_page(page); + return 0; out_unlock: unlock_page(page); return ret; } +EXPORT_SYMBOL(__block_page_mkwrite); + +int block_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf, + get_block_t get_block) +{ + int ret; + struct super_block *sb = file_inode(vma->vm_file)->i_sb; + + sb_start_pagefault(sb); + + /* + * Update file times before taking page lock. We may end up failing the + * fault so this update may be superfluous but who really cares... + */ + file_update_time(vma->vm_file); + + ret = __block_page_mkwrite(vma, vmf, get_block); + sb_end_pagefault(sb); + return block_page_mkwrite_return(ret); +} +EXPORT_SYMBOL(block_page_mkwrite); /* * nobh_write_begin()'s prereads are special: the buffer_heads are freed @@ -2424,8 +2505,9 @@ static void attach_nobh_buffers(struct page *page, struct buffer_head *head) /* * On entry, the page is fully not uptodate. * On exit the page is fully uptodate in the areas outside (from,to) + * The filesystem needs to handle block truncation upon failure. */ -int nobh_write_begin(struct file *file, struct address_space *mapping, +int nobh_write_begin(struct address_space *mapping, loff_t pos, unsigned len, unsigned flags, struct page **pagep, void **fsdata, get_block_t *get_block) @@ -2448,18 +2530,17 @@ int nobh_write_begin(struct file *file, struct address_space *mapping, from = pos & (PAGE_CACHE_SIZE - 1); to = from + len; - page = __grab_cache_page(mapping, index); + 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); + ret = __block_write_begin(page, pos, len, get_block); + if (unlikely(ret)) + goto out_release; + return ret; } if (PageMappedToDisk(page)) @@ -2563,9 +2644,6 @@ out_release: page_cache_release(page); *pagep = NULL; - if (pos + len > inode->i_size) - vmtruncate(inode, inode->i_size); - return ret; } EXPORT_SYMBOL(nobh_write_begin); @@ -2579,7 +2657,7 @@ int nobh_write_end(struct file *file, struct address_space *mapping, struct buffer_head *bh; BUG_ON(fsdata != NULL && page_has_buffers(page)); - if (unlikely(copied < len) && !page_has_buffers(page)) + if (unlikely(copied < len) && head) attach_nobh_buffers(page, head); if (page_has_buffers(page)) return generic_write_end(file, mapping, pos, len, @@ -2651,7 +2729,8 @@ int nobh_writepage(struct page *page, get_block_t *get_block, out: ret = mpage_writepage(page, get_block, wbc); if (ret == -EAGAIN) - ret = __block_write_full_page(inode, page, get_block, wbc); + ret = __block_write_full_page(inode, page, get_block, wbc, + end_buffer_async_write); return ret; } EXPORT_SYMBOL(nobh_writepage); @@ -2698,6 +2777,8 @@ has_buffers: pos += blocksize; } + map_bh.b_size = blocksize; + map_bh.b_state = 0; err = get_block(inode, iblock, &map_bh, 0); if (err) goto unlock; @@ -2806,6 +2887,7 @@ unlock: out: return err; } +EXPORT_SYMBOL(block_truncate_page); /* * The generic ->writepage function for buffer-backed address_spaces @@ -2820,7 +2902,8 @@ int block_write_full_page(struct page *page, get_block_t *get_block, /* Is the page fully inside i_size? */ if (page->index < end_index) - return __block_write_full_page(inode, page, get_block, wbc); + return __block_write_full_page(inode, page, get_block, wbc, + end_buffer_async_write); /* Is the page fully outside i_size? (truncate in progress) */ offset = i_size & (PAGE_CACHE_SIZE-1); @@ -2830,21 +2913,23 @@ int block_write_full_page(struct page *page, get_block_t *get_block, * they may have been added in ext3_writepage(). Make them * freeable here, so the page does not leak. */ - do_invalidatepage(page, 0); + do_invalidatepage(page, 0, PAGE_CACHE_SIZE); unlock_page(page); return 0; /* don't care */ } /* * The page straddles i_size. It must be zeroed out on each and every - * writepage invokation because it may be mmapped. "A file is mapped + * writepage invocation because it may be mmapped. "A file is mapped * in multiples of the page size. For a file that is not a multiple of * the page size, the remaining memory is zeroed when mapped, and * writes to that region are not written out to the file." */ zero_user_segment(page, offset, PAGE_CACHE_SIZE); - return __block_write_full_page(inode, page, get_block, wbc); + return __block_write_full_page(inode, page, get_block, wbc, + end_buffer_async_write); } +EXPORT_SYMBOL(block_write_full_page); sector_t generic_block_bmap(struct address_space *mapping, sector_t block, get_block_t *get_block) @@ -2857,6 +2942,7 @@ sector_t generic_block_bmap(struct address_space *mapping, sector_t block, get_block(inode, block, &tmp, 0); return tmp.b_blocknr; } +EXPORT_SYMBOL(generic_block_bmap); static void end_bio_bh_io_sync(struct bio *bio, int err) { @@ -2864,14 +2950,66 @@ static void end_bio_bh_io_sync(struct bio *bio, int err) if (err == -EOPNOTSUPP) { set_bit(BIO_EOPNOTSUPP, &bio->bi_flags); - 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); } -int submit_bh(int rw, struct buffer_head * bh) +/* + * This allows us to do IO even on the odd last sectors + * of a device, even if the bh block size is some multiple + * of the physical sector size. + * + * We'll just truncate the bio to the size of the device, + * and clear the end of the buffer head manually. + * + * Truly out-of-range accesses will turn into actual IO + * errors, this only handles the "we need to be able to + * do IO at the final sector" case. + */ +static void guard_bh_eod(int rw, struct bio *bio, struct buffer_head *bh) +{ + sector_t maxsector; + unsigned bytes; + + maxsector = i_size_read(bio->bi_bdev->bd_inode) >> 9; + if (!maxsector) + return; + + /* + * If the *whole* IO is past the end of the device, + * let it through, and the IO layer will turn it into + * an EIO. + */ + if (unlikely(bio->bi_iter.bi_sector >= maxsector)) + return; + + maxsector -= bio->bi_iter.bi_sector; + bytes = bio->bi_iter.bi_size; + if (likely((bytes >> 9) <= maxsector)) + return; + + /* Uhhuh. We've got a bh that straddles the device size! */ + bytes = maxsector << 9; + + /* Truncate the bio.. */ + bio->bi_iter.bi_size = bytes; + bio->bi_io_vec[0].bv_len = bytes; + + /* ..and clear the end of the buffer for reads */ + if ((rw & RW_MASK) == READ) { + void *kaddr = kmap_atomic(bh->b_page); + memset(kaddr + bh_offset(bh) + bytes, 0, bh->b_size - bytes); + kunmap_atomic(kaddr); + flush_dcache_page(bh->b_page); + } +} + +int _submit_bh(int rw, struct buffer_head *bh, unsigned long bio_flags) { struct bio *bio; int ret = 0; @@ -2879,15 +3017,13 @@ int submit_bh(int rw, struct buffer_head * bh) BUG_ON(!buffer_locked(bh)); BUG_ON(!buffer_mapped(bh)); BUG_ON(!bh->b_end_io); - - if (buffer_ordered(bh) && (rw == WRITE)) - rw = WRITE_BARRIER; + BUG_ON(buffer_delay(bh)); + BUG_ON(buffer_unwritten(bh)); /* - * 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); /* @@ -2896,18 +3032,26 @@ int submit_bh(int rw, struct buffer_head * bh) */ bio = bio_alloc(GFP_NOIO, 1); - bio->bi_sector = bh->b_blocknr * (bh->b_size >> 9); + bio->bi_iter.bi_sector = bh->b_blocknr * (bh->b_size >> 9); bio->bi_bdev = bh->b_bdev; bio->bi_io_vec[0].bv_page = bh->b_page; bio->bi_io_vec[0].bv_len = bh->b_size; bio->bi_io_vec[0].bv_offset = bh_offset(bh); bio->bi_vcnt = 1; - bio->bi_idx = 0; - bio->bi_size = bh->b_size; + bio->bi_iter.bi_size = bh->b_size; bio->bi_end_io = end_bio_bh_io_sync; bio->bi_private = bh; + bio->bi_flags |= bio_flags; + + /* Take care of bh's that straddle the end of the device */ + guard_bh_eod(rw, bio, bh); + + if (buffer_meta(bh)) + rw |= REQ_META; + if (buffer_prio(bh)) + rw |= REQ_PRIO; bio_get(bio); submit_bio(rw, bio); @@ -2918,28 +3062,34 @@ int submit_bh(int rw, struct buffer_head * bh) bio_put(bio); return ret; } +EXPORT_SYMBOL_GPL(_submit_bh); + +int submit_bh(int rw, struct buffer_head *bh) +{ + return _submit_bh(rw, bh, 0); +} +EXPORT_SYMBOL(submit_bh); /** * ll_rw_block: low-level access to block devices (DEPRECATED) - * @rw: whether to %READ or %WRITE or %SWRITE or maybe %READA (readahead) + * @rw: whether to %READ or %WRITE or maybe %READA (readahead) * @nr: number of &struct buffer_heads in the array * @bhs: array of pointers to &struct buffer_head * * ll_rw_block() takes an array of pointers to &struct buffer_heads, and * requests an I/O operation on them, either a %READ or a %WRITE. The third - * %SWRITE is like %WRITE only we make sure that the *current* data in buffers - * are sent to disk. The fourth %READA option is described in the documentation - * for generic_make_request() which ll_rw_block() calls. + * %READA option is described in the documentation for generic_make_request() + * which ll_rw_block() calls. * * This function drops any buffer that it cannot get a lock on (with the - * BH_Lock state bit) unless SWRITE is required, any buffer that appears to be - * clean when doing a write request, and any buffer that appears to be - * up-to-date when doing read request. Further it marks as clean buffers that - * are processed for writing (the buffer cache won't assume that they are - * actually clean until the buffer gets unlocked). + * BH_Lock state bit), any buffer that appears to be clean when doing a write + * request, and any buffer that appears to be up-to-date when doing read + * request. Further it marks as clean buffers that are processed for + * writing (the buffer cache won't assume that they are actually clean + * until the buffer gets unlocked). * * ll_rw_block sets b_end_io to simple completion handler that marks - * the buffer up-to-date (if approriate), unlocks the buffer and wakes + * the buffer up-to-date (if appropriate), unlocks the buffer and wakes * any waiters. * * All of the buffers must be for the same device, and must also be a @@ -2952,12 +3102,9 @@ 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) - lock_buffer(bh); - else if (test_set_buffer_locked(bh)) + if (!trylock_buffer(bh)) continue; - - if (rw == WRITE || rw == SWRITE) { + if (rw == WRITE) { if (test_clear_buffer_dirty(bh)) { bh->b_end_io = end_buffer_write_sync; get_bh(bh); @@ -2975,13 +3122,27 @@ void ll_rw_block(int rw, int nr, struct buffer_head *bhs[]) unlock_buffer(bh); } } +EXPORT_SYMBOL(ll_rw_block); + +void write_dirty_buffer(struct buffer_head *bh, int rw) +{ + lock_buffer(bh); + if (!test_clear_buffer_dirty(bh)) { + unlock_buffer(bh); + return; + } + bh->b_end_io = end_buffer_write_sync; + get_bh(bh); + submit_bh(rw, bh); +} +EXPORT_SYMBOL(write_dirty_buffer); /* * For a data-integrity writeout, we need to wait upon any in-progress I/O * and then start new I/O and then wait upon it. The caller must have a ref on * the buffer_head. */ -int sync_dirty_buffer(struct buffer_head *bh) +int __sync_dirty_buffer(struct buffer_head *bh, int rw) { int ret = 0; @@ -2990,12 +3151,8 @@ int sync_dirty_buffer(struct buffer_head *bh) if (test_clear_buffer_dirty(bh)) { get_bh(bh); bh->b_end_io = end_buffer_write_sync; - ret = submit_bh(WRITE, bh); + ret = submit_bh(rw, bh); wait_on_buffer(bh); - if (buffer_eopnotsupp(bh)) { - clear_buffer_eopnotsupp(bh); - ret = -EOPNOTSUPP; - } if (!ret && !buffer_uptodate(bh)) ret = -EIO; } else { @@ -3003,6 +3160,13 @@ int sync_dirty_buffer(struct buffer_head *bh) } return ret; } +EXPORT_SYMBOL(__sync_dirty_buffer); + +int sync_dirty_buffer(struct buffer_head *bh) +{ + return __sync_dirty_buffer(bh, WRITE_SYNC); +} +EXPORT_SYMBOL(sync_dirty_buffer); /* * try_to_free_buffers() checks if all the buffers on this particular page @@ -3108,24 +3272,14 @@ out: } EXPORT_SYMBOL(try_to_free_buffers); -void block_sync_page(struct page *page) -{ - struct address_space *mapping; - - smp_mb(); - mapping = page_mapping(page); - if (mapping) - blk_run_backing_dev(mapping->backing_dev_info, page); -} - /* * There are no bdflush tunables left. But distributions are * still running obsolete flush daemons, so we terminate them here. * * Use of bdflush() is deprecated and will be removed in a future kernel. - * The `pdflush' kernel threads fully replace bdflush daemons and this call. + * The `flush-X' 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; @@ -3148,13 +3302,13 @@ asmlinkage long sys_bdflush(int func, long data) /* * Buffer-head allocation */ -static struct kmem_cache *bh_cachep; +static struct kmem_cache *bh_cachep __read_mostly; /* * Once the number of bh's in the machine exceeds this level, we start * stripping them in writeback. */ -static int max_buffer_heads; +static unsigned long max_buffer_heads; int buffer_heads_over_limit; @@ -3170,23 +3324,23 @@ static void recalc_bh_state(void) int i; int tot = 0; - if (__get_cpu_var(bh_accounting).ratelimit++ < 4096) + if (__this_cpu_inc_return(bh_accounting.ratelimit) - 1 < 4096) return; - __get_cpu_var(bh_accounting).ratelimit = 0; + __this_cpu_write(bh_accounting.ratelimit, 0); for_each_online_cpu(i) tot += per_cpu(bh_accounting, i).nr; buffer_heads_over_limit = (tot > max_buffer_heads); } - + struct buffer_head *alloc_buffer_head(gfp_t gfp_flags) { - struct buffer_head *ret = kmem_cache_alloc(bh_cachep, - set_migrateflags(gfp_flags, __GFP_RECLAIMABLE)); + struct buffer_head *ret = kmem_cache_zalloc(bh_cachep, gfp_flags); if (ret) { INIT_LIST_HEAD(&ret->b_assoc_buffers); - get_cpu_var(bh_accounting).nr++; + preempt_disable(); + __this_cpu_inc(bh_accounting.nr); recalc_bh_state(); - put_cpu_var(bh_accounting); + preempt_enable(); } return ret; } @@ -3196,9 +3350,10 @@ void free_buffer_head(struct buffer_head *bh) { BUG_ON(!list_empty(&bh->b_assoc_buffers)); kmem_cache_free(bh_cachep, bh); - get_cpu_var(bh_accounting).nr--; + preempt_disable(); + __this_cpu_dec(bh_accounting.nr); recalc_bh_state(); - put_cpu_var(bh_accounting); + preempt_enable(); } EXPORT_SYMBOL(free_buffer_head); @@ -3211,9 +3366,8 @@ static void buffer_exit_cpu(int cpu) brelse(b->bhs[i]); b->bhs[i] = NULL; } - get_cpu_var(bh_accounting).nr += per_cpu(bh_accounting, cpu).nr; + this_cpu_add(bh_accounting.nr, per_cpu(bh_accounting, cpu).nr); per_cpu(bh_accounting, cpu).nr = 0; - put_cpu_var(bh_accounting); } static int buffer_cpu_notify(struct notifier_block *self, @@ -3268,24 +3422,15 @@ int bh_submit_read(struct buffer_head *bh) } EXPORT_SYMBOL(bh_submit_read); -static void -init_buffer_head(struct kmem_cache *cachep, 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; + unsigned long nrpages; bh_cachep = kmem_cache_create("buffer_head", sizeof(struct buffer_head), 0, (SLAB_RECLAIM_ACCOUNT|SLAB_PANIC| SLAB_MEM_SPREAD), - init_buffer_head); + NULL); /* * Limit the bh occupancy to 10% of ZONE_NORMAL @@ -3294,29 +3439,3 @@ void __init buffer_init(void) max_buffer_heads = nrpages * (PAGE_SIZE / sizeof(struct buffer_head)); hotcpu_notifier(buffer_cpu_notify, 0); } - -EXPORT_SYMBOL(__bforget); -EXPORT_SYMBOL(__brelse); -EXPORT_SYMBOL(__wait_on_buffer); -EXPORT_SYMBOL(block_commit_write); -EXPORT_SYMBOL(block_prepare_write); -EXPORT_SYMBOL(block_page_mkwrite); -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_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_simple); -EXPORT_SYMBOL(init_buffer); -EXPORT_SYMBOL(invalidate_bdev); -EXPORT_SYMBOL(ll_rw_block); -EXPORT_SYMBOL(mark_buffer_dirty); -EXPORT_SYMBOL(submit_bh); -EXPORT_SYMBOL(sync_dirty_buffer); -EXPORT_SYMBOL(unlock_buffer); |