X-Git-Url: http://git.onelab.eu/?a=blobdiff_plain;f=fs%2Fbuffer.c;h=670a36e2c2aaa5b9e2314be9f80f775b19501724;hb=refs%2Fheads%2Fvserver;hp=a61beb1b1e228391f2b58a4bfb21425e82fae2ed;hpb=7172c64a7cee4dfa95864f49c914f7ea8cf497c8;p=linux-2.6.git diff --git a/fs/buffer.c b/fs/buffer.c index a61beb1b1..670a36e2c 100644 --- a/fs/buffer.c +++ b/fs/buffer.c @@ -35,6 +35,7 @@ #include #include #include +#include #include #include #include @@ -77,6 +78,7 @@ EXPORT_SYMBOL(__lock_buffer); void fastcall unlock_buffer(struct buffer_head *bh) { + smp_mb__before_clear_bit(); clear_buffer_locked(bh); smp_mb__after_clear_bit(); wake_up_bit(&bh->b_state, BH_Lock); @@ -159,31 +161,6 @@ int sync_blockdev(struct block_device *bdev) } EXPORT_SYMBOL(sync_blockdev); -static void __fsync_super(struct super_block *sb) -{ - sync_inodes_sb(sb, 0); - DQUOT_SYNC(sb); - lock_super(sb); - if (sb->s_dirt && sb->s_op->write_super) - sb->s_op->write_super(sb); - unlock_super(sb); - if (sb->s_op->sync_fs) - sb->s_op->sync_fs(sb, 1); - sync_blockdev(sb->s_bdev); - sync_inodes_sb(sb, 1); -} - -/* - * Write out and wait upon all dirty data associated with this - * superblock. Filesystem data as well as the underlying block - * device. Takes the superblock lock. - */ -int fsync_super(struct super_block *sb) -{ - __fsync_super(sb); - return sync_blockdev(sb->s_bdev); -} - EXPORT_SYMBOL(fsync_super); /* @@ -206,7 +183,7 @@ int fsync_bdev(struct block_device *bdev) * freeze_bdev -- lock a filesystem and force it into a consistent state * @bdev: blockdevice to lock * - * This takes the block device bd_mount_mutex to make sure no new mounts + * 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. @@ -215,7 +192,7 @@ struct super_block *freeze_bdev(struct block_device *bdev) { struct super_block *sb; - mutex_lock(&bdev->bd_mount_mutex); + down(&bdev->bd_mount_sem); sb = get_super(bdev); if (sb && !(sb->s_flags & MS_RDONLY)) { sb->s_frozen = SB_FREEZE_WRITE; @@ -257,122 +234,10 @@ void thaw_bdev(struct block_device *bdev, struct super_block *sb) drop_super(sb); } - mutex_unlock(&bdev->bd_mount_mutex); + up(&bdev->bd_mount_sem); } EXPORT_SYMBOL(thaw_bdev); -/* - * sync everything. Start out by waking pdflush, because that writes back - * all queues in parallel. - */ -static void do_sync(unsigned long wait) -{ - wakeup_pdflush(0); - sync_inodes(0); /* All mappings, inodes and their blockdevs */ - DQUOT_SYNC(NULL); - sync_supers(); /* Write the superblocks */ - sync_filesystems(0); /* Start syncing the filesystems */ - sync_filesystems(wait); /* Waitingly sync the filesystems */ - sync_inodes(wait); /* Mappings, inodes and blockdevs, again. */ - if (!wait) - printk("Emergency Sync complete\n"); - if (unlikely(laptop_mode)) - laptop_sync_completion(); -} - -asmlinkage long sys_sync(void) -{ - do_sync(1); - return 0; -} - -void emergency_sync(void) -{ - pdflush_operation(do_sync, 0); -} - -/* - * Generic function to fsync a file. - * - * filp may be NULL if called via the msync of a vma. - */ - -int file_fsync(struct file *filp, struct dentry *dentry, int datasync) -{ - struct inode * inode = dentry->d_inode; - struct super_block * sb; - int ret, err; - - /* sync the inode to buffers */ - ret = write_inode_now(inode, 0); - - /* sync the superblock to buffers */ - sb = inode->i_sb; - lock_super(sb); - if (sb->s_op->write_super) - sb->s_op->write_super(sb); - unlock_super(sb); - - /* .. finally sync the buffers to disk */ - err = sync_blockdev(sb->s_bdev); - if (!ret) - ret = err; - return ret; -} - -long do_fsync(struct file *file, int datasync) -{ - int ret; - int err; - struct address_space *mapping = file->f_mapping; - - if (!file->f_op || !file->f_op->fsync) { - /* Why? We can still call filemap_fdatawrite */ - ret = -EINVAL; - goto out; - } - - ret = filemap_fdatawrite(mapping); - - /* - * We need to protect against concurrent writers, which could cause - * livelocks in fsync_buffers_list(). - */ - mutex_lock(&mapping->host->i_mutex); - err = file->f_op->fsync(file, file->f_dentry, datasync); - if (!ret) - ret = err; - mutex_unlock(&mapping->host->i_mutex); - err = filemap_fdatawait(mapping); - if (!ret) - ret = err; -out: - return ret; -} - -static long __do_fsync(unsigned int fd, int datasync) -{ - struct file *file; - int ret = -EBADF; - - file = fget(fd); - if (file) { - ret = do_fsync(file, datasync); - fput(file); - } - return ret; -} - -asmlinkage long sys_fsync(unsigned int fd) -{ - return __do_fsync(fd, 0); -} - -asmlinkage long sys_fdatasync(unsigned int fd) -{ - return __do_fsync(fd, 1); -} - /* * Various filesystems appear to want __find_get_block to be non-blocking. * But it's the page lock which protects the buffers. To get around this, @@ -591,6 +456,7 @@ static void end_buffer_async_write(struct buffer_head *bh, int uptodate) bdevname(bh->b_bdev, b)); } set_bit(AS_EIO, &page->mapping->flags); + set_buffer_write_io_error(bh); clear_buffer_uptodate(bh); SetPageError(page); } @@ -710,6 +576,10 @@ EXPORT_SYMBOL(mark_buffer_async_write); static inline void __remove_assoc_queue(struct buffer_head *bh) { list_del_init(&bh->b_assoc_buffers); + WARN_ON(!bh->b_assoc_map); + if (buffer_write_io_error(bh)) + set_bit(AS_EIO, &bh->b_assoc_map->flags); + bh->b_assoc_map = NULL; } int inode_has_buffers(struct inode *inode) @@ -808,6 +678,7 @@ void mark_buffer_dirty_inode(struct buffer_head *bh, struct inode *inode) spin_lock(&buffer_mapping->private_lock); list_move_tail(&bh->b_assoc_buffers, &mapping->private_list); + bh->b_assoc_map = mapping; spin_unlock(&buffer_mapping->private_lock); } } @@ -857,20 +728,21 @@ int __set_page_dirty_buffers(struct page *page) } spin_unlock(&mapping->private_lock); - if (!TestSetPageDirty(page)) { - write_lock_irq(&mapping->tree_lock); - if (page->mapping) { /* Race with truncate? */ - if (mapping_cap_account_dirty(mapping)) - __inc_zone_page_state(page, NR_FILE_DIRTY); - radix_tree_tag_set(&mapping->page_tree, - page_index(page), - PAGECACHE_TAG_DIRTY); + if (TestSetPageDirty(page)) + return 0; + + write_lock_irq(&mapping->tree_lock); + if (page->mapping) { /* Race with truncate? */ + if (mapping_cap_account_dirty(mapping)) { + __inc_zone_page_state(page, NR_FILE_DIRTY); + task_io_account_write(PAGE_CACHE_SIZE); } - write_unlock_irq(&mapping->tree_lock); - __mark_inode_dirty(mapping->host, I_DIRTY_PAGES); - return 1; + radix_tree_tag_set(&mapping->page_tree, + page_index(page), PAGECACHE_TAG_DIRTY); } - return 0; + write_unlock_irq(&mapping->tree_lock); + __mark_inode_dirty(mapping->host, I_DIRTY_PAGES); + return 1; } EXPORT_SYMBOL(__set_page_dirty_buffers); @@ -904,7 +776,7 @@ static int fsync_buffers_list(spinlock_t *lock, struct list_head *list) spin_lock(lock); while (!list_empty(list)) { bh = BH_ENTRY(list->next); - list_del_init(&bh->b_assoc_buffers); + __remove_assoc_queue(bh); if (buffer_dirty(bh) || buffer_locked(bh)) { list_add(&bh->b_assoc_buffers, &tmp); if (buffer_dirty(bh)) { @@ -925,7 +797,7 @@ static int fsync_buffers_list(spinlock_t *lock, struct list_head *list) while (!list_empty(&tmp)) { bh = BH_ENTRY(tmp.prev); - __remove_assoc_queue(bh); + list_del_init(&bh->b_assoc_buffers); get_bh(bh); spin_unlock(lock); wait_on_buffer(bh); @@ -1306,6 +1178,7 @@ void __bforget(struct buffer_head *bh) spin_lock(&buffer_mapping->private_lock); list_del_init(&bh->b_assoc_buffers); + bh->b_assoc_map = NULL; spin_unlock(&buffer_mapping->private_lock); } __brelse(bh); @@ -1572,35 +1445,6 @@ static void discard_buffer(struct buffer_head * bh) unlock_buffer(bh); } -/** - * try_to_release_page() - release old fs-specific metadata on a page - * - * @page: the page which the kernel is trying to free - * @gfp_mask: memory allocation flags (and I/O mode) - * - * The address_space is to try to release any data against the page - * (presumably at page->private). If the release was successful, return `1'. - * Otherwise return zero. - * - * The @gfp_mask argument specifies whether I/O may be performed to release - * this page (__GFP_IO), and whether the call may block (__GFP_WAIT). - * - * NOTE: @gfp_mask may go away, and this function may become non-blocking. - */ -int try_to_release_page(struct page *page, gfp_t gfp_mask) -{ - struct address_space * const mapping = page->mapping; - - BUG_ON(!PageLocked(page)); - if (PageWriteback(page)) - return 0; - - if (mapping && mapping->a_ops->releasepage) - return mapping->a_ops->releasepage(page, gfp_mask); - return try_to_free_buffers(page); -} -EXPORT_SYMBOL(try_to_release_page); - /** * block_invalidatepage - invalidate part of all of a buffer-backed page * @@ -1652,14 +1496,6 @@ out: } EXPORT_SYMBOL(block_invalidatepage); -void do_invalidatepage(struct page *page, unsigned long offset) -{ - void (*invalidatepage)(struct page *, unsigned long); - invalidatepage = page->mapping->a_ops->invalidatepage ? : - block_invalidatepage; - (*invalidatepage)(page, offset); -} - /* * We attach and possibly dirty the buffers atomically wrt * __set_page_dirty_buffers() via private_lock. try_to_free_buffers @@ -2030,6 +1866,7 @@ static int __block_prepare_write(struct inode *inode, struct page *page, clear_buffer_new(bh); kaddr = kmap_atomic(page, KM_USER0); memset(kaddr+block_start, 0, bh->b_size); + flush_dcache_page(page); kunmap_atomic(kaddr, KM_USER0); set_buffer_uptodate(bh); mark_buffer_dirty(bh); @@ -2536,6 +2373,7 @@ failed: */ kaddr = kmap_atomic(page, KM_USER0); memset(kaddr, 0, PAGE_CACHE_SIZE); + flush_dcache_page(page); kunmap_atomic(kaddr, KM_USER0); SetPageUptodate(page); set_page_dirty(page); @@ -3009,18 +2847,24 @@ int try_to_free_buffers(struct page *page) spin_lock(&mapping->private_lock); ret = drop_buffers(page, &buffers_to_free); + + /* + * If the filesystem writes its buffers by hand (eg ext3) + * then we can have clean buffers against a dirty page. We + * clean the page here; otherwise the VM will never notice + * that the filesystem did any IO at all. + * + * Also, during truncate, discard_buffer will have marked all + * the page's buffers clean. We discover that here and clean + * the page also. + * + * private_lock must be held over this entire operation in order + * to synchronise against __set_page_dirty_buffers and prevent the + * dirty bit from being lost. + */ + if (ret) + cancel_dirty_page(page, PAGE_CACHE_SIZE); spin_unlock(&mapping->private_lock); - if (ret) { - /* - * If the filesystem writes its buffers by hand (eg ext3) - * then we can have clean buffers against a dirty page. We - * clean the page here; otherwise later reattachment of buffers - * could encounter a non-uptodate page, which is unresolvable. - * This only applies in the rare case where try_to_free_buffers - * succeeds but the page is not freed. - */ - clear_page_dirty(page); - } out: if (buffers_to_free) { struct buffer_head *bh = buffers_to_free; @@ -3075,7 +2919,7 @@ asmlinkage long sys_bdflush(int func, long data) /* * Buffer-head allocation */ -static kmem_cache_t *bh_cachep; +static struct kmem_cache *bh_cachep; /* * Once the number of bh's in the machine exceeds this level, we start @@ -3128,7 +2972,7 @@ void free_buffer_head(struct buffer_head *bh) EXPORT_SYMBOL(free_buffer_head); static void -init_buffer_head(void *data, kmem_cache_t *cachep, unsigned long flags) +init_buffer_head(void *data, struct kmem_cache *cachep, unsigned long flags) { if ((flags & (SLAB_CTOR_VERIFY|SLAB_CTOR_CONSTRUCTOR)) == SLAB_CTOR_CONSTRUCTOR) { @@ -3139,7 +2983,6 @@ init_buffer_head(void *data, kmem_cache_t *cachep, unsigned long flags) } } -#ifdef CONFIG_HOTPLUG_CPU static void buffer_exit_cpu(int cpu) { int i; @@ -3161,7 +3004,6 @@ static int buffer_cpu_notify(struct notifier_block *self, buffer_exit_cpu((unsigned long)hcpu); return NOTIFY_OK; } -#endif /* CONFIG_HOTPLUG_CPU */ void __init buffer_init(void) {