Merge branch 'master' into for-2.6.39

6 files changed, 200 insertions, 82 deletions

diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h
index 0c8d97b56f34..3aa0b72b3b94 100644
--- a/fs/ext4/ext4.h
+++ b/fs/ext4/ext4.h
@@ -848,6 +848,7 @@ struct ext4_inode_info {
 	atomic_t i_ioend_count;	/* Number of outstanding io_end structs */
 	/* current io_end structure for async DIO write*/
 	ext4_io_end_t *cur_aio_dio;
+	atomic_t i_aiodio_unwritten; /* Nr. of inflight conversions pending */
 
 	spinlock_t i_block_reservation_lock;
 
@@ -2119,6 +2120,15 @@ static inline void set_bitmap_uptodate(struct buffer_head *bh)
 
 #define in_range(b, first, len)	((b) >= (first) && (b) <= (first) + (len) - 1)
 
+/* For ioend & aio unwritten conversion wait queues */
+#define EXT4_WQ_HASH_SZ		37
+#define ext4_ioend_wq(v)   (&ext4__ioend_wq[((unsigned long)(v)) %\
+					    EXT4_WQ_HASH_SZ])
+#define ext4_aio_mutex(v)  (&ext4__aio_mutex[((unsigned long)(v)) %\
+					     EXT4_WQ_HASH_SZ])
+extern wait_queue_head_t ext4__ioend_wq[EXT4_WQ_HASH_SZ];
+extern struct mutex ext4__aio_mutex[EXT4_WQ_HASH_SZ];
+
 #endif	/* __KERNEL__ */
 
 #endif	/* _EXT4_H */
diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c
index 63a75810b7c3..ccce8a7e94ed 100644
--- a/fs/ext4/extents.c
+++ b/fs/ext4/extents.c
@@ -3174,9 +3174,10 @@ ext4_ext_handle_uninitialized_extents(handle_t *handle, struct inode *inode,
 		 * that this IO needs to convertion to written when IO is
 		 * completed
 		 */
-		if (io)
+		if (io && !(io->flag & EXT4_IO_END_UNWRITTEN)) {
 			io->flag = EXT4_IO_END_UNWRITTEN;
-		else
+			atomic_inc(&EXT4_I(inode)->i_aiodio_unwritten);
+		} else
 			ext4_set_inode_state(inode, EXT4_STATE_DIO_UNWRITTEN);
 		if (ext4_should_dioread_nolock(inode))
 			map->m_flags |= EXT4_MAP_UNINIT;
@@ -3463,9 +3464,10 @@ int ext4_ext_map_blocks(handle_t *handle, struct inode *inode,
 		 * that we need to perform convertion when IO is done.
 		 */
 		if ((flags & EXT4_GET_BLOCKS_PRE_IO)) {
-			if (io)
+			if (io && !(io->flag & EXT4_IO_END_UNWRITTEN)) {
 				io->flag = EXT4_IO_END_UNWRITTEN;
-			else
+				atomic_inc(&EXT4_I(inode)->i_aiodio_unwritten);
+			} else
 				ext4_set_inode_state(inode,
 						     EXT4_STATE_DIO_UNWRITTEN);
 		}
diff --git a/fs/ext4/file.c b/fs/ext4/file.c
index 2e8322c8aa88..7b80d543b89e 100644
--- a/fs/ext4/file.c
+++ b/fs/ext4/file.c
@@ -55,11 +55,47 @@ static int ext4_release_file(struct inode *inode, struct file *filp)
 	return 0;
 }
 
+static void ext4_aiodio_wait(struct inode *inode)
+{
+	wait_queue_head_t *wq = ext4_ioend_wq(inode);
+
+	wait_event(*wq, (atomic_read(&EXT4_I(inode)->i_aiodio_unwritten) == 0));
+}
+
+/*
+ * This tests whether the IO in question is block-aligned or not.
+ * Ext4 utilizes unwritten extents when hole-filling during direct IO, and they
+ * are converted to written only after the IO is complete.  Until they are
+ * mapped, these blocks appear as holes, so dio_zero_block() will assume that
+ * it needs to zero out portions of the start and/or end block.  If 2 AIO
+ * threads are at work on the same unwritten block, they must be synchronized
+ * or one thread will zero the other's data, causing corruption.
+ */
+static int
+ext4_unaligned_aio(struct inode *inode, const struct iovec *iov,
+		   unsigned long nr_segs, loff_t pos)
+{
+	struct super_block *sb = inode->i_sb;
+	int blockmask = sb->s_blocksize - 1;
+	size_t count = iov_length(iov, nr_segs);
+	loff_t final_size = pos + count;
+
+	if (pos >= inode->i_size)
+		return 0;
+
+	if ((pos & blockmask) || (final_size & blockmask))
+		return 1;
+
+	return 0;
+}
+
 static ssize_t
 ext4_file_write(struct kiocb *iocb, const struct iovec *iov,
 		unsigned long nr_segs, loff_t pos)
 {
 	struct inode *inode = iocb->ki_filp->f_path.dentry->d_inode;
+	int unaligned_aio = 0;
+	int ret;
 
 	/*
 	 * If we have encountered a bitmap-format file, the size limit
@@ -78,9 +114,31 @@ ext4_file_write(struct kiocb *iocb, const struct iovec *iov,
 			nr_segs = iov_shorten((struct iovec *)iov, nr_segs,
 					      sbi->s_bitmap_maxbytes - pos);
 		}
+	} else if (unlikely((iocb->ki_filp->f_flags & O_DIRECT) &&
+		   !is_sync_kiocb(iocb))) {
+		unaligned_aio = ext4_unaligned_aio(inode, iov, nr_segs, pos);
 	}
 
-	return generic_file_aio_write(iocb, iov, nr_segs, pos);
+	/* Unaligned direct AIO must be serialized; see comment above */
+	if (unaligned_aio) {
+		static unsigned long unaligned_warn_time;
+
+		/* Warn about this once per day */
+		if (printk_timed_ratelimit(&unaligned_warn_time, 60*60*24*HZ))
+			ext4_msg(inode->i_sb, KERN_WARNING,
+				 "Unaligned AIO/DIO on inode %ld by %s; "
+				 "performance will be poor.",
+				 inode->i_ino, current->comm);
+		mutex_lock(ext4_aio_mutex(inode));
+		ext4_aiodio_wait(inode);
+	}
+
+	ret = generic_file_aio_write(iocb, iov, nr_segs, pos);
+
+	if (unaligned_aio)
+		mutex_unlock(ext4_aio_mutex(inode));
+
+	return ret;
 }
 
 static const struct vm_operations_struct ext4_file_vm_ops = {
diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c
index 851f49b2f9d2..d1fe09aea73d 100644
--- a/fs/ext4/mballoc.c
+++ b/fs/ext4/mballoc.c
@@ -342,10 +342,15 @@ static struct kmem_cache *ext4_free_ext_cachep;
 /* We create slab caches for groupinfo data structures based on the
  * superblock block size.  There will be one per mounted filesystem for
  * each unique s_blocksize_bits */
-#define NR_GRPINFO_CACHES	\
-	(EXT4_MAX_BLOCK_LOG_SIZE - EXT4_MIN_BLOCK_LOG_SIZE + 1)
+#define NR_GRPINFO_CACHES 8
 static struct kmem_cache *ext4_groupinfo_caches[NR_GRPINFO_CACHES];
 
+static const char *ext4_groupinfo_slab_names[NR_GRPINFO_CACHES] = {
+	"ext4_groupinfo_1k", "ext4_groupinfo_2k", "ext4_groupinfo_4k",
+	"ext4_groupinfo_8k", "ext4_groupinfo_16k", "ext4_groupinfo_32k",
+	"ext4_groupinfo_64k", "ext4_groupinfo_128k"
+};
+
 static void ext4_mb_generate_from_pa(struct super_block *sb, void *bitmap,
 					ext4_group_t group);
 static void ext4_mb_generate_from_freelist(struct super_block *sb, void *bitmap,
@@ -2414,6 +2419,55 @@ err_freesgi:
 	return -ENOMEM;
 }
 
+static void ext4_groupinfo_destroy_slabs(void)
+{
+	int i;
+
+	for (i = 0; i < NR_GRPINFO_CACHES; i++) {
+		if (ext4_groupinfo_caches[i])
+			kmem_cache_destroy(ext4_groupinfo_caches[i]);
+		ext4_groupinfo_caches[i] = NULL;
+	}
+}
+
+static int ext4_groupinfo_create_slab(size_t size)
+{
+	static DEFINE_MUTEX(ext4_grpinfo_slab_create_mutex);
+	int slab_size;
+	int blocksize_bits = order_base_2(size);
+	int cache_index = blocksize_bits - EXT4_MIN_BLOCK_LOG_SIZE;
+	struct kmem_cache *cachep;
+
+	if (cache_index >= NR_GRPINFO_CACHES)
+		return -EINVAL;
+
+	if (unlikely(cache_index < 0))
+		cache_index = 0;
+
+	mutex_lock(&ext4_grpinfo_slab_create_mutex);
+	if (ext4_groupinfo_caches[cache_index]) {
+		mutex_unlock(&ext4_grpinfo_slab_create_mutex);
+		return 0;	/* Already created */
+	}
+
+	slab_size = offsetof(struct ext4_group_info,
+				bb_counters[blocksize_bits + 2]);
+
+	cachep = kmem_cache_create(ext4_groupinfo_slab_names[cache_index],
+					slab_size, 0, SLAB_RECLAIM_ACCOUNT,
+					NULL);
+
+	mutex_unlock(&ext4_grpinfo_slab_create_mutex);
+	if (!cachep) {
+		printk(KERN_EMERG "EXT4: no memory for groupinfo slab cache\n");
+		return -ENOMEM;
+	}
+
+	ext4_groupinfo_caches[cache_index] = cachep;
+
+	return 0;
+}
+
 int ext4_mb_init(struct super_block *sb, int needs_recovery)
 {
 	struct ext4_sb_info *sbi = EXT4_SB(sb);
@@ -2421,9 +2475,6 @@ int ext4_mb_init(struct super_block *sb, int needs_recovery)
 	unsigned offset;
 	unsigned max;
 	int ret;
-	int cache_index;
-	struct kmem_cache *cachep;
-	char *namep = NULL;
 
 	i = (sb->s_blocksize_bits + 2) * sizeof(*sbi->s_mb_offsets);
 
@@ -2440,30 +2491,9 @@ int ext4_mb_init(struct super_block *sb, int needs_recovery)
 		goto out;
 	}
 
-	cache_index = sb->s_blocksize_bits - EXT4_MIN_BLOCK_LOG_SIZE;
-	cachep = ext4_groupinfo_caches[cache_index];
-	if (!cachep) {
-		char name[32];
-		int len = offsetof(struct ext4_group_info,
-					bb_counters[sb->s_blocksize_bits + 2]);
-
-		sprintf(name, "ext4_groupinfo_%d", sb->s_blocksize_bits);
-		namep = kstrdup(name, GFP_KERNEL);
-		if (!namep) {
-			ret = -ENOMEM;
-			goto out;
-		}
-
-		/* Need to free the kmem_cache_name() when we
-		 * destroy the slab */
-		cachep = kmem_cache_create(namep, len, 0,
-					     SLAB_RECLAIM_ACCOUNT, NULL);
-		if (!cachep) {
-			ret = -ENOMEM;
-			goto out;
-		}
-		ext4_groupinfo_caches[cache_index] = cachep;
-	}
+	ret = ext4_groupinfo_create_slab(sb->s_blocksize);
+	if (ret < 0)
+		goto out;
 
 	/* order 0 is regular bitmap */
 	sbi->s_mb_maxs[0] = sb->s_blocksize << 3;
@@ -2520,7 +2550,6 @@ out:
 	if (ret) {
 		kfree(sbi->s_mb_offsets);
 		kfree(sbi->s_mb_maxs);
-		kfree(namep);
 	}
 	return ret;
 }
@@ -2734,7 +2763,6 @@ int __init ext4_init_mballoc(void)
 
 void ext4_exit_mballoc(void)
 {
-	int i;
 	/*
 	 * Wait for completion of call_rcu()'s on ext4_pspace_cachep
 	 * before destroying the slab cache.
@@ -2743,15 +2771,7 @@ void ext4_exit_mballoc(void)
 	kmem_cache_destroy(ext4_pspace_cachep);
 	kmem_cache_destroy(ext4_ac_cachep);
 	kmem_cache_destroy(ext4_free_ext_cachep);
-
-	for (i = 0; i < NR_GRPINFO_CACHES; i++) {
-		struct kmem_cache *cachep = ext4_groupinfo_caches[i];
-		if (cachep) {
-			char *name = (char *)kmem_cache_name(cachep);
-			kmem_cache_destroy(cachep);
-			kfree(name);
-		}
-	}
+	ext4_groupinfo_destroy_slabs();
 	ext4_remove_debugfs_entry();
 }
 
diff --git a/fs/ext4/page-io.c b/fs/ext4/page-io.c
index 7270dcfca92a..955cc309142f 100644
--- a/fs/ext4/page-io.c
+++ b/fs/ext4/page-io.c
@@ -32,14 +32,8 @@
 
 static struct kmem_cache *io_page_cachep, *io_end_cachep;
 
-#define WQ_HASH_SZ		37
-#define to_ioend_wq(v)	(&ioend_wq[((unsigned long)v) % WQ_HASH_SZ])
-static wait_queue_head_t ioend_wq[WQ_HASH_SZ];
-
 int __init ext4_init_pageio(void)
 {
-	int i;
-
 	io_page_cachep = KMEM_CACHE(ext4_io_page, SLAB_RECLAIM_ACCOUNT);
 	if (io_page_cachep == NULL)
 		return -ENOMEM;
@@ -48,9 +42,6 @@ int __init ext4_init_pageio(void)
 		kmem_cache_destroy(io_page_cachep);
 		return -ENOMEM;
 	}
-	for (i = 0; i < WQ_HASH_SZ; i++)
-		init_waitqueue_head(&ioend_wq[i]);
-
 	return 0;
 }
 
@@ -62,7 +53,7 @@ void ext4_exit_pageio(void)
 
 void ext4_ioend_wait(struct inode *inode)
 {
-	wait_queue_head_t *wq = to_ioend_wq(inode);
+	wait_queue_head_t *wq = ext4_ioend_wq(inode);
 
 	wait_event(*wq, (atomic_read(&EXT4_I(inode)->i_ioend_count) == 0));
 }
@@ -87,7 +78,7 @@ void ext4_free_io_end(ext4_io_end_t *io)
 	for (i = 0; i < io->num_io_pages; i++)
 		put_io_page(io->pages[i]);
 	io->num_io_pages = 0;
-	wq = to_ioend_wq(io->inode);
+	wq = ext4_ioend_wq(io->inode);
 	if (atomic_dec_and_test(&EXT4_I(io->inode)->i_ioend_count) &&
 	    waitqueue_active(wq))
 		wake_up_all(wq);
@@ -102,6 +93,7 @@ int ext4_end_io_nolock(ext4_io_end_t *io)
 	struct inode *inode = io->inode;
 	loff_t offset = io->offset;
 	ssize_t size = io->size;
+	wait_queue_head_t *wq;
 	int ret = 0;
 
 	ext4_debug("ext4_end_io_nolock: io 0x%p from inode %lu,list->next 0x%p,"
@@ -126,7 +118,16 @@ int ext4_end_io_nolock(ext4_io_end_t *io)
 	if (io->iocb)
 		aio_complete(io->iocb, io->result, 0);
 	/* clear the DIO AIO unwritten flag */
-	io->flag &= ~EXT4_IO_END_UNWRITTEN;
+	if (io->flag & EXT4_IO_END_UNWRITTEN) {
+		io->flag &= ~EXT4_IO_END_UNWRITTEN;
+		/* Wake up anyone waiting on unwritten extent conversion */
+		wq = ext4_ioend_wq(io->inode);
+		if (atomic_dec_and_test(&EXT4_I(inode)->i_aiodio_unwritten) &&
+		    waitqueue_active(wq)) {
+			wake_up_all(wq);
+		}
+	}
+
 	return ret;
 }
 
@@ -190,6 +191,7 @@ static void ext4_end_bio(struct bio *bio, int error)
 	struct inode *inode;
 	unsigned long flags;
 	int i;
+	sector_t bi_sector = bio->bi_sector;
 
 	BUG_ON(!io_end);
 	bio->bi_private = NULL;
@@ -207,9 +209,7 @@ static void ext4_end_bio(struct bio *bio, int error)
 		if (error)
 			SetPageError(page);
 		BUG_ON(!head);
-		if (head->b_size == PAGE_CACHE_SIZE)
-			clear_buffer_dirty(head);
-		else {
+		if (head->b_size != PAGE_CACHE_SIZE) {
 			loff_t offset;
 			loff_t io_end_offset = io_end->offset + io_end->size;
 
@@ -221,7 +221,6 @@ static void ext4_end_bio(struct bio *bio, int error)
 					if (error)
 						buffer_io_error(bh);
 
-					clear_buffer_dirty(bh);
 				}
 				if (buffer_delay(bh))
 					partial_write = 1;
@@ -257,7 +256,7 @@ static void ext4_end_bio(struct bio *bio, int error)
 			     (unsigned long long) io_end->offset,
 			     (long) io_end->size,
 			     (unsigned long long)
-			     bio->bi_sector >> (inode->i_blkbits - 9));
+			     bi_sector >> (inode->i_blkbits - 9));
 	}
 
 	/* Add the io_end to per-inode completed io list*/
@@ -380,6 +379,7 @@ int ext4_bio_write_page(struct ext4_io_submit *io,
 
 	blocksize = 1 << inode->i_blkbits;
 
+	BUG_ON(!PageLocked(page));
 	BUG_ON(PageWriteback(page));
 	set_page_writeback(page);
 	ClearPageError(page);
@@ -397,12 +397,14 @@ int ext4_bio_write_page(struct ext4_io_submit *io,
 	for (bh = head = page_buffers(page), block_start = 0;
 	     bh != head || !block_start;
 	     block_start = block_end, bh = bh->b_this_page) {
+
 		block_end = block_start + blocksize;
 		if (block_start >= len) {
 			clear_buffer_dirty(bh);
 			set_buffer_uptodate(bh);
 			continue;
 		}
+		clear_buffer_dirty(bh);
 		ret = io_submit_add_bh(io, io_page, inode, wbc, bh);
 		if (ret) {
 			/*
diff --git a/fs/ext4/super.c b/fs/ext4/super.c
index 0fcf6720af09..c1d0f5972ca8 100644
--- a/fs/ext4/super.c
+++ b/fs/ext4/super.c
@@ -77,6 +77,7 @@ static struct dentry *ext4_mount(struct file_system_type *fs_type, int flags,
 		       const char *dev_name, void *data);
 static void ext4_destroy_lazyinit_thread(void);
 static void ext4_unregister_li_request(struct super_block *sb);
+static void ext4_clear_request_list(void);
 
 #if !defined(CONFIG_EXT3_FS) && !defined(CONFIG_EXT3_FS_MODULE) && defined(CONFIG_EXT4_USE_FOR_EXT23)
 static struct file_system_type ext3_fs_type = {
@@ -832,6 +833,7 @@ static struct inode *ext4_alloc_inode(struct super_block *sb)
 	ei->i_sync_tid = 0;
 	ei->i_datasync_tid = 0;
 	atomic_set(&ei->i_ioend_count, 0);
+	atomic_set(&ei->i_aiodio_unwritten, 0);
 
 	return &ei->vfs_inode;
 }
@@ -2716,6 +2718,8 @@ static void ext4_unregister_li_request(struct super_block *sb)
 	mutex_unlock(&ext4_li_info->li_list_mtx);
 }
 
+static struct task_struct *ext4_lazyinit_task;
+
 /*
  * This is the function where ext4lazyinit thread lives. It walks
  * through the request list searching for next scheduled filesystem.
@@ -2784,6 +2788,10 @@ cont_thread:
 		if (time_before(jiffies, next_wakeup))
 			schedule();
 		finish_wait(&eli->li_wait_daemon, &wait);
+		if (kthread_should_stop()) {
+			ext4_clear_request_list();
+			goto exit_thread;
+		}
 	}
 
 exit_thread:
@@ -2808,6 +2816,7 @@ exit_thread:
 	wake_up(&eli->li_wait_task);
 
 	kfree(ext4_li_info);
+	ext4_lazyinit_task = NULL;
 	ext4_li_info = NULL;
 	mutex_unlock(&ext4_li_mtx);
 
@@ -2830,11 +2839,10 @@ static void ext4_clear_request_list(void)
 
 static int ext4_run_lazyinit_thread(void)
 {
-	struct task_struct *t;
-
-	t = kthread_run(ext4_lazyinit_thread, ext4_li_info, "ext4lazyinit");
-	if (IS_ERR(t)) {
-		int err = PTR_ERR(t);
+	ext4_lazyinit_task = kthread_run(ext4_lazyinit_thread,
+					 ext4_li_info, "ext4lazyinit");
+	if (IS_ERR(ext4_lazyinit_task)) {
+		int err = PTR_ERR(ext4_lazyinit_task);
 		ext4_clear_request_list();
 		del_timer_sync(&ext4_li_info->li_timer);
 		kfree(ext4_li_info);
@@ -2985,16 +2993,10 @@ static void ext4_destroy_lazyinit_thread(void)
 	 * If thread exited earlier
 	 * there's nothing to be done.
 	 */
-	if (!ext4_li_info)
+	if (!ext4_li_info || !ext4_lazyinit_task)
 		return;
 
-	ext4_clear_request_list();
-
-	while (ext4_li_info->li_task) {
-		wake_up(&ext4_li_info->li_wait_daemon);
-		wait_event(ext4_li_info->li_wait_task,
-			   ext4_li_info->li_task == NULL);
-	}
+	kthread_stop(ext4_lazyinit_task);
 }
 
 static int ext4_fill_super(struct super_block *sb, void *data, int silent)
@@ -4773,7 +4775,7 @@ static struct file_system_type ext4_fs_type = {
 	.fs_flags	= FS_REQUIRES_DEV,
 };
 
-int __init ext4_init_feat_adverts(void)
+static int __init ext4_init_feat_adverts(void)
 {
 	struct ext4_features *ef;
 	int ret = -ENOMEM;
@@ -4797,23 +4799,44 @@ out:
 	return ret;
 }
 
+static void ext4_exit_feat_adverts(void)
+{
+	kobject_put(&ext4_feat->f_kobj);
+	wait_for_completion(&ext4_feat->f_kobj_unregister);
+	kfree(ext4_feat);
+}
+
+/* Shared across all ext4 file systems */
+wait_queue_head_t ext4__ioend_wq[EXT4_WQ_HASH_SZ];
+struct mutex ext4__aio_mutex[EXT4_WQ_HASH_SZ];
+
 static int __init ext4_init_fs(void)
 {
-	int err;
+	int i, err;
 
 	ext4_check_flag_values();
+
+	for (i = 0; i < EXT4_WQ_HASH_SZ; i++) {
+		mutex_init(&ext4__aio_mutex[i]);
+		init_waitqueue_head(&ext4__ioend_wq[i]);
+	}
+
 	err = ext4_init_pageio();
 	if (err)
 		return err;
 	err = ext4_init_system_zone();
 	if (err)
-		goto out5;
+		goto out7;
 	ext4_kset = kset_create_and_add("ext4", NULL, fs_kobj);
 	if (!ext4_kset)
-		goto out4;
+		goto out6;
 	ext4_proc_root = proc_mkdir("fs/ext4", NULL);
+	if (!ext4_proc_root)
+		goto out5;
 
 	err = ext4_init_feat_adverts();
+	if (err)
+		goto out4;
 
 	err = ext4_init_mballoc();
 	if (err)
@@ -4843,12 +4866,14 @@ out1:
 out2:
 	ext4_exit_mballoc();
 out3:
-	kfree(ext4_feat);
+	ext4_exit_feat_adverts();
+out4:
 	remove_proc_entry("fs/ext4", NULL);
+out5:
 	kset_unregister(ext4_kset);
-out4:
+out6:
 	ext4_exit_system_zone();
-out5:
+out7:
 	ext4_exit_pageio();
 	return err;
 }
@@ -4862,6 +4887,7 @@ static void __exit ext4_exit_fs(void)
 	destroy_inodecache();
 	ext4_exit_xattr();
 	ext4_exit_mballoc();
+	ext4_exit_feat_adverts();
 	remove_proc_entry("fs/ext4", NULL);
 	kset_unregister(ext4_kset);
 	ext4_exit_system_zone();