Merge branch 'for-linus' into for-2.6.33

Conflicts:
	block/cfq-iosched.c

Signed-off-by: Jens Axboe <jens.axboe@oracle.com>

65 files changed, 933 insertions, 403 deletions

diff --git a/fs/Kconfig b/fs/Kconfig
index d4bf8caad8d0..2126078a38ed 100644
--- a/fs/Kconfig
+++ b/fs/Kconfig
@@ -135,8 +135,8 @@ config TMPFS_POSIX_ACL
 
 config HUGETLBFS
 	bool "HugeTLB file system support"
-	depends on X86 || IA64 || PPC64 || SPARC64 || (SUPERH && MMU) || \
-		   (S390 && 64BIT) || SYS_SUPPORTS_HUGETLBFS || BROKEN
+	depends on X86 || IA64 || PPC_BOOK3S_64 || SPARC64 || (S390 && 64BIT) || \
+		   SYS_SUPPORTS_HUGETLBFS || BROKEN
 	help
 	  hugetlbfs is a filesystem backing for HugeTLB pages, based on
 	  ramfs. For architectures that support it, say Y here and read
diff --git a/fs/bio.c b/fs/bio.c
index 402cb84a92a1..12da5db8682c 100644
--- a/fs/bio.c
+++ b/fs/bio.c
@@ -325,8 +325,16 @@ static void bio_fs_destructor(struct bio *bio)
  *	@gfp_mask: allocation mask to use
  *	@nr_iovecs: number of iovecs
  *
- *	Allocate a new bio with @nr_iovecs bvecs.  If @gfp_mask
- *	contains __GFP_WAIT, the allocation is guaranteed to succeed.
+ *	bio_alloc will allocate a bio and associated bio_vec array that can hold
+ *	at least @nr_iovecs entries. Allocations will be done from the
+ *	fs_bio_set. Also see @bio_alloc_bioset and @bio_kmalloc.
+ *
+ *	If %__GFP_WAIT is set, then bio_alloc will always be able to allocate
+ *	a bio. This is due to the mempool guarantees. To make this work, callers
+ *	must never allocate more than 1 bio at a time from this pool. Callers
+ *	that need to allocate more than 1 bio must always submit the previously
+ *	allocated bio for IO before attempting to allocate a new one. Failure to
+ *	do so can cause livelocks under memory pressure.
  *
  *	RETURNS:
  *	Pointer to new bio on success, NULL on failure.
@@ -350,21 +358,13 @@ static void bio_kmalloc_destructor(struct bio *bio)
 }
 
 /**
- * bio_alloc - allocate a bio for I/O
+ * bio_kmalloc - allocate a bio for I/O using kmalloc()
  * @gfp_mask:   the GFP_ mask given to the slab allocator
  * @nr_iovecs:	number of iovecs to pre-allocate
  *
  * Description:
- *   bio_alloc will allocate a bio and associated bio_vec array that can hold
- *   at least @nr_iovecs entries. Allocations will be done from the
- *   fs_bio_set. Also see @bio_alloc_bioset.
- *
- *   If %__GFP_WAIT is set, then bio_alloc will always be able to allocate
- *   a bio. This is due to the mempool guarantees. To make this work, callers
- *   must never allocate more than 1 bio at a time from this pool. Callers
- *   that need to allocate more than 1 bio must always submit the previously
- *   allocated bio for IO before attempting to allocate a new one. Failure to
- *   do so can cause livelocks under memory pressure.
+ *   Allocate a new bio with @nr_iovecs bvecs.  If @gfp_mask contains
+ *   %__GFP_WAIT, the allocation is guaranteed to succeed.
  *
  **/
 struct bio *bio_kmalloc(gfp_t gfp_mask, int nr_iovecs)
@@ -407,7 +407,7 @@ EXPORT_SYMBOL(zero_fill_bio);
  *
  * Description:
  *   Put a reference to a &struct bio, either one you have gotten with
- *   bio_alloc or bio_get. The last put of a bio will free it.
+ *   bio_alloc, bio_get or bio_clone. The last put of a bio will free it.
  **/
 void bio_put(struct bio *bio)
 {
diff --git a/fs/block_dev.c b/fs/block_dev.c
index dde91e7e1c3a..73d6a735b8f3 100644
--- a/fs/block_dev.c
+++ b/fs/block_dev.c
@@ -1258,8 +1258,8 @@ static int __blkdev_get(struct block_device *bdev, fmode_t mode, int for_part)
 			bd_set_size(bdev, (loff_t)bdev->bd_part->nr_sects << 9);
 		}
 	} else {
-		put_disk(disk);
 		module_put(disk->fops->owner);
+		put_disk(disk);
 		disk = NULL;
 		if (bdev->bd_contains == bdev) {
 			if (bdev->bd_disk->fops->open) {
diff --git a/fs/btrfs/acl.c b/fs/btrfs/acl.c
index 69b355ae7f49..361604244271 100644
--- a/fs/btrfs/acl.c
+++ b/fs/btrfs/acl.c
@@ -27,7 +27,7 @@
 #include "btrfs_inode.h"
 #include "xattr.h"
 
-#ifdef CONFIG_BTRFS_POSIX_ACL
+#ifdef CONFIG_BTRFS_FS_POSIX_ACL
 
 static struct posix_acl *btrfs_get_acl(struct inode *inode, int type)
 {
@@ -313,7 +313,7 @@ struct xattr_handler btrfs_xattr_acl_access_handler = {
 	.set	= btrfs_xattr_acl_access_set,
 };
 
-#else /* CONFIG_BTRFS_POSIX_ACL */
+#else /* CONFIG_BTRFS_FS_POSIX_ACL */
 
 int btrfs_acl_chmod(struct inode *inode)
 {
@@ -325,4 +325,4 @@ int btrfs_init_acl(struct inode *inode, struct inode *dir)
 	return 0;
 }
 
-#endif /* CONFIG_BTRFS_POSIX_ACL */
+#endif /* CONFIG_BTRFS_FS_POSIX_ACL */
diff --git a/fs/btrfs/async-thread.c b/fs/btrfs/async-thread.c
index 282ca085c2fb..c0861e781cdb 100644
--- a/fs/btrfs/async-thread.c
+++ b/fs/btrfs/async-thread.c
@@ -64,6 +64,51 @@ struct btrfs_worker_thread {
 };
 
 /*
+ * btrfs_start_workers uses kthread_run, which can block waiting for memory
+ * for a very long time.  It will actually throttle on page writeback,
+ * and so it may not make progress until after our btrfs worker threads
+ * process all of the pending work structs in their queue
+ *
+ * This means we can't use btrfs_start_workers from inside a btrfs worker
+ * thread that is used as part of cleaning dirty memory, which pretty much
+ * involves all of the worker threads.
+ *
+ * Instead we have a helper queue who never has more than one thread
+ * where we scheduler thread start operations.  This worker_start struct
+ * is used to contain the work and hold a pointer to the queue that needs
+ * another worker.
+ */
+struct worker_start {
+	struct btrfs_work work;
+	struct btrfs_workers *queue;
+};
+
+static void start_new_worker_func(struct btrfs_work *work)
+{
+	struct worker_start *start;
+	start = container_of(work, struct worker_start, work);
+	btrfs_start_workers(start->queue, 1);
+	kfree(start);
+}
+
+static int start_new_worker(struct btrfs_workers *queue)
+{
+	struct worker_start *start;
+	int ret;
+
+	start = kzalloc(sizeof(*start), GFP_NOFS);
+	if (!start)
+		return -ENOMEM;
+
+	start->work.func = start_new_worker_func;
+	start->queue = queue;
+	ret = btrfs_queue_worker(queue->atomic_worker_start, &start->work);
+	if (ret)
+		kfree(start);
+	return ret;
+}
+
+/*
  * helper function to move a thread onto the idle list after it
  * has finished some requests.
  */
@@ -118,11 +163,13 @@ static void check_pending_worker_creates(struct btrfs_worker_thread *worker)
 		goto out;
 
 	workers->atomic_start_pending = 0;
-	if (workers->num_workers >= workers->max_workers)
+	if (workers->num_workers + workers->num_workers_starting >=
+	    workers->max_workers)
 		goto out;
 
+	workers->num_workers_starting += 1;
 	spin_unlock_irqrestore(&workers->lock, flags);
-	btrfs_start_workers(workers, 1);
+	start_new_worker(workers);
 	return;
 
 out:
@@ -390,9 +437,11 @@ int btrfs_stop_workers(struct btrfs_workers *workers)
 /*
  * simple init on struct btrfs_workers
  */
-void btrfs_init_workers(struct btrfs_workers *workers, char *name, int max)
+void btrfs_init_workers(struct btrfs_workers *workers, char *name, int max,
+			struct btrfs_workers *async_helper)
 {
 	workers->num_workers = 0;
+	workers->num_workers_starting = 0;
 	INIT_LIST_HEAD(&workers->worker_list);
 	INIT_LIST_HEAD(&workers->idle_list);
 	INIT_LIST_HEAD(&workers->order_list);
@@ -404,14 +453,15 @@ void btrfs_init_workers(struct btrfs_workers *workers, char *name, int max)
 	workers->name = name;
 	workers->ordered = 0;
 	workers->atomic_start_pending = 0;
-	workers->atomic_worker_start = 0;
+	workers->atomic_worker_start = async_helper;
 }
 
 /*
  * starts new worker threads.  This does not enforce the max worker
  * count in case you need to temporarily go past it.
  */
-int btrfs_start_workers(struct btrfs_workers *workers, int num_workers)
+static int __btrfs_start_workers(struct btrfs_workers *workers,
+				 int num_workers)
 {
 	struct btrfs_worker_thread *worker;
 	int ret = 0;
@@ -444,6 +494,8 @@ int btrfs_start_workers(struct btrfs_workers *workers, int num_workers)
 		list_add_tail(&worker->worker_list, &workers->idle_list);
 		worker->idle = 1;
 		workers->num_workers++;
+		workers->num_workers_starting--;
+		WARN_ON(workers->num_workers_starting < 0);
 		spin_unlock_irq(&workers->lock);
 	}
 	return 0;
@@ -452,6 +504,14 @@ fail:
 	return ret;
 }
 
+int btrfs_start_workers(struct btrfs_workers *workers, int num_workers)
+{
+	spin_lock_irq(&workers->lock);
+	workers->num_workers_starting += num_workers;
+	spin_unlock_irq(&workers->lock);
+	return __btrfs_start_workers(workers, num_workers);
+}
+
 /*
  * run through the list and find a worker thread that doesn't have a lot
  * to do right now.  This can return null if we aren't yet at the thread
@@ -461,7 +521,10 @@ static struct btrfs_worker_thread *next_worker(struct btrfs_workers *workers)
 {
 	struct btrfs_worker_thread *worker;
 	struct list_head *next;
-	int enforce_min = workers->num_workers < workers->max_workers;
+	int enforce_min;
+
+	enforce_min = (workers->num_workers + workers->num_workers_starting) <
+		workers->max_workers;
 
 	/*
 	 * if we find an idle thread, don't move it to the end of the
@@ -509,15 +572,17 @@ again:
 	worker = next_worker(workers);
 
 	if (!worker) {
-		if (workers->num_workers >= workers->max_workers) {
+		if (workers->num_workers + workers->num_workers_starting >=
+		    workers->max_workers) {
 			goto fallback;
 		} else if (workers->atomic_worker_start) {
 			workers->atomic_start_pending = 1;
 			goto fallback;
 		} else {
+			workers->num_workers_starting++;
 			spin_unlock_irqrestore(&workers->lock, flags);
 			/* we're below the limit, start another worker */
-			btrfs_start_workers(workers, 1);
+			__btrfs_start_workers(workers, 1);
 			goto again;
 		}
 	}
diff --git a/fs/btrfs/async-thread.h b/fs/btrfs/async-thread.h
index fc089b95ec14..5077746cf85e 100644
--- a/fs/btrfs/async-thread.h
+++ b/fs/btrfs/async-thread.h
@@ -64,6 +64,8 @@ struct btrfs_workers {
 	/* current number of running workers */
 	int num_workers;
 
+	int num_workers_starting;
+
 	/* max number of workers allowed.  changed by btrfs_start_workers */
 	int max_workers;
 
@@ -78,9 +80,10 @@ struct btrfs_workers {
 
 	/*
 	 * are we allowed to sleep while starting workers or are we required
-	 * to start them at a later time?
+	 * to start them at a later time?  If we can't sleep, this indicates
+	 * which queue we need to use to schedule thread creation.
 	 */
-	int atomic_worker_start;
+	struct btrfs_workers *atomic_worker_start;
 
 	/* list with all the work threads.  The workers on the idle thread
 	 * may be actively servicing jobs, but they haven't yet hit the
@@ -109,7 +112,8 @@ struct btrfs_workers {
 int btrfs_queue_worker(struct btrfs_workers *workers, struct btrfs_work *work);
 int btrfs_start_workers(struct btrfs_workers *workers, int num_workers);
 int btrfs_stop_workers(struct btrfs_workers *workers);
-void btrfs_init_workers(struct btrfs_workers *workers, char *name, int max);
+void btrfs_init_workers(struct btrfs_workers *workers, char *name, int max,
+			struct btrfs_workers *async_starter);
 int btrfs_requeue_work(struct btrfs_work *work);
 void btrfs_set_work_high_prio(struct btrfs_work *work);
 #endif
diff --git a/fs/btrfs/btrfs_inode.h b/fs/btrfs/btrfs_inode.h
index a54d354cefcb..f6783a42f010 100644
--- a/fs/btrfs/btrfs_inode.h
+++ b/fs/btrfs/btrfs_inode.h
@@ -86,6 +86,12 @@ struct btrfs_inode {
 	 * transid of the trans_handle that last modified this inode
 	 */
 	u64 last_trans;
+
+	/*
+	 * log transid when this inode was last modified
+	 */
+	u64 last_sub_trans;
+
 	/*
 	 * transid that last logged this inode
 	 */
@@ -128,12 +134,14 @@ struct btrfs_inode {
 	u64 last_unlink_trans;
 
 	/*
-	 * These two counters are for delalloc metadata reservations.  We keep
-	 * track of how many extents we've accounted for vs how many extents we
-	 * have.
+	 * Counters to keep track of the number of extent item's we may use due
+	 * to delalloc and such.  outstanding_extents is the number of extent
+	 * items we think we'll end up using, and reserved_extents is the number
+	 * of extent items we've reserved metadata for.
 	 */
-	int delalloc_reserved_extents;
-	int delalloc_extents;
+	spinlock_t accounting_lock;
+	int reserved_extents;
+	int outstanding_extents;
 
 	/*
 	 * ordered_data_close is set by truncate when a file that used
diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h
index dd8ced9814c4..444b3e9b92a4 100644
--- a/fs/btrfs/ctree.h
+++ b/fs/btrfs/ctree.h
@@ -691,14 +691,17 @@ struct btrfs_space_info {
 
 	struct list_head list;
 
+	/* for controlling how we free up space for allocations */
+	wait_queue_head_t allocate_wait;
+	wait_queue_head_t flush_wait;
+	int allocating_chunk;
+	int flushing;
+
 	/* for block groups in our same type */
 	struct list_head block_groups;
 	spinlock_t lock;
 	struct rw_semaphore groups_sem;
 	atomic_t caching_threads;
-
-	int allocating_chunk;
-	wait_queue_head_t wait;
 };
 
 /*
@@ -907,6 +910,7 @@ struct btrfs_fs_info {
 	 * A third pool does submit_bio to avoid deadlocking with the other
 	 * two
 	 */
+	struct btrfs_workers generic_worker;
 	struct btrfs_workers workers;
 	struct btrfs_workers delalloc_workers;
 	struct btrfs_workers endio_workers;
@@ -914,6 +918,7 @@ struct btrfs_fs_info {
 	struct btrfs_workers endio_meta_write_workers;
 	struct btrfs_workers endio_write_workers;
 	struct btrfs_workers submit_workers;
+	struct btrfs_workers enospc_workers;
 	/*
 	 * fixup workers take dirty pages that didn't properly go through
 	 * the cow mechanism and make them safe to write.  It happens
@@ -1004,7 +1009,10 @@ struct btrfs_root {
 	atomic_t log_writers;
 	atomic_t log_commit[2];
 	unsigned long log_transid;
+	unsigned long last_log_commit;
 	unsigned long log_batch;
+	pid_t log_start_pid;
+	bool log_multiple_pids;
 
 	u64 objectid;
 	u64 last_trans;
@@ -1145,6 +1153,7 @@ struct btrfs_root {
 #define BTRFS_MOUNT_FLUSHONCOMMIT       (1 << 7)
 #define BTRFS_MOUNT_SSD_SPREAD		(1 << 8)
 #define BTRFS_MOUNT_NOSSD		(1 << 9)
+#define BTRFS_MOUNT_DISCARD		(1 << 10)
 
 #define btrfs_clear_opt(o, opt)		((o) &= ~BTRFS_MOUNT_##opt)
 #define btrfs_set_opt(o, opt)		((o) |= BTRFS_MOUNT_##opt)
@@ -2323,7 +2332,7 @@ int btrfs_orphan_del(struct btrfs_trans_handle *trans, struct inode *inode);
 void btrfs_orphan_cleanup(struct btrfs_root *root);
 int btrfs_cont_expand(struct inode *inode, loff_t size);
 int btrfs_invalidate_inodes(struct btrfs_root *root);
-extern struct dentry_operations btrfs_dentry_operations;
+extern const struct dentry_operations btrfs_dentry_operations;
 
 /* ioctl.c */
 long btrfs_ioctl(struct file *file, unsigned int cmd, unsigned long arg);
@@ -2366,7 +2375,7 @@ int btrfs_parse_options(struct btrfs_root *root, char *options);
 int btrfs_sync_fs(struct super_block *sb, int wait);
 
 /* acl.c */
-#ifdef CONFIG_BTRFS_POSIX_ACL
+#ifdef CONFIG_BTRFS_FS_POSIX_ACL
 int btrfs_check_acl(struct inode *inode, int mask);
 #else
 #define btrfs_check_acl NULL
diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c
index af0435f79fa6..02b6afbd7450 100644
--- a/fs/btrfs/disk-io.c
+++ b/fs/btrfs/disk-io.c
@@ -917,6 +917,7 @@ static int __setup_root(u32 nodesize, u32 leafsize, u32 sectorsize,
 	atomic_set(&root->log_writers, 0);
 	root->log_batch = 0;
 	root->log_transid = 0;
+	root->last_log_commit = 0;
 	extent_io_tree_init(&root->dirty_log_pages,
 			     fs_info->btree_inode->i_mapping, GFP_NOFS);
 
@@ -1087,6 +1088,7 @@ int btrfs_add_log_tree(struct btrfs_trans_handle *trans,
 	WARN_ON(root->log_root);
 	root->log_root = log_root;
 	root->log_transid = 0;
+	root->last_log_commit = 0;
 	return 0;
 }
 
@@ -1746,21 +1748,25 @@ struct btrfs_root *open_ctree(struct super_block *sb,
 		err = -EINVAL;
 		goto fail_iput;
 	}
-printk("thread pool is %d\n", fs_info->thread_pool_size);
-	/*
-	 * we need to start all the end_io workers up front because the
-	 * queue work function gets called at interrupt time, and so it
-	 * cannot dynamically grow.
-	 */
+
+	btrfs_init_workers(&fs_info->generic_worker,
+			   "genwork", 1, NULL);
+
 	btrfs_init_workers(&fs_info->workers, "worker",
-			   fs_info->thread_pool_size);
+			   fs_info->thread_pool_size,
+			   &fs_info->generic_worker);
 
 	btrfs_init_workers(&fs_info->delalloc_workers, "delalloc",
-			   fs_info->thread_pool_size);
+			   fs_info->thread_pool_size,
+			   &fs_info->generic_worker);
 
 	btrfs_init_workers(&fs_info->submit_workers, "submit",
 			   min_t(u64, fs_devices->num_devices,
-			   fs_info->thread_pool_size));
+			   fs_info->thread_pool_size),
+			   &fs_info->generic_worker);
+	btrfs_init_workers(&fs_info->enospc_workers, "enospc",
+			   fs_info->thread_pool_size,
+			   &fs_info->generic_worker);
 
 	/* a higher idle thresh on the submit workers makes it much more
 	 * likely that bios will be send down in a sane order to the
@@ -1774,15 +1780,20 @@ printk("thread pool is %d\n", fs_info->thread_pool_size);
 	fs_info->delalloc_workers.idle_thresh = 2;
 	fs_info->delalloc_workers.ordered = 1;
 
-	btrfs_init_workers(&fs_info->fixup_workers, "fixup", 1);
+	btrfs_init_workers(&fs_info->fixup_workers, "fixup", 1,
+			   &fs_info->generic_worker);
 	btrfs_init_workers(&fs_info->endio_workers, "endio",
-			   fs_info->thread_pool_size);
+			   fs_info->thread_pool_size,
+			   &fs_info->generic_worker);
 	btrfs_init_workers(&fs_info->endio_meta_workers, "endio-meta",
-			   fs_info->thread_pool_size);
+			   fs_info->thread_pool_size,
+			   &fs_info->generic_worker);
 	btrfs_init_workers(&fs_info->endio_meta_write_workers,
-			   "endio-meta-write", fs_info->thread_pool_size);
+			   "endio-meta-write", fs_info->thread_pool_size,
+			   &fs_info->generic_worker);
 	btrfs_init_workers(&fs_info->endio_write_workers, "endio-write",
-			   fs_info->thread_pool_size);
+			   fs_info->thread_pool_size,
+			   &fs_info->generic_worker);
 
 	/*
 	 * endios are largely parallel and should have a very
@@ -1794,12 +1805,8 @@ printk("thread pool is %d\n", fs_info->thread_pool_size);
 	fs_info->endio_write_workers.idle_thresh = 2;
 	fs_info->endio_meta_write_workers.idle_thresh = 2;
 
-	fs_info->endio_workers.atomic_worker_start = 1;
-	fs_info->endio_meta_workers.atomic_worker_start = 1;
-	fs_info->endio_write_workers.atomic_worker_start = 1;
-	fs_info->endio_meta_write_workers.atomic_worker_start = 1;
-
 	btrfs_start_workers(&fs_info->workers, 1);
+	btrfs_start_workers(&fs_info->generic_worker, 1);
 	btrfs_start_workers(&fs_info->submit_workers, 1);
 	btrfs_start_workers(&fs_info->delalloc_workers, 1);
 	btrfs_start_workers(&fs_info->fixup_workers, 1);
@@ -1807,6 +1814,7 @@ printk("thread pool is %d\n", fs_info->thread_pool_size);
 	btrfs_start_workers(&fs_info->endio_meta_workers, 1);
 	btrfs_start_workers(&fs_info->endio_meta_write_workers, 1);
 	btrfs_start_workers(&fs_info->endio_write_workers, 1);
+	btrfs_start_workers(&fs_info->enospc_workers, 1);
 
 	fs_info->bdi.ra_pages *= btrfs_super_num_devices(disk_super);
 	fs_info->bdi.ra_pages = max(fs_info->bdi.ra_pages,
@@ -2012,6 +2020,7 @@ fail_chunk_root:
 	free_extent_buffer(chunk_root->node);
 	free_extent_buffer(chunk_root->commit_root);
 fail_sb_buffer:
+	btrfs_stop_workers(&fs_info->generic_worker);
 	btrfs_stop_workers(&fs_info->fixup_workers);
 	btrfs_stop_workers(&fs_info->delalloc_workers);
 	btrfs_stop_workers(&fs_info->workers);
@@ -2020,6 +2029,7 @@ fail_sb_buffer:
 	btrfs_stop_workers(&fs_info->endio_meta_write_workers);
 	btrfs_stop_workers(&fs_info->endio_write_workers);
 	btrfs_stop_workers(&fs_info->submit_workers);
+	btrfs_stop_workers(&fs_info->enospc_workers);
 fail_iput:
 	invalidate_inode_pages2(fs_info->btree_inode->i_mapping);
 	iput(fs_info->btree_inode);
@@ -2437,6 +2447,7 @@ int close_ctree(struct btrfs_root *root)
 
 	iput(fs_info->btree_inode);
 
+	btrfs_stop_workers(&fs_info->generic_worker);
 	btrfs_stop_workers(&fs_info->fixup_workers);
 	btrfs_stop_workers(&fs_info->delalloc_workers);
 	btrfs_stop_workers(&fs_info->workers);
@@ -2445,6 +2456,7 @@ int close_c