Merge branch 'master' of /home/davem/src/GIT/linux-2.6/

Conflicts:
	drivers/net/wimax/i2400m/usb-notif.c

110 files changed, 2251 insertions, 2745 deletions

diff --git a/fs/aio.c b/fs/aio.c
index 8fa77e23394..76da1253795 100644
--- a/fs/aio.c
+++ b/fs/aio.c
@@ -443,7 +443,7 @@ static struct kiocb *__aio_get_req(struct kioctx *ctx)
 	req->private = NULL;
 	req->ki_iovec = NULL;
 	INIT_LIST_HEAD(&req->ki_run_list);
-	req->ki_eventfd = ERR_PTR(-EINVAL);
+	req->ki_eventfd = NULL;
 
 	/* Check if the completion queue has enough free space to
 	 * accept an event from this io.
@@ -485,8 +485,6 @@ static inline void really_put_req(struct kioctx *ctx, struct kiocb *req)
 {
 	assert_spin_locked(&ctx->ctx_lock);
 
-	if (!IS_ERR(req->ki_eventfd))
-		fput(req->ki_eventfd);
 	if (req->ki_dtor)
 		req->ki_dtor(req);
 	if (req->ki_iovec != &req->ki_inline_vec)
@@ -508,8 +506,11 @@ static void aio_fput_routine(struct work_struct *data)
 		list_del(&req->ki_list);
 		spin_unlock_irq(&fput_lock);
 
-		/* Complete the fput */
-		__fput(req->ki_filp);
+		/* Complete the fput(s) */
+		if (req->ki_filp != NULL)
+			__fput(req->ki_filp);
+		if (req->ki_eventfd != NULL)
+			__fput(req->ki_eventfd);
 
 		/* Link the iocb into the context's free list */
 		spin_lock_irq(&ctx->ctx_lock);
@@ -527,12 +528,14 @@ static void aio_fput_routine(struct work_struct *data)
  */
 static int __aio_put_req(struct kioctx *ctx, struct kiocb *req)
 {
+	int schedule_putreq = 0;
+
 	dprintk(KERN_DEBUG "aio_put(%p): f_count=%ld\n",
 		req, atomic_long_read(&req->ki_filp->f_count));
 
 	assert_spin_locked(&ctx->ctx_lock);
 
-	req->ki_users --;
+	req->ki_users--;
 	BUG_ON(req->ki_users < 0);
 	if (likely(req->ki_users))
 		return 0;
@@ -540,10 +543,23 @@ static int __aio_put_req(struct kioctx *ctx, struct kiocb *req)
 	req->ki_cancel = NULL;
 	req->ki_retry = NULL;
 
-	/* Must be done under the lock to serialise against cancellation.
-	 * Call this aio_fput as it duplicates fput via the fput_work.
+	/*
+	 * Try to optimize the aio and eventfd file* puts, by avoiding to
+	 * schedule work in case it is not __fput() time. In normal cases,
+	 * we would not be holding the last reference to the file*, so
+	 * this function will be executed w/out any aio kthread wakeup.
 	 */
-	if (unlikely(atomic_long_dec_and_test(&req->ki_filp->f_count))) {
+	if (unlikely(atomic_long_dec_and_test(&req->ki_filp->f_count)))
+		schedule_putreq++;
+	else
+		req->ki_filp = NULL;
+	if (req->ki_eventfd != NULL) {
+		if (unlikely(atomic_long_dec_and_test(&req->ki_eventfd->f_count)))
+			schedule_putreq++;
+		else
+			req->ki_eventfd = NULL;
+	}
+	if (unlikely(schedule_putreq)) {
 		get_ioctx(ctx);
 		spin_lock(&fput_lock);
 		list_add(&req->ki_list, &fput_head);
@@ -571,7 +587,7 @@ int aio_put_req(struct kiocb *req)
 static struct kioctx *lookup_ioctx(unsigned long ctx_id)
 {
 	struct mm_struct *mm = current->mm;
-	struct kioctx *ctx = NULL;
+	struct kioctx *ctx, *ret = NULL;
 	struct hlist_node *n;
 
 	rcu_read_lock();
@@ -579,12 +595,13 @@ static struct kioctx *lookup_ioctx(unsigned long ctx_id)
 	hlist_for_each_entry_rcu(ctx, n, &mm->ioctx_list, list) {
 		if (ctx->user_id == ctx_id && !ctx->dead) {
 			get_ioctx(ctx);
+			ret = ctx;
 			break;
 		}
 	}
 
 	rcu_read_unlock();
-	return ctx;
+	return ret;
 }
 
 /*
@@ -1009,7 +1026,7 @@ int aio_complete(struct kiocb *iocb, long res, long res2)
 	 * eventfd. The eventfd_signal() function is safe to be called
 	 * from IRQ context.
 	 */
-	if (!IS_ERR(iocb->ki_eventfd))
+	if (iocb->ki_eventfd != NULL)
 		eventfd_signal(iocb->ki_eventfd, 1);
 
 put_rq:
@@ -1608,6 +1625,7 @@ static int io_submit_one(struct kioctx *ctx, struct iocb __user *user_iocb,
 		req->ki_eventfd = eventfd_fget((int) iocb->aio_resfd);
 		if (IS_ERR(req->ki_eventfd)) {
 			ret = PTR_ERR(req->ki_eventfd);
+			req->ki_eventfd = NULL;
 			goto out_put_req;
 		}
 	}
diff --git a/fs/bio-integrity.c b/fs/bio-integrity.c
index 549b0144da1..fe2b1aa2464 100644
--- a/fs/bio-integrity.c
+++ b/fs/bio-integrity.c
@@ -685,19 +685,20 @@ EXPORT_SYMBOL(bio_integrity_split);
  * bio_integrity_clone - Callback for cloning bios with integrity metadata
  * @bio:	New bio
  * @bio_src:	Original bio
+ * @gfp_mask:	Memory allocation mask
  * @bs:		bio_set to allocate bip from
  *
  * Description:	Called to allocate a bip when cloning a bio
  */
 int bio_integrity_clone(struct bio *bio, struct bio *bio_src,
-			struct bio_set *bs)
+			gfp_t gfp_mask, struct bio_set *bs)
 {
 	struct bio_integrity_payload *bip_src = bio_src->bi_integrity;
 	struct bio_integrity_payload *bip;
 
 	BUG_ON(bip_src == NULL);
 
-	bip = bio_integrity_alloc_bioset(bio, GFP_NOIO, bip_src->bip_vcnt, bs);
+	bip = bio_integrity_alloc_bioset(bio, gfp_mask, bip_src->bip_vcnt, bs);
 
 	if (bip == NULL)
 		return -EIO;
diff --git a/fs/bio.c b/fs/bio.c
index 124b95c4d58..d4f06327c81 100644
--- a/fs/bio.c
+++ b/fs/bio.c
@@ -463,10 +463,12 @@ struct bio *bio_clone(struct bio *bio, gfp_t gfp_mask)
 	if (bio_integrity(bio)) {
 		int ret;
 
-		ret = bio_integrity_clone(b, bio, fs_bio_set);
+		ret = bio_integrity_clone(b, bio, gfp_mask, fs_bio_set);
 
-		if (ret < 0)
+		if (ret < 0) {
+			bio_put(b);
 			return NULL;
+		}
 	}
 
 	return b;
diff --git a/fs/btrfs/ctree.c b/fs/btrfs/ctree.c
index 42491d728e9..37f31b5529a 100644
--- a/fs/btrfs/ctree.c
+++ b/fs/btrfs/ctree.c
@@ -277,7 +277,7 @@ static noinline int __btrfs_cow_block(struct btrfs_trans_handle *trans,
 	if (*cow_ret == buf)
 		unlock_orig = 1;
 
-	WARN_ON(!btrfs_tree_locked(buf));
+	btrfs_assert_tree_locked(buf);
 
 	if (parent)
 		parent_start = parent->start;
@@ -2365,7 +2365,7 @@ static int push_leaf_right(struct btrfs_trans_handle *trans, struct btrfs_root
 	if (slot >= btrfs_header_nritems(upper) - 1)
 		return 1;
 
-	WARN_ON(!btrfs_tree_locked(path->nodes[1]));
+	btrfs_assert_tree_locked(path->nodes[1]);
 
 	right = read_node_slot(root, upper, slot + 1);
 	btrfs_tree_lock(right);
@@ -2562,7 +2562,7 @@ static int push_leaf_left(struct btrfs_trans_handle *trans, struct btrfs_root
 	if (right_nritems == 0)
 		return 1;
 
-	WARN_ON(!btrfs_tree_locked(path->nodes[1]));
+	btrfs_assert_tree_locked(path->nodes[1]);
 
 	left = read_node_slot(root, path->nodes[1], slot - 1);
 	btrfs_tree_lock(left);
@@ -4101,7 +4101,7 @@ int btrfs_next_leaf(struct btrfs_root *root, struct btrfs_path *path)
 
 		next = read_node_slot(root, c, slot);
 		if (!path->skip_locking) {
-			WARN_ON(!btrfs_tree_locked(c));
+			btrfs_assert_tree_locked(c);
 			btrfs_tree_lock(next);
 			btrfs_set_lock_blocking(next);
 		}
@@ -4126,7 +4126,7 @@ int btrfs_next_leaf(struct btrfs_root *root, struct btrfs_path *path)
 			reada_for_search(root, path, level, slot, 0);
 		next = read_node_slot(root, next, 0);
 		if (!path->skip_locking) {
-			WARN_ON(!btrfs_tree_locked(path->nodes[level]));
+			btrfs_assert_tree_locked(path->nodes[level]);
 			btrfs_tree_lock(next);
 			btrfs_set_lock_blocking(next);
 		}
diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h
index 82491ba8fa4..5e1d4e30e9d 100644
--- a/fs/btrfs/ctree.h
+++ b/fs/btrfs/ctree.h
@@ -784,7 +784,14 @@ struct btrfs_fs_info {
 	struct list_head dirty_cowonly_roots;
 
 	struct btrfs_fs_devices *fs_devices;
+
+	/*
+	 * the space_info list is almost entirely read only.  It only changes
+	 * when we add a new raid type to the FS, and that happens
+	 * very rarely.  RCU is used to protect it.
+	 */
 	struct list_head space_info;
+
 	spinlock_t delalloc_lock;
 	spinlock_t new_trans_lock;
 	u64 delalloc_bytes;
@@ -1797,6 +1804,8 @@ int btrfs_cleanup_reloc_trees(struct btrfs_root *root);
 int btrfs_reloc_clone_csums(struct inode *inode, u64 file_pos, u64 len);
 u64 btrfs_reduce_alloc_profile(struct btrfs_root *root, u64 flags);
 void btrfs_set_inode_space_info(struct btrfs_root *root, struct inode *ionde);
+void btrfs_clear_space_info_full(struct btrfs_fs_info *info);
+
 int btrfs_check_metadata_free_space(struct btrfs_root *root);
 int btrfs_check_data_free_space(struct btrfs_root *