Merge branch 'linus' into perfcounters/core

Conflicts:
	arch/x86/kernel/irqinit.c
	arch/x86/kernel/irqinit_64.c
	arch/x86/kernel/traps.c
	arch/x86/mm/fault.c
	include/linux/sched.h
	kernel/exit.c

8 files changed, 96 insertions, 39 deletions

diff --git a/fs/autofs4/waitq.c b/fs/autofs4/waitq.c
index eeb24684590..2341375386f 100644
--- a/fs/autofs4/waitq.c
+++ b/fs/autofs4/waitq.c
@@ -297,20 +297,14 @@ static int validate_request(struct autofs_wait_queue **wait,
 	 */
 	if (notify == NFY_MOUNT) {
 		/*
-		 * If the dentry isn't hashed just go ahead and try the
-		 * mount again with a new wait (not much else we can do).
-		*/
-		if (!d_unhashed(dentry)) {
-			/*
-			 * But if the dentry is hashed, that means that we
-			 * got here through the revalidate path.  Thus, we
-			 * need to check if the dentry has been mounted
-			 * while we waited on the wq_mutex. If it has,
-			 * simply return success.
-			 */
-			if (d_mountpoint(dentry))
-				return 0;
-		}
+		 * If the dentry was successfully mounted while we slept
+		 * on the wait queue mutex we can return success. If it
+		 * isn't mounted (doesn't have submounts for the case of
+		 * a multi-mount with no mount at it's base) we can
+		 * continue on and create a new request.
+		 */
+		if (have_submounts(dentry))
+			return 0;
 	}
 
 	return 1;
diff --git a/fs/bio.c b/fs/bio.c
index 98711647ece..740699c4f90 100644
--- a/fs/bio.c
+++ b/fs/bio.c
@@ -26,10 +26,9 @@
 #include <linux/mempool.h>
 #include <linux/workqueue.h>
 #include <linux/blktrace_api.h>
-#include <trace/block.h>
 #include <scsi/sg.h>		/* for struct sg_iovec */
 
-DEFINE_TRACE(block_split);
+#include <trace/events/block.h>
 
 /*
  * Test patch to inline a certain number of bi_io_vec's inside the bio
diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c
index 3e2c7c738f2..35af9335506 100644
--- a/fs/btrfs/extent-tree.c
+++ b/fs/btrfs/extent-tree.c
@@ -2622,7 +2622,18 @@ static noinline int find_free_extent(struct btrfs_trans_handle *trans,
 						       search_start);
 		if (block_group && block_group_bits(block_group, data)) {
 			down_read(&space_info->groups_sem);
-			goto have_block_group;
+			if (list_empty(&block_group->list) ||
+			    block_group->ro) {
+				/*
+				 * someone is removing this block group,
+				 * we can't jump into the have_block_group
+				 * target because our list pointers are not
+				 * valid
+				 */
+				btrfs_put_block_group(block_group);
+				up_read(&space_info->groups_sem);
+			} else
+				goto have_block_group;
 		} else if (block_group) {
 			btrfs_put_block_group(block_group);
 		}
@@ -2656,6 +2667,13 @@ have_block_group:
 			 * people trying to start a new cluster
 			 */
 			spin_lock(&last_ptr->refill_lock);
+			if (last_ptr->block_group &&
+			    (last_ptr->block_group->ro ||
+			    !block_group_bits(last_ptr->block_group, data))) {
+				offset = 0;
+				goto refill_cluster;
+			}
+
 			offset = btrfs_alloc_from_cluster(block_group, last_ptr,
 						 num_bytes, search_start);
 			if (offset) {
@@ -2681,10 +2699,17 @@ have_block_group:
 
 				last_ptr_loop = 1;
 				search_start = block_group->key.objectid;
+				/*
+				 * we know this block group is properly
+				 * in the list because
+				 * btrfs_remove_block_group, drops the
+				 * cluster before it removes the block
+				 * group from the list
+				 */
 				goto have_block_group;
 			}
 			spin_unlock(&last_ptr->lock);
-
+refill_cluster:
 			/*
 			 * this cluster didn't work out, free it and
 			 * start over
@@ -5968,6 +5993,7 @@ int btrfs_remove_block_group(struct btrfs_trans_handle *trans,
 {
 	struct btrfs_path *path;
 	struct btrfs_block_group_cache *block_group;
+	struct btrfs_free_cluster *cluster;
 	struct btrfs_key key;
 	int ret;
 
@@ -5979,6 +6005,21 @@ int btrfs_remove_block_group(struct btrfs_trans_handle *trans,
 
 	memcpy(&key, &block_group->key, sizeof(key));
 
+	/* make sure this block group isn't part of an allocation cluster */
+	cluster = &root->fs_info->data_alloc_cluster;
+	spin_lock(&cluster->refill_lock);
+	btrfs_return_cluster_to_free_space(block_group, cluster);
+	spin_unlock(&cluster->refill_lock);
+
+	/*
+	 * make sure this block group isn't part of a metadata
+	 * allocation cluster
+	 */
+	cluster = &root->fs_info->meta_alloc_cluster;
+	spin_lock(&cluster->refill_lock);
+	btrfs_return_cluster_to_free_space(block_group, cluster);
+	spin_unlock(&cluster->refill_lock);
+
 	path = btrfs_alloc_path();
 	BUG_ON(!path);
 
@@ -5988,7 +6029,11 @@ int btrfs_remove_block_group(struct btrfs_trans_handle *trans,
 	spin_unlock(&root->fs_info->block_group_cache_lock);
 	btrfs_remove_free_space_cache(block_group);
 	down_write(&block_group->space_info->groups_sem);
-	list_del(&block_group->list);
+	/*
+	 * we must use list_del_init so people can check to see if they
+	 * are still on the list after taking the semaphore
+	 */
+	list_del_init(&block_group->list);
 	up_write(&block_group->space_info->groups_sem);
 
 	spin_lock(&block_group->space_info->lock);
diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c
index 5f01dad4b69..a6d35b0054c 100644
--- a/fs/btrfs/volumes.c
+++ b/fs/btrfs/volumes.c
@@ -1440,6 +1440,7 @@ int btrfs_init_new_device(struct btrfs_root *root, char *device_path)
 	device->io_align = root->sectorsize;
 	device->sector_size = root->sectorsize;
 	device->total_bytes = i_size_read(bdev->bd_inode);
+	device->disk_total_bytes = device->total_bytes;
 	device->dev_root = root->fs_info->dev_root;
 	device->bdev = bdev;
 	device->in_fs_metadata = 1;
diff --git a/fs/buffer.c b/fs/buffer.c
index aed297739eb..49106127a4a 100644
--- a/fs/buffer.c
+++ b/fs/buffer.c
@@ -2736,6 +2736,8 @@ 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;
diff --git a/fs/inode.c b/fs/inode.c
index 0571983755d..bca0c618fdb 100644
--- a/fs/inode.c
+++ b/fs/inode.c
@@ -219,6 +219,7 @@ static struct inode *alloc_inode(struct super_block *sb)
 void destroy_inode(struct inode *inode)
 {
 	BUG_ON(inode_has_buffers(inode));
+	ima_inode_free(inode);
 	security_inode_free(inode);
 	if (inode->i_sb->s_op->destroy_inode)
 		inode->i_sb->s_op->destroy_inode(inode);
@@ -1053,13 +1054,22 @@ int insert_inode_locked(struct inode *inode)
 	struct super_block *sb = inode->i_sb;
 	ino_t ino = inode->i_ino;
 	struct hlist_head *head = inode_hashtable + hash(sb, ino);
-	struct inode *old;
 
 	inode->i_state |= I_LOCK|I_NEW;
 	while (1) {
+		struct hlist_node *node;
+		struct inode *old = NULL;
 		spin_lock(&inode_lock);
-		old = find_inode_fast(sb, head, ino);
-		if (likely(!old)) {
+		hlist_for_each_entry(old, node, head, i_hash) {
+			if (old->i_ino != ino)
+				continue;
+			if (old->i_sb != sb)
+				continue;
+			if (old->i_state & (I_FREEING|I_CLEAR|I_WILL_FREE))
+				continue;
+			break;
+		}
+		if (likely(!node)) {
 			hlist_add_head(&inode->i_hash, head);
 			spin_unlock(&inode_lock);
 			return 0;
@@ -1081,14 +1091,24 @@ int insert_inode_locked4(struct inode *inode, unsigned long hashval,
 {
 	struct super_block *sb = inode->i_sb;
 	struct hlist_head *head = inode_hashtable + hash(sb, hashval);
-	struct inode *old;
 
 	inode->i_state |= I_LOCK|I_NEW;
 
 	while (1) {
+		struct hlist_node *node;
+		struct inode *old = NULL;
+
 		spin_lock(&inode_lock);
-		old = find_inode(sb, head, test, data);
-		if (likely(!old)) {
+		hlist_for_each_entry(old, node, head, i_hash) {
+			if (old->i_sb != sb)
+				continue;
+			if (!test(old, data))
+				continue;
+			if (old->i_state & (I_FREEING|I_CLEAR|I_WILL_FREE))
+				continue;
+			break;
+		}
+		if (likely(!node)) {
 			hlist_add_head(&inode->i_hash, head);
 			spin_unlock(&inode_lock);
 			return 0;
diff --git a/fs/jbd/commit.c b/fs/jbd/commit.c
index 06560c520f4..618e21c0b7a 100644
--- a/fs/jbd/commit.c
+++ b/fs/jbd/commit.c
@@ -241,7 +241,7 @@ write_out_data:
 			spin_lock(&journal->j_list_lock);
 		}
 		/* Someone already cleaned up the buffer? */
-		if (!buffer_jbd(bh)
+		if (!buffer_jbd(bh) || bh2jh(bh) != jh
 			|| jh->b_transaction != commit_transaction
 			|| jh->b_jlist != BJ_SyncData) {
 			jbd_unlock_bh_state(bh);
@@ -478,7 +478,9 @@ void journal_commit_transaction(journal_t *journal)
 			spin_lock(&journal->j_list_lock);
 			continue;
 		}
-		if (buffer_jbd(bh) && jh->b_jlist == BJ_Locked) {
+		if (buffer_jbd(bh) && bh2jh(bh) == jh &&
+		    jh->b_transaction == commit_transaction &&
+		    jh->b_jlist == BJ_Locked) {
 			__journal_unfile_buffer(jh);
 			jbd_unlock_bh_state(bh);
 			journal_remove_journal_head(bh);
diff --git a/fs/proc/loadavg.c b/fs/proc/loadavg.c
index 9bca39cf99e..1afa4dd4cae 100644
--- a/fs/proc/loadavg.c
+++ b/fs/proc/loadavg.c
@@ -12,20 +12,14 @@
 
 static int loadavg_proc_show(struct seq_file *m, void *v)
 {
-	int a, b, c;
-	unsigned long seq;
+	unsigned long avnrun[3];
 
-	do {
-		seq = read_seqbegin(&xtime_lock);
-		a = avenrun[0] + (FIXED_1/200);
-		b = avenrun[1] + (FIXED_1/200);
-		c = avenrun[2] + (FIXED_1/200);
-	} while (read_seqretry(&xtime_lock, seq));
+	get_avenrun(avnrun, FIXED_1/200, 0);
 
-	seq_printf(m, "%d.%02d %d.%02d %d.%02d %ld/%d %d\n",
-		LOAD_INT(a), LOAD_FRAC(a),
-		LOAD_INT(b), LOAD_FRAC(b),
-		LOAD_INT(c), LOAD_FRAC(c),
+	seq_printf(m, "%lu.%02lu %lu.%02lu %lu.%02lu %ld/%d %d\n",
+		LOAD_INT(avnrun[0]), LOAD_FRAC(avnrun[0]),
+		LOAD_INT(avnrun[1]), LOAD_FRAC(avnrun[1]),
+		LOAD_INT(avnrun[2]), LOAD_FRAC(avnrun[2]),
 		nr_running(), nr_threads,
 		task_active_pid_ns(current)->last_pid);
 	return 0;