Merge branch 'tip/perf/urgent-2' of git://git.kernel.org/pub/scm/linux/kernel/git/rostedt/linux-trace into perf/urgent

11 files changed, 77 insertions, 96 deletions

diff --git a/fs/btrfs/async-thread.c b/fs/btrfs/async-thread.c
index cb97174..0b39458 100644
--- a/fs/btrfs/async-thread.c
+++ b/fs/btrfs/async-thread.c
@@ -563,8 +563,8 @@ static struct btrfs_worker_thread *find_worker(struct btrfs_workers *workers)
 	struct list_head *fallback;
 	int ret;
 
-again:
 	spin_lock_irqsave(&workers->lock, flags);
+again:
 	worker = next_worker(workers);
 
 	if (!worker) {
@@ -579,6 +579,7 @@ again:
 			spin_unlock_irqrestore(&workers->lock, flags);
 			/* we're below the limit, start another worker */
 			ret = __btrfs_start_workers(workers);
+			spin_lock_irqsave(&workers->lock, flags);
 			if (ret)
 				goto fallback;
 			goto again;
diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index 0a6b928..fd1a06d 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -4590,10 +4590,6 @@ static int btrfs_add_nondir(struct btrfs_trans_handle *trans,
 	int err = btrfs_add_link(trans, dir, inode,
 				 dentry->d_name.name, dentry->d_name.len,
 				 backref, index);
-	if (!err) {
-		d_instantiate(dentry, inode);
-		return 0;
-	}
 	if (err > 0)
 		err = -EEXIST;
 	return err;
@@ -4655,6 +4651,7 @@ static int btrfs_mknod(struct inode *dir, struct dentry *dentry,
 	else {
 		init_special_inode(inode, inode->i_mode, rdev);
 		btrfs_update_inode(trans, root, inode);
+		d_instantiate(dentry, inode);
 	}
 out_unlock:
 	nr = trans->blocks_used;
@@ -4722,6 +4719,7 @@ static int btrfs_create(struct inode *dir, struct dentry *dentry,
 		inode->i_mapping->a_ops = &btrfs_aops;
 		inode->i_mapping->backing_dev_info = &root->fs_info->bdi;
 		BTRFS_I(inode)->io_tree.ops = &btrfs_extent_io_ops;
+		d_instantiate(dentry, inode);
 	}
 out_unlock:
 	nr = trans->blocks_used;
@@ -4779,6 +4777,7 @@ static int btrfs_link(struct dentry *old_dentry, struct inode *dir,
 		struct dentry *parent = dentry->d_parent;
 		err = btrfs_update_inode(trans, root, inode);
 		BUG_ON(err);
+		d_instantiate(dentry, inode);
 		btrfs_log_new_name(trans, inode, NULL, parent);
 	}
 
@@ -7245,6 +7244,8 @@ static int btrfs_symlink(struct inode *dir, struct dentry *dentry,
 		drop_inode = 1;
 
 out_unlock:
+	if (!err)
+		d_instantiate(dentry, inode);
 	nr = trans->blocks_used;
 	btrfs_end_transaction_throttle(trans, root);
 	if (drop_inode) {
diff --git a/fs/ceph/dir.c b/fs/ceph/dir.c
index 3eeb976..9895400 100644
--- a/fs/ceph/dir.c
+++ b/fs/ceph/dir.c
@@ -1094,42 +1094,19 @@ static int ceph_snapdir_d_revalidate(struct dentry *dentry,
 /*
  * Set/clear/test dir complete flag on the dir's dentry.
  */
-static struct dentry * __d_find_any_alias(struct inode *inode)
-{
-	struct dentry *alias;
-
-	if (list_empty(&inode->i_dentry))
-		return NULL;
-	alias = list_first_entry(&inode->i_dentry, struct dentry, d_alias);
-	return alias;
-}
-
 void ceph_dir_set_complete(struct inode *inode)
 {
-	struct dentry *dentry = __d_find_any_alias(inode);
-	
-	if (dentry && ceph_dentry(dentry)) {
-		dout(" marking %p (%p) complete\n", inode, dentry);
-		set_bit(CEPH_D_COMPLETE, &ceph_dentry(dentry)->flags);
-	}
+	/* not yet implemented */
 }
 
 void ceph_dir_clear_complete(struct inode *inode)
 {
-	struct dentry *dentry = __d_find_any_alias(inode);
-
-	if (dentry && ceph_dentry(dentry)) {
-		dout(" marking %p (%p) NOT complete\n", inode, dentry);
-		clear_bit(CEPH_D_COMPLETE, &ceph_dentry(dentry)->flags);
-	}
+	/* not yet implemented */
 }
 
 bool ceph_dir_test_complete(struct inode *inode)
 {
-	struct dentry *dentry = __d_find_any_alias(inode);
-
-	if (dentry && ceph_dentry(dentry))
-		return test_bit(CEPH_D_COMPLETE, &ceph_dentry(dentry)->flags);
+	/* not yet implemented */
 	return false;
 }
 
diff --git a/fs/cifs/connect.c b/fs/cifs/connect.c
index 8cd4b52..f3670cf 100644
--- a/fs/cifs/connect.c
+++ b/fs/cifs/connect.c
@@ -282,7 +282,7 @@ static int coalesce_t2(struct smb_hdr *psecond, struct smb_hdr *pTargetSMB)
 	byte_count = be32_to_cpu(pTargetSMB->smb_buf_length);
 	byte_count += total_in_buf2;
 	/* don't allow buffer to overflow */
-	if (byte_count > CIFSMaxBufSize)
+	if (byte_count > CIFSMaxBufSize + MAX_CIFS_HDR_SIZE - 4)
 		return -ENOBUFS;
 	pTargetSMB->smb_buf_length = cpu_to_be32(byte_count);
 
@@ -2122,7 +2122,7 @@ cifs_get_smb_ses(struct TCP_Server_Info *server, struct smb_vol *volume_info)
 		warned_on_ntlm = true;
 		cERROR(1, "default security mechanism requested.  The default "
 			"security mechanism will be upgraded from ntlm to "
-			"ntlmv2 in kernel release 3.2");
+			"ntlmv2 in kernel release 3.3");
 	}
 	ses->overrideSecFlg = volume_info->secFlg;
 
diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c
index ac86f8b..517f211 100644
--- a/fs/fs-writeback.c
+++ b/fs/fs-writeback.c
@@ -47,17 +47,6 @@ struct wb_writeback_work {
 	struct completion *done;	/* set if the caller waits */
 };
 
-const char *wb_reason_name[] = {
-	[WB_REASON_BACKGROUND]		= "background",
-	[WB_REASON_TRY_TO_FREE_PAGES]	= "try_to_free_pages",
-	[WB_REASON_SYNC]		= "sync",
-	[WB_REASON_PERIODIC]		= "periodic",
-	[WB_REASON_LAPTOP_TIMER]	= "laptop_timer",
-	[WB_REASON_FREE_MORE_MEM]	= "free_more_memory",
-	[WB_REASON_FS_FREE_SPACE]	= "fs_free_space",
-	[WB_REASON_FORKER_THREAD]	= "forker_thread"
-};
-
 /*
  * Include the creation of the trace points after defining the
  * wb_writeback_work structure so that the definition remains local to this
diff --git a/fs/locks.c b/fs/locks.c
index 3b0d05d..637694b 100644
--- a/fs/locks.c
+++ b/fs/locks.c
@@ -1205,6 +1205,8 @@ int __break_lease(struct inode *inode, unsigned int mode)
 	int want_write = (mode & O_ACCMODE) != O_RDONLY;
 
 	new_fl = lease_alloc(NULL, want_write ? F_WRLCK : F_RDLCK);
+	if (IS_ERR(new_fl))
+		return PTR_ERR(new_fl);
 
 	lock_flocks();
 
@@ -1221,12 +1223,6 @@ int __break_lease(struct inode *inode, unsigned int mode)
 		if (fl->fl_owner == current->files)
 			i_have_this_lease = 1;
 
-	if (IS_ERR(new_fl) && !i_have_this_lease
-			&& ((mode & O_NONBLOCK) == 0)) {
-		error = PTR_ERR(new_fl);
-		goto out;
-	}
-
 	break_time = 0;
 	if (lease_break_time > 0) {
 		break_time = jiffies + lease_break_time * HZ;
@@ -1284,8 +1280,7 @@ restart:
 
 out:
 	unlock_flocks();
-	if (!IS_ERR(new_fl))
-		locks_free_lock(new_fl);
+	locks_free_lock(new_fl);
 	return error;
 }
 
diff --git a/fs/minix/inode.c b/fs/minix/inode.c
index 1d9e339..4d46a6a 100644
--- a/fs/minix/inode.c
+++ b/fs/minix/inode.c
@@ -263,23 +263,6 @@ static int minix_fill_super(struct super_block *s, void *data, int silent)
 		goto out_no_root;
 	}
 
-	ret = -ENOMEM;
-	s->s_root = d_alloc_root(root_inode);
-	if (!s->s_root)
-		goto out_iput;
-
-	if (!(s->s_flags & MS_RDONLY)) {
-		if (sbi->s_version != MINIX_V3) /* s_state is now out from V3 sb */
-			ms->s_state &= ~MINIX_VALID_FS;
-		mark_buffer_dirty(bh);
-	}
-	if (!(sbi->s_mount_state & MINIX_VALID_FS))
-		printk("MINIX-fs: mounting unchecked file system, "
-			"running fsck is recommended\n");
- 	else if (sbi->s_mount_state & MINIX_ERROR_FS)
-		printk("MINIX-fs: mounting file system with errors, "
-			"running fsck is recommended\n");
-
 	/* Apparently minix can create filesystems that allocate more blocks for
 	 * the bitmaps than needed.  We simply ignore that, but verify it didn't
 	 * create one with not enough blocks and bail out if so.
@@ -300,6 +283,23 @@ static int minix_fill_super(struct super_block *s, void *data, int silent)
 		goto out_iput;
 	}
 
+	ret = -ENOMEM;
+	s->s_root = d_alloc_root(root_inode);
+	if (!s->s_root)
+		goto out_iput;
+
+	if (!(s->s_flags & MS_RDONLY)) {
+		if (sbi->s_version != MINIX_V3) /* s_state is now out from V3 sb */
+			ms->s_state &= ~MINIX_VALID_FS;
+		mark_buffer_dirty(bh);
+	}
+	if (!(sbi->s_mount_state & MINIX_VALID_FS))
+		printk("MINIX-fs: mounting unchecked file system, "
+			"running fsck is recommended\n");
+	else if (sbi->s_mount_state & MINIX_ERROR_FS)
+		printk("MINIX-fs: mounting file system with errors, "
+			"running fsck is recommended\n");
+
 	return 0;
 
 out_iput:
diff --git a/fs/proc/stat.c b/fs/proc/stat.c
index 2a30d67..0855e6f 100644
--- a/fs/proc/stat.c
+++ b/fs/proc/stat.c
@@ -32,7 +32,7 @@ static cputime64_t get_idle_time(int cpu)
 		idle = kstat_cpu(cpu).cpustat.idle;
 		idle = cputime64_add(idle, arch_idle_time(cpu));
 	} else
-		idle = nsecs_to_jiffies64(1000 * idle_time);
+		idle = usecs_to_cputime64(idle_time);
 
 	return idle;
 }
@@ -46,7 +46,7 @@ static cputime64_t get_iowait_time(int cpu)
 		/* !NO_HZ so we can rely on cpustat.iowait */
 		iowait = kstat_cpu(cpu).cpustat.iowait;
 	else
-		iowait = nsecs_to_jiffies64(1000 * iowait_time);
+		iowait = usecs_to_cputime64(iowait_time);
 
 	return iowait;
 }
diff --git a/fs/xfs/xfs_super.c b/fs/xfs/xfs_super.c
index 3eca58f..8a89949 100644
--- a/fs/xfs/xfs_super.c
+++ b/fs/xfs/xfs_super.c
@@ -869,27 +869,6 @@ xfs_fs_dirty_inode(
 }
 
 STATIC int
-xfs_log_inode(
-	struct xfs_inode	*ip)
-{
-	struct xfs_mount	*mp = ip->i_mount;
-	struct xfs_trans	*tp;
-	int			error;
-
-	tp = xfs_trans_alloc(mp, XFS_TRANS_FSYNC_TS);
-	error = xfs_trans_reserve(tp, 0, XFS_FSYNC_TS_LOG_RES(mp), 0, 0, 0);
-	if (error) {
-		xfs_trans_cancel(tp, 0);
-		return error;
-	}
-
-	xfs_ilock(ip, XFS_ILOCK_EXCL);
-	xfs_trans_ijoin(tp, ip, XFS_ILOCK_EXCL);
-	xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE);
-	return xfs_trans_commit(tp, 0);
-}
-
-STATIC int
 xfs_fs_write_inode(
 	struct inode		*inode,
 	struct writeback_control *wbc)
@@ -902,10 +881,8 @@ xfs_fs_write_inode(
 
 	if (XFS_FORCED_SHUTDOWN(mp))
 		return -XFS_ERROR(EIO);
-	if (!ip->i_update_core)
-		return 0;
 
-	if (wbc->sync_mode == WB_SYNC_ALL) {
+	if (wbc->sync_mode == WB_SYNC_ALL || wbc->for_kupdate) {
 		/*
 		 * Make sure the inode has made it it into the log.  Instead
 		 * of forcing it all the way to stable storage using a
@@ -913,11 +890,14 @@ xfs_fs_write_inode(
 		 * ->sync_fs call do that for thus, which reduces the number
 		 * of synchronous log forces dramatically.
 		 */
-		error = xfs_log_inode(ip);
+		error = xfs_log_dirty_inode(ip, NULL, 0);
 		if (error)
 			goto out;
 		return 0;
 	} else {
+		if (!ip->i_update_core)
+			return 0;
+
 		/*
 		 * We make this non-blocking if the inode is contended, return
 		 * EAGAIN to indicate to the caller that they did not succeed.
diff --git a/fs/xfs/xfs_sync.c b/fs/xfs/xfs_sync.c
index be5c51d..f0994aedc 100644
--- a/fs/xfs/xfs_sync.c
+++ b/fs/xfs/xfs_sync.c
@@ -336,6 +336,32 @@ xfs_sync_fsdata(
 	return error;
 }
 
+int
+xfs_log_dirty_inode(
+	struct xfs_inode	*ip,
+	struct xfs_perag	*pag,
+	int			flags)
+{
+	struct xfs_mount	*mp = ip->i_mount;
+	struct xfs_trans	*tp;
+	int			error;
+
+	if (!ip->i_update_core)
+		return 0;
+
+	tp = xfs_trans_alloc(mp, XFS_TRANS_FSYNC_TS);
+	error = xfs_trans_reserve(tp, 0, XFS_FSYNC_TS_LOG_RES(mp), 0, 0, 0);
+	if (error) {
+		xfs_trans_cancel(tp, 0);
+		return error;
+	}
+
+	xfs_ilock(ip, XFS_ILOCK_EXCL);
+	xfs_trans_ijoin(tp, ip, XFS_ILOCK_EXCL);
+	xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE);
+	return xfs_trans_commit(tp, 0);
+}
+
 /*
  * When remounting a filesystem read-only or freezing the filesystem, we have
  * two phases to execute. This first phase is syncing the data before we
@@ -359,6 +385,16 @@ xfs_quiesce_data(
 {
 	int			error, error2 = 0;
 
+	/*
+	 * Log all pending size and timestamp updates.  The vfs writeback
+	 * code is supposed to do this, but due to its overagressive
+	 * livelock detection it will skip inodes where appending writes
+	 * were written out in the first non-blocking sync phase if their
+	 * completion took long enough that it happened after taking the
+	 * timestamp for the cut-off in the blocking phase.
+	 */
+	xfs_inode_ag_iterator(mp, xfs_log_dirty_inode, 0);
+
 	xfs_qm_sync(mp, SYNC_TRYLOCK);
 	xfs_qm_sync(mp, SYNC_WAIT);
 
diff --git a/fs/xfs/xfs_sync.h b/fs/xfs/xfs_sync.h
index 941202e..fa96547 100644
--- a/fs/xfs/xfs_sync.h
+++ b/fs/xfs/xfs_sync.h
@@ -34,6 +34,8 @@ void xfs_quiesce_attr(struct xfs_mount *mp);
 
 void xfs_flush_inodes(struct xfs_inode *ip);
 
+int xfs_log_dirty_inode(struct xfs_inode *ip, struct xfs_perag *pag, int flags);
+
 int xfs_reclaim_inodes(struct xfs_mount *mp, int mode);
 int xfs_reclaim_inodes_count(struct xfs_mount *mp);
 void xfs_reclaim_inodes_nr(struct xfs_mount *mp, int nr_to_scan);