Merge branch 'core/locking' into tracing/ftrace

13 files changed, 69 insertions, 48 deletions

diff --git a/fs/devpts/inode.c b/fs/devpts/inode.c
index 5f3231b9633..bff4052b05e 100644
--- a/fs/devpts/inode.c
+++ b/fs/devpts/inode.c
@@ -198,9 +198,6 @@ static int mknod_ptmx(struct super_block *sb)
 
 	fsi->ptmx_dentry = dentry;
 	rc = 0;
-
-	printk(KERN_DEBUG "Created ptmx node in devpts ino %lu\n",
-			inode->i_ino);
 out:
 	mutex_unlock(&root->d_inode->i_mutex);
 	return rc;
@@ -369,8 +366,6 @@ static int new_pts_mount(struct file_system_type *fs_type, int flags,
 	struct pts_fs_info *fsi;
 	struct pts_mount_opts *opts;
 
-	printk(KERN_NOTICE "devpts: newinstance mount\n");
-
 	err = get_sb_nodev(fs_type, flags, data, devpts_fill_super, mnt);
 	if (err)
 		return err;
diff --git a/fs/fat/inode.c b/fs/fat/inode.c
index 6b74d09adbe..de0004fe6e0 100644
--- a/fs/fat/inode.c
+++ b/fs/fat/inode.c
@@ -202,9 +202,9 @@ static sector_t _fat_bmap(struct address_space *mapping, sector_t block)
 	sector_t blocknr;
 
 	/* fat_get_cluster() assumes the requested blocknr isn't truncated. */
-	mutex_lock(&mapping->host->i_mutex);
+	down_read(&mapping->host->i_alloc_sem);
 	blocknr = generic_block_bmap(mapping, block, fat_get_block);
-	mutex_unlock(&mapping->host->i_mutex);
+	up_read(&mapping->host->i_alloc_sem);
 
 	return blocknr;
 }
diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c
index e5eaa62fd17..e3fe9918faa 100644
--- a/fs/fs-writeback.c
+++ b/fs/fs-writeback.c
@@ -274,6 +274,7 @@ __sync_single_inode(struct inode *inode, struct writeback_control *wbc)
 	int ret;
 
 	BUG_ON(inode->i_state & I_SYNC);
+	WARN_ON(inode->i_state & I_NEW);
 
 	/* Set I_SYNC, reset I_DIRTY */
 	dirty = inode->i_state & I_DIRTY;
@@ -298,6 +299,7 @@ __sync_single_inode(struct inode *inode, struct writeback_control *wbc)
 	}
 
 	spin_lock(&inode_lock);
+	WARN_ON(inode->i_state & I_NEW);
 	inode->i_state &= ~I_SYNC;
 	if (!(inode->i_state & I_FREEING)) {
 		if (!(inode->i_state & I_DIRTY) &&
@@ -470,6 +472,11 @@ void generic_sync_sb_inodes(struct super_block *sb,
 			break;
 		}
 
+		if (inode->i_state & I_NEW) {
+			requeue_io(inode);
+			continue;
+		}
+
 		if (wbc->nonblocking && bdi_write_congested(bdi)) {
 			wbc->encountered_congestion = 1;
 			if (!sb_is_blkdev_sb(sb))
@@ -531,7 +538,7 @@ void generic_sync_sb_inodes(struct super_block *sb,
 		list_for_each_entry(inode, &sb->s_inodes, i_sb_list) {
 			struct address_space *mapping;
 
-			if (inode->i_state & (I_FREEING|I_WILL_FREE))
+			if (inode->i_state & (I_FREEING|I_WILL_FREE|I_NEW))
 				continue;
 			mapping = inode->i_mapping;
 			if (mapping->nrpages == 0)
diff --git a/fs/inode.c b/fs/inode.c
index 913ab2d9a5d..826fb0b9d1c 100644
--- a/fs/inode.c
+++ b/fs/inode.c
@@ -359,6 +359,7 @@ static int invalidate_list(struct list_head *head, struct list_head *dispose)
 		invalidate_inode_buffers(inode);
 		if (!atomic_read(&inode->i_count)) {
 			list_move(&inode->i_list, dispose);
+			WARN_ON(inode->i_state & I_NEW);
 			inode->i_state |= I_FREEING;
 			count++;
 			continue;
@@ -460,6 +461,7 @@ static void prune_icache(int nr_to_scan)
 				continue;
 		}
 		list_move(&inode->i_list, &freeable);
+		WARN_ON(inode->i_state & I_NEW);
 		inode->i_state |= I_FREEING;
 		nr_pruned++;
 	}
@@ -656,6 +658,7 @@ void unlock_new_inode(struct inode *inode)
 	 * just created it (so there can be no old holders
 	 * that haven't tested I_LOCK).
 	 */
+	WARN_ON((inode->i_state & (I_LOCK|I_NEW)) != (I_LOCK|I_NEW));
 	inode->i_state &= ~(I_LOCK|I_NEW);
 	wake_up_inode(inode);
 }
@@ -1145,6 +1148,7 @@ void generic_delete_inode(struct inode *inode)
 
 	list_del_init(&inode->i_list);
 	list_del_init(&inode->i_sb_list);
+	WARN_ON(inode->i_state & I_NEW);
 	inode->i_state |= I_FREEING;
 	inodes_stat.nr_inodes--;
 	spin_unlock(&inode_lock);
@@ -1186,16 +1190,19 @@ static void generic_forget_inode(struct inode *inode)
 			spin_unlock(&inode_lock);
 			return;
 		}
+		WARN_ON(inode->i_state & I_NEW);
 		inode->i_state |= I_WILL_FREE;
 		spin_unlock(&inode_lock);
 		write_inode_now(inode, 1);
 		spin_lock(&inode_lock);
+		WARN_ON(inode->i_state & I_NEW);
 		inode->i_state &= ~I_WILL_FREE;
 		inodes_stat.nr_unused--;
 		hlist_del_init(&inode->i_hash);
 	}
 	list_del_init(&inode->i_list);
 	list_del_init(&inode->i_sb_list);
+	WARN_ON(inode->i_state & I_NEW);
 	inode->i_state |= I_FREEING;
 	inodes_stat.nr_inodes--;
 	spin_unlock(&inode_lock);
diff --git a/fs/pipe.c b/fs/pipe.c
index 3a48ba5179d..14f502b89cf 100644
--- a/fs/pipe.c
+++ b/fs/pipe.c
@@ -699,12 +699,12 @@ pipe_rdwr_fasync(int fd, struct file *filp, int on)
 	int retval;
 
 	mutex_lock(&inode->i_mutex);
-
 	retval = fasync_helper(fd, filp, on, &pipe->fasync_readers);
-
-	if (retval >= 0)
+	if (retval >= 0) {
 		retval = fasync_helper(fd, filp, on, &pipe->fasync_writers);
-
+		if (retval < 0) /* this can happen only if on == T */
+			fasync_helper(-1, filp, 0, &pipe->fasync_readers);
+	}
 	mutex_unlock(&inode->i_mutex);
 
 	if (retval < 0)
diff --git a/fs/proc/page.c b/fs/proc/page.c
index 2d1345112a4..e9983837d08 100644
--- a/fs/proc/page.c
+++ b/fs/proc/page.c
@@ -80,7 +80,7 @@ static const struct file_operations proc_kpagecount_operations = {
 #define KPF_RECLAIM    9
 #define KPF_BUDDY     10
 
-#define kpf_copy_bit(flags, srcpos, dstpos) (((flags >> srcpos) & 1) << dstpos)
+#define kpf_copy_bit(flags, dstpos, srcpos) (((flags >> srcpos) & 1) << dstpos)
 
 static ssize_t kpageflags_read(struct file *file, char __user *buf,
 			     size_t count, loff_t *ppos)
diff --git a/fs/squashfs/block.c b/fs/squashfs/block.c
index 321728f48f2..2a796031034 100644
--- a/fs/squashfs/block.c
+++ b/fs/squashfs/block.c
@@ -184,15 +184,7 @@ int squashfs_read_data(struct super_block *sb, void **buffer, u64 index,
 				offset = 0;
 			}
 
-			if (msblk->stream.avail_out == 0) {
-				if (page == pages) {
-					ERROR("zlib_inflate tried to "
-						"decompress too much data, "
-						"expected %d bytes.  Zlib "
-						"data probably corrupt\n",
-						srclength);
-					goto release_mutex;
-				}
+			if (msblk->stream.avail_out == 0 && page < pages) {
 				msblk->stream.next_out = buffer[page++];
 				msblk->stream.avail_out = PAGE_CACHE_SIZE;
 			}
@@ -209,25 +201,20 @@ int squashfs_read_data(struct super_block *sb, void **buffer, u64 index,
 				zlib_init = 1;
 			}
 
-			zlib_err = zlib_inflate(&msblk->stream, Z_NO_FLUSH);
+			zlib_err = zlib_inflate(&msblk->stream, Z_SYNC_FLUSH);
 
 			if (msblk->stream.avail_in == 0 && k < b)
 				put_bh(bh[k++]);
 		} while (zlib_err == Z_OK);
 
 		if (zlib_err != Z_STREAM_END) {
-			ERROR("zlib_inflate returned unexpected result"
-				" 0x%x, srclength %d, avail_in %d,"
-				" avail_out %d\n", zlib_err, srclength,
-				msblk->stream.avail_in,
-				msblk->stream.avail_out);
+			ERROR("zlib_inflate error, data probably corrupt\n");
 			goto release_mutex;
 		}
 
 		zlib_err = zlib_inflateEnd(&msblk->stream);
 		if (zlib_err != Z_OK) {
-			ERROR("zlib_inflateEnd returned unexpected result 0x%x,"
-				" srclength %d\n", zlib_err, srclength);
+			ERROR("zlib_inflate error, data probably corrupt\n");
 			goto release_mutex;
 		}
 		length = msblk->stream.total_out;
diff --git a/fs/super.c b/fs/super.c
index 8349ed6b141..6ce501447ad 100644
--- a/fs/super.c
+++ b/fs/super.c
@@ -371,8 +371,10 @@ retry:
 				continue;
 			if (!grab_super(old))
 				goto retry;
-			if (s)
+			if (s) {
+				up_write(&s->s_umount);
 				destroy_super(s);
+			}
 			return old;
 		}
 	}
@@ -387,6 +389,7 @@ retry:
 	err = set(s, data);
 	if (err) {
 		spin_unlock(&sb_lock);
+		up_write(&s->s_umount);
 		destroy_super(s);
 		return ERR_PTR(err);
 	}
diff --git a/fs/xfs/linux-2.6/xfs_buf.c b/fs/xfs/linux-2.6/xfs_buf.c
index cb329edc925..aa1016bb913 100644
--- a/fs/xfs/linux-2.6/xfs_buf.c
+++ b/fs/xfs/linux-2.6/xfs_buf.c
@@ -34,6 +34,12 @@
 #include <linux/backing-dev.h>
 #include <linux/freezer.h>
 
+#include "xfs_sb.h"
+#include "xfs_inum.h"
+#include "xfs_ag.h"
+#include "xfs_dmapi.h"
+#include "xfs_mount.h"
+
 static kmem_zone_t *xfs_buf_zone;
 STATIC int xfsbufd(void *);
 STATIC int xfsbufd_wakeup(int, gfp_t);
@@ -1435,10 +1441,12 @@ xfs_unregister_buftarg(
 
 void
 xfs_free_buftarg(
-	xfs_buftarg_t		*btp)
+	struct xfs_mount	*mp,
+	struct xfs_buftarg	*btp)
 {
 	xfs_flush_buftarg(btp, 1);
-	xfs_blkdev_issue_flush(btp);
+	if (mp->m_flags & XFS_MOUNT_BARRIER)
+		xfs_blkdev_issue_flush(btp);
 	xfs_free_bufhash(btp);
 	iput(btp->bt_mapping->host);
 
diff --git a/fs/xfs/linux-2.6/xfs_buf.h b/fs/xfs/linux-2.6/xfs_buf.h
index 288ae7c4c80..9b4d666ad31 100644
--- a/fs/xfs/linux-2.6/xfs_buf.h
+++ b/fs/xfs/linux-2.6/xfs_buf.h
@@ -413,7 +413,7 @@ static inline int XFS_bwrite(xfs_buf_t *bp)
  *	Handling of buftargs.
  */
 extern xfs_buftarg_t *xfs_alloc_buftarg(struct block_device *, int);
-extern void xfs_free_buftarg(xfs_buftarg_t *);
+extern void xfs_free_buftarg(struct xfs_mount *, struct xfs_buftarg *);
 extern void xfs_wait_buftarg(xfs_buftarg_t *);
 extern int xfs_setsize_buftarg(xfs_buftarg_t *, unsigned int, unsigned int);
 extern int xfs_flush_buftarg(xfs_buftarg_t *, int);
diff --git a/fs/xfs/linux-2.6/xfs_super.c b/fs/xfs/linux-2.6/xfs_super.c
index c71e226da7f..32ae5028e96 100644
--- a/fs/xfs/linux-2.6/xfs_super.c
+++ b/fs/xfs/linux-2.6/xfs_super.c
@@ -734,15 +734,15 @@ xfs_close_devices(
 {
 	if (mp->m_logdev_targp && mp->m_logdev_targp != mp->m_ddev_targp) {
 		struct block_device *logdev = mp->m_logdev_targp->bt_bdev;
-		xfs_free_buftarg(mp->m_logdev_targp);
+		xfs_free_buftarg(mp, mp->m_logdev_targp);
 		xfs_blkdev_put(logdev);
 	}
 	if (mp->m_rtdev_targp) {
 		struct block_device *rtdev = mp->m_rtdev_targp->bt_bdev;
-		xfs_free_buftarg(mp->m_rtdev_targp);
+		xfs_free_buftarg(mp, mp->m_rtdev_targp);
 		xfs_blkdev_put(rtdev);
 	}
-	xfs_free_buftarg(mp->m_ddev_targp);
+	xfs_free_buftarg(mp, mp->m_ddev_targp);
 }
 
 /*
@@ -811,9 +811,9 @@ xfs_open_devices(
 
  out_free_rtdev_targ:
 	if (mp->m_rtdev_targp)
-		xfs_free_buftarg(mp->m_rtdev_targp);
+		xfs_free_buftarg(mp, mp->m_rtdev_targp);
  out_free_ddev_targ:
-	xfs_free_buftarg(mp->m_ddev_targp);
+	xfs_free_buftarg(mp, mp->m_ddev_targp);
  out_close_rtdev:
 	if (rtdev)
 		xfs_blkdev_put(rtdev);
diff --git a/fs/xfs/xfs_iget.c b/fs/xfs/xfs_iget.c
index e2fb6210d4c..478e587087f 100644
--- a/fs/xfs/xfs_iget.c
+++ b/fs/xfs/xfs_iget.c
@@ -246,9 +246,6 @@ xfs_iget_cache_miss(
 		goto out_destroy;
 	}
 
-	if (lock_flags)
-		xfs_ilock(ip, lock_flags);
-
 	/*
 	 * Preload the radix tree so we can insert safely under the
 	 * write spinlock. Note that we cannot sleep inside the preload
@@ -256,7 +253,16 @@ xfs_iget_cache_miss(
 	 */
 	if (radix_tree_preload(GFP_KERNEL)) {
 		error = EAGAIN;
-		goto out_unlock;
+		goto out_destroy;
+	}
+
+	/*
+	 * Because the inode hasn't been added to the radix-tree yet it can't
+	 * be found by another thread, so we can do the non-sleeping lock here.
+	 */
+	if (lock_flags) {
+		if (!xfs_ilock_nowait(ip, lock_flags))
+			BUG();
 	}
 
 	mask = ~(((XFS_INODE_CLUSTER_SIZE(mp) >> mp->m_sb.sb_inodelog)) - 1);
@@ -284,7 +290,6 @@ xfs_iget_cache_miss(
 out_preload_end:
 	write_unlock(&pag->pag_ici_lock);
 	radix_tree_preload_end();
-out_unlock:
 	if (lock_flags)
 		xfs_iunlock(ip, lock_flags);
 out_destroy:
diff --git a/fs/xfs/xfs_log_recover.c b/fs/xfs/xfs_log_recover.c
index b1047de2fff..61af610d79b 100644
--- a/fs/xfs/xfs_log_recover.c
+++ b/fs/xfs/xfs_log_recover.c
@@ -1455,10 +1455,19 @@ xlog_recover_add_to_trans(
 	item = item->ri_prev;
 
 	if (item->ri_total == 0) {		/* first region to be added */
-		item->ri_total	= in_f->ilf_size;
-		ASSERT(item->ri_total <= XLOG_MAX_REGIONS_IN_ITEM);
-		item->ri_buf = kmem_zalloc((item->ri_total *
-					    sizeof(xfs_log_iovec_t)), KM_SLEEP);
+		if (in_f->ilf_size == 0 ||
+		    in_f->ilf_size > XLOG_MAX_REGIONS_IN_ITEM) {
+			xlog_warn(
+	"XFS: bad number of regions (%d) in inode log format",
+				  in_f->ilf_size);
+			ASSERT(0);
+			return XFS_ERROR(EIO);
+		}
+
+		item->ri_total = in_f->ilf_size;
+		item->ri_buf =
+			kmem_zalloc(item->ri_total * sizeof(xfs_log_iovec_t),
+				    KM_SLEEP);
 	}
 	ASSERT(item->ri_total > item->ri_cnt);
 	/* Description region is ri_buf[0] */