Merge branch 'reiserfs/kill-bkl' of git://git.kernel.org/pub/scm/linux/kernel/git/frederic/random-tracing

* 'reiserfs/kill-bkl' of git://git.kernel.org/pub/scm/linux/kernel/git/frederic/random-tracing: (31 commits)
  kill-the-bkl/reiserfs: turn GFP_ATOMIC flag to GFP_NOFS in reiserfs_get_block()
  kill-the-bkl/reiserfs: drop the fs race watchdog from _get_block_create_0()
  kill-the-bkl/reiserfs: definitely drop the bkl from reiserfs_ioctl()
  kill-the-bkl/reiserfs: always lock the ioctl path
  kill-the-bkl/reiserfs: fix reiserfs lock to cpu_add_remove_lock dependency
  kill-the-bkl/reiserfs: Fix induced mm->mmap_sem to sysfs_mutex dependency
  kill-the-bkl/reiserfs: panic in case of lock imbalance
  kill-the-bkl/reiserfs: fix recursive reiserfs write lock in reiserfs_commit_write()
  kill-the-bkl/reiserfs: fix recursive reiserfs lock in reiserfs_mkdir()
  kill-the-bkl/reiserfs: fix "reiserfs lock" / "inode mutex" lock inversion dependency
  kill-the-bkl/reiserfs: move the concurrent tree accesses checks per superblock
  kill-the-bkl/reiserfs: acquire the inode mutex safely
  kill-the-bkl/reiserfs: unlock only when needed in search_by_key
  kill-the-bkl/reiserfs: use mutex_lock in reiserfs_mutex_lock_safe
  kill-the-bkl/reiserfs: factorize the locking in reiserfs_write_end()
  kill-the-bkl/reiserfs: reduce number of contentions in search_by_key()
  kill-the-bkl/reiserfs: don't hold the write recursively in reiserfs_lookup()
  kill-the-bkl/reiserfs: lock only once on reiserfs_get_block()
  kill-the-bkl/reiserfs: conditionaly release the write lock on fs_changed()
  kill-the-BKL/reiserfs: add reiserfs_cond_resched()
  ...

16 files changed, 420 insertions, 163 deletions

diff --git a/fs/reiserfs/Makefile b/fs/reiserfs/Makefile
index 7c5ab6330dd..6a9e30c041d 100644
--- a/fs/reiserfs/Makefile
+++ b/fs/reiserfs/Makefile
@@ -7,7 +7,7 @@ obj-$(CONFIG_REISERFS_FS) += reiserfs.o
 reiserfs-objs := bitmap.o do_balan.o namei.o inode.o file.o dir.o fix_node.o \
 		 super.o prints.o objectid.o lbalance.o ibalance.o stree.o \
 		 hashes.o tail_conversion.o journal.o resize.o \
-		 item_ops.o ioctl.o procfs.o xattr.o
+		 item_ops.o ioctl.o procfs.o xattr.o lock.o
 
 ifeq ($(CONFIG_REISERFS_FS_XATTR),y)
 reiserfs-objs += xattr_user.o xattr_trusted.o
diff --git a/fs/reiserfs/bitmap.c b/fs/reiserfs/bitmap.c
index e716161ab32..68549570718 100644
--- a/fs/reiserfs/bitmap.c
+++ b/fs/reiserfs/bitmap.c
@@ -1249,14 +1249,18 @@ struct buffer_head *reiserfs_read_bitmap_block(struct super_block *sb,
 	else if (bitmap == 0)
 		block = (REISERFS_DISK_OFFSET_IN_BYTES >> sb->s_blocksize_bits) + 1;
 
+	reiserfs_write_unlock(sb);
 	bh = sb_bread(sb, block);
+	reiserfs_write_lock(sb);
 	if (bh == NULL)
 		reiserfs_warning(sb, "sh-2029: %s: bitmap block (#%u) "
 		                 "reading failed", __func__, block);
 	else {
 		if (buffer_locked(bh)) {
 			PROC_INFO_INC(sb, scan_bitmap.wait);
+			reiserfs_write_unlock(sb);
 			__wait_on_buffer(bh);
+			reiserfs_write_lock(sb);
 		}
 		BUG_ON(!buffer_uptodate(bh));
 		BUG_ON(atomic_read(&bh->b_count) == 0);
diff --git a/fs/reiserfs/dir.c b/fs/reiserfs/dir.c
index 6d2668fdc38..c094f58c744 100644
--- a/fs/reiserfs/dir.c
+++ b/fs/reiserfs/dir.c
@@ -20,7 +20,7 @@ const struct file_operations reiserfs_dir_operations = {
 	.read = generic_read_dir,
 	.readdir = reiserfs_readdir,
 	.fsync = reiserfs_dir_fsync,
-	.ioctl = reiserfs_ioctl,
+	.unlocked_ioctl = reiserfs_ioctl,
 #ifdef CONFIG_COMPAT
 	.compat_ioctl = reiserfs_compat_ioctl,
 #endif
@@ -174,14 +174,22 @@ int reiserfs_readdir_dentry(struct dentry *dentry, void *dirent,
 				// user space buffer is swapped out. At that time
 				// entry can move to somewhere else
 				memcpy(local_buf, d_name, d_reclen);
+
+				/*
+				 * Since filldir might sleep, we can release
+				 * the write lock here for other waiters
+				 */
+				reiserfs_write_unlock(inode->i_sb);
 				if (filldir
 				    (dirent, local_buf, d_reclen, d_off, d_ino,
 				     DT_UNKNOWN) < 0) {
+					reiserfs_write_lock(inode->i_sb);
 					if (local_buf != small_buf) {
 						kfree(local_buf);
 					}
 					goto end;
 				}
+				reiserfs_write_lock(inode->i_sb);
 				if (local_buf != small_buf) {
 					kfree(local_buf);
 				}
diff --git a/fs/reiserfs/do_balan.c b/fs/reiserfs/do_balan.c
index 128d3f7c8aa..60c08044066 100644
--- a/fs/reiserfs/do_balan.c
+++ b/fs/reiserfs/do_balan.c
@@ -21,14 +21,6 @@
 #include <linux/buffer_head.h>
 #include <linux/kernel.h>
 
-#ifdef CONFIG_REISERFS_CHECK
-
-struct tree_balance *cur_tb = NULL;	/* detects whether more than one
-					   copy of tb exists as a means
-					   of checking whether schedule
-					   is interrupting do_balance */
-#endif
-
 static inline void buffer_info_init_left(struct tree_balance *tb,
                                          struct buffer_info *bi)
 {
@@ -1840,11 +1832,12 @@ static int check_before_balancing(struct tree_balance *tb)
 {
 	int retval = 0;
 
-	if (cur_tb) {
+	if (REISERFS_SB(tb->tb_sb)->cur_tb) {
 		reiserfs_panic(tb->tb_sb, "vs-12335", "suspect that schedule "
 			       "occurred based on cur_tb not being null at "
 			       "this point in code. do_balance cannot properly "
-			       "handle schedule occurring while it runs.");
+			       "handle concurrent tree accesses on a same "
+			       "mount point.");
 	}
 
 	/* double check that buffers that we will modify are unlocked. (fix_nodes should already have
@@ -1986,7 +1979,7 @@ static inline void do_balance_starts(struct tree_balance *tb)
 	     "check");*/
 	RFALSE(check_before_balancing(tb), "PAP-12340: locked buffers in TB");
 #ifdef CONFIG_REISERFS_CHECK
-	cur_tb = tb;
+	REISERFS_SB(tb->tb_sb)->cur_tb = tb;
 #endif
 }
 
@@ -1996,7 +1989,7 @@ static inline void do_balance_completed(struct tree_balance *tb)
 #ifdef CONFIG_REISERFS_CHECK
 	check_leaf_level(tb);
 	check_internal_levels(tb);
-	cur_tb = NULL;
+	REISERFS_SB(tb->tb_sb)->cur_tb = NULL;
 #endif
 
 	/* reiserfs_free_block is no longer schedule safe.  So, we need to
diff --git a/fs/reiserfs/file.c b/fs/reiserfs/file.c
index 9f436668b7f..da2dba082e2 100644
--- a/fs/reiserfs/file.c
+++ b/fs/reiserfs/file.c
@@ -284,7 +284,7 @@ static ssize_t reiserfs_file_write(struct file *file,	/* the file we are going t
 const struct file_operations reiserfs_file_operations = {
 	.read = do_sync_read,
 	.write = reiserfs_file_write,
-	.ioctl = reiserfs_ioctl,
+	.unlocked_ioctl = reiserfs_ioctl,
 #ifdef CONFIG_COMPAT
 	.compat_ioctl = reiserfs_compat_ioctl,
 #endif
diff --git a/fs/reiserfs/fix_node.c b/fs/reiserfs/fix_node.c
index 5e5a4e6fbaf..d2f31330dca 100644
--- a/fs/reiserfs/fix_node.c
+++ b/fs/reiserfs/fix_node.c
@@ -563,9 +563,6 @@ static int get_num_ver(int mode, struct tree_balance *tb, int h,
 	return needed_nodes;
 }
 
-#ifdef CONFIG_REISERFS_CHECK
-extern struct tree_balance *cur_tb;
-#endif
 
 /* Set parameters for balancing.
  * Performs write of results of analysis of balancing into structure tb,
@@ -1022,7 +1019,11 @@ static int get_far_parent(struct tree_balance *tb,
 	/* Check whether the common parent is locked. */
 
 	if (buffer_locked(*pcom_father)) {
+
+		/* Release the write lock while the buffer is busy */
+		reiserfs_write_unlock(tb->tb_sb);
 		__wait_on_buffer(*pcom_father);
+		reiserfs_write_lock(tb->tb_sb);
 		if (FILESYSTEM_CHANGED_TB(tb)) {
 			brelse(*pcom_father);
 			return REPEAT_SEARCH;
@@ -1927,7 +1928,9 @@ static int get_direct_parent(struct tree_balance *tb, int h)
 		return REPEAT_SEARCH;
 
 	if (buffer_locked(bh)) {
+		reiserfs_write_unlock(tb->tb_sb);
 		__wait_on_buffer(bh);
+		reiserfs_write_lock(tb->tb_sb);
 		if (FILESYSTEM_CHANGED_TB(tb))
 			return REPEAT_SEARCH;
 	}
@@ -1965,7 +1968,9 @@ static int get_neighbors(struct tree_balance *tb, int h)
 		     tb->FL[h]) ? tb->lkey[h] : B_NR_ITEMS(tb->
 								       FL[h]);
 		son_number = B_N_CHILD_NUM(tb->FL[h], child_position);
+		reiserfs_write_unlock(sb);
 		bh = sb_bread(sb, son_number);
+		reiserfs_write_lock(sb);
 		if (!bh)
 			return IO_ERROR;
 		if (FILESYSTEM_CHANGED_TB(tb)) {
@@ -2003,7 +2008,9 @@ static int get_neighbors(struct tree_balance *tb, int h)
 		child_position =
 		    (bh == tb->FR[h]) ? tb->rkey[h] + 1 : 0;
 		son_number = B_N_CHILD_NUM(tb->FR[h], child_position);
+		reiserfs_write_unlock(sb);
 		bh = sb_bread(sb, son_number);
+		reiserfs_write_lock(sb);
 		if (!bh)
 			return IO_ERROR;
 		if (FILESYSTEM_CHANGED_TB(tb)) {
@@ -2278,7 +2285,9 @@ static int wait_tb_buffers_until_unlocked(struct tree_balance *tb)
 				    REPEAT_SEARCH : CARRY_ON;
 			}
 #endif
+			reiserfs_write_unlock(tb->tb_sb);
 			__wait_on_buffer(locked);
+			reiserfs_write_lock(tb->tb_sb);
 			if (FILESYSTEM_CHANGED_TB(tb))
 				return REPEAT_SEARCH;
 		}
@@ -2349,12 +2358,14 @@ int fix_nodes(int op_mode, struct tree_balance *tb,
 
 	/* if it possible in indirect_to_direct conversion */
 	if (buffer_locked(tbS0)) {
+		reiserfs_write_unlock(tb->tb_sb);
 		__wait_on_buffer(tbS0);
+		reiserfs_write_lock(tb->tb_sb);
 		if (FILESYSTEM_CHANGED_TB(tb))
 			return REPEAT_SEARCH;
 	}
 #ifdef CONFIG_REISERFS_CHECK
-	if (cur_tb) {
+	if (REISERFS_SB(tb->tb_sb)->cur_tb) {
 		print_cur_tb("fix_nodes");
 		reiserfs_panic(tb->tb_sb, "PAP-8305",
 			       "there is pending do_balance");
diff --git a/fs/reiserfs/inode.c b/fs/reiserfs/inode.c
index a14d6cd9eed..3a28e7751b3 100644
--- a/fs/reiserfs/inode.c
+++ b/fs/reiserfs/inode.c
@@ -251,7 +251,6 @@ static int _get_block_create_0(struct inode *inode, sector_t block,
 	struct cpu_key key;
 	struct buffer_head *bh;
 	struct item_head *ih, tmp_ih;
-	int fs_gen;
 	b_blocknr_t blocknr;
 	char *p = NULL;
 	int chars;
@@ -265,7 +264,6 @@ static int _get_block_create_0(struct inode *inode, sector_t block,
 		     (loff_t) block * inode->i_sb->s_blocksize + 1, TYPE_ANY,
 		     3);
 
-      research:
 	result = search_for_position_by_key(inode->i_sb, &key, &path);
 	if (result != POSITION_FOUND) {
 		pathrelse(&path);
@@ -340,7 +338,6 @@ static int _get_block_create_0(struct inode *inode, sector_t block,
 	}
 	// read file tail into part of page
 	offset = (cpu_key_k_offset(&key) - 1) & (PAGE_CACHE_SIZE - 1);
-	fs_gen = get_generation(inode->i_sb);
 	copy_item_head(&tmp_ih, ih);
 
 	/* we only want to kmap if we are reading the tail into the page.
@@ -348,13 +345,9 @@ static int _get_block_create_0(struct inode *inode, sector_t block,
 	 ** sure we need to.  But, this means the item might move if
 	 ** kmap schedules
 	 */
-	if (!p) {
+	if (!p)
 		p = (char *)kmap(bh_result->b_page);
-		if (fs_changed(fs_gen, inode->i_sb)
-		    && item_moved(&tmp_ih, &path)) {
-			goto research;
-		}
-	}
+
 	p += offset;
 	memset(p, 0, inode->i_sb->s_blocksize);
 	do {
@@ -489,10 +482,14 @@ static int reiserfs_get_blocks_direct_io(struct inode *inode,
 	   disappeared */
 	if (REISERFS_I(inode)->i_flags & i_pack_on_close_mask) {
 		int err;
-		lock_kernel();
+
+		reiserfs_write_lock(inode->i_sb);
+
 		err = reiserfs_commit_for_inode(inode);
 		REISERFS_I(inode)->i_flags &= ~i_pack_on_close_mask;
-		unlock_kernel();
+
+		reiserfs_write_unlock(inode->i_sb);
+
 		if (err < 0)
 			ret = err;
 	}
@@ -601,6 +598,7 @@ int reiserfs_get_block(struct inode *inode, sector_t block,
 	__le32 *item;
 	int done;
 	int fs_gen;
+	int lock_depth;
 	struct reiserfs_transaction_handle *th = NULL;
 	/* space reserved in transaction batch:
 	   . 3 balancings in direct->indirect conversion
@@ -616,12 +614,11 @@ int reiserfs_get_block(struct inode *inode, sector_t block,
 	loff_t new_offset =
 	    (((loff_t) block) << inode->i_sb->s_blocksize_bits) + 1;
 
-	/* bad.... */
-	reiserfs_write_lock(inode->i_sb);
+	lock_depth = reiserfs_write_lock_once(inode->i_sb);
 	version = get_inode_item_key_version(inode);
 
 	if (!file_capable(inode, block)) {
-		reiserfs_write_unlock(inode->i_sb);
+		reiserfs_write_unlock_once(inode->i_sb, lock_depth);
 		return -EFBIG;
 	}
 
@@ -633,7 +630,7 @@ int reiserfs_get_block(struct inode *inode, sector_t block,
 		/* find number of block-th logical block of the file */
 		ret = _get_block_create_0(inode, block, bh_result,
 					  create | GET_BLOCK_READ_DIRECT);
-		reiserfs_write_unlock(inode->i_sb);
+		reiserfs_write_unlock_once(inode->i_sb, lock_depth);
 		return ret;
 	}
 	/*
@@ -751,7 +748,7 @@ int reiserfs_get_block(struct inode *inode, sector_t block,
 		if (!dangle && th)
 			retval = reiserfs_end_persistent_transaction(th);
 
-		reiserfs_write_unlock(inode->i_sb);
+		reiserfs_write_unlock_once(inode->i_sb, lock_depth);
 
 		/* the item was found, so new blocks were not added to the file
 		 ** there is no need to make sure the inode is updated with this
@@ -935,7 +932,7 @@ int reiserfs_get_block(struct inode *inode, sector_t block,
 			if (blocks_needed == 1) {
 				un = &unf_single;
 			} else {
-				un = kzalloc(min(blocks_needed, max_to_insert) * UNFM_P_SIZE, GFP_ATOMIC);	// We need to avoid scheduling.
+				un = kzalloc(min(blocks_needed, max_to_insert) * UNFM_P_SIZE, GFP_NOFS);
 				if (!un) {
 					un = &unf_single;
 					blocks_needed = 1;
@@ -997,10 +994,16 @@ int reiserfs_get_block(struct inode *inode, sector_t block,
 			if (retval)
 				goto failure;
 		}
-		/* inserting indirect pointers for a hole can take a
-		 ** long time.  reschedule if needed
+		/*
+		 * inserting indirect pointers for a hole can take a
+		 * long time.  reschedule if needed and also release the write
+		 * lock for others.
 		 */
-		cond_resched();
+		if (need_resched()) {
+			reiserfs_write_unlock_once(inode->i_sb, lock_depth);
+			schedule();
+			lock_depth = reiserfs_write_lock_once(inode->i_sb);
+		}
 
 		retval = search_for_position_by_key(inode->i_sb, &key, &path);
 		if (retval == IO_ERROR) {
@@ -1035,7 +1038,7 @@ int reiserfs_get_block(struct inode *inode, sector_t block,
 			retval = err;
 	}
 
-	reiserfs_write_unlock(inode->i_sb);
+	reiserfs_write_unlock_once(inode->i_sb, lock_depth);
 	reiserfs_check_path(&path);
 	return retval;
 }
@@ -2072,8 +2075,9 @@ int reiserfs_truncate_file(struct inode *inode, int update_timestamps)
 	int error;
 	struct buffer_head *bh = NULL;
 	int err2;
+	int lock_depth;
 
-	reiserfs_write_lock(inode->i_sb);
+	lock_depth = reiserfs_write_lock_once(inode->i_sb);
 
 	if (inode->i_size > 0) {
 		error = grab_tail_page(inode, &page, &bh);
@@ -2142,14 +2146,17 @@ int reiserfs_truncate_file(struct inode *inode, int update_timestamps)
 		page_cache_release(page);
 	}
 
-	reiserfs_write_unlock(inode->i_sb);
+	reiserfs_write_unlock_once(inode->i_sb, lock_depth);
+
 	return 0;
       out:
 	if (page) {
 		unlock_page(page);
 		page_cache_release(page);
 	}
-	reiserfs_write_unlock(inode->i_sb);
+
+	reiserfs_write_unlock_once(inode->i_sb, lock_depth);
+
 	return error;
 }
 
@@ -2608,7 +2615,10 @@ int reiserfs_prepare_write(struct file *f, struct page *page,
 	int ret;
 	int old_ref = 0;
 
+	reiserfs_write_unlock(inode->i_sb);
 	reiserfs_wait_on_write_block(inode->i_sb);
+	reiserfs_write_lock(inode->i_sb);
+
 	fix_tail_page_for_writing(page);
 	if (reiserfs_transaction_running(inode->i_sb)) {
 		struct reiserfs_transaction_handle *th;
@@ -2664,6 +2674,8 @@ static int reiserfs_write_end(struct file *file, struct address_space *mapping,
 	int update_sd = 0;
 	struct reiserfs_transaction_handle *th;
 	unsigned start;
+	int lock_depth = 0;
+	bool locked = false;
 
 	if ((unsigned long)fsdata & AOP_FLAG_CONT_EXPAND)
 		pos ++;
@@ -2690,9 +2702,11 @@ static int reiserfs_write_end(struct file *file, struct address_space *mapping,
 	 ** to do the i_size updates here.
 	 */
 	pos += copied;
+
 	if (pos > inode->i_size) {
 		struct reiserfs_transaction_handle myth;
-		reiserfs_write_lock(inode->i_sb);
+		lock_depth = reiserfs_write_lock_once(inode->i_sb);
+		locked = true;
 		/* If the file have grown beyond the border where it
 		   can have a tail, unmark it as needing a tail
 		   packing */
@@ -2703,10 +2717,9 @@ static int reiserfs_write_end(struct file *file, struct address_space *mapping,
 			REISERFS_I(inode)->i_flags &= ~i_pack_on_close_mask;
 
 		ret = journal_begin(&myth, inode->i_sb, 1);
-		if (ret) {
-			reiserfs_write_unlock(inode->i_sb);
+		if (ret)
 			goto journal_error;
-		}
+
 		reiserfs_update_inode_transaction(inode);
 		inode->i_size = pos;
 		/*
@@ -2718,34 +2731,36 @@ static int reiserfs_write_end(struct file *file, struct address_space *mapping,
 		reiserfs_update_sd(&myth, inode);
 		update_sd = 1;
 		ret = journal_end(&myth, inode->i_sb, 1);
-		reiserfs_write_unlock(inode->i_sb);
 		if (ret)
 			goto journal_error;
 	}
 	if (th) {
-		reiserfs_write_lock(inode->i_sb);
+		if (!locked) {
+			lock_depth = reiserfs_write_lock_once(inode->i_sb);
+			locked = true;
+		}
 		if (!update_sd)
 			mark_inode_dirty(inode);
 		ret = reiserfs_end_persistent_transaction(th);
-		reiserfs_write_unlock(inode->i_sb);
 		if (ret)
 			goto out;
 	}
 
       out:
+	if (locked)
+		reiserfs_write_unlock_once(inode->i_sb, lock_depth);
 	unlock_page(page);
 	page_cache_release(page);
 	return ret == 0 ? copied : ret;
 
       journal_error:
+	reiserfs_write_unlock_once(inode->i_sb, lock_depth);
+	locked = false;
 	if (th) {
-		reiserfs_write_lock(inode->i_sb);
 		if (!update_sd)
 			reiserfs_update_sd(th, inode);
 		ret = reiserfs_end_persistent_transaction(th);
-		reiserfs_write_unlock(inode->i_sb);
 	}
-
 	goto out;
 }
 
@@ -2758,7 +2773,10 @@ int reiserfs_commit_write(struct file *f, struct page *page,
 	int update_sd = 0;
 	struct reiserfs_transaction_handle *th = NULL;
 
+	reiserfs_write_unlock(inode->i_sb);
 	reiserfs_wait_on_write_block(inode->i_sb);
+	reiserfs_write_lock(inode->i_sb);
+
 	if (reiserfs_transaction_running(inode->i_sb)) {
 		th = current->journal_info;
 	}
@@ -2770,7 +2788,6 @@ int reiserfs_commit_write(struct file *f, struct page *page,
 	 */
 	if (pos > inode->i_size) {
 		struct reiserfs_transaction_handle myth;
-		reiserfs_write_lock(inode->i_sb);
 		/* If the file have grown beyond the border where it
 		   can have a tail, unmark it as needing a tail
 		   packing */
@@ -2781,10 +2798,9 @@ int reiserfs_commit_write(struct file *f, struct page *page,
 			REISERFS_I(inode)->i_flags &= ~i_pack_on_close_mask;
 
 		ret = journal_begin(&myth, inode->i_sb, 1);
-		if (ret) {
-			reiserfs_write_unlock(inode->i_sb);
+		if (ret)
 			goto journal_error;
-		}
+
 		reiserfs_update_inode_transaction(inode);
 		inode->i_size = pos;
 		/*
@@ -2796,16 +2812,13 @@ int reiserfs_commit_write(struct file *f, struct page *page,
 		reiserfs_update_sd(&myth, inode);
 		update_sd = 1;
 		ret = journal_end(&myth, inode->i_sb, 1);
-		reiserfs_write_unlock(inode->i_sb);
 		if (ret)
 			goto journal_error;
 	}
 	if (th) {
-		reiserfs_write_lock(inode->i_sb);
 		if (!update_sd)
 			mark_inode_dirty(inode);
 		ret = reiserfs_end_persistent_transaction(th);
-		reiserfs_write_unlock(inode->i_sb);
 		if (ret)
 			goto out;
 	}
@@ -2815,11 +2828,9 @@ int reiserfs_commit_write(struct file *f, struct page *page,
 
       journal_error:
 	if (th) {
-		reiserfs_write_lock(inode->i_sb);
 		if (!update_sd)
 			reiserfs_update_sd(th, inode);
 		ret = reiserfs_end_persistent_transaction(th);
-		reiserfs_write_unlock(inode->i_sb);
 	}
 
 	return ret;
diff --git a/fs/reiserfs/ioctl.c b/fs/reiserfs/ioctl.c
index 0ccc3fdda7b..ace77451ceb 100644
--- a/fs/reiserfs/ioctl.c
+++ b/fs/reiserfs/ioctl.c
@@ -13,44 +13,52 @@
 #include <linux/compat.h>
 
 /*
-** reiserfs_ioctl - handler for ioctl for inode
-** supported commands:
-**  1) REISERFS_IOC_UNPACK - try to unpack tail from direct item into indirect
-**                           and prevent packing file (argument arg has to be non-zero)
-**  2) REISERFS_IOC_[GS]ETFLAGS, REISERFS_IOC_[GS]ETVERSION
-**  3) That's all for a while ...
-*/
-int reiserfs_ioctl(struct inode *inode, struct file *filp, unsigned int cmd,
-		   unsigned long arg)
+ * reiserfs_ioctl - handler for ioctl for inode
+ * supported commands:
+ *  1) REISERFS_IOC_UNPACK - try to unpack tail from direct item into indirect
+ *                           and prevent packing file (argument arg has to be non-zero)
+ *  2) REISERFS_IOC_[GS]ETFLAGS, REISERFS_IOC_[GS]ETVERSION
+ *  3) That's all for a while ...
+ */
+long reiserfs_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
 {
+	struct inode *inode = filp->f_path.dentry->d_inode;
 	unsigned int flags;
 	int err = 0;
 
+	reiserfs_write_lock(inode->i_sb);
+
 	switch (cmd) {
 	case REISERFS_IOC_UNPACK:
 		if (S_ISREG(inode->i_mode)) {
 			if (arg)
-				return reiserfs_unpack(inode, filp);
-			else
-				return 0;
+				err = reiserfs_unpack(inode, filp);
 		} else
-			return -ENOTTY;
-		/* following two cases are taken from fs/ext2/ioctl.c by Remy
-		   Card (card@masi.ibp.fr) */
+			err = -ENOTTY;
+		break;
+		/*
+		 * following two cases are taken from fs/ext2/ioctl.c by Remy
+		 * Card (card@masi.ibp.fr)
+		 */
 	case REISERFS_IOC_GETFLAGS:
-		if (!reiserfs_attrs(inode->i_sb))
-			return -ENOTTY;
+		if (!reiserfs_attrs(inode->i_sb)) {
+			err = -ENOTTY;
+			break;
+		}
 
 		flags = REISERFS_I(inode)->i_attrs;
 		i_attrs_to_sd_attrs(inode, (__u16 *) & flags);
-		return put_user(flags, (int __user *)arg);
+		err = put_user(flags, (int __user *)arg);
+		break;
 	case REISERFS_IOC_SETFLAGS:{
-			if (!reiserfs_attrs(inode->i_sb))
-				return -ENOTTY;
+			if (!reiserfs_attrs(inode->i_sb)) {
+				err = -ENOTTY;
+				break;
+			}
 
 			err = mnt_want_write(filp->f_path.mnt);
 			if (err)
-				return err;
+				break;
 
 			if (!is_owner_or_cap(inode)) {
 				err = -EPERM;
@@ -90,16 +98,18 @@ int reiserfs_ioctl(struct inode *inode, struct file *filp, unsigned int cmd,
 			mark_inode_dirty(inode);
 setflags_out:
 			mnt_drop_write(filp->f_path.mnt);
-			return err;
+			break;
 		}
 	case REISERFS_IOC_GETVERSION:
-		return put_user(inode->i_generation, (int __user *)arg);
+		err = put_user(inode->i_generation, (int __user *)arg);
+		break;
 	case REISERFS_IOC_SETVERSION:
 		if (!is_owner_or_cap(inode))
-			return -EPERM;
+			err = -EPERM;
+			break;
 		err = mnt_want_write(filp->f_path.mnt);
 		if (err)
-			return err;
+			break;
 		if (get_user(inode->i_generation, (int __user *)arg)) {
 			err = -EFAULT;
 			goto setversion_out;
@@ -108,19 +118,20 @@ setflags_out:
 		mark_inode_dirty(inode);
 setversion_out:
 		mnt_drop_write(filp->f_path.mnt);
-		return err;
+		break;
 	default:
-		return -ENOTTY;
+		err = -ENOTTY;
 	}
+
+	reiserfs_write_unlock(inode->i_sb);
+
+	return err;
 }
 
 #ifdef CONFIG_COMPAT
 long reiserfs_compat_ioctl(struct file *file, unsigned int cmd,
 				unsigned long arg)
 {
-	struct inode *inode = file->f_path.dentry->d_inode;
-	int ret;
-
 	/* These are just misnamed, they actually get/put from/to user an int */
 	switch (cmd) {
 	case REISERFS_IOC32_UNPACK:
@@ -141,10 +152,8 @@ long reiserfs_compat_ioctl(struct file *file, unsigned int cmd,
 	default:
 		return -ENOIOCTLCMD;
 	}
-	lock_kernel();
-	ret = reiserfs_ioctl(inode, file, cmd, (unsigned long) compat_ptr(arg));
-	unlock_kernel();
-	return ret;
+
+	return reiserfs_ioctl(file, cmd, (unsigned long) compat_ptr(arg));
 }
 #endif
 
diff --git a/fs/reiserfs/journal.c b/fs/reiserfs/journal.c
index 90622200b39..2f8a7e7b8da 100644
--- a/fs/reiserfs/journal.c
+++ b/fs/reiserfs/journal.c
@@ -429,21 +429,6 @@ static void clear_prepared_bits(struct buffer_head *bh)
 	clear_buffer_journal_restore_dirty(bh);
 }
 
-/* utility function to force a BUG if it is called without the big
-** kernel lock held.  caller is the string printed just before calling BUG()
-*/
-void reiserfs_check_lock_depth(struct super_block *sb, char *caller)
-{
-#ifdef CONFIG_SMP
-	if (current->lock_depth < 0) {
-		reiserfs_panic(sb, "journal-1", "%s called without kernel "
-			       "lock held", caller);
-	}
-#else
-	;
-#endif
-}
-
 /* return a cnode with same dev, block number and size in table, or null if not found */
 static inline struct reiserfs_journal_cnode *get_journal_hash_dev(struct
 								  super_block
@@ -556,7 +541,8 @@ static inline void insert_journal_hash(struct reiserfs_journal_cnode **table,
 static inline void lock_journal(struct super_block *sb)
 {
 	PROC_INFO_INC(sb, journal.lock_journal);
-	mutex_lock(&SB_JOURNAL(sb)->j_mutex);
+
+	reiserfs_mutex_lock_safe(&SB_JOURNAL(sb)->j_mutex, sb);
 }
 
 /* unlock the current transaction */
@@ -708,7 +694,9 @@ static void check_barrier_completion(struct super_block *s,
 		disable_barrier(s);
 		set_buffer_uptodate(bh);
 		set_buffer_dirty(bh);
+		reiserfs_write_unlock(s);
 		sync_dirty_buffer(bh);
+		reiserfs_write_lock(s);
 	}
 }
 
@@ -996,8 +984,13 @@ static int reiserfs_async_progress_wait(struct super_block *s)
 {
 	DEFINE_WAIT(wait);
 	struct reiserfs_journal *j = SB_JOURNAL(s);
-	if (atomic_read(&j->j_async_throttle))
+
+	if (atomic_read(&j->j_async_throttle)) {
+		reiserfs_write_unlock(s);
 		congestion_wait(BLK_RW_ASYNC, HZ / 10);
+		reiserfs_write_lock(s);
+	}
+
 	return 0;
 }
 
@@ -1043,7 +1036,8 @@ static int flush_commit_list(struct super_block *s,
 	}
 
 	/* make sure nobody is trying to flush this one at the same time */
-	mutex_lock(&jl->j_commit_mutex);
+	reiserfs_mutex_lock_safe(&jl->j_commit_mutex, s);
+
 	if (!journal_list_still_alive(s, trans_id)) {
 		mutex_unlock(&jl->j_commit_mutex);
 		goto put_jl;
@@ -1061,12 +1055,17 @@ static int flush_commit_list(struct super_block *s,
 
 	if (!list_empty(&jl->j_bh_list)) {
 		int ret;
-		unlock_kernel();
+
+		/*
+		 * We might sleep in numerous places inside
+		 * write_ordered_buffers. Relax the write lock.
+		 */
+		reiserfs_write_unlock(s);
 		ret = write_ordered_buffers(&journal->j_dirty_buffers_lock,
 					    journal, jl, &jl->j_bh_list);
 		if (ret < 0 && retval == 0)
 			retval = ret;
-		lock_kernel();
+		reiserfs_write_lock(s);
 	}
 	BUG_ON(!list_empty(&jl->j_bh_list));
 	/*
@@ -1085,8 +1084,11 @@ static int flush_commit_list(struct super_block *s,
 		    SB_ONDISK_JOURNAL_SIZE(s);
 		tbh = journal_find_get_block(s, bn);
 		if (tbh) {
-			if (buffer_dirty(tbh))
-			    ll_rw_block(WRITE, 1, &tbh) ;
+			if (buffer_dirty(tbh)) {
+		            reiserfs_write_unlock(s);
+			    ll_rw_block(WRITE, 1, &tbh);
+			    reiserfs_write_lock(s);
+			}
 			put_bh(tbh) ;
 		}
 	}
@@ -1114,12 +1116,19 @@ static int flush_commit_list(struct super_block *s,
 		bn = SB_ONDISK_JOURNAL_1st_BLOCK(s) +
 		    (jl->j_start + i) % SB_ONDISK_JOURNAL_SIZE(s);
 		tbh = journal_find_get_block(s, bn);
+
+		reiserfs_write_unlock(s);
 		wait_on_buffer(tbh);
+		reiserfs_write_lock(s);
 		// since we're using ll_rw_blk above, it might have skipped over
 		// a locked buffer.  Double check here
 		//
-		if (buffer_dirty(tbh))	/* redundant, sync_dirty_buffer() checks */
+		/* redundant, sync_dirty_buffer() checks */
+		if (buffer_dirty(tbh)) {
+			reiserfs_write_unlock(s);
 			sync_dirty_buffer(tbh);
+			reiserfs_write_lock(s);
+		}
 		if (unlikely(!buffer_uptodate(tbh))) {
 #ifdef CONFIG_REISERFS_CHECK
 			reiserfs_warning(s, "journal-601",
@@ -1143,10 +1152,15 @@ static int flush_commit_list(struct super_block *s,
 			if (buffer_dirty(jl->j_commit_bh))
 				BUG();
 			mark_buffer_dirty(jl->j_commit_bh) ;
+			reiserfs_write_unlock(s);
 			sync_dirty_buffer(jl->j_commit_bh) ;
+			reiserfs_write_lock(s);
 		}
-	} else
+	} else {
+		reiserfs_write_unlock(s);
 		wait_on_buffer(jl->j_commit_bh);
+		reiserfs_write_lock(s);
+	}
 
 	check_barrier_completion(s, jl->j_commit_bh);
 
@@ -1286,7 +1300,9 @@ static int _update_journal_header_block(struct super_block *sb,
 
 	if (trans_id >= journal->j_last_flush_trans_id) {
 		if (buffer_locked((journal->j_header_bh))) {
+			reiserfs_write_unlock(sb);
 			wait_on_buffer((journal->j_header_bh));
+			reiserfs_write_lock(sb);
 			if (unlikely(!buffer_uptodate(journal->j_header_bh))) {
 #ifdef CONFIG_REISERFS_CHECK
 				reiserfs_warning(sb, "journal-699",
@@ -1312,12 +1328,16 @@ static int _update_journal_header_block(struct super_block *sb,
 				disable_barrier(sb);
 				goto sync;
 			}
+			reiserfs_write_unlock(sb);
 			wait_on_buffer(journal->j_header_bh);
+			reiserfs_write_lock(sb);
 			check_barrier_completion(sb, journal->j_header_bh);
 		} else {
 		      sync:
 			set_buffer_dirty(journal->j_header_bh);
+			reiserfs_write_unlock(sb);
 			sync_dirty_buffer(journal->j_header_bh);
+			reiserfs_write_lock(sb);
 		}
 		if (!buffer_uptodate(journal->j_header_bh)) {
 			reiserfs_warning(sb, "journal-837",
@@ -1409,7 +1429,7 @@ static int flush_journal_list(struct super_block *s,
 
 	/* if flushall == 0, the lock is already held */
 	if (flushall) {
-		mutex_lock(&journal->j_flush_mutex);
+		reiserfs_mutex_lock_safe(&journal->j_flush_mutex, s);
 	} else if (mutex_trylock(&journal->j_flush_mutex)) {
 		BUG();
 	}
@@ -1553,7 +1573,11 @@ static int flush_journal_list(struct super_block *s,
 					reiserfs_panic(s, "journal-1011",
 						       "cn->bh is NULL");
 				}
+
+				reiserfs_write_unlock(s);
 				wait_on_buffer(cn->bh);
+				reiserfs_write_lock(s);
+
 				if (!cn->bh) {
 					reiserfs_panic(s, "journal-1012",
 						       "cn->bh is NULL");
@@ -1769,7 +1793,7 @@ static int kupdate_transactions(struct super_block *s,
 	struct reiserfs_journal *journal = SB_JOURNAL(s);
 	chunk.nr = 0;
 
-	mutex_lock(&journal->j_flush_mutex);
+	reiserfs_mutex_lock_safe(&journal->j_flush_mutex, s);
 	if (!journal_list_still_alive(s, orig_trans_id)) {
 		goto done;
 	}
@@ -1973,11 +1997,19 @@ static int do_journal_release(struct reiserfs_transaction_handle *th,
 	reiserfs_mounted_fs_count--;
 	/* wait for all commits to finish */
 	cancel_delayed_work(&SB_JOURNAL(sb)->j_work);
+
+	/*
+	 * We must release the write lock here because
+	 * the workqueue job (flush_async_commit) needs this lock
+	 */
+	reiserfs_write_unlock(sb);
 	flush_workqueue(commit_wq);
+
 	if (!reiserfs_mounted_fs_count) {
 		destroy_workqueue(commit_wq);
 		commit_wq = NULL;
 	}
+	reiserfs_write_lock(sb);
 
 	free_journal_ram(sb);
 
@@ -2243,7 +2275,11 @@ static int journal_read_transaction(struct super_block *sb,
 	/* read in the log blocks, memcpy to the corresponding real block */
 	ll_rw_block(READ, get_desc_trans_len(desc), log_blocks);
 	for (i = 0; i < get_desc_trans_len(desc); i++) {
+
+		reiserfs_write_unlock(sb);
 		wait_on_buffer(log_blocks[i]);
+		reiserfs_write_lock(sb);
+
 		if (!buffer_uptodate(log_blocks[i])) {
 			reiserfs_warning(sb, "journal-1212",
 					 "REPLAY FAILURE fsck required! "
@@ -2765,11 +2801,27 @@ int journal_init(struct super_block *sb, const char *j_dev_name,
 		goto free_and_return;
 	}
 
+