Merge with /pub/scm/linux/kernel/git/torvalds/linux-2.6.git

Signed-off-by: Steve French <sfrench@us.ibm.com>

26 files changed, 337 insertions, 296 deletions

diff --git a/fs/Kconfig b/fs/Kconfig
index ef78e3a42d3..93b5dc4082f 100644
--- a/fs/Kconfig
+++ b/fs/Kconfig
@@ -1327,7 +1327,7 @@ config UFS_FS
 
 config UFS_FS_WRITE
 	bool "UFS file system write support (DANGEROUS)"
-	depends on UFS_FS && EXPERIMENTAL
+	depends on UFS_FS && EXPERIMENTAL && BROKEN
 	help
 	  Say Y here if you want to try writing to UFS partitions. This is
 	  experimental, so you should back up your UFS partitions beforehand.
diff --git a/fs/bio.c b/fs/bio.c
index bbc442b8c86..1f3bb501c26 100644
--- a/fs/bio.c
+++ b/fs/bio.c
@@ -411,6 +411,7 @@ static int __bio_add_page(request_queue_t *q, struct bio *bio, struct page
 
 /**
  *	bio_add_pc_page	-	attempt to add page to bio
+ *	@q: the target queue
  *	@bio: destination bio
  *	@page: page to add
  *	@len: vec entry length
diff --git a/fs/buffer.c b/fs/buffer.c
index 3dc712f29d2..5e4a90ee103 100644
--- a/fs/buffer.c
+++ b/fs/buffer.c
@@ -1022,6 +1022,7 @@ try_again:
 
 		bh->b_state = 0;
 		atomic_set(&bh->b_count, 0);
+		bh->b_private = NULL;
 		bh->b_size = size;
 
 		/* Link the buffer to its page */
@@ -3050,6 +3051,66 @@ asmlinkage long sys_bdflush(int func, long data)
 }
 
 /*
+ * Migration function for pages with buffers. This function can only be used
+ * if the underlying filesystem guarantees that no other references to "page"
+ * exist.
+ */
+#ifdef CONFIG_MIGRATION
+int buffer_migrate_page(struct page *newpage, struct page *page)
+{
+	struct address_space *mapping = page->mapping;
+	struct buffer_head *bh, *head;
+
+	if (!mapping)
+		return -EAGAIN;
+
+	if (!page_has_buffers(page))
+		return migrate_page(newpage, page);
+
+	head = page_buffers(page);
+
+	if (migrate_page_remove_references(newpage, page, 3))
+		return -EAGAIN;
+
+	bh = head;
+	do {
+		get_bh(bh);
+		lock_buffer(bh);
+		bh = bh->b_this_page;
+
+	} while (bh != head);
+
+	ClearPagePrivate(page);
+	set_page_private(newpage, page_private(page));
+	set_page_private(page, 0);
+	put_page(page);
+	get_page(newpage);
+
+	bh = head;
+	do {
+		set_bh_page(bh, newpage, bh_offset(bh));
+		bh = bh->b_this_page;
+
+	} while (bh != head);
+
+	SetPagePrivate(newpage);
+
+	migrate_page_copy(newpage, page);
+
+	bh = head;
+	do {
+		unlock_buffer(bh);
+ 		put_bh(bh);
+		bh = bh->b_this_page;
+
+	} while (bh != head);
+
+	return 0;
+}
+EXPORT_SYMBOL(buffer_migrate_page);
+#endif
+
+/*
  * Buffer-head allocation
  */
 static kmem_cache_t *bh_cachep;
diff --git a/fs/compat.c b/fs/compat.c
index ff0bafcff72..cc58a20df57 100644
--- a/fs/compat.c
+++ b/fs/compat.c
@@ -1781,7 +1781,7 @@ asmlinkage long compat_sys_pselect7(int n, compat_ulong_t __user *inp,
 {
 	compat_sigset_t ss32;
 	sigset_t ksigmask, sigsaved;
-	long timeout = MAX_SCHEDULE_TIMEOUT;
+	s64 timeout = MAX_SCHEDULE_TIMEOUT;
 	struct compat_timespec ts;
 	int ret;
 
diff --git a/fs/ext2/inode.c b/fs/ext2/inode.c
index e7d3f0522d0..a717837f272 100644
--- a/fs/ext2/inode.c
+++ b/fs/ext2/inode.c
@@ -706,6 +706,7 @@ struct address_space_operations ext2_aops = {
 	.bmap			= ext2_bmap,
 	.direct_IO		= ext2_direct_IO,
 	.writepages		= ext2_writepages,
+	.migratepage		= buffer_migrate_page,
 };
 
 struct address_space_operations ext2_aops_xip = {
@@ -723,6 +724,7 @@ struct address_space_operations ext2_nobh_aops = {
 	.bmap			= ext2_bmap,
 	.direct_IO		= ext2_direct_IO,
 	.writepages		= ext2_writepages,
+	.migratepage		= buffer_migrate_page,
 };
 
 /*
diff --git a/fs/ext3/inode.c b/fs/ext3/inode.c
index 8824e84f8a5..3fc4238e970 100644
--- a/fs/ext3/inode.c
+++ b/fs/ext3/inode.c
@@ -1559,6 +1559,7 @@ static struct address_space_operations ext3_ordered_aops = {
 	.invalidatepage	= ext3_invalidatepage,
 	.releasepage	= ext3_releasepage,
 	.direct_IO	= ext3_direct_IO,
+	.migratepage	= buffer_migrate_page,
 };
 
 static struct address_space_operations ext3_writeback_aops = {
@@ -1572,6 +1573,7 @@ static struct address_space_operations ext3_writeback_aops = {
 	.invalidatepage	= ext3_invalidatepage,
 	.releasepage	= ext3_releasepage,
 	.direct_IO	= ext3_direct_IO,
+	.migratepage	= buffer_migrate_page,
 };
 
 static struct address_space_operations ext3_journalled_aops = {
diff --git a/fs/fuse/file.c b/fs/fuse/file.c
index a7ef5e716f3..296351615b0 100644
--- a/fs/fuse/file.c
+++ b/fs/fuse/file.c
@@ -335,9 +335,14 @@ static void fuse_send_readpages(struct fuse_req *req, struct file *file,
 	loff_t pos = page_offset(req->pages[0]);
 	size_t count = req->num_pages << PAGE_CACHE_SHIFT;
 	req->out.page_zeroing = 1;
-	req->end = fuse_readpages_end;
 	fuse_read_fill(req, file, inode, pos, count, FUSE_READ);
-	request_send_background(fc, req);
+	if (fc->async_read) {
+		req->end = fuse_readpages_end;
+		request_send_background(fc, req);
+	} else {
+		request_send(fc, req);
+		fuse_readpages_end(fc, req);
+	}
 }
 
 struct fuse_readpages_data {
diff --git a/fs/fuse/fuse_i.h b/fs/fuse/fuse_i.h
index 46cf933aa3b..4a83adfec96 100644
--- a/fs/fuse/fuse_i.h
+++ b/fs/fuse/fuse_i.h
@@ -272,6 +272,9 @@ struct fuse_conn {
 	    reply, before any other request, and never cleared */
 	unsigned conn_error : 1;
 
+	/** Do readpages asynchronously?  Only set in INIT */
+	unsigned async_read : 1;
+
 	/*
 	 * The following bitfields are only for optimization purposes
 	 * and hence races in setting them will not cause malfunction
diff --git a/fs/fuse/inode.c b/fs/fuse/inode.c
index c755a0440a6..879e6fba948 100644
--- a/fs/fuse/inode.c
+++ b/fs/fuse/inode.c
@@ -473,6 +473,16 @@ static void process_init_reply(struct fuse_conn *fc, struct fuse_req *req)
 	if (req->out.h.error || arg->major != FUSE_KERNEL_VERSION)
 		fc->conn_error = 1;
 	else {
+		unsigned long ra_pages;
+
+		if (arg->minor >= 6) {
+			ra_pages = arg->max_readahead / PAGE_CACHE_SIZE;
+			if (arg->flags & FUSE_ASYNC_READ)
+				fc->async_read = 1;
+		} else
+			ra_pages = fc->max_read / PAGE_CACHE_SIZE;
+
+		fc->bdi.ra_pages = min(fc->bdi.ra_pages, ra_pages);
 		fc->minor = arg->minor;
 		fc->max_write = arg->minor < 5 ? 4096 : arg->max_write;
 	}
@@ -496,6 +506,8 @@ static void fuse_send_init(struct fuse_conn *fc)
 
 	arg->major = FUSE_KERNEL_VERSION;
 	arg->minor = FUSE_KERNEL_MINOR_VERSION;
+	arg->max_readahead = fc->bdi.ra_pages * PAGE_CACHE_SIZE;
+	arg->flags |= FUSE_ASYNC_READ;
 	req->in.h.opcode = FUSE_INIT;
 	req->in.numargs = 1;
 	req->in.args[0].size = sizeof(*arg);
@@ -552,8 +564,6 @@ static int fuse_fill_super(struct super_block *sb, void *data, int silent)
 	fc->user_id = d.user_id;
 	fc->group_id = d.group_id;
 	fc->max_read = d.max_read;
-	if (fc->max_read / PAGE_CACHE_SIZE < fc->bdi.ra_pages)
-		fc->bdi.ra_pages = fc->max_read / PAGE_CACHE_SIZE;
 
 	/* Used by get_root_inode() */
 	sb->s_fs_info = fc;
diff --git a/fs/hugetlbfs/inode.c b/fs/hugetlbfs/inode.c
index f568102da1e..b3519528994 100644
--- a/fs/hugetlbfs/inode.c
+++ b/fs/hugetlbfs/inode.c
@@ -72,8 +72,8 @@ huge_pages_needed(struct address_space *mapping, struct vm_area_struct *vma)
 	unsigned long start = vma->vm_start;
 	unsigned long end = vma->vm_end;
 	unsigned long hugepages = (end - start) >> HPAGE_SHIFT;
-	pgoff_t next = vma->vm_pgoff;
-	pgoff_t endpg = next + ((end - start) >> PAGE_SHIFT);
+	pgoff_t next = vma->vm_pgoff >> (HPAGE_SHIFT - PAGE_SHIFT);
+	pgoff_t endpg = next + hugepages;
 
 	pagevec_init(&pvec, 0);
 	while (next < endpg) {
diff --git a/fs/inode.c b/fs/inode.c
index 108138d4e90..d0be6159eb7 100644
--- a/fs/inode.c
+++ b/fs/inode.c
@@ -1179,7 +1179,7 @@ EXPORT_SYMBOL(bmap);
 /**
  *	touch_atime	-	update the access time
  *	@mnt: mount the inode is accessed on
- *	@inode: inode accessed
+ *	@dentry: dentry accessed
  *
  *	Update the accessed time on an inode and mark it for writeback.
  *	This function automatically handles read only file systems and media,
diff --git a/fs/namei.c b/fs/namei.c
index 4acdac043b6..7ac9fb4acb2 100644
--- a/fs/namei.c
+++ b/fs/namei.c
@@ -1161,6 +1161,7 @@ static int __path_lookup_intent_open(int dfd, const char *name,
 
 /**
  * path_lookup_open - lookup a file path with open intent
+ * @dfd: the directory to use as base, or AT_FDCWD
  * @name: pointer to file name
  * @lookup_flags: lookup intent flags
  * @nd: pointer to nameidata
@@ -1175,6 +1176,7 @@ int path_lookup_open(int dfd, const char *name, unsigned int lookup_flags,
 
 /**
  * path_lookup_create - lookup a file path with open + create intent
+ * @dfd: the directory to use as base, or AT_FDCWD
  * @name: pointer to file name
  * @lookup_flags: lookup intent flags
  * @nd: pointer to nameidata
diff --git a/fs/nfsd/nfssvc.c b/fs/nfsd/nfssvc.c
index 89ed0469686..1d163b61691 100644
--- a/fs/nfsd/nfssvc.c
+++ b/fs/nfsd/nfssvc.c
@@ -64,6 +64,32 @@ struct nfsd_list {
 };
 static struct list_head nfsd_list = LIST_HEAD_INIT(nfsd_list);
 
+#if defined(CONFIG_NFSD_V2_ACL) || defined(CONFIG_NFSD_V3_ACL)
+static struct svc_stat	nfsd_acl_svcstats;
+static struct svc_version *	nfsd_acl_version[] = {
+	[2] = &nfsd_acl_version2,
+	[3] = &nfsd_acl_version3,
+};
+
+#define NFSD_ACL_MINVERS            2
+#define NFSD_ACL_NRVERS		(sizeof(nfsd_acl_version)/sizeof(nfsd_acl_version[0]))
+static struct svc_version *nfsd_acl_versions[NFSD_ACL_NRVERS];
+
+static struct svc_program	nfsd_acl_program = {
+	.pg_prog		= NFS_ACL_PROGRAM,
+	.pg_nvers		= NFSD_ACL_NRVERS,
+	.pg_vers		= nfsd_acl_versions,
+	.pg_name		= "nfsd",
+	.pg_class		= "nfsd",
+	.pg_stats		= &nfsd_acl_svcstats,
+	.pg_authenticate	= &svc_set_client,
+};
+
+static struct svc_stat	nfsd_acl_svcstats = {
+	.program	= &nfsd_acl_program,
+};
+#endif /* defined(CONFIG_NFSD_V2_ACL) || defined(CONFIG_NFSD_V3_ACL) */
+
 static struct svc_version *	nfsd_version[] = {
 	[2] = &nfsd_version2,
 #if defined(CONFIG_NFSD_V3)
@@ -79,6 +105,9 @@ static struct svc_version *	nfsd_version[] = {
 static struct svc_version *nfsd_versions[NFSD_NRVERS];
 
 struct svc_program		nfsd_program = {
+#if defined(CONFIG_NFSD_V2_ACL) || defined(CONFIG_NFSD_V3_ACL)
+	.pg_next		= &nfsd_acl_program,
+#endif
 	.pg_prog		= NFS_PROGRAM,		/* program number */
 	.pg_nvers		= NFSD_NRVERS,		/* nr of entries in nfsd_version */
 	.pg_vers		= nfsd_versions,	/* version table */
@@ -147,6 +176,26 @@ nfsd_svc(unsigned short port, int nrservs)
 				nfsd_program.pg_vers[i] = nfsd_version[i];
 		}
 
+
+#if defined(CONFIG_NFSD_V2_ACL) || defined(CONFIG_NFSD_V3_ACL)
+		found_one = 0;
+
+		for (i = NFSD_ACL_MINVERS; i < NFSD_ACL_NRVERS; i++) {
+			if (NFSCTL_VERISSET(nfsd_versbits, i)) {
+				nfsd_acl_program.pg_vers[i] =
+					nfsd_acl_version[i];
+				found_one = 1;
+			} else
+				nfsd_acl_program.pg_vers[i] = NULL;
+		}
+
+		if (!found_one) {
+			for (i = NFSD_ACL_MINVERS; i < NFSD_ACL_NRVERS; i++)
+				nfsd_acl_program.pg_vers[i] =
+					nfsd_acl_version[i];
+		}
+#endif
+
 		atomic_set(&nfsd_busy, 0);
 		error = -ENOMEM;
 		nfsd_serv = svc_create(&nfsd_program, NFSD_BUFSIZE);
@@ -411,30 +460,3 @@ nfsd_dispatch(struct svc_rqst *rqstp, u32 *statp)
 	nfsd_cache_update(rqstp, proc->pc_cachetype, statp + 1);
 	return 1;
 }
-
-#if defined(CONFIG_NFSD_V2_ACL) || defined(CONFIG_NFSD_V3_ACL)
-static struct svc_stat	nfsd_acl_svcstats;
-static struct svc_version *	nfsd_acl_version[] = {
-	[2] = &nfsd_acl_version2,
-	[3] = &nfsd_acl_version3,
-};
-
-#define NFSD_ACL_NRVERS		(sizeof(nfsd_acl_version)/sizeof(nfsd_acl_version[0]))
-static struct svc_program	nfsd_acl_program = {
-	.pg_prog		= NFS_ACL_PROGRAM,
-	.pg_nvers		= NFSD_ACL_NRVERS,
-	.pg_vers		= nfsd_acl_version,
-	.pg_name		= "nfsd",
-	.pg_class		= "nfsd",
-	.pg_stats		= &nfsd_acl_svcstats,
-	.pg_authenticate	= &svc_set_client,
-};
-
-static struct svc_stat	nfsd_acl_svcstats = {
-	.program	= &nfsd_acl_program,
-};
-
-#define nfsd_acl_program_p	&nfsd_acl_program
-#else
-#define nfsd_acl_program_p	NULL
-#endif /* defined(CONFIG_NFSD_V2_ACL) || defined(CONFIG_NFSD_V3_ACL) */
diff --git a/fs/reiserfs/dir.c b/fs/reiserfs/dir.c
index 9dd71e80703..d71ac657928 100644
--- a/fs/reiserfs/dir.c
+++ b/fs/reiserfs/dir.c
@@ -150,18 +150,15 @@ static int reiserfs_readdir(struct file *filp, void *dirent, filldir_t filldir)
 				if (d_reclen <= 32) {
 					local_buf = small_buf;
 				} else {
-					local_buf =
-					    reiserfs_kmalloc(d_reclen, GFP_NOFS,
-							     inode->i_sb);
+					local_buf = kmalloc(d_reclen,
+							    GFP_NOFS);
 					if (!local_buf) {
 						pathrelse(&path_to_entry);
 						ret = -ENOMEM;
 						goto out;
 					}
 					if (item_moved(&tmp_ih, &path_to_entry)) {
-						reiserfs_kfree(local_buf,
-							       d_reclen,
-							       inode->i_sb);
+						kfree(local_buf);
 						goto research;
 					}
 				}
@@ -174,15 +171,12 @@ static int reiserfs_readdir(struct file *filp, void *dirent, filldir_t filldir)
 				    (dirent, local_buf, d_reclen, d_off, d_ino,
 				     DT_UNKNOWN) < 0) {
 					if (local_buf != small_buf) {
-						reiserfs_kfree(local_buf,
-							       d_reclen,
-							       inode->i_sb);
+						kfree(local_buf);
 					}
 					goto end;
 				}
 				if (local_buf != small_buf) {
-					reiserfs_kfree(local_buf, d_reclen,
-						       inode->i_sb);
+					kfree(local_buf);
 				}
 				// next entry should be looked for with such offset
 				next_pos = deh_offset(deh) + 1;
diff --git a/fs/reiserfs/file.c b/fs/reiserfs/file.c
index ad6fa964b0e..f3473176c83 100644
--- a/fs/reiserfs/file.c
+++ b/fs/reiserfs/file.c
@@ -192,6 +192,8 @@ static int reiserfs_allocate_blocks_for_region(struct reiserfs_transaction_handl
 
 	allocated_blocks = kmalloc((blocks_to_allocate + will_prealloc) *
 				   sizeof(b_blocknr_t), GFP_NOFS);
+	if (!allocated_blocks)
+		return -ENOMEM;
 
 	/* First we compose a key to point at the writing position, we want to do
 	   that outside of any locking region. */
@@ -1285,6 +1287,23 @@ static ssize_t reiserfs_file_write(struct file *file,	/* the file we are going t
 	struct reiserfs_transaction_handle th;
 	th.t_trans_id = 0;
 
+	/* If a filesystem is converted from 3.5 to 3.6, we'll have v3.5 items
+	* lying around (most of the disk, in fact). Despite the filesystem
+	* now being a v3.6 format, the old items still can't support large
+	* file sizes. Catch this case here, as the rest of the VFS layer is
+	* oblivious to the different limitations between old and new items.
+	* reiserfs_setattr catches this for truncates. This chunk is lifted
+	* from generic_write_checks. */
+	if (get_inode_item_key_version (inode) == KEY_FORMAT_3_5 &&
+	    *ppos + count > MAX_NON_LFS) {
+		if (*ppos >= MAX_NON_LFS) {
+			send_sig(SIGXFSZ, current, 0);
+			return -EFBIG;
+		}
+		if (count > MAX_NON_LFS - (unsigned long)*ppos)
+			count = MAX_NON_LFS - (unsigned long)*ppos;
+	}
+
 	if (file->f_flags & O_DIRECT) {	// Direct IO needs treatment
 		ssize_t result, after_file_end = 0;
 		if ((*ppos + count >= inode->i_size)
diff --git a/fs/reiserfs/fix_node.c b/fs/reiserfs/fix_node.c
index 45829889dcd..aa22588019e 100644
--- a/fs/reiserfs/fix_node.c
+++ b/fs/reiserfs/fix_node.c
@@ -2021,38 +2021,6 @@ static int get_neighbors(struct tree_balance *p_s_tb, int n_h)
 	return CARRY_ON;
 }
 
-#ifdef CONFIG_REISERFS_CHECK
-void *reiserfs_kmalloc(size_t size, gfp_t flags, struct super_block *s)
-{
-	void *vp;
-	static size_t malloced;
-
-	vp = kmalloc(size, flags);
-	if (vp) {
-		REISERFS_SB(s)->s_kmallocs += size;
-		if (REISERFS_SB(s)->s_kmallocs > malloced + 200000) {
-			reiserfs_warning(s,
-					 "vs-8301: reiserfs_kmalloc: allocated memory %d",
-					 REISERFS_SB(s)->s_kmallocs);
-			malloced = REISERFS_SB(s)->s_kmallocs;
-		}
-	}
-	return vp;
-}
-
-void reiserfs_kfree(const void *vp, size_t size, struct super_block *s)
-{
-	kfree(vp);
-
-	REISERFS_SB(s)->s_kmallocs -= size;
-	if (REISERFS_SB(s)->s_kmallocs < 0)
-		reiserfs_warning(s,
-				 "vs-8302: reiserfs_kfree: allocated memory %d",
-				 REISERFS_SB(s)->s_kmallocs);
-
-}
-#endif
-
 static int get_virtual_node_size(struct super_block *sb, struct buffer_head *bh)
 {
 	int max_num_of_items;
@@ -2086,7 +2054,7 @@ static int get_mem_for_virtual_node(struct tree_balance *tb)
 		/* we have to allocate more memory for virtual node */
 		if (tb->vn_buf) {
 			/* free memory allocated before */
-			reiserfs_kfree(tb->vn_buf, tb->vn_buf_size, tb->tb_sb);
+			kfree(tb->vn_buf);
 			/* this is not needed if kfree is atomic */
 			check_fs = 1;
 		}
@@ -2095,24 +2063,15 @@ static int get_mem_for_virtual_node(struct tree_balance *tb)
 		tb->vn_buf_size = size;
 
 		/* get memory for virtual item */
-		buf =
-		    reiserfs_kmalloc(size, GFP_ATOMIC | __GFP_NOWARN,
-				     tb->tb_sb);
+		buf = kmalloc(size, GFP_ATOMIC | __GFP_NOWARN);
 		if (!buf) {
 			/* getting memory with GFP_KERNEL priority may involve
 			   balancing now (due to indirect_to_direct conversion on
 			   dcache shrinking). So, release path and collected
 			   resources here */
 			free_buffers_in_tb(tb);
-			buf = reiserfs_kmalloc(size, GFP_NOFS, tb->tb_sb);
+			buf = kmalloc(size, GFP_NOFS);
 			if (!buf) {
-#ifdef CONFIG_REISERFS_CHECK
-				reiserfs_warning(tb->tb_sb,
-						 "vs-8345: get_mem_for_virtual_node: "
-						 "kmalloc failed. reiserfs kmalloced %d bytes",
-						 REISERFS_SB(tb->tb_sb)->
-						 s_kmallocs);
-#endif
 				tb->vn_buf_size = 0;
 			}
 			tb->vn_buf = buf;
@@ -2619,7 +2578,6 @@ void unfix_nodes(struct tree_balance *tb)
 		}
 	}
 
-	if (tb->vn_buf)
-		reiserfs_kfree(tb->vn_buf, tb->vn_buf_size, tb->tb_sb);
+	kfree(tb->vn_buf);
 
 }
diff --git a/fs/reiserfs/inode.c b/fs/reiserfs/inode.c
index ffa34b861bd..b33d67bba2f 100644
--- a/fs/reiserfs/inode.c
+++ b/fs/reiserfs/inode.c
@@ -2363,6 +2363,13 @@ static int reiserfs_write_full_page(struct page *page,
 	int bh_per_page = PAGE_CACHE_SIZE / s->s_blocksize;
 	th.t_trans_id = 0;
 
+	/* no logging allowed when nonblocking or from PF_MEMALLOC */
+	if (checked && (current->flags & PF_MEMALLOC)) {
+		redirty_page_for_writepage(wbc, page);
+		unlock_page(page);
+		return 0;
+	}
+
 	/* The page dirty bit is cleared before writepage is called, which
 	 * means we have to tell create_empty_buffers to make dirty buffers
 	 * The page really should be up to date at this point, so tossing
@@ -2743,6 +2750,7 @@ static int invalidatepage_can_drop(struct inode *inode, struct buffer_head *bh)
 	int ret = 1;
 	struct reiserfs_journal *j = SB_JOURNAL(inode->i_sb);
 
+	lock_buffer(bh);
 	spin_lock(&j->j_dirty_buffers_lock);
 	if (!buffer_mapped(bh)) {
 		goto free_jh;
@@ -2758,7 +2766,7 @@ static int invalidatepage_can_drop(struct inode *inode, struct buffer_head *bh)
 		if (buffer_journaled(bh) || buffer_journal_dirty(bh)) {
 			ret = 0;
 		}
-	} else if (buffer_dirty(bh) || buffer_locked(bh)) {
+	} else  if (buffer_dirty(bh)) {
 		struct reiserfs_journal_list *jl;
 		struct reiserfs_jh *jh = bh->b_private;
 
@@ -2784,6 +2792,7 @@ static int invalidatepage_can_drop(struct inode *inode, struct buffer_head *bh)
 		reiserfs_free_jh(bh);
 	}
 	spin_unlock(&j->j_dirty_buffers_lock);
+	unlock_buffer(bh);
 	return ret;
 }
 
diff --git a/fs/reiserfs/journal.c b/fs/reiserfs/journal.c
index 4491fcf2a0e..b7a179560ab 100644
--- a/fs/reiserfs/journal.c
+++ b/fs/reiserfs/journal.c
@@ -152,18 +152,16 @@ static struct reiserfs_bitmap_node *allocate_bitmap_node(struct super_block
 	struct reiserfs_bitmap_node *bn;
 	static int id;
 
-	bn = reiserfs_kmalloc(sizeof(struct reiserfs_bitmap_node), GFP_NOFS,
-			      p_s_sb);
+	bn = kmalloc(sizeof(struct reiserfs_bitmap_node), GFP_NOFS);
 	if (!bn) {
 		return NULL;
 	}
-	bn->data = reiserfs_kmalloc(p_s_sb->s_blocksize, GFP_NOFS, p_s_sb);
+	bn->data = kzalloc(p_s_sb->s_blocksize, GFP_NOFS);
 	if (!bn->data) {
-		reiserfs_kfree(bn, sizeof(struct reiserfs_bitmap_node), p_s_sb);
+		kfree(bn);
 		return NULL;
 	}
 	bn->id = id++;
-	memset(bn->data, 0, p_s_sb->s_blocksize);
 	INIT_LIST_HEAD(&bn->list);
 	return bn;
 }
@@ -197,8 +195,8 @@ static inline void free_bitmap_node(struct super_block *p_s_sb,
 	struct reiserfs_journal *journal = SB_JOURNAL(p_s_sb);
 	journal->j_used_bitmap_nodes--;
 	if (journal->j_free_bitmap_nodes > REISERFS_MAX_BITMAP_NODES) {
-		reiserfs_kfree(bn->data, p_s_sb->s_blocksize, p_s_sb);
-		reiserfs_kfree(bn, sizeof(struct reiserfs_bitmap_node), p_s_sb);
+		kfree(bn->data);
+		kfree(bn);
 	} else {
 		list_add(&bn->list, &journal->j_bitmap_nodes);
 		journal->j_free_bitmap_nodes++;
@@ -276,8 +274,8 @@ static int free_bitmap_nodes(struct super_block *p_s_sb)
 	while (next != &journal->j_bitmap_nodes) {
 		bn = list_entry(next, struct reiserfs_bitmap_node, list);
 		list_del(next);
-		reiserfs_kfree(bn->data, p_s_sb->s_blocksize, p_s_sb);
-		reiserfs_kfree(bn, sizeof(struct reiserfs_bitmap_node), p_s_sb);
+		kfree(bn->data);
+		kfree(bn);
 		next = journal->j_bitmap_nodes.next;
 		journal->j_free_bitmap_nodes--;
 	}
@@ -581,7 +579,7 @@ static inline void put_journal_list(struct super_block *s,
 			       jl->j_trans_id, jl->j_refcount);
 	}
 	if (--jl->j_refcount == 0)
-		reiserfs_kfree(jl, sizeof(struct reiserfs_journal_list), s);
+		kfree(jl);
 }
 
 /*
@@ -848,6 +846,14 @@ static int write_ordered_buffers(spinlock_t * lock,
 			spin_lock(lock);
 			goto loop_next;
 		}
+		/* in theory, dirty non-uptodate buffers should never get here,
+		 * but the upper layer io error paths still have a few quirks.
+		 * Handle them here as gracefully as we can
+		 */
+		if (!buffer_uptodate(bh) && buffer_dirty(bh)) {
+			clear_buffer_dirty(bh);
+			ret = -EIO;
+		}
 		if (buffer_dirty(bh)) {
 			list_del_init(&jh->list);
 			list_add(&jh->list, &tmp);
@@ -879,6 +885,19 @@ static int write_ordered_buffers(spinlock_t * lock,
 		if (!buffer_uptodate(bh)) {
 			ret = -EIO;
 		}
+		/* ugly interaction with invalidatepage here.
+		 * reiserfs_invalidate_page will pin any buffer that has a valid
+		 * journal head from an older transaction.  If someone else sets
+		 * our buffer dirty after we write it in the first loop, and
+		 * then someone truncates the page away, nobody will ever write
+		 * the buffer. We're safe if we write the page one last time
+		 * after freeing the journal header.
+		 */
+		if (buffer_dirty(bh) && unlikely(bh->b_page->mapping == NULL)) {
+			spin_unlock(lock);
+			ll_rw_block(WRITE, 1, &bh);
+			spin_lock(lock);
+		}
 		put_bh(bh);
 		cond_resched_lock(lock);
 	}
@@ -977,6 +996,7 @@ static int flush_commit_list(struct super_block *s,
 	struct reiserfs_journal *journal = SB_JOURNAL(s);
 	int barrier = 0;
 	int retval = 0;
+	int write_len;
 
 	reiserfs_check_lock_depth(s, "flush_commit_list");
 
@@ -1018,24 +1038,35 @@ static int flush_commit_list(struct super_block *s,
 	}
 
 	if (!list_empty(&jl->j_bh_list)) {
+		int ret;
 		unlock_kernel();
-		write_ordered_buffers(&journal->j_dirty_buffers_lock,
-				      journal, jl, &jl->j_bh_list);
+		ret = write_ordered_buffers(&journal->j_dirty_buffers_lock,
+					    journal, jl, &jl->j_bh_list);
+		if (ret < 0 && retval == 0)
+			retval = ret;
 		lock_kernel();
 	}
 	BUG_ON(!list_empty(&jl->j_bh_list));
 	/*
 	 * for the description block and all the log blocks, submit any buffers
-	 * that haven't already reached the disk
+	 * that haven't already reached the disk.  Try to write at least 256
+	 * log blocks. later on, we will only wait on blocks that correspond
+	 * to this transaction, but while we're unplugging we might as well
+	 * get a chunk of data on there.
 	 */
 	atomic_inc(&journal->j_async_throttle);
-	for (i = 0; i < (jl->j_len + 1); i++) {
+	write_len = jl->j_len + 1;
+	if (write_len < 256)
+		write_len = 256;
+	for (i = 0 ; i < write_len ; i++) {
 		bn = SB_ONDISK_JOURNAL_1st_BLOCK(s) + (jl->j_start + i) %
 		    SB_ONDISK_JOURNAL_SIZE(s);
 		tbh = journal_find_get_block(s, bn);
-		if (buffer_dirty(tbh))	/* redundant, ll_rw_block() checks */
-			ll_rw_block(SWRITE, 1, &tbh);
-		put_bh(tbh);
+		if (tbh) {
+			if (buffer_dirty(tbh))
+			    ll_rw_block(WRITE, 1, &tbh) ;
+			put_bh(tbh) ;
+		}
 	}
 	atomic_dec(&journal->j_async_throttle);
 
@@ -1818,8 +1849,7 @@ void remove_journal_hash(struct super_block *sb,
 static void free_journal_ram(struct super_block *p_s_sb)
 {
 	struct reiserfs_journal *journal = SB_JOURNAL(p_s_sb);
-	reiserfs_kfree(journal->j_current_jl,
-		       sizeof(struct reiserfs_journal_list), p_s_sb);
+	kfree(journal->j_current_jl);
 	journal->j_num_lists--;
 
 	vfree(journal->j_cnode_free_orig);
@@ -2093,21 +2123,15 @@ static int journal_read_transaction(struct super_block *p_s_sb,
 	}
 	trans_id = get_desc_trans_id(desc);
 	/* now we know we've got a good transaction, and it was inside the valid time ranges */
-	log_blocks =
-	    reiserfs_kmalloc(get_desc_trans_len(desc) *
-			     sizeof(struct buffer_head *), GFP_NOFS, p_s_sb);
-	real_blocks =
-	    reiserfs_kmalloc(get_desc_trans_len(desc) *
-			     sizeof(struct buffer_head *), GFP_NOFS, p_s_sb);
+	log_blocks = kmalloc(get_desc_trans_len(desc) *
+			     sizeof(struct buffer_head *), GFP_NOFS);
+	real_blocks = kmalloc(get_desc_trans_len(desc) *
+			      sizeof(struct buffer_head *), GFP_NOFS);
 	if (!log_blocks || !real_blocks) {
 		brelse(c_bh);
 		brelse(d_bh);
-		reiserfs_kfree(log_blocks,
-			       get_desc_trans_len(desc) *
-			       sizeof(struct buffer_head *), p_s_sb);
-		reiserfs_kfree(real_blocks,
-			       get_desc_trans_len(desc) *
-			       sizeof(struct buffer_head *), p_s_sb);
+		kfree(log_blocks);
+		kfree(real_blocks);
 		reiserfs_warning(p_s_sb,
 				 "journal-1169: kmalloc failed, unable to mount FS");
 		return -1;
@@ -2145,12 +2169,8 @@ static int journal_read_transaction(struct super_block *p_s_sb,
 			brelse_array(real_blocks, i);
 			brelse(c_bh);
 			brelse(d_bh);
-			reiserfs_kfree(log_blocks,
-				       get_desc_trans_len(desc) *
-				       sizeof(struct buffer_head *), p_s_sb);
-			reiserfs_kfree(real_blocks,
-				       get_desc_trans_len(desc) *
-				       sizeof(struct buffer_head *), p_s_sb);
+			kfree(log_blocks);
+			kfree(real_blocks);
 			return -1;
 		}
 	}
@@ -2166,12 +2186,8 @@ static int journal_read_transaction(struct super_block *p_s_sb,
 			brelse_array(real_blocks, get_desc_trans_len(desc));
 			brelse(c_bh);
 			brelse(d_bh);
-			reiserfs_kfree(log_blocks,
-				       get_desc_trans_len(desc) *
-				       sizeof(struct buffer_head *), p_s_sb);
-			reiserfs_kfree(real_blocks,
-				       get_desc_trans_len(desc) *
-				       sizeof(struct buffer_head *), p_s_sb);
+			kfree(log_blocks);
+			kfree(real_blocks);
 			return -1;
 		}
 		memcpy(real_blocks[i]->b_data, log_blocks[i]->b_data,
@@ -2193,12 +2209,8 @@ static int journal_read_transaction(struct super_block *p_s_sb,
 				     get_desc_trans_len(desc) - i);
 			brelse(c_bh);
 			brelse(d_bh);
-			reiserfs_kfree(log_blocks,
-				       get_desc_trans_len(desc) *
-				       sizeof(struct buffer_head *), p_s_sb);
-			reiserfs_kfree(real_blocks,
-				       get_desc_trans_len(desc) *
-				       sizeof(struct buffer_head *), p_s_sb);
+			kfree(log_blocks);
+			kfree(real_blocks);
 			return -1;
 		}
 		brelse(real_blocks[i]);
@@ -2217,12 +2229,8 @@ static int journal_read_transaction(struct super_block *p_s_sb,
 	journal->j_trans_id = trans_id + 1;
 	brelse(c_bh);
 	brelse(d_bh);
-	reiserfs_kfree(log_blocks,
-		       le32_to_cpu(desc->j_len) * sizeof(struct buffer_head *),
-		       p_s_sb);
-	reiserfs_kfree(real_blocks,
-		       le32_to_cpu(desc->j_len) * sizeof(struct buffer_head *),
-		       p_s_sb);
+	kfree(log_blocks);
+	kfree(real_blocks);
 	return 0;
 }
 
@@ -2471,14 +2479,8 @@ static int journal_read(struct super_block *p_s_sb)
 static struct reiserfs_journal_list *alloc_journal_list(struct super_block *s)
 {
 	struct reiserfs_journal_list *jl;
-      retry:
-	jl = reiserfs_kmalloc(sizeof(struct reiserfs_journal_list), GFP_NOFS,
-			      s);
-	if (!jl) {
-		yield();
-		goto retry;
-	}
-	memset(jl, 0, sizeof(*jl));
+	jl = kzalloc(sizeof(struct reiserfs_journal_list),
+		     GFP_NOFS | __GFP_NOFAIL);
 	INIT_LIST_HEAD(&jl->j_list);
 	INIT_LIST_HEAD(&jl->j_working_list);
 	INIT_LIST_HEAD(&jl->j_tail_bh_list);
@@ -2821,6 +2823,9 @@ int journal_transaction_should_end(struct reiserfs_transaction_handle *th,
 	    journal->j_cnode_free < (journal->j_trans_max * 3)) {
 		return 1;
 	}
+	/* protected by the BKL here */
+	journal->j_len_alloc += new_alloc;
+	th->t_blocks_allocated += new_alloc ;
 	return 0;
 }
 
@@ -3042,14 +3047,12 @@ struct reiserfs_transaction_handle *reiserfs_persistent_transaction(struct
 		}
 		return th;
 	}
-	th = reiserfs_kmalloc(sizeof(struct reiserfs_transaction_handle),
-			      GFP_NOFS, s);
+	th = kmalloc(sizeof(struct reiserfs_transaction_handle), GFP_NOFS);
 	if (!th)
 		return NULL;
 	ret = journal_begin(th, s, nblocks);
 	if (ret) {
-		reiserfs_kfree(th, sizeof(struct reiserfs_transaction_handle),
-			       s);
+		kfree(th);
 		return NULL;
 	}
 
@@ -3067,8 +3070,7 @@ int reiserfs_end_persistent_transaction(struct reiserfs_transaction_handle *th)
 		ret = -EIO;
 	if (th->t_refcount == 0) {
 		SB_JOURNAL(s)->j_persistent_trans--;
-		reiserfs_kfree(th, sizeof(struct reiserfs_transaction_handle),
-			       s);
+		kfree(th);
 	}
 	return ret;
 }
diff --git a/fs/reiserfs/namei.c b/fs/reiserfs/namei.c
index 8f8d8d01107..c8123308e06 100644
--- a/fs/reiserfs/namei.c
+++ b/fs/reiserfs/namei.c
@@ -456,7 +456,7 @@ static int reiserfs_add_entry(struct reiserfs_transaction_handle *th,
 	/* get memory for composing the entry */
 	buflen = DEH_SIZE + ROUND_UP(namelen);
 	if (buflen > sizeof(small_buf)) {
-		buffer = reiserfs_kmalloc(buflen, GFP_NOFS, dir->i_sb);
+		buffer = kmalloc(buflen, GFP_NOFS);
 		if (buffer == 0)
 			return -ENOMEM;
 	} else
@@ -490,7 +490,7 @@ static int reiserfs_add_entry(struct reiserfs_transaction_handle *th,
 	retval = reiserfs_find_entry(dir, name, namelen, &path, &de);
 	if (retval != NAME_NOT_FOUND) {
 		if (buffer != small_buf)
-			reiserfs_kfree(buffer, buflen, dir->i_sb);
+			kfree(buffer);
 		pathrelse(&path);
 
 		if (retval == IO_ERROR) {
@@ -515,7 +515,7 @@ static int reiserfs_add_entry(struct reiserfs_transaction_handle *th,
 		reiserfs_warning(dir->i_sb,
 				 "reiserfs_add_entry: Congratulations! we have got hash function screwed up");
 		if (buffer != small_buf)
-			reiserfs_kfree(buffer, buflen, dir->i_sb);
+			kfree(buffer);
 		pathrelse(&path);
 		return -EBUSY;
 	}
@@ -535,7 +535,7 @@ static int reiserfs_add_entry(struct reiserfs_transaction_handle *th,
 					 &entry_key);
 
 			if (buffer != small_buf)
-				reiserfs_kfree(buffer, buflen, dir->i_sb);
+				kfree(buffer);
 			pathrelse(&path);
 			return -EBUSY;
 		}
@@ -546,7 +546,7 @@ static int reiserfs_add_entry(struct reiserfs_transaction_handle *th,
 	    reiserfs_paste_into_item(th, &path, &entry_key, dir, buffer,
 				     paste_size);
 	if (buffer != small_buf)
-		reiserfs_kfree(buffer, buflen, dir->i_sb);
+		kfree(buffer);
 	if (retval) {
 		reiserfs_check_path(&path);
 		return retval;
@@ -1065,7 +1065,7 @@ static int reiserfs_symlink(struct inode *parent_dir,
 		goto out_failed;
 	}
 
-	name = reiserfs_kmalloc(item_len, GFP_NOFS, parent_dir->i_sb);
+	name = kmalloc(item_len, GFP_NOFS);
 	if (!name) {
 		drop_new_inode(inode);
 		retval = -ENOMEM;
@@ -1079,14 +1079,14 @@ static int reiserfs_symlink(struct inode *parent_dir,
 	retval = journal_begin(&th, parent_dir->i_sb, jbegin_count);
 	if (retval) {
 		drop_new_inode(inode);
-		reiserfs_kfree(name, item_len, parent_dir->i_sb);
+		kfree(name);
 		goto out_failed;
 	}
 
 	retval =
 	    reiserfs_new_inode(&th, parent_dir, mode, name, strlen(symname),
 			       dentry, inode);
-	reiserfs_kfree(name, item_len, parent_dir->i_sb);
+	kfree(name);
 	if (retval) {		/* reiserfs_new_inode iputs for us */
 		goto out_failed;
 	}
diff --git a/fs/reiserfs/procfs.c b/fs/reiserfs/procfs.c
index fc2f43c75df..ef6caed9336 100644
--- a/fs/reiserfs/procfs.c
+++ b/fs/reiserfs/procfs.c
@@ -88,7 +88,6 @@ static int show_super(struct seq_file *m, struct super_block *sb)
 	seq_printf(m, "state: \t%s\n"
 		   "mount options: \t%s%s%s%s%s%s%s%s%s%s%s\n"
 		   "gen. counter: \t%i\n"
-		   "s_kmallocs: \t%i\n"
 		   "s_disk_reads: \t%i\n"
 		   "s_disk_writes: \t%i\n"
 		   "s_fix_nodes: \t%i\n"
@@ -128,7 +127,7 @@ static int show_super(struct seq_file *m, struct super_block *sb)
 		   "SMALL_TAILS " : "NO_TAILS ",
 		   replay_only(sb) ? "REPLAY_ONLY " : "",
 		   convert_reiserfs(sb) ? "CONV " : "",
-		   atomic_read(&r->s_generation_counter), SF(s_kmallocs),
+		   atomic_read(&r->s_generation_counter),
 		   SF(s_disk_reads), SF(s_disk_writes), SF(s_fix_nodes),
 		   SF(s_do_balance), SF(s_unneeded_left_neighbor),
 		   SF(s_good_search_by_key_reada), SF(s_bmaps),
diff --git a/fs/reiserfs/super.c b/fs/reiserfs/super.c
index 397d9590c8f..77891de0e02 100644
--- a/fs/reiserfs/super.c
+++ b/fs/reiserfs/super.c
@@ -472,12 +472,6 @@ static void reiserfs_put_super(struct super_block *s)
 
 	print_statistics(s);
 
-	if (REISERFS_SB(s)->s_kmallocs != 0) {
-		reiserfs_warning(s,
-				 "vs-2004: reiserfs_put_super: allocated memory left %d",
-				 REISERFS_SB(s)->s_kmallocs);
-	}
-
 	if (REISERFS_SB(s)->reserved_blocks != 0) {
 		reiserfs_warning(s,
 				 "green-2005: reiserfs_put_super: reserved blocks left %d",
diff --git a/fs/reiserfs/xattr.c b/fs/reiserfs/xattr.c
index cc061bfd437..ffb79c48c5b 100644
--- a/fs/reiserfs/xattr.c
+++ b/fs/reiserfs/xattr.c
@@ -368,15 +368,13 @@ static int __xattr_readdir(struct file *filp, void *dirent, filldir_t filldir)
 		if (d_reclen <= 32) {
 			local_buf = small_buf;
 		} else {
-			local_buf =
-			    reiserfs_kmalloc(d_reclen, GFP_NOFS, inode->i_sb);
+			local_buf = kmalloc(d_reclen, GFP_NOFS);
 			if (!local_buf) {
 				pathrelse(&path_to_entry);
 				return -ENOMEM;
 			}
 			if (item_moved(&tmp_ih, &path_to_entry)) {
-				reiserfs_kfree(local_buf, d_reclen,
-					       inode->i_sb);
+				kfree(local_buf);
 
 				/* sigh, must retry.  Do this same offset again */
 				next_pos = d_off;
@@ -399,13 +397,12 @@ static int __xattr_readdir(struct file *filp, void *dirent, filldir_t filldir)
 		if (filldir(dirent, local_buf, d_reclen, d_off, d_ino,
 			    DT_UNKNOWN) < 0) {
 			if (local_buf != small_buf) {
-				reiserfs_kfree(local_buf, d_reclen,
-					       inode->i_sb);
+				kfree(local_buf);
 			}
 			goto end;
 		}
 		if (local_buf != small_buf) {
-			reiserfs_kfree(local_buf, d_reclen, inode->i_sb);
+			kfree(local_buf);
 		}
 	}			/* while */
 
@@ -1322,109 +1319,44 @@ int reiserfs_xattr_init(struct super_block *s, int mount_flags)
 	return err;
 }
 
-static int
-__reiserfs_permission(struct inode *inode, int mask, struct nameidata *nd,
-		      int need_lock)
+static int reiserfs_check_acl(struct inode *inode, int mask)
 {
-	umode_t mode = inode->i_mode;
-
-	if (mask & MAY_WRITE) {
-		/*
-		 * Nobody gets write access to a read-only fs.
-		 */
-		if (IS_RDONLY(inode) &&
-		    (S_ISREG(mode) || S_ISDIR(mode) || S_ISLNK(mode)))
-			return -EROFS;
+	struct posix_acl *acl;
+	int error = -EAGAIN; /* do regular unix permission checks by default */
 
-		/*
-		 * Nobody gets write access to an immutable file.
-		 */
-		if (IS_IMMUTABLE(inode))
-			return -EACCES;
-	}
+	reiserfs_read_lock_xattr_i(inode);
+	reiserfs_read_lock_xattrs(inode->i_sb);
 
-	/* We don't do permission checks on the internal objects.
-	 * Permissions are determined by the "owning" object. */
-	if (is_reiserfs_priv_object(inode))
-		return 0;
+	acl = reiserfs_get_acl(inode, ACL_TYPE_ACCESS);
 
-	if (current->fsuid == inode->i_uid) {
-		mode >>= 6;
-#ifdef CONFIG_REISERFS_FS_POSIX_ACL
-	} else if (reiserfs_posixacl(inode->i_sb) &&
-		   get_inode_sd_version(inode) != STAT_DATA_V1) {
-		struct posix_acl *acl;
-
-		/* ACL can't contain additional permissions if
-		   the ACL_MASK entry is 0 */
-		if (!(mode & S_IRWXG))
-			goto check_groups;
-
-		if (need_lock) {
-			reiserfs_read_lock_xattr_i(inode);
-			reiserfs_read_lock_xattrs(inode->i_sb);
-		}
-		acl = reiserfs_get_acl(inode, ACL_TYPE_ACCESS);
-		if (need_lock) {
-			reiserfs_read_unlock_xattrs(inode->i_sb);
-			reiserfs_read_unlock_xattr_i(inode);
-		}
-		if (IS_ERR(acl)) {
-			if (PTR_ERR(acl) == -ENODATA)
-				goto check_groups;
-			return PTR_ERR(acl);
-		}
+	reiserfs_read_unlock_xattrs(inode->i_sb);
+	reiserfs_read_unlock_xattr_i(inode);
 
-		if (acl) {
-			int err = posix_acl_permission(inode, acl, mask);
+	if (acl) {
+		if (!IS_ERR(acl)) {
+			error = posix_acl_permission(inode, acl, mask);
 			posix_acl_release(acl);
-			if (err == -EACCES) {
-				goto check_capabilities;
-			}
-			return err;
-		} else {
-			goto check_groups;
-		}
-#endif
-	} else {
-	      check_groups:
-		if (in_group_p(inode->i_gid))
-			mode >>= 3;
+		} else if (PTR_ERR(acl) != -ENODATA)
+			error = PTR_ERR(acl);
 	}
 
-	/*
-	 * If the DACs are ok we don't need any capability check.
-	 */
-	if (((mode & mask & (MAY_READ | MAY_WRITE | MAY_EXEC)) == mask))
-		return 0;
+	return error;
+}
 
-      check_capabilities:
+int reiserfs_permission(struct inode *inode, int mask, struct nameidata *nd)
+{
 	/*
-	 * Read/write DACs are always overridable.
-	 * Executable DACs are overridable if at least one exec bit is set.
+	 * We don't do permission checks on the internal objects.
+	 * Permissions are determined by the "owning" object.
 	 */
-	if (!(mask & MAY_EXEC) ||
-	    (inode->i_mode & S_IXUGO) || S_ISDIR(inode->i_mode))
-		if (capable(CAP_DAC_OVERRIDE))
-			return 0;
+	if (is_reiserfs_priv_object(inode))
+		return 0;
 
 	/*
-	 * Searching includes executable on directories, else just read.
+	 * Stat data v1 doesn't support ACLs.
 	 */
-	if (mask == MAY_READ || (S_ISDIR(inode->i_mode) && !(mask & MAY_WRITE)))
-		if (capable(CAP_DAC_READ_SEARCH))
-			return 0;
-
-	return -EACCES;
-}
-
-int reiserfs_permission(struct inode *inode, int mask, struct nameidata *nd)
-{
-	return __reiserfs_permission(inode, mask, nd, 1);
-}
-
-int
-reiserfs_permission_locked(struct inode *inode, int mask, struct nameidata *nd)
-{
-	return __reiserfs_permission(inode, mask, nd, 0);
+	if (get_inode_sd_version(inode) == STAT_DATA_V1)
+		return generic_permission(inode, mask, NULL);
+	else
+		return generic_permission(inode, mask, reiserfs_check_acl);
 }
diff --git a/fs/smbfs/dir.c b/fs/smbfs/dir.c
index c6c33e15143..0424d06b147 100644
--- a/fs/smbfs/dir.c
+++ b/fs/smbfs/dir.c
@@ -209,6 +209,8 @@ init_cache:
 	ctl.valid  = 1;
 read_really:
 	result = server->ops->readdir(filp, dirent, filldir, &ctl);
+	if (result == -ERESTARTSYS && page)
+		ClearPageUptodate(page);
 	if (ctl.idx == -1)
 		goto invalid_cache;	/* retry */
 	ctl.head.end = ctl.fpos - 1;
@@ -217,7 +219,8 @@ finished:
 	if (page) {
 		cache->head = ctl.head;
 		kunmap(page);
-		SetPageUptodate(page);
+		if (result != -ERESTARTSYS)
+			SetPageUptodate(page);
 		unlock_page(page);
 		page_cache_release(page);
 	}
diff --git a/fs/xfs/linux-2.6/xfs_aops.c b/fs/xfs/linux-2.6/xfs_aops.c
index 12062678940..9892268e300 100644
--- a/fs/xfs/linux-2.6/xfs_aops.c
+++ b/fs/xfs/linux-2.6/xfs_aops.c
@@ -1462,4 +1462,5 @@ struct address_space_operations linvfs_aops = {
 	.commit_write		= generic_commit_write,
 	.bmap			= linvfs_bmap,
 	.direct_IO		= linvfs_direct_IO,
+	.migratepage		= buffer_migrate_page,
 };
diff --git a/fs/xfs/linux-2.6/xfs_buf.c b/fs/xfs/linux-2.6/xfs_buf.c
index e44b7c1a3a3..bfb4f2917bb 100644
--- a/fs/xfs/linux-2.6/xfs_buf.c
+++ b/fs/xfs/linux-2.6/xfs_buf.c
@@ -822,6 +822,13 @@ xfs_buf_rele(
 
 	XB_TRACE(bp, "rele", bp->b_relse);
 
+	if (unlikely(!hash)) {
+		ASSERT(!bp->b_relse);
+		if (atomic_dec_and_test(&bp->b_hold))
+			xfs_buf_free(bp);
+		return;
+	}
+
 	if (atomic_dec_and_lock(&bp->b_hold, &hash->bh_lock)) {
 		if (bp->b_relse) {
 			atomic_inc(&bp->b_hold);
@@ -1514,6 +1521,7 @@ xfs_mapping_buftarg(
 	struct address_space	*mapping;
 	static struct address_space_operations mapping_aops = {
 		.sync_page = block_sync_page,
+		.migratepage = fail_migrate_page,
 	};
 
 	inode = new_inode(bdev->bd_inode->i_sb);
diff --git a/fs/xfs/linux-2.6/xfs_iops.c b/fs/xfs/linux-2.6/xfs_iops.c
index 76c6df34d0d..eda7919b70a 100644
--- a/fs/xfs/linux-2.6/xfs_iops.c
+++ b/fs/xfs/linux-2.6/xfs_iops.c
@@ -262,6 +262,31 @@ has_fs_struct(struct task_struct *task)
 	return (task->fs != init_task.fs);
 }
 
+STATIC inline void
+cleanup_inode(
+	vnode_t		*dvp,
+	vnode_t		*vp,
+	struct dentry	*dentry,	
+	int		mode)
+{
+	struct dentry   teardown = {};
+	int             err2;
+
+	/* Oh, the horror.
+	 * If we can't add the ACL or we fail in 
+	 * linvfs_init_security we must back out.
+	 * ENOSPC can hit here, among other things.
+	 */
+	teardown.d_inode = LINVFS_GET_IP(vp);
+	teardown.d_name = dentry->d_name;
+
+	if (S_ISDIR(mode))
+	  	VOP_RMDIR(dvp, &teardown, NULL, err2);
+	else
+		VOP_REMOVE(dvp, &teardown, NULL, err2);
+	VN_RELE(vp);
+}
+
 STATIC int
 linvfs_mknod(
 	struct inode	*dir,
@@ -316,30 +341,19 @@ linvfs_mknod(
 	}
 
 	if (!error)
+	{
 		error = linvfs_init_security(vp, dir);
+		if (error)
+			cleanup_inode(dvp, vp, dentry, mode);
+	}
 
 	if (default_acl) {
 		if (!error) {
 			error = _ACL_INHERIT(vp, &va, default_acl);
-			if (!error) {
+			if (!error) 
 				VMODIFY(vp);
-			} else {
-				struct dentry	teardown = {};
-				int		err2;
-
-				/* Oh, the horror.
-				 * If we can't add the ACL we must back out.
-				 * ENOSPC can hit here, among other things.
-				 */
-				teardown.d_inode = ip = LINVFS_GET_IP(vp);
-				teardown.d_name = dentry->d_name;
-
-				if (S_ISDIR(mode))
-					VOP_RMDIR(dvp, &teardown, NULL, err2);
-				else
-					VOP_REMOVE(dvp, &teardown, NULL, err2);
-				VN_RELE(vp);
-			}
+			else
+				cleanup_inode(dvp, vp, dentry, mode);
 		}
 		_ACL_FREE(default_acl);
 	}