Merge branch 'master'

105 files changed, 1523 insertions, 993 deletions

diff --git a/fs/9p/conv.c b/fs/9p/conv.c
index 32a9f99154e..bf1f1006796 100644
--- a/fs/9p/conv.c
+++ b/fs/9p/conv.c
@@ -116,13 +116,19 @@ static void buf_put_int64(struct cbuf *buf, u64 val)
 	}
 }
 
-static void buf_put_stringn(struct cbuf *buf, const char *s, u16 slen)
+static char *buf_put_stringn(struct cbuf *buf, const char *s, u16 slen)
 {
+	char *ret;
+
+	ret = NULL;
 	if (buf_check_size(buf, slen + 2)) {
 		buf_put_int16(buf, slen);
+		ret = buf->p;
 		memcpy(buf->p, s, slen);
 		buf->p += slen;
 	}
+
+	return ret;
 }
 
 static inline void buf_put_string(struct cbuf *buf, const char *s)
@@ -430,15 +436,19 @@ static inline void v9fs_put_int64(struct cbuf *bufp, u64 val, u64 * p)
 static void
 v9fs_put_str(struct cbuf *bufp, char *data, struct v9fs_str *str)
 {
-	if (data) {
-		str->len = strlen(data);
-		str->str = bufp->p;
-	} else {
-		str->len = 0;
-		str->str = NULL;
-	}
+	int len;
+	char *s;
+
+	if (data)
+		len = strlen(data);
+	else
+		len = 0;
 
-	buf_put_stringn(bufp, data, str->len);
+	s = buf_put_stringn(bufp, data, len);
+	if (str) {
+		str->len = len;
+		str->str = s;
+	}
 }
 
 static int
diff --git a/fs/9p/mux.c b/fs/9p/mux.c
index 945cb368d45..ea1134eb47c 100644
--- a/fs/9p/mux.c
+++ b/fs/9p/mux.c
@@ -471,10 +471,13 @@ static void v9fs_write_work(void *a)
 		}
 
 		spin_lock(&m->lock);
-		req =
-		    list_entry(m->unsent_req_list.next, struct v9fs_req,
+again:
+		req = list_entry(m->unsent_req_list.next, struct v9fs_req,
 			       req_list);
 		list_move_tail(&req->req_list, &m->req_list);
+		if (req->err == ERREQFLUSH)
+			goto again;
+
 		m->wbuf = req->tcall->sdata;
 		m->wsize = req->tcall->size;
 		m->wpos = 0;
@@ -525,7 +528,7 @@ static void process_request(struct v9fs_mux_data *m, struct v9fs_req *req)
 	struct v9fs_str *ename;
 
 	tag = req->tag;
-	if (req->rcall->id == RERROR && !req->err) {
+	if (!req->err && req->rcall->id == RERROR) {
 		ecode = req->rcall->params.rerror.errno;
 		ename = &req->rcall->params.rerror.error;
 
@@ -551,7 +554,10 @@ static void process_request(struct v9fs_mux_data *m, struct v9fs_req *req)
 			req->err = -EIO;
 	}
 
-	if (req->cb && req->err != ERREQFLUSH) {
+	if (req->err == ERREQFLUSH)
+		return;
+
+	if (req->cb) {
 		dprintk(DEBUG_MUX, "calling callback tcall %p rcall %p\n",
 			req->tcall, req->rcall);
 
@@ -812,6 +818,7 @@ v9fs_mux_rpc_cb(void *a, struct v9fs_fcall *tc, struct v9fs_fcall *rc, int err)
 	struct v9fs_mux_rpc *r;
 
 	if (err == ERREQFLUSH) {
+		kfree(rc);
 		dprintk(DEBUG_MUX, "err req flush\n");
 		return;
 	}
diff --git a/fs/9p/v9fs.c b/fs/9p/v9fs.c
index 5250c428fc1..ef338654914 100644
--- a/fs/9p/v9fs.c
+++ b/fs/9p/v9fs.c
@@ -66,7 +66,7 @@ static match_table_t tokens = {
 	{Opt_afid, "afid=%u"},
 	{Opt_rfdno, "rfdno=%u"},
 	{Opt_wfdno, "wfdno=%u"},
-	{Opt_debug, "debug=%u"},
+	{Opt_debug, "debug=%x"},
 	{Opt_name, "name=%s"},
 	{Opt_remotename, "aname=%s"},
 	{Opt_unix, "proto=unix"},
diff --git a/fs/9p/vfs_inode.c b/fs/9p/vfs_inode.c
index 91f552454c7..63e5b0398e8 100644
--- a/fs/9p/vfs_inode.c
+++ b/fs/9p/vfs_inode.c
@@ -886,8 +886,8 @@ static int v9fs_readlink(struct dentry *dentry, char *buffer, int buflen)
 	}
 
 	/* copy extension buffer into buffer */
-	if (fcall->params.rstat.stat.extension.len < buflen)
-		buflen = fcall->params.rstat.stat.extension.len;
+	if (fcall->params.rstat.stat.extension.len+1 < buflen)
+		buflen = fcall->params.rstat.stat.extension.len + 1;
 
 	memcpy(buffer, fcall->params.rstat.stat.extension.str, buflen - 1);
 	buffer[buflen-1] = 0;
@@ -951,7 +951,7 @@ static void *v9fs_vfs_follow_link(struct dentry *dentry, struct nameidata *nd)
 	if (!link)
 		link = ERR_PTR(-ENOMEM);
 	else {
-		len = v9fs_readlink(dentry, link, strlen(link));
+		len = v9fs_readlink(dentry, link, PATH_MAX);
 
 		if (len < 0) {
 			__putname(link);
diff --git a/fs/Kconfig b/fs/Kconfig
index 3a32f3f97e9..14bcce80034 100644
--- a/fs/Kconfig
+++ b/fs/Kconfig
@@ -884,8 +884,6 @@ config CONFIGFS_FS
 	  Both sysfs and configfs can and should exist together on the
 	  same system. One is not a replacement for the other.
 
-	  If unsure, say N.
-
 endmenu
 
 menu "Miscellaneous filesystems"
@@ -1328,7 +1326,7 @@ 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..62cfd17dc5f 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 */
@@ -2866,22 +2867,22 @@ void ll_rw_block(int rw, int nr, struct buffer_head *bhs[])
 		else if (test_set_buffer_locked(bh))
 			continue;
 
-		get_bh(bh);
 		if (rw == WRITE || rw == SWRITE) {
 			if (test_clear_buffer_dirty(bh)) {
 				bh->b_end_io = end_buffer_write_sync;
+				get_bh(bh);
 				submit_bh(WRITE, bh);
 				continue;
 			}
 		} else {
 			if (!buffer_uptodate(bh)) {
 				bh->b_end_io = end_buffer_read_sync;
+				get_bh(bh);
 				submit_bh(rw, bh);
 				continue;
 			}
 		}
 		unlock_buffer(bh);
-		put_bh(bh);
 	}
 }
 
@@ -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/cifs/cifssmb.c b/fs/cifs/cifssmb.c
index 217323b0c89..b41e8b37965 100644
--- a/fs/cifs/cifssmb.c
+++ b/fs/cifs/cifssmb.c
@@ -1048,13 +1048,14 @@ CIFSSMBRead(const int xid, struct cifsTconInfo *tcon,
 			cifs_small_buf_release(iov[0].iov_base);
 		else if(resp_buf_type == CIFS_LARGE_BUFFER)
 			cifs_buf_release(iov[0].iov_base);
-	} else /* return buffer to caller to free */ /* BB FIXME how do we tell caller if it is not a large buffer */ {
-		*buf = iov[0].iov_base;
+	} else if(resp_buf_type != CIFS_NO_BUFFER) {
+		/* return buffer to caller to free */ 
+		*buf = iov[0].iov_base;		
 		if(resp_buf_type == CIFS_SMALL_BUFFER)
 			*pbuf_type = CIFS_SMALL_BUFFER;
 		else if(resp_buf_type == CIFS_LARGE_BUFFER)
 			*pbuf_type = CIFS_LARGE_BUFFER;
-	}
+	} /* else no valid buffer on return - leave as null */
 
 	/* Note: On -EAGAIN error only caller can retry on handle based calls
 		since file handle passed in no longer valid */
diff --git a/fs/cifs/connect.c b/fs/cifs/connect.c
index 88f60aa5205..ef5ae6f93c7 100644
--- a/fs/cifs/connect.c
+++ b/fs/cifs/connect.c
@@ -1785,11 +1785,20 @@ cifs_mount(struct super_block *sb, struct cifs_sb_info *cifs_sb,
 		} else if(volume_info.wsize)
 			cifs_sb->wsize = volume_info.wsize;
 		else
-			cifs_sb->wsize = CIFSMaxBufSize; /* default */
-		if(cifs_sb->rsize < PAGE_CACHE_SIZE) {
-			cifs_sb->rsize = PAGE_CACHE_SIZE; 
-			/* Windows ME does this */
-			cFYI(1,("Attempt to set readsize for mount to less than one page (4096)"));
+			cifs_sb->wsize = 
+				min_t(const int, PAGEVEC_SIZE * PAGE_CACHE_SIZE,
+					127*1024);
+			/* old default of CIFSMaxBufSize was too small now
+			   that SMB Write2 can send multiple pages in kvec.   
+			   RFC1001 does not describe what happens when frame
+			   bigger than 128K is sent so use that as max in
+			   conjunction with 52K kvec constraint on arch with 4K
+			   page size  */
+
+		if(cifs_sb->rsize < 2048) {
+			cifs_sb->rsize = 2048; 
+			/* Windows ME may prefer this */
+			cFYI(1,("readsize set to minimum 2048"));
 		}
 		cifs_sb->mnt_uid = volume_info.linux_uid;
 		cifs_sb->mnt_gid = volume_info.linux_gid;
diff --git a/fs/cifs/file.c b/fs/cifs/file.c
index 77c990f0cb9..675bd256829 100644
--- a/fs/cifs/file.c
+++ b/fs/cifs/file.c
@@ -1190,7 +1190,6 @@ retry:
 					/* BB what if continued retry is
 					   requested via mount flags? */
 					set_bit(AS_EIO, &mapping->flags);
-					SetPageError(page);
 				} else {
 					cifs_stats_bytes_written(cifs_sb->tcon,
 								 bytes_written);
@@ -1198,6 +1197,13 @@ retry:
 			}
 			for (i = 0; i < n_iov; i++) {
 				page = pvec.pages[first + i];
+				/* Should we also set page error on
+				success rc but too little data written? */
+				/* BB investigate retry logic on temporary
+				server crash cases and how recovery works
+				when page marked as error */ 
+				if(rc)
+					SetPageError(page);
 				kunmap(page);
 				unlock_page(page);
 				page_cache_release(page);
@@ -1436,13 +1442,15 @@ ssize_t cifs_user_read(struct file *file, char __user *read_data,
 					 &bytes_read, &smb_read_data,
 					 &buf_type);
 			pSMBr = (struct smb_com_read_rsp *)smb_read_data;
-			if (copy_to_user(current_offset, 
-					 smb_read_data + 4 /* RFC1001 hdr */
-					 + le16_to_cpu(pSMBr->DataOffset), 
-					 bytes_read)) {
-				rc = -EFAULT;
-			}
 			if (smb_read_data) {
+				if (copy_to_user(current_offset,
+						smb_read_data +
+						4 /* RFC1001 length field */ +
+						le16_to_cpu(pSMBr->DataOffset),
+						bytes_read)) {
+					rc = -EFAULT;
+				}
+
 				if(buf_type == CIFS_SMALL_BUFFER)
 					cifs_small_buf_release(smb_read_data);
 				else if(buf_type == CIFS_LARGE_BUFFER)
diff --git a/fs/cifs/transport.c b/fs/cifs/transport.c
index 7b98792150e..b12cb8a7da7 100644
--- a/fs/cifs/transport.c
+++ b/fs/cifs/transport.c
@@ -498,7 +498,6 @@ SendReceive2(const unsigned int xid, struct cifsSesInfo *ses,
 			else
 				*pRespBufType = CIFS_SMALL_BUFFER;
 			iov[0].iov_len = receive_len + 4;
-			iov[1].iov_len = 0;
 
 			dump_smb(midQ->resp_buf, 80);
 			/* convert the length into a more usable form */
diff --git a/fs/compat.c b/fs/compat.c
index ff0bafcff72..5333c7d7427 100644
--- a/fs/compat.c
+++ b/fs/compat.c
@@ -73,17 +73,17 @@ asmlinkage long compat_sys_utime(char __user *filename, struct compat_utimbuf __
 	return do_utimes(AT_FDCWD, filename, t ? tv : NULL);
 }
 
-asmlinkage long compat_sys_futimesat(int dfd, char __user *filename, struct compat_timeval __user *t)
+asmlinkage long compat_sys_futimesat(unsigned int dfd, char __user *filename, struct compat_timeval __user *t)
 {
 	struct timeval tv[2];
 
-	if (t) { 
+	if (t) {
 		if (get_user(tv[0].tv_sec, &t[0].tv_sec) ||
 		    get_user(tv[0].tv_usec, &t[0].tv_usec) ||
 		    get_user(tv[1].tv_sec, &t[1].tv_sec) ||
 		    get_user(tv[1].tv_usec, &t[1].tv_usec))
-			return -EFAULT; 
-	} 
+			return -EFAULT;
+	}
 	return do_utimes(dfd, filename, t ? tv : NULL);
 }
 
@@ -114,7 +114,7 @@ asmlinkage long compat_sys_newlstat(char __user * filename,
 	return error;
 }
 
-asmlinkage long compat_sys_newfstatat(int dfd, char __user *filename,
+asmlinkage long compat_sys_newfstatat(unsigned int dfd, char __user *filename,
 		struct compat_stat __user *statbuf, int flag)
 {
 	struct kstat stat;
@@ -1326,7 +1326,7 @@ compat_sys_open(const char __user *filename, int flags, int mode)
  * O_LARGEFILE flag.
  */
 asmlinkage long
-compat_sys_openat(int dfd, const char __user *filename, int flags, int mode)
+compat_sys_openat(unsigned int dfd, const char __user *filename, int flags, int mode)
 {
 	return do_sys_open(dfd, filename, flags, mode);
 }
@@ -1751,11 +1751,15 @@ asmlinkage long compat_sys_select(int n, compat_ulong_t __user *inp,
 	ret = compat_core_sys_select(n, inp, outp, exp, &timeout);
 
 	if (tvp) {
+		struct compat_timeval rtv;
+
 		if (current->personality & STICKY_TIMEOUTS)
 			goto sticky;
-		tv.tv_usec = jiffies_to_usecs(do_div((*(u64*)&timeout), HZ));
-		tv.tv_sec = timeout;
-		if (copy_to_user(tvp, &tv, sizeof(tv))) {
+		rtv.tv_usec = jiffies_to_usecs(do_div((*(u64*)&timeout), HZ));
+		rtv.tv_sec = timeout;
+		if (compat_timeval_compare(&rtv, &tv) >= 0)
+			rtv = tv;
+		if (copy_to_user(tvp, &rtv, sizeof(rtv))) {
 sticky:
 			/*
 			 * If an application puts its timeval in read-only
@@ -1781,7 +1785,7 @@ 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;
 
@@ -1822,13 +1826,17 @@ asmlinkage long compat_sys_pselect7(int n, compat_ulong_t __user *inp,
 	} while (!ret && !timeout && tsp && (ts.tv_sec || ts.tv_nsec));
 
 	if (tsp && !(current->personality & STICKY_TIMEOUTS)) {
-		ts.tv_sec += timeout / HZ;
-		ts.tv_nsec += (timeout % HZ) * (1000000000/HZ);
-		if (ts.tv_nsec >= 1000000000) {
-			ts.tv_sec++;
-			ts.tv_nsec -= 1000000000;
+		struct compat_timespec rts;
+
+		rts.tv_sec = timeout / HZ;
+		rts.tv_nsec = (timeout % HZ) * (NSEC_PER_SEC/HZ);
+		if (rts.tv_nsec >= NSEC_PER_SEC) {
+			rts.tv_sec++;
+			rts.tv_nsec -= NSEC_PER_SEC;
 		}
-		(void)copy_to_user(tsp, &ts, sizeof(ts));
+		if (compat_timespec_compare(&rts, &ts) >= 0)
+			rts = ts;
+		copy_to_user(tsp, &rts, sizeof(rts));
 	}
 
 	if (ret == -ERESTARTNOHAND) {
@@ -1918,12 +1926,17 @@ asmlinkage long compat_sys_ppoll(struct pollfd __user *ufds,
 		sigprocmask(SIG_SETMASK, &sigsaved, NULL);
 
 	if (tsp && timeout >= 0) {
+		struct compat_timespec rts;
+
 		if (current->personality & STICKY_TIMEOUTS)
 			goto sticky;
 		/* Yes, we know it's actually an s64, but it's also positive. */
-		ts.tv_nsec = jiffies_to_usecs(do_div((*(u64*)&timeout), HZ)) * 1000;
-		ts.tv_sec = timeout;
-		if (copy_to_user(tsp, &ts, sizeof(ts))) {
+		rts.tv_nsec = jiffies_to_usecs(do_div((*(u64*)&timeout), HZ)) *
+					1000;
+		rts.tv_sec = timeout;
+		if (compat_timespec_compare(&rts, &ts) >= 0)
+			rts = ts;
+		if (copy_to_user(tsp, &rts, sizeof(rts))) {
 sticky:
 			/*
 			 * If an application puts its timeval in read-only
diff --git a/fs/compat_ioctl.c b/fs/compat_ioctl.c
index 5dd0207ffd4..057e60217fc 100644
--- a/fs/compat_ioctl.c
+++ b/fs/compat_ioctl.c
@@ -931,8 +931,8 @@ struct compat_sg_req_info { /* used by SG_GET_REQUEST_TABLE ioctl() */
 static int sg_grt_trans(unsigned int fd, unsigned int cmd, unsigned long arg)
 {
 	int err, i;
-	sg_req_info_t *r;
-	struct compat_sg_req_info *o = (struct compat_sg_req_info *)arg;
+	sg_req_info_t __user *r;
+	struct compat_sg_req_info __user *o = (void __user *)arg;
 	r = compat_alloc_user_space(sizeof(sg_req_info_t)*SG_MAX_QUEUE);
 	err = sys_ioctl(fd,cmd,(unsigned long)r);
 	if (err < 0)
@@ -2739,8 +2739,8 @@ static int do_ncp_setprivatedata(unsigned int fd, unsigned int cmd, unsigned lon
 static int
 lp_timeout_trans(unsigned int fd, unsigned int cmd, unsigned long arg)
 {
-	struct compat_timeval *tc = (struct compat_timeval *)arg;
-	struct timeval *tn = compat_alloc_user_space(sizeof(struct timeval));
+	struct compat_timeval __user *tc = (struct compat_timeval __user *)arg;
+	struct timeval __user *tn = compat_alloc_user_space(sizeof(struct timeval));
 	struct timeval ts;
 	if (get_user(ts.tv_sec, &tc->tv_sec) ||
 	    get_user(ts.tv_usec, &tc->tv_usec) ||
diff --git a/fs/configfs/configfs_internal.h b/fs/configfs/configfs_internal.h
index 8899d9c5f6b..f70e46951b3 100644
--- a/fs/configfs/configfs_internal.h
+++ b/fs/configfs/configfs_internal.h
@@ -36,6 +36,7 @@ struct configfs_dirent {
 	int			s_type;
 	umode_t			s_mode;
 	struct dentry		* s_dentry;
+	struct iattr		* s_iattr;
 };
 
 #define CONFIGFS_ROOT		0x0001
@@ -48,10 +49,11 @@ struct configfs_dirent {
 #define CONFIGFS_NOT_PINNED	(CONFIGFS_ITEM_ATTR)
 
 extern struct vfsmount * configfs_mount;
+extern kmem_cache_t *configfs_dir_cachep;
 
 extern int configfs_is_root(struct config_item *item);
 
-extern struct inode * configfs_new_inode(mode_t mode);
+extern struct inode * configfs_new_inode(mode_t mode, struct configfs_dirent *);
 extern int configfs_create(struct dentry *, int mode, int (*init)(struct inode *));
 
 extern int configfs_create_file(struct config_item *, const struct configfs_attribute *);
@@ -63,6 +65,7 @@ extern void configfs_hash_and_remove(struct dentry * dir, const char * name);
 
 extern const unsigned char * configfs_get_name(struct configfs_dirent *sd);
 extern void configfs_drop_dentry(struct configfs_dirent *sd, struct dentry *parent);
+extern int configfs_setattr(struct dentry *dentry, struct iattr *iattr);
 
 extern int configfs_pin_fs(void);
 extern void configfs_release_fs(void);
@@ -120,8 +123,10 @@ static inline struct config_item *configfs_get_config_item(struct dentry *dentry
 
 static inline void release_configfs_dirent(struct configfs_dirent * sd)
 {
-	if (!(sd->s_type & CONFIGFS_ROOT))
-		kfree(sd);
+	if (!(sd->s_type & CONFIGFS_ROOT)) {
+		kfree(sd->s_iattr);
+		kmem_cache_free(configfs_dir_cachep, sd);
+	}
 }
 
 static inline struct configfs_dirent * configfs_get(struct configfs_dirent * sd)
diff --git a/fs/configfs/dir.c b/fs/configfs/dir.c
index b668ec61527..ca60e3abef4 100644
--- a/fs/configfs/dir.c
+++ b/fs/configfs/dir.c
@@ -72,7 +72,7 @@ static struct configfs_dirent *configfs_new_dirent(struct configfs_dirent * pare
 {
 	struct configfs_dirent * sd;
 
-	sd = kmalloc(sizeof(*sd), GFP_KERNEL);
+	sd = kmem_cache_alloc(configfs_dir_cachep, GFP_KERNEL);
 	if (!sd)
 		return NULL;
 
@@ -136,13 +136,19 @@ static int create_dir(struct config_item * k, struct dentry * p,
 	int error;
 	umode_t mode = S_IFDIR| S_IRWXU | S_IRUGO | S_IXUGO;
 
-	error = configfs_create(d, mode, init_dir);
+	error = configfs_make_dirent(p->d_fsdata, d, k, mode,
+				     CONFIGFS_DIR);
 	if (!error) {
-		error = configfs_make_dirent(p->d_fsdata, d, k, mode,
-					   CONFIGFS_DIR);
+		error = configfs_create(d, mode, init_dir);
 		if (!error) {
 			p->d_inode->i_nlink++;
 			(d)->d_op = &configfs_dentry_ops;
+		} else {
+			struct configfs_dirent *sd = d->d_fsdata;
+			if (sd) {
+				list_del_init(&sd->s_sibling);
+				configfs_put(sd);
+			}
 		}
 	}
 	return error;
@@ -182,12 +188,19 @@ int configfs_create_link(struct configfs_symlink *sl,
 	int err = 0;
 	umode_t mode = S_IFLNK | S_IRWXUGO;
 
-	err = configfs_create(dentry, mode, init_symlink);
+	err = configfs_make_dirent(parent->d_fsdata, dentry, sl, mode,
+				   CONFIGFS_ITEM_LINK);
 	if (!err) {
-		err = configfs_make_dirent(parent->d_fsdata, dentry, sl,
-					 mode, CONFIGFS_ITEM_LINK);
+		err = configfs_create(dentry, mode, init_symlink);
 		if (!err)
 			dentry->d_op = &configfs_dentry_ops;
+		else {
+			struct configfs_dirent *sd = dentry->d_fsdata;
+			if (sd) {
+				list_del_init(&sd->s_sibling);
+				configfs_put(sd);
+			}
+		}
 	}
 	return err;
 }
@@ -241,13 +254,15 @@ static int configfs_attach_attr(struct configfs_dirent * sd, struct dentry * den
 	struct configfs_attribute * attr = sd->s_element;
 	int error;
 
+	dentry->d_fsdata = configfs_get(sd);
+	sd->s_dentry = dentry;
 	error = configfs_create(dentry, (attr->ca_mode & S_IALLUGO) | S_IFREG, init_file);
-	if (error)
+	if (error) {
+		configfs_put(sd);
 		return error;
+	}
 
 	dentry->d_op = &configfs_dentry_ops;
-	dentry->d_fsdata = configfs_get(sd);
-	sd->s_dentry = dentry;
 	d_rehash(dentry);
 
 	return 0;
@@ -839,6 +854,7 @@ struct inode_operations configfs_dir_inode_operations = {
 	.symlink	= configfs_symlink,
 	.unlink		= configfs_unlink,
 	.lookup		= configfs_lookup,
+	.setattr	= configfs_setattr,
 };
 
 #if 0
diff --git a/fs/configfs/file.c b/fs/configfs/file.c
index c26cd61f13a..3921920d871 100644
--- a/fs/configfs/file.c
+++ b/fs/configfs/file.c
@@ -26,7 +26,6 @@
 
 #include <linux/fs.h>
 #include <linux/module.h>
-#include <linux/dnotify.h>
 #include <linux/slab.h>
 #include <asm/uaccess.h>
 #include <asm/semaphore.h>
@@ -150,7 +149,7 @@ out:
 /**
  *	fill_write_buffer - copy buffer from userspace.
  *	@buffer:	data buffer for file.
- *	@userbuf:	data from user.
+ *	@buf:		data from user.
  *	@count:		number of bytes in @userbuf.
  *
  *	Allocate @buffer->page if it hasn't been already, then
@@ -177,8 +176,9 @@ fill_write_buffer(struct configfs_buffer * buffer, const char __user * buf, size
 
 /**
  *	flush_write_buffer - push buffer to config_item.
- *	@file:		file pointer.
+ *	@dentry:	dentry to the attribute
  *	@buffer:	data buffer for file.
+ *	@count:		number of bytes
  *
  *	Get the correct pointers for the config_item and the attribute we're
  *	dealing with, then call the store() method for the attribute,
@@ -217,15 +217,16 @@ static ssize_t
 configfs_write_file(struct file *file, const char __user *buf, size_t count, loff_t *ppos)
 {
 	struct configfs_buffer * buffer = file->private_data;
+	ssize_t len;
 
 	down(&buffer->sem);
-	count = fill_write_buffer(buffer,buf,count);
-	if (count > 0)
-		count = flush_write_buffer(file->f_dentry,buffer,count);
-	if (count > 0)
-		*ppos += count;
+	len = fill_write_buffer(buffer, buf, count);
+	if (len > 0)
+		len = flush_write_buffer(file->f_dentry, buffer, count);
+	if (len > 0)
+		*ppos += len;
 	up(&buffer->sem);
-	return count;
+	return len;
 }
 
 static int check_perm(struct inode * inode, struct file * file)
diff --git a/fs/configfs/inode.c b/fs/configfs/inode.c
index 6577c588de9..c153bd9534c 100644
--- a/fs/configfs/inode.c
+++ b/fs/configfs/inode.c
@@ -31,6 +31,7 @@
 #include <linux/pagemap.h>
 #include <linux/namei.h>
 #include <linux/backing-dev.h>
+#include <linux/capability.h>
 
 #include <linux/configfs.h>
 #include "configfs_internal.h"
@@ -48,18 +49,107 @@ static struct backing_dev_info configfs_backing_dev_info = {
 	.capabilities	= BDI_CAP_NO_ACCT_DIRTY | BDI_CAP_NO_WRITEBACK,
 };
 
-struct inode * configfs_new_inode(mode_t mode)
+static struct inode_operations configfs_inode_operations ={
+	.setattr	= configfs_setattr,
+};
+
+int configfs_setattr(struct dentry * dentry, struct iattr * iattr)
+{
+	struct inode * inode = dentry->d_inode;
+	struct configfs_dirent * sd = dentry->d_fsdata;
+	struct iattr * sd_iattr;
+	unsigned int ia_valid = iattr->ia_valid;
+	int error;
+
+	if (!sd)
+		return -EINVAL;
+
+	sd_iattr = sd->s_iattr;
+
+	error = inode_change_ok(inode, iattr);
+	if (error)
+		return error;
+
+	error = inode_setattr(inode, iattr);
+	if (error)
+		return error;
+
+	if (!sd_iattr) {
+		/* setting attributes for the first time, allocate now */
+		sd_iattr = kmalloc(sizeof(struct iattr), GFP_KERNEL);
+		if (!sd_iattr)
+			return -ENOMEM;
+		/* assign default attributes */
+		memset(sd_iattr, 0, sizeof(struct iattr));
+		sd_iattr->ia_mode = sd->s_mode;
+		sd_iattr->ia_uid = 0;
+		sd_iattr->ia_gid = 0;
+		sd_iattr->ia_atime = sd_iattr->ia_mtime = sd_iattr->ia_ctime = CURRENT_TIME;
+		sd->s_iattr = sd_iattr;
+	}
+
+	/* attributes were changed atleast once in past */
+
+	if (ia_valid & ATTR_UID)
+		sd_iattr->ia_uid = iattr->ia_uid;
+	if (ia_valid & ATTR_GID)
+		sd_iattr->ia_gid = iattr->ia_gid;
+	if (ia_valid & ATTR_ATIME)
+		sd_iattr->ia_atime = timespec_trunc(iattr->ia_atime,
+						inode->i_sb->s_time_gran);
+	if (ia_valid & ATTR_MTIME)
+		sd_iattr->ia_mtime = timespec_trunc(iattr->ia_mtime,
+						inode->i_sb->s_time_gran);
+	if (ia_valid & ATTR_CTIME)
+		sd_iattr->ia_ctime = timespec_trunc(iattr->ia_ctime,
+						inode->i_sb->s_time_gran);
+	if (ia_valid & ATTR_MODE) {
+		umode_t mode = iattr->ia_mode;
+
+		if (!in_group_p(inode->i_gid) && !capable(CAP_FSETID))
+			mode &= ~S_ISGID;
+		sd_iattr->ia_mode = sd->s_mode = mode;
+	}
+
+	return error;
+}
+
+static inline void set_default_inode_attr(struct inode * inode, mode_t mode)
+{
+	inode->i_mode = mode;
+	inode->i_uid = 0;
+	inode->i_gid = 0;
+	inode->i_atime = inode->i_mtime = inode->i_ctime = CURRENT_TIME;
+}
+
+static inline void set_inode_attr(struct inode * inode, struct iattr * iattr)
+{
+	inode->i_mode = iattr->ia_mode;
+	inode->i_uid = iattr->ia_uid;
+	inode->i_gid = iattr->ia_gid;
+	inode->i_atime = iattr->ia_atime;
+	inode->i_mtime = iattr->ia_mtime;
+	inode->i_ctime = iattr->ia_ctime;
+}
+
+struct inode * configfs_new_inode(mode_t mode, struct configfs_dirent * sd)
 {
 	struct inode * inode = new_inode(configfs_sb);
 	if (inode) {
-		inode->i_mode = mode;
-		inode->i_uid = 0;
-		inode->i_gid = 0;
 		inode->i_blksize = PAGE_CACHE_SIZE;
 		inode->i_blocks = 0;
-		inode->i_atime = inode->i_mtime = inode->i_ctime = CURRENT_TIME;
 		inode->i_mapping->a_ops = &configfs_aops;
 		inode->i_mapping->backing_dev_info = &configfs_backing_dev_info;
+		inode->i_op = &configfs_inode_operations;
+
+		if (sd->s_iattr) {
+			/* sysfs_dirent has non-default attributes
+			 * get them for the new inode from persistent copy
+			 * in sysfs_dirent
+			 */
+			set_inode_attr(inode, sd->s_iattr);
+		} else
+			set_default_inode_attr(inode, mode);
 	}
 	return inode;
 }
@@ -70,7 +160,8 @@ int configfs_create(struct dentry * dentry, int mode, int (*init)(struct inode *
 	struct inode * inode = NULL;
 	if (dentry) {
 		if (!dentry->d_inode) {
-			if ((inode = configfs_new_inode(mode))) {
+			struct configfs_dirent *sd = dentry->d_fsdata;
+			if ((inode = configfs_new_inode(mode, sd))) {
 				if (dentry->d_parent && dentry->d_parent->d_inode) {
 					struct inode *p_inode = dentry->d_parent->d_inode;
 					p_inode->i_mtime = p_inode->i_ctime = CURRENT_TIME;
@@ -103,10 +194,9 @@ int configfs_create(struct dentry * dentry, int mode, int (*init)(struct inode *
  */
 const unsigned char * configfs_get_name(struct configfs_dirent *sd)
 {
-	struct attribute * attr;
+	struct configfs_attribute *attr;
 
-	if (!sd || !sd->s_element)
-		BUG();
+	BUG_ON(!sd || !sd->s_element);
 
 	/* These always have a dentry, so use that */
 	if (sd->s_type & (CONFIGFS_DIR | CONFIGFS_ITEM_LINK))
@@ -114,7 +204,7 @@ const unsigned char * configfs_get_name(struct configfs_dirent *sd)
 
 	if (sd->s_type & CONFIGFS_ITEM_ATTR) {
 		attr = sd->s_element;
-		return attr->name;
+		return attr->ca_name;
 	}
 	return NULL;
 }
@@ -130,13 +220,17 @@ void configfs_drop_dentry(struct configfs_dirent * sd, struct dentry * parent)
 
 	if (dentry) {
 		spin_lock(&dcache_lock);
+		spin_lock(&dentry->d_lock);
 		if (!(d_unhashed(dentry) && dentry->d_inode)) {
 			dget_locked(dentry);
 			__d_drop(dentry);
+			spin_unlock(&dentry->d_lock);
 			spin_unlock(&dcache_lock);
 			simple_unlink(parent->d_inode, dentry);
-		} else
+		} else {
+			spin_unlock(&dentry->d_lock);
 			spin_unlock(&dcache_lock);
+		}
 	}
 }
 
@@ -145,6 +239,10 @@ void configfs_hash_and_remove(struct dentry * dir, const char * name)
 	struct configfs_dirent * sd;
 	struct configfs_dirent * parent_sd = dir->d_fsdata;
 
+	if (dir->d_inode == NULL)
+		/* no inode means this hasn't been made visible yet */
+		return;
+
 	mutex_lock(&dir->d_inode->i_mutex);
 	list_for_each_entry(sd, &parent_sd->s_children, s_sibling) {
 		if (!sd->s_element)
diff --git a/fs/configfs/mount.c b/fs/configfs/mount.c
index 1a2f6f6a4d9..f920d30478e 100644
--- a/fs/configfs/mount.c
+++ b/fs/configfs/mount.c
@@ -38,6 +38,7 @@
 
 struct vfsmount * configfs_mount = NULL;
 struct super_block * configfs_sb = NULL;
+kmem_cache_t *configfs_dir_cachep;
 static int configfs_mnt_count = 0;
 
 static struct super_operations configfs_ops = {
@@ -62,6 +63,7 @@ static struct configfs_dirent configfs_root = {
 	.s_children	= LIST_HEAD_INIT(configfs_root.s_children),
 	.s_element	= &configfs_root_group.cg_item,
 	.s_type		= CONFIGFS_ROOT,
+	.s_iattr	= NULL,
 };
 
 static int configfs_fill_super(struct super_block *sb, void *data, int silent)
@@ -73,9 +75,11 @@ static int configfs_fill_super(struct super_block *sb, void *data, int silent)
 	sb->s_blocksize_bits = PAGE_CACHE_SHIFT;
 	sb->s_magic = CONFIGFS_MAGIC;
 	sb->s_op = &configfs_ops;
+	sb->s_time_gran = 1;
 	configfs_sb = sb;
 
-	inode = configfs_new_inode(S_IFDIR | S_IRWXU | S_IRUGO | S_IXUGO);
+	inode = configfs_new_inode(S_IFDIR | S_IRWXU | S_IRUGO | S_IXUGO,
+				   &configfs_root);
 	if (inode) {
 		inode->i_op = &configfs_dir_inode_operations;
 		inode->i_fop = &configfs_dir_operations;
@@ -128,19 +132,31 @@ static decl_subsys(config, NULL, NULL);
 
 static int __init configfs_init(void)
 {
-	int err;
+	int err = -ENOMEM;
+
+	configfs_dir_cachep = kmem_cache_create("configfs_dir_cache",
+						sizeof(struct configfs_dirent),
+						0, 0, NULL, NULL);
+	if (!configfs_dir_cachep)
+		goto out;
 
 	kset_set_kset_s(&config_subsys, kernel_subsys);
 	err = subsystem_register(&config_subsys);
-	if (err)
-		return err;
+	if (err) {
+		kmem_cache_destroy(configfs_dir_cachep);
+		configfs_dir_cachep = NULL;
+		goto out;
+	}
 
 	err = register_filesystem(&configfs_fs_type);
 	if (err) {
 		printk(KERN_ERR "configfs: Unable to register filesystem!\n");
 		subsystem_unregister(&config_subsys);
+		kmem_cache_destroy(configfs_dir_cachep);
+		configfs_dir_cachep = NULL;
 	}
 
+out:
 	return err;
 }
 
@@ -148,11 +164,13 @@ static void __exit configfs_exit(void)
 {
 	unregister_filesystem(&configfs_fs_type);
 	subsystem_unregister(&config_subsys);
+	kmem_cache_destroy(configfs_dir_cachep);
+	configfs_dir_cachep = NULL;
 }
 
 MODULE_AUTHOR("Oracle");
 MODULE_LICENSE("GPL");
-MODULE_VERSION("0.0.1");
+MODULE_VERSION("0.0.2");
 MODULE_DESCRIPTION("Simple RAM filesystem for user driven kernel subsystem configuration.");
 
 module_init(configfs_init);
diff --git a/fs/configfs/symlink.c b/fs/configfs/symlink.c
index 50f5840521a..e5512e295cf 100644
--- a/fs/configfs/symlink.c
+++ b/fs/configfs/symlink.c
@@ -162,8 +162,7 @@ int configfs_unlink(struct inode *dir, struct dentry *dentry)
 	if (!(sd->s_type & CONFIGFS_ITEM_LINK))
 		goto out;
 
-	if (dentry->d_parent == configfs_sb->s_root)
-		BUG();
+	BUG_ON(dentry->d_parent == configfs_sb->s_root);
 
 	sl = sd->s_element;
 
@@ -277,5 +276,6 @@ struct inode_operations configfs_symlink_inode_operations = {
 	.follow_link = configfs_follow_link,
 	.readlink = generic_readlink,
 	.put_link = configfs_put_link,
+	.setattr = configfs_setattr,
 };
 
diff --git a/fs/dcache.c b/fs/dcache.c
index 86bdb93789c..a173bba3266 100644
--- a/fs/dcache.c
+++ b/fs/dcache.c
@@ -743,7 +743,9 @@ struct dentry *d_alloc(struct dentry * parent, const struct qstr *name)
 	dentry->d_op = NULL;
 	dentry->d_fsdata = NULL;
 	dentry->d_mounted = 0;
+#ifdef CONFIG_PROFILING
 	dentry->d_cookie = NULL;
+#endif
 	INIT_HLIST_NODE(&dentry->d_hash);
 	INIT_LIST_HEAD(&dentry->d_lru);
 	INIT_LIST_HEAD(&dentry->d_subdirs);
diff --git a/fs/debugfs/file.c b/fs/debugfs/file.c
index efc97d9b786..d575452cd9f 100644
--- a/fs/debugfs/file.c
+++ b/fs/debugfs/file.c
@@ -56,7 +56,7 @@ static u64 debugfs_u8_get(void *data)
 DEFINE_SIMPLE_ATTRIBUTE(fops_u8, debugfs_u8_get, debugfs_u8_set, "%llu\n");
 
 /**
- * debugfs_create_u8 - create a file in the debugfs filesystem that is used to read and write a unsigned 8 bit value.
+ * debugfs_create_u8 - create a file in the debugfs filesystem that is used to read and write an unsigned 8 bit value.
  *
  * @name: a pointer to a string containing the name of the file to create.
  * @mode: the permission that the file should have
@@ -98,7 +98,7 @@ static u64 debugfs_u16_get(void *data)
 DEFINE_SIMPLE_ATTRIBUTE(fops_u16, debugfs_u16_get, debugfs_u16_set, "%llu\n");
 
 /**
- * debugfs_create_u16 - create a file in the debugfs filesystem that is used to read and write a unsigned 8 bit value.
+ * debugfs_create_u16 - create a file in the debugfs filesystem that is used to read and write an unsigned 16 bit value.
  *
  * @name: a pointer to a string containing the name of the file to create.
  * @mode: the permission that the file should have
@@ -140,7 +140,7 @@ static u64 debugfs_u32_get(void *data)
 DEFINE_SIMPLE_ATTRIBUTE(fops_u32, debugfs_u32_get, debugfs_u32_set, "%llu\n");
 
 /**
- * debugfs_create_u32 - create a file in the debugfs filesystem that is used to read and write a unsigned 8 bit value.
+ * debugfs_create_u32 - create a file in the debugfs filesystem that is used to read and write an unsigned 32 bit value.
  *
  * @name: a pointer to a string containing the name of the file to create.
  * @mode: the permission that the file should have
diff --git a/fs/direct-io.c b/fs/direct-io.c
index 30dbbd1df51..848044af7e1 100644
--- a/fs/direct-io.c
+++ b/fs/direct-io.c
@@ -857,6 +857,7 @@ do_holes:
 			/* Handle holes */
 			if (!buffer_mapped(map_bh)) {
 				char *kaddr;
+				loff_t i_size_aligned;
 
 				/* AKPM: eargh, -ENOTBLK is a hack */
 				if (dio->rw == WRITE) {
@@ -864,8 +865,14 @@ do_holes:
 					return -ENOTBLK;
 				}
 
+				/*
+				 * Be sure to account for a partial block as the
+				 * last block in the file
+				 */
+				i_size_aligned = ALIGN(i_size_read(dio->inode),
+							1 << blkbits);
 				if (dio->block_in_file >=
-					i_size_read(dio->inode)>>blkbits) {
+						i_size_aligned >> blkbits) {
 					/* We hit eof */
 					page_cache_release(page);
 					goto out;
diff --git a/fs/exec.c b/fs/exec.c
index 055378d2513..0e1c95074d4 100644
--- a/fs/exec.c
+++ b/fs/exec.c
@@ -1403,7 +1403,7 @@ static void zap_threads (struct mm_struct *mm)
 		do_each_thread(g,p) {
 			if (mm == p->mm && p != tsk &&
 			    p->ptrace && p->parent->mm == mm) {
-				__ptrace_unlink(p);
+				__ptrace_detach(p, 0);
 			}
 		} while_each_thread(g,p);
 		write_unlock_irq(&tasklist_lock);
diff --git a/fs/ext2/acl.c b/fs/ext2/acl.c
index 35acc43b897..da52b4a5db6 100644
--- a/fs/ext2/acl.c
+++ b/fs/ext2/acl.c
@@ -220,7 +220,7 @@ ext2_set_acl(struct inode *inode, int type, struct posix_acl *acl)
 	struct ext2_inode_info *ei = EXT2_I(inode);
 	int name_index;
 	void *value = NULL;
-	size_t size;
+	size_t size = 0;
 	int error;
 
 	if (S_ISLNK(inode->i_mode))
diff --git a/fs/ext2/ialloc.c b/fs/ext2/ialloc.c
index 74714af4ae6..e52765219e1 100644
--- a/fs/ext2/ialloc.c
+++ b/fs/ext2/ialloc.c
@@ -605,7 +605,7 @@ got:
 	insert_inode_hash(inode);
 
 	if (DQUOT_ALLOC_INODE(inode)) {
-		err = -ENOSPC;
+		err = -EDQUOT;
 		goto fail_drop;
 	}
 
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/ext2/super.c b/fs/ext2/super.c
index 8d6819846fc..cb6f9bd658d 100644
--- a/fs/ext2/super.c
+++ b/fs/ext2/super.c
@@ -221,6 +221,11 @@ static int ext2_show_options(struct seq_file *seq, struct vfsmount *vfs)
 		seq_puts(seq, ",grpquota");
 #endif
 
+#if defined(CONFIG_EXT2_FS_XIP)
+	if (sbi->s_mount_opt & EXT2_MOUNT_XIP)
+		seq_puts(seq, ",xip");
+#endif
+
 	return 0;
 }
 
diff --git a/fs/ext2/xattr.c b/fs/ext2/xattr.c
index a2ca3107d47..86ae8e93adb 100644
--- a/fs/ext2/xattr.c
+++ b/fs/ext2/xattr.c
@@ -792,18 +792,20 @@ ext2_xattr_delete_inode(struct inode *inode)
 		ext2_free_blocks(inode, EXT2_I(inode)->i_file_acl, 1);
 		get_bh(bh);
 		bforget(bh);
+		unlock_buffer(bh);
 	} else {
 		HDR(bh)->h_refcount = cpu_to_le32(
 			le32_to_cpu(HDR(bh)->h_refcount) - 1);
 		if (ce)
 			mb_cache_entry_release(ce);
+		ea_bdebug(bh, "refcount now=%d",
+			le32_to_cpu(HDR(bh)->h_refcount));
+		unlock_buffer(bh);
 		mark_buffer_dirty(bh);
 		if (IS_SYNC(inode))
 			sync_dirty_buffer(bh);
 		DQUOT_FREE_BLOCK(inode, 1);
 	}
-	ea_bdebug(bh, "refcount now=%d", le32_to_cpu(HDR(bh)->h_refcount) - 1);
-	unlock_buffer(bh);
 	EXT2_I(inode)->i_file_acl = 0;
 
 cleanup:
diff --git a/fs/ext3/acl.c b/fs/ext3/acl.c
index 47a9da2dfb4..0d21d558b87 100644
--- a/fs/ext3/acl.c
+++ b/fs/ext3/acl.c
@@ -226,7 +226,7 @@ ext3_set_acl(handle_t *handle, struct inode *inode, int type,
 	struct ext3_inode_info *ei = EXT3_I(inode);
 	int name_index;
 	void *value = NULL;
-	size_t size;
+	size_t size = 0;
 	int error;
 
 	if (S_ISLNK(inode->i_mode))
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/fat/file.c b/fs/fat/file.c
index e99c5a73b39..88aa1ae13f9 100644
--- a/fs/fat/file.c
+++ b/fs/fat/file.c
@@ -210,10 +210,30 @@ static int fat_free(struct inode *inode, int skip)
 	if (MSDOS_I(inode)->i_start == 0)
 		return 0;
 
-	/*
-	 * Write a new EOF, and get the remaining cluster chain for freeing.
-	 */
+	fat_cache_inval_inode(inode);
+
 	wait = IS_DIRSYNC(inode);
+	i_start = free_start = MSDOS_I(inode)->i_start;
+	i_logstart = MSDOS_I(inode)->i_logstart;
+
+	/* First, we write the new file size. */
+	if (!skip) {
+		MSDOS_I(inode)->i_start = 0;
+		MSDOS_I(inode)->i_logstart = 0;
+	}
+	MSDOS_I(inode)->i_attrs |= ATTR_ARCH;
+	inode->i_ctime = inode->i_mtime = CURRENT_TIME_SEC;
+	if (wait) {
+		err = fat_sync_inode(inode);
+		if (err) {
+			MSDOS_I(inode)->i_start = i_start;
+			MSDOS_I(inode)->i_logstart = i_logstart;
+			return err;
+		}
+	} else
+		mark_inode_dirty(inode);
+
+	/* Write a new EOF, and get the remaining cluster chain for freeing. */
 	if (skip) {
 		struct fat_entry fatent;
 		int ret, fclus, dclus;
@@ -244,35 +264,11 @@ static int fat_free(struct inode *inode, int skip)
 			return ret;
 
 		free_start = ret;
-		i_start = i_logstart = 0;
-		fat_cache_inval_inode(inode);
-	} else {
-		fat_cache_inval_inode(inode);
-
-		i_start = free_start = MSDOS_I(inode)->i_start;
-		i_logstart = MSDOS_I(inode)->i_logstart;
-		MSDOS_I(inode)->i_start = 0;
-		MSDOS_I(inode)->i_logstart = 0;
 	}
-	MSDOS_I(inode)->i_attrs |= ATTR_ARCH;
-	inode->i_ctime = inode->i_mtime = CURRENT_TIME_SEC;
-	if (wait) {
-		err = fat_sync_inode(inode);
-		if (err)
-			goto error;
-	} else
-		mark_inode_dirty(inode);
 	inode->i_blocks = skip << (MSDOS_SB(sb)->cluster_bits - 9);
 
 	/* Freeing the remained cluster chain */
 	return fat_free_clusters(inode, free_start);
-
-error:
-	if (i_start) {
-		MSDOS_I(inode)->i_start = i_start;
-		MSDOS_I(inode)->i_logstart = i_logstart;
-	}
-	return err;
 }
 
 void fat_truncate(struct inode *inode)
diff --git a/fs/fat/misc.c b/fs/fat/misc.c
index 32fb0a3f1da..944652e9dde 100644
--- a/fs/fat/misc.c
+++ b/fs/fat/misc.c
@@ -196,19 +196,9 @@ EXPORT_SYMBOL_GPL(fat_date_unix2dos);
 
 int fat_sync_bhs(struct buffer_head **bhs, int nr_bhs)
 {
-	int i, e, err = 0;
+	int i, err = 0;
 
-	for (i = 0; i < nr_bhs; i++) {
-		lock_buffer(bhs[i]);
-		if (test_clear_buffer_dirty(bhs[i])) {
-			get_bh(bhs[i]);
-			bhs[i]->b_end_io = end_buffer_write_sync;
-			e = submit_bh(WRITE, bhs[i]);
-			if (!err && e)
-				err = e;
-		} else
-			unlock_buffer(bhs[i]);
-	}
+	ll_rw_block(SWRITE, nr_bhs, bhs);
 	for (i = 0; i < nr_bhs; i++) {
 		wait_on_buffer(bhs[i]);
 		if (buffer_eopnotsupp(bhs[i])) {
diff --git a/fs/fcntl.c b/fs/fcntl.c
index 5f96786d1c7..dc4a7007f4e 100644
--- a/fs/fcntl.c
+++ b/fs/fcntl.c
@@ -208,8 +208,11 @@ static int setfl(int fd, struct file * filp, unsigned long arg)
 	struct inode * inode = filp->f_dentry->d_inode;
 	int error = 0;
 
-	/* O_APPEND cannot be cleared if the file is marked as append-only */
-	if (!(arg & O_APPEND) && IS_APPEND(inode))
+	/*
+	 * O_APPEND cannot be cleared if the file is marked as append-only
+	 * and the file is open for write.
+	 */
+	if (((arg ^ filp->f_flags) & O_APPEND) && IS_APPEND(inode))
 		return -EPERM;
 
 	/* O_NOATIME can only be set by the owner or superuser */
diff --git a/fs/file.c b/fs/file.c
index fd066b261c7..cea7cbea11d 100644
--- a/fs/file.c
+++ b/fs/file.c
@@ -379,7 +379,6 @@ static void __devinit fdtable_defer_list_init(int cpu)
 void __init files_defer_init(void)
 {
 	int i;
-	/* Really early - can't use for_each_cpu */
-	for (i = 0; i < NR_CPUS; i++)
+	for_each_cpu(i)
 		fdtable_defer_list_init(i);
 }
diff --git a/fs/fuse/dev.c b/fs/fuse/dev.c
index 4526da8907c..0c9a2ee54c9 100644
--- a/fs/fuse/dev.c
+++ b/fs/fuse/dev.c
@@ -66,6 +66,12 @@ static void restore_sigs(sigset_t *oldset)
 	sigprocmask(SIG_SETMASK, oldset, NULL);
 }
 
+/*
+ * Reset request, so that it can be reused
+ *
+ * The caller must be _very_ careful to make sure, that it is holding
+ * the only reference to req
+ */
 void fuse_reset_request(struct fuse_req *req)
 {
 	int preallocated = req->preallocated;
@@ -120,9 +126,9 @@ struct fuse_req *fuse_get_request(struct fuse_conn *fc)
 	return do_get_request(fc);
 }
 
+/* Must be called with fuse_lock held */
 static void fuse_putback_request(struct fuse_conn *fc, struct fuse_req *req)
 {
-	spin_lock(&fuse_lock);
 	if (req->preallocated) {
 		atomic_dec(&fc->num_waiting);
 		list_add(&req->list, &fc->unused_list);
@@ -134,11 +140,19 @@ static void fuse_putback_request(struct fuse_conn *fc, struct fuse_req *req)
 		fc->outstanding_debt--;
 	else
 		up(&fc->outstanding_sem);
-	spin_unlock(&fuse_lock);
 }
 
 void fuse_put_request(struct fuse_conn *fc, struct fuse_req *req)
 {
+	if (atomic_dec_and_test(&req->count)) {
+		spin_lock(&fuse_lock);
+		fuse_putback_request(fc, req);
+		spin_unlock(&fuse_lock);
+	}
+}
+
+static void fuse_put_request_locked(struct fuse_conn *fc, struct fuse_req *req)
+{
 	if (atomic_dec_and_test(&req->count))
 		fuse_putback_request(fc, req);
 }
@@ -163,26 +177,36 @@ void fuse_release_background(struct fuse_req *req)
  * still waiting), the 'end' callback is called if given, else the
  * reference to the request is released
  *
+ * Releasing extra reference for foreground requests must be done
+ * within the same locked region as setting state to finished.  This
+ * is because fuse_reset_request() may be called after request is
+ * finished and it must be the sole possessor.  If request is
+ * interrupted and put in the background, it will return with an error
+ * and hence never be reset and reused.
+ *
  * Called with fuse_lock, unlocks it
  */
 static void request_end(struct fuse_conn *fc, struct fuse_req *req)
 {
-	void (*end) (struct fuse_conn *, struct fuse_req *) = req->end;
-	req->end = NULL;
 	list_del(&req->list);
 	req->state = FUSE_REQ_FINISHED;
-	spin_unlock(&fuse_lock);
-	if (req->background) {
+	if (!req->background) {
+		wake_up(&req->waitq);
+		fuse_put_request_locked(fc, req);
+		spin_unlock(&fuse_lock);
+	} else {
+		void (*end) (struct fuse_conn *, struct fuse_req *) = req->end;
+		req->end = NULL;
+		spin_unlock(&fuse_lock);
 		down_read(&fc->sbput_sem);
 		if (fc->mounted)
 			fuse_release_background(req);
 		up_read(&fc->sbput_sem);
+		if (end)
+			end(fc, req);
+		else
+			fuse_put_request(fc, req);
 	}
-	wake_up(&req->waitq);
-	if (end)
-		end(fc, req);
-	else
-		fuse_put_request(fc, req);
 }
 
 /*
diff --git a/fs/fuse/file.c b/fs/fuse/file.c
index a7ef5e716f3..6f05379b0a0 100644
--- a/fs/fuse/file.c
+++ b/fs/fuse/file.c
@@ -116,9 +116,14 @@ int fuse_open_common(struct inode *inode, struct file *file, int isdir)
 /* Special case for failed iget in CREATE */
 static void fuse_release_end(struct fuse_conn *fc, struct fuse_req *req)
 {
-	u64 nodeid = req->in.h.nodeid;
-	fuse_reset_request(req);
-	fuse_send_forget(fc, req, nodeid, 1);
+	/* If called from end_io_requests(), req has more than one
+	   reference and fuse_reset_request() cannot work */
+	if (fc->connected) {
+		u64 nodeid = req->in.h.nodeid;
+		fuse_reset_request(req);
+		fuse_send_forget(fc, req, nodeid, 1);
+	} else
+		fuse_put_request(fc, req);
 }
 
 void fuse_send_release(struct fuse_conn *fc, struct fuse_file *ff,
@@ -335,9 +340,14 @@ 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/inotify.c b/fs/inotify.c
index 878ccca6121..3041503bde0 100644
--- a/fs/inotify.c
+++ b/fs/inotify.c
@@ -967,7 +967,7 @@ asmlinkage long sys_inotify_add_watch(int fd, const char __user *path, u32 mask)
 		mask_add = 1;
 
 	/* don't let user-space set invalid bits: we don't want flags set */
-	mask &= IN_ALL_EVENTS;
+	mask &= IN_ALL_EVENTS | IN_ONESHOT;
 	if (unlikely(!mask)) {
 		ret = -EINVAL;
 		goto out;
diff --git a/fs/jbd/checkpoint.c b/fs/jbd/checkpoint.c
index e6265a0b56b..543ed543d1e 100644
--- a/fs/jbd/checkpoint.c
+++ b/fs/jbd/checkpoint.c
@@ -24,75 +24,29 @@
 #include <linux/slab.h>
 
 /*
- * Unlink a buffer from a transaction checkpoint list.
+ * Unlink a buffer from a transaction.
  *
  * Called with j_list_lock held.
  */
 
-static void __buffer_unlink_first(struct journal_head *jh)
+static inline void __buffer_unlink(struct journal_head *jh)
 {
 	transaction_t *transaction;
 
 	transaction = jh->b_cp_transaction;
+	jh->b_cp_transaction = NULL;
 
 	jh->b_cpnext->b_cpprev = jh->b_cpprev;
 	jh->b_cpprev->b_cpnext = jh->b_cpnext;
-	if (transaction->t_checkpoint_list == jh) {
+	if (transaction->t_checkpoint_list == jh)
 		transaction->t_checkpoint_list = jh->b_cpnext;
-		if (transaction->t_checkpoint_list == jh)
-			transaction->t_checkpoint_list = NULL;
-	}
-}
-
-/*
- * Unlink a buffer from a transaction checkpoint(io) list.
- *
- * Called with j_list_lock held.
- */
-
-static inline void __buffer_unlink(struct journal_head *jh)
-{
-	transaction_t *transaction;
-
-	transaction = jh->b_cp_transaction;
-
-	__buffer_unlink_first(jh);
-	if (transaction->t_checkpoint_io_list == jh) {
-		transaction->t_checkpoint_io_list = jh->b_cpnext;
-		if (transaction->t_checkpoint_io_list == jh)
-			transaction->t_checkpoint_io_list = NULL;
-	}
-}
-
-/*
- * Move a buffer from the checkpoint list to the checkpoint io list
- *
- * Called with j_list_lock held
- */
-
-static inline void __buffer_relink_io(struct journal_head *jh)
-{
-	transaction_t *transaction;
-
-	transaction = jh->b_cp_transaction;
-	__buffer_unlink_first(jh);
-
-	if (!transaction->t_checkpoint_io_list) {
-		jh->b_cpnext = jh->b_cpprev = jh;
-	} else {
-		jh->b_cpnext = transaction->t_checkpoint_io_list;
-		jh->b_cpprev = transaction->t_checkpoint_io_list->b_cpprev;
-		jh->b_cpprev->b_cpnext = jh;
-		jh->b_cpnext->b_cpprev = jh;
-	}
-	transaction->t_checkpoint_io_list = jh;
+	if (transaction->t_checkpoint_list == jh)
+		transaction->t_checkpoint_list = NULL;
 }
 
 /*
  * Try to release a checkpointed buffer from its transaction.
- * Returns 1 if we released it and 2 if we also released the
- * whole transaction.
- *
+ * Returns 1 if we released it.
  * Requires j_list_lock
  * Called under jbd_lock_bh_state(jh2bh(jh)), and drops it
  */
@@ -103,11 +57,12 @@ static int __try_to_free_cp_buf(struct journal_head *jh)
 
 	if (jh->b_jlist == BJ_None && !buffer_locked(bh) && !buffer_dirty(bh)) {
 		JBUFFER_TRACE(jh, "remove from checkpoint list");
-		ret = __journal_remove_checkpoint(jh) + 1;
+		__journal_remove_checkpoint(jh);
 		jbd_unlock_bh_state(bh);
 		journal_remove_journal_head(bh);
 		BUFFER_TRACE(bh, "release");
 		__brelse(bh);
+		ret = 1;
 	} else {
 		jbd_unlock_bh_state(bh);
 	}
@@ -162,53 +117,83 @@ static void jbd_sync_bh(journal_t *journal, struct buffer_head *bh)
 }
 
 /*
- * Clean up transaction's list of buffers submitted for io.
- * We wait for any pending IO to complete and remove any clean
- * buffers. Note that we take the buffers in the opposite ordering
- * from the one in which they were submitted for IO.
+ * Clean up a transaction's checkpoint list.
+ *
+ * We wait for any pending IO to complete and make sure any clean
+ * buffers are removed from the transaction.
+ *
+ * Return 1 if we performed any actions which might have destroyed the
+ * checkpoint.  (journal_remove_checkpoint() deletes the transaction when
+ * the last checkpoint buffer is cleansed)
  *
  * Called with j_list_lock held.
  */
-
-static void __wait_cp_io(journal_t *journal, transaction_t *transaction)
+static int __cleanup_transaction(journal_t *journal, transaction_t *transaction)
 {
-	struct journal_head *jh;
+	struct journal_head *jh, *next_jh, *last_jh;
 	struct buffer_head *bh;
-	tid_t this_tid;
-	int released = 0;
-
-	this_tid = transaction->t_tid;
-restart:
-	/* Didn't somebody clean up the transaction in the meanwhile */
-	if (journal->j_checkpoint_transactions != transaction ||
-		transaction->t_tid != this_tid)
-		return;
-	while (!released && transaction->t_checkpoint_io_list) {
-		jh = transaction->t_checkpoint_io_list;
+	int ret = 0;
+
+	assert_spin_locked(&journal->j_list_lock);
+	jh = transaction->t_checkpoint_list;
+	if (!jh)
+		return 0;
+
+	last_jh = jh->b_cpprev;
+	next_jh = jh;
+	do {
+		jh = next_jh;
 		bh = jh2bh(jh);
-		if (!jbd_trylock_bh_state(bh)) {
-			jbd_sync_bh(journal, bh);
-			spin_lock(&journal->j_list_lock);
-			goto restart;
-		}
 		if (buffer_locked(bh)) {
 			atomic_inc(&bh->b_count);
 			spin_unlock(&journal->j_list_lock);
-			jbd_unlock_bh_state(bh);
 			wait_on_buffer(bh);
 			/* the journal_head may have gone by now */
 			BUFFER_TRACE(bh, "brelse");
 			__brelse(bh);
-			spin_lock(&journal->j_list_lock);
-			goto restart;
+			goto out_return_1;
 		}
+
 		/*
-		 * Now in whatever state the buffer currently is, we know that
-		 * it has been written out and so we can drop it from the list
+		 * This is foul
 		 */
-		released = __journal_remove_checkpoint(jh);
-		jbd_unlock_bh_state(bh);
-	}
+		if (!jbd_trylock_bh_state(bh)) {
+			jbd_sync_bh(journal, bh);
+			goto out_return_1;
+		}
+
+		if (jh->b_transaction != NULL) {
+			transaction_t *t = jh->b_transaction;
+			tid_t tid = t->t_tid;
+
+			spin_unlock(&journal->j_list_lock);
+			jbd_unlock_bh_state(bh);
+			log_start_commit(journal, tid);
+			log_wait_commit(journal, tid);
+			goto out_return_1;
+		}
+
+		/*
+		 * AKPM: I think the buffer_jbddirty test is redundant - it
+		 * shouldn't have NULL b_transaction?
+		 */
+		next_jh = jh->b_cpnext;
+		if (!buffer_dirty(bh) && !buffer_jbddirty(bh)) {
+			BUFFER_TRACE(bh, "remove from checkpoint");
+			__journal_remove_checkpoint(jh);
+			jbd_unlock_bh_state(bh);
+			journal_remove_journal_head(bh);
+			__brelse(bh);
+			ret = 1;
+		} else {
+			jbd_unlock_bh_state(bh);
+		}
+	} while (jh != last_jh);
+
+	return ret;
+out_return_1:
+	spin_lock(&journal->j_list_lock);
+	return 1;
 }
 
 #define NR_BATCH	64
@@ -218,7 +203,9 @@ __flush_batch(journal_t *journal, struct buffer_head **bhs, int *batch_count)
 {
 	int i;
 
+	spin_unlock(&journal->j_list_lock);
 	ll_rw_block(SWRITE, *batch_count, bhs);
+	spin_lock(&journal->j_list_lock);
 	for (i = 0; i < *batch_count; i++) {
 		struct buffer_head *bh = bhs[i];
 		clear_buffer_jwrite(bh);
@@ -234,46 +221,19 @@ __flush_batch(journal_t *journal, struct buffer_head **bhs, int *batch_count)
  * Return 1 if something happened which requires us to abort the current
  * scan of the checkpoint list.  
  *
- * Called with j_list_lock held and drops it if 1 is returned
+ * Called with j_list_lock held.
  * Called under jbd_lock_bh_state(jh2bh(jh)), and drops it
  */
-static int __process_buffer(journal_t *journal, struct journal_head *jh,
-			struct buffer_head **bhs, int *batch_count)
+static int __flush_buffer(journal_t *journal, struct journal_head *jh,
+			struct buffer_head **bhs, int *batch_count,
+			int *drop_count)
 {
 	struct buffer_head *bh = jh2bh(jh);
 	int ret = 0;
 
-	if (buffer_locked(bh)) {
-		get_bh(bh);
-		spin_unlock(&journal->j_list_lock);
-		jbd_unlock_bh_state(bh);
-		wait_on_buffer(bh);
-		/* the journal_head may have gone by now */
-		BUFFER_TRACE(bh, "brelse");
-		put_bh(bh);
-		ret = 1;
-	}
-	else if (jh->b_transaction != NULL) {
-		transaction_t *t = jh->b_transaction;
-		tid_t tid = t->t_tid;
+	if (buffer_dirty(bh) && !buffer_locked(bh) && jh->b_jlist == BJ_None) {
+		J_ASSERT_JH(jh, jh->b_transaction == NULL);
 
-		spin_unlock(&journal->j_list_lock);
-		jbd_unlock_bh_state(bh);
-		log_start_commit(journal, tid);
-		log_wait_commit(journal, tid);
-		ret = 1;
-	}
-	else if (!buffer_dirty(bh)) {
-		J_ASSERT_JH(jh, !buffer_jbddirty(bh));
-		BUFFER_TRACE(bh, "remove from checkpoint");
-		__journal_remove_checkpoint(jh);
-		spin_unlock(&journal->j_list_lock);
-		jbd_unlock_bh_state(bh);
-		journal_remove_journal_head(bh);
-		put_bh(bh);
-		ret = 1;
-	}
-	else {
 		/*
 		 * Important: we are about to write the buffer, and
 		 * possibly block, while still holding the journal lock.
@@ -286,30 +246,45 @@ static int __process_buffer(journal_t *journal, struct journal_head *jh,
 		J_ASSERT_BH(bh, !buffer_jwrite(bh));
 		set_buffer_jwrite(bh);
 		bhs[*batch_count] = bh;
-		__buffer_relink_io(jh);
 		jbd_unlock_bh_state(bh);
 		(*batch_count)++;
 		if (*batch_count == NR_BATCH) {
-			spin_unlock(&journal->j_list_lock);
 			__flush_batch(journal, bhs, batch_count);
 			ret = 1;
 		}
+	} else {
+		int last_buffer = 0;
+		if (jh->b_cpnext == jh) {
+			/* We may be about to drop the transaction.  Tell the
+			 * caller that the lists have changed.
+			 */
+			last_buffer = 1;
+		}
+		if (__try_to_free_cp_buf(jh)) {
+			(*drop_count)++;
+			ret = last_buffer;
+		}
 	}
 	return ret;
 }
 
 /*
- * Perform an actual checkpoint. We take the first transaction on the
- * list of transactions to be checkpointed and send all its buffers
- * to disk. We submit larger chunks of data at once.
+ * Perform an actual checkpoint.  We don't write out only enough to
+ * satisfy the current blocked requests: rather we submit a reasonably
+ * sized chunk of the outstanding data to disk at once for
+ * efficiency.  __log_wait_for_space() will retry if we didn't free enough.
  * 
+ * However, we _do_ take into account the amount requested so that once
+ * the IO has been queued, we can return as soon as enough of it has
+ * completed to disk.
+ *
  * The journal should be locked before calling this function.
  */
 int log_do_checkpoint(journal_t *journal)
 {
-	transaction_t *transaction;
-	tid_t this_tid;
 	int result;
+	int batch_count = 0;
+	struct buffer_head *bhs[NR_BATCH];
 
 	jbd_debug(1, "Start checkpoint\n");
 
@@ -324,70 +299,79 @@ int log_do_checkpoint(journal_t *journal)
 		return result;
 
 	/*
-	 * OK, we need to start writing disk blocks.  Take one transaction
-	 * and write it.
+	 * OK, we need to start writing disk blocks.  Try to free up a
+	 * quarter of the log in a single checkpoint if we can.
 	 */
-	spin_lock(&journal->j_list_lock);
-	if (!journal->j_checkpoint_transactions)
-		goto out;
-	transaction = journal->j_checkpoint_transactions;
-	this_tid = transaction->t_tid;
-restart:
 	/*
-	 * If someone cleaned up this transaction while we slept, we're
-	 * done (maybe it's a new transaction, but it fell at the same
-	 * address).
+	 * AKPM: check this code.  I had a feeling a while back that it
+	 * degenerates into a busy loop at unmount time.
 	 */
- 	if (journal->j_checkpoint_transactions == transaction &&
-			transaction->t_tid == this_tid) {
-		int batch_count = 0;
-		struct buffer_head *bhs[NR_BATCH];
-		struct journal_head *jh;
-		int retry = 0;
-
-		while (!retry && transaction->t_checkpoint_list) {
+	spin_lock(&journal->j_list_lock);
+	while (journal->j_checkpoint_transactions) {
+		transaction_t *transaction;
+		struct journal_head *jh, *last_jh, *next_jh;
+		int drop_count = 0;
+		int cleanup_ret, retry = 0;
+		tid_t this_tid;
+
+		transaction = journal->j_checkpoint_transactions;
+		this_tid = transaction->t_tid;
+		jh = transaction->t_checkpoint_list;
+		last_jh = jh->b_cpprev;
+		next_jh = jh;
+		do {
 			struct buffer_head *bh;
 
-			jh = transaction->t_checkpoint_list;
+			jh = next_jh;
+			next_jh = jh->b_cpnext;
 			bh = jh2bh(jh);
 			if (!jbd_trylock_bh_state(bh)) {
 				jbd_sync_bh(journal, bh);
+				spin_lock(&journal->j_list_lock);
 				retry = 1;
 				break;
 			}
-			retry = __process_buffer(journal, jh, bhs,
-						&batch_count);
-			if (!retry &&
-			    lock_need_resched(&journal->j_list_lock)) {
-				spin_unlock(&journal->j_list_lock);
+			retry = __flush_buffer(journal, jh, bhs, &batch_count, &drop_count);
+			if (cond_resched_lock(&journal->j_list_lock)) {
 				retry = 1;
 				break;
 			}
-		}
+		} while (jh != last_jh && !retry);
 
 		if (batch_count) {
-			if (!retry) {
-				spin_unlock(&journal->j_list_lock);
-				retry = 1;
-			}
 			__flush_batch(journal, bhs, &batch_count);
+			retry = 1;
 		}
 
-		if (retry) {
-			spin_lock(&journal->j_list_lock);
-			goto restart;
-		}
 		/*
-		 * Now we have cleaned up the first transaction's checkpoint
-		 * list.  Let's clean up the second one.
+		 * If someone cleaned up this transaction while we slept, we're
+		 * done
+		 */
+		if (journal->j_checkpoint_transactions != transaction)
+			break;
+		if (retry)
+			continue;
+		/*
+		 * Maybe it's a new transaction, but it fell at the same
+		 * address
 		 */
-		__wait_cp_io(journal, transaction);
+		if (transaction->t_tid != this_tid)
+			continue;
+		/*
+		 * We have walked the whole transaction list without
+		 * finding anything to write to disk.  We had better be
+		 * able to make some progress or we are in trouble.
+		 */
+		cleanup_ret = __cleanup_transaction(journal, transaction);
+		J_ASSERT(drop_count != 0 || cleanup_ret != 0);
+		if (journal->j_checkpoint_transactions != transaction)
+			break;
 	}
-out:
 	spin_unlock(&journal->j_list_lock);
 	result = cleanup_journal_tail(journal);
 	if (result < 0)
 		return result;
+
 	return 0;
 }
 
@@ -472,91 +456,52 @@ int cleanup_journal_tail(journal_t *journal)
 /* Checkpoint list management */
 
 /*
- * journal_clean_one_cp_list
- *
- * Find all the written-back checkpoint buffers in the given list and release them.
- *
- * Called with the journal locked.
- * Called with j_list_lock held.
- * Returns number of bufers reaped (for debug)
- */
-
-static int journal_clean_one_cp_list(struct journal_head *jh, int *released)
-{
-	struct journal_head *last_jh;
-	struct journal_head *next_jh = jh;
-	int ret, freed = 0;
-
-	*released = 0;
-	if (!jh)
-		return 0;
-
- 	last_jh = jh->b_cpprev;
-	do {
-		jh = next_jh;
-		next_jh = jh->b_cpnext;
-		/* Use trylock because of the ranking */
-		if (jbd_trylock_bh_state(jh2bh(jh))) {
-			ret = __try_to_free_cp_buf(jh);
-			if (ret) {
-				freed++;
-				if (ret == 2) {
-					*released = 1;
-					return freed;
-				}
-			}
-		}
-		/*
-		 * This function only frees up some memory if possible so we
-		 * dont have an obligation to finish processing. Bail out if
-		 * preemption requested:
-		 */
-		if (need_resched())
-			return freed;
-	} while (jh != last_jh);
-
-	return freed;
-}
-
-/*
  * journal_clean_checkpoint_list
  *
  * Find all the written-back checkpoint buffers in the journal and release them.
  *
  * Called with the journal locked.
  * Called with j_list_lock held.
- * Returns number of buffers reaped (for debug)
+ * Returns number of bufers reaped (for debug)
  */
 
 int __journal_clean_checkpoint_list(journal_t *journal)
 {
 	transaction_t *transaction, *last_transaction, *next_transaction;
-	int ret = 0, released;
+	int ret = 0;
 
 	transaction = journal->j_checkpoint_transactions;
-	if (!transaction)
+	if (transaction == 0)
 		goto out;
 
 	last_transaction = transaction->t_cpprev;
 	next_transaction = transaction;
 	do {
+		struct journal_head *jh;
+
 		transaction = next_transaction;
 		next_transaction = transaction->t_cpnext;
-		ret += journal_clean_one_cp_list(transaction->
-				t_checkpoint_list, &released);
-		if (need_resched())
-			goto out;
-		if (released)
-			continue;
-		/*
-		 * It is essential that we are as careful as in the case of
-		 * t_checkpoint_list with removing the buffer from the list as
-		 * we can possibly see not yet submitted buffers on io_list
-		 */
-		ret += journal_clean_one_cp_list(transaction->
-				t_checkpoint_io_list, &released);
-		if (need_resched())
-			goto out;
+		jh = transaction->t_checkpoint_list;
+		if (jh) {
+			struct journal_head *last_jh = jh->b_cpprev;
+			struct journal_head *next_jh = jh;
+
+			do {
+				jh = next_jh;
+				next_jh = jh->b_cpnext;
+				/* Use trylock because of the ranknig */
+				if (jbd_trylock_bh_state(jh2bh(jh)))
+					ret += __try_to_free_cp_buf(jh);
+				/*
+				 * This function only frees up some memory
+				 * if possible so we dont have an obligation
+				 * to finish processing. Bail out if preemption
+				 * requested:
+				 */
+				if (need_resched())
+					goto out;
+			} while (jh != last_jh);
+		}
 	} while (transaction != last_transaction);
 out:
 	return ret;
@@ -571,22 +516,18 @@ out:
  * buffer updates committed in that transaction have safely been stored
  * elsewhere on disk.  To achieve this, all of the buffers in a
  * transaction need to be maintained on the transaction's checkpoint
- * lists until they have been rewritten, at which point this function is
+ * list until they have been rewritten, at which point this function is
  * called to remove the buffer from the existing transaction's
- * checkpoint lists.
- *
- * The function returns 1 if it frees the transaction, 0 otherwise.
+ * checkpoint list.
  *
  * This function is called with the journal locked.
  * This function is called with j_list_lock held.
- * This function is called with jbd_lock_bh_state(jh2bh(jh))
  */
 
-int __journal_remove_checkpoint(struct journal_head *jh)
+void __journal_remove_checkpoint(struct journal_head *jh)
 {
 	transaction_t *transaction;
 	journal_t *journal;
-	int ret = 0;
 
 	JBUFFER_TRACE(jh, "entry");
 
@@ -597,10 +538,8 @@ int __journal_remove_checkpoint(struct journal_head *jh)
 	journal = transaction->t_journal;
 
 	__buffer_unlink(jh);
-	jh->b_cp_transaction = NULL;
 
-	if (transaction->t_checkpoint_list != NULL ||
-	    transaction->t_checkpoint_io_list != NULL)
+	if (transaction->t_checkpoint_list != NULL)
 		goto out;
 	JBUFFER_TRACE(jh, "transaction has no more buffers");
 
@@ -626,10 +565,8 @@ int __journal_remove_checkpoint(struct journal_head *jh)
 	/* Just in case anybody was waiting for more transactions to be
            checkpointed... */
 	wake_up(&journal->j_wait_logspace);
-	ret = 1;
 out:
 	JBUFFER_TRACE(jh, "exit");
-	return ret;
 }
 
 /*
@@ -691,7 +628,6 @@ void __journal_drop_transaction(journal_t *journal, transaction_t *transaction)
 	J_ASSERT(transaction->t_shadow_list == NULL);
 	J_ASSERT(transaction->t_log_list == NULL);
 	J_ASSERT(transaction->t_checkpoint_list == NULL);
-	J_ASSERT(transaction->t_checkpoint_io_list == NULL);
 	J_ASSERT(transaction->t_updates == 0);
 	J_ASSERT(journal->j_committing_transaction != transaction);
 	J_ASSERT(journal->j_running_transaction != transaction);
diff --git a/fs/jbd/commit.c b/fs/jbd/commit.c
index 29e62d98bae..002ad2bbc76 100644
--- a/fs/jbd/commit.c
+++ b/fs/jbd/commit.c
@@ -829,8 +829,7 @@ restart_loop:
 	journal->j_committing_transaction = NULL;
 	spin_unlock(&journal->j_state_lock);
 
-	if (commit_transaction->t_checkpoint_list == NULL &&
-	    commit_transaction->t_checkpoint_io_list == NULL) {
+	if (commit_transaction->t_checkpoint_list == NULL) {
 		__journal_drop_transaction(journal, commit_transaction);
 	} else {
 		if (journal->j_checkpoint_transactions == NULL) {
diff --git a/fs/jbd/transaction.c b/fs/jbd/transaction.c
index 429f4b263cf..ca917973c2c 100644
--- a/fs/jbd/transaction.c
+++ b/fs/jbd/transaction.c
@@ -1308,6 +1308,7 @@ int journal_stop(handle_t *handle)
 	transaction_t *transaction = handle->h_transaction;
 	journal_t *journal = transaction->t_journal;
 	int old_handle_count, err;
+	pid_t pid;
 
 	J_ASSERT(transaction->t_updates > 0);
 	J_ASSERT(journal_current_handle() == handle);
@@ -1333,8 +1334,15 @@ int journal_stop(handle_t *handle)
 	 * It doesn't cost much - we're about to run a commit and sleep
 	 * on IO anyway.  Speeds up many-threaded, many-dir operations
 	 * by 30x or more...
+	 *
+	 * But don't do this if this process was the most recent one to
+	 * perform a synchronous write.  We do this to detect the case where a
+	 * single process is doing a stream of sync writes.  No point in waiting
+	 * for joiners in that case.
 	 */
-	if (handle->h_sync) {
+	pid = current->pid;
+	if (handle->h_sync && journal->j_last_sync_writer != pid) {
+		journal->j_last_sync_writer = pid;
 		do {
 			old_handle_count = transaction->t_handle_count;
 			schedule_timeout_uninterruptible(1);
diff --git a/fs/jffs/intrep.c b/fs/jffs/intrep.c
index b2e95421d93..ce7b54b0b2b 100644
--- a/fs/jffs/intrep.c
+++ b/fs/jffs/intrep.c
@@ -1965,7 +1965,7 @@ retry:
 		iovec_cnt++;
 
 		if (JFFS_GET_PAD_BYTES(raw_inode->nsize)) {
-			static char allff[3]={255,255,255};
+			static unsigned char allff[3]={255,255,255};
 			/* Add some extra padding if necessary */
 			node_iovec[iovec_cnt].iov_base = allff;
 			node_iovec[iovec_cnt].iov_len =
diff --git a/fs/libfs.c b/fs/libfs.c
index 63c020e6589..71fd08fa410 100644
--- a/fs/libfs.c
+++ b/fs/libfs.c
@@ -388,6 +388,7 @@ int simple_fill_super(struct super_block *s, int magic, struct tree_descr *files
 	inode->i_atime = inode->i_mtime = inode->i_ctime = CURRENT_TIME;
 	inode->i_op = &simple_dir_inode_operations;
 	inode->i_fop = &simple_dir_operations;
+	inode->i_nlink = 2;
 	root = d_alloc_root(inode);
 	if (!root) {
 		iput(inode);
diff --git a/fs/lockd/clntlock.c b/fs/lockd/clntlock.c
index 3eaf6e70108..da6354baa0b 100644
--- a/fs/lockd/clntlock.c
+++ b/fs/lockd/clntlock.c
@@ -111,9 +111,10 @@ long nlmclnt_block(struct nlm_rqst *req, long timeout)
 /*
  * The server lockd has called us back to tell us the lock was granted
  */
-u32
-nlmclnt_grant(struct nlm_lock *lock)
+u32 nlmclnt_grant(const struct sockaddr_in *addr, const struct nlm_lock *lock)
 {
+	const struct file_lock *fl = &lock->fl;
+	const struct nfs_fh *fh = &lock->fh;
 	struct nlm_wait	*block;
 	u32 res = nlm_lck_denied;
 
@@ -122,14 +123,20 @@ nlmclnt_grant(struct nlm_lock *lock)
 	 * Warning: must not use cookie to match it!
 	 */
 	list_for_each_entry(block, &nlm_blocked, b_list) {
-		if (nlm_compare_locks(block->b_lock, &lock->fl)) {
-			/* Alright, we found a lock. Set the return status
-			 * and wake up the caller
-			 */
-			block->b_status = NLM_LCK_GRANTED;
-			wake_up(&block->b_wait);
-			res = nlm_granted;
-		}
+		struct file_lock *fl_blocked = block->b_lock;
+
+		if (!nlm_compare_locks(fl_blocked, fl))
+			continue;
+		if (!nlm_cmp_addr(&block->b_host->h_addr, addr))
+			continue;
+		if (nfs_compare_fh(NFS_FH(fl_blocked->fl_file->f_dentry->d_inode) ,fh) != 0)
+			continue;
+		/* Alright, we found a lock. Set the return status
+		 * and wake up the caller
+		 */
+		block->b_status = NLM_LCK_GRANTED;
+		wake_up(&block->b_wait);
+		res = nlm_granted;
 	}
 	return res;
 }
diff --git a/fs/lockd/clntproc.c b/fs/lockd/clntproc.c
index 14552403957..220058d8616 100644
--- a/fs/lockd/clntproc.c
+++ b/fs/lockd/clntproc.c
@@ -22,12 +22,14 @@
 #define NLMDBG_FACILITY		NLMDBG_CLIENT
 #define NLMCLNT_GRACE_WAIT	(5*HZ)
 #define NLMCLNT_POLL_TIMEOUT	(30*HZ)
+#define NLMCLNT_MAX_RETRIES	3
 
 static int	nlmclnt_test(struct nlm_rqst *, struct file_lock *);
 static int	nlmclnt_lock(struct nlm_rqst *, struct file_lock *);
 static int	nlmclnt_unlock(struct nlm_rqst *, struct file_lock *);
 static int	nlm_stat_to_errno(u32 stat);
 static void	nlmclnt_locks_init_private(struct file_lock *fl, struct nlm_host *host);
+static int	nlmclnt_cancel(struct nlm_host *, int , struct file_lock *);
 
 static const struct rpc_call_ops nlmclnt_unlock_ops;
 static const struct rpc_call_ops nlmclnt_cancel_ops;
@@ -598,7 +600,7 @@ out_unblock:
 	nlmclnt_finish_block(req);
 	/* Cancel the blocked request if it is still pending */
 	if (resp->status == NLM_LCK_BLOCKED)
-		nlmclnt_cancel(host, fl);
+		nlmclnt_cancel(host, req->a_args.block, fl);
 out:
 	nlmclnt_release_lockargs(req);
 	return status;
@@ -728,8 +730,7 @@ static const struct rpc_call_ops nlmclnt_unlock_ops = {
  * We always use an async RPC call for this in order not to hang a
  * process that has been Ctrl-C'ed.
  */
-int
-nlmclnt_cancel(struct nlm_host *host, struct file_lock *fl)
+static int nlmclnt_cancel(struct nlm_host *host, int block, struct file_lock *fl)
 {
 	struct nlm_rqst	*req;
 	unsigned long	flags;
@@ -750,6 +751,7 @@ nlmclnt_cancel(struct nlm_host *host, struct file_lock *fl)
 	req->a_flags = RPC_TASK_ASYNC;
 
 	nlmclnt_setlockargs(req, fl);
+	req->a_args.block = block;
 
 	status = nlmclnt_async_call(req, NLMPROC_CANCEL, &nlmclnt_cancel_ops);
 	if (status < 0) {
@@ -801,6 +803,9 @@ die:
 	return;
 
 retry_cancel:
+	/* Don't ever retry more than 3 times */
+	if (req->a_retries++ >= NLMCLNT_MAX_RETRIES)
+		goto die;
 	nlm_rebind_host(req->a_host);
 	rpc_restart_call(task);
 	rpc_delay(task, 30 * HZ);
diff --git a/fs/lockd/svc4proc.c b/fs/lockd/svc4proc.c
index 4063095d849..b10f913aa06 100644
--- a/fs/lockd/svc4proc.c
+++ b/fs/lockd/svc4proc.c
@@ -228,7 +228,7 @@ nlm4svc_proc_granted(struct svc_rqst *rqstp, struct nlm_args *argp,
 	resp->cookie = argp->cookie;
 
 	dprintk("lockd: GRANTED       called\n");
-	resp->status = nlmclnt_grant(&argp->lock);
+	resp->status = nlmclnt_grant(&rqstp->rq_addr, &argp->lock);
 	dprintk("lockd: GRANTED       status %d\n", ntohl(resp->status));
 	return rpc_success;
 }
diff --git a/fs/lockd/svcproc.c b/fs/lockd/svcproc.c
index 3bc437e0cf5..35681d9cf1f 100644
--- a/fs/lockd/svcproc.c
+++ b/fs/lockd/svcproc.c
@@ -256,7 +256,7 @@ nlmsvc_proc_granted(struct svc_rqst *rqstp, struct nlm_args *argp,
 	resp->cookie = argp->cookie;
 
 	dprintk("lockd: GRANTED       called\n");
-	resp->status = nlmclnt_grant(&argp->lock);
+	resp->status = nlmclnt_grant(&rqstp->rq_addr, &argp->lock);
 	dprintk("lockd: GRANTED       status %d\n", ntohl(resp->status));
 	return rpc_success;
 }
diff --git a/fs/namei.c b/fs/namei.c
index 4acdac043b6..e28de846c59 100644
--- a/fs/namei.c
+++ b/fs/namei.c
@@ -790,7 +790,7 @@ static fastcall int __link_path_walk(const char * name, struct nameidata *nd)
 
 	inode = nd->dentry->d_inode;
 	if (nd->depth)
-		lookup_flags = LOOKUP_FOLLOW;
+		lookup_flags = LOOKUP_FOLLOW | (nd->flags & LOOKUP_CONTINUE);
 
 	/* At this point we know we have a real path component. */
 	for(;;) {
@@ -885,7 +885,8 @@ static fastcall int __link_path_walk(const char * name, struct nameidata *nd)
 last_with_slashes:
 		lookup_flags |= LOOKUP_FOLLOW | LOOKUP_DIRECTORY;
 last_component:
-		nd->flags &= ~LOOKUP_CONTINUE;
+		/* Clear LOOKUP_CONTINUE iff it was previously unset */
+		nd->flags &= lookup_flags | ~LOOKUP_CONTINUE;
 		if (lookup_flags & LOOKUP_PARENT)
 			goto lookup_parent;
 		if (this.name[0] == '.') switch (this.len) {
@@ -1069,6 +1070,8 @@ static int fastcall do_path_lookup(int dfd, const char *name,
 				unsigned int flags, struct nameidata *nd)
 {
 	int retval = 0;
+	int fput_needed;
+	struct file *file;
 
 	nd->last_type = LAST_ROOT; /* if there are only slashes... */
 	nd->flags = flags;
@@ -1090,29 +1093,22 @@ static int fastcall do_path_lookup(int dfd, const char *name,
 		nd->mnt = mntget(current->fs->pwdmnt);
 		nd->dentry = dget(current->fs->pwd);
 	} else {
-		struct file *file;
-		int fput_needed;
 		struct dentry *dentry;
 
 		file = fget_light(dfd, &fput_needed);
-		if (!file) {
-			retval = -EBADF;
-			goto out_fail;
-		}
+		retval = -EBADF;
+		if (!file)
+			goto unlock_fail;
 
 		dentry = file->f_dentry;
 
-		if (!S_ISDIR(dentry->d_inode->i_mode)) {
-			retval = -ENOTDIR;
-			fput_light(file, fput_needed);
-			goto out_fail;
-		}
+		retval = -ENOTDIR;
+		if (!S_ISDIR(dentry->d_inode->i_mode))
+			goto fput_unlock_fail;
 
 		retval = file_permission(file, MAY_EXEC);
-		if (retval) {
-			fput_light(file, fput_needed);
-			goto out_fail;
-		}
+		if (retval)
+			goto fput_unlock_fail;
 
 		nd->mnt = mntget(file->f_vfsmnt);
 		nd->dentry = dget(dentry);
@@ -1123,10 +1119,17 @@ static int fastcall do_path_lookup(int dfd, const char *name,
 	current->total_link_count = 0;
 	retval = link_path_walk(name, nd);
 out:
-	if (unlikely(current->audit_context
-		     && nd && nd->dentry && nd->dentry->d_inode))
+	if (likely(retval == 0)) {
+		if (unlikely(current->audit_context && nd && nd->dentry &&
+				nd->dentry->d_inode))
 		audit_inode(name, nd->dentry->d_inode, flags);
-out_fail:
+	}
+	return retval;
+
+fput_unlock_fail:
+	fput_light(file, fput_needed);
+unlock_fail:
+	read_unlock(&current->fs->lock);
 	return retval;
 }
 
@@ -1161,6 +1164,7 @@ 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 +1179,7 @@ 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/namespace.c b/fs/namespace.c
index ce97becff46..058a44865be 100644
--- a/fs/namespace.c
+++ b/fs/namespace.c
@@ -494,7 +494,7 @@ void umount_tree(struct vfsmount *mnt, int propagate, struct list_head *kill)
 		p->mnt_namespace = NULL;
 		list_del_init(&p->mnt_child);
 		if (p->mnt_parent != p)
-			mnt->mnt_mountpoint->d_mounted--;
+			p->mnt_mountpoint->d_mounted--;
 		change_mnt_propagation(p, MS_PRIVATE);
 	}
 }
@@ -1325,27 +1325,17 @@ dput_out:
 	return retval;
 }
 
-int copy_namespace(int flags, struct task_struct *tsk)
+/*
+ * Allocate a new namespace structure and populate it with contents
+ * copied from the namespace of the passed in task structure.
+ */
+struct namespace *dup_namespace(struct task_struct *tsk, struct fs_struct *fs)
 {
 	struct namespace *namespace = tsk->namespace;
 	struct namespace *new_ns;
 	struct vfsmount *rootmnt = NULL, *pwdmnt = NULL, *altrootmnt = NULL;
-	struct fs_struct *fs = tsk->fs;
 	struct vfsmount *p, *q;
 
-	if (!namespace)
-		return 0;
-
-	get_namespace(namespace);
-
-	if (!(flags & CLONE_NEWNS))
-		return 0;
-
-	if (!capable(CAP_SYS_ADMIN)) {
-		put_namespace(namespace);
-		return -EPERM;
-	}
-
 	new_ns = kmalloc(sizeof(struct namespace), GFP_KERNEL);
 	if (!new_ns)
 		goto out;
@@ -1396,8 +1386,6 @@ int copy_namespace(int flags, struct task_struct *tsk)
 	}
 	up_write(&namespace_sem);
 
-	tsk->namespace = new_ns;
-
 	if (rootmnt)
 		mntput(rootmnt);
 	if (pwdmnt)
@@ -1405,12 +1393,40 @@ int copy_namespace(int flags, struct task_struct *tsk)
 	if (altrootmnt)
 		mntput(altrootmnt);
 
-	put_namespace(namespace);
-	return 0;
+out:
+	return new_ns;
+}
+
+int copy_namespace(int flags, struct task_struct *tsk)
+{
+	struct namespace *namespace = tsk->namespace;
+	struct namespace *new_ns;
+	int err = 0;
+
+	if (!namespace)
+		return 0;
+
+	get_namespace(namespace);
+
+	if (!(flags & CLONE_NEWNS))
+		return 0;
+
+	if (!capable(CAP_SYS_ADMIN)) {
+		err = -EPERM;
+		goto out;
+	}
+
+	new_ns = dup_namespace(tsk, tsk->fs);
+	if (!new_ns) {
+		err = -ENOMEM;
+		goto out;
+	}
+
+	tsk->namespace = new_ns;
 
 out:
 	put_namespace(namespace);
-	return -ENOMEM;
+	return err;
 }
 
 asmlinkage long sys_mount(char __user * dev_name, char __user * dir_name,
diff --git a/fs/nfs/direct.c b/fs/nfs/direct.c
index 10ae377e68f..04ab2fc360e 100644
--- a/fs/nfs/direct.c
+++ b/fs/nfs/direct.c
@@ -481,7 +481,7 @@ retry:
 		if (wdata->verf.committed != NFS_FILE_SYNC) {
 			need_commit = 1;
 			if (memcmp(&first_verf.verifier, &wdata->verf.verifier,
-					sizeof(first_verf.verifier)));
+					sizeof(first_verf.verifier)))
 				goto sync_retry;
 		}
 
diff --git a/fs/nfs/nfsroot.c b/fs/nfs/nfsroot.c
index e897e00c2c9..c0a754ecdee 100644
--- a/fs/nfs/nfsroot.c
+++ b/fs/nfs/nfsroot.c
@@ -465,10 +465,11 @@ static int __init root_nfs_ports(void)
 					"number from server, using default\n");
 			port = nfsd_port;
 		}
-		nfs_port = htons(port);
+		nfs_port = port;
 		dprintk("Root-NFS: Portmapper on server returned %d "
 			"as nfsd port\n", port);
 	}
+	nfs_port = htons(nfs_port);
 
 	if ((port = root_nfs_getport(NFS_MNT_PROGRAM, mountd_ver, proto)) < 0) {
 		printk(KERN_ERR "Root-NFS: Unable to get mountd port "
diff --git a/fs/nfsd/nfs4proc.c b/fs/nfsd/nfs4proc.c
index a00fe868629..6d63f1d9e5f 100644
--- a/fs/nfsd/nfs4proc.c
+++ b/fs/nfsd/nfs4proc.c
@@ -195,10 +195,12 @@ nfsd4_open(struct svc_rqst *rqstp, struct svc_fh *current_fh, struct nfsd4_open
 
 	/* Openowner is now set, so sequence id will get bumped.  Now we need
 	 * these checks before we do any creates: */
+	status = nfserr_grace;
 	if (nfs4_in_grace() && open->op_claim_type != NFS4_OPEN_CLAIM_PREVIOUS)
-		return nfserr_grace;
+		goto out;
+	status = nfserr_no_grace;
 	if (!nfs4_in_grace() && open->op_claim_type == NFS4_OPEN_CLAIM_PREVIOUS)
-		return nfserr_no_grace;
+		goto out;
 
 	switch (open->op_claim_type) {
 		case NFS4_OPEN_CLAIM_DELEGATE_CUR:
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/ocfs2/buffer_head_io.c b/fs/ocfs2/buffer_head_io.c
index d424041b38e..bae3d7548be 100644
--- a/fs/ocfs2/buffer_head_io.c
+++ b/fs/ocfs2/buffer_head_io.c
@@ -58,7 +58,7 @@ int ocfs2_write_block(struct ocfs2_super *osb, struct buffer_head *bh,
 		goto out;
 	}
 
-	down(&OCFS2_I(inode)->ip_io_sem);
+	mutex_lock(&OCFS2_I(inode)->ip_io_mutex);
 
 	lock_buffer(bh);
 	set_buffer_uptodate(bh);
@@ -82,7 +82,7 @@ int ocfs2_write_block(struct ocfs2_super *osb, struct buffer_head *bh,
 		brelse(bh);
 	}
 
-	up(&OCFS2_I(inode)->ip_io_sem);
+	mutex_unlock(&OCFS2_I(inode)->ip_io_mutex);
 out:
 	mlog_exit(ret);
 	return ret;
@@ -125,13 +125,13 @@ int ocfs2_read_blocks(struct ocfs2_super *osb, u64 block, int nr,
 		flags &= ~OCFS2_BH_CACHED;
 
 	if (inode)
-		down(&OCFS2_I(inode)->ip_io_sem);
+		mutex_lock(&OCFS2_I(inode)->ip_io_mutex);
 	for (i = 0 ; i < nr ; i++) {
 		if (bhs[i] == NULL) {
 			bhs[i] = sb_getblk(sb, block++);
 			if (bhs[i] == NULL) {
 				if (inode)
-					up(&OCFS2_I(inode)->ip_io_sem);
+					mutex_unlock(&OCFS2_I(inode)->ip_io_mutex);
 				status = -EIO;
 				mlog_errno(status);
 				goto bail;
@@ -220,7 +220,7 @@ int ocfs2_read_blocks(struct ocfs2_super *osb, u64 block, int nr,
 			ocfs2_set_buffer_uptodate(inode, bh);
 	}
 	if (inode)
-		up(&OCFS2_I(inode)->ip_io_sem);
+		mutex_unlock(&OCFS2_I(inode)->ip_io_mutex);
 
 	mlog(ML_BH_IO, "block=(%"MLFu64"), nr=(%d), cached=%s\n", block, nr,
 	     (!(flags & OCFS2_BH_CACHED) || ignore_cache) ? "no" : "yes");
diff --git a/fs/ocfs2/cluster/heartbeat.c b/fs/ocfs2/cluster/heartbeat.c
index 7307ba52891..d08971d29b6 100644
--- a/fs/ocfs2/cluster/heartbeat.c
+++ b/fs/ocfs2/cluster/heartbeat.c
@@ -917,8 +917,9 @@ static int o2hb_thread(void *data)
 		elapsed_msec = o2hb_elapsed_msecs(&before_hb, &after_hb);
 
 		mlog(0, "start = %lu.%lu, end = %lu.%lu, msec = %u\n",
-		     before_hb.tv_sec, before_hb.tv_usec,
-		     after_hb.tv_sec, after_hb.tv_usec, elapsed_msec);
+		     before_hb.tv_sec, (unsigned long) before_hb.tv_usec,
+		     after_hb.tv_sec, (unsigned long) after_hb.tv_usec,
+		     elapsed_msec);
 
 		if (elapsed_msec < reg->hr_timeout_ms) {
 			/* the kthread api has blocked signals for us so no
diff --git a/fs/ocfs2/cluster/tcp.c b/fs/ocfs2/cluster/tcp.c
index 35d92c01a97..d22d4cf08db 100644
--- a/fs/ocfs2/cluster/tcp.c
+++ b/fs/ocfs2/cluster/tcp.c
@@ -1285,14 +1285,16 @@ static void o2net_idle_timer(unsigned long data)
 	mlog(ML_NOTICE, "here are some times that might help debug the "
 	     "situation: (tmr %ld.%ld now %ld.%ld dr %ld.%ld adv "
 	     "%ld.%ld:%ld.%ld func (%08x:%u) %ld.%ld:%ld.%ld)\n",
-	     sc->sc_tv_timer.tv_sec, sc->sc_tv_timer.tv_usec, 
-	     now.tv_sec, now.tv_usec,
-	     sc->sc_tv_data_ready.tv_sec, sc->sc_tv_data_ready.tv_usec, 
-	     sc->sc_tv_advance_start.tv_sec, sc->sc_tv_advance_start.tv_usec, 
-	     sc->sc_tv_advance_stop.tv_sec, sc->sc_tv_advance_stop.tv_usec, 
+	     sc->sc_tv_timer.tv_sec, (long) sc->sc_tv_timer.tv_usec, 
+	     now.tv_sec, (long) now.tv_usec,
+	     sc->sc_tv_data_ready.tv_sec, (long) sc->sc_tv_data_ready.tv_usec,
+	     sc->sc_tv_advance_start.tv_sec,
+	     (long) sc->sc_tv_advance_start.tv_usec,
+	     sc->sc_tv_advance_stop.tv_sec,
+	     (long) sc->sc_tv_advance_stop.tv_usec,
 	     sc->sc_msg_key, sc->sc_msg_type,
-	     sc->sc_tv_func_start.tv_sec, sc->sc_tv_func_start.tv_usec,
-	     sc->sc_tv_func_stop.tv_sec, sc->sc_tv_func_stop.tv_usec);
+	     sc->sc_tv_func_start.tv_sec, (long) sc->sc_tv_func_start.tv_usec,
+	     sc->sc_tv_func_stop.tv_sec, (long) sc->sc_tv_func_stop.tv_usec);
 
 	o2net_sc_queue_work(sc, &sc->sc_shutdown_work);
 }
diff --git a/fs/ocfs2/dlm/dlmcommon.h b/fs/ocfs2/dlm/dlmcommon.h
index 3fecba0a602..23ceaa7127b 100644
--- a/fs/ocfs2/dlm/dlmcommon.h
+++ b/fs/ocfs2/dlm/dlmcommon.h
@@ -208,6 +208,9 @@ static inline void __dlm_set_joining_node(struct dlm_ctxt *dlm,
 #define DLM_LOCK_RES_IN_PROGRESS          0x00000010
 #define DLM_LOCK_RES_MIGRATING            0x00000020
 
+/* max milliseconds to wait to sync up a network failure with a node death */
+#define DLM_NODE_DEATH_WAIT_MAX (5 * 1000)
+
 #define DLM_PURGE_INTERVAL_MS   (8 * 1000)
 
 struct dlm_lock_resource
@@ -657,6 +660,8 @@ void dlm_complete_thread(struct dlm_ctxt *dlm);
 int dlm_launch_recovery_thread(struct dlm_ctxt *dlm);
 void dlm_complete_recovery_thread(struct dlm_ctxt *dlm);
 void dlm_wait_for_recovery(struct dlm_ctxt *dlm);
+int dlm_is_node_dead(struct dlm_ctxt *dlm, u8 node);
+int dlm_wait_for_node_death(struct dlm_ctxt *dlm, u8 node, int timeout);
 
 void dlm_put(struct dlm_ctxt *dlm);
 struct dlm_ctxt *dlm_grab(struct dlm_ctxt *dlm);
diff --git a/fs/ocfs2/dlm/dlmconvert.c b/fs/ocfs2/dlm/dlmconvert.c
index 6001b22a997..f66e2d818cc 100644
--- a/fs/ocfs2/dlm/dlmconvert.c
+++ b/fs/ocfs2/dlm/dlmconvert.c
@@ -392,6 +392,11 @@ static enum dlm_status dlm_send_remote_convert_request(struct dlm_ctxt *dlm,
 	} else {
 		mlog_errno(tmpret);
 		if (dlm_is_host_down(tmpret)) {
+			/* instead of logging the same network error over
+			 * and over, sleep here and wait for the heartbeat
+			 * to notice the node is dead.  times out after 5s. */
+			dlm_wait_for_node_death(dlm, res->owner, 
+						DLM_NODE_DEATH_WAIT_MAX);
 			ret = DLM_RECOVERING;
 			mlog(0, "node %u died so returning DLM_RECOVERING "
 			     "from convert message!\n", res->owner);
@@ -421,7 +426,7 @@ int dlm_convert_lock_handler(struct o2net_msg *msg, u32 len, void *data)
 	struct dlm_lockstatus *lksb;
 	enum dlm_status status = DLM_NORMAL;
 	u32 flags;
-	int call_ast = 0, kick_thread = 0;
+	int call_ast = 0, kick_thread = 0, ast_reserved = 0;
 
 	if (!dlm_grab(dlm)) {
 		dlm_error(DLM_REJECTED);
@@ -490,6 +495,7 @@ int dlm_convert_lock_handler(struct o2net_msg *msg, u32 len, void *data)
 	status = __dlm_lockres_state_to_status(res);
 	if (status == DLM_NORMAL) {
 		__dlm_lockres_reserve_ast(res);
+		ast_reserved = 1;
 		res->state |= DLM_LOCK_RES_IN_PROGRESS;
 		status = __dlmconvert_master(dlm, res, lock, flags,
 					     cnv->requested_type,
@@ -512,10 +518,10 @@ leave:
 	else
 		dlm_lock_put(lock);
 
-	/* either queue the ast or release it */
+	/* either queue the ast or release it, if reserved */
 	if (call_ast)
 		dlm_queue_ast(dlm, lock);
-	else
+	else if (ast_reserved)
 		dlm_lockres_release_ast(dlm, res);
 
 	if (kick_thread)
diff --git a/fs/ocfs2/dlm/dlmdomain.c b/fs/ocfs2/dlm/dlmdomain.c
index da3c22045f8..6ee30837389 100644
--- a/fs/ocfs2/dlm/dlmdomain.c
+++ b/fs/ocfs2/dlm/dlmdomain.c
@@ -573,8 +573,11 @@ static int dlm_query_join_handler(struct o2net_msg *msg, u32 len, void *data)
 	spin_lock(&dlm_domain_lock);
 	dlm = __dlm_lookup_domain_full(query->domain, query->name_len);
 	/* Once the dlm ctxt is marked as leaving then we don't want
-	 * to be put in someone's domain map. */
+	 * to be put in someone's domain map. 
+	 * Also, explicitly disallow joining at certain troublesome
+	 * times (ie. during recovery). */
 	if (dlm && dlm->dlm_state != DLM_CTXT_LEAVING) {
+		int bit = query->node_idx;
 		spin_lock(&dlm->spinlock);
 
 		if (dlm->dlm_state == DLM_CTXT_NEW &&
@@ -586,6 +589,19 @@ static int dlm_query_join_handler(struct o2net_msg *msg, u32 len, void *data)
 		} else if (dlm->joining_node != DLM_LOCK_RES_OWNER_UNKNOWN) {
 			/* Disallow parallel joins. */
 			response = JOIN_DISALLOW;
+		} else if (dlm->reco.state & DLM_RECO_STATE_ACTIVE) {
+			mlog(ML_NOTICE, "node %u trying to join, but recovery "
+			     "is ongoing.\n", bit);
+			response = JOIN_DISALLOW;
+		} else if (test_bit(bit, dlm->recovery_map)) {
+			mlog(ML_NOTICE, "node %u trying to join, but it "
+			     "still needs recovery.\n", bit);
+			response = JOIN_DISALLOW;
+		} else if (test_bit(bit, dlm->domain_map)) {
+			mlog(ML_NOTICE, "node %u trying to join, but it "
+			     "is still in the domain! needs recovery?\n",
+			     bit);
+			response = JOIN_DISALLOW;
 		} else {
 			/* Alright we're fully a part of this domain
 			 * so we keep some state as to who's joining
diff --git a/fs/ocfs2/dlm/dlmlock.c b/fs/ocfs2/dlm/dlmlock.c
index d1a0038557a..671d4ff222c 100644
--- a/fs/ocfs2/dlm/dlmlock.c
+++ b/fs/ocfs2/dlm/dlmlock.c
@@ -220,6 +220,17 @@ static enum dlm_status dlmlock_remote(struct dlm_ctxt *dlm,
 			dlm_error(status);
 		dlm_revert_pending_lock(res, lock);
 		dlm_lock_put(lock);
+	} else if (dlm_is_recovery_lock(res->lockname.name, 
+					res->lockname.len)) {
+		/* special case for the $RECOVERY lock.
+		 * there will never be an AST delivered to put
+		 * this lock on the proper secondary queue
+		 * (granted), so do it manually. */
+		mlog(0, "%s: $RECOVERY lock for this node (%u) is "
+		     "mastered by %u; got lock, manually granting (no ast)\n",
+		     dlm->name, dlm->node_num, res->owner);
+		list_del_init(&lock->list);
+		list_add_tail(&lock->list, &res->granted);
 	}
 	spin_unlock(&res->spinlock);
 
@@ -646,7 +657,19 @@ retry_lock:
 			mlog(0, "retrying lock with migration/"
 			     "recovery/in progress\n");
 			msleep(100);
-			dlm_wait_for_recovery(dlm);
+			/* no waiting for dlm_reco_thread */
+			if (recovery) {
+				if (status == DLM_RECOVERING) {
+					mlog(0, "%s: got RECOVERING "
+					     "for $REOCVERY lock, master "
+					     "was %u\n", dlm->name, 
+					     res->owner);
+					dlm_wait_for_node_death(dlm, res->owner, 
+							DLM_NODE_DEATH_WAIT_MAX);
+				}
+			} else {
+				dlm_wait_for_recovery(dlm);
+			}
 			goto retry_lock;
 		}
 
diff --git a/fs/ocfs2/dlm/dlmmaster.c b/fs/ocfs2/dlm/dlmmaster.c
index 27e984f7e4c..2e2e95e6949 100644
--- a/fs/ocfs2/dlm/dlmmaster.c
+++ b/fs/ocfs2/dlm/dlmmaster.c
@@ -1050,17 +1050,10 @@ static int dlm_restart_lock_mastery(struct dlm_ctxt *dlm,
 	node = dlm_bitmap_diff_iter_next(&bdi, &sc);
 	while (node >= 0) {
 		if (sc == NODE_UP) {
-			/* a node came up.  easy.  might not even need
-			 * to talk to it if its node number is higher
-			 * or if we are already blocked. */
-			mlog(0, "node up! %d\n", node);
-			if (blocked)
-				goto next;
-
-			if (node > dlm->node_num) {
-				mlog(0, "node > this node. skipping.\n");
-				goto next;
-			}
+			/* a node came up.  clear any old vote from
+			 * the response map and set it in the vote map
+			 * then restart the mastery. */
+			mlog(ML_NOTICE, "node %d up while restarting\n", node);
 
 			/* redo the master request, but only for the new node */
 			mlog(0, "sending request to new node\n");
@@ -2005,6 +1998,15 @@ fail:
 				break;
 
 			mlog(0, "timed out during migration\n");
+			/* avoid hang during shutdown when migrating lockres 
+			 * to a node which also goes down */
+			if (dlm_is_node_dead(dlm, target)) {
+				mlog(0, "%s:%.*s: expected migration target %u "
+				     "is no longer up.  restarting.\n",
+				     dlm->name, res->lockname.len,
+				     res->lockname.name, target);
+				ret = -ERESTARTSYS;
+			}
 		}
 		if (ret == -ERESTARTSYS) {
 			/* migration failed, detach and clean up mle */
@@ -2480,7 +2482,9 @@ top:
 				atomic_set(&mle->woken, 1);
 				spin_unlock(&mle->spinlock);
 				wake_up(&mle->wq);
-				/* final put will take care of list removal */
+				/* do not need events any longer, so detach 
+				 * from heartbeat */
+				__dlm_mle_detach_hb_events(dlm, mle);
 				__dlm_put_mle(mle);
 			}
 			continue;
@@ -2535,6 +2539,9 @@ top:
 			spin_unlock(&res->spinlock);
 			dlm_lockres_put(res);
 
+			/* about to get rid of mle, detach from heartbeat */
+			__dlm_mle_detach_hb_events(dlm, mle);
+
 			/* dump the mle */
 			spin_lock(&dlm->master_lock);
 			__dlm_put_mle(mle);
diff --git a/fs/ocfs2/dlm/dlmrecovery.c b/fs/ocfs2/dlm/dlmrecovery.c
index 0c8eb1093f0..ed76bda1a53 100644
--- a/fs/ocfs2/dlm/dlmrecovery.c
+++ b/fs/ocfs2/dlm/dlmrecovery.c
@@ -39,6 +39,7 @@
 #include <linux/inet.h>
 #include <linux/timer.h>
 #include <linux/kthread.h>
+#include <linux/delay.h>
 
 
 #include "cluster/heartbeat.h"
@@ -256,6 +257,45 @@ static int dlm_recovery_thread(void *data)
 	return 0;
 }
 
+/* returns true when the recovery master has contacted us */
+static int dlm_reco_master_ready(struct dlm_ctxt *dlm)
+{
+	int ready;
+	spin_lock(&dlm->spinlock);
+	ready = (dlm->reco.new_master != O2NM_INVALID_NODE_NUM);
+	spin_unlock(&dlm->spinlock);
+	return ready;
+}
+
+/* returns true if node is no longer in the domain
+ * could be dead or just not joined */
+int dlm_is_node_dead(struct dlm_ctxt *dlm, u8 node)
+{
+	int dead;
+	spin_lock(&dlm->spinlock);
+	dead = test_bit(node, dlm->domain_map);
+	spin_unlock(&dlm->spinlock);
+	return dead;
+}
+
+int dlm_wait_for_node_death(struct dlm_ctxt *dlm, u8 node, int timeout)
+{
+	if (timeout) {
+		mlog(ML_NOTICE, "%s: waiting %dms for notification of "
+		     "death of node %u\n", dlm->name, timeout, node);
+		wait_event_timeout(dlm->dlm_reco_thread_wq,
+			   dlm_is_node_dead(dlm, node),
+			   msecs_to_jiffies(timeout));
+	} else {
+		mlog(ML_NOTICE, "%s: waiting indefinitely for notification "
+		     "of death of node %u\n", dlm->name, node);
+		wait_event(dlm->dlm_reco_thread_wq,
+			   dlm_is_node_dead(dlm, node));
+	}
+	/* for now, return 0 */
+	return 0;
+}
+
 /* callers of the top-level api calls (dlmlock/dlmunlock) should
  * block on the dlm->reco.event when recovery is in progress.
  * the dlm recovery thread will set this state when it begins
@@ -297,6 +337,7 @@ static void dlm_end_recovery(struct dlm_ctxt *dlm)
 static int dlm_do_recovery(struct dlm_ctxt *dlm)
 {
 	int status = 0;
+	int ret;
 
 	spin_lock(&dlm->spinlock);
 
@@ -343,10 +384,13 @@ static int dlm_do_recovery(struct dlm_ctxt *dlm)
 		goto master_here;
 
 	if (dlm->reco.new_master == O2NM_INVALID_NODE_NUM) {
-		/* choose a new master */
-		if (!dlm_pick_recovery_master(dlm)) {
+		/* choose a new master, returns 0 if this node
+		 * is the master, -EEXIST if it's another node.
+		 * this does not return until a new master is chosen
+		 * or recovery completes entirely. */
+		ret = dlm_pick_recovery_master(dlm);
+		if (!ret) {
 			/* already notified everyone.  go. */
-			dlm->reco.new_master = dlm->node_num;
 			goto master_here;
 		}
 		mlog(0, "another node will master this recovery session.\n");
@@ -371,8 +415,13 @@ master_here:
 	if (status < 0) {
 		mlog(ML_ERROR, "error %d remastering locks for node %u, "
 		     "retrying.\n", status, dlm->reco.dead_node);
+		/* yield a bit to allow any final network messages
+		 * to get handled on remaining nodes */
+		msleep(100);
 	} else {
 		/* success!  see if any other nodes need recovery */
+		mlog(0, "DONE mastering recovery of %s:%u here(this=%u)!\n",
+		     dlm->name, dlm->reco.dead_node, dlm->node_num);
 		dlm_reset_recovery(dlm);
 	}
 	dlm_end_recovery(dlm);
@@ -477,7 +526,7 @@ static int dlm_remaster_locks(struct dlm_ctxt *dlm, u8 dead_node)
 					BUG();
 					break;
 				case DLM_RECO_NODE_DATA_DEAD:
-					mlog(0, "node %u died after "
+					mlog(ML_NOTICE, "node %u died after "
 					     "requesting recovery info for "
 					     "node %u\n", ndata->node_num,
 					     dead_node);
@@ -485,6 +534,19 @@ static int dlm_remaster_locks(struct dlm_ctxt *dlm, u8 dead_node)
 					// start all over
 					destroy = 1;
 					status = -EAGAIN;
+					/* instead of spinning like crazy here,
+					 * wait for the domain map to catch up
+					 * with the network state.  otherwise this
+					 * can be hit hundreds of times before
+					 * the node is really seen as dead. */
+					wait_event_timeout(dlm->dlm_reco_thread_wq,
+							   dlm_is_node_dead(dlm,
+								ndata->node_num),
+							   msecs_to_jiffies(1000));
+					mlog(0, "waited 1 sec for %u, "
+					     "dead? %s\n", ndata->node_num,
+					     dlm_is_node_dead(dlm, ndata->node_num) ?
+					     "yes" : "no");
 					goto leave;
 				case DLM_RECO_NODE_DATA_RECEIVING:
 				case DLM_RECO_NODE_DATA_REQUESTED:
@@ -678,11 +740,27 @@ static void dlm_request_all_locks_worker(struct dlm_work_item *item, void *data)
 	dlm = item->dlm;
 	dead_node = item->u.ral.dead_node;
 	reco_master = item->u.ral.reco_master;
+	mres = (struct dlm_migratable_lockres *)data;
+
+	if (dead_node != dlm->reco.dead_node ||
+	    reco_master != dlm->reco.new_master) {
+		/* show extra debug info if the recovery state is messed */
+		mlog(ML_ERROR, "%s: bad reco state: reco(dead=%u, master=%u), "
+		     "request(dead=%u, master=%u)\n",
+		     dlm->name, dlm->reco.dead_node, dlm->reco.new_master,
+		     dead_node, reco_master);
+		mlog(ML_ERROR, "%s: name=%.*s master=%u locks=%u/%u flags=%u "
+		     "entry[0]={c=%"MLFu64",l=%u,f=%u,t=%d,ct=%d,hb=%d,n=%u}\n",
+		     dlm->name, mres->lockname_len, mres->lockname, mres->master,
+		     mres->num_locks, mres->total_locks, mres->flags,
+		     mres->ml[0].cookie, mres->ml[0].list, mres->ml[0].flags,
+		     mres->ml[0].type, mres->ml[0].convert_type,
+		     mres->ml[0].highest_blocked, mres->ml[0].node);
+		BUG();
+	}
 	BUG_ON(dead_node != dlm->reco.dead_node);
 	BUG_ON(reco_master != dlm->reco.new_master);
 
-	mres = (struct dlm_migratable_lockres *)data;
-
 	/* lock resources should have already been moved to the
  	 * dlm->reco.resources list.  now move items from that list
  	 * to a temp list if the dead owner matches.  note that the
@@ -757,15 +835,18 @@ int dlm_reco_data_done_handler(struct o2net_msg *msg, u32 len, void *data)
 			continue;
 
 		switch (ndata->state) {
+			/* should have moved beyond INIT but not to FINALIZE yet */
 			case DLM_RECO_NODE_DATA_INIT:
 			case DLM_RECO_NODE_DATA_DEAD:
-			case DLM_RECO_NODE_DATA_DONE:
 			case DLM_RECO_NODE_DATA_FINALIZE_SENT:
 				mlog(ML_ERROR, "bad ndata state for node %u:"
 				     " state=%d\n", ndata->node_num,
 				     ndata->state);
 				BUG();
 				break;
+			/* these states are possible at this point, anywhere along
+			 * the line of recovery */
+			case DLM_RECO_NODE_DATA_DONE:
 			case DLM_RECO_NODE_DATA_RECEIVING:
 			case DLM_RECO_NODE_DATA_REQUESTED:
 			case DLM_RECO_NODE_DATA_REQUESTING:
@@ -799,13 +880,31 @@ static void dlm_move_reco_locks_to_list(struct dlm_ctxt *dlm,
 {
 	struct dlm_lock_resource *res;
 	struct list_head *iter, *iter2;
+	struct dlm_lock *lock;
 
 	spin_lock(&dlm->spinlock);
 	list_for_each_safe(iter, iter2, &dlm->reco.resources) {
 		res = list_entry (iter, struct dlm_lock_resource, recovering);
+		/* always prune any $RECOVERY entries for dead nodes,
+		 * otherwise hangs can occur during later recovery */
 		if (dlm_is_recovery_lock(res->lockname.name,
-					 res->lockname.len))
+					 res->lockname.len)) {
+			spin_lock(&res->spinlock);
+			list_for_each_entry(lock, &res->granted, list) {
+				if (lock->ml.node == dead_node) {
+					mlog(0, "AHA! there was "
+					     "a $RECOVERY lock for dead "
+					     "node %u (%s)!\n", 
+					     dead_node, dlm->name);
+					list_del_init(&lock->list);
+					dlm_lock_put(lock);
+					break;
+				}
+			}
+			spin_unlock(&res->spinlock);
 			continue;
+		}
+
 		if (res->owner == dead_node) {
 			mlog(0, "found lockres owned by dead node while "
 				  "doing recovery for node %u. sending it.\n",
@@ -1179,7 +1278,7 @@ static void dlm_mig_lockres_worker(struct dlm_work_item *item, void *data)
 again:
 		ret = dlm_lockres_master_requery(dlm, res, &real_master);
 		if (ret < 0) {
-			mlog(0, "dlm_lockres_master_requery failure: %d\n",
+			mlog(0, "dlm_lockres_master_requery ret=%d\n",
 				  ret);
 			goto again;
 		}
@@ -1757,6 +1856,7 @@ static void dlm_do_local_recovery_cleanup(struct dlm_ctxt *dlm, u8 dead_node)
 	struct dlm_lock_resource *res;
 	int i;
 	struct list_head *bucket;
+	struct dlm_lock *lock;
 
 
 	/* purge any stale mles */
@@ -1780,10 +1880,25 @@ static void dlm_do_local_recovery_cleanup(struct dlm_ctxt *dlm, u8 dead_node)
 		bucket = &(dlm->resources[i]);
 		list_for_each(iter, bucket) {
 			res = list_entry (iter, struct dlm_lock_resource, list);
+ 			/* always prune any $RECOVERY entries for dead nodes,
+ 			 * otherwise hangs can occur during later recovery */
 			if (dlm_is_recovery_lock(res->lockname.name,
-						 res->lockname.len))
+						 res->lockname.len)) {
+				spin_lock(&res->spinlock);
+				list_for_each_entry(lock, &res->granted, list) {
+					if (lock->ml.node == dead_node) {
+						mlog(0, "AHA! there was "
+						     "a $RECOVERY lock for dead "
+						     "node %u (%s)!\n",
+						     dead_node, dlm->name);
+						list_del_init(&lock->list);
+						dlm_lock_put(lock);
+						break;
+					}
+				}
+				spin_unlock(&res->spinlock);
 				continue;
-			
+			}			
 			spin_lock(&res->spinlock);
 			/* zero the lvb if necessary */
 			dlm_revalidate_lvb(dlm, res, dead_node);
@@ -1869,12 +1984,9 @@ void dlm_hb_node_up_cb(struct o2nm_node *node, int idx, void *data)
 		return;
 
 	spin_lock(&dlm->spinlock);
-
 	set_bit(idx, dlm->live_nodes_map);
-
-	/* notify any mles attached to the heartbeat events */
-	dlm_hb_event_notify_attached(dlm, idx, 1);
-
+	/* do NOT notify mle attached to the heartbeat events.
+	 * new nodes are not interesting in mastery until joined. */
 	spin_unlock(&dlm->spinlock);
 
 	dlm_put(dlm);
@@ -1897,7 +2009,18 @@ static void dlm_reco_unlock_ast(void *astdata, enum dlm_status st)
 	mlog(0, "unlockast for recovery lock fired!\n");
 }
 
-
+/*
+ * dlm_pick_recovery_master will continually attempt to use
+ * dlmlock() on the special "$RECOVERY" lockres with the
+ * LKM_NOQUEUE flag to get an EX.  every thread that enters
+ * this function on each node racing to become the recovery
+ * master will not stop attempting this until either:
+ * a) this node gets the EX (and becomes the recovery master),
+ * or b) dlm->reco.new_master gets set to some nodenum 
+ * != O2NM_INVALID_NODE_NUM (another node will do the reco).
+ * so each time a recovery master is needed, the entire cluster
+ * will sync at this point.  if the new master dies, that will
+ * be detected in dlm_do_recovery */
 static int dlm_pick_recovery_master(struct dlm_ctxt *dlm)
 {
 	enum dlm_status ret;
@@ -1906,23 +2029,69 @@ static int dlm_pick_recovery_master(struct dlm_ctxt *dlm)
 
 	mlog(0, "starting recovery of %s at %lu, dead=%u, this=%u\n",
 	     dlm->name, jiffies, dlm->reco.dead_node, dlm->node_num);
-retry:
+again:	
 	memset(&lksb, 0, sizeof(lksb));
 
 	ret = dlmlock(dlm, LKM_EXMODE, &lksb, LKM_NOQUEUE|LKM_RECOVERY,
 		      DLM_RECOVERY_LOCK_NAME, dlm_reco_ast, dlm, dlm_reco_bast);
 
+	mlog(0, "%s: dlmlock($RECOVERY) returned %d, lksb=%d\n",
+	     dlm->name, ret, lksb.status);
+
 	if (ret == DLM_NORMAL) {
 		mlog(0, "dlm=%s dlmlock says I got it (this=%u)\n",
 		     dlm->name, dlm->node_num);
-		/* I am master, send message to all nodes saying
-		 * that I am beginning a recovery session */
-		status = dlm_send_begin_reco_message(dlm,
-					      dlm->reco.dead_node);
+		
+		/* got the EX lock.  check to see if another node 
+		 * just became the reco master */
+		if (dlm_reco_master_ready(dlm)) {
+			mlog(0, "%s: got reco EX lock, but %u will "
+			     "do the recovery\n", dlm->name,
+			     dlm->reco.new_master);
+			status = -EEXIST;
+		} else {
+			status = 0;
+
+			/* see if recovery was already finished elsewhere */
+			spin_lock(&dlm->spinlock);
+			if (dlm->reco.dead_node == O2NM_INVALID_NODE_NUM) {
+				status = -EINVAL;	
+				mlog(0, "%s: got reco EX lock, but "
+				     "node got recovered already\n", dlm->name);
+				if (dlm->reco.new_master != O2NM_INVALID_NODE_NUM) {
+					mlog(ML_ERROR, "%s: new master is %u "
+					     "but no dead node!\n", 
+					     dlm->name, dlm->reco.new_master);
+					BUG();
+				}
+			}
+			spin_unlock(&dlm->spinlock);
+		}
+
+		/* if this node has actually become the recovery master,
+		 * set the master and send the messages to begin recovery */
+		if (!status) {
+			mlog(0, "%s: dead=%u, this=%u, sending "
+			     "begin_reco now\n", dlm->name, 
+			     dlm->reco.dead_node, dlm->node_num);
+			status = dlm_send_begin_reco_message(dlm,
+				      dlm->reco.dead_node);
+			/* this always succeeds */
+			BUG_ON(status);
+
+			/* set the new_master to this node */
+			spin_lock(&dlm->spinlock);
+			dlm->reco.new_master = dlm->node_num;
+			spin_unlock(&dlm->spinlock);
+		}
 
 		/* recovery lock is a special case.  ast will not get fired,
 		 * so just go ahead and unlock it. */
 		ret = dlmunlock(dlm, &lksb, 0, dlm_reco_unlock_ast, dlm);
+		if (ret == DLM_DENIED) {
+			mlog(0, "got DLM_DENIED, trying LKM_CANCEL\n");
+			ret = dlmunlock(dlm, &lksb, LKM_CANCEL, dlm_reco_unlock_ast, dlm);
+		}
 		if (ret != DLM_NORMAL) {
 			/* this would really suck. this could only happen
 			 * if there was a network error during the unlock
@@ -1930,20 +2099,42 @@ retry:
 			 * is actually "done" and the lock structure is
 			 * even freed.  we can continue, but only
 			 * because this specific lock name is special. */
-			mlog(0, "dlmunlock returned %d\n", ret);
-		}
-
-		if (status < 0) {
-			mlog(0, "failed to send recovery message. "
-				   "must retry with new node map.\n");
-			goto retry;
+			mlog(ML_ERROR, "dlmunlock returned %d\n", ret);
 		}
 	} else if (ret == DLM_NOTQUEUED) {
 		mlog(0, "dlm=%s dlmlock says another node got it (this=%u)\n",
 		     dlm->name, dlm->node_num);
 		/* another node is master. wait on
-		 * reco.new_master != O2NM_INVALID_NODE_NUM */
+		 * reco.new_master != O2NM_INVALID_NODE_NUM 
+		 * for at most one second */
+		wait_event_timeout(dlm->dlm_reco_thread_wq,
+					 dlm_reco_master_ready(dlm),
+					 msecs_to_jiffies(1000));
+		if (!dlm_reco_master_ready(dlm)) {
+			mlog(0, "%s: reco master taking awhile\n",
+			     dlm->name);
+			goto again;
+		}
+		/* another node has informed this one that it is reco master */
+		mlog(0, "%s: reco master %u is ready to recover %u\n",
+		     dlm->name, dlm->reco.new_master, dlm->reco.dead_node);
 		status = -EEXIST;
+	} else {
+		struct dlm_lock_resource *res;
+
+		/* dlmlock returned something other than NOTQUEUED or NORMAL */
+		mlog(ML_ERROR, "%s: got %s from dlmlock($RECOVERY), "
+		     "lksb.status=%s\n", dlm->name, dlm_errname(ret),
+		     dlm_errname(lksb.status));
+		res = dlm_lookup_lockres(dlm, DLM_RECOVERY_LOCK_NAME,
+					 DLM_RECOVERY_LOCK_NAME_LEN);
+		if (res) {
+			dlm_print_one_lock_resource(res);
+			dlm_lockres_put(res);
+		} else {
+			mlog(ML_ERROR, "recovery lock not found\n");
+		}
+		BUG();
 	}
 
 	return status;
@@ -1982,7 +2173,7 @@ static int dlm_send_begin_reco_message(struct dlm_ctxt *dlm, u8 dead_node)
 			mlog(0, "not sending begin reco to self\n");
 			continue;
 		}
-
+retry:
 		ret = -EINVAL;
 		mlog(0, "attempting to send begin reco msg to %d\n",
 			  nodenum);
@@ -1991,8 +2182,17 @@ static int dlm_send_begin_reco_message(struct dlm_ctxt *dlm, u8 dead_node)
 		/* negative status is handled ok by caller here */
 		if (ret >= 0)
 			ret = status;
+		if (dlm_is_host_down(ret)) {
+			/* node is down.  not involved in recovery
+			 * so just keep going */
+			mlog(0, "%s: node %u was down when sending "
+			     "begin reco msg (%d)\n", dlm->name, nodenum, ret);
+			ret = 0;
+		}
 		if (ret < 0) {
 			struct dlm_lock_resource *res;
+			/* this is now a serious problem, possibly ENOMEM 
+			 * in the network stack.  must retry */
 			mlog_errno(ret);
 			mlog(ML_ERROR, "begin reco of dlm %s to node %u "
 			    " returned %d\n", dlm->name, nodenum, ret);
@@ -2004,7 +2204,10 @@ static int dlm_send_begin_reco_message(struct dlm_ctxt *dlm, u8 dead_node)
 			} else {
 				mlog(ML_ERROR, "recovery lock not found\n");
 			}
-			break;
+			/* sleep for a bit in hopes that we can avoid 
+			 * another ENOMEM */
+			msleep(100);
+			goto retry;
 		}
 	}
 
@@ -2027,19 +2230,34 @@ int dlm_begin_reco_handler(struct o2net_msg *msg, u32 len, void *data)
 
 	spin_lock(&dlm->spinlock);
 	if (dlm->reco.new_master != O2NM_INVALID_NODE_NUM) {
-		mlog(0, "new_master already set to %u!\n",
-			  dlm->reco.new_master);
+		if (test_bit(dlm->reco.new_master, dlm->recovery_map)) {
+			mlog(0, "%s: new_master %u died, changing "
+			     "to %u\n", dlm->name, dlm->reco.new_master,
+			     br->node_idx);
+		} else {
+			mlog(0, "%s: new_master %u NOT DEAD, changing "
+			     "to %u\n", dlm->name, dlm->reco.new_master,
+			     br->node_idx);
+			/* may not have seen the new master as dead yet */
+		}
 	}
 	if (dlm->reco.dead_node != O2NM_INVALID_NODE_NUM) {
-		mlog(0, "dead_node already set to %u!\n",
-			  dlm->reco.dead_node);
+		mlog(ML_NOTICE, "%s: dead_node previously set to %u, "
+		     "node %u changing it to %u\n", dlm->name, 
+		     dlm->reco.dead_node, br->node_idx, br->dead_node);
 	}
 	dlm->reco.new_master = br->node_idx;
 	dlm->reco.dead_node = br->dead_node;
 	if (!test_bit(br->dead_node, dlm->recovery_map)) {
-		mlog(ML_ERROR, "recovery master %u sees %u as dead, but this "
+		mlog(0, "recovery master %u sees %u as dead, but this "
 		     "node has not yet.  marking %u as dead\n",
 		     br->node_idx, br->dead_node, br->dead_node);
+		if (!test_bit(br->dead_node, dlm->domain_map) ||
+		    !test_bit(br->dead_node, dlm->live_nodes_map))
+			mlog(0, "%u not in domain/live_nodes map "
+			     "so setting it in reco map manually\n",
+			     br->dead_node);
+		set_bit(br->dead_node, dlm->recovery_map);
 		__dlm_hb_node_down(dlm, br->dead_node);
 	}
 	spin_unlock(&dlm->spinlock);
diff --git a/fs/ocfs2/dlm/dlmunlock.c b/fs/ocfs2/dlm/dlmunlock.c
index cec2ce1cd31..c95f08d2e92 100644
--- a/fs/ocfs2/dlm/dlmunlock.c
+++ b/fs/ocfs2/dlm/dlmunlock.c
@@ -188,6 +188,19 @@ static enum dlm_status dlmunlock_common(struct dlm_ctxt *dlm,
 			actions &= ~(DLM_UNLOCK_REMOVE_LOCK|
 				     DLM_UNLOCK_REGRANT_LOCK|
 				     DLM_UNLOCK_CLEAR_CONVERT_TYPE);
+		} else if (status == DLM_RECOVERING || 
+			   status == DLM_MIGRATING || 
+			   status == DLM_FORWARD) {
+			/* must clear the actions because this unlock
+			 * is about to be retried.  cannot free or do
+			 * any list manipulation. */
+			mlog(0, "%s:%.*s: clearing actions, %s\n",
+			     dlm->name, res->lockname.len,
+			     res->lockname.name,
+			     status==DLM_RECOVERING?"recovering":
+			     (status==DLM_MIGRATING?"migrating":
+			      "forward"));
+			actions = 0;
 		}
 		if (flags & LKM_CANCEL)
 			lock->cancel_pending = 0;
diff --git a/fs/ocfs2/dlm/userdlm.c b/fs/ocfs2/dlm/userdlm.c
index e1fdd288796..c3764f4744e 100644
--- a/fs/ocfs2/dlm/userdlm.c
+++ b/fs/ocfs2/dlm/userdlm.c
@@ -27,7 +27,7 @@
  * Boston, MA 021110-1307, USA.
  */
 
-#include <asm/signal.h>
+#include <linux/signal.h>
 
 #include <linux/module.h>
 #include <linux/fs.h>
diff --git a/fs/ocfs2/extent_map.c b/fs/ocfs2/extent_map.c
index f2fb40cd296..b6ba292e954 100644
--- a/fs/ocfs2/extent_map.c
+++ b/fs/ocfs2/extent_map.c
@@ -262,8 +262,7 @@ static int ocfs2_extent_map_find_leaf(struct inode *inode,
 		el = &eb->h_list;
 	}
 
-	if (el->l_tree_depth)
-		BUG();
+	BUG_ON(el->l_tree_depth);
 
 	for (i = 0; i < le16_to_cpu(el->l_next_free_rec); i++) {
 		rec = &el->l_recs[i];
@@ -364,8 +363,8 @@ static int ocfs2_extent_map_lookup_read(struct inode *inode,
 		return ret;
 	}
 
-	if (ent->e_tree_depth)
-		BUG();  /* FIXME: Make sure this isn't a corruption */
+	/* FIXME: Make sure this isn't a corruption */
+	BUG_ON(ent->e_tree_depth);
 
 	*ret_ent = ent;
 
@@ -423,8 +422,7 @@ static int ocfs2_extent_map_try_insert(struct inode *inode,
 					  le32_to_cpu(rec->e_clusters), NULL,
 					  NULL);
 
-	if (!old_ent)
-		BUG();
+	BUG_ON(!old_ent);
 
 	ret = -EEXIST;
 	if (old_ent->e_tree_depth < tree_depth)
@@ -988,7 +986,7 @@ int __init init_ocfs2_extent_maps(void)
 	return 0;
 }
 
-void __exit exit_ocfs2_extent_maps(void)
+void exit_ocfs2_extent_maps(void)
 {
 	kmem_cache_destroy(ocfs2_em_ent_cachep);
 }
diff --git a/fs/ocfs2/file.c b/fs/ocfs2/file.c
index eaf33caa0a1..1715bc90e70 100644
--- a/fs/ocfs2/file.c
+++ b/fs/ocfs2/file.c
@@ -1022,8 +1022,9 @@ static ssize_t ocfs2_file_aio_write(struct kiocb *iocb,
 		}
 		newsize = count + saved_pos;
 
-		mlog(0, "pos=%lld newsize=%"MLFu64" cursize=%lld\n",
-		     saved_pos, newsize, i_size_read(inode));
+		mlog(0, "pos=%lld newsize=%lld cursize=%lld\n",
+		     (long long) saved_pos, (long long) newsize,
+		     (long long) i_size_read(inode));
 
 		/* No need for a higher level metadata lock if we're
 		 * never going past i_size. */
@@ -1042,8 +1043,9 @@ static ssize_t ocfs2_file_aio_write(struct kiocb *iocb,
 		spin_unlock(&OCFS2_I(inode)->ip_lock);
 
 		mlog(0, "Writing at EOF, may need more allocation: "
-		     "i_size = %lld, newsize = %"MLFu64", need %u clusters\n",
-		     i_size_read(inode), newsize, clusters);
+		     "i_size = %lld, newsize = %lld, need %u clusters\n",
+		     (long long) i_size_read(inode), (long long) newsize,
+		     clusters);
 
 		/* We only want to continue the rest of this loop if
 		 * our extend will actually require more
diff --git a/fs/ocfs2/inode.c b/fs/ocfs2/inode.c
index d4ecc062771..8122489c576 100644
--- a/fs/ocfs2/inode.c
+++ b/fs/ocfs2/inode.c
@@ -903,10 +903,10 @@ void ocfs2_clear_inode(struct inode *inode)
 			"Clear inode of %"MLFu64", inode is locked\n",
 			oi->ip_blkno);
 
-	mlog_bug_on_msg(down_trylock(&oi->ip_io_sem),
-			"Clear inode of %"MLFu64", io_sem is locked\n",
+	mlog_bug_on_msg(!mutex_trylock(&oi->ip_io_mutex),
+			"Clear inode of %"MLFu64", io_mutex is locked\n",
 			oi->ip_blkno);
-	up(&oi->ip_io_sem);
+	mutex_unlock(&oi->ip_io_mutex);
 
 	/*
 	 * down_trylock() returns 0, down_write_trylock() returns 1
diff --git a/fs/ocfs2/inode.h b/fs/ocfs2/inode.h
index 9b017743365..84c50796128 100644
--- a/fs/ocfs2/inode.h
+++ b/fs/ocfs2/inode.h
@@ -46,10 +46,10 @@ struct ocfs2_inode_info
 	struct list_head		ip_io_markers;
 	int				ip_orphaned_slot;
 
-	struct semaphore		ip_io_sem;
+	struct mutex			ip_io_mutex;
 
 	/* Used by the journalling code to attach an inode to a
-	 * handle.  These are protected by ip_io_sem in order to lock
+	 * handle.  These are protected by ip_io_mutex in order to lock
 	 * out other I/O to the inode until we either commit or
 	 * abort. */
 	struct list_head		ip_handle_list;
diff --git a/fs/ocfs2/journal.c b/fs/ocfs2/journal.c
index 303c8d96457..d329c9df90a 100644
--- a/fs/ocfs2/journal.c
+++ b/fs/ocfs2/journal.c
@@ -147,8 +147,7 @@ struct ocfs2_journal_handle *ocfs2_start_trans(struct ocfs2_super *osb,
 
 	mlog_entry("(max_buffs = %d)\n", max_buffs);
 
-	if (!osb || !osb->journal->j_journal)
-		BUG();
+	BUG_ON(!osb || !osb->journal->j_journal);
 
 	if (ocfs2_is_hard_readonly(osb)) {
 		ret = -EROFS;
@@ -401,7 +400,7 @@ int ocfs2_journal_access(struct ocfs2_journal_handle *handle,
 	 * j_trans_barrier for us. */
 	ocfs2_set_inode_lock_trans(OCFS2_SB(inode->i_sb)->journal, inode);
 
-	down(&OCFS2_I(inode)->ip_io_sem);
+	mutex_lock(&OCFS2_I(inode)->ip_io_mutex);
 	switch (type) {
 	case OCFS2_JOURNAL_ACCESS_CREATE:
 	case OCFS2_JOURNAL_ACCESS_WRITE:
@@ -416,7 +415,7 @@ int ocfs2_journal_access(struct ocfs2_journal_handle *handle,
 		status = -EINVAL;
 		mlog(ML_ERROR, "Uknown access type!\n");
 	}
-	up(&OCFS2_I(inode)->ip_io_sem);
+	mutex_unlock(&OCFS2_I(inode)->ip_io_mutex);
 
 	if (status < 0)
 		mlog(ML_ERROR, "Error %d getting %d access to buffer!\n",
@@ -561,7 +560,11 @@ int ocfs2_journal_init(struct ocfs2_journal *journal, int *dirty)
 	SET_INODE_JOURNAL(inode);
 	OCFS2_I(inode)->ip_open_count++;
 
-	status = ocfs2_meta_lock(inode, NULL, &bh, 1);
+	/* Skip recovery waits here - journal inode metadata never
+	 * changes in a live cluster so it can be considered an
+	 * exception to the rule. */
+	status = ocfs2_meta_lock_full(inode, NULL, &bh, 1,
+				      OCFS2_META_LOCK_RECOVERY);
 	if (status < 0) {
 		if (status != -ERESTARTSYS)
 			mlog(ML_ERROR, "Could not get lock on journal!\n");
@@ -672,8 +675,7 @@ void ocfs2_journal_shutdown(struct ocfs2_super *osb)
 
 	mlog_entry_void();
 
-	if (!osb)
-		BUG();
+	BUG_ON(!osb);
 
 	journal = osb->journal;
 	if (!journal)
@@ -805,8 +807,7 @@ int ocfs2_journal_wipe(struct ocfs2_journal *journal, int full)
 
 	mlog_entry_void();
 
-	if (!journal)
-		BUG();
+	BUG_ON(!journal);
 
 	status = journal_wipe(journal->j_journal, full);
 	if (status < 0) {
@@ -1072,10 +1073,10 @@ restart:
 					NULL);
 
 bail:
-	down(&osb->recovery_lock);
+	mutex_lock(&osb->recovery_lock);
 	if (!status &&
 	    !ocfs2_node_map_is_empty(osb, &osb->recovery_map)) {
-		up(&osb->recovery_lock);
+		mutex_unlock(&osb->recovery_lock);
 		goto restart;
 	}
 
@@ -1083,7 +1084,7 @@ bail:
 	mb(); /* sync with ocfs2_recovery_thread_running */
 	wake_up(&osb->recovery_event);
 
-	up(&osb->recovery_lock);
+	mutex_unlock(&osb->recovery_lock);
 
 	mlog_exit(status);
 	/* no one is callint kthread_stop() for us so the kthread() api
@@ -1098,7 +1099,7 @@ void ocfs2_recovery_thread(struct ocfs2_super *osb, int node_num)
 	mlog_entry("(node_num=%d, osb->node_num = %d)\n",
 		   node_num, osb->node_num);
 
-	down(&osb->recovery_lock);
+	mutex_lock(&osb->recovery_lock);
 	if (osb->disable_recovery)
 		goto out;
 
@@ -1120,7 +1121,7 @@ void ocfs2_recovery_thread(struct ocfs2_super *osb, int node_num)
 	}
 
 out:
-	up(&osb->recovery_lock);
+	mutex_unlock(&osb->recovery_lock);
 	wake_up(&osb->recovery_event);
 
 	mlog_exit_void();
@@ -1271,8 +1272,7 @@ static int ocfs2_recover_node(struct ocfs2_super *osb,
 
 	/* Should not ever be called to recover ourselves -- in that
 	 * case we should've called ocfs2_journal_load instead. */
-	if (osb->node_num == node_num)
-		BUG();
+	BUG_ON(osb->node_num == node_num);
 
 	slot_num = ocfs2_node_num_to_slot(si, node_num);
 	if (slot_num == OCFS2_INVALID_SLOT) {
@@ -1584,10 +1584,9 @@ static int ocfs2_commit_thread(void *arg)
 	while (!(kthread_should_stop() &&
 		 atomic_read(&journal->j_num_trans) == 0)) {
 
-		wait_event_interruptible_timeout(osb->checkpoint_event,
-						 atomic_read(&journal->j_num_trans)
-						 || kthread_should_stop(),
-						 OCFS2_CHECKPOINT_INTERVAL);
+		wait_event_interruptible(osb->checkpoint_event,
+					 atomic_read(&journal->j_num_trans)
+					 || kthread_should_stop());
 
 		status = ocfs2_commit_cache(osb);
 		if (status < 0)
diff --git a/fs/ocfs2/journal.h b/fs/ocfs2/journal.h
index 7d0a816184f..2f3a6acdac4 100644
--- a/fs/ocfs2/journal.h
+++ b/fs/ocfs2/journal.h
@@ -29,8 +29,6 @@
 #include <linux/fs.h>
 #include <linux/jbd.h>
 
-#define OCFS2_CHECKPOINT_INTERVAL        (8 * HZ)
-
 enum ocfs2_journal_state {
 	OCFS2_JOURNAL_FREE = 0,
 	OCFS2_JOURNAL_LOADED,
diff --git a/fs/ocfs2/ocfs2.h b/fs/ocfs2/ocfs2.h
index f468c600cf9..8d8e4779df9 100644
--- a/fs/ocfs2/ocfs2.h
+++ b/fs/ocfs2/ocfs2.h
@@ -33,6 +33,7 @@
 #include <linux/rbtree.h>
 #include <linux/workqueue.h>
 #include <linux/kref.h>
+#include <linux/mutex.h>
 
 #include "cluster/nodemanager.h"
 #include "cluster/heartbeat.h"
@@ -233,7 +234,7 @@ struct ocfs2_super
 	struct proc_dir_entry *proc_sub_dir; /* points to /proc/fs/ocfs2/<maj_min> */
 
 	atomic_t vol_state;
-	struct semaphore recovery_lock;
+	struct mutex recovery_lock;
 	struct task_struct *recovery_thread_task;
 	int disable_recovery;
 	wait_queue_head_t checkpoint_event;
diff --git a/fs/ocfs2/super.c b/fs/ocfs2/super.c
index 364d64bd5f1..046824b6b62 100644
--- a/fs/ocfs2/super.c
+++ b/fs/ocfs2/super.c
@@ -932,7 +932,7 @@ static void ocfs2_inode_init_once(void *data,
 		oi->ip_dir_start_lookup = 0;
 
 		init_rwsem(&oi->ip_alloc_sem);
-		init_MUTEX(&(oi->ip_io_sem));
+		mutex_init(&oi->ip_io_mutex);
 
 		oi->ip_blkno = 0ULL;
 		oi->ip_clusters = 0;
@@ -1137,9 +1137,9 @@ static void ocfs2_dismount_volume(struct super_block *sb, int mnt_err)
 
 	/* disable any new recovery threads and wait for any currently
 	 * running ones to exit. Do this before setting the vol_state. */
-	down(&osb->recovery_lock);
+	mutex_lock(&osb->recovery_lock);
 	osb->disable_recovery = 1;
-	up(&osb->recovery_lock);
+	mutex_unlock(&osb->recovery_lock);
 	wait_event(osb->recovery_event, !ocfs2_recovery_thread_running(osb));
 
 	/* At this point, we know that no more recovery threads can be
@@ -1254,8 +1254,7 @@ static int ocfs2_initialize_super(struct super_block *sb,
 	osb->sb = sb;
 	/* Save off for ocfs2_rw_direct */
 	osb->s_sectsize_bits = blksize_bits(sector_size);
-	if (!osb->s_sectsize_bits)
-		BUG();
+	BUG_ON(!osb->s_sectsize_bits);
 
 	osb->net_response_ids = 0;
 	spin_lock_init(&osb->net_response_lock);
@@ -1283,7 +1282,7 @@ static int ocfs2_initialize_super(struct super_block *sb,
 	snprintf(osb->dev_str, sizeof(osb->dev_str), "%u,%u",
 		 MAJOR(osb->sb->s_dev), MINOR(osb->sb->s_dev));
 
-	init_MUTEX(&osb->recovery_lock);
+	mutex_init(&osb->recovery_lock);
 
 	osb->disable_recovery = 0;
 	osb->recovery_thread_task = NULL;
diff --git a/fs/ocfs2/sysfile.c b/fs/ocfs2/sysfile.c
index 600a8bc5b54..fc29cb7a437 100644
--- a/fs/ocfs2/sysfile.c
+++ b/fs/ocfs2/sysfile.c
@@ -77,8 +77,7 @@ struct inode *ocfs2_get_system_file_inode(struct ocfs2_super *osb,
 	if (arr && ((inode = *arr) != NULL)) {
 		/* get a ref in addition to the array ref */
 		inode = igrab(inode);
-		if (!inode)
-			BUG();
+		BUG_ON(!inode);
 
 		return inode;
 	}
@@ -89,8 +88,7 @@ struct inode *ocfs2_get_system_file_inode(struct ocfs2_super *osb,
 	/* add one more if putting into array for first time */
 	if (arr && inode) {
 		*arr = igrab(inode);
-		if (!*arr)
-			BUG();
+		BUG_ON(!*arr);
 	}
 	return inode;
 }
diff --git a/fs/ocfs2/uptodate.c b/fs/ocfs2/uptodate.c
index 3a0458fd3e1..300b5bedfb2 100644
--- a/fs/ocfs2/uptodate.c
+++ b/fs/ocfs2/uptodate.c
@@ -388,7 +388,7 @@ out_free:
 	}
 }
 
-/* Item insertion is guarded by ip_io_sem, so the insertion path takes
+/* Item insertion is guarded by ip_io_mutex, so the insertion path takes
  * advantage of this by not rechecking for a duplicate insert during
  * the slow case. Additionally, if the cache needs to be bumped up to
  * a tree, the code will not recheck after acquiring the lock --
@@ -418,7 +418,7 @@ void ocfs2_set_buffer_uptodate(struct inode *inode,
 	     (unsigned long long) bh->b_blocknr);
 
 	/* No need to recheck under spinlock - insertion is guarded by
-	 * ip_io_sem */
+	 * ip_io_mutex */
 	spin_lock(&oi->ip_lock);
 	if (ocfs2_insert_can_use_array(oi, ci)) {
 		/* Fast case - it's an array and there's a free
@@ -440,7 +440,7 @@ void ocfs2_set_buffer_uptodate(struct inode *inode,
 
 /* Called against a newly allocated buffer. Most likely nobody should
  * be able to read this sort of metadata while it's still being
- * allocated, but this is careful to take ip_io_sem anyway. */
+ * allocated, but this is careful to take ip_io_mutex anyway. */
 void ocfs2_set_new_buffer_uptodate(struct inode *inode,
 				   struct buffer_head *bh)
 {
@@ -451,9 +451,9 @@ void ocfs2_set_new_buffer_uptodate(struct inode *inode,
 
 	set_buffer_uptodate(bh);
 
-	down(&oi->ip_io_sem);
+	mutex_lock(&oi->ip_io_mutex);
 	ocfs2_set_buffer_uptodate(inode, bh);
-	up(&oi->ip_io_sem);
+	mutex_unlock(&oi->ip_io_mutex);
 }
 
 /* Requires ip_lock. */
@@ -537,7 +537,7 @@ int __init init_ocfs2_uptodate_cache(void)
 	return 0;
 }
 
-void __exit exit_ocfs2_uptodate_cache(void)
+void exit_ocfs2_uptodate_cache(void)
 {
 	if (ocfs2_uptodate_cachep)
 		kmem_cache_destroy(ocfs2_uptodate_cachep);
diff --git a/fs/ocfs2/uptodate.h b/fs/ocfs2/uptodate.h
index e5aacdf4eab..01cd32d26b0 100644
--- a/fs/ocfs2/uptodate.h
+++ b/fs/ocfs2/uptodate.h
@@ -27,7 +27,7 @@
 #define OCFS2_UPTODATE_H
 
 int __init init_ocfs2_uptodate_cache(void);
-void __exit exit_ocfs2_uptodate_cache(void);
+void exit_ocfs2_uptodate_cache(void);
 
 void ocfs2_metadata_cache_init(struct inode *inode);
 void ocfs2_metadata_cache_purge(struct inode *inode);
diff --git a/fs/proc/inode.c b/fs/proc/inode.c
index 6573f31f1fd..075d3e94560 100644
--- a/fs/proc/inode.c
+++ b/fs/proc/inode.c
@@ -204,10 +204,6 @@ int proc_fill_super(struct super_block *s, void *data, int silent)
 	root_inode = proc_get_inode(s, PROC_ROOT_INO, &proc_root);
 	if (!root_inode)
 		goto out_no_root;
-	/*
-	 * Fixup the root inode's nlink value
-	 */
-	root_inode->i_nlink += nr_processes();
 	root_inode->i_uid = 0;
 	root_inode->i_gid = 0;
 	s->s_root = d_alloc_root(root_inode);
diff --git a/fs/proc/proc_misc.c b/fs/proc/proc_misc.c
index 8f8014285a3..1d24fead51a 100644
--- a/fs/proc/proc_misc.c
+++ b/fs/proc/proc_misc.c
@@ -548,7 +548,7 @@ static int show_stat(struct seq_file *p, void *v)
 	}
 	seq_printf(p, "intr %llu", (unsigned long long)sum);
 
-#if !defined(CONFIG_PPC64) && !defined(CONFIG_ALPHA)
+#if !defined(CONFIG_PPC64) && !defined(CONFIG_ALPHA) && !defined(CONFIG_IA64)
 	for (i = 0; i < NR_IRQS; i++)
 		seq_printf(p, " %u", kstat_irqs(i));
 #endif
diff --git a/fs/proc/root.c b/fs/proc/root.c
index 68896283c8a..c3fd3611112 100644
--- a/fs/proc/root.c
+++ b/fs/proc/root.c
@@ -80,16 +80,16 @@ void __init proc_root_init(void)
 	proc_bus = proc_mkdir("bus", NULL);
 }
 
-static struct dentry *proc_root_lookup(struct inode * dir, struct dentry * dentry, struct nameidata *nd)
+static int proc_root_getattr(struct vfsmount *mnt, struct dentry *dentry, struct kstat *stat
+)
 {
-	/*
-	 * nr_threads is actually protected by the tasklist_lock;
-	 * however, it's conventional to do reads, especially for
-	 * reporting, without any locking whatsoever.
-	 */
-	if (dir->i_ino == PROC_ROOT_INO) /* check for safety... */
-		dir->i_nlink = proc_root.nlink + nr_threads;
+	generic_fillattr(dentry->d_inode, stat);
+	stat->nlink = proc_root.nlink + nr_processes();
+	return 0;
+}
 
+static struct dentry *proc_root_lookup(struct inode * dir, struct dentry * dentry, struct nameidata *nd)
+{
 	if (!proc_lookup(dir, dentry, nd)) {
 		return NULL;
 	}
@@ -134,6 +134,7 @@ static struct file_operations proc_root_operations = {
  */
 static struct inode_operations proc_root_inode_operations = {
 	.lookup		= proc_root_lookup,
+	.getattr	= proc_root_getattr,
 };
 
 /*
diff --git a/fs/quota_v2.c b/fs/quota_v2.c
index a4ef91bb4f3..b4199ec3ece 100644
--- a/fs/quota_v2.c
+++ b/fs/quota_v2.c
@@ -35,7 +35,7 @@ static int v2_check_quota_file(struct super_block *sb, int type)
  
 	size = sb->s_op->quota_read(sb, type, (char *)&dqhead, sizeof(struct v2_disk_dqheader), 0);
 	if (size != sizeof(struct v2_disk_dqheader)) {
-		printk("quota_v2: failed read expected=%d got=%d\n",
+		printk("quota_v2: failed read expected=%zd got=%zd\n",
 			sizeof(struct v2_disk_dqheader), size);
 		return 0;
 	}
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/hashes.c b/fs/reiserfs/hashes.c
index a3ec238fd9e..e664ac16fad 100644
--- a/fs/reiserfs/hashes.c
+++ b/fs/reiserfs/hashes.c
@@ -21,7 +21,6 @@
 #include <linux/kernel.h>
 #include <linux/reiserfs_fs.h>
 #include <asm/types.h>
-#include <asm/bug.h>
 
 #define DELTA 0x9E3779B9
 #define FULLROUNDS 10		/* 32 is overkill, 16 is strong crypto */
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..d63da756eb4 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",
@@ -1130,8 +1124,6 @@ static void handle_attrs(struct super_block *s)
 					 "reiserfs: cannot support attributes until flag is set in super-block");
 			REISERFS_SB(s)->s_mount_opt &= ~(1 << REISERFS_ATTRS);
 		}
-	} else if (le32_to_cpu(rs->s_flags) & reiserfs_attrs_cleared) {
-		REISERFS_SB(s)->s_mount_opt |= REISERFS_ATTRS;
 	}
 }
 
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/reiserfs/xattr_acl.c b/fs/reiserfs/xattr_acl.c
index 43de3ba8333..ab8894c3b9e 100644
--- a/fs/reiserfs/xattr_acl.c
+++ b/fs/reiserfs/xattr_acl.c
@@ -228,7 +228,8 @@ struct posix_acl *reiserfs_get_acl(struct inode *inode, int type)
 		acl = ERR_PTR(retval);
 	} else {
 		acl = posix_acl_from_disk(value, retval);
-		*p_acl = posix_acl_dup(acl);
+		if (!IS_ERR(acl))
+			*p_acl = posix_acl_dup(acl);
 	}
 
 	kfree(value);
diff --git a/fs/select.c b/fs/select.c
index c0f02d36c60..1815a57d225 100644
--- a/fs/select.c
+++ b/fs/select.c
@@ -398,11 +398,15 @@ asmlinkage long sys_select(int n, fd_set __user *inp, fd_set __user *outp,
 	ret = core_sys_select(n, inp, outp, exp, &timeout);
 
 	if (tvp) {
+		struct timeval rtv;
+
 		if (current->personality & STICKY_TIMEOUTS)
 			goto sticky;
-		tv.tv_usec = jiffies_to_usecs(do_div((*(u64*)&timeout), HZ));
-		tv.tv_sec = timeout;
-		if (copy_to_user(tvp, &tv, sizeof(tv))) {
+		rtv.tv_usec = jiffies_to_usecs(do_div((*(u64*)&timeout), HZ));
+		rtv.tv_sec = timeout;
+		if (timeval_compare(&rtv, &tv) >= 0)
+			rtv = tv;
+		if (copy_to_user(tvp, &rtv, sizeof(rtv))) {
 sticky:
 			/*
 			 * If an application puts its timeval in read-only
@@ -460,11 +464,16 @@ asmlinkage long sys_pselect7(int n, fd_set __user *inp, fd_set __user *outp,
 	ret = core_sys_select(n, inp, outp, exp, &timeout);
 
 	if (tsp) {
+		struct timespec rts;
+
 		if (current->personality & STICKY_TIMEOUTS)
 			goto sticky;
-		ts.tv_nsec = jiffies_to_usecs(do_div((*(u64*)&timeout), HZ)) * 1000;
-		ts.tv_sec = timeout;
-		if (copy_to_user(tsp, &ts, sizeof(ts))) {
+		rts.tv_nsec = jiffies_to_usecs(do_div((*(u64*)&timeout), HZ)) *
+						1000;
+		rts.tv_sec = timeout;
+		if (timespec_compare(&rts, &ts) >= 0)
+			rts = ts;
+		if (copy_to_user(tsp, &rts, sizeof(rts))) {
 sticky:
 			/*
 			 * If an application puts its timeval in read-only
@@ -510,9 +519,9 @@ asmlinkage long sys_pselect6(int n, fd_set __user *inp, fd_set __user *outp,
 
 	if (sig) {
 		if (!access_ok(VERIFY_READ, sig, sizeof(void *)+sizeof(size_t))
-		    || __get_user(up, (sigset_t * __user *)sig)
+		    || __get_user(up, (sigset_t __user * __user *)sig)
 		    || __get_user(sigsetsize,
-				(size_t * __user)(sig+sizeof(void *))))
+				(size_t __user *)(sig+sizeof(void *))))
 			return -EFAULT;
 	}
 
@@ -758,12 +767,17 @@ asmlinkage long sys_ppoll(struct pollfd __user *ufds, unsigned int nfds,
 		sigprocmask(SIG_SETMASK, &sigsaved, NULL);
 
 	if (tsp && timeout >= 0) {
+		struct timespec rts;
+
 		if (current->personality & STICKY_TIMEOUTS)
 			goto sticky;
 		/* Yes, we know it's actually an s64, but it's also positive. */
-		ts.tv_nsec = jiffies_to_usecs(do_div((*(u64*)&timeout), HZ)) * 1000;
-		ts.tv_sec = timeout;
-		if (copy_to_user(tsp, &ts, sizeof(ts))) {
+		rts.tv_nsec = jiffies_to_usecs(do_div((*(u64*)&timeout), HZ)) *
+						1000;
+		rts.tv_sec = timeout;
+		if (timespec_compare(&rts, &ts) >= 0)
+			rts = ts;
+		if (copy_to_user(tsp, &rts, sizeof(rts))) {
 		sticky:
 			/*
 			 * If an application puts its timeval in read-only
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/stat.c b/fs/stat.c
index 24211b030f3..9948cc1685a 100644
--- a/fs/stat.c
+++ b/fs/stat.c
@@ -261,6 +261,7 @@ asmlinkage long sys_newlstat(char __user *filename, struct stat __user *statbuf)
 	return error;
 }
 
+#ifndef __ARCH_WANT_STAT64
 asmlinkage long sys_newfstatat(int dfd, char __user *filename,
 				struct stat __user *statbuf, int flag)
 {
@@ -281,6 +282,7 @@ asmlinkage long sys_newfstatat(int dfd, char __user *filename,
 out:
 	return error;
 }
+#endif
 
 asmlinkage long sys_newfstat(unsigned int fd, struct stat __user *statbuf)
 {
@@ -395,6 +397,26 @@ asmlinkage long sys_fstat64(unsigned long fd, struct stat64 __user * statbuf)
 	return error;
 }
 
+asmlinkage long sys_fstatat64(int dfd, char __user *filename,
+			       struct stat64 __user *statbuf, int flag)
+{
+	struct kstat stat;
+	int error = -EINVAL;
+
+	if ((flag & ~AT_SYMLINK_NOFOLLOW) != 0)
+		goto out;
+
+	if (flag & AT_SYMLINK_NOFOLLOW)
+		error = vfs_lstat_fd(dfd, filename, &stat);
+	else
+		error = vfs_stat_fd(dfd, filename, &stat);
+
+	if (!error)
+		error = cp_new_stat64(&stat, statbuf);
+
+out:
+	return error;
+}
 #endif /* __ARCH_WANT_STAT64 */
 
 void inode_add_bytes(struct inode *inode, loff_t bytes)
diff --git a/fs/super.c b/fs/super.c
index c177b92419c..e20b5580afd 100644
--- a/fs/super.c
+++ b/fs/super.c
@@ -247,8 +247,9 @@ void generic_shutdown_super(struct super_block *sb)
 
 		/* Forget any remaining inodes */
 		if (invalidate_inodes(sb)) {
-			printk("VFS: Busy inodes after unmount. "
-			   "Self-destruct in 5 seconds.  Have a nice day...\n");
+			printk("VFS: Busy inodes after unmount of %s. "
+			   "Self-destruct in 5 seconds.  Have a nice day...\n",
+			   sb->s_id);
 		}
 
 		unlock_kernel();
@@ -665,6 +666,16 @@ static int test_bdev_super(struct super_block *s, void *data)
 	return (void *)s->s_bdev == data;
 }
 
+static void bdev_uevent(struct block_device *bdev, enum kobject_action action)
+{
+	if (bdev->bd_disk) {
+		if (bdev->bd_part)
+			kobject_uevent(&bdev->bd_part->kobj, action);
+		else
+			kobject_uevent(&bdev->bd_disk->kobj, action);
+	}
+}
+
 struct super_block *get_sb_bdev(struct file_system_type *fs_type,
 	int flags, const char *dev_name, void *data,
 	int (*fill_super)(struct super_block *, void *, int))
@@ -706,8 +717,10 @@ struct super_block *get_sb_bdev(struct file_system_type *fs_type,
 			up_write(&s->s_umount);
 			deactivate_super(s);
 			s = ERR_PTR(error);
-		} else
+		} else {
 			s->s_flags |= MS_ACTIVE;
+			bdev_uevent(bdev, KOBJ_MOUNT);
+		}
 	}
 
 	return s;
@@ -723,6 +736,7 @@ void kill_block_super(struct super_block *sb)
 {
 	struct block_device *bdev = sb->s_bdev;
 
+	bdev_uevent(bdev, KOBJ_UMOUNT);
 	generic_shutdown_super(sb);
 	sync_blockdev(bdev);
 	close_bdev_excl(bdev);
diff --git a/fs/udf/balloc.c b/fs/udf/balloc.c
index 4fae57d9d11..201049ac8a9 100644
--- a/fs/udf/balloc.c
+++ b/fs/udf/balloc.c
@@ -579,10 +579,9 @@ static void udf_table_free_blocks(struct super_block * sb,
 			{
 				loffset = nextoffset;
 				aed->lengthAllocDescs = cpu_to_le32(adsize);
-				if (obh)
-					sptr = UDF_I_DATA(inode) + nextoffset -  udf_file_entry_alloc_offset(inode) + UDF_I_LENEATTR(inode) - adsize;
-				else
-					sptr = obh->b_data + nextoffset - adsize;
+				sptr = UDF_I_DATA(inode) + nextoffset -
+					udf_file_entry_alloc_offset(inode) +
+					UDF_I_LENEATTR(inode) - adsize;
 				dptr = nbh->b_data + sizeof(struct allocExtDesc);
 				memcpy(dptr, sptr, adsize);
 				nextoffset = sizeof(struct allocExtDesc) + adsize;
diff --git a/fs/udf/namei.c b/fs/udf/namei.c
index ca732e79c48..ab9a7629d23 100644
--- a/fs/udf/namei.c
+++ b/fs/udf/namei.c
@@ -296,7 +296,7 @@ static struct dentry *
 udf_lookup(struct inode *dir, struct dentry *dentry, struct nameidata *nd)
 {
 	struct inode *inode = NULL;
-	struct fileIdentDesc cfi, *fi;
+	struct fileIdentDesc cfi;
 	struct udf_fileident_bh fibh;
 
 	if (dentry->d_name.len > UDF_NAME_LEN-2)
@@ -318,7 +318,7 @@ udf_lookup(struct inode *dir, struct dentry *dentry, struct nameidata *nd)
 	else
 #endif /* UDF_RECOVERY */
 
-	if ((fi = udf_find_entry(dir, dentry, &fibh, &cfi)))
+	if (udf_find_entry(dir, dentry, &fibh, &cfi))
 	{
 		if (fibh.sbh != fibh.ebh)
 			udf_release_data(fibh.ebh);
diff --git a/fs/ufs/inode.c b/fs/ufs/inode.c
index e0c04e36a05..3c3f62ce2ad 100644
--- a/fs/ufs/inode.c
+++ b/fs/ufs/inode.c
@@ -376,7 +376,7 @@ out:
  * This function gets the block which contains the fragment.
  */
 
-static int ufs_getfrag_block (struct inode *inode, sector_t fragment, struct buffer_head *bh_result, int create)
+int ufs_getfrag_block (struct inode *inode, sector_t fragment, struct buffer_head *bh_result, int create)
 {
 	struct super_block * sb = inode->i_sb;
 	struct ufs_sb_private_info * uspi = UFS_SB(sb)->s_uspi;
diff --git a/fs/ufs/super.c b/fs/ufs/super.c
index d4aacee593f..e9055ef7f5a 100644
--- a/fs/ufs/super.c
+++ b/fs/ufs/super.c
@@ -388,7 +388,8 @@ static int ufs_parse_options (char * options, unsigned * mount_options)
 /*
  * Read on-disk structures associated with cylinder groups
  */
-static int ufs_read_cylinder_structures (struct super_block *sb) {
+static int ufs_read_cylinder_structures (struct super_block *sb)
+{
 	struct ufs_sb_info * sbi = UFS_SB(sb);
 	struct ufs_sb_private_info * uspi;
 	struct ufs_super_block *usb;
@@ -415,6 +416,7 @@ static int ufs_read_cylinder_structures (struct super_block *sb) {
 	base = space = kmalloc(size, GFP_KERNEL);
 	if (!base)
 		goto failed; 
+	sbi->s_csp = (struct ufs_csum *)space;
 	for (i = 0; i < blks; i += uspi->s_fpb) {
 		size = uspi->s_bsize;
 		if (i + uspi->s_fpb > blks)
@@ -430,7 +432,6 @@ static int ufs_read_cylinder_structures (struct super_block *sb) {
 			goto failed;
 
 		ubh_ubhcpymem (space, ubh, size);
-		sbi->s_csp[ufs_fragstoblks(i)]=(struct ufs_csum *)space;
 
 		space += size;
 		ubh_brelse (ubh);
@@ -486,7 +487,8 @@ failed:
  * Put on-disk structures associated with cylinder groups and 
  * write them back to disk
  */
-static void ufs_put_cylinder_structures (struct super_block *sb) {
+static void ufs_put_cylinder_structures (struct super_block *sb)
+{
 	struct ufs_sb_info * sbi = UFS_SB(sb);
 	struct ufs_sb_private_info * uspi;
 	struct ufs_buffer_head * ubh;
@@ -499,7 +501,7 @@ static void ufs_put_cylinder_structures (struct super_block *sb) {
 
 	size = uspi->s_cssize;
 	blks = (size + uspi->s_fsize - 1) >> uspi->s_fshift;
-	base = space = (char*) sbi->s_csp[0];
+	base = space = (char*) sbi->s_csp;
 	for (i = 0; i < blks; i += uspi->s_fpb) {
 		size = uspi->s_bsize;
 		if (i + uspi->s_fpb > blks)
diff --git a/fs/ufs/truncate.c b/fs/ufs/truncate.c
index 61d2e35012a..02e86291ef8 100644
--- a/fs/ufs/truncate.c
+++ b/fs/ufs/truncate.c
@@ -29,6 +29,11 @@
  * Idea from Pierre del Perugia <delperug@gla.ecoledoc.ibp.fr>
  */
 
+/*
+ * Modified to avoid infinite loop on 2006 by
+ * Evgeniy Dushistov <dushistov@mail.ru>
+ */
+
 #include <linux/errno.h>
 #include <linux/fs.h>
 #include <linux/ufs_fs.h>
@@ -65,19 +70,16 @@
 #define DIRECT_BLOCK ((inode->i_size + uspi->s_bsize - 1) >> uspi->s_bshift)
 #define DIRECT_FRAGMENT ((inode->i_size + uspi->s_fsize - 1) >> uspi->s_fshift)
 
-#define DATA_BUFFER_USED(bh) \
-	(atomic_read(&bh->b_count)>1 || buffer_locked(bh))
 
 static int ufs_trunc_direct (struct inode * inode)
 {
 	struct ufs_inode_info *ufsi = UFS_I(inode);
 	struct super_block * sb;
 	struct ufs_sb_private_info * uspi;
-	struct buffer_head * bh;
 	__fs32 * p;
 	unsigned frag1, frag2, frag3, frag4, block1, block2;
 	unsigned frag_to_free, free_count;
-	unsigned i, j, tmp;
+	unsigned i, tmp;
 	int retry;
 	
 	UFSD(("ENTER\n"))
@@ -117,15 +119,7 @@ static int ufs_trunc_direct (struct inode * inode)
 		ufs_panic (sb, "ufs_trunc_direct", "internal error");
 	frag1 = ufs_fragnum (frag1);
 	frag2 = ufs_fragnum (frag2);
-	for (j = frag1; j < frag2; j++) {
-		bh = sb_find_get_block (sb, tmp + j);
-		if ((bh && DATA_BUFFER_USED(bh)) || tmp != fs32_to_cpu(sb, *p)) {
-			retry = 1;
-			brelse (bh);
-			goto next1;
-		}
-		bforget (bh);
-	}
+
 	inode->i_blocks -= (frag2-frag1) << uspi->s_nspfshift;
 	mark_inode_dirty(inode);
 	ufs_free_fragments (inode, tmp + frag1, frag2 - frag1);
@@ -140,15 +134,7 @@ next1:
 		tmp = fs32_to_cpu(sb, *p);
 		if (!tmp)
 			continue;
-		for (j = 0; j < uspi->s_fpb; j++) {
-			bh = sb_find_get_block(sb, tmp + j);
-			if ((bh && DATA_BUFFER_USED(bh)) || tmp != fs32_to_cpu(sb, *p)) {
-				retry = 1;
-				brelse (bh);
-				goto next2;
-			}
-			bforget (bh);
-		}
+
 		*p = 0;
 		inode->i_blocks -= uspi->s_nspb;
 		mark_inode_dirty(inode);
@@ -162,7 +148,6 @@ next1:
 			frag_to_free = tmp;
 			free_count = uspi->s_fpb;
 		}
-next2:;
 	}
 	
 	if (free_count > 0)
@@ -179,15 +164,7 @@ next2:;
 	if (!tmp )
 		ufs_panic(sb, "ufs_truncate_direct", "internal error");
 	frag4 = ufs_fragnum (frag4);
-	for (j = 0; j < frag4; j++) {
-		bh = sb_find_get_block (sb, tmp + j);
-		if ((bh && DATA_BUFFER_USED(bh)) || tmp != fs32_to_cpu(sb, *p)) {
-			retry = 1;
-			brelse (bh);
-			goto next1;
-		}
-		bforget (bh);
-	}
+
 	*p = 0;
 	inode->i_blocks -= frag4 << uspi->s_nspfshift;
 	mark_inode_dirty(inode);
@@ -204,9 +181,8 @@ static int ufs_trunc_indirect (struct inode * inode, unsigned offset, __fs32 *p)
 	struct super_block * sb;
 	struct ufs_sb_private_info * uspi;
 	struct ufs_buffer_head * ind_ubh;
-	struct buffer_head * bh;
 	__fs32 * ind;
-	unsigned indirect_block, i, j, tmp;
+	unsigned indirect_block, i, tmp;
 	unsigned frag_to_free, free_count;
 	int retry;
 
@@ -238,15 +214,7 @@ static int ufs_trunc_indirect (struct inode * inode, unsigned offset, __fs32 *p)
 		tmp = fs32_to_cpu(sb, *ind);
 		if (!tmp)
 			continue;
-		for (j = 0; j < uspi->s_fpb; j++) {
-			bh = sb_find_get_block(sb, tmp + j);
-			if ((bh && DATA_BUFFER_USED(bh)) || tmp != fs32_to_cpu(sb, *ind)) {
-				retry = 1;
-				brelse (bh);
-				goto next;
-			}
-			bforget (bh);
-		}	
+
 		*ind = 0;
 		ubh_mark_buffer_dirty(ind_ubh);
 		if (free_count == 0) {
@@ -261,7 +229,6 @@ static int ufs_trunc_indirect (struct inode * inode, unsigned offset, __fs32 *p)
 		}
 		inode->i_blocks -= uspi->s_nspb;
 		mark_inode_dirty(inode);
-next:;
 	}
 
 	if (free_count > 0) {
@@ -430,9 +397,7 @@ void ufs_truncate (struct inode * inode)
 	struct ufs_inode_info *ufsi = UFS_I(inode);
 	struct super_block * sb;
 	struct ufs_sb_private_info * uspi;
-	struct buffer_head * bh;
-	unsigned offset;
-	int err, retry;
+	int retry;
 	
 	UFSD(("ENTER\n"))
 	sb = inode->i_sb;
@@ -442,6 +407,9 @@ void ufs_truncate (struct inode * inode)
 		return;
 	if (IS_APPEND(inode) || IS_IMMUTABLE(inode))
 		return;
+
+	block_truncate_page(inode->i_mapping,	inode->i_size, ufs_getfrag_block);
+
 	lock_kernel();
 	while (1) {
 		retry = ufs_trunc_direct(inode);
@@ -457,15 +425,7 @@ void ufs_truncate (struct inode * inode)
 		blk_run_address_space(inode->i_mapping);
 		yield();
 	}
-	offset = inode->i_size & uspi->s_fshift;
-	if (offset) {
-		bh = ufs_bread (inode, inode->i_size >> uspi->s_fshift, 0, &err);
-		if (bh) {
-			memset (bh->b_data + offset, 0, uspi->s_fsize - offset);
-			mark_buffer_dirty (bh);
-			brelse (bh);
-		}
-	}
+
 	inode->i_mtime = inode->i_ctime = CURRENT_TIME_SEC;
 	ufsi->i_lastfrag = DIRECT_FRAGMENT;
 	unlock_kernel();
diff --git a/fs/xfs/linux-2.6/xfs_aops.c b/fs/xfs/linux-2.6/xfs_aops.c
index 12062678940..8f2beec526c 100644
--- a/fs/xfs/linux-2.6/xfs_aops.c
+++ b/fs/xfs/linux-2.6/xfs_aops.c
@@ -747,10 +747,11 @@ xfs_convert_page(
 			struct backing_dev_info *bdi;
 
 			bdi = inode->i_mapping->backing_dev_info;
+			wbc->nr_to_write--;
 			if (bdi_write_congested(bdi)) {
 				wbc->encountered_congestion = 1;
 				done = 1;
-			} else if (--wbc->nr_to_write <= 0) {
+			} else if (wbc->nr_to_write <= 0) {
 				done = 1;
 			}
 		}
@@ -1462,4 +1463,5 @@ 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..d7f6f2d8ac8 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);
 	}
@@ -659,6 +673,8 @@ linvfs_setattr(
 	if (ia_valid & ATTR_ATIME) {
 		vattr.va_mask |= XFS_AT_ATIME;
 		vattr.va_atime = attr->ia_atime;
+		if (ia_valid & ATTR_ATIME_SET)
+			inode->i_atime = attr->ia_atime;
 	}
 	if (ia_valid & ATTR_MTIME) {
 		vattr.va_mask |= XFS_AT_MTIME;