Merge branch 'for-next/dwc3' of git://git.kernel.org/pub/scm/linux/kernel/git/balbi/usb into usb-next

* 'for-next/dwc3' of git://git.kernel.org/pub/scm/linux/kernel/git/balbi/usb: (392 commits)
  usb: dwc3: ep0: fix for possible early delayed_status
  usb: dwc3: gadget: fix stream enable bit
  usb: dwc3: ep0: fix GetStatus handling (again)
  usb: dwc3: ep0: use dwc3_request for ep0 requsts instead of usb_request
  usb: dwc3: use correct hwparam register for power mgm check
  usb: dwc3: omap: move to module_platform_driver
  usb: dwc3: workaround: missing disconnect event
  usb: dwc3: workaround: missing USB3 Reset event
  usb: dwc3: workaround: U1/U2 -> U0 transiton
  usb: dwc3: gadget: return early in dwc3_cleanup_done_reqs()
  usb: dwc3: ep0: handle delayed_status again
  usb: dwc3: ep0: push ep0state into xfernotready processing
  usb: dwc3: fix sparse errors
  usb: dwc3: fix few coding style problems
  usb: dwc3: move generic dwc3 code from gadget into core
  usb: dwc3: use a helper function for operation mode setting
  usb: dwc3: ep0: don't use ep0in for transfers
  usb: dwc3: ep0: use proper endianess in SetFeature for wIndex
  usb: dwc3: core: drop DWC3_EVENT_BUFFERS_MAX
  usb: dwc3: omap: add multiple instances support to OMAP
  ...

21 files changed, 443 insertions, 322 deletions

diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c
index f0d5718d2587..2ad813674d77 100644
--- a/fs/btrfs/extent-tree.c
+++ b/fs/btrfs/extent-tree.c
@@ -5107,11 +5107,11 @@ static noinline int find_free_extent(struct btrfs_trans_handle *trans,
         struct btrfs_root *root = orig_root->fs_info->extent_root;
         struct btrfs_free_cluster *last_ptr = NULL;
         struct btrfs_block_group_cache *block_group = NULL;
+        struct btrfs_block_group_cache *used_block_group;
         int empty_cluster = 2 * 1024 * 1024;
         int allowed_chunk_alloc = 0;
         int done_chunk_alloc = 0;
         struct btrfs_space_info *space_info;
-        int last_ptr_loop = 0;
         int loop = 0;
         int index = 0;
         int alloc_type = (data & BTRFS_BLOCK_GROUP_DATA) ?
@@ -5173,6 +5173,7 @@ static noinline int find_free_extent(struct btrfs_trans_handle *trans,
 ideal_cache:
                 block_group = btrfs_lookup_block_group(root->fs_info,
                                                        search_start);
+                used_block_group = block_group;
                 /*
                  * we don't want to use the block group if it doesn't match our
                  * allocation bits, or if its not cached.
@@ -5210,6 +5211,7 @@ search:
                 u64 offset;
                 int cached;
 
+                used_block_group = block_group;
                 btrfs_get_block_group(block_group);
                 search_start = block_group->key.objectid;
 
@@ -5286,71 +5288,62 @@ alloc:
                 spin_unlock(&block_group->free_space_ctl->tree_lock);
 
                 /*
-                 * Ok we want to try and use the cluster allocator, so lets look
-                 * there, unless we are on LOOP_NO_EMPTY_SIZE, since we will
-                 * have tried the cluster allocator plenty of times at this
-                 * point and not have found anything, so we are likely way too
-                 * fragmented for the clustering stuff to find anything, so lets
-                 * just skip it and let the allocator find whatever block it can
-                 * find
+                 * Ok we want to try and use the cluster allocator, so
+                 * lets look there
                  */
-                if (last_ptr && loop < LOOP_NO_EMPTY_SIZE) {
+                if (last_ptr) {
                         /*
                          * the refill lock keeps out other
                          * people trying to start a new cluster
                          */
                         spin_lock(&last_ptr->refill_lock);
-                        if (!last_ptr->block_group ||
-                            last_ptr->block_group->ro ||
-                            !block_group_bits(last_ptr->block_group, data))
+                        used_block_group = last_ptr->block_group;
+                        if (used_block_group != block_group &&
+                            (!used_block_group ||
+                             used_block_group->ro ||
+                             !block_group_bits(used_block_group, data))) {
+                                used_block_group = block_group;
                                 goto refill_cluster;
+                        }
+
+                        if (used_block_group != block_group)
+                                btrfs_get_block_group(used_block_group);
 
-                        offset = btrfs_alloc_from_cluster(block_group, last_ptr,
-                                                 num_bytes, search_start);
+                        offset = btrfs_alloc_from_cluster(used_block_group,
+                          last_ptr, num_bytes, used_block_group->key.objectid);
                         if (offset) {
                                 /* we have a block, we're done */
                                 spin_unlock(&last_ptr->refill_lock);
                                 goto checks;
                         }
 
-                        spin_lock(&last_ptr->lock);
-                        /*
-                         * whoops, this cluster doesn't actually point to
-                         * this block group.  Get a ref on the block
-                         * group is does point to and try again
-                         */
-                        if (!last_ptr_loop && last_ptr->block_group &&
-                            last_ptr->block_group != block_group &&
-                            index <=
-                                 get_block_group_index(last_ptr->block_group)) {
-
-                                btrfs_put_block_group(block_group);
-                                block_group = last_ptr->block_group;
-                                btrfs_get_block_group(block_group);
-                                spin_unlock(&last_ptr->lock);
-                                spin_unlock(&last_ptr->refill_lock);
-
-                                last_ptr_loop = 1;
-                                search_start = block_group->key.objectid;
-                                /*
-                                 * we know this block group is properly
-                                 * in the list because
-                                 * btrfs_remove_block_group, drops the
-                                 * cluster before it removes the block
-                                 * group from the list
-                                 */
-                                goto have_block_group;
+                        WARN_ON(last_ptr->block_group != used_block_group);
+                        if (used_block_group != block_group) {
+                                btrfs_put_block_group(used_block_group);
+                                used_block_group = block_group;
                         }
-                        spin_unlock(&last_ptr->lock);
 refill_cluster:
+                        BUG_ON(used_block_group != block_group);
+                        /* If we are on LOOP_NO_EMPTY_SIZE, we can't
+                         * set up a new clusters, so lets just skip it
+                         * and let the allocator find whatever block
+                         * it can find.  If we reach this point, we
+                         * will have tried the cluster allocator
+                         * plenty of times and not have found
+                         * anything, so we are likely way too
+                         * fragmented for the clustering stuff to find
+                         * anything.  */
+                        if (loop >= LOOP_NO_EMPTY_SIZE) {
+                                spin_unlock(&last_ptr->refill_lock);
+                                goto unclustered_alloc;
+                        }
+
                         /*
                          * this cluster didn't work out, free it and
                          * start over
                          */
                         btrfs_return_cluster_to_free_space(NULL, last_ptr);
 
-                        last_ptr_loop = 0;
-
                         /* allocate a cluster in this block group */
                         ret = btrfs_find_space_cluster(trans, root,
                                                block_group, last_ptr,
@@ -5390,6 +5383,7 @@ refill_cluster:
                         goto loop;
                 }
 
+unclustered_alloc:
                 offset = btrfs_find_space_for_alloc(block_group, search_start,
                                                     num_bytes, empty_size);
                 /*
@@ -5416,14 +5410,14 @@ checks:
                 search_start = stripe_align(root, offset);
                 /* move on to the next group */
                 if (search_start + num_bytes >= search_end) {
-                        btrfs_add_free_space(block_group, offset, num_bytes);
+                        btrfs_add_free_space(used_block_group, offset, num_bytes);
                         goto loop;
                 }
 
                 /* move on to the next group */
                 if (search_start + num_bytes >
-                    block_group->key.objectid + block_group->key.offset) {
-                        btrfs_add_free_space(block_group, offset, num_bytes);
+                    used_block_group->key.objectid + used_block_group->key.offset) {
+                        btrfs_add_free_space(used_block_group, offset, num_bytes);
                         goto loop;
                 }
 
@@ -5431,14 +5425,14 @@ checks:
                 ins->offset = num_bytes;
 
                 if (offset < search_start)
-                        btrfs_add_free_space(block_group, offset,
+                        btrfs_add_free_space(used_block_group, offset,
                                              search_start - offset);
                 BUG_ON(offset > search_start);
 
-                ret = btrfs_update_reserved_bytes(block_group, num_bytes,
+                ret = btrfs_update_reserved_bytes(used_block_group, num_bytes,
                                                   alloc_type);
                 if (ret == -EAGAIN) {
-                        btrfs_add_free_space(block_group, offset, num_bytes);
+                        btrfs_add_free_space(used_block_group, offset, num_bytes);
                         goto loop;
                 }
 
@@ -5447,15 +5441,19 @@ checks:
                 ins->offset = num_bytes;
 
                 if (offset < search_start)
-                        btrfs_add_free_space(block_group, offset,
+                        btrfs_add_free_space(used_block_group, offset,
                                              search_start - offset);
                 BUG_ON(offset > search_start);
+                if (used_block_group != block_group)
+                        btrfs_put_block_group(used_block_group);
                 btrfs_put_block_group(block_group);
                 break;
 loop:
                 failed_cluster_refill = false;
                 failed_alloc = false;
                 BUG_ON(index != get_block_group_index(block_group));
+                if (used_block_group != block_group)
+                        btrfs_put_block_group(used_block_group);
                 btrfs_put_block_group(block_group);
         }
         up_read(&space_info->groups_sem);
diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c
index be1bf627a14b..49f3c9dc09f4 100644
--- a/fs/btrfs/extent_io.c
+++ b/fs/btrfs/extent_io.c
@@ -935,8 +935,10 @@ again:
         node = tree_search(tree, start);
         if (!node) {
                 prealloc = alloc_extent_state_atomic(prealloc);
-                if (!prealloc)
-                        return -ENOMEM;
+                if (!prealloc) {
+                        err = -ENOMEM;
+                        goto out;
+                }
                 err = insert_state(tree, prealloc, start, end, &bits);
                 prealloc = NULL;
                 BUG_ON(err == -EEXIST);
@@ -992,8 +994,10 @@ hit_next:
          */
         if (state->start < start) {
                 prealloc = alloc_extent_state_atomic(prealloc);
-                if (!prealloc)
-                        return -ENOMEM;
+                if (!prealloc) {
+                        err = -ENOMEM;
+                        goto out;
+                }
                 err = split_state(tree, state, prealloc, start);
                 BUG_ON(err == -EEXIST);
                 prealloc = NULL;
@@ -1024,8 +1028,10 @@ hit_next:
                         this_end = last_start - 1;
 
                 prealloc = alloc_extent_state_atomic(prealloc);
-                if (!prealloc)
-                        return -ENOMEM;
+                if (!prealloc) {
+                        err = -ENOMEM;
+                        goto out;
+                }
 
                 /*
                  * Avoid to free 'prealloc' if it can be merged with
@@ -1051,8 +1057,10 @@ hit_next:
          */
         if (state->start <= end && state->end > end) {
                 prealloc = alloc_extent_state_atomic(prealloc);
-                if (!prealloc)
-                        return -ENOMEM;
+                if (!prealloc) {
+                        err = -ENOMEM;
+                        goto out;
+                }
 
                 err = split_state(tree, state, prealloc, end + 1);
                 BUG_ON(err == -EEXIST);
diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c
index c37433d3cd82..0a8c8f8304b1 100644
--- a/fs/btrfs/volumes.c
+++ b/fs/btrfs/volumes.c
@@ -1611,7 +1611,7 @@ int btrfs_init_new_device(struct btrfs_root *root, char *device_path)
         if ((sb->s_flags & MS_RDONLY) && !root->fs_info->fs_devices->seeding)
                 return -EINVAL;
 
-        bdev = blkdev_get_by_path(device_path, FMODE_EXCL,
+        bdev = blkdev_get_by_path(device_path, FMODE_WRITE | FMODE_EXCL,
                                   root->fs_info->bdev_holder);
         if (IS_ERR(bdev))
                 return PTR_ERR(bdev);
diff --git a/fs/cifs/connect.c b/fs/cifs/connect.c
index d6a972df0338..8cd4b52d4217 100644
--- a/fs/cifs/connect.c
+++ b/fs/cifs/connect.c
@@ -441,6 +441,8 @@ cifs_readv_from_socket(struct TCP_Server_Info *server, struct kvec *iov_orig,
         smb_msg.msg_controllen = 0;
 
         for (total_read = 0; to_read; total_read += length, to_read -= length) {
+                try_to_freeze();
+
                 if (server_unresponsive(server)) {
                         total_read = -EAGAIN;
                         break;
diff --git a/fs/cifs/file.c b/fs/cifs/file.c
index cf0b1539b321..4dd9283885e7 100644
--- a/fs/cifs/file.c
+++ b/fs/cifs/file.c
@@ -702,6 +702,13 @@ cifs_find_lock_conflict(struct cifsInodeInfo *cinode, struct cifsLockInfo *lock,
                                          lock->type, lock->netfid, conf_lock);
 }
 
+/*
+ * Check if there is another lock that prevents us to set the lock (mandatory
+ * style). If such a lock exists, update the flock structure with its
+ * properties. Otherwise, set the flock type to F_UNLCK if we can cache brlocks
+ * or leave it the same if we can't. Returns 0 if we don't need to request to
+ * the server or 1 otherwise.
+ */
 static int
 cifs_lock_test(struct cifsInodeInfo *cinode, __u64 offset, __u64 length,
                __u8 type, __u16 netfid, struct file_lock *flock)
@@ -739,6 +746,12 @@ cifs_lock_add(struct cifsInodeInfo *cinode, struct cifsLockInfo *lock)
         mutex_unlock(&cinode->lock_mutex);
 }
 
+/*
+ * Set the byte-range lock (mandatory style). Returns:
+ * 1) 0, if we set the lock and don't need to request to the server;
+ * 2) 1, if no locks prevent us but we need to request to the server;
+ * 3) -EACCESS, if there is a lock that prevents us and wait is false.
+ */
 static int
 cifs_lock_add_if(struct cifsInodeInfo *cinode, struct cifsLockInfo *lock,
                  bool wait)
@@ -778,6 +791,13 @@ try_again:
         return rc;
 }
 
+/*
+ * Check if there is another lock that prevents us to set the lock (posix
+ * style). If such a lock exists, update the flock structure with its
+ * properties. Otherwise, set the flock type to F_UNLCK if we can cache brlocks
+ * or leave it the same if we can't. Returns 0 if we don't need to request to
+ * the server or 1 otherwise.
+ */
 static int
 cifs_posix_lock_test(struct file *file, struct file_lock *flock)
 {
@@ -800,6 +820,12 @@ cifs_posix_lock_test(struct file *file, struct file_lock *flock)
         return rc;
 }
 
+/*
+ * Set the byte-range lock (posix style). Returns:
+ * 1) 0, if we set the lock and don't need to request to the server;
+ * 2) 1, if we need to request to the server;
+ * 3) <0, if the error occurs while setting the lock.
+ */
 static int
 cifs_posix_lock_set(struct file *file, struct file_lock *flock)
 {
diff --git a/fs/cifs/readdir.c b/fs/cifs/readdir.c
index 5de03ec20144..a090bbe6ee29 100644
--- a/fs/cifs/readdir.c
+++ b/fs/cifs/readdir.c
@@ -554,7 +554,10 @@ static int find_cifs_entry(const int xid, struct cifs_tcon *pTcon,
                                  rc);
                         return rc;
                 }
-                cifs_save_resume_key(cifsFile->srch_inf.last_entry, cifsFile);
+                /* FindFirst/Next set last_entry to NULL on malformed reply */
+                if (cifsFile->srch_inf.last_entry)
+                        cifs_save_resume_key(cifsFile->srch_inf.last_entry,
+                                                cifsFile);
         }
 
         while ((index_to_find >= cifsFile->srch_inf.index_of_last_entry) &&
@@ -562,7 +565,10 @@ static int find_cifs_entry(const int xid, struct cifs_tcon *pTcon,
                 cFYI(1, "calling findnext2");
                 rc = CIFSFindNext(xid, pTcon, cifsFile->netfid,
                                   &cifsFile->srch_inf);
-                cifs_save_resume_key(cifsFile->srch_inf.last_entry, cifsFile);
+                /* FindFirst/Next set last_entry to NULL on malformed reply */
+                if (cifsFile->srch_inf.last_entry)
+                        cifs_save_resume_key(cifsFile->srch_inf.last_entry,
+                                                cifsFile);
                 if (rc)
                         return -ENOENT;
         }
diff --git a/fs/cifs/smbencrypt.c b/fs/cifs/smbencrypt.c
index 7cacba12b8f1..80d850881938 100644
--- a/fs/cifs/smbencrypt.c
+++ b/fs/cifs/smbencrypt.c
@@ -209,7 +209,7 @@ E_md4hash(const unsigned char *passwd, unsigned char *p16,
 {
         int rc;
         int len;
-        __u16 wpwd[129];
+        __le16 wpwd[129];
 
         /* Password cannot be longer than 128 characters */
         if (passwd) /* Password must be converted to NT unicode */
@@ -219,8 +219,8 @@ E_md4hash(const unsigned char *passwd, unsigned char *p16,
                 *wpwd = 0; /* Ensure string is null terminated */
         }
 
-        rc = mdfour(p16, (unsigned char *) wpwd, len * sizeof(__u16));
-        memset(wpwd, 0, 129 * sizeof(__u16));
+        rc = mdfour(p16, (unsigned char *) wpwd, len * sizeof(__le16));
+        memset(wpwd, 0, 129 * sizeof(__le16));
 
         return rc;
 }
diff --git a/fs/dcache.c b/fs/dcache.c
index 10ba92def3f6..89509b5a090e 100644
--- a/fs/dcache.c
+++ b/fs/dcache.c
@@ -2439,16 +2439,14 @@ static int prepend_name(char **buffer, int *buflen, struct qstr *name)
 /**
  * prepend_path - Prepend path string to a buffer
  * @path: the dentry/vfsmount to report
- * @root: root vfsmnt/dentry (may be modified by this function)
+ * @root: root vfsmnt/dentry
  * @buffer: pointer to the end of the buffer
  * @buflen: pointer to buffer length
  *
  * Caller holds the rename_lock.
- *
- * If path is not reachable from the supplied root, then the value of
- * root is changed (without modifying refcounts).
  */
-static int prepend_path(const struct path *path, struct path *root,
+static int prepend_path(const struct path *path,
+                        const struct path *root,
                         char **buffer, int *buflen)
 {
         struct dentry *dentry = path->dentry;
@@ -2483,10 +2481,10 @@ static int prepend_path(const struct path *path, struct path *root,
                 dentry = parent;
         }
 
-out:
         if (!error && !slash)
                 error = prepend(buffer, buflen, "/", 1);
 
+out:
         br_read_unlock(vfsmount_lock);
         return error;
 
@@ -2500,15 +2498,17 @@ global_root:
                 WARN(1, "Root dentry has weird name <%.*s>\n",
                      (int) dentry->d_name.len, dentry->d_name.name);
         }
-        root->mnt = vfsmnt;
-        root->dentry = dentry;
+        if (!slash)
+                error = prepend(buffer, buflen, "/", 1);
+        if (!error)
+                error = vfsmnt->mnt_ns ? 1 : 2;
         goto out;
 }
 
 /**
  * __d_path - return the path of a dentry
  * @path: the dentry/vfsmount to report
- * @root: root vfsmnt/dentry (may be modified by this function)
+ * @root: root vfsmnt/dentry
  * @buf: buffer to return value in
  * @buflen: buffer length
  *
@@ -2519,10 +2519,10 @@ global_root:
  *
  * "buflen" should be positive.
  *
- * If path is not reachable from the supplied root, then the value of
- * root is changed (without modifying refcounts).
+ * If the path is not reachable from the supplied root, return %NULL.
  */
-char *__d_path(const struct path *path, struct path *root,
+char *__d_path(const struct path *path,
+               const struct path *root,
                char *buf, int buflen)
 {
         char *res = buf + buflen;
@@ -2533,7 +2533,28 @@ char *__d_path(const struct path *path, struct path *root,
         error = prepend_path(path, root, &res, &buflen);
         write_sequnlock(&rename_lock);
 
-        if (error)
+        if (error < 0)
+                return ERR_PTR(error);
+        if (error > 0)
+                return NULL;
+        return res;
+}
+
+char *d_absolute_path(const struct path *path,
+               char *buf, int buflen)
+{
+        struct path root = {};
+        char *res = buf + buflen;
+        int error;
+
+        prepend(&res, &buflen, "\0", 1);
+        write_seqlock(&rename_lock);
+        error = prepend_path(path, &root, &res, &buflen);
+        write_sequnlock(&rename_lock);
+
+        if (error > 1)
+                error = -EINVAL;
+        if (error < 0)
                 return ERR_PTR(error);
         return res;
 }
@@ -2541,8 +2562,9 @@ char *__d_path(const struct path *path, struct path *root,
 /*
  * same as __d_path but appends "(deleted)" for unlinked files.
  */
-static int path_with_deleted(const struct path *path, struct path *root,
-                                 char **buf, int *buflen)
+static int path_with_deleted(const struct path *path,
+                             const struct path *root,
+                             char **buf, int *buflen)
 {
         prepend(buf, buflen, "\0", 1);
         if (d_unlinked(path->dentry)) {
@@ -2579,7 +2601,6 @@ char *d_path(const struct path *path, char *buf, int buflen)
 {
         char *res = buf + buflen;
         struct path root;
-        struct path tmp;
         int error;
 
         /*
@@ -2594,9 +2615,8 @@ char *d_path(const struct path *path, char *buf, int buflen)
 
         get_fs_root(current->fs, &root);
         write_seqlock(&rename_lock);
-        tmp = root;
-        error = path_with_deleted(path, &tmp, &res, &buflen);
-        if (error)
+        error = path_with_deleted(path, &root, &res, &buflen);
+        if (error < 0)
                 res = ERR_PTR(error);
         write_sequnlock(&rename_lock);
         path_put(&root);
@@ -2617,7 +2637,6 @@ char *d_path_with_unreachable(const struct path *path, char *buf, int buflen)
 {
         char *res = buf + buflen;
         struct path root;
-        struct path tmp;
         int error;
 
         if (path->dentry->d_op && path->dentry->d_op->d_dname)
@@ -2625,9 +2644,8 @@ char *d_path_with_unreachable(const struct path *path, char *buf, int buflen)
 
         get_fs_root(current->fs, &root);
         write_seqlock(&rename_lock);
-        tmp = root;
-        error = path_with_deleted(path, &tmp, &res, &buflen);
-        if (!error && !path_equal(&tmp, &root))
+        error = path_with_deleted(path, &root, &res, &buflen);
+        if (error > 0)
                 error = prepend_unreachable(&res, &buflen);
         write_sequnlock(&rename_lock);
         path_put(&root);
@@ -2758,19 +2776,18 @@ SYSCALL_DEFINE2(getcwd, char __user *, buf, unsigned long, size)
         write_seqlock(&rename_lock);
         if (!d_unlinked(pwd.dentry)) {
                 unsigned long len;
-                struct path tmp = root;
                 char *cwd = page + PAGE_SIZE;
                 int buflen = PAGE_SIZE;
 
                 prepend(&cwd, &buflen, "\0", 1);
-                error = prepend_path(&pwd, &tmp, &cwd, &buflen);
+                error = prepend_path(&pwd, &root, &cwd, &buflen);
                 write_sequnlock(&rename_lock);
 
-                if (error)
+                if (error < 0)
                         goto out;
 
                 /* Unreachable from current root */
-                if (!path_equal(&tmp, &root)) {
+                if (error > 0) {
                         error = prepend_unreachable(&cwd, &buflen);
                         if (error)
                                 goto out;
diff --git a/fs/namespace.c b/fs/namespace.c
index 6d3a1963879b..cfc6d4448aa5 100644
--- a/fs/namespace.c
+++ b/fs/namespace.c
@@ -1048,15 +1048,12 @@ static int show_mountinfo(struct seq_file *m, void *v)
         if (err)
                 goto out;
         seq_putc(m, ' ');
-        seq_path_root(m, &mnt_path, &root, " \t\n\\");
-        if (root.mnt != p->root.mnt || root.dentry != p->root.dentry) {
-                /*
-                 * Mountpoint is outside root, discard that one.  Ugly,
-                 * but less so than trying to do that in iterator in a
-                 * race-free way (due to renames).
-                 */
-                return SEQ_SKIP;
-        }
+
+        /* mountpoints outside of chroot jail will give SEQ_SKIP on this */
+        err = seq_path_root(m, &mnt_path, &root, " \t\n\\");
+        if (err)
+                goto out;
+
         seq_puts(m, mnt->mnt_flags & MNT_READONLY ? " ro" : " rw");
         show_mnt_opts(m, mnt);
 
@@ -2776,3 +2773,8 @@ void kern_unmount(struct vfsmount *mnt)
         }
 }
 EXPORT_SYMBOL(kern_unmount);
+
+bool our_mnt(struct vfsmount *mnt)
+{
+        return check_mnt(mnt);
+}
diff --git a/fs/proc/meminfo.c b/fs/proc/meminfo.c
index 586174168e2a..80e4645f7990 100644
--- a/fs/proc/meminfo.c
+++ b/fs/proc/meminfo.c
@@ -131,12 +131,13 @@ static int meminfo_proc_show(struct seq_file *m, void *v)
                 K(i.freeswap),
                 K(global_page_state(NR_FILE_DIRTY)),
                 K(global_page_state(NR_WRITEBACK)),
-                K(global_page_state(NR_ANON_PAGES)
 #ifdef CONFIG_TRANSPARENT_HUGEPAGE
+                K(global_page_state(NR_ANON_PAGES)
                   + global_page_state(NR_ANON_TRANSPARENT_HUGEPAGES) *
-                  HPAGE_PMD_NR
+                  HPAGE_PMD_NR),
+#else
+                K(global_page_state(NR_ANON_PAGES)),
 #endif
-                  ),
                 K(global_page_state(NR_FILE_MAPPED)),
                 K(global_page_state(NR_SHMEM)),
                 K(global_page_state(NR_SLAB_RECLAIMABLE) +
diff --git a/fs/proc/stat.c b/fs/proc/stat.c
index 42b274da92c3..2a30d67dd6b8 100644
--- a/fs/proc/stat.c
+++ b/fs/proc/stat.c
@@ -32,7 +32,7 @@ static cputime64_t get_idle_time(int cpu)
                 idle = kstat_cpu(cpu).cpustat.idle;
                 idle = cputime64_add(idle, arch_idle_time(cpu));
         } else
-                idle = usecs_to_cputime(idle_time);
+                idle = nsecs_to_jiffies64(1000 * idle_time);
 
         return idle;
 }
@@ -46,7 +46,7 @@ static cputime64_t get_iowait_time(int cpu)
                 /* !NO_HZ so we can rely on cpustat.iowait */
                 iowait = kstat_cpu(cpu).cpustat.iowait;
         else
-                iowait = usecs_to_cputime(iowait_time);
+                iowait = nsecs_to_jiffies64(1000 * iowait_time);
 
         return iowait;
 }
diff --git a/fs/seq_file.c b/fs/seq_file.c
index 05d6b0e78c95..dba43c3ea3af 100644
--- a/fs/seq_file.c
+++ b/fs/seq_file.c
@@ -449,8 +449,6 @@ EXPORT_SYMBOL(seq_path);
 
 /*
  * Same as seq_path, but relative to supplied root.
- *
- * root may be changed, see __d_path().
  */
 int seq_path_root(struct seq_file *m, struct path *path, struct path *root,
                   char *esc)
@@ -463,6 +461,8 @@ int seq_path_root(struct seq_file *m, struct path *path, struct path *root,
                 char *p;
 
                 p = __d_path(path, root, buf, size);
+                if (!p)
+                        return SEQ_SKIP;
                 res = PTR_ERR(p);
                 if (!IS_ERR(p)) {
                         char *end = mangle_path(buf, p, esc);
@@ -474,7 +474,7 @@ int seq_path_root(struct seq_file *m, struct path *path, struct path *root,
         }
         seq_commit(m, res);
 
-        return res < 0 ? res : 0;
+        return res < 0 && res != -ENAMETOOLONG ? res : 0;
 }
 
 /*
diff --git a/fs/xfs/xfs_acl.c b/fs/xfs/xfs_acl.c
index b6c4b3795c4a..76e4266d2e7e 100644
--- a/fs/xfs/xfs_acl.c
+++ b/fs/xfs/xfs_acl.c
@@ -42,6 +42,8 @@ xfs_acl_from_disk(struct xfs_acl *aclp)
         int count, i;
 
         count = be32_to_cpu(aclp->acl_cnt);
+        if (count > XFS_ACL_MAX_ENTRIES)
+                return ERR_PTR(-EFSCORRUPTED);
 
         acl = posix_acl_alloc(count, GFP_KERNEL);
         if (!acl)
diff --git a/fs/xfs/xfs_attr_leaf.c b/fs/xfs/xfs_attr_leaf.c
index d4906e7c9787..c1b55e596551 100644
--- a/fs/xfs/xfs_attr_leaf.c
+++ b/fs/xfs/xfs_attr_leaf.c
@@ -110,6 +110,7 @@ xfs_attr_namesp_match(int arg_flags, int ondisk_flags)
 /*
  * Query whether the requested number of additional bytes of extended
  * attribute space will be able to fit inline.
+ *
  * Returns zero if not, else the di_forkoff fork offset to be used in the
  * literal area for attribute data once the new bytes have been added.
  *
@@ -122,7 +123,7 @@ xfs_attr_shortform_bytesfit(xfs_inode_t *dp, int bytes)
         int offset;
         int minforkoff; /* lower limit on valid forkoff locations */
         int maxforkoff; /* upper limit on valid forkoff locations */
-        int dsize;      
+        int dsize;
         xfs_mount_t *mp = dp->i_mount;
 
         offset = (XFS_LITINO(mp) - bytes) >> 3; /* rounded down */
@@ -136,47 +137,60 @@ xfs_attr_shortform_bytesfit(xfs_inode_t *dp, int bytes)
                 return (offset >= minforkoff) ? minforkoff : 0;
         }
 
-        if (!(mp->m_flags & XFS_MOUNT_ATTR2)) {
-                if (bytes <= XFS_IFORK_ASIZE(dp))
-                        return dp->i_d.di_forkoff;
+        /*
+         * If the requested numbers of bytes is smaller or equal to the
+         * current attribute fork size we can always proceed.
+         *
+         * Note that if_bytes in the data fork might actually be larger than
+         * the current data fork size is due to delalloc extents. In that
+         * case either the extent count will go down when they are converted
+         * to real extents, or the delalloc conversion will take care of the
+         * literal area rebalancing.
+         */
+        if (bytes <= XFS_IFORK_ASIZE(dp))
+                return dp->i_d.di_forkoff;
+
+        /*
+         * For attr2 we can try to move the forkoff if there is space in the
+         * literal area, but for the old format we are done if there is no
+         * space in the fixed attribute fork.
+         */
+        if (!(mp->m_flags & XFS_MOUNT_ATTR2))
                 return 0;
-        }
 
         dsize = dp->i_df.if_bytes;
-        
+
         switch (dp->i_d.di_format) {
         case XFS_DINODE_FMT_EXTENTS:
-                /* 
+                /*
                  * If there is no attr fork and the data fork is extents, 
-                 * determine if creating the default attr fork will result 
-                 * in the extents form migrating to btree. If so, the 
-                 * minimum offset only needs to be the space required for 
+                 * determine if creating the default attr fork will result
+                 * in the extents form migrating to btree. If so, the
+                 * minimum offset only needs to be the space required for
                  * the btree root.
-                 */ 
+                 */
                 if (!dp->i_d.di_forkoff && dp->i_df.if_bytes >
                     xfs_default_attroffset(dp))
                         dsize = XFS_BMDR_SPACE_CALC(MINDBTPTRS);
                 break;
-                
         case XFS_DINODE_FMT_BTREE:
                 /*
-                 * If have data btree then keep forkoff if we have one,
-                 * otherwise we are adding a new attr, so then we set 
-                 * minforkoff to where the btree root can finish so we have 
+                 * If we have a data btree then keep forkoff if we have one,
+                 * otherwise we are adding a new attr, so then we set
+                 * minforkoff to where the btree root can finish so we have
                  * plenty of room for attrs
                  */
                 if (dp->i_d.di_forkoff) {
-                        if (offset < dp->i_d.di_forkoff) 
+                        if (offset < dp->i_d.di_forkoff)
                                 return 0;
-                        else 
-                                return dp->i_d.di_forkoff;
-                } else
-                        dsize = XFS_BMAP_BROOT_SPACE(dp->i_df.if_broot);
+                        return dp->i_d.di_forkoff;
+                }
+                dsize = XFS_BMAP_BROOT_SPACE(dp->i_df.if_broot);
                 break;
         }
-        
-        /* 
-         * A data fork btree root must have space for at least 
+
+        /*
+         * A data fork btree root must have space for at least
          * MINDBTPTRS key/ptr pairs if the data fork is small or empty.
          */
         minforkoff = MAX(dsize, XFS_BMDR_SPACE_CALC(MINDBTPTRS));
@@ -186,10 +200,10 @@ xfs_attr_shortform_bytesfit(xfs_inode_t *dp, int bytes)
         maxforkoff = XFS_LITINO(mp) - XFS_BMDR_SPACE_CALC(MINABTPTRS);
         maxforkoff = maxforkoff >> 3;   /* rounded down */
 
-        if (offset >= minforkoff && offset < maxforkoff)
-                return offset;
         if (offset >= maxforkoff)
                 return maxforkoff;
+        if (offset >= minforkoff)
+                return offset;
         return 0;
 }
 
diff --git a/fs/xfs/xfs_bmap.c b/fs/xfs/xfs_bmap.c
index c68baeb0974a..d0ab78837057 100644
--- a/fs/xfs/xfs_bmap.c
+++ b/fs/xfs/xfs_bmap.c
@@ -2383,6 +2383,8 @@ xfs_bmap_btalloc(
         int             tryagain;
         int             error;
 
+        ASSERT(ap->length);
+
         mp = ap->ip->i_mount;
         align = ap->userdata ? xfs_get_extsz_hint(ap->ip) : 0;
         if (unlikely(align)) {
@@ -4629,6 +4631,8 @@ xfs_bmapi_allocate(
         int                     error;
         int                     rt;
 
+        ASSERT(bma->length > 0);
+
         rt = (whichfork == XFS_DATA_FORK) && XFS_IS_REALTIME_INODE(bma->ip);
 
         /*
@@ -4849,6 +4853,7 @@ xfs_bmapi_write(
         ASSERT(*nmap <= XFS_BMAP_MAX_NMAP);
         ASSERT(!(flags & XFS_BMAPI_IGSTATE));
         ASSERT(tp != NULL);
+        ASSERT(len > 0);
 
         whichfork = (flags & XFS_BMAPI_ATTRFORK) ?
                 XFS_ATTR_FORK : XFS_DATA_FORK;
@@ -4918,9 +4923,22 @@ xfs_bmapi_write(
                         bma.eof = eof;
                         bma.conv = !!(flags & XFS_BMAPI_CONVERT);
                         bma.wasdel = wasdelay;
-                        bma.length = len;
                         bma.offset = bno;
 
+                        /*
+                         * There's a 32/64 bit type mismatch between the
+                         * allocation length request (which can be 64 bits in
+                         * length) and the bma length request, which is
+                         * xfs_extlen_t and therefore 32 bits. Hence we have to
+                         * check for 32-bit overflows and handle them here.
+                         */
+                        if (len > (xfs_filblks_t)MAXEXTLEN)
+                                bma.length = MAXEXTLEN;
+                        else
+                                bma.length = len;
+
+                        ASSERT(len > 0);
+                        ASSERT(bma.length > 0);
                         error = xfs_bmapi_allocate(&bma, flags);
                         if (error)
                                 goto error0;
diff --git a/fs/xfs/xfs_export.c b/fs/xfs/xfs_export.c
index da108977b21f..558910f5e3c0 100644
--- a/fs/xfs/xfs_export.c
+++ b/fs/xfs/xfs_export.c
@@ -98,22 +98,22 @@ xfs_fs_encode_fh(
         switch (fileid_type) {
         case FILEID_INO32_GEN_PARENT:
                 spin_lock(&dentry->d_lock);
-                fid->i32.parent_ino = dentry->d_parent->d_inode->i_ino;
+                fid->i32.parent_ino = XFS_I(dentry->d_parent->d_inode)->i_ino;
                 fid->i32.parent_gen = dentry->d_parent->d_inode->i_generation;
                 spin_unlock(&dentry->d_lock);
                 /*FALLTHRU*/
         case FILEID_INO32_GEN:
-                fid->i32.ino = inode->i_ino;
+                fid->i32.ino = XFS_I(inode)->i_ino;
                 fid->i32.gen = inode->i_generation;
                 break;
         case FILEID_INO32_GEN_PARENT | XFS_FILEID_TYPE_64FLAG:
                 spin_lock(&dentry->d_lock);
-                fid64->parent_ino = dentry->d_parent->d_inode->i_ino;
+                fid64->parent_ino = XFS_I(dentry->d_parent->d_inode)->i_ino;
                 fid64->parent_gen = dentry->d_parent->d_inode->i_generation;
                 spin_unlock(&dentry->d_lock);
                 /*FALLTHRU*/
         case FILEID_INO32_GEN | XFS_FILEID_TYPE_64FLAG:
-                fid64->ino = inode->i_ino;
+                fid64->ino = XFS_I(inode)->i_ino;
                 fid64->gen = inode->i_generation;
                 break;
         }
diff --git a/fs/xfs/xfs_inode.c b/fs/xfs/xfs_inode.c
index c0237c602f11..755ee8164880 100644
--- a/fs/xfs/xfs_inode.c
+++ b/fs/xfs/xfs_inode.c
@@ -2835,6 +2835,27 @@ corrupt_out:
         return XFS_ERROR(EFSCORRUPTED);
 }
 
+void
+xfs_promote_inode(
+        struct xfs_inode        *ip)
+{
+        struct xfs_buf          *bp;
+
+        ASSERT(xfs_isilocked(ip, XFS_ILOCK_EXCL|XFS_ILOCK_SHARED));
+
+        bp = xfs_incore(ip->i_mount->m_ddev_targp, ip->i_imap.im_blkno,
+                        ip->i_imap.im_len, XBF_TRYLOCK);
+        if (!bp)
+                return;
+
+        if (XFS_BUF_ISDELAYWRITE(bp)) {
+                xfs_buf_delwri_promote(bp);
+                wake_up_process(ip->i_mount->m_ddev_targp->bt_task);
+        }
+
+        xfs_buf_relse(bp);
+}
+
 /*
  * Return a pointer to the extent record at file index idx.
  */
diff --git a/fs/xfs/xfs_inode.h b/fs/xfs/xfs_inode.h
index 760140d1dd66..b4cd4739f98e 100644
--- a/fs/xfs/xfs_inode.h
+++ b/fs/xfs/xfs_inode.h
@@ -498,6 +498,7 @@ int		xfs_iunlink(struct xfs_trans *, xfs_inode_t *);
 void            xfs_iext_realloc(xfs_inode_t *, int, int);
 void            xfs_iunpin_wait(xfs_inode_t *);
 int             xfs_iflush(xfs_inode_t *, uint);
+void            xfs_promote_inode(struct xfs_inode *);
 void            xfs_lock_inodes(xfs_inode_t **, int, uint);
 void            xfs_lock_two_inodes(xfs_inode_t *, xfs_inode_t *, uint);
 
diff --git a/fs/xfs/xfs_log.c b/fs/xfs/xfs_log.c
index a14cd89fe465..34817adf4b9e 100644
--- a/fs/xfs/xfs_log.c
+++ b/fs/xfs/xfs_log.c
@@ -150,6 +150,117 @@ xlog_grant_add_space(
         } while (head_val != old);
 }
 
+STATIC bool
+xlog_reserveq_wake(
+        struct log              *log,
+        int                     *free_bytes)
+{
+        struct xlog_ticket      *tic;
+        int                     need_bytes;
+
+        list_for_each_entry(tic, &log->l_reserveq, t_queue) {
+                if (tic->t_flags & XLOG_TIC_PERM_RESERV)
+                        need_bytes = tic->t_unit_res * tic->t_cnt;
+                else
+                        need_bytes = tic->t_unit_res;
+
+                if (*free_bytes < need_bytes)
+                        return false;
+                *free_bytes -= need_bytes;
+
+                trace_xfs_log_grant_wake_up(log, tic);
+                wake_up(&tic->t_wait);
+        }
+
+        return true;
+}
+
+STATIC bool
+xlog_writeq_wake(
+        struct log              *log,
+        int                     *free_bytes)
+{
+        struct xlog_ticket      *tic;
+        int                     need_bytes;
+
+        list_for_each_entry(tic, &log->l_writeq, t_queue) {
+                ASSERT(tic->t_flags & XLOG_TIC_PERM_RESERV);
+
+                need_bytes = tic->t_unit_res;
+
+                if (*free_bytes < need_bytes)
+                        return false;
+                *free_bytes -= need_bytes;
+
+                trace_xfs_log_regrant_write_wake_up(log, tic);
+                wake_up(&tic->t_wait);
+        }
+
+        return true;
+}
+
+STATIC int
+xlog_reserveq_wait(
+        struct log              *log,
+        struct xlog_ticket      *tic,
+        int                     need_bytes)
+{
+        list_add_tail(&tic->t_queue, &log->l_reserveq);
+
+        do {
+                if (XLOG_FORCED_SHUTDOWN(log))
+                        goto shutdown;
+                xlog_grant_push_ail(log, need_bytes);
+
+                XFS_STATS_INC(xs_sleep_logspace);
+                trace_xfs_log_grant_sleep(log, tic);
+
+                xlog_wait(&tic->t_wait, &log->l_grant_reserve_lock);
+                trace_xfs_log_grant_wake(log, tic);
+
+                spin_lock(&log->l_grant_reserve_lock);
+                if (XLOG_FORCED_SHUTDOWN(log))
+                        goto shutdown;
+        } while (xlog_space_left(log, &log->l_grant_reserve_head) < need_bytes);
+
+        list_del_init(&tic->t_queue);
+        return 0;
+shutdown:
+        list_del_init(&tic->t_queue);
+        return XFS_ERROR(EIO);
+}
+
+STATIC int
+xlog_writeq_wait(
+        struct log              *log,
+        struct xlog_ticket      *tic,
+        int                     need_bytes)
+{
+        list_add_tail(&tic->t_queue, &log->l_writeq);
+
+        do {
+                if (XLOG_FORCED_SHUTDOWN(log))
+                        goto shutdown;
+                xlog_grant_push_ail(log, need_bytes);
+
+                XFS_STATS_INC(xs_sleep_logspace);
+                trace_xfs_log_regrant_write_sleep(log, tic);
+
+                xlog_wait(&tic->t_wait, &log->l_grant_write_lock);
+                trace_xfs_log_regrant_write_wake(log, tic);
+
+                spin_lock(&log->l_grant_write_lock);
+                if (XLOG_FORCED_SHUTDOWN(log))
+                        goto shutdown;
+        } while (xlog_space_left(log, &log->l_grant_write_head) < need_bytes);
+
+        list_del_init(&tic->t_queue);
+        return 0;
+shutdown:
+        list_del_init(&tic->t_queue);
+        return XFS_ERROR(EIO);
+}
+
 static void
 xlog_tic_reset_res(xlog_ticket_t *tic)
 {
@@ -350,8 +461,19 @@ xfs_log_reserve(
                 retval = xlog_grant_log_space(log, internal_ticket);
         }
 
+        if (unlikely(retval)) {
+                /*
+                 * If we are failing, make sure the ticket doesn't have any
+                 * current reservations.  We don't want to add this back
+                 * when the ticket/ transaction gets cancelled.
+                 */
+                internal_ticket->t_curr_res = 0;
+                /* ungrant will give back unit_res * t_cnt. */
+                internal_ticket->t_cnt = 0;
+        }
+
         return retval;
-}       /* xfs_log_reserve */
+}
 
 
 /*
@@ -2481,8 +2603,8 @@ restart:
 /*
  * Atomically get the log space required for a log ticket.
  *
- * Once a ticket gets put onto the reserveq, it will only return after
- * the needed reservation is satisfied.
+ * Once a ticket gets put onto the reserveq, it will only return after the
+ * needed reservation is satisfied.
  *
  * This function is structured so that it has a lock free fast path. This is
  * necessary because every new transaction reservation will come through this
@@ -2490,113 +2612,53 @@ restart:
  * every pass.
  *
  * As tickets are only ever moved on and off the reserveq under the
- * l_grant_reserve_lock, we only need to take that lock if we are going
- * to add the ticket to the queue and sleep. We can avoid taking the lock if the
- * ticket was never added to the reserveq because the t_queue list head will be
- * empty and we hold the only reference to it so it can safely be checked
- * unlocked.
+ * l_grant_reserve_lock, we only need to take that lock if we are going to add
+ * the ticket to the queue and sleep. We can avoid taking the lock if the ticket
+ * was never added to the reserveq because the t_queue list head will be empty
+ * and we hold the only reference to it so it can safely be checked unlocked.
  */
 STATIC int
-xlog_grant_log_space(xlog_t        *log,
-                     xlog_ticket_t *tic)
+xlog_grant_log_space(
+        struct log              *log,
+        struct xlog_ticket      *tic)
 {
-        int              free_bytes;
-        int              need_bytes;
+        int                     free_bytes, need_bytes;
+        int                     error = 0;
 
-#ifdef DEBUG
-        if (log->l_flags & XLOG_ACTIVE_RECOVERY)
-                panic("grant Recovery problem");
-#endif
+        ASSERT(!(log->l_flags & XLOG_ACTIVE_RECOVERY));
 
         trace_xfs_log_grant_enter(log, tic);
 
+        /*
+         * If there are other waiters on the queue then give them a chance at
+         * logspace before us.  Wake up the first waiters, if we do not wake
+         * up all the waiters then go to sleep waiting for more free space,
+         * otherwise try to get some space for this transaction.
+         */
         need_bytes = tic->t_unit_res;
         if (tic->t_flags & XFS_LOG_PERM_RESERV)
                 need_bytes *= tic->t_ocnt;
-
-        /* something is already sleeping; insert new transaction at end */
-        if (!list_empty_careful(&log->l_reserveq)) {
-                spin_lock(&log->l_grant_reserve_lock);
-                /* recheck the queue now we are locked */
-                if (list_empty(&log->l_reserveq)) {
-                        spin_unlock(&log->l_grant_reserve_lock);
-                        goto redo;
-                }
-                list_add_tail(&tic->t_queue, &log->l_reserveq);
-
-                trace_xfs_log_grant_sleep1(log, tic);
-
-                /*
-                 * Gotta check this before going to sleep, while we're
-                 * holding the grant lock.
-                 */
-                if (XLOG_FORCED_SHUTDOWN(log))
-                        goto error_return;
-
-                XFS_STATS_INC(xs_sleep_logspace);
-                xlog_wait(&tic->t_wait, &log->l_grant_reserve_lock);
-
-                /*
-                 * If we got an error, and the filesystem is shutting down,
-                 * we'll catch it down below. So just continue...
-                 */
-                trace_xfs_log_grant_wake1(log, tic);
-        }
-
-redo:
-        if (XLOG_FORCED_SHUTDOWN(log))
-                goto error_return_unlocked;
-
         free_bytes = xlog_space_left(log, &log->l_grant_reserve_head);
-        if (free_bytes < need_bytes) {
+        if (!list_empty_careful(&log->l_reserveq)) {
                 spin_lock(&log->l_grant_reserve_lock);
-                if (list_empty(&tic->t_queue))
-                        list_add_tail(&tic->t_queue, &log->l_reserveq);
-
-                trace_xfs_log_grant_sleep2(log, tic);
-
-                if (XLOG_FORCED_SHUTDOWN(log))
-                        goto error_return;
-
-                xlog_grant_push_ail(log, need_bytes);
-
-                XFS_STATS_INC(xs_sleep_logspace);
-                xlog_wait(&tic->t_wait, &log->l_grant_reserve_lock);
-
-                trace_xfs_log_grant_wake2(log, tic);
-                goto redo;
-        }
-
-        if (!list_empty(&tic->t_queue)) {
+                if (!xlog_reserveq_wake(log, &free_bytes) ||
+                    free_bytes < need_bytes)
+                        error = xlog_reserveq_wait(log, tic, need_bytes);
+                spin_unlock(&log->l_grant_reserve_lock);
+        } else if (free_bytes < need_bytes) {
                 spin_lock(&log->l_grant_reserve_lock);
-                list_del_init(&tic->t_queue);
+                error = xlog_reserveq_wait(log, tic, need_bytes);
                 spin_unlock(&log->l_grant_reserve_lock);
         }
+        if (error)
+                return error;
 
-        /* we've got enough space */
         xlog_grant_add_space(log, &log->l_grant_reserve_head, need_bytes);
         xlog_grant_add_space(log, &log->l_grant_write_head, need_bytes);
         trace_xfs_log_grant_exit(log, tic);
         xlog_verify_grant_tail(log);
         return 0;
-
-error_return_unlocked:
-        spin_lock(&log->l_grant_reserve_lock);
-error_return:
-        list_del_init(&tic->t_queue);
-        spin_unlock(&log->l_grant_reserve_lock);
-        trace_xfs_log_grant_error(log, tic);
-
-        /*
-         * If we are failing, make sure the ticket doesn't have any
-         * current reservations. We don't want to add this back when
-         * the ticket/transaction gets cancelled.
-         */
-        tic->t_curr_res = 0;
-        tic->t_cnt = 0; /* ungrant will give back unit_res * t_cnt. */
-        return XFS_ERROR(EIO);
-}       /* xlog_grant_log_space */
-
+}
 
 /*
  * Replenish the byte reservation required by moving the grant write head.
@@ -2605,10 +2667,12 @@ error_return:
  * free fast path.
  */
 STATIC int
-xlog_regrant_write_log_space(xlog_t        *log,
-                             xlog_ticket_t *tic)
+xlog_regrant_write_log_space(
+        struct log              *log,
+        struct xlog_ticket      *tic)
 {
-        int             free_bytes, need_bytes;
+        int                     free_bytes, need_bytes;
+        int                     error = 0;
 
         tic->t_curr_res = tic->t_unit_res;
         xlog_tic_reset_res(tic);
@@ -2616,104 +2680,38 @@ xlog_regrant_write_log_space(xlog_t	   *log,
         if (tic->t_cnt > 0)
                 return 0;
 
-#ifdef DEBUG
-        if (log->l_flags & XLOG_ACTIVE_RECOVERY)
-                panic("regrant Recovery problem");
-#endif
+        ASSERT(!(log->l_flags & XLOG_ACTIVE_RECOVERY));
 
         trace_xfs_log_regrant_write_enter(log, tic);
-        if (XLOG_FORCED_SHUTDOWN(log))
-                goto error_return_unlocked;
 
-        /* If there are other waiters on the queue then give them a
-         * chance at logspace before us. Wake up the first waiters,
-         * if we do not wake up all the waiters then go to sleep waiting
-         * for more free space, otherwise try to get some space for
-         * this transaction.
+        /*
+         * If there are other waiters on the queue then give them a chance at
+         * logspace before us.  Wake up the first waiters, if we do not wake
+         * up all the waiters then go to sleep waiting for more free space,
+         * otherwise try to get some space for this transaction.
          */
         need_bytes = tic->t_unit_res;
-        if (!list_empty_careful(&log->l_writeq)) {
-                struct xlog_ticket *ntic;
-
-                spin_lock(&log->l_grant_write_lock);
-                free_bytes = xlog_space_left(log, &log->l_grant_write_head);
-                list_for_each_entry(ntic, &log->l_writeq, t_queue) {
-                        ASSERT(ntic->t_flags & XLOG_TIC_PERM_RESERV);
-
-                        if (free_bytes < ntic->t_unit_res)
-                                break;
-                        free_bytes -= ntic->t_unit_res;
-                        wake_up(&ntic->t_wait);
-                }
-
-                if (ntic != list_first_entry(&log->l_writeq,
-                                                struct xlog_ticket, t_queue)) {
-                        if (list_empty(&tic->t_queue))
-                                list_add_tail(&tic->t_queue, &log->l_writeq);
-                        trace_xfs_log_regrant_write_sleep1(log, tic);
-
-                        xlog_grant_push_ail(log, need_bytes);
-
-                        XFS_STATS_INC(xs_sleep_logspace);
-                        xlog_wait(&tic->t_wait, &log->l_grant_write_lock);
-                        trace_xfs_log_regrant_write_wake1(log, tic);
-                } else
-                        spin_unlock(&log->l_grant_write_lock);
-        }
-
-redo:
-        if (XLOG_FORCED_SHUTDOWN(log))
-                goto error_return_unlocked;
-
         free_bytes = xlog_space_left(log, &log->l_grant_write_head);
-        if (free_bytes < need_bytes) {
+        if (!list_empty_careful(&log->l_writeq)) {
                 spin_lock(&log->l_grant_write_lock);
-                if (list_empty(&tic->t_queue))
-                        list_add_tail(&tic->t_queue, &log->l_writeq);
-
-                if (XLOG_FORCED_SHUTDOWN(log))
-                        goto error_return;
-
-                xlog_grant_push_ail(log, need_bytes);
-
-                XFS_STATS_INC(xs_sleep_logspace);
-                trace_xfs_log_regrant_write_sleep2(log, tic);
-                xlog_wait(&tic->t_wait, &log->l_grant_write_lock);
-
-                trace_xfs_log_regrant_write_wake2(log, tic);
-                goto redo;
-        }
-
-        if (!list_empty(&tic->t_queue)) {
+                if (!xlog_writeq_wake(log, &free_bytes) ||
+                    free_bytes < need_bytes)
+                        error = xlog_writeq_wait(log, tic, need_bytes);
+                spin_unlock(&log->l_grant_write_lock);
+        } else if (free_bytes < need_bytes) {
                 spin_lock(&log->l_grant_write_lock);
-                list_del_init(&tic->t_queue);
+                error = xlog_writeq_wait(log, tic, need_bytes);
                 spin_unlock(&log->l_grant_write_lock);
         }
 
-        /* we've got enough space */
+        if (error)
+                return error;
+
         xlog_grant_add_space(log, &log->l_grant_write_head, need_bytes);
         trace_xfs_log_regrant_write_exit(log, tic);
         xlog_verify_grant_tail(log);
         return 0;
-
-
- error_return_unlocked:
-        spin_lock(&log->l_grant_write_lock);
- error_return:
-        list_del_init(&tic->t_queue);
-        spin_unlock(&log->l_grant_write_lock);
-        trace_xfs_log_regrant_write_error(log, tic);
-
-        /*
-         * If we are failing, make sure the ticket doesn't have any
-         * current reservations. We don't want to add this back when
-         * the ticket/transaction gets cancelled.
-         */
-        tic->t_curr_res = 0;
-        tic->t_cnt = 0; /* ungrant will give back unit_res * t_cnt. */
-        return XFS_ERROR(EIO);
-}       /* xlog_regrant_write_log_space */
-
+}
 
 /* The first cnt-1 times through here we don't need to
  * move the grant write head because the permanent
diff --git a/fs/xfs/xfs_sync.c b/fs/xfs/xfs_sync.c
index aa3dc1a4d53d..be5c51d8f757 100644
--- a/fs/xfs/xfs_sync.c
+++ b/fs/xfs/xfs_sync.c
@@ -770,6 +770,17 @@ restart:
         if (!xfs_iflock_nowait(ip)) {
                 if (!(sync_mode & SYNC_WAIT))
                         goto out;
+
+                /*
+                 * If we only have a single dirty inode in a cluster there is
+                 * a fair chance that the AIL push may have pushed it into
+                 * the buffer, but xfsbufd won't touch it until 30 seconds
+                 * from now, and thus we will lock up here.
+                 *
+                 * Promote the inode buffer to the front of the delwri list
+                 * and wake up xfsbufd now.
+                 */
+                xfs_promote_inode(ip);
                 xfs_iflock(ip);
         }
 
diff --git a/fs/xfs/xfs_trace.h b/fs/xfs/xfs_trace.h
index f1d2802b2f07..494035798873 100644
--- a/fs/xfs/xfs_trace.h
+++ b/fs/xfs/xfs_trace.h
@@ -834,18 +834,14 @@ DEFINE_LOGGRANT_EVENT(xfs_log_umount_write);
 DEFINE_LOGGRANT_EVENT(xfs_log_grant_enter);
 DEFINE_LOGGRANT_EVENT(xfs_log_grant_exit);
 DEFINE_LOGGRANT_EVENT(xfs_log_grant_error);
-DEFINE_LOGGRANT_EVENT(xfs_log_grant_sleep1);
-DEFINE_LOGGRANT_EVENT(xfs_log_grant_wake1);
-DEFINE_LOGGRANT_EVENT(xfs_log_grant_sleep2);
-DEFINE_LOGGRANT_EVENT(xfs_log_grant_wake2);
+DEFINE_LOGGRANT_EVENT(xfs_log_grant_sleep);
+DEFINE_LOGGRANT_EVENT(xfs_log_grant_wake);
 DEFINE_LOGGRANT_EVENT(xfs_log_grant_wake_up);
 DEFINE_LOGGRANT_EVENT(xfs_log_regrant_write_enter);
 DEFINE_LOGGRANT_EVENT(xfs_log_regrant_write_exit);
 DEFINE_LOGGRANT_EVENT(xfs_log_regrant_write_error);
-DEFINE_LOGGRANT_EVENT(xfs_log_regrant_write_sleep1);
-DEFINE_LOGGRANT_EVENT(xfs_log_regrant_write_wake1);
-DEFINE_LOGGRANT_EVENT(xfs_log_regrant_write_sleep2);
-DEFINE_LOGGRANT_EVENT(xfs_log_regrant_write_wake2);
+DEFINE_LOGGRANT_EVENT(xfs_log_regrant_write_sleep);
+DEFINE_LOGGRANT_EVENT(xfs_log_regrant_write_wake);
 DEFINE_LOGGRANT_EVENT(xfs_log_regrant_write_wake_up);
 DEFINE_LOGGRANT_EVENT(xfs_log_regrant_reserve_enter);
 DEFINE_LOGGRANT_EVENT(xfs_log_regrant_reserve_exit);