16 files changed, 297 insertions, 185 deletions

diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h
index 6f820fa23df4..7f78cc78fdd0 100644
--- a/fs/btrfs/ctree.h
+++ b/fs/btrfs/ctree.h
@@ -729,6 +729,15 @@ struct btrfs_space_info {
         u64 disk_total;         /* total bytes on disk, takes mirrors into
                                    account */
 
+        /*
+         * we bump reservation progress every time we decrement
+         * bytes_reserved.  This way people waiting for reservations
+         * know something good has happened and they can check
+         * for progress.  The number here isn't to be trusted, it
+         * just shows reclaim activity
+         */
+        unsigned long reservation_progress;
+
         int full;               /* indicates that we cannot allocate any more
                                    chunks for this space */
         int force_alloc;        /* set if we need to force a chunk alloc for
diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c
index 588ff9849873..7b3089b5c2df 100644
--- a/fs/btrfs/extent-tree.c
+++ b/fs/btrfs/extent-tree.c
@@ -3342,15 +3342,16 @@ static int shrink_delalloc(struct btrfs_trans_handle *trans,
         u64 max_reclaim;
         u64 reclaimed = 0;
         long time_left;
-        int pause = 1;
         int nr_pages = (2 * 1024 * 1024) >> PAGE_CACHE_SHIFT;
         int loops = 0;
+        unsigned long progress;
 
         block_rsv = &root->fs_info->delalloc_block_rsv;
         space_info = block_rsv->space_info;
 
         smp_mb();
         reserved = space_info->bytes_reserved;
+        progress = space_info->reservation_progress;
 
         if (reserved == 0)
                 return 0;
@@ -3365,31 +3366,36 @@ static int shrink_delalloc(struct btrfs_trans_handle *trans,
                 writeback_inodes_sb_nr_if_idle(root->fs_info->sb, nr_pages);
 
                 spin_lock(&space_info->lock);
-                if (reserved > space_info->bytes_reserved) {
-                        loops = 0;
+                if (reserved > space_info->bytes_reserved)
                         reclaimed += reserved - space_info->bytes_reserved;
-                } else {
-                        loops++;
-                }
                 reserved = space_info->bytes_reserved;
                 spin_unlock(&space_info->lock);
 
+                loops++;
+
                 if (reserved == 0 || reclaimed >= max_reclaim)
                         break;
 
                 if (trans && trans->transaction->blocked)
                         return -EAGAIN;
 
-                __set_current_state(TASK_INTERRUPTIBLE);
-                time_left = schedule_timeout(pause);
+                time_left = schedule_timeout_interruptible(1);
 
                 /* We were interrupted, exit */
                 if (time_left)
                         break;
 
-                pause <<= 1;
-                if (pause > HZ / 10)
-                        pause = HZ / 10;
+                /* we've kicked the IO a few times, if anything has been freed,
+                 * exit.  There is no sense in looping here for a long time
+                 * when we really need to commit the transaction, or there are
+                 * just too many writers without enough free space
+                 */
+
+                if (loops > 3) {
+                        smp_mb();
+                        if (progress != space_info->reservation_progress)
+                                break;
+                }
 
         }
         return reclaimed >= to_reclaim;
@@ -3612,6 +3618,7 @@ void block_rsv_release_bytes(struct btrfs_block_rsv *block_rsv,
                 if (num_bytes) {
                         spin_lock(&space_info->lock);
                         space_info->bytes_reserved -= num_bytes;
+                        space_info->reservation_progress++;
                         spin_unlock(&space_info->lock);
                 }
         }
@@ -3844,6 +3851,7 @@ static void update_global_block_rsv(struct btrfs_fs_info *fs_info)
         if (block_rsv->reserved >= block_rsv->size) {
                 num_bytes = block_rsv->reserved - block_rsv->size;
                 sinfo->bytes_reserved -= num_bytes;
+                sinfo->reservation_progress++;
                 block_rsv->reserved = block_rsv->size;
                 block_rsv->full = 1;
         }
@@ -4005,7 +4013,6 @@ int btrfs_delalloc_reserve_metadata(struct inode *inode, u64 num_bytes)
                 to_reserve = 0;
         }
         spin_unlock(&BTRFS_I(inode)->accounting_lock);
-
         to_reserve += calc_csum_metadata_size(inode, num_bytes);
         ret = reserve_metadata_bytes(NULL, root, block_rsv, to_reserve, 1);
         if (ret)
@@ -4133,6 +4140,7 @@ static int update_block_group(struct btrfs_trans_handle *trans,
                         btrfs_set_block_group_used(&cache->item, old_val);
                         cache->reserved -= num_bytes;
                         cache->space_info->bytes_reserved -= num_bytes;
+                        cache->space_info->reservation_progress++;
                         cache->space_info->bytes_used += num_bytes;
                         cache->space_info->disk_used += num_bytes * factor;
                         spin_unlock(&cache->lock);
@@ -4184,6 +4192,7 @@ static int pin_down_extent(struct btrfs_root *root,
         if (reserved) {
                 cache->reserved -= num_bytes;
                 cache->space_info->bytes_reserved -= num_bytes;
+                cache->space_info->reservation_progress++;
         }
         spin_unlock(&cache->lock);
         spin_unlock(&cache->space_info->lock);
@@ -4234,6 +4243,7 @@ static int update_reserved_bytes(struct btrfs_block_group_cache *cache,
                                 space_info->bytes_readonly += num_bytes;
                         cache->reserved -= num_bytes;
                         space_info->bytes_reserved -= num_bytes;
+                        space_info->reservation_progress++;
                 }
                 spin_unlock(&cache->lock);
                 spin_unlock(&space_info->lock);
@@ -4712,6 +4722,7 @@ void btrfs_free_tree_block(struct btrfs_trans_handle *trans,
                 if (ret) {
                         spin_lock(&cache->space_info->lock);
                         cache->space_info->bytes_reserved -= buf->len;
+                        cache->space_info->reservation_progress++;
                         spin_unlock(&cache->space_info->lock);
                 }
                 goto out;
diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c
index fd3f172e94e6..714adc4ac4c2 100644
--- a/fs/btrfs/extent_io.c
+++ b/fs/btrfs/extent_io.c
@@ -3046,17 +3046,38 @@ int extent_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
         }
 
         while (!end) {
-                off = extent_map_end(em);
-                if (off >= max)
-                        end = 1;
+                u64 offset_in_extent;
+
+                /* break if the extent we found is outside the range */
+                if (em->start >= max || extent_map_end(em) < off)
+                        break;
+
+                /*
+                 * get_extent may return an extent that starts before our
+                 * requested range.  We have to make sure the ranges
+                 * we return to fiemap always move forward and don't
+                 * overlap, so adjust the offsets here
+                 */
+                em_start = max(em->start, off);
 
-                em_start = em->start;
-                em_len = em->len;
+                /*
+                 * record the offset from the start of the extent
+                 * for adjusting the disk offset below
+                 */
+                offset_in_extent = em_start - em->start;
                 em_end = extent_map_end(em);
+                em_len = em_end - em_start;
                 emflags = em->flags;
                 disko = 0;
                 flags = 0;
 
+                /*
+                 * bump off for our next call to get_extent
+                 */
+                off = extent_map_end(em);
+                if (off >= max)
+                        end = 1;
+
                 if (em->block_start == EXTENT_MAP_LAST_BYTE) {
                         end = 1;
                         flags |= FIEMAP_EXTENT_LAST;
@@ -3067,7 +3088,7 @@ int extent_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
                         flags |= (FIEMAP_EXTENT_DELALLOC |
                                   FIEMAP_EXTENT_UNKNOWN);
                 } else {
-                        disko = em->block_start;
+                        disko = em->block_start + offset_in_extent;
                 }
                 if (test_bit(EXTENT_FLAG_COMPRESSED, &em->flags))
                         flags |= FIEMAP_EXTENT_ENCODED;
diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c
index 7084140d5940..f447b783bb84 100644
--- a/fs/btrfs/file.c
+++ b/fs/btrfs/file.c
@@ -70,6 +70,19 @@ static noinline int btrfs_copy_from_user(loff_t pos, int num_pages,
 
                 /* Flush processor's dcache for this page */
                 flush_dcache_page(page);
+
+                /*
+                 * if we get a partial write, we can end up with
+                 * partially up to date pages.  These add
+                 * a lot of complexity, so make sure they don't
+                 * happen by forcing this copy to be retried.
+                 *
+                 * The rest of the btrfs_file_write code will fall
+                 * back to page at a time copies after we return 0.
+                 */
+                if (!PageUptodate(page) && copied < count)
+                        copied = 0;
+
                 iov_iter_advance(i, copied);
                 write_bytes -= copied;
                 total_copied += copied;
@@ -763,6 +776,27 @@ out:
 }
 
 /*
+ * on error we return an unlocked page and the error value
+ * on success we return a locked page and 0
+ */
+static int prepare_uptodate_page(struct page *page, u64 pos)
+{
+        int ret = 0;
+
+        if ((pos & (PAGE_CACHE_SIZE - 1)) && !PageUptodate(page)) {
+                ret = btrfs_readpage(NULL, page);
+                if (ret)
+                        return ret;
+                lock_page(page);
+                if (!PageUptodate(page)) {
+                        unlock_page(page);
+                        return -EIO;
+                }
+        }
+        return 0;
+}
+
+/*
  * this gets pages into the page cache and locks them down, it also properly
  * waits for data=ordered extents to finish before allowing the pages to be
  * modified.
@@ -777,6 +811,7 @@ static noinline int prepare_pages(struct btrfs_root *root, struct file *file,
         unsigned long index = pos >> PAGE_CACHE_SHIFT;
         struct inode *inode = fdentry(file)->d_inode;
         int err = 0;
+        int faili = 0;
         u64 start_pos;
         u64 last_pos;
 
@@ -794,15 +829,24 @@ again:
         for (i = 0; i < num_pages; i++) {
                 pages[i] = grab_cache_page(inode->i_mapping, index + i);
                 if (!pages[i]) {
-                        int c;
-                        for (c = i - 1; c >= 0; c--) {
-                                unlock_page(pages[c]);
-                                page_cache_release(pages[c]);
-                        }
-                        return -ENOMEM;
+                        faili = i - 1;
+                        err = -ENOMEM;
+                        goto fail;
+                }
+
+                if (i == 0)
+                        err = prepare_uptodate_page(pages[i], pos);
+                if (i == num_pages - 1)
+                        err = prepare_uptodate_page(pages[i],
+                                                    pos + write_bytes);
+                if (err) {
+                        page_cache_release(pages[i]);
+                        faili = i - 1;
+                        goto fail;
                 }
                 wait_on_page_writeback(pages[i]);
         }
+        err = 0;
         if (start_pos < inode->i_size) {
                 struct btrfs_ordered_extent *ordered;
                 lock_extent_bits(&BTRFS_I(inode)->io_tree,
@@ -842,6 +886,14 @@ again:
                 WARN_ON(!PageLocked(pages[i]));
         }
         return 0;
+fail:
+        while (faili >= 0) {
+                unlock_page(pages[faili]);
+                page_cache_release(pages[faili]);
+                faili--;
+        }
+        return err;
+
 }
 
 static ssize_t btrfs_file_aio_write(struct kiocb *iocb,
@@ -851,7 +903,6 @@ static ssize_t btrfs_file_aio_write(struct kiocb *iocb,
         struct file *file = iocb->ki_filp;
         struct inode *inode = fdentry(file)->d_inode;
         struct btrfs_root *root = BTRFS_I(inode)->root;
-        struct page *pinned[2];
         struct page **pages = NULL;
         struct iov_iter i;
         loff_t *ppos = &iocb->ki_pos;
@@ -872,9 +923,6 @@ static ssize_t btrfs_file_aio_write(struct kiocb *iocb,
         will_write = ((file->f_flags & O_DSYNC) || IS_SYNC(inode) ||
                       (file->f_flags & O_DIRECT));
 
-        pinned[0] = NULL;
-        pinned[1] = NULL;
-
         start_pos = pos;
 
         vfs_check_frozen(inode->i_sb, SB_FREEZE_WRITE);
@@ -962,32 +1010,6 @@ static ssize_t btrfs_file_aio_write(struct kiocb *iocb,
         first_index = pos >> PAGE_CACHE_SHIFT;
         last_index = (pos + iov_iter_count(&i)) >> PAGE_CACHE_SHIFT;
 
-        /*
-         * there are lots of better ways to do this, but this code
-         * makes sure the first and last page in the file range are
-         * up to date and ready for cow
-         */
-        if ((pos & (PAGE_CACHE_SIZE - 1))) {
-                pinned[0] = grab_cache_page(inode->i_mapping, first_index);
-                if (!PageUptodate(pinned[0])) {
-                        ret = btrfs_readpage(NULL, pinned[0]);
-                        BUG_ON(ret);
-                        wait_on_page_locked(pinned[0]);
-                } else {
-                        unlock_page(pinned[0]);
-                }
-        }
-        if ((pos + iov_iter_count(&i)) & (PAGE_CACHE_SIZE - 1)) {
-                pinned[1] = grab_cache_page(inode->i_mapping, last_index);
-                if (!PageUptodate(pinned[1])) {
-                        ret = btrfs_readpage(NULL, pinned[1]);
-                        BUG_ON(ret);
-                        wait_on_page_locked(pinned[1]);
-                } else {
-                        unlock_page(pinned[1]);
-                }
-        }
-
         while (iov_iter_count(&i) > 0) {
                 size_t offset = pos & (PAGE_CACHE_SIZE - 1);
                 size_t write_bytes = min(iov_iter_count(&i),
@@ -1024,8 +1046,20 @@ static ssize_t btrfs_file_aio_write(struct kiocb *iocb,
 
                 copied = btrfs_copy_from_user(pos, num_pages,
                                            write_bytes, pages, &i);
-                dirty_pages = (copied + offset + PAGE_CACHE_SIZE - 1) >>
-                                PAGE_CACHE_SHIFT;
+
+                /*
+                 * if we have trouble faulting in the pages, fall
+                 * back to one page at a time
+                 */
+                if (copied < write_bytes)
+                        nrptrs = 1;
+
+                if (copied == 0)
+                        dirty_pages = 0;
+                else
+                        dirty_pages = (copied + offset +
+                                       PAGE_CACHE_SIZE - 1) >>
+                                       PAGE_CACHE_SHIFT;
 
                 if (num_pages > dirty_pages) {
                         if (copied > 0)
@@ -1069,10 +1103,6 @@ out:
                 err = ret;
 
         kfree(pages);
-        if (pinned[0])
-                page_cache_release(pinned[0]);
-        if (pinned[1])
-                page_cache_release(pinned[1]);
         *ppos = pos;
 
         /*
diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index c23f050f47c2..4a0107e18747 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -4818,10 +4818,11 @@ static int btrfs_link(struct dentry *old_dentry, struct inode *dir,
                 goto fail;
 
         /*
-         * 1 item for inode ref
+         * 2 items for inode and inode ref
          * 2 items for dir items
+         * 1 item for parent inode
          */
-        trans = btrfs_start_transaction(root, 3);
+        trans = btrfs_start_transaction(root, 5);
         if (IS_ERR(trans)) {
                 err = PTR_ERR(trans);
                 goto fail;
@@ -6053,6 +6054,7 @@ static void btrfs_submit_direct(int rw, struct bio *bio, struct inode *inode,
         if (!skip_sum) {
                 dip->csums = kmalloc(sizeof(u32) * bio->bi_vcnt, GFP_NOFS);
                 if (!dip->csums) {
+                        kfree(dip);
                         ret = -ENOMEM;
                         goto free_ordered;
                 }
diff --git a/fs/dcache.c b/fs/dcache.c
index 611ffe928c03..a39fe47c466f 100644
--- a/fs/dcache.c
+++ b/fs/dcache.c
@@ -296,8 +296,12 @@ static struct dentry *d_kill(struct dentry *dentry, struct dentry *parent)
         __releases(parent->d_lock)
         __releases(dentry->d_inode->i_lock)
 {
-        dentry->d_parent = NULL;
         list_del(&dentry->d_u.d_child);
+        /*
+         * Inform try_to_ascend() that we are no longer attached to the
+         * dentry tree
+         */
+        dentry->d_flags |= DCACHE_DISCONNECTED;
         if (parent)
                 spin_unlock(&parent->d_lock);
         dentry_iput(dentry);
@@ -1012,6 +1016,35 @@ void shrink_dcache_for_umount(struct super_block *sb)
 }
 
 /*
+ * This tries to ascend one level of parenthood, but
+ * we can race with renaming, so we need to re-check
+ * the parenthood after dropping the lock and check
+ * that the sequence number still matches.
+ */
+static struct dentry *try_to_ascend(struct dentry *old, int locked, unsigned seq)
+{
+        struct dentry *new = old->d_parent;
+
+        rcu_read_lock();
+        spin_unlock(&old->d_lock);
+        spin_lock(&new->d_lock);
+
+        /*
+         * might go back up the wrong parent if we have had a rename
+         * or deletion
+         */
+        if (new != old->d_parent ||
+                 (old->d_flags & DCACHE_DISCONNECTED) ||
+                 (!locked && read_seqretry(&rename_lock, seq))) {
+                spin_unlock(&new->d_lock);
+                new = NULL;
+        }
+        rcu_read_unlock();
+        return new;
+}
+
+
+/*
  * Search for at least 1 mount point in the dentry's subdirs.
  * We descend to the next level whenever the d_subdirs
  * list is non-empty and continue searching.
@@ -1066,24 +1099,10 @@ resume:
          * All done at this level ... ascend and resume the search.
          */
         if (this_parent != parent) {
-                struct dentry *tmp;
-                struct dentry *child;
-
-                tmp = this_parent->d_parent;
-                rcu_read_lock();
-                spin_unlock(&this_parent->d_lock);
-                child = this_parent;
-                this_parent = tmp;
-                spin_lock(&this_parent->d_lock);
-                /* might go back up the wrong parent if we have had a rename
-                 * or deletion */
-                if (this_parent != child->d_parent ||
-                         (!locked && read_seqretry(&rename_lock, seq))) {
-                        spin_unlock(&this_parent->d_lock);
-                        rcu_read_unlock();
+                struct dentry *child = this_parent;
+                this_parent = try_to_ascend(this_parent, locked, seq);
+                if (!this_parent)
                         goto rename_retry;
-                }
-                rcu_read_unlock();
                 next = child->d_u.d_child.next;
                 goto resume;
         }
@@ -1181,24 +1200,10 @@ resume:
          * All done at this level ... ascend and resume the search.
          */
         if (this_parent != parent) {
-                struct dentry *tmp;
-                struct dentry *child;
-
-                tmp = this_parent->d_parent;
-                rcu_read_lock();
-                spin_unlock(&this_parent->d_lock);
-                child = this_parent;
-                this_parent = tmp;
-                spin_lock(&this_parent->d_lock);
-                /* might go back up the wrong parent if we have had a rename
-                 * or deletion */
-                if (this_parent != child->d_parent ||
-                        (!locked && read_seqretry(&rename_lock, seq))) {
-                        spin_unlock(&this_parent->d_lock);
-                        rcu_read_unlock();
+                struct dentry *child = this_parent;
+                this_parent = try_to_ascend(this_parent, locked, seq);
+                if (!this_parent)
                         goto rename_retry;
-                }
-                rcu_read_unlock();
                 next = child->d_u.d_child.next;
                 goto resume;
         }
@@ -2942,28 +2947,14 @@ resume:
                 spin_unlock(&dentry->d_lock);
         }
         if (this_parent != root) {
-                struct dentry *tmp;
-                struct dentry *child;
-
-                tmp = this_parent->d_parent;
+                struct dentry *child = this_parent;
                 if (!(this_parent->d_flags & DCACHE_GENOCIDE)) {
                         this_parent->d_flags |= DCACHE_GENOCIDE;
                         this_parent->d_count--;
                 }
-                rcu_read_lock();
-                spin_unlock(&this_parent->d_lock);
-                child = this_parent;
-                this_parent = tmp;
-                spin_lock(&this_parent->d_lock);
-                /* might go back up the wrong parent if we have had a rename
-                 * or deletion */
-                if (this_parent != child->d_parent ||
-                         (!locked && read_seqretry(&rename_lock, seq))) {
-                        spin_unlock(&this_parent->d_lock);
-                        rcu_read_unlock();
+                this_parent = try_to_ascend(this_parent, locked, seq);
+                if (!this_parent)
                         goto rename_retry;
-                }
-                rcu_read_unlock();
                 next = child->d_u.d_child.next;
                 goto resume;
         }
diff --git a/fs/nfs/inode.c b/fs/nfs/inode.c
index 1cc600e77bb4..2f8e61816d75 100644
--- a/fs/nfs/inode.c
+++ b/fs/nfs/inode.c
@@ -37,6 +37,7 @@
 #include <linux/inet.h>
 #include <linux/nfs_xdr.h>
 #include <linux/slab.h>
+#include <linux/compat.h>
 
 #include <asm/system.h>
 #include <asm/uaccess.h>
@@ -89,7 +90,11 @@ int nfs_wait_bit_killable(void *word)
  */
 u64 nfs_compat_user_ino64(u64 fileid)
 {
-        int ino;
+#ifdef CONFIG_COMPAT
+        compat_ulong_t ino;
+#else   
+        unsigned long ino;
+#endif
 
         if (enable_ino64)
                 return fileid;
diff --git a/fs/nfs/nfs4_fs.h b/fs/nfs/nfs4_fs.h
index 7a7474073148..1be36cf65bfc 100644
--- a/fs/nfs/nfs4_fs.h
+++ b/fs/nfs/nfs4_fs.h
@@ -298,6 +298,11 @@ struct rpc_cred *nfs4_get_renew_cred_locked(struct nfs_client *clp);
 #if defined(CONFIG_NFS_V4_1)
 struct rpc_cred *nfs4_get_machine_cred_locked(struct nfs_client *clp);
 struct rpc_cred *nfs4_get_exchange_id_cred(struct nfs_client *clp);
+extern void nfs4_schedule_session_recovery(struct nfs4_session *);
+#else
+static inline void nfs4_schedule_session_recovery(struct nfs4_session *session)
+{
+}
 #endif /* CONFIG_NFS_V4_1 */
 
 extern struct nfs4_state_owner * nfs4_get_state_owner(struct nfs_server *, struct rpc_cred *);
@@ -307,10 +312,9 @@ extern void nfs4_put_open_state(struct nfs4_state *);
 extern void nfs4_close_state(struct path *, struct nfs4_state *, fmode_t);
 extern void nfs4_close_sync(struct path *, struct nfs4_state *, fmode_t);
 extern void nfs4_state_set_mode_locked(struct nfs4_state *, fmode_t);
-extern void nfs4_schedule_state_recovery(struct nfs_client *);
+extern void nfs4_schedule_lease_recovery(struct nfs_client *);
 extern void nfs4_schedule_state_manager(struct nfs_client *);
-extern int nfs4_state_mark_reclaim_nograce(struct nfs_client *clp, struct nfs4_state *state);
-extern int nfs4_state_mark_reclaim_reboot(struct nfs_client *clp, struct nfs4_state *state);
+extern void nfs4_schedule_stateid_recovery(const struct nfs_server *, struct nfs4_state *);
 extern void nfs41_handle_sequence_flag_errors(struct nfs_client *clp, u32 flags);
 extern void nfs41_handle_recall_slot(struct nfs_client *clp);
 extern void nfs4_put_lock_state(struct nfs4_lock_state *lsp);
diff --git a/fs/nfs/nfs4filelayoutdev.c b/fs/nfs/nfs4filelayoutdev.c
index f5c9b125e8cc..b73c34375f60 100644
--- a/fs/nfs/nfs4filelayoutdev.c
+++ b/fs/nfs/nfs4filelayoutdev.c
@@ -219,6 +219,10 @@ decode_and_add_ds(__be32 **pp, struct inode *inode)
                 goto out_err;
         }
         buf = kmalloc(rlen + 1, GFP_KERNEL);
+        if (!buf) {
+                dprintk("%s: Not enough memory\n", __func__);
+                goto out_err;
+        }
         buf[rlen] = '\0';
         memcpy(buf, r_addr, rlen);
 
diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c
index 1ff76acc7e98..0a07e353a961 100644
--- a/fs/nfs/nfs4proc.c
+++ b/fs/nfs/nfs4proc.c
@@ -51,7 +51,6 @@
 #include <linux/sunrpc/bc_xprt.h>
 #include <linux/xattr.h>
 #include <linux/utsname.h>
-#include <linux/mm.h>
 
 #include "nfs4_fs.h"
 #include "delegation.h"
@@ -257,12 +256,13 @@ static int nfs4_handle_exception(const struct nfs_server *server, int errorcode,
                 case -NFS4ERR_OPENMODE:
                         if (state == NULL)
                                 break;
-                        nfs4_state_mark_reclaim_nograce(clp, state);
-                        goto do_state_recovery;
+                        nfs4_schedule_stateid_recovery(server, state);
+                        goto wait_on_recovery;
                 case -NFS4ERR_STALE_STATEID:
                 case -NFS4ERR_STALE_CLIENTID:
                 case -NFS4ERR_EXPIRED:
-                        goto do_state_recovery;
+                        nfs4_schedule_lease_recovery(clp);
+                        goto wait_on_recovery;
 #if defined(CONFIG_NFS_V4_1)
                 case -NFS4ERR_BADSESSION:
                 case -NFS4ERR_BADSLOT:
@@ -273,7 +273,7 @@ static int nfs4_handle_exception(const struct nfs_server *server, int errorcode,
                 case -NFS4ERR_SEQ_MISORDERED:
                         dprintk("%s ERROR: %d Reset session\n", __func__,
                                 errorcode);
-                        nfs4_schedule_state_recovery(clp);
+                        nfs4_schedule_session_recovery(clp->cl_session);
                         exception->retry = 1;
                         break;
 #endif /* defined(CONFIG_NFS_V4_1) */
@@ -296,8 +296,7 @@ static int nfs4_handle_exception(const struct nfs_server *server, int errorcode,
         }
         /* We failed to handle the error */
         return nfs4_map_errors(ret);
-do_state_recovery:
-        nfs4_schedule_state_recovery(clp);
+wait_on_recovery:
         ret = nfs4_wait_clnt_recover(clp);
         if (ret == 0)
                 exception->retry = 1;
@@ -436,8 +435,8 @@ static int nfs41_sequence_done(struct rpc_task *task, struct nfs4_sequence_res *
                 clp = res->sr_session->clp;
                 do_renew_lease(clp, timestamp);
                 /* Check sequence flags */
-                if (atomic_read(&clp->cl_count) > 1)
-                        nfs41_handle_sequence_flag_errors(clp, res->sr_status_flags);
+                if (res->sr_status_flags != 0)
+                        nfs4_schedule_lease_recovery(clp);
                 break;
         case -NFS4ERR_DELAY:
                 /* The server detected a resend of the RPC call and
@@ -1256,14 +1255,13 @@ int nfs4_open_delegation_recall(struct nfs_open_context *ctx, struct nfs4_state
                         case -NFS4ERR_BAD_HIGH_SLOT:
                         case -NFS4ERR_CONN_NOT_BOUND_TO_SESSION:
                         case -NFS4ERR_DEADSESSION:
-                                nfs4_schedule_state_recovery(
-                                        server->nfs_client);
+                                nfs4_schedule_session_recovery(server->nfs_client->cl_session);
                                 goto out;
                         case -NFS4ERR_STALE_CLIENTID:
                         case -NFS4ERR_STALE_STATEID:
                         case -NFS4ERR_EXPIRED:
                                 /* Don't recall a delegation if it was lost */
-                                nfs4_schedule_state_recovery(server->nfs_client);
+                                nfs4_schedule_lease_recovery(server->nfs_client);
                                 goto out;
                         case -ERESTARTSYS:
                                 /*
@@ -1272,7 +1270,7 @@ int nfs4_open_delegation_recall(struct nfs_open_context *ctx, struct nfs4_state
                                  */
                         case -NFS4ERR_ADMIN_REVOKED:
                         case -NFS4ERR_BAD_STATEID:
-                                nfs4_state_mark_reclaim_nograce(server->nfs_client, state);
+                                nfs4_schedule_stateid_recovery(server, state);
                         case -EKEYEXPIRED:
                                 /*
                                  * User RPCSEC_GSS context has expired.
@@ -1588,7 +1586,7 @@ static int nfs4_recover_expired_lease(struct nfs_server *server)
                 if (!test_bit(NFS4CLNT_LEASE_EXPIRED, &clp->cl_state) &&
                     !test_bit(NFS4CLNT_CHECK_LEASE,&clp->cl_state))
                         break;
-                nfs4_schedule_state_recovery(clp);
+                nfs4_schedule_state_manager(clp);
                 ret = -EIO;
         }
         return ret;
@@ -3179,7 +3177,7 @@ static void nfs4_renew_done(struct rpc_task *task, void *calldata)
         if (task->tk_status < 0) {
                 /* Unless we're shutting down, schedule state recovery! */
                 if (test_bit(NFS_CS_RENEWD, &clp->cl_res_state) != 0)
-                        nfs4_schedule_state_recovery(clp);
+                        nfs4_schedule_lease_recovery(clp);
                 return;
         }
         do_renew_lease(clp, timestamp);
@@ -3262,7 +3260,7 @@ static int buf_to_pages_noslab(const void *buf, size_t buflen,
         spages = pages;
 
         do {
-                len = min(PAGE_CACHE_SIZE, buflen);
+                len = min_t(size_t, PAGE_CACHE_SIZE, buflen);
                 newpage = alloc_page(GFP_KERNEL);
 
                 if (newpage == NULL)
@@ -3504,12 +3502,13 @@ nfs4_async_handle_error(struct rpc_task *task, const struct nfs_server *server,
                 case -NFS4ERR_OPENMODE:
                         if (state == NULL)
                                 break;
-                        nfs4_state_mark_reclaim_nograce(clp, state);
-                        goto do_state_recovery;
+                        nfs4_schedule_stateid_recovery(server, state);
+                        goto wait_on_recovery;
                 case -NFS4ERR_STALE_STATEID:
                 case -NFS4ERR_STALE_CLIENTID:
                 case -NFS4ERR_EXPIRED:
-                        goto do_state_recovery;
+                        nfs4_schedule_lease_recovery(clp);
+                        goto wait_on_recovery;
 #if defined(CONFIG_NFS_V4_1)
                 case -NFS4ERR_BADSESSION:
                 case -NFS4ERR_BADSLOT:
@@ -3520,7 +3519,7 @@ nfs4_async_handle_error(struct rpc_task *task, const struct nfs_server *server,
                 case -NFS4ERR_SEQ_MISORDERED:
                         dprintk("%s ERROR %d, Reset session\n", __func__,
                                 task->tk_status);
-                        nfs4_schedule_state_recovery(clp);
+                        nfs4_schedule_session_recovery(clp->cl_session);
                         task->tk_status = 0;
                         return -EAGAIN;
 #endif /* CONFIG_NFS_V4_1 */
@@ -3537,9 +3536,8 @@ nfs4_async_handle_error(struct rpc_task *task, const struct nfs_server *server,
         }
         task->tk_status = nfs4_map_errors(task->tk_status);
         return 0;
-do_state_recovery:
+wait_on_recovery:
         rpc_sleep_on(&clp->cl_rpcwaitq, task, NULL);
-        nfs4_schedule_state_recovery(clp);
         if (test_bit(NFS4CLNT_MANAGER_RUNNING, &clp->cl_state) == 0)
                 rpc_wake_up_queued_task(&clp->cl_rpcwaitq, task);
         task->tk_status = 0;
@@ -4150,7 +4148,7 @@ static void nfs4_lock_release(void *calldata)
                 task = nfs4_do_unlck(&data->fl, data->ctx, data->lsp,
                                 data->arg.lock_seqid);
                 if (!IS_ERR(task))
-                        rpc_put_task(task);
+                        rpc_put_task_async(task);
                 dprintk("%s: cancelling lock!\n", __func__);
         } else
                 nfs_free_seqid(data->arg.lock_seqid);
@@ -4174,23 +4172,18 @@ static const struct rpc_call_ops nfs4_recover_lock_ops = {
 
 static void nfs4_handle_setlk_error(struct nfs_server *server, struct nfs4_lock_state *lsp, int new_lock_owner, int error)
 {
-        struct nfs_client *clp = server->nfs_client;
-        struct nfs4_state *state = lsp->ls_state;
-
         switch (error) {
         case -NFS4ERR_ADMIN_REVOKED:
         case -NFS4ERR_BAD_STATEID:
-        case -NFS4ERR_EXPIRED:
+                lsp->ls_seqid.flags &= ~NFS_SEQID_CONFIRMED;
                 if (new_lock_owner != 0 ||
                    (lsp->ls_flags & NFS_LOCK_INITIALIZED) != 0)
-                        nfs4_state_mark_reclaim_nograce(clp, state);
-                lsp->ls_seqid.flags &= ~NFS_SEQID_CONFIRMED;
+                        nfs4_schedule_stateid_recovery(server, lsp->ls_state);
                 break;
         case -NFS4ERR_STALE_STATEID:
-                if (new_lock_owner != 0 ||
-                    (lsp->ls_flags & NFS_LOCK_INITIALIZED) != 0)
-                        nfs4_state_mark_reclaim_reboot(clp, state);
                 lsp->ls_seqid.flags &= ~NFS_SEQID_CONFIRMED;
+        case -NFS4ERR_EXPIRED:
+                nfs4_schedule_lease_recovery(server->nfs_client);
         };
 }
 
@@ -4406,12 +4399,14 @@ int nfs4_lock_delegation_recall(struct nfs4_state *state, struct file_lock *fl)
                         case -NFS4ERR_EXPIRED:
                         case -NFS4ERR_STALE_CLIENTID:
                         case -NFS4ERR_STALE_STATEID:
+                                nfs4_schedule_lease_recovery(server->nfs_client);
+                                goto out;
                         case -NFS4ERR_BADSESSION:
                         case -NFS4ERR_BADSLOT:
                         case -NFS4ERR_BAD_HIGH_SLOT:
                         case -NFS4ERR_CONN_NOT_BOUND_TO_SESSION:
                         case -NFS4ERR_DEADSESSION:
-                                nfs4_schedule_state_recovery(server->nfs_client);
+                                nfs4_schedule_session_recovery(server->nfs_client->cl_session);
                                 goto out;
                         case -ERESTARTSYS:
                                 /*
@@ -4421,7 +4416,7 @@ int nfs4_lock_delegation_recall(struct nfs4_state *state, struct file_lock *fl)
                         case -NFS4ERR_ADMIN_REVOKED:
                         case -NFS4ERR_BAD_STATEID:
                         case -NFS4ERR_OPENMODE:
-                                nfs4_state_mark_reclaim_nograce(server->nfs_client, state);
+                                nfs4_schedule_stateid_recovery(server, state);
                                 err = 0;
                                 goto out;
                         case -EKEYEXPIRED:
@@ -5028,10 +5023,20 @@ int nfs4_proc_create_session(struct nfs_client *clp)
         int status;
         unsigned *ptr;
         struct nfs4_session *session = clp->cl_session;
+        long timeout = 0;
+        int err;
 
         dprintk("--> %s clp=%p session=%p\n", __func__, clp, session);
 
-        status = _nfs4_proc_create_session(clp);
+        do {
+                status = _nfs4_proc_create_session(clp);
+                if (status == -NFS4ERR_DELAY) {
+                        err = nfs4_delay(clp->cl_rpcclient, &timeout);
+                        if (err)
+                                status = err;
+                }
+        } while (status == -NFS4ERR_DELAY);
+
         if (status)
                 goto out;
 
@@ -5140,7 +5145,7 @@ static int nfs41_sequence_handle_errors(struct rpc_task *task, struct nfs_client
                 rpc_delay(task, NFS4_POLL_RETRY_MAX);
                 return -EAGAIN;
         default:
-                nfs4_schedule_state_recovery(clp);
+                nfs4_schedule_lease_recovery(clp);
         }
         return 0;
 }
@@ -5227,7 +5232,7 @@ static int nfs41_proc_async_sequence(struct nfs_client *clp, struct rpc_cred *cr
         if (IS_ERR(task))
                 ret = PTR_ERR(task);
         else
-                rpc_put_task(task);
+                rpc_put_task_async(task);
         dprintk("<-- %s status=%d\n", __func__, ret);
         return ret;
 }
@@ -5243,8 +5248,13 @@ static int nfs4_proc_sequence(struct nfs_client *clp, struct rpc_cred *cred)
                 goto out;
         }
         ret = rpc_wait_for_completion_task(task);
-        if (!ret)
+        if (!ret) {
+                struct nfs4_sequence_res *res = task->tk_msg.rpc_resp;
+
+                if (task->tk_status == 0)
+                        nfs41_handle_sequence_flag_errors(clp, res->sr_status_flags);
                 ret = task->tk_status;
+        }
         rpc_put_task(task);
 out:
         dprintk("<-- %s status=%d\n", __func__, ret);
@@ -5281,7 +5291,7 @@ static int nfs41_reclaim_complete_handle_errors(struct rpc_task *task, struct nf
                 rpc_delay(task, NFS4_POLL_RETRY_MAX);
                 return -EAGAIN;
         default:
-                nfs4_schedule_state_recovery(clp);
+                nfs4_schedule_lease_recovery(clp);
         }
         return 0;
 }
@@ -5349,6 +5359,9 @@ static int nfs41_proc_reclaim_complete(struct nfs_client *clp)
                 status = PTR_ERR(task);
                 goto out;
         }
+        status = nfs4_wait_for_completion_rpc_task(task);
+        if (status == 0)
+                status = task->tk_status;
         rpc_put_task(task);
         return 0;
 out:
diff --git a/fs/nfs/nfs4state.c b/fs/nfs/nfs4state.c
index e6742b57a04c..0592288f9f06 100644
--- a/fs/nfs/nfs4state.c
+++ b/fs/nfs/nfs4state.c
@@ -1007,9 +1007,9 @@ void nfs4_schedule_state_manager(struct nfs_client *clp)
 }
 
 /*
- * Schedule a state recovery attempt
+ * Schedule a lease recovery attempt
  */
-void nfs4_schedule_state_recovery(struct nfs_client *clp)
+void nfs4_schedule_lease_recovery(struct nfs_client *clp)
 {
         if (!clp)
                 return;
@@ -1018,7 +1018,7 @@ void nfs4_schedule_state_recovery(struct nfs_client *clp)
         nfs4_schedule_state_manager(clp);
 }
 
-int nfs4_state_mark_reclaim_reboot(struct nfs_client *clp, struct nfs4_state *state)
+static int nfs4_state_mark_reclaim_reboot(struct nfs_client *clp, struct nfs4_state *state)
 {
 
         set_bit(NFS_STATE_RECLAIM_REBOOT, &state->flags);
@@ -1032,7 +1032,7 @@ int nfs4_state_mark_reclaim_reboot(struct nfs_client *clp, struct nfs4_state *st
         return 1;
 }
 
-int nfs4_state_mark_reclaim_nograce(struct nfs_client *clp, struct nfs4_state *state)
+static int nfs4_state_mark_reclaim_nograce(struct nfs_client *clp, struct nfs4_state *state)
 {
         set_bit(NFS_STATE_RECLAIM_NOGRACE, &state->flags);
         clear_bit(NFS_STATE_RECLAIM_REBOOT, &state->flags);
@@ -1041,6 +1041,14 @@ int nfs4_state_mark_reclaim_nograce(struct nfs_client *clp, struct nfs4_state *s
         return 1;
 }
 
+void nfs4_schedule_stateid_recovery(const struct nfs_server *server, struct nfs4_state *state)
+{
+        struct nfs_client *clp = server->nfs_client;
+
+        nfs4_state_mark_reclaim_nograce(clp, state);
+        nfs4_schedule_state_manager(clp);
+}
+
 static int nfs4_reclaim_locks(struct nfs4_state *state, const struct nfs4_state_recovery_ops *ops)
 {
         struct inode *inode = state->inode;
@@ -1436,10 +1444,15 @@ static int nfs4_reclaim_lease(struct nfs_client *clp)
 }
 
 #ifdef CONFIG_NFS_V4_1
+void nfs4_schedule_session_recovery(struct nfs4_session *session)
+{
+        nfs4_schedule_lease_recovery(session->clp);
+}
+
 void nfs41_handle_recall_slot(struct nfs_client *clp)
 {
         set_bit(NFS4CLNT_RECALL_SLOT, &clp->cl_state);
-        nfs4_schedule_state_recovery(clp);
+        nfs4_schedule_state_manager(clp);
 }
 
 static void nfs4_reset_all_state(struct nfs_client *clp)
@@ -1447,7 +1460,7 @@ static void nfs4_reset_all_state(struct nfs_client *clp)
         if (test_and_set_bit(NFS4CLNT_LEASE_EXPIRED, &clp->cl_state) == 0) {
                 clp->cl_boot_time = CURRENT_TIME;
                 nfs4_state_start_reclaim_nograce(clp);
-                nfs4_schedule_state_recovery(clp);
+                nfs4_schedule_state_manager(clp);
         }
 }
 
@@ -1455,7 +1468,7 @@ static void nfs41_handle_server_reboot(struct nfs_client *clp)
 {
         if (test_and_set_bit(NFS4CLNT_LEASE_EXPIRED, &clp->cl_state) == 0) {
                 nfs4_state_start_reclaim_reboot(clp);
-                nfs4_schedule_state_recovery(clp);
+                nfs4_schedule_state_manager(clp);
         }
 }
 
@@ -1475,7 +1488,7 @@ static void nfs41_handle_cb_path_down(struct nfs_client *clp)
 {
         nfs_expire_all_delegations(clp);
         if (test_and_set_bit(NFS4CLNT_SESSION_RESET, &clp->cl_state) == 0)
-                nfs4_schedule_state_recovery(clp);
+                nfs4_schedule_state_manager(clp);
 }
 
 void nfs41_handle_sequence_flag_errors(struct nfs_client *clp, u32 flags)
diff --git a/fs/nfs/nfs4xdr.c b/fs/nfs/nfs4xdr.c
index 4e2c168b6ee9..94d50e86a124 100644
--- a/fs/nfs/nfs4xdr.c
+++ b/fs/nfs/nfs4xdr.c
@@ -1660,7 +1660,7 @@ static void encode_create_session(struct xdr_stream *xdr,
 
         p = reserve_space(xdr, 20 + 2*28 + 20 + len + 12);
         *p++ = cpu_to_be32(OP_CREATE_SESSION);
-        p = xdr_encode_hyper(p, clp->cl_ex_clid);
+        p = xdr_encode_hyper(p, clp->cl_clientid);
         *p++ = cpu_to_be32(clp->cl_seqid);                      /*Sequence id */
         *p++ = cpu_to_be32(args->flags);                        /*flags */
 
@@ -4694,7 +4694,7 @@ static int decode_exchange_id(struct xdr_stream *xdr,
         p = xdr_inline_decode(xdr, 8);
         if (unlikely(!p))
                 goto out_overflow;
-        xdr_decode_hyper(p, &clp->cl_ex_clid);
+        xdr_decode_hyper(p, &clp->cl_clientid);
         p = xdr_inline_decode(xdr, 12);
         if (unlikely(!p))
                 goto out_overflow;
diff --git a/fs/nfs/nfsroot.c b/fs/nfs/nfsroot.c
index 903908a20023..c541093a5bf2 100644
--- a/fs/nfs/nfsroot.c
+++ b/fs/nfs/nfsroot.c
@@ -86,11 +86,14 @@
 /* Default path we try to mount. "%s" gets replaced by our IP address */
 #define NFS_ROOT                "/tftpboot/%s"
 
+/* Default NFSROOT mount options. */
+#define NFS_DEF_OPTIONS         "udp"
+
 /* Parameters passed from the kernel command line */
 static char nfs_root_parms[256] __initdata = "";
 
 /* Text-based mount options passed to super.c */
-static char nfs_root_options[256] __initdata = "";
+static char nfs_root_options[256] __initdata = NFS_DEF_OPTIONS;
 
 /* Address of NFS server */
 static __be32 servaddr __initdata = htonl(INADDR_NONE);
@@ -160,8 +163,14 @@ static int __init root_nfs_copy(char *dest, const char *src,
 }
 
 static int __init root_nfs_cat(char *dest, const char *src,
-                                  const size_t destlen)
+                               const size_t destlen)
 {
+        size_t len = strlen(dest);
+
+        if (len && dest[len - 1] != ',')
+                if (strlcat(dest, ",", destlen) > destlen)
+                        return -1;
+
         if (strlcat(dest, src, destlen) > destlen)
                 return -1;
         return 0;
@@ -194,16 +203,6 @@ static int __init root_nfs_parse_options(char *incoming, char *exppath,
                 if (root_nfs_cat(nfs_root_options, incoming,
                                                 sizeof(nfs_root_options)))
                         return -1;
-
-        /*
-         * Possibly prepare for more options to be appended
-         */
-        if (nfs_root_options[0] != '\0' &&
-            nfs_root_options[strlen(nfs_root_options)] != ',')
-                if (root_nfs_cat(nfs_root_options, ",",
-                                                sizeof(nfs_root_options)))
-                        return -1;
-
         return 0;
 }
 
@@ -217,7 +216,7 @@ static int __init root_nfs_parse_options(char *incoming, char *exppath,
  */
 static int __init root_nfs_data(char *cmdline)
 {
-        char addr_option[sizeof("nolock,addr=") + INET_ADDRSTRLEN + 1];
+        char mand_options[sizeof("nolock,addr=") + INET_ADDRSTRLEN + 1];
         int len, retval = -1;
         char *tmp = NULL;
         const size_t tmplen = sizeof(nfs_export_path);
@@ -244,9 +243,9 @@ static int __init root_nfs_data(char *cmdline)
          * Append mandatory options for nfsroot so they override
          * what has come before
          */
-        snprintf(addr_option, sizeof(addr_option), "nolock,addr=%pI4",
+        snprintf(mand_options, sizeof(mand_options), "nolock,addr=%pI4",
                         &servaddr);
-        if (root_nfs_cat(nfs_root_options, addr_option,
+        if (root_nfs_cat(nfs_root_options, mand_options,
                                                 sizeof(nfs_root_options)))
                 goto out_optionstoolong;
 
diff --git a/fs/nfs/unlink.c b/fs/nfs/unlink.c
index e313a51acdd1..6481d537d69d 100644
--- a/fs/nfs/unlink.c
+++ b/fs/nfs/unlink.c
@@ -180,7 +180,7 @@ static int nfs_do_call_unlink(struct dentry *parent, struct inode *dir, struct n
         task_setup_data.rpc_client = NFS_CLIENT(dir);
         task = rpc_run_task(&task_setup_data);
         if (!IS_ERR(task))
-                rpc_put_task(task);
+                rpc_put_task_async(task);
         return 1;
 }
 
diff --git a/fs/nfs/write.c b/fs/nfs/write.c
index c8278f4046cb..42b92d7a9cc4 100644
--- a/fs/nfs/write.c
+++ b/fs/nfs/write.c
@@ -1292,6 +1292,8 @@ static int nfs_commit_rpcsetup(struct list_head *head,
         task = rpc_run_task(&task_setup_data);
         if (IS_ERR(task))
                 return PTR_ERR(task);
+        if (how & FLUSH_SYNC)
+                rpc_wait_for_completion_task(task);
         rpc_put_task(task);
         return 0;
 }
diff --git a/fs/partitions/osf.c b/fs/partitions/osf.c
index 48cec7cbca17..be03a0b08b47 100644
--- a/fs/partitions/osf.c
+++ b/fs/partitions/osf.c
@@ -10,10 +10,13 @@
 #include "check.h"
 #include "osf.h"
 
+#define MAX_OSF_PARTITIONS 8
+
 int osf_partition(struct parsed_partitions *state)
 {
         int i;
         int slot = 1;
+        unsigned int npartitions;
         Sector sect;
         unsigned char *data;
         struct disklabel {
@@ -45,7 +48,7 @@ int osf_partition(struct parsed_partitions *state)
                         u8  p_fstype;
                         u8  p_frag;
                         __le16 p_cpg;
-                } d_partitions[8];
+                } d_partitions[MAX_OSF_PARTITIONS];
         } * label;
         struct d_partition * partition;
 
@@ -63,7 +66,12 @@ int osf_partition(struct parsed_partitions *state)
                 put_dev_sector(sect);
                 return 0;
         }
-        for (i = 0 ; i < le16_to_cpu(label->d_npartitions); i++, partition++) {
+        npartitions = le16_to_cpu(label->d_npartitions);
+        if (npartitions > MAX_OSF_PARTITIONS) {
+                put_dev_sector(sect);
+                return 0;
+        }
+        for (i = 0 ; i < npartitions; i++, partition++) {
                 if (slot == state->limit)
                         break;
                 if (le32_to_cpu(partition->p_size))