Merge branch 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/sage/ceph-client

Pull Ceph changes from Sage Weil:
 "On the RBD side, there is a conversion to blk-mq from Christoph,
  several long-standing bug fixes from Ilya, and some cleanup from
  Rickard Strandqvist.

  On the CephFS side there is a long list of fixes from Zheng, including
  improved session handling, a few IO path fixes, some dcache management
  correctness fixes, and several blocking while !TASK_RUNNING fixes.

  The core code gets a few cleanups and Chaitanya has added support for
  TCP_NODELAY (which has been used on the server side for ages but we
  somehow missed on the kernel client).

  There is also an update to MAINTAINERS to fix up some email addresses
  and reflect that Ilya and Zheng are doing most of the maintenance for
  RBD and CephFS these days.  Do not be surprised to see a pull request
  come from one of them in the future if I am unavailable for some
  reason"

* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/sage/ceph-client: (27 commits)
  MAINTAINERS: update Ceph and RBD maintainers
  libceph: kfree() in put_osd() shouldn't depend on authorizer
  libceph: fix double __remove_osd() problem
  rbd: convert to blk-mq
  ceph: return error for traceless reply race
  ceph: fix dentry leaks
  ceph: re-send requests when MDS enters reconnecting stage
  ceph: show nocephx_require_signatures and notcp_nodelay options
  libceph: tcp_nodelay support
  rbd: do not treat standalone as flatten
  ceph: fix atomic_open snapdir
  ceph: properly mark empty directory as complete
  client: include kernel version in client metadata
  ceph: provide seperate {inode,file}_operations for snapdir
  ceph: fix request time stamp encoding
  ceph: fix reading inline data when i_size > PAGE_SIZE
  ceph: avoid block operation when !TASK_RUNNING (ceph_mdsc_close_sessions)
  ceph: avoid block operation when !TASK_RUNNING (ceph_get_caps)
  ceph: avoid block operation when !TASK_RUNNING (ceph_mdsc_sync)
  rbd: fix error paths in rbd_dev_refresh()
  ...

1 files changed, 22 insertions, 15 deletions

diff --git a/fs/ceph/file.c b/fs/ceph/file.c
index 905986dd4c3c..a3d774b35149 100644
--- a/fs/ceph/file.c
+++ b/fs/ceph/file.c
@@ -275,10 +275,10 @@ int ceph_atomic_open(struct inode *dir, struct dentry *dentry,
 	err = ceph_mdsc_do_request(mdsc,
 				   (flags & (O_CREAT|O_TRUNC)) ? dir : NULL,
 				   req);
+	err = ceph_handle_snapdir(req, dentry, err);
 	if (err)
 		goto out_req;
 
-	err = ceph_handle_snapdir(req, dentry, err);
 	if (err == 0 && (flags & O_CREAT) && !req->r_reply_info.head->is_dentry)
 		err = ceph_handle_notrace_create(dir, dentry);
 
@@ -392,13 +392,14 @@ more:
 	if (ret >= 0) {
 		int didpages;
 		if (was_short && (pos + ret < inode->i_size)) {
-			u64 tmp = min(this_len - ret,
-					inode->i_size - pos - ret);
+			int zlen = min(this_len - ret,
+				       inode->i_size - pos - ret);
+			int zoff = (o_direct ? buf_align : io_align) +
+				    read + ret;
 			dout(" zero gap %llu to %llu\n",
-				pos + ret, pos + ret + tmp);
-			ceph_zero_page_vector_range(page_align + read + ret,
-							tmp, pages);
-			ret += tmp;
+				pos + ret, pos + ret + zlen);
+			ceph_zero_page_vector_range(zoff, zlen, pages);
+			ret += zlen;
 		}
 
 		didpages = (page_align + ret) >> PAGE_CACHE_SHIFT;
@@ -878,28 +879,34 @@ again:
 
 		i_size = i_size_read(inode);
 		if (retry_op == READ_INLINE) {
-			/* does not support inline data > PAGE_SIZE */
-			if (i_size > PAGE_CACHE_SIZE) {
-				ret = -EIO;
-			} else if (iocb->ki_pos < i_size) {
+			BUG_ON(ret > 0 || read > 0);
+			if (iocb->ki_pos < i_size &&
+			    iocb->ki_pos < PAGE_CACHE_SIZE) {
 				loff_t end = min_t(loff_t, i_size,
 						   iocb->ki_pos + len);
+				end = min_t(loff_t, end, PAGE_CACHE_SIZE);
 				if (statret < end)
 					zero_user_segment(page, statret, end);
 				ret = copy_page_to_iter(page,
 						iocb->ki_pos & ~PAGE_MASK,
 						end - iocb->ki_pos, to);
 				iocb->ki_pos += ret;
-			} else {
-				ret = 0;
+				read += ret;
+			}
+			if (iocb->ki_pos < i_size && read < len) {
+				size_t zlen = min_t(size_t, len - read,
+						    i_size - iocb->ki_pos);
+				ret = iov_iter_zero(zlen, to);
+				iocb->ki_pos += ret;
+				read += ret;
 			}
 			__free_pages(page, 0);
-			return ret;
+			return read;
 		}
 
 		/* hit EOF or hole? */
 		if (retry_op == CHECK_EOF && iocb->ki_pos < i_size &&
-			ret < len) {
+		    ret < len) {
 			dout("sync_read hit hole, ppos %lld < size %lld"
 			     ", reading more\n", iocb->ki_pos,
 			     inode->i_size);