Merge tag 'ceph-for-5.19-rc1' of https://github.com/ceph/ceph-client

Pull ceph updates from Ilya Dryomov:
 "A big pile of assorted fixes and improvements for the filesystem with
  nothing in particular standing out, except perhaps that the fact that
  the MDS never really maintained atime was made official and thus it's
  no longer updated on the client either.

  We also have a MAINTAINERS update: Jeff is transitioning his
  filesystem maintainership duties to Xiubo"

* tag 'ceph-for-5.19-rc1' of https://github.com/ceph/ceph-client: (23 commits)
  MAINTAINERS: move myself from ceph "Maintainer" to "Reviewer"
  ceph: fix decoding of client session messages flags
  ceph: switch TASK_INTERRUPTIBLE to TASK_KILLABLE
  ceph: remove redundant variable ino
  ceph: try to queue a writeback if revoking fails
  ceph: fix statfs for subdir mounts
  ceph: fix possible deadlock when holding Fwb to get inline_data
  ceph: redirty the page for writepage on failure
  ceph: try to choose the auth MDS if possible for getattr
  ceph: disable updating the atime since cephfs won't maintain it
  ceph: flush the mdlog for filesystem sync
  ceph: rename unsafe_request_wait()
  libceph: use swap() macro instead of taking tmp variable
  ceph: fix statx AT_STATX_DONT_SYNC vs AT_STATX_FORCE_SYNC check
  ceph: no need to invalidate the fscache twice
  ceph: replace usage of found with dedicated list iterator variable
  ceph: use dedicated list iterator variable
  ceph: update the dlease for the hashed dentry when removing
  ceph: stop retrying the request when exceeding 256 times
  ceph: stop forwarding the request when exceeding 256 times
  ...

1 files changed, 25 insertions, 17 deletions

diff --git a/fs/ceph/addr.c b/fs/ceph/addr.c
index 7584aa6e5025..e5221be6eb55 100644
--- a/fs/ceph/addr.c
+++ b/fs/ceph/addr.c
@@ -256,6 +256,7 @@ static bool ceph_netfs_issue_op_inline(struct netfs_io_subrequest *subreq)
 	struct iov_iter iter;
 	ssize_t err = 0;
 	size_t len;
+	int mode;
 
 	__set_bit(NETFS_SREQ_CLEAR_TAIL, &subreq->flags);
 	__clear_bit(NETFS_SREQ_COPY_TO_CACHE, &subreq->flags);
@@ -264,7 +265,8 @@ static bool ceph_netfs_issue_op_inline(struct netfs_io_subrequest *subreq)
 		goto out;
 
 	/* We need to fetch the inline data. */
-	req = ceph_mdsc_create_request(mdsc, CEPH_MDS_OP_GETATTR, USE_ANY_MDS);
+	mode = ceph_try_to_choose_auth_mds(inode, CEPH_STAT_CAP_INLINE_DATA);
+	req = ceph_mdsc_create_request(mdsc, CEPH_MDS_OP_GETATTR, mode);
 	if (IS_ERR(req)) {
 		err = PTR_ERR(req);
 		goto out;
@@ -604,8 +606,10 @@ static int writepage_nounlock(struct page *page, struct writeback_control *wbc)
 				    CEPH_OSD_OP_WRITE, CEPH_OSD_FLAG_WRITE, snapc,
 				    ceph_wbc.truncate_seq, ceph_wbc.truncate_size,
 				    true);
-	if (IS_ERR(req))
+	if (IS_ERR(req)) {
+		redirty_page_for_writepage(wbc, page);
 		return PTR_ERR(req);
+	}
 
 	set_page_writeback(page);
 	if (caching)
@@ -1644,7 +1648,7 @@ int ceph_uninline_data(struct file *file)
 	struct inode *inode = file_inode(file);
 	struct ceph_inode_info *ci = ceph_inode(inode);
 	struct ceph_fs_client *fsc = ceph_inode_to_client(inode);
-	struct ceph_osd_request *req;
+	struct ceph_osd_request *req = NULL;
 	struct ceph_cap_flush *prealloc_cf;
 	struct folio *folio = NULL;
 	u64 inline_version = CEPH_INLINE_NONE;
@@ -1652,10 +1656,23 @@ int ceph_uninline_data(struct file *file)
 	int err = 0;
 	u64 len;
 
+	spin_lock(&ci->i_ceph_lock);
+	inline_version = ci->i_inline_version;
+	spin_unlock(&ci->i_ceph_lock);
+
+	dout("uninline_data %p %llx.%llx inline_version %llu\n",
+	     inode, ceph_vinop(inode), inline_version);
+
+	if (inline_version == CEPH_INLINE_NONE)
+		return 0;
+
 	prealloc_cf = ceph_alloc_cap_flush();
 	if (!prealloc_cf)
 		return -ENOMEM;
 
+	if (inline_version == 1) /* initial version, no data */
+		goto out_uninline;
+
 	folio = read_mapping_folio(inode->i_mapping, 0, file);
 	if (IS_ERR(folio)) {
 		err = PTR_ERR(folio);
@@ -1664,17 +1681,6 @@ int ceph_uninline_data(struct file *file)
 
 	folio_lock(folio);
 
-	spin_lock(&ci->i_ceph_lock);
-	inline_version = ci->i_inline_version;
-	spin_unlock(&ci->i_ceph_lock);
-
-	dout("uninline_data %p %llx.%llx inline_version %llu\n",
-	     inode, ceph_vinop(inode), inline_version);
-
-	if (inline_version == 1 || /* initial version, no data */
-	    inline_version == CEPH_INLINE_NONE)
-		goto out_unlock;
-
 	len = i_size_read(inode);
 	if (len > folio_size(folio))
 		len = folio_size(folio);
@@ -1739,6 +1745,7 @@ int ceph_uninline_data(struct file *file)
 	ceph_update_write_metrics(&fsc->mdsc->metric, req->r_start_latency,
 				  req->r_end_latency, len, err);
 
+out_uninline:
 	if (!err) {
 		int dirty;
 
@@ -1757,8 +1764,10 @@ out_put_req:
 	if (err == -ECANCELED)
 		err = 0;
 out_unlock:
-	folio_unlock(folio);
-	folio_put(folio);
+	if (folio) {
+		folio_unlock(folio);
+		folio_put(folio);
+	}
 out:
 	ceph_free_cap_flush(prealloc_cf);
 	dout("uninline_data %p %llx.%llx inline_version %llu = %d\n",
@@ -1777,7 +1786,6 @@ int ceph_mmap(struct file *file, struct vm_area_struct *vma)
 
 	if (!mapping->a_ops->read_folio)
 		return -ENOEXEC;
-	file_accessed(file);
 	vma->vm_ops = &ceph_vmops;
 	return 0;
 }