Merge tag 'ceph-for-4.12-rc1' of git://github.com/ceph/ceph-client

Pull ceph updates from Ilya Dryomov:
 "The two main items are support for disabling automatic rbd exclusive
  lock transfers from myself and the long awaited -ENOSPC handling
  series from Jeff.

  The former will allow rbd users to take advantage of exclusive lock's
  built-in blacklist/break-lock functionality while staying in control
  of who owns the lock. With the latter in place, we will abort
  filesystem writes on -ENOSPC instead of having them block
  indefinitely.

  Beyond that we've got the usual pile of filesystem fixes from Zheng,
  some refcount_t conversion patches from Elena and a patch for an
  ancient open() flags handling bug from Alexander"

* tag 'ceph-for-4.12-rc1' of git://github.com/ceph/ceph-client: (31 commits)
  ceph: fix memory leak in __ceph_setxattr()
  ceph: fix file open flags on ppc64
  ceph: choose readdir frag based on previous readdir reply
  rbd: exclusive map option
  rbd: return ResponseMessage result from rbd_handle_request_lock()
  rbd: kill rbd_is_lock_supported()
  rbd: support updating the lock cookie without releasing the lock
  rbd: store lock cookie
  rbd: ignore unlock errors
  rbd: fix error handling around rbd_init_disk()
  rbd: move rbd_unregister_watch() call into rbd_dev_image_release()
  rbd: move rbd_dev_destroy() call out of rbd_dev_image_release()
  ceph: when seeing write errors on an inode, switch to sync writes
  Revert "ceph: SetPageError() for writeback pages if writepages fails"
  ceph: handle epoch barriers in cap messages
  libceph: add an epoch_barrier field to struct ceph_osd_client
  libceph: abort already submitted but abortable requests when map or pool goes full
  libceph: allow requests to return immediately on full conditions if caller wishes
  libceph: remove req->r_replay_version
  ceph: make seeky readdir more efficient
  ...

1 files changed, 53 insertions, 15 deletions

diff --git a/fs/ceph/file.c b/fs/ceph/file.c
index 18c045e2ead6..3fdde0b283c9 100644
--- a/fs/ceph/file.c
+++ b/fs/ceph/file.c
@@ -13,6 +13,38 @@
 #include "mds_client.h"
 #include "cache.h"
 
+static __le32 ceph_flags_sys2wire(u32 flags)
+{
+        u32 wire_flags = 0;
+
+        switch (flags & O_ACCMODE) {
+        case O_RDONLY:
+                wire_flags |= CEPH_O_RDONLY;
+                break;
+        case O_WRONLY:
+                wire_flags |= CEPH_O_WRONLY;
+                break;
+        case O_RDWR:
+                wire_flags |= CEPH_O_RDWR;
+                break;
+        }
+
+#define ceph_sys2wire(a) if (flags & a) { wire_flags |= CEPH_##a; flags &= ~a; }
+
+        ceph_sys2wire(O_CREAT);
+        ceph_sys2wire(O_EXCL);
+        ceph_sys2wire(O_TRUNC);
+        ceph_sys2wire(O_DIRECTORY);
+        ceph_sys2wire(O_NOFOLLOW);
+
+#undef ceph_sys2wire
+
+        if (flags)
+                dout("unused open flags: %x", flags);
+
+        return cpu_to_le32(wire_flags);
+}
+
 /*
  * Ceph file operations
  *
@@ -120,7 +152,7 @@ prepare_open_request(struct super_block *sb, int flags, int create_mode)
         if (IS_ERR(req))
                 goto out;
         req->r_fmode = ceph_flags_to_mode(flags);
-        req->r_args.open.flags = cpu_to_le32(flags);
+        req->r_args.open.flags = ceph_flags_sys2wire(flags);
         req->r_args.open.mode = cpu_to_le32(create_mode);
 out:
         return req;
@@ -189,7 +221,7 @@ int ceph_renew_caps(struct inode *inode)
         spin_lock(&ci->i_ceph_lock);
         wanted = __ceph_caps_file_wanted(ci);
         if (__ceph_is_any_real_caps(ci) &&
-            (!(wanted & CEPH_CAP_ANY_WR) == 0 || ci->i_auth_cap)) {
+            (!(wanted & CEPH_CAP_ANY_WR) || ci->i_auth_cap)) {
                 int issued = __ceph_caps_issued(ci, NULL);
                 spin_unlock(&ci->i_ceph_lock);
                 dout("renew caps %p want %s issued %s updating mds_wanted\n",
@@ -778,6 +810,7 @@ static void ceph_aio_retry_work(struct work_struct *work)
         req->r_callback = ceph_aio_complete_req;
         req->r_inode = inode;
         req->r_priv = aio_req;
+        req->r_abort_on_full = true;
 
         ret = ceph_osdc_start_request(req->r_osdc, req, false);
 out:
@@ -1085,19 +1118,22 @@ ceph_sync_write(struct kiocb *iocb, struct iov_iter *from, loff_t pos,
 
 out:
                 ceph_osdc_put_request(req);
-                if (ret == 0) {
-                        pos += len;
-                        written += len;
-
-                        if (pos > i_size_read(inode)) {
-                                check_caps = ceph_inode_set_size(inode, pos);
-                                if (check_caps)
-                                        ceph_check_caps(ceph_inode(inode),
-                                                        CHECK_CAPS_AUTHONLY,
-                                                        NULL);
-                        }
-                } else
+                if (ret != 0) {
+                        ceph_set_error_write(ci);
                         break;
+                }
+
+                ceph_clear_error_write(ci);
+                pos += len;
+                written += len;
+                if (pos > i_size_read(inode)) {
+                        check_caps = ceph_inode_set_size(inode, pos);
+                        if (check_caps)
+                                ceph_check_caps(ceph_inode(inode),
+                                                CHECK_CAPS_AUTHONLY,
+                                                NULL);
+                }
+
         }
 
         if (ret != -EOLDSNAPC && written > 0) {
@@ -1303,6 +1339,7 @@ static ssize_t ceph_write_iter(struct kiocb *iocb, struct iov_iter *from)
         }
 
 retry_snap:
+        /* FIXME: not complete since it doesn't account for being at quota */
         if (ceph_osdmap_flag(osdc, CEPH_OSDMAP_FULL)) {
                 err = -ENOSPC;
                 goto out;
@@ -1324,7 +1361,8 @@ retry_snap:
              inode, ceph_vinop(inode), pos, count, ceph_cap_string(got));
 
         if ((got & (CEPH_CAP_FILE_BUFFER|CEPH_CAP_FILE_LAZYIO)) == 0 ||
-            (iocb->ki_flags & IOCB_DIRECT) || (fi->flags & CEPH_F_SYNC)) {
+            (iocb->ki_flags & IOCB_DIRECT) || (fi->flags & CEPH_F_SYNC) ||
+            (ci->i_ceph_flags & CEPH_I_ERROR_WRITE)) {
                 struct ceph_snap_context *snapc;
                 struct iov_iter data;
                 inode_unlock(inode);