ceph: add infrastructure for waiting for async create to complete

When we issue an async create, we must ensure that any later on-the-wire
requests involving it wait for the create reply.

Expand i_ceph_flags to be an unsigned long, and add a new bit that
MDS requests can wait on. If the bit is set in the inode when sending
caps, then don't send it and just return that it has been delayed.

Signed-off-by: Jeff Layton <jlayton@kernel.org>
Reviewed-by: "Yan, Zheng" <zyan@redhat.com>
Signed-off-by: Ilya Dryomov <idryomov@gmail.com>

diff --git a/fs/ceph/caps.c b/fs/ceph/caps.c
index 739c06611522b8111fc0f6a330a9ff6182bf2f99..fcad5d8ebcfa8c1c5ddc02f9628e21b0929f252e 100644 (file)
--- a/fs/ceph/caps.c
+++ b/fs/ceph/caps.c
@@ -511,7 +511,7 @@ static void __cap_delay_requeue(struct ceph_mds_client *mdsc,
                                struct ceph_inode_info *ci,
                                bool set_timeout)
 {
-       dout("__cap_delay_requeue %p flags %d at %lu\n", &ci->vfs_inode,
+       dout("__cap_delay_requeue %p flags 0x%lx at %lu\n", &ci->vfs_inode,
             ci->i_ceph_flags, ci->i_hold_caps_max);
        if (!mdsc->stopping) {
                spin_lock(&mdsc->cap_delay_lock);
@@ -1294,6 +1294,13 @@ static int __send_cap(struct ceph_mds_client *mdsc, struct ceph_cap *cap,
        int delayed = 0;
        int ret;
 
+       /* Don't send anything if it's still being created. Return delayed */
+       if (ci->i_ceph_flags & CEPH_I_ASYNC_CREATE) {
+               spin_unlock(&ci->i_ceph_lock);
+               dout("%s async create in flight for %p\n", __func__, inode);
+               return 1;
+       }
+
        held = cap->issued | cap->implemented;
        revoking = cap->implemented & ~cap->issued;
        retain &= ~revoking;
@@ -2253,6 +2260,10 @@ int ceph_fsync(struct file *file, loff_t start, loff_t end, int datasync)
        if (datasync)
                goto out;
 
+       ret = ceph_wait_on_async_create(inode);
+       if (ret)
+               goto out;
+
        dirty = try_flush_caps(inode, &flush_tid);
        dout("fsync dirty caps are %s\n", ceph_cap_string(dirty));
 

diff --git a/fs/ceph/dir.c b/fs/ceph/dir.c
index a87274935a09529033ab72a1a5116c2273f1e778..5b83bda5705653a0689a5d8502ffad0b32af34bf 100644 (file)
--- a/fs/ceph/dir.c
+++ b/fs/ceph/dir.c
@@ -752,7 +752,7 @@ static struct dentry *ceph_lookup(struct inode *dir, struct dentry *dentry,
                struct ceph_dentry_info *di = ceph_dentry(dentry);
 
                spin_lock(&ci->i_ceph_lock);
-               dout(" dir %p flags are %d\n", dir, ci->i_ceph_flags);
+               dout(" dir %p flags are 0x%lx\n", dir, ci->i_ceph_flags);
                if (strncmp(dentry->d_name.name,
                            fsc->mount_options->snapdir_name,
                            dentry->d_name.len) &&

diff --git a/fs/ceph/mds_client.c b/fs/ceph/mds_client.c
index 9e8b2099e63f58f63443838e2f1c09ea7d0c94ee..c433655eba62548dcb530f75a6672675e16b400e 100644 (file)
--- a/fs/ceph/mds_client.c
+++ b/fs/ceph/mds_client.c
@@ -2730,7 +2730,7 @@ static void kick_requests(struct ceph_mds_client *mdsc, int mds)
 int ceph_mdsc_submit_request(struct ceph_mds_client *mdsc, struct inode *dir,
                              struct ceph_mds_request *req)
 {
-       int err;
+       int err = 0;
 
        /* take CAP_PIN refs for r_inode, r_parent, r_old_dentry */
        if (req->r_inode)
@@ -2743,6 +2743,24 @@ int ceph_mdsc_submit_request(struct ceph_mds_client *mdsc, struct inode *dir,
                ceph_get_cap_refs(ceph_inode(req->r_old_dentry_dir),
                                  CEPH_CAP_PIN);
 
+       if (req->r_inode) {
+               err = ceph_wait_on_async_create(req->r_inode);
+               if (err) {
+                       dout("%s: wait for async create returned: %d\n",
+                            __func__, err);
+                       return err;
+               }
+       }
+
+       if (!err && req->r_old_inode) {
+               err = ceph_wait_on_async_create(req->r_old_inode);
+               if (err) {
+                       dout("%s: wait for async create returned: %d\n",
+                            __func__, err);
+                       return err;
+               }
+       }
+
        dout("submit_request on %p for inode %p\n", req, dir);
        mutex_lock(&mdsc->mutex);
        __register_request(mdsc, req, dir);

diff --git a/fs/ceph/mds_client.h b/fs/ceph/mds_client.h
index 95ac00e59e66a54e025db6fa5512cd1ef294d5ea..8043f2b439b14e8da26f74f99ca5ff5363fe4708 100644 (file)
--- a/fs/ceph/mds_client.h
+++ b/fs/ceph/mds_client.h
@@ -538,4 +538,11 @@ extern void ceph_mdsc_open_export_target_sessions(struct ceph_mds_client *mdsc,
 extern int ceph_trim_caps(struct ceph_mds_client *mdsc,
                          struct ceph_mds_session *session,
                          int max_caps);
+static inline int ceph_wait_on_async_create(struct inode *inode)
+{
+       struct ceph_inode_info *ci = ceph_inode(inode);
+
+       return wait_on_bit(&ci->i_ceph_flags, CEPH_ASYNC_CREATE_BIT,
+                          TASK_INTERRUPTIBLE);
+}
 #endif

diff --git a/fs/ceph/super.h b/fs/ceph/super.h
index 7a93f37e7708ef20dd475c42f3b043eaa48ae109..00bf846e00141102863f34385915bd19d9b15bce 100644 (file)
--- a/fs/ceph/super.h
+++ b/fs/ceph/super.h
@@ -316,7 +316,7 @@ struct ceph_inode_info {
        u64 i_inline_version;
        u32 i_time_warp_seq;
 
-       unsigned i_ceph_flags;
+       unsigned long i_ceph_flags;
        atomic64_t i_release_count;
        atomic64_t i_ordered_count;
        atomic64_t i_complete_seq[2];
@@ -524,6 +524,8 @@ static inline struct inode *ceph_find_inode(struct super_block *sb,
 #define CEPH_I_ERROR_WRITE     (1 << 10) /* have seen write errors */
 #define CEPH_I_ERROR_FILELOCK  (1 << 11) /* have seen file lock errors */
 #define CEPH_I_ODIRECT         (1 << 12) /* inode in direct I/O mode */
+#define CEPH_ASYNC_CREATE_BIT  (13)      /* async create in flight for this */
+#define CEPH_I_ASYNC_CREATE    (1 << CEPH_ASYNC_CREATE_BIT)
 
 /*
  * Masks of ceph inode work.