summaryrefslogtreecommitdiff
path: root/fs/ceph
diff options
context:
space:
mode:
authorLinus Torvalds <torvalds@linux-foundation.org>2015-09-11 12:33:03 -0700
committerLinus Torvalds <torvalds@linux-foundation.org>2015-09-11 12:33:03 -0700
commite013f74b60bbd37ee8c3a55214eb351ea3101c15 (patch)
tree096b59f550dea6df9347edf97b872dc75a79f653 /fs/ceph
parent01cab5549c3e9a0fe7248fc5ad0fd79361cc0d39 (diff)
parent438386853d4c0c48fe73bf05a7d61c70ca5a3bfb (diff)
Merge branch 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/sage/ceph-client
Pull Ceph update from Sage Weil: "There are a few fixes for snapshot behavior with CephFS and support for the new keepalive protocol from Zheng, a libceph fix that affects both RBD and CephFS, a few bug fixes and cleanups for RBD from Ilya, and several small fixes and cleanups from Jianpeng and others" * 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/sage/ceph-client: ceph: improve readahead for file holes ceph: get inode size for each append write libceph: check data_len in ->alloc_msg() libceph: use keepalive2 to verify the mon session is alive rbd: plug rbd_dev->header.object_prefix memory leak rbd: fix double free on rbd_dev->header_name libceph: set 'exists' flag for newly up osd ceph: cleanup use of ceph_msg_get ceph: no need to get parent inode in ceph_open ceph: remove the useless judgement ceph: remove redundant test of head->safe and silence static analysis warnings ceph: fix queuing inode to mdsdir's snaprealm libceph: rename con_work() to ceph_con_workfn() libceph: Avoid holding the zero page on ceph_msgr_slab_init errors libceph: remove the unused macro AES_KEY_SIZE ceph: invalidate dirty pages after forced umount ceph: EIO all operations after forced umount
Diffstat (limited to 'fs/ceph')
-rw-r--r--fs/ceph/addr.c6
-rw-r--r--fs/ceph/caps.c8
-rw-r--r--fs/ceph/file.c14
-rw-r--r--fs/ceph/mds_client.c59
-rw-r--r--fs/ceph/mds_client.h1
-rw-r--r--fs/ceph/snap.c7
-rw-r--r--fs/ceph/super.c1
7 files changed, 67 insertions, 29 deletions
diff --git a/fs/ceph/addr.c b/fs/ceph/addr.c
index a268abfe60ac..9d23e788d1df 100644
--- a/fs/ceph/addr.c
+++ b/fs/ceph/addr.c
@@ -276,7 +276,7 @@ static void finish_read(struct ceph_osd_request *req, struct ceph_msg *msg)
for (i = 0; i < num_pages; i++) {
struct page *page = osd_data->pages[i];
- if (rc < 0)
+ if (rc < 0 && rc != ENOENT)
goto unlock;
if (bytes < (int)PAGE_CACHE_SIZE) {
/* zero (remainder of) page */
@@ -717,8 +717,10 @@ static int ceph_writepages_start(struct address_space *mapping,
wbc->sync_mode == WB_SYNC_NONE ? "NONE" :
(wbc->sync_mode == WB_SYNC_ALL ? "ALL" : "HOLD"));
- if (fsc->mount_state == CEPH_MOUNT_SHUTDOWN) {
+ if (ACCESS_ONCE(fsc->mount_state) == CEPH_MOUNT_SHUTDOWN) {
pr_warn("writepage_start %p on forced umount\n", inode);
+ truncate_pagecache(inode, 0);
+ mapping_set_error(mapping, -EIO);
return -EIO; /* we're in a forced umount, don't write! */
}
if (fsc->mount_options->wsize && fsc->mount_options->wsize < wsize)
diff --git a/fs/ceph/caps.c b/fs/ceph/caps.c
index ddd5e9471290..27b566874bc1 100644
--- a/fs/ceph/caps.c
+++ b/fs/ceph/caps.c
@@ -2413,6 +2413,14 @@ again:
goto out_unlock;
}
+ if (!__ceph_is_any_caps(ci) &&
+ ACCESS_ONCE(mdsc->fsc->mount_state) == CEPH_MOUNT_SHUTDOWN) {
+ dout("get_cap_refs %p forced umount\n", inode);
+ *err = -EIO;
+ ret = 1;
+ goto out_unlock;
+ }
+
dout("get_cap_refs %p have %s needed %s\n", inode,
ceph_cap_string(have), ceph_cap_string(need));
}
diff --git a/fs/ceph/file.c b/fs/ceph/file.c
index 8b79d87eaf46..0c62868b5c56 100644
--- a/fs/ceph/file.c
+++ b/fs/ceph/file.c
@@ -136,7 +136,6 @@ int ceph_open(struct inode *inode, struct file *file)
struct ceph_mds_client *mdsc = fsc->mdsc;
struct ceph_mds_request *req;
struct ceph_file_info *cf = file->private_data;
- struct inode *parent_inode = NULL;
int err;
int flags, fmode, wanted;
@@ -210,10 +209,7 @@ int ceph_open(struct inode *inode, struct file *file)
ihold(inode);
req->r_num_caps = 1;
- if (flags & O_CREAT)
- parent_inode = ceph_get_dentry_parent_inode(file->f_path.dentry);
- err = ceph_mdsc_do_request(mdsc, parent_inode, req);
- iput(parent_inode);
+ err = ceph_mdsc_do_request(mdsc, NULL, req);
if (!err)
err = ceph_init_file(inode, file, req->r_fmode);
ceph_mdsc_put_request(req);
@@ -279,7 +275,7 @@ int ceph_atomic_open(struct inode *dir, struct dentry *dentry,
if (err)
goto out_req;
- if (err == 0 && (flags & O_CREAT) && !req->r_reply_info.head->is_dentry)
+ if ((flags & O_CREAT) && !req->r_reply_info.head->is_dentry)
err = ceph_handle_notrace_create(dir, dentry);
if (d_unhashed(dentry)) {
@@ -956,6 +952,12 @@ static ssize_t ceph_write_iter(struct kiocb *iocb, struct iov_iter *from)
/* We can write back this queue in page reclaim */
current->backing_dev_info = inode_to_bdi(inode);
+ if (iocb->ki_flags & IOCB_APPEND) {
+ err = ceph_do_getattr(inode, CEPH_STAT_CAP_SIZE, false);
+ if (err < 0)
+ goto out;
+ }
+
err = generic_write_checks(iocb, from);
if (err <= 0)
goto out;
diff --git a/fs/ceph/mds_client.c b/fs/ceph/mds_client.c
index 6aa07af67603..51cb02da75d9 100644
--- a/fs/ceph/mds_client.c
+++ b/fs/ceph/mds_client.c
@@ -2107,7 +2107,6 @@ static int __prepare_send_request(struct ceph_mds_client *mdsc,
msg = create_request_message(mdsc, req, mds, drop_cap_releases);
if (IS_ERR(msg)) {
req->r_err = PTR_ERR(msg);
- complete_request(mdsc, req);
return PTR_ERR(msg);
}
req->r_request = msg;
@@ -2135,7 +2134,7 @@ static int __do_request(struct ceph_mds_client *mdsc,
{
struct ceph_mds_session *session = NULL;
int mds = -1;
- int err = -EAGAIN;
+ int err = 0;
if (req->r_err || req->r_got_result) {
if (req->r_aborted)
@@ -2149,6 +2148,11 @@ static int __do_request(struct ceph_mds_client *mdsc,
err = -EIO;
goto finish;
}
+ if (ACCESS_ONCE(mdsc->fsc->mount_state) == CEPH_MOUNT_SHUTDOWN) {
+ dout("do_request forced umount\n");
+ err = -EIO;
+ goto finish;
+ }
put_request_session(req);
@@ -2196,13 +2200,15 @@ static int __do_request(struct ceph_mds_client *mdsc,
out_session:
ceph_put_mds_session(session);
+finish:
+ if (err) {
+ dout("__do_request early error %d\n", err);
+ req->r_err = err;
+ complete_request(mdsc, req);
+ __unregister_request(mdsc, req);
+ }
out:
return err;
-
-finish:
- req->r_err = err;
- complete_request(mdsc, req);
- goto out;
}
/*
@@ -2289,8 +2295,6 @@ int ceph_mdsc_do_request(struct ceph_mds_client *mdsc,
if (req->r_err) {
err = req->r_err;
- __unregister_request(mdsc, req);
- dout("do_request early error %d\n", err);
goto out;
}
@@ -2411,7 +2415,7 @@ static void handle_reply(struct ceph_mds_session *session, struct ceph_msg *msg)
mutex_unlock(&mdsc->mutex);
goto out;
}
- if (req->r_got_safe && !head->safe) {
+ if (req->r_got_safe) {
pr_warn("got unsafe after safe on %llu from mds%d\n",
tid, mds);
mutex_unlock(&mdsc->mutex);
@@ -2520,8 +2524,7 @@ out_err:
if (err) {
req->r_err = err;
} else {
- req->r_reply = msg;
- ceph_msg_get(msg);
+ req->r_reply = ceph_msg_get(msg);
req->r_got_result = true;
}
} else {
@@ -3555,7 +3558,7 @@ void ceph_mdsc_sync(struct ceph_mds_client *mdsc)
{
u64 want_tid, want_flush, want_snap;
- if (mdsc->fsc->mount_state == CEPH_MOUNT_SHUTDOWN)
+ if (ACCESS_ONCE(mdsc->fsc->mount_state) == CEPH_MOUNT_SHUTDOWN)
return;
dout("sync\n");
@@ -3584,7 +3587,7 @@ void ceph_mdsc_sync(struct ceph_mds_client *mdsc)
*/
static bool done_closing_sessions(struct ceph_mds_client *mdsc)
{
- if (mdsc->fsc->mount_state == CEPH_MOUNT_SHUTDOWN)
+ if (ACCESS_ONCE(mdsc->fsc->mount_state) == CEPH_MOUNT_SHUTDOWN)
return true;
return atomic_read(&mdsc->num_sessions) == 0;
}
@@ -3643,6 +3646,34 @@ void ceph_mdsc_close_sessions(struct ceph_mds_client *mdsc)
dout("stopped\n");
}
+void ceph_mdsc_force_umount(struct ceph_mds_client *mdsc)
+{
+ struct ceph_mds_session *session;
+ int mds;
+
+ dout("force umount\n");
+
+ mutex_lock(&mdsc->mutex);
+ for (mds = 0; mds < mdsc->max_sessions; mds++) {
+ session = __ceph_lookup_mds_session(mdsc, mds);
+ if (!session)
+ continue;
+ mutex_unlock(&mdsc->mutex);
+ mutex_lock(&session->s_mutex);
+ __close_session(mdsc, session);
+ if (session->s_state == CEPH_MDS_SESSION_CLOSING) {
+ cleanup_session_requests(mdsc, session);
+ remove_session_caps(session);
+ }
+ mutex_unlock(&session->s_mutex);
+ ceph_put_mds_session(session);
+ mutex_lock(&mdsc->mutex);
+ kick_requests(mdsc, mds);
+ }
+ __wake_requests(mdsc, &mdsc->waiting_for_map);
+ mutex_unlock(&mdsc->mutex);
+}
+
static void ceph_mdsc_stop(struct ceph_mds_client *mdsc)
{
dout("stop\n");
diff --git a/fs/ceph/mds_client.h b/fs/ceph/mds_client.h
index 762757e6cebf..f575eafe2261 100644
--- a/fs/ceph/mds_client.h
+++ b/fs/ceph/mds_client.h
@@ -366,6 +366,7 @@ extern int ceph_send_msg_mds(struct ceph_mds_client *mdsc,
extern int ceph_mdsc_init(struct ceph_fs_client *fsc);
extern void ceph_mdsc_close_sessions(struct ceph_mds_client *mdsc);
+extern void ceph_mdsc_force_umount(struct ceph_mds_client *mdsc);
extern void ceph_mdsc_destroy(struct ceph_fs_client *fsc);
extern void ceph_mdsc_sync(struct ceph_mds_client *mdsc);
diff --git a/fs/ceph/snap.c b/fs/ceph/snap.c
index 233d906aec02..4aa7122a8d38 100644
--- a/fs/ceph/snap.c
+++ b/fs/ceph/snap.c
@@ -338,12 +338,6 @@ static int build_snap_context(struct ceph_snap_realm *realm)
return 0;
}
- if (num == 0 && realm->seq == ceph_empty_snapc->seq) {
- ceph_get_snap_context(ceph_empty_snapc);
- snapc = ceph_empty_snapc;
- goto done;
- }
-
/* alloc new snap context */
err = -ENOMEM;
if (num > (SIZE_MAX - sizeof(*snapc)) / sizeof(u64))
@@ -381,7 +375,6 @@ static int build_snap_context(struct ceph_snap_realm *realm)
realm->ino, realm, snapc, snapc->seq,
(unsigned int) snapc->num_snaps);
-done:
ceph_put_snap_context(realm->cached_context);
realm->cached_context = snapc;
return 0;
diff --git a/fs/ceph/super.c b/fs/ceph/super.c
index 7b6bfcbf801c..f446afada328 100644
--- a/fs/ceph/super.c
+++ b/fs/ceph/super.c
@@ -708,6 +708,7 @@ static void ceph_umount_begin(struct super_block *sb)
if (!fsc)
return;
fsc->mount_state = CEPH_MOUNT_SHUTDOWN;
+ ceph_mdsc_force_umount(fsc->mdsc);
return;
}