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

torvalds · torvalds · commit e013f74b60bb · 2015-09-11T12:33:03.000-07:00
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 -&gt;alloc_msg()
  libceph: use keepalive2 to verify the mon session is alive
  rbd: plug rbd_dev-&gt;header.object_prefix memory leak
  rbd: fix double free on rbd_dev-&gt;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-&gt;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
diff --git a/drivers/block/rbd.c b/drivers/block/rbd.c
@@ -4673,7 +4673,10 @@ static int rbd_dev_v2_header_info(struct rbd_device *rbd_dev)
 	}
 
 	ret = rbd_dev_v2_snap_context(rbd_dev);
-	dout("rbd_dev_v2_snap_context returned %d\n", ret);
+	if (ret && first_time) {
+		kfree(rbd_dev->header.object_prefix);
+		rbd_dev->header.object_prefix = NULL;
+	}
 
 	return ret;
 }
@@ -5154,7 +5157,6 @@ static int rbd_dev_probe_parent(struct rbd_device *rbd_dev)
 out_err:
 	if (parent) {
 		rbd_dev_unparent(rbd_dev);
-		kfree(rbd_dev->header_name);
 		rbd_dev_destroy(parent);
 	} else {
 		rbd_put_client(rbdc);
diff --git 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
@@ -2413,6 +2413,14 @@ static int try_get_cap_refs(struct ceph_inode_info *ci, int need, int want,
 			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
@@ -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
@@ -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 @@ static void handle_reply(struct ceph_mds_session *session, struct ceph_msg *msg)
 		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
@@ -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
@@ -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
@@ -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;
 }
 
diff --git a/include/linux/ceph/libceph.h b/include/linux/ceph/libceph.h
@@ -46,6 +46,7 @@ struct ceph_options {
 	unsigned long mount_timeout;		/* jiffies */
 	unsigned long osd_idle_ttl;		/* jiffies */
 	unsigned long osd_keepalive_timeout;	/* jiffies */
+	unsigned long monc_ping_timeout;	/* jiffies */
 
 	/*
 	 * any type that can't be simply compared or doesn't need need
@@ -66,6 +67,7 @@ struct ceph_options {
 #define CEPH_MOUNT_TIMEOUT_DEFAULT	msecs_to_jiffies(60 * 1000)
 #define CEPH_OSD_KEEPALIVE_DEFAULT	msecs_to_jiffies(5 * 1000)
 #define CEPH_OSD_IDLE_TTL_DEFAULT	msecs_to_jiffies(60 * 1000)
+#define CEPH_MONC_PING_TIMEOUT_DEFAULT	msecs_to_jiffies(30 * 1000)
 
 #define CEPH_MSG_MAX_FRONT_LEN	(16*1024*1024)
 #define CEPH_MSG_MAX_MIDDLE_LEN	(16*1024*1024)
diff --git a/include/linux/ceph/messenger.h b/include/linux/ceph/messenger.h
@@ -248,6 +248,8 @@ struct ceph_connection {
 	int in_base_pos;     /* bytes read */
 	__le64 in_temp_ack;  /* for reading an ack */
 
+	struct timespec last_keepalive_ack;
+
 	struct delayed_work work;	    /* send|recv work */
 	unsigned long       delay;          /* current delay interval */
 };
@@ -285,6 +287,8 @@ extern void ceph_msg_revoke(struct ceph_msg *msg);
 extern void ceph_msg_revoke_incoming(struct ceph_msg *msg);
 
 extern void ceph_con_keepalive(struct ceph_connection *con);
+extern bool ceph_con_keepalive_expired(struct ceph_connection *con,
+				       unsigned long interval);
 
 extern void ceph_msg_data_add_pages(struct ceph_msg *msg, struct page **pages,
 				size_t length, size_t alignment);
diff --git a/include/linux/ceph/msgr.h b/include/linux/ceph/msgr.h
@@ -84,10 +84,12 @@ struct ceph_entity_inst {
 #define CEPH_MSGR_TAG_MSG           7  /* message */
 #define CEPH_MSGR_TAG_ACK           8  /* message ack */
 #define CEPH_MSGR_TAG_KEEPALIVE     9  /* just a keepalive byte! */
-#define CEPH_MSGR_TAG_BADPROTOVER  10  /* bad protocol version */
+#define CEPH_MSGR_TAG_BADPROTOVER   10 /* bad protocol version */
 #define CEPH_MSGR_TAG_BADAUTHORIZER 11 /* bad authorizer */
 #define CEPH_MSGR_TAG_FEATURES      12 /* insufficient features */
 #define CEPH_MSGR_TAG_SEQ           13 /* 64-bit int follows with seen seq number */
+#define CEPH_MSGR_TAG_KEEPALIVE2    14 /* keepalive2 byte + ceph_timespec */
+#define CEPH_MSGR_TAG_KEEPALIVE2_ACK 15 /* keepalive2 reply */
 
 
 /*
diff --git a/net/ceph/ceph_common.c b/net/ceph/ceph_common.c
@@ -357,6 +357,7 @@ ceph_parse_options(char *options, const char *dev_name,
 	opt->osd_keepalive_timeout = CEPH_OSD_KEEPALIVE_DEFAULT;
 	opt->mount_timeout = CEPH_MOUNT_TIMEOUT_DEFAULT;
 	opt->osd_idle_ttl = CEPH_OSD_IDLE_TTL_DEFAULT;
+	opt->monc_ping_timeout = CEPH_MONC_PING_TIMEOUT_DEFAULT;
 
 	/* get mon ip(s) */
 	/* ip1[:port1][,ip2[:port2]...] */
diff --git a/net/ceph/crypto.c b/net/ceph/crypto.c
@@ -79,10 +79,6 @@ int ceph_crypto_key_unarmor(struct ceph_crypto_key *key, const char *inkey)
 	return 0;
 }
 
-
-
-#define AES_KEY_SIZE 16
-
 static struct crypto_blkcipher *ceph_crypto_alloc_cipher(void)
 {
 	return crypto_alloc_blkcipher("cbc(aes)", 0, CRYPTO_ALG_ASYNC);
diff --git a/net/ceph/messenger.c b/net/ceph/messenger.c
diff --git a/net/ceph/mon_client.c b/net/ceph/mon_client.c
diff --git a/net/ceph/osd_client.c b/net/ceph/osd_client.c
diff --git a/net/ceph/osdmap.c b/net/ceph/osdmap.c

Original file line number	Diff line number	Diff line change
`@@ -2413,6 +2413,14 @@ static int try_get_cap_refs(struct ceph_inode_info *ci, int need, int want,`
`2413`	`2413`	`goto out_unlock;`
`2414`	`2414`	`}`
`2415`	`2415`
	`2416`	`+ if (!__ceph_is_any_caps(ci) &&`
	`2417`	`+ ACCESS_ONCE(mdsc->fsc->mount_state) == CEPH_MOUNT_SHUTDOWN) {`
	`2418`	`+ dout("get_cap_refs %p forced umount\n", inode);`
	`2419`	`+ *err = -EIO;`
	`2420`	`+ ret = 1;`
	`2421`	`+ goto out_unlock;`
	`2422`	`+ }`
	`2423`	`+`
`2416`	`2424`	`dout("get_cap_refs %p have %s needed %s\n", inode,`
`2417`	`2425`	`ceph_cap_string(have), ceph_cap_string(need));`
`2418`	`2426`	`}`
Original file line number	Diff line number	Diff line change
`@@ -708,6 +708,7 @@ static void ceph_umount_begin(struct super_block *sb)`
`708`	`708`	`if (!fsc)`
`709`	`709`	`return;`
`710`	`710`	`fsc->mount_state = CEPH_MOUNT_SHUTDOWN;`
	`711`	`+ ceph_mdsc_force_umount(fsc->mdsc);`
`711`	`712`	`return;`
`712`	`713`	`}`
`713`	`714`
Original file line number	Diff line number	Diff line change
`@@ -79,10 +79,6 @@ int ceph_crypto_key_unarmor(struct ceph_crypto_key key, const char inkey)`
`79`	`79`	`return 0;`
`80`	`80`	`}`
`81`	`81`
`82`		`-`
`83`		`-`
`84`		`-#define AES_KEY_SIZE 16`
`85`		`-`
`86`	`82`	`static struct crypto_blkcipher *ceph_crypto_alloc_cipher(void)`
`87`	`83`	`{`
`88`	`84`	`return crypto_alloc_blkcipher("cbc(aes)", 0, CRYPTO_ALG_ASYNC);`