* the sender.
*/
+/* State values for ceph_connection->sock_state; NEW is assumed to be 0 */
+
+#define CON_SOCK_STATE_NEW 0 /* -> CLOSED */
+#define CON_SOCK_STATE_CLOSED 1 /* -> CONNECTING */
+#define CON_SOCK_STATE_CONNECTING 2 /* -> CONNECTED or -> CLOSING */
+#define CON_SOCK_STATE_CONNECTED 3 /* -> CLOSING or -> CLOSED */
+#define CON_SOCK_STATE_CLOSING 4 /* -> CLOSED */
+
/* static tag bytes (protocol control messages) */
static char tag_msg = CEPH_MSGR_TAG_MSG;
static char tag_ack = CEPH_MSGR_TAG_ACK;
}
EXPORT_SYMBOL(ceph_msgr_flush);
+/* Connection socket state transition functions */
+
+static void con_sock_state_init(struct ceph_connection *con)
+{
+ int old_state;
+
+ old_state = atomic_xchg(&con->sock_state, CON_SOCK_STATE_CLOSED);
+ if (WARN_ON(old_state != CON_SOCK_STATE_NEW))
+ printk("%s: unexpected old state %d\n", __func__, old_state);
+}
+
+static void con_sock_state_connecting(struct ceph_connection *con)
+{
+ int old_state;
+
+ old_state = atomic_xchg(&con->sock_state, CON_SOCK_STATE_CONNECTING);
+ if (WARN_ON(old_state != CON_SOCK_STATE_CLOSED))
+ printk("%s: unexpected old state %d\n", __func__, old_state);
+}
+
+static void con_sock_state_connected(struct ceph_connection *con)
+{
+ int old_state;
+
+ old_state = atomic_xchg(&con->sock_state, CON_SOCK_STATE_CONNECTED);
+ if (WARN_ON(old_state != CON_SOCK_STATE_CONNECTING))
+ printk("%s: unexpected old state %d\n", __func__, old_state);
+}
+
+static void con_sock_state_closing(struct ceph_connection *con)
+{
+ int old_state;
+
+ old_state = atomic_xchg(&con->sock_state, CON_SOCK_STATE_CLOSING);
+ if (WARN_ON(old_state != CON_SOCK_STATE_CONNECTING &&
+ old_state != CON_SOCK_STATE_CONNECTED &&
+ old_state != CON_SOCK_STATE_CLOSING))
+ printk("%s: unexpected old state %d\n", __func__, old_state);
+}
+
+static void con_sock_state_closed(struct ceph_connection *con)
+{
+ int old_state;
+
+ old_state = atomic_xchg(&con->sock_state, CON_SOCK_STATE_CLOSED);
+ if (WARN_ON(old_state != CON_SOCK_STATE_CONNECTED &&
+ old_state != CON_SOCK_STATE_CLOSING))
+ printk("%s: unexpected old state %d\n", __func__, old_state);
+}
/*
* socket callback functions
*/
/* data available on socket, or listen socket received a connect */
-static void ceph_data_ready(struct sock *sk, int count_unused)
+static void ceph_sock_data_ready(struct sock *sk, int count_unused)
{
struct ceph_connection *con = sk->sk_user_data;
if (sk->sk_state != TCP_CLOSE_WAIT) {
- dout("ceph_data_ready on %p state = %lu, queueing work\n",
+ dout("%s on %p state = %lu, queueing work\n", __func__,
con, con->state);
queue_con(con);
}
}
/* socket has buffer space for writing */
-static void ceph_write_space(struct sock *sk)
+static void ceph_sock_write_space(struct sock *sk)
{
struct ceph_connection *con = sk->sk_user_data;
/* only queue to workqueue if there is data we want to write,
* and there is sufficient space in the socket buffer to accept
- * more data. clear SOCK_NOSPACE so that ceph_write_space()
+ * more data. clear SOCK_NOSPACE so that ceph_sock_write_space()
* doesn't get called again until try_write() fills the socket
* buffer. See net/ipv4/tcp_input.c:tcp_check_space()
* and net/core/stream.c:sk_stream_write_space().
*/
- if (test_bit(WRITE_PENDING, &con->state)) {
+ if (test_bit(WRITE_PENDING, &con->flags)) {
if (sk_stream_wspace(sk) >= sk_stream_min_wspace(sk)) {
- dout("ceph_write_space %p queueing write work\n", con);
+ dout("%s %p queueing write work\n", __func__, con);
clear_bit(SOCK_NOSPACE, &sk->sk_socket->flags);
queue_con(con);
}
} else {
- dout("ceph_write_space %p nothing to write\n", con);
+ dout("%s %p nothing to write\n", __func__, con);
}
}
/* socket's state has changed */
-static void ceph_state_change(struct sock *sk)
+static void ceph_sock_state_change(struct sock *sk)
{
struct ceph_connection *con = sk->sk_user_data;
- dout("ceph_state_change %p state = %lu sk_state = %u\n",
+ dout("%s %p state = %lu sk_state = %u\n", __func__,
con, con->state, sk->sk_state);
if (test_bit(CLOSED, &con->state))
switch (sk->sk_state) {
case TCP_CLOSE:
- dout("ceph_state_change TCP_CLOSE\n");
+ dout("%s TCP_CLOSE\n", __func__);
case TCP_CLOSE_WAIT:
- dout("ceph_state_change TCP_CLOSE_WAIT\n");
- if (test_and_set_bit(SOCK_CLOSED, &con->state) == 0) {
+ dout("%s TCP_CLOSE_WAIT\n", __func__);
+ con_sock_state_closing(con);
+ if (test_and_set_bit(SOCK_CLOSED, &con->flags) == 0) {
if (test_bit(CONNECTING, &con->state))
con->error_msg = "connection failed";
else
}
break;
case TCP_ESTABLISHED:
- dout("ceph_state_change TCP_ESTABLISHED\n");
+ dout("%s TCP_ESTABLISHED\n", __func__);
+ con_sock_state_connected(con);
queue_con(con);
break;
default: /* Everything else is uninteresting */
{
struct sock *sk = sock->sk;
sk->sk_user_data = con;
- sk->sk_data_ready = ceph_data_ready;
- sk->sk_write_space = ceph_write_space;
- sk->sk_state_change = ceph_state_change;
+ sk->sk_data_ready = ceph_sock_data_ready;
+ sk->sk_write_space = ceph_sock_write_space;
+ sk->sk_state_change = ceph_sock_state_change;
}
dout("connect %s\n", ceph_pr_addr(&con->peer_addr.in_addr));
+ con_sock_state_connecting(con);
ret = sock->ops->connect(sock, (struct sockaddr *)paddr, sizeof(*paddr),
O_NONBLOCK);
if (ret == -EINPROGRESS) {
return ret;
}
con->sock = sock;
-
return 0;
}
sock_release(con->sock);
con->sock = NULL;
clear_bit(SOCK_CLOSED, &con->state);
+ con_sock_state_closed(con);
return rc;
}
static void ceph_msg_remove(struct ceph_msg *msg)
{
list_del_init(&msg->list_head);
+ BUG_ON(msg->con == NULL);
+ msg->con->ops->put(msg->con);
+ msg->con = NULL;
+
ceph_msg_put(msg);
}
static void ceph_msg_remove_list(struct list_head *head)
ceph_msg_remove_list(&con->out_sent);
if (con->in_msg) {
+ BUG_ON(con->in_msg->con != con);
+ con->in_msg->con = NULL;
ceph_msg_put(con->in_msg);
con->in_msg = NULL;
+ con->ops->put(con);
}
con->connect_seq = 0;
{
dout("con_close %p peer %s\n", con,
ceph_pr_addr(&con->peer_addr.in_addr));
- set_bit(CLOSED, &con->state); /* in case there's queued work */
+ clear_bit(NEGOTIATING, &con->state);
clear_bit(STANDBY, &con->state); /* avoid connect_seq bump */
- clear_bit(LOSSYTX, &con->state); /* so we retry next connect */
- clear_bit(KEEPALIVE_PENDING, &con->state);
- clear_bit(WRITE_PENDING, &con->state);
+ set_bit(CLOSED, &con->state);
+
+ clear_bit(LOSSYTX, &con->flags); /* so we retry next connect */
+ clear_bit(KEEPALIVE_PENDING, &con->flags);
+ clear_bit(WRITE_PENDING, &con->flags);
+
mutex_lock(&con->mutex);
reset_connection(con);
con->peer_global_seq = 0;
{
dout("con_open %p %s\n", con, ceph_pr_addr(&addr->in_addr));
set_bit(OPENING, &con->state);
- clear_bit(CLOSED, &con->state);
+ WARN_ON(!test_and_clear_bit(CLOSED, &con->state));
+
memcpy(&con->peer_addr, addr, sizeof(*addr));
con->delay = 0; /* reset backoff memory */
queue_con(con);
return con->connect_seq > 0;
}
-/*
- * generic get/put
- */
-struct ceph_connection *ceph_con_get(struct ceph_connection *con)
-{
- int nref = __atomic_add_unless(&con->nref, 1, 0);
-
- dout("con_get %p nref = %d -> %d\n", con, nref, nref + 1);
-
- return nref ? con : NULL;
-}
-
-void ceph_con_put(struct ceph_connection *con)
-{
- int nref = atomic_dec_return(&con->nref);
-
- BUG_ON(nref < 0);
- if (nref == 0) {
- BUG_ON(con->sock);
- kfree(con);
- }
- dout("con_put %p nref = %d -> %d\n", con, nref + 1, nref);
-}
-
/*
* initialize a new connection.
*/
-void ceph_con_init(struct ceph_messenger *msgr, struct ceph_connection *con)
+void ceph_con_init(struct ceph_connection *con, void *private,
+ const struct ceph_connection_operations *ops,
+ struct ceph_messenger *msgr, __u8 entity_type, __u64 entity_num)
{
dout("con_init %p\n", con);
memset(con, 0, sizeof(*con));
- atomic_set(&con->nref, 1);
+ con->private = private;
+ con->ops = ops;
con->msgr = msgr;
+
+ con_sock_state_init(con);
+
+ con->peer_name.type = (__u8) entity_type;
+ con->peer_name.num = cpu_to_le64(entity_num);
+
mutex_init(&con->mutex);
INIT_LIST_HEAD(&con->out_queue);
INIT_LIST_HEAD(&con->out_sent);
INIT_DELAYED_WORK(&con->work, con_work);
+
+ set_bit(CLOSED, &con->state);
}
EXPORT_SYMBOL(ceph_con_init);
return ret;
}
-static void ceph_con_out_kvec_reset(struct ceph_connection *con)
+static void con_out_kvec_reset(struct ceph_connection *con)
{
con->out_kvec_left = 0;
con->out_kvec_bytes = 0;
con->out_kvec_cur = &con->out_kvec[0];
}
-static void ceph_con_out_kvec_add(struct ceph_connection *con,
+static void con_out_kvec_add(struct ceph_connection *con,
size_t size, void *data)
{
int index;
con->out_kvec_bytes += size;
}
+static void prepare_write_message_data(struct ceph_connection *con)
+{
+ struct ceph_msg *msg = con->out_msg;
+
+ BUG_ON(!msg);
+ BUG_ON(!msg->hdr.data_len);
+
+ /* initialize page iterator */
+ con->out_msg_pos.page = 0;
+ if (msg->pages)
+ con->out_msg_pos.page_pos = msg->page_alignment;
+ else
+ con->out_msg_pos.page_pos = 0;
+ con->out_msg_pos.data_pos = 0;
+ con->out_msg_pos.did_page_crc = false;
+ con->out_more = 1; /* data + footer will follow */
+}
+
/*
* Prepare footer for currently outgoing message, and finish things
* off. Assumes out_kvec* are already valid.. we just add on to the end.
struct ceph_msg *m = con->out_msg;
int v = con->out_kvec_left;
+ m->footer.flags |= CEPH_MSG_FOOTER_COMPLETE;
+
dout("prepare_write_message_footer %p\n", con);
con->out_kvec_is_msg = true;
con->out_kvec[v].iov_base = &m->footer;
struct ceph_msg *m;
u32 crc;
- ceph_con_out_kvec_reset(con);
+ con_out_kvec_reset(con);
con->out_kvec_is_msg = true;
con->out_msg_done = false;
* TCP packet that's a good thing. */
if (con->in_seq > con->in_seq_acked) {
con->in_seq_acked = con->in_seq;
- ceph_con_out_kvec_add(con, sizeof (tag_ack), &tag_ack);
+ con_out_kvec_add(con, sizeof (tag_ack), &tag_ack);
con->out_temp_ack = cpu_to_le64(con->in_seq_acked);
- ceph_con_out_kvec_add(con, sizeof (con->out_temp_ack),
+ con_out_kvec_add(con, sizeof (con->out_temp_ack),
&con->out_temp_ack);
}
+ BUG_ON(list_empty(&con->out_queue));
m = list_first_entry(&con->out_queue, struct ceph_msg, list_head);
con->out_msg = m;
+ BUG_ON(m->con != con);
/* put message on sent list */
ceph_msg_get(m);
m->hdr.seq = cpu_to_le64(++con->out_seq);
m->needs_out_seq = false;
}
+#ifdef CONFIG_BLOCK
+ else
+ m->bio_iter = NULL;
+#endif
dout("prepare_write_message %p seq %lld type %d len %d+%d+%d %d pgs\n",
m, con->out_seq, le16_to_cpu(m->hdr.type),
BUG_ON(le32_to_cpu(m->hdr.front_len) != m->front.iov_len);
/* tag + hdr + front + middle */
- ceph_con_out_kvec_add(con, sizeof (tag_msg), &tag_msg);
- ceph_con_out_kvec_add(con, sizeof (m->hdr), &m->hdr);
- ceph_con_out_kvec_add(con, m->front.iov_len, m->front.iov_base);
+ con_out_kvec_add(con, sizeof (tag_msg), &tag_msg);
+ con_out_kvec_add(con, sizeof (m->hdr), &m->hdr);
+ con_out_kvec_add(con, m->front.iov_len, m->front.iov_base);
if (m->middle)
- ceph_con_out_kvec_add(con, m->middle->vec.iov_len,
+ con_out_kvec_add(con, m->middle->vec.iov_len,
m->middle->vec.iov_base);
/* fill in crc (except data pages), footer */
crc = crc32c(0, &m->hdr, offsetof(struct ceph_msg_header, crc));
con->out_msg->hdr.crc = cpu_to_le32(crc);
- con->out_msg->footer.flags = CEPH_MSG_FOOTER_COMPLETE;
+ con->out_msg->footer.flags = 0;
crc = crc32c(0, m->front.iov_base, m->front.iov_len);
con->out_msg->footer.front_crc = cpu_to_le32(crc);
con->out_msg->footer.middle_crc = cpu_to_le32(crc);
} else
con->out_msg->footer.middle_crc = 0;
- con->out_msg->footer.data_crc = 0;
- dout("prepare_write_message front_crc %u data_crc %u\n",
+ dout("%s front_crc %u middle_crc %u\n", __func__,
le32_to_cpu(con->out_msg->footer.front_crc),
le32_to_cpu(con->out_msg->footer.middle_crc));
/* is there a data payload? */
- if (le32_to_cpu(m->hdr.data_len) > 0) {
- /* initialize page iterator */
- con->out_msg_pos.page = 0;
- if (m->pages)
- con->out_msg_pos.page_pos = m->page_alignment;
- else
- con->out_msg_pos.page_pos = 0;
- con->out_msg_pos.data_pos = 0;
- con->out_msg_pos.did_page_crc = false;
- con->out_more = 1; /* data + footer will follow */
- } else {
+ con->out_msg->footer.data_crc = 0;
+ if (m->hdr.data_len)
+ prepare_write_message_data(con);
+ else
/* no, queue up footer too and be done */
prepare_write_message_footer(con);
- }
- set_bit(WRITE_PENDING, &con->state);
+ set_bit(WRITE_PENDING, &con->flags);
}
/*
con->in_seq_acked, con->in_seq);
con->in_seq_acked = con->in_seq;
- ceph_con_out_kvec_reset(con);
+ con_out_kvec_reset(con);
- ceph_con_out_kvec_add(con, sizeof (tag_ack), &tag_ack);
+ con_out_kvec_add(con, sizeof (tag_ack), &tag_ack);
con->out_temp_ack = cpu_to_le64(con->in_seq_acked);
- ceph_con_out_kvec_add(con, sizeof (con->out_temp_ack),
+ con_out_kvec_add(con, sizeof (con->out_temp_ack),
&con->out_temp_ack);
con->out_more = 1; /* more will follow.. eventually.. */
- set_bit(WRITE_PENDING, &con->state);
+ set_bit(WRITE_PENDING, &con->flags);
}
/*
static void prepare_write_keepalive(struct ceph_connection *con)
{
dout("prepare_write_keepalive %p\n", con);
- ceph_con_out_kvec_reset(con);
- ceph_con_out_kvec_add(con, sizeof (tag_keepalive), &tag_keepalive);
- set_bit(WRITE_PENDING, &con->state);
+ con_out_kvec_reset(con);
+ con_out_kvec_add(con, sizeof (tag_keepalive), &tag_keepalive);
+ set_bit(WRITE_PENDING, &con->flags);
}
/*
* Connection negotiation.
*/
-static int prepare_connect_authorizer(struct ceph_connection *con)
+static struct ceph_auth_handshake *get_connect_authorizer(struct ceph_connection *con,
+ int *auth_proto)
{
- void *auth_buf;
- int auth_len = 0;
- int auth_protocol = 0;
+ struct ceph_auth_handshake *auth;
+
+ if (!con->ops->get_authorizer) {
+ con->out_connect.authorizer_protocol = CEPH_AUTH_UNKNOWN;
+ con->out_connect.authorizer_len = 0;
+
+ return NULL;
+ }
+
+ /* Can't hold the mutex while getting authorizer */
mutex_unlock(&con->mutex);
- if (con->ops->get_authorizer)
- con->ops->get_authorizer(con, &auth_buf, &auth_len,
- &auth_protocol, &con->auth_reply_buf,
- &con->auth_reply_buf_len,
- con->auth_retry);
+
+ auth = con->ops->get_authorizer(con, auth_proto, con->auth_retry);
+
mutex_lock(&con->mutex);
- if (test_bit(CLOSED, &con->state) ||
- test_bit(OPENING, &con->state))
- return -EAGAIN;
+ if (IS_ERR(auth))
+ return auth;
+ if (test_bit(CLOSED, &con->state) || test_bit(OPENING, &con->flags))
+ return ERR_PTR(-EAGAIN);
- con->out_connect.authorizer_protocol = cpu_to_le32(auth_protocol);
- con->out_connect.authorizer_len = cpu_to_le32(auth_len);
+ con->auth_reply_buf = auth->authorizer_reply_buf;
+ con->auth_reply_buf_len = auth->authorizer_reply_buf_len;
- if (auth_len)
- ceph_con_out_kvec_add(con, auth_len, auth_buf);
- return 0;
+ return auth;
}
/*
* We connected to a peer and are saying hello.
*/
-static void prepare_write_banner(struct ceph_messenger *msgr,
- struct ceph_connection *con)
+static void prepare_write_banner(struct ceph_connection *con)
{
- ceph_con_out_kvec_reset(con);
- ceph_con_out_kvec_add(con, strlen(CEPH_BANNER), CEPH_BANNER);
- ceph_con_out_kvec_add(con, sizeof (msgr->my_enc_addr),
- &msgr->my_enc_addr);
+ con_out_kvec_add(con, strlen(CEPH_BANNER), CEPH_BANNER);
+ con_out_kvec_add(con, sizeof (con->msgr->my_enc_addr),
+ &con->msgr->my_enc_addr);
con->out_more = 0;
- set_bit(WRITE_PENDING, &con->state);
+ set_bit(WRITE_PENDING, &con->flags);
}
-static int prepare_write_connect(struct ceph_messenger *msgr,
- struct ceph_connection *con,
- int include_banner)
+static int prepare_write_connect(struct ceph_connection *con)
{
unsigned int global_seq = get_global_seq(con->msgr, 0);
int proto;
+ int auth_proto;
+ struct ceph_auth_handshake *auth;
switch (con->peer_name.type) {
case CEPH_ENTITY_TYPE_MON:
dout("prepare_write_connect %p cseq=%d gseq=%d proto=%d\n", con,
con->connect_seq, global_seq, proto);
- con->out_connect.features = cpu_to_le64(msgr->supported_features);
+ con->out_connect.features = cpu_to_le64(con->msgr->supported_features);
con->out_connect.host_type = cpu_to_le32(CEPH_ENTITY_TYPE_CLIENT);
con->out_connect.connect_seq = cpu_to_le32(con->connect_seq);
con->out_connect.global_seq = cpu_to_le32(global_seq);
con->out_connect.protocol_version = cpu_to_le32(proto);
con->out_connect.flags = 0;
- if (include_banner)
- prepare_write_banner(msgr, con);
- else
- ceph_con_out_kvec_reset(con);
- ceph_con_out_kvec_add(con, sizeof (con->out_connect), &con->out_connect);
+ auth_proto = CEPH_AUTH_UNKNOWN;
+ auth = get_connect_authorizer(con, &auth_proto);
+ if (IS_ERR(auth))
+ return PTR_ERR(auth);
+
+ con->out_connect.authorizer_protocol = cpu_to_le32(auth_proto);
+ con->out_connect.authorizer_len = auth ?
+ cpu_to_le32(auth->authorizer_buf_len) : 0;
+
+ con_out_kvec_add(con, sizeof (con->out_connect),
+ &con->out_connect);
+ if (auth && auth->authorizer_buf_len)
+ con_out_kvec_add(con, auth->authorizer_buf_len,
+ auth->authorizer_buf);
con->out_more = 0;
- set_bit(WRITE_PENDING, &con->state);
+ set_bit(WRITE_PENDING, &con->flags);
- return prepare_connect_authorizer(con);
+ return 0;
}
/*
}
#endif
+static void out_msg_pos_next(struct ceph_connection *con, struct page *page,
+ size_t len, size_t sent, bool in_trail)
+{
+ struct ceph_msg *msg = con->out_msg;
+
+ BUG_ON(!msg);
+ BUG_ON(!sent);
+
+ con->out_msg_pos.data_pos += sent;
+ con->out_msg_pos.page_pos += sent;
+ if (sent == len) {
+ con->out_msg_pos.page_pos = 0;
+ con->out_msg_pos.page++;
+ con->out_msg_pos.did_page_crc = false;
+ if (in_trail)
+ list_move_tail(&page->lru,
+ &msg->trail->head);
+ else if (msg->pagelist)
+ list_move_tail(&page->lru,
+ &msg->pagelist->head);
+#ifdef CONFIG_BLOCK
+ else if (msg->bio)
+ iter_bio_next(&msg->bio_iter, &msg->bio_seg);
+#endif
+ }
+}
+
/*
* Write as much message data payload as we can. If we finish, queue
* up the footer.
bool do_datacrc = !con->msgr->nocrc;
int ret;
int total_max_write;
- int in_trail = 0;
+ bool in_trail = false;
size_t trail_len = (msg->trail ? msg->trail->length : 0);
dout("write_partial_msg_pages %p msg %p page %d/%d offset %d\n",
- con, con->out_msg, con->out_msg_pos.page, con->out_msg->nr_pages,
+ con, msg, con->out_msg_pos.page, msg->nr_pages,
con->out_msg_pos.page_pos);
#ifdef CONFIG_BLOCK
/* have we reached the trail part of the data? */
if (con->out_msg_pos.data_pos >= data_len - trail_len) {
- in_trail = 1;
+ in_trail = true;
total_max_write = data_len - con->out_msg_pos.data_pos;
page = list_first_entry(&msg->trail->head,
struct page, lru);
- max_write = PAGE_SIZE;
} else if (msg->pages) {
page = msg->pages[con->out_msg_pos.page];
} else if (msg->pagelist) {
if (do_datacrc && !con->out_msg_pos.did_page_crc) {
void *base;
u32 crc;
- u32 tmpcrc = le32_to_cpu(con->out_msg->footer.data_crc);
+ u32 tmpcrc = le32_to_cpu(msg->footer.data_crc);
char *kaddr;
kaddr = kmap(page);
BUG_ON(kaddr == NULL);
base = kaddr + con->out_msg_pos.page_pos + bio_offset;
crc = crc32c(tmpcrc, base, len);
- con->out_msg->footer.data_crc = cpu_to_le32(crc);
+ msg->footer.data_crc = cpu_to_le32(crc);
con->out_msg_pos.did_page_crc = true;
}
ret = ceph_tcp_sendpage(con->sock, page,
if (ret <= 0)
goto out;
- con->out_msg_pos.data_pos += ret;
- con->out_msg_pos.page_pos += ret;
- if (ret == len) {
- con->out_msg_pos.page_pos = 0;
- con->out_msg_pos.page++;
- con->out_msg_pos.did_page_crc = false;
- if (in_trail)
- list_move_tail(&page->lru,
- &msg->trail->head);
- else if (msg->pagelist)
- list_move_tail(&page->lru,
- &msg->pagelist->head);
-#ifdef CONFIG_BLOCK
- else if (msg->bio)
- iter_bio_next(&msg->bio_iter, &msg->bio_seg);
-#endif
- }
+ out_msg_pos_next(con, page, len, (size_t) ret, in_trail);
}
dout("write_partial_msg_pages %p msg %p done\n", con, msg);
/* prepare and queue up footer, too */
if (!do_datacrc)
- con->out_msg->footer.flags |= CEPH_MSG_FOOTER_NOCRC;
- ceph_con_out_kvec_reset(con);
+ msg->footer.flags |= CEPH_MSG_FOOTER_NOCRC;
+ con_out_kvec_reset(con);
prepare_write_message_footer(con);
ret = 1;
out:
static int read_partial(struct ceph_connection *con,
- int *to, int size, void *object)
+ int end, int size, void *object)
{
- *to += size;
- while (con->in_base_pos < *to) {
- int left = *to - con->in_base_pos;
+ while (con->in_base_pos < end) {
+ int left = end - con->in_base_pos;
int have = size - left;
int ret = ceph_tcp_recvmsg(con->sock, object + have, left);
if (ret <= 0)
*/
static int read_partial_banner(struct ceph_connection *con)
{
- int ret, to = 0;
+ int size;
+ int end;
+ int ret;
dout("read_partial_banner %p at %d\n", con, con->in_base_pos);
/* peer's banner */
- ret = read_partial(con, &to, strlen(CEPH_BANNER), con->in_banner);
+ size = strlen(CEPH_BANNER);
+ end = size;
+ ret = read_partial(con, end, size, con->in_banner);
if (ret <= 0)
goto out;
- ret = read_partial(con, &to, sizeof(con->actual_peer_addr),
- &con->actual_peer_addr);
+
+ size = sizeof (con->actual_peer_addr);
+ end += size;
+ ret = read_partial(con, end, size, &con->actual_peer_addr);
if (ret <= 0)
goto out;
- ret = read_partial(con, &to, sizeof(con->peer_addr_for_me),
- &con->peer_addr_for_me);
+
+ size = sizeof (con->peer_addr_for_me);
+ end += size;
+ ret = read_partial(con, end, size, &con->peer_addr_for_me);
if (ret <= 0)
goto out;
+
out:
return ret;
}
static int read_partial_connect(struct ceph_connection *con)
{
- int ret, to = 0;
+ int size;
+ int end;
+ int ret;
dout("read_partial_connect %p at %d\n", con, con->in_base_pos);
- ret = read_partial(con, &to, sizeof(con->in_reply), &con->in_reply);
+ size = sizeof (con->in_reply);
+ end = size;
+ ret = read_partial(con, end, size, &con->in_reply);
if (ret <= 0)
goto out;
- ret = read_partial(con, &to, le32_to_cpu(con->in_reply.authorizer_len),
- con->auth_reply_buf);
+
+ size = le32_to_cpu(con->in_reply.authorizer_len);
+ end += size;
+ ret = read_partial(con, end, size, con->auth_reply_buf);
if (ret <= 0)
goto out;
{
reset_connection(con);
set_bit(CLOSED, &con->state); /* in case there's queued work */
-
- mutex_unlock(&con->mutex);
- if (con->ops->bad_proto)
- con->ops->bad_proto(con);
- mutex_lock(&con->mutex);
}
static int process_connect(struct ceph_connection *con)
return -1;
}
con->auth_retry = 1;
- ret = prepare_write_connect(con->msgr, con, 0);
+ con_out_kvec_reset(con);
+ ret = prepare_write_connect(con);
if (ret < 0)
return ret;
prepare_read_connect(con);
ENTITY_NAME(con->peer_name),
ceph_pr_addr(&con->peer_addr.in_addr));
reset_connection(con);
- prepare_write_connect(con->msgr, con, 0);
+ con_out_kvec_reset(con);
+ ret = prepare_write_connect(con);
+ if (ret < 0)
+ return ret;
prepare_read_connect(con);
/* Tell ceph about it. */
le32_to_cpu(con->out_connect.connect_seq),
le32_to_cpu(con->in_connect.connect_seq));
con->connect_seq = le32_to_cpu(con->in_connect.connect_seq);
- prepare_write_connect(con->msgr, con, 0);
+ con_out_kvec_reset(con);
+ ret = prepare_write_connect(con);
+ if (ret < 0)
+ return ret;
prepare_read_connect(con);
break;
le32_to_cpu(con->in_connect.global_seq));
get_global_seq(con->msgr,
le32_to_cpu(con->in_connect.global_seq));
- prepare_write_connect(con->msgr, con, 0);
+ con_out_kvec_reset(con);
+ ret = prepare_write_connect(con);
+ if (ret < 0)
+ return ret;
prepare_read_connect(con);
break;
le32_to_cpu(con->in_reply.connect_seq));
if (con->in_reply.flags & CEPH_MSG_CONNECT_LOSSY)
- set_bit(LOSSYTX, &con->state);
+ set_bit(LOSSYTX, &con->flags);
prepare_read_tag(con);
break;
*/
static int read_partial_ack(struct ceph_connection *con)
{
- int to = 0;
+ int size = sizeof (con->in_temp_ack);
+ int end = size;
- return read_partial(con, &to, sizeof(con->in_temp_ack),
- &con->in_temp_ack);
+ return read_partial(con, end, size, &con->in_temp_ack);
}
return 1;
}
-static struct ceph_msg *ceph_alloc_msg(struct ceph_connection *con,
- struct ceph_msg_header *hdr,
- int *skip);
+static bool ceph_con_in_msg_alloc(struct ceph_connection *con,
+ struct ceph_msg_header *hdr);
static int read_partial_message_pages(struct ceph_connection *con,
static int read_partial_message(struct ceph_connection *con)
{
struct ceph_msg *m = con->in_msg;
+ int size;
+ int end;
int ret;
- int to, left;
unsigned int front_len, middle_len, data_len;
bool do_datacrc = !con->msgr->nocrc;
- int skip;
u64 seq;
u32 crc;
dout("read_partial_message con %p msg %p\n", con, m);
/* header */
- while (con->in_base_pos < sizeof(con->in_hdr)) {
- left = sizeof(con->in_hdr) - con->in_base_pos;
- ret = ceph_tcp_recvmsg(con->sock,
- (char *)&con->in_hdr + con->in_base_pos,
- left);
- if (ret <= 0)
- return ret;
- con->in_base_pos += ret;
- }
+ size = sizeof (con->in_hdr);
+ end = size;
+ ret = read_partial(con, end, size, &con->in_hdr);
+ if (ret <= 0)
+ return ret;
crc = crc32c(0, &con->in_hdr, offsetof(struct ceph_msg_header, crc));
if (cpu_to_le32(crc) != con->in_hdr.crc) {
if (!con->in_msg) {
dout("got hdr type %d front %d data %d\n", con->in_hdr.type,
con->in_hdr.front_len, con->in_hdr.data_len);
- skip = 0;
- con->in_msg = ceph_alloc_msg(con, &con->in_hdr, &skip);
- if (skip) {
+ if (ceph_con_in_msg_alloc(con, &con->in_hdr)) {
/* skip this message */
dout("alloc_msg said skip message\n");
BUG_ON(con->in_msg);
"error allocating memory for incoming message";
return -ENOMEM;
}
+
+ BUG_ON(con->in_msg->con != con);
m = con->in_msg;
m->front.iov_len = 0; /* haven't read it yet */
if (m->middle)
}
/* footer */
- to = sizeof(m->hdr) + sizeof(m->footer);
- while (con->in_base_pos < to) {
- left = to - con->in_base_pos;
- ret = ceph_tcp_recvmsg(con->sock, (char *)&m->footer +
- (con->in_base_pos - sizeof(m->hdr)),
- left);
- if (ret <= 0)
- return ret;
- con->in_base_pos += ret;
- }
+ size = sizeof (m->footer);
+ end += size;
+ ret = read_partial(con, end, size, &m->footer);
+ if (ret <= 0)
+ return ret;
+
dout("read_partial_message got msg %p %d (%u) + %d (%u) + %d (%u)\n",
m, front_len, m->footer.front_crc, middle_len,
m->footer.middle_crc, data_len, m->footer.data_crc);
{
struct ceph_msg *msg;
+ BUG_ON(con->in_msg->con != con);
+ con->in_msg->con = NULL;
msg = con->in_msg;
con->in_msg = NULL;
+ con->ops->put(con);
/* if first message, set peer_name */
if (con->peer_name.type == 0)
*/
static int try_write(struct ceph_connection *con)
{
- struct ceph_messenger *msgr = con->msgr;
int ret = 1;
- dout("try_write start %p state %lu nref %d\n", con, con->state,
- atomic_read(&con->nref));
+ dout("try_write start %p state %lu\n", con, con->state);
more:
dout("try_write out_kvec_bytes %d\n", con->out_kvec_bytes);
/* open the socket first? */
if (con->sock == NULL) {
- prepare_write_connect(msgr, con, 1);
- prepare_read_banner(con);
- set_bit(CONNECTING, &con->state);
clear_bit(NEGOTIATING, &con->state);
+ set_bit(CONNECTING, &con->state);
+
+ con_out_kvec_reset(con);
+ prepare_write_banner(con);
+ ret = prepare_write_connect(con);
+ if (ret < 0)
+ goto out;
+ prepare_read_banner(con);
BUG_ON(con->in_msg);
con->in_tag = CEPH_MSGR_TAG_READY;
prepare_write_ack(con);
goto more;
}
- if (test_and_clear_bit(KEEPALIVE_PENDING, &con->state)) {
+ if (test_and_clear_bit(KEEPALIVE_PENDING, &con->flags)) {
prepare_write_keepalive(con);
goto more;
}
}
/* Nothing to do! */
- clear_bit(WRITE_PENDING, &con->state);
+ clear_bit(WRITE_PENDING, &con->flags);
dout("try_write nothing else to write.\n");
ret = 0;
out:
*/
static void queue_con(struct ceph_connection *con)
{
- if (test_bit(DEAD, &con->state)) {
- dout("queue_con %p ignoring: DEAD\n",
- con);
- return;
- }
-
if (!con->ops->get(con)) {
dout("queue_con %p ref count 0\n", con);
return;
mutex_lock(&con->mutex);
restart:
- if (test_and_clear_bit(BACKOFF, &con->state)) {
+ if (test_and_clear_bit(BACKOFF, &con->flags)) {
dout("con_work %p backing off\n", con);
if (queue_delayed_work(ceph_msgr_wq, &con->work,
round_jiffies_relative(con->delay))) {
con_close_socket(con);
}
- if (test_and_clear_bit(SOCK_CLOSED, &con->state))
+ if (test_and_clear_bit(SOCK_CLOSED, &con->flags))
goto fault;
ret = try_read(con);
dout("fault %p state %lu to peer %s\n",
con, con->state, ceph_pr_addr(&con->peer_addr.in_addr));
- if (test_bit(LOSSYTX, &con->state)) {
+ if (test_bit(LOSSYTX, &con->flags)) {
dout("fault on LOSSYTX channel\n");
goto out;
}
con_close_socket(con);
if (con->in_msg) {
+ BUG_ON(con->in_msg->con != con);
+ con->in_msg->con = NULL;
ceph_msg_put(con->in_msg);
con->in_msg = NULL;
+ con->ops->put(con);
}
/* Requeue anything that hasn't been acked */
/* If there are no messages queued or keepalive pending, place
* the connection in a STANDBY state */
if (list_empty(&con->out_queue) &&
- !test_bit(KEEPALIVE_PENDING, &con->state)) {
+ !test_bit(KEEPALIVE_PENDING, &con->flags)) {
dout("fault %p setting STANDBY clearing WRITE_PENDING\n", con);
- clear_bit(WRITE_PENDING, &con->state);
+ clear_bit(WRITE_PENDING, &con->flags);
set_bit(STANDBY, &con->state);
} else {
/* retry after a delay. */
* that when con_work restarts we schedule the
* delay then.
*/
- set_bit(BACKOFF, &con->state);
+ set_bit(BACKOFF, &con->flags);
}
}
/*
- * create a new messenger instance
+ * initialize a new messenger instance
*/
-struct ceph_messenger *ceph_messenger_create(struct ceph_entity_addr *myaddr,
- u32 supported_features,
- u32 required_features)
+void ceph_messenger_init(struct ceph_messenger *msgr,
+ struct ceph_entity_addr *myaddr,
+ u32 supported_features,
+ u32 required_features,
+ bool nocrc)
{
- struct ceph_messenger *msgr;
-
- msgr = kzalloc(sizeof(*msgr), GFP_KERNEL);
- if (msgr == NULL)
- return ERR_PTR(-ENOMEM);
-
msgr->supported_features = supported_features;
msgr->required_features = required_features;
msgr->inst.addr.type = 0;
get_random_bytes(&msgr->inst.addr.nonce, sizeof(msgr->inst.addr.nonce));
encode_my_addr(msgr);
+ msgr->nocrc = nocrc;
- dout("messenger_create %p\n", msgr);
- return msgr;
-}
-EXPORT_SYMBOL(ceph_messenger_create);
-
-void ceph_messenger_destroy(struct ceph_messenger *msgr)
-{
- dout("destroy %p\n", msgr);
- kfree(msgr);
- dout("destroyed messenger %p\n", msgr);
+ dout("%s %p\n", __func__, msgr);
}
-EXPORT_SYMBOL(ceph_messenger_destroy);
+EXPORT_SYMBOL(ceph_messenger_init);
static void clear_standby(struct ceph_connection *con)
{
mutex_lock(&con->mutex);
dout("clear_standby %p and ++connect_seq\n", con);
con->connect_seq++;
- WARN_ON(test_bit(WRITE_PENDING, &con->state));
- WARN_ON(test_bit(KEEPALIVE_PENDING, &con->state));
+ WARN_ON(test_bit(WRITE_PENDING, &con->flags));
+ WARN_ON(test_bit(KEEPALIVE_PENDING, &con->flags));
mutex_unlock(&con->mutex);
}
}
/* queue */
mutex_lock(&con->mutex);
+
+ BUG_ON(msg->con != NULL);
+ msg->con = con->ops->get(con);
+ BUG_ON(msg->con == NULL);
+
BUG_ON(!list_empty(&msg->list_head));
list_add_tail(&msg->list_head, &con->out_queue);
dout("----- %p to %s%lld %d=%s len %d+%d+%d -----\n", msg,
/* if there wasn't anything waiting to send before, queue
* new work */
clear_standby(con);
- if (test_and_set_bit(WRITE_PENDING, &con->state) == 0)
+ if (test_and_set_bit(WRITE_PENDING, &con->flags) == 0)
queue_con(con);
}
EXPORT_SYMBOL(ceph_con_send);
/*
* Revoke a message that was previously queued for send
*/
-void ceph_con_revoke(struct ceph_connection *con, struct ceph_msg *msg)
+void ceph_msg_revoke(struct ceph_msg *msg)
{
+ struct ceph_connection *con = msg->con;
+
+ if (!con)
+ return; /* Message not in our possession */
+
mutex_lock(&con->mutex);
if (!list_empty(&msg->list_head)) {
- dout("con_revoke %p msg %p - was on queue\n", con, msg);
+ dout("%s %p msg %p - was on queue\n", __func__, con, msg);
list_del_init(&msg->list_head);
- ceph_msg_put(msg);
+ BUG_ON(msg->con == NULL);
+ msg->con->ops->put(msg->con);
+ msg->con = NULL;
msg->hdr.seq = 0;
+
+ ceph_msg_put(msg);
}
if (con->out_msg == msg) {
- dout("con_revoke %p msg %p - was sending\n", con, msg);
+ dout("%s %p msg %p - was sending\n", __func__, con, msg);
con->out_msg = NULL;
if (con->out_kvec_is_msg) {
con->out_skip = con->out_kvec_bytes;
con->out_kvec_is_msg = false;
}
- ceph_msg_put(msg);
msg->hdr.seq = 0;
+
+ ceph_msg_put(msg);
}
mutex_unlock(&con->mutex);
}
/*
* Revoke a message that we may be reading data into
*/
-void ceph_con_revoke_message(struct ceph_connection *con, struct ceph_msg *msg)
+void ceph_msg_revoke_incoming(struct ceph_msg *msg)
{
+ struct ceph_connection *con;
+
+ BUG_ON(msg == NULL);
+ if (!msg->con) {
+ dout("%s msg %p null con\n", __func__, msg);
+
+ return; /* Message not in our possession */
+ }
+
+ con = msg->con;
mutex_lock(&con->mutex);
- if (con->in_msg && con->in_msg == msg) {
+ if (con->in_msg == msg) {
unsigned int front_len = le32_to_cpu(con->in_hdr.front_len);
unsigned int middle_len = le32_to_cpu(con->in_hdr.middle_len);
unsigned int data_len = le32_to_cpu(con->in_hdr.data_len);
/* skip rest of message */
- dout("con_revoke_pages %p msg %p revoked\n", con, msg);
- con->in_base_pos = con->in_base_pos -
+ dout("%s %p msg %p revoked\n", __func__, con, msg);
+ con->in_base_pos = con->in_base_pos -
sizeof(struct ceph_msg_header) -
front_len -
middle_len -
con->in_tag = CEPH_MSGR_TAG_READY;
con->in_seq++;
} else {
- dout("con_revoke_pages %p msg %p pages %p no-op\n",
- con, con->in_msg, msg);
+ dout("%s %p in_msg %p msg %p no-op\n",
+ __func__, con, con->in_msg, msg);
}
mutex_unlock(&con->mutex);
}
{
dout("con_keepalive %p\n", con);
clear_standby(con);
- if (test_and_set_bit(KEEPALIVE_PENDING, &con->state) == 0 &&
- test_and_set_bit(WRITE_PENDING, &con->state) == 0)
+ if (test_and_set_bit(KEEPALIVE_PENDING, &con->flags) == 0 &&
+ test_and_set_bit(WRITE_PENDING, &con->flags) == 0)
queue_con(con);
}
EXPORT_SYMBOL(ceph_con_keepalive);
if (m == NULL)
goto out;
kref_init(&m->kref);
+
+ m->con = NULL;
INIT_LIST_HEAD(&m->list_head);
m->hdr.tid = 0;
}
/*
- * Generic message allocator, for incoming messages.
+ * Allocate a message for receiving an incoming message on a
+ * connection, and save the result in con->in_msg. Uses the
+ * connection's private alloc_msg op if available.
+ *
+ * Returns true if the message should be skipped, false otherwise.
+ * If true is returned (skip message), con->in_msg will be NULL.
+ * If false is returned, con->in_msg will contain a pointer to the
+ * newly-allocated message, or NULL in case of memory exhaustion.
*/
-static struct ceph_msg *ceph_alloc_msg(struct ceph_connection *con,
- struct ceph_msg_header *hdr,
- int *skip)
+static bool ceph_con_in_msg_alloc(struct ceph_connection *con,
+ struct ceph_msg_header *hdr)
{
int type = le16_to_cpu(hdr->type);
int front_len = le32_to_cpu(hdr->front_len);
int middle_len = le32_to_cpu(hdr->middle_len);
- struct ceph_msg *msg = NULL;
int ret;
+ BUG_ON(con->in_msg != NULL);
+
if (con->ops->alloc_msg) {
+ int skip = 0;
+
mutex_unlock(&con->mutex);
- msg = con->ops->alloc_msg(con, hdr, skip);
+ con->in_msg = con->ops->alloc_msg(con, hdr, &skip);
mutex_lock(&con->mutex);
- if (!msg || *skip)
- return NULL;
+ if (con->in_msg) {
+ con->in_msg->con = con->ops->get(con);
+ BUG_ON(con->in_msg->con == NULL);
+ }
+ if (skip)
+ con->in_msg = NULL;
+
+ if (!con->in_msg)
+ return skip != 0;
}
- if (!msg) {
- *skip = 0;
- msg = ceph_msg_new(type, front_len, GFP_NOFS, false);
- if (!msg) {
+ if (!con->in_msg) {
+ con->in_msg = ceph_msg_new(type, front_len, GFP_NOFS, false);
+ if (!con->in_msg) {
pr_err("unable to allocate msg type %d len %d\n",
type, front_len);
- return NULL;
+ return false;
}
- msg->page_alignment = le16_to_cpu(hdr->data_off);
+ con->in_msg->con = con->ops->get(con);
+ BUG_ON(con->in_msg->con == NULL);
+ con->in_msg->page_alignment = le16_to_cpu(hdr->data_off);
}
- memcpy(&msg->hdr, &con->in_hdr, sizeof(con->in_hdr));
+ memcpy(&con->in_msg->hdr, &con->in_hdr, sizeof(con->in_hdr));
- if (middle_len && !msg->middle) {
- ret = ceph_alloc_middle(con, msg);
+ if (middle_len && !con->in_msg->middle) {
+ ret = ceph_alloc_middle(con, con->in_msg);
if (ret < 0) {
- ceph_msg_put(msg);
- return NULL;
+ ceph_msg_put(con->in_msg);
+ con->in_msg = NULL;
}
}
- return msg;
+ return false;
}