diff options
Diffstat (limited to 'net/ceph/messenger.c')
| -rw-r--r-- | net/ceph/messenger.c | 2041 |
1 files changed, 1369 insertions, 672 deletions
diff --git a/net/ceph/messenger.c b/net/ceph/messenger.c index b332c3d7605..1948d592aa5 100644 --- a/net/ceph/messenger.c +++ b/net/ceph/messenger.c @@ -9,17 +9,22 @@ #include <linux/slab.h> #include <linux/socket.h> #include <linux/string.h> +#ifdef CONFIG_BLOCK #include <linux/bio.h> -#include <linux/blkdev.h> +#endif /* CONFIG_BLOCK */ #include <linux/dns_resolver.h> #include <net/tcp.h> +#include <linux/ceph/ceph_features.h> #include <linux/ceph/libceph.h> #include <linux/ceph/messenger.h> #include <linux/ceph/decode.h> #include <linux/ceph/pagelist.h> #include <linux/export.h> +#define list_entry_next(pos, member) \ + list_entry(pos->member.next, typeof(*pos), member) + /* * Ceph uses the messenger to exchange ceph_msg messages with other * hosts in the system. The messenger provides ordered and reliable @@ -29,6 +34,130 @@ * the sender. */ +/* + * We track the state of the socket on a given connection using + * values defined below. The transition to a new socket state is + * handled by a function which verifies we aren't coming from an + * unexpected state. + * + * -------- + * | NEW* | transient initial state + * -------- + * | con_sock_state_init() + * v + * ---------- + * | CLOSED | initialized, but no socket (and no + * ---------- TCP connection) + * ^ \ + * | \ con_sock_state_connecting() + * | ---------------------- + * | \ + * + con_sock_state_closed() \ + * |+--------------------------- \ + * | \ \ \ + * | ----------- \ \ + * | | CLOSING | socket event; \ \ + * | ----------- await close \ \ + * | ^ \ | + * | | \ | + * | + con_sock_state_closing() \ | + * | / \ | | + * | / --------------- | | + * | / \ v v + * | / -------------- + * | / -----------------| CONNECTING | socket created, TCP + * | | / -------------- connect initiated + * | | | con_sock_state_connected() + * | | v + * ------------- + * | CONNECTED | TCP connection established + * ------------- + * + * 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 */ + +/* + * connection states + */ +#define CON_STATE_CLOSED 1 /* -> PREOPEN */ +#define CON_STATE_PREOPEN 2 /* -> CONNECTING, CLOSED */ +#define CON_STATE_CONNECTING 3 /* -> NEGOTIATING, CLOSED */ +#define CON_STATE_NEGOTIATING 4 /* -> OPEN, CLOSED */ +#define CON_STATE_OPEN 5 /* -> STANDBY, CLOSED */ +#define CON_STATE_STANDBY 6 /* -> PREOPEN, CLOSED */ + +/* + * ceph_connection flag bits + */ +#define CON_FLAG_LOSSYTX 0 /* we can close channel or drop + * messages on errors */ +#define CON_FLAG_KEEPALIVE_PENDING 1 /* we need to send a keepalive */ +#define CON_FLAG_WRITE_PENDING 2 /* we have data ready to send */ +#define CON_FLAG_SOCK_CLOSED 3 /* socket state changed to closed */ +#define CON_FLAG_BACKOFF 4 /* need to retry queuing delayed work */ + +static bool con_flag_valid(unsigned long con_flag) +{ + switch (con_flag) { + case CON_FLAG_LOSSYTX: + case CON_FLAG_KEEPALIVE_PENDING: + case CON_FLAG_WRITE_PENDING: + case CON_FLAG_SOCK_CLOSED: + case CON_FLAG_BACKOFF: + return true; + default: + return false; + } +} + +static void con_flag_clear(struct ceph_connection *con, unsigned long con_flag) +{ + BUG_ON(!con_flag_valid(con_flag)); + + clear_bit(con_flag, &con->flags); +} + +static void con_flag_set(struct ceph_connection *con, unsigned long con_flag) +{ + BUG_ON(!con_flag_valid(con_flag)); + + set_bit(con_flag, &con->flags); +} + +static bool con_flag_test(struct ceph_connection *con, unsigned long con_flag) +{ + BUG_ON(!con_flag_valid(con_flag)); + + return test_bit(con_flag, &con->flags); +} + +static bool con_flag_test_and_clear(struct ceph_connection *con, + unsigned long con_flag) +{ + BUG_ON(!con_flag_valid(con_flag)); + + return test_and_clear_bit(con_flag, &con->flags); +} + +static bool con_flag_test_and_set(struct ceph_connection *con, + unsigned long con_flag) +{ + BUG_ON(!con_flag_valid(con_flag)); + + return test_and_set_bit(con_flag, &con->flags); +} + +/* Slab caches for frequently-allocated structures */ + +static struct kmem_cache *ceph_msg_cache; +static struct kmem_cache *ceph_msg_data_cache; + /* static tag bytes (protocol control messages) */ static char tag_msg = CEPH_MSGR_TAG_MSG; static char tag_ack = CEPH_MSGR_TAG_ACK; @@ -46,7 +175,7 @@ static struct lock_class_key socket_class; static void queue_con(struct ceph_connection *con); static void con_work(struct work_struct *); -static void ceph_fault(struct ceph_connection *con); +static void con_fault(struct ceph_connection *con); /* * Nicely render a sockaddr as a string. An array of formatted @@ -103,13 +232,50 @@ static void encode_my_addr(struct ceph_messenger *msgr) */ static struct workqueue_struct *ceph_msgr_wq; -void _ceph_msgr_exit(void) +static int ceph_msgr_slab_init(void) +{ + BUG_ON(ceph_msg_cache); + ceph_msg_cache = kmem_cache_create("ceph_msg", + sizeof (struct ceph_msg), + __alignof__(struct ceph_msg), 0, NULL); + + if (!ceph_msg_cache) + return -ENOMEM; + + BUG_ON(ceph_msg_data_cache); + ceph_msg_data_cache = kmem_cache_create("ceph_msg_data", + sizeof (struct ceph_msg_data), + __alignof__(struct ceph_msg_data), + 0, NULL); + if (ceph_msg_data_cache) + return 0; + + kmem_cache_destroy(ceph_msg_cache); + ceph_msg_cache = NULL; + + return -ENOMEM; +} + +static void ceph_msgr_slab_exit(void) +{ + BUG_ON(!ceph_msg_data_cache); + kmem_cache_destroy(ceph_msg_data_cache); + ceph_msg_data_cache = NULL; + + BUG_ON(!ceph_msg_cache); + kmem_cache_destroy(ceph_msg_cache); + ceph_msg_cache = NULL; +} + +static void _ceph_msgr_exit(void) { if (ceph_msgr_wq) { destroy_workqueue(ceph_msgr_wq); ceph_msgr_wq = NULL; } + ceph_msgr_slab_exit(); + BUG_ON(zero_page == NULL); kunmap(zero_page); page_cache_release(zero_page); @@ -122,7 +288,10 @@ int ceph_msgr_init(void) zero_page = ZERO_PAGE(0); page_cache_get(zero_page); - ceph_msgr_wq = alloc_workqueue("ceph-msgr", WQ_NON_REENTRANT, 0); + if (ceph_msgr_slab_init()) + return -ENOMEM; + + ceph_msgr_wq = alloc_workqueue("ceph-msgr", 0, 0); if (ceph_msgr_wq) return 0; @@ -147,72 +316,130 @@ void ceph_msgr_flush(void) } 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); + dout("%s con %p sock %d -> %d\n", __func__, con, old_state, + CON_SOCK_STATE_CLOSED); +} + +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); + dout("%s con %p sock %d -> %d\n", __func__, con, old_state, + CON_SOCK_STATE_CONNECTING); +} + +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); + dout("%s con %p sock %d -> %d\n", __func__, con, old_state, + CON_SOCK_STATE_CONNECTED); +} + +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); + dout("%s con %p sock %d -> %d\n", __func__, con, old_state, + CON_SOCK_STATE_CLOSING); +} + +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 && + old_state != CON_SOCK_STATE_CONNECTING && + old_state != CON_SOCK_STATE_CLOSED)) + printk("%s: unexpected old state %d\n", __func__, old_state); + dout("%s con %p sock %d -> %d\n", __func__, con, old_state, + CON_SOCK_STATE_CLOSED); +} /* * 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) { struct ceph_connection *con = sk->sk_user_data; + if (atomic_read(&con->msgr->stopping)) { + return; + } 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 (sk_stream_wspace(sk) >= sk_stream_min_wspace(sk)) { - dout("ceph_write_space %p queueing write work\n", con); + if (con_flag_test(con, CON_FLAG_WRITE_PENDING)) { + if (sk_stream_is_writeable(sk)) { + 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)) - return; - 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) { - if (test_bit(CONNECTING, &con->state)) - con->error_msg = "connection failed"; - else - con->error_msg = "socket closed"; - queue_con(con); - } + dout("%s TCP_CLOSE_WAIT\n", __func__); + con_sock_state_closing(con); + con_flag_set(con, CON_FLAG_SOCK_CLOSED); + queue_con(con); 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 */ @@ -228,9 +455,9 @@ static void set_sock_callbacks(struct socket *sock, { 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; } @@ -262,6 +489,7 @@ static int ceph_tcp_connect(struct ceph_connection *con) 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) { @@ -277,7 +505,6 @@ static int ceph_tcp_connect(struct ceph_connection *con) return ret; } con->sock = sock; - return 0; } @@ -293,6 +520,22 @@ static int ceph_tcp_recvmsg(struct socket *sock, void *buf, size_t len) return r; } +static int ceph_tcp_recvpage(struct socket *sock, struct page *page, + int page_offset, size_t length) +{ + void *kaddr; + int ret; + + BUG_ON(page_offset + length > PAGE_SIZE); + + kaddr = kmap(page); + BUG_ON(!kaddr); + ret = ceph_tcp_recvmsg(sock, kaddr + page_offset, length); + kunmap(page); + + return ret; +} + /* * write something. @more is true if caller will be sending more data * shortly. @@ -314,8 +557,8 @@ static int ceph_tcp_sendmsg(struct socket *sock, struct kvec *iov, return r; } -static int ceph_tcp_sendpage(struct socket *sock, struct page *page, - int offset, size_t size, int more) +static int __ceph_tcp_sendpage(struct socket *sock, struct page *page, + int offset, size_t size, bool more) { int flags = MSG_DONTWAIT | MSG_NOSIGNAL | (more ? MSG_MORE : MSG_EOR); int ret; @@ -327,22 +570,48 @@ static int ceph_tcp_sendpage(struct socket *sock, struct page *page, return ret; } +static int ceph_tcp_sendpage(struct socket *sock, struct page *page, + int offset, size_t size, bool more) +{ + int ret; + struct kvec iov; + + /* sendpage cannot properly handle pages with page_count == 0, + * we need to fallback to sendmsg if that's the case */ + if (page_count(page) >= 1) + return __ceph_tcp_sendpage(sock, page, offset, size, more); + + iov.iov_base = kmap(page) + offset; + iov.iov_len = size; + ret = ceph_tcp_sendmsg(sock, &iov, 1, size, more); + kunmap(page); + + return ret; +} /* * Shutdown/close the socket for the given connection. */ static int con_close_socket(struct ceph_connection *con) { - int rc; + int rc = 0; dout("con_close_socket on %p sock %p\n", con, con->sock); - if (!con->sock) - return 0; - set_bit(SOCK_CLOSED, &con->state); - rc = con->sock->ops->shutdown(con->sock, SHUT_RDWR); - sock_release(con->sock); - con->sock = NULL; - clear_bit(SOCK_CLOSED, &con->state); + if (con->sock) { + rc = con->sock->ops->shutdown(con->sock, SHUT_RDWR); + sock_release(con->sock); + con->sock = NULL; + } + + /* + * Forcibly clear the SOCK_CLOSED flag. It gets set + * independent of the connection mutex, and we could have + * received a socket close event before we had the chance to + * shut the socket down. + */ + con_flag_clear(con, CON_FLAG_SOCK_CLOSED); + + con_sock_state_closed(con); return rc; } @@ -353,6 +622,10 @@ static int con_close_socket(struct ceph_connection *con) 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) @@ -368,12 +641,16 @@ static void reset_connection(struct ceph_connection *con) { /* reset connection, out_queue, msg_ and connect_seq */ /* discard existing out_queue and msg_seq */ + dout("reset_connection %p\n", con); ceph_msg_remove_list(&con->out_queue); 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; @@ -391,32 +668,43 @@ static void reset_connection(struct ceph_connection *con) */ void ceph_con_close(struct ceph_connection *con) { + mutex_lock(&con->mutex); 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(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); - mutex_lock(&con->mutex); + con->state = CON_STATE_CLOSED; + + con_flag_clear(con, CON_FLAG_LOSSYTX); /* so we retry next connect */ + con_flag_clear(con, CON_FLAG_KEEPALIVE_PENDING); + con_flag_clear(con, CON_FLAG_WRITE_PENDING); + con_flag_clear(con, CON_FLAG_BACKOFF); + reset_connection(con); con->peer_global_seq = 0; cancel_delayed_work(&con->work); + con_close_socket(con); mutex_unlock(&con->mutex); - queue_con(con); } EXPORT_SYMBOL(ceph_con_close); /* * Reopen a closed connection, with a new peer address. */ -void ceph_con_open(struct ceph_connection *con, struct ceph_entity_addr *addr) +void ceph_con_open(struct ceph_connection *con, + __u8 entity_type, __u64 entity_num, + struct ceph_entity_addr *addr) { + mutex_lock(&con->mutex); 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(con->state != CON_STATE_CLOSED); + con->state = CON_STATE_PREOPEN; + + con->peer_name.type = (__u8) entity_type; + con->peer_name.num = cpu_to_le64(entity_num); + memcpy(&con->peer_addr, addr, sizeof(*addr)); con->delay = 0; /* reset backoff memory */ + mutex_unlock(&con->mutex); queue_con(con); } EXPORT_SYMBOL(ceph_con_open); @@ -430,42 +718,26 @@ bool ceph_con_opened(struct ceph_connection *con) } /* - * 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) { 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); + mutex_init(&con->mutex); INIT_LIST_HEAD(&con->out_queue); INIT_LIST_HEAD(&con->out_sent); INIT_DELAYED_WORK(&con->work, con_work); + + con->state = CON_STATE_CLOSED; } EXPORT_SYMBOL(ceph_con_init); @@ -486,14 +758,14 @@ static u32 get_global_seq(struct ceph_messenger *msgr, u32 gt) 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; @@ -507,6 +779,401 @@ static void ceph_con_out_kvec_add(struct ceph_connection *con, con->out_kvec_bytes += size; } +#ifdef CONFIG_BLOCK + +/* + * For a bio data item, a piece is whatever remains of the next + * entry in the current bio iovec, or the first entry in the next + * bio in the list. + */ +static void ceph_msg_data_bio_cursor_init(struct ceph_msg_data_cursor *cursor, + size_t length) +{ + struct ceph_msg_data *data = cursor->data; + struct bio *bio; + + BUG_ON(data->type != CEPH_MSG_DATA_BIO); + + bio = data->bio; + BUG_ON(!bio); + + cursor->resid = min(length, data->bio_length); + cursor->bio = bio; + cursor->bvec_iter = bio->bi_iter; + cursor->last_piece = + cursor->resid <= bio_iter_len(bio, cursor->bvec_iter); +} + +static struct page *ceph_msg_data_bio_next(struct ceph_msg_data_cursor *cursor, + size_t *page_offset, + size_t *length) +{ + struct ceph_msg_data *data = cursor->data; + struct bio *bio; + struct bio_vec bio_vec; + + BUG_ON(data->type != CEPH_MSG_DATA_BIO); + + bio = cursor->bio; + BUG_ON(!bio); + + bio_vec = bio_iter_iovec(bio, cursor->bvec_iter); + + *page_offset = (size_t) bio_vec.bv_offset; + BUG_ON(*page_offset >= PAGE_SIZE); + if (cursor->last_piece) /* pagelist offset is always 0 */ + *length = cursor->resid; + else + *length = (size_t) bio_vec.bv_len; + BUG_ON(*length > cursor->resid); + BUG_ON(*page_offset + *length > PAGE_SIZE); + + return bio_vec.bv_page; +} + +static bool ceph_msg_data_bio_advance(struct ceph_msg_data_cursor *cursor, + size_t bytes) +{ + struct bio *bio; + struct bio_vec bio_vec; + + BUG_ON(cursor->data->type != CEPH_MSG_DATA_BIO); + + bio = cursor->bio; + BUG_ON(!bio); + + bio_vec = bio_iter_iovec(bio, cursor->bvec_iter); + + /* Advance the cursor offset */ + + BUG_ON(cursor->resid < bytes); + cursor->resid -= bytes; + + bio_advance_iter(bio, &cursor->bvec_iter, bytes); + + if (bytes < bio_vec.bv_len) + return false; /* more bytes to process in this segment */ + + /* Move on to the next segment, and possibly the next bio */ + + if (!cursor->bvec_iter.bi_size) { + bio = bio->bi_next; + cursor->bio = bio; + if (bio) + cursor->bvec_iter = bio->bi_iter; + else + memset(&cursor->bvec_iter, 0, + sizeof(cursor->bvec_iter)); + } + + if (!cursor->last_piece) { + BUG_ON(!cursor->resid); + BUG_ON(!bio); + /* A short read is OK, so use <= rather than == */ + if (cursor->resid <= bio_iter_len(bio, cursor->bvec_iter)) + cursor->last_piece = true; + } + + return true; +} +#endif /* CONFIG_BLOCK */ + +/* + * For a page array, a piece comes from the first page in the array + * that has not already been fully consumed. + */ +static void ceph_msg_data_pages_cursor_init(struct ceph_msg_data_cursor *cursor, + size_t length) +{ + struct ceph_msg_data *data = cursor->data; + int page_count; + + BUG_ON(data->type != CEPH_MSG_DATA_PAGES); + + BUG_ON(!data->pages); + BUG_ON(!data->length); + + cursor->resid = min(length, data->length); + page_count = calc_pages_for(data->alignment, (u64)data->length); + cursor->page_offset = data->alignment & ~PAGE_MASK; + cursor->page_index = 0; + BUG_ON(page_count > (int)USHRT_MAX); + cursor->page_count = (unsigned short)page_count; + BUG_ON(length > SIZE_MAX - cursor->page_offset); + cursor->last_piece = (size_t)cursor->page_offset + length <= PAGE_SIZE; +} + +static struct page * +ceph_msg_data_pages_next(struct ceph_msg_data_cursor *cursor, + size_t *page_offset, size_t *length) +{ + struct ceph_msg_data *data = cursor->data; + + BUG_ON(data->type != CEPH_MSG_DATA_PAGES); + + BUG_ON(cursor->page_index >= cursor->page_count); + BUG_ON(cursor->page_offset >= PAGE_SIZE); + + *page_offset = cursor->page_offset; + if (cursor->last_piece) + *length = cursor->resid; + else + *length = PAGE_SIZE - *page_offset; + + return data->pages[cursor->page_index]; +} + +static bool ceph_msg_data_pages_advance(struct ceph_msg_data_cursor *cursor, + size_t bytes) +{ + BUG_ON(cursor->data->type != CEPH_MSG_DATA_PAGES); + + BUG_ON(cursor->page_offset + bytes > PAGE_SIZE); + + /* Advance the cursor page offset */ + + cursor->resid -= bytes; + cursor->page_offset = (cursor->page_offset + bytes) & ~PAGE_MASK; + if (!bytes || cursor->page_offset) + return false; /* more bytes to process in the current page */ + + if (!cursor->resid) + return false; /* no more data */ + + /* Move on to the next page; offset is already at 0 */ + + BUG_ON(cursor->page_index >= cursor->page_count); + cursor->page_index++; + cursor->last_piece = cursor->resid <= PAGE_SIZE; + + return true; +} + +/* + * For a pagelist, a piece is whatever remains to be consumed in the + * first page in the list, or the front of the next page. + */ +static void +ceph_msg_data_pagelist_cursor_init(struct ceph_msg_data_cursor *cursor, + size_t length) +{ + struct ceph_msg_data *data = cursor->data; + struct ceph_pagelist *pagelist; + struct page *page; + + BUG_ON(data->type != CEPH_MSG_DATA_PAGELIST); + + pagelist = data->pagelist; + BUG_ON(!pagelist); + + if (!length) + return; /* pagelist can be assigned but empty */ + + BUG_ON(list_empty(&pagelist->head)); + page = list_first_entry(&pagelist->head, struct page, lru); + + cursor->resid = min(length, pagelist->length); + cursor->page = page; + cursor->offset = 0; + cursor->last_piece = cursor->resid <= PAGE_SIZE; +} + +static struct page * +ceph_msg_data_pagelist_next(struct ceph_msg_data_cursor *cursor, + size_t *page_offset, size_t *length) +{ + struct ceph_msg_data *data = cursor->data; + struct ceph_pagelist *pagelist; + + BUG_ON(data->type != CEPH_MSG_DATA_PAGELIST); + + pagelist = data->pagelist; + BUG_ON(!pagelist); + + BUG_ON(!cursor->page); + BUG_ON(cursor->offset + cursor->resid != pagelist->length); + + /* offset of first page in pagelist is always 0 */ + *page_offset = cursor->offset & ~PAGE_MASK; + if (cursor->last_piece) + *length = cursor->resid; + else + *length = PAGE_SIZE - *page_offset; + + return cursor->page; +} + +static bool ceph_msg_data_pagelist_advance(struct ceph_msg_data_cursor *cursor, + size_t bytes) +{ + struct ceph_msg_data *data = cursor->data; + struct ceph_pagelist *pagelist; + + BUG_ON(data->type != CEPH_MSG_DATA_PAGELIST); + + pagelist = data->pagelist; + BUG_ON(!pagelist); + + BUG_ON(cursor->offset + cursor->resid != pagelist->length); + BUG_ON((cursor->offset & ~PAGE_MASK) + bytes > PAGE_SIZE); + + /* Advance the cursor offset */ + + cursor->resid -= bytes; + cursor->offset += bytes; + /* offset of first page in pagelist is always 0 */ + if (!bytes || cursor->offset & ~PAGE_MASK) + return false; /* more bytes to process in the current page */ + + if (!cursor->resid) + return false; /* no more data */ + + /* Move on to the next page */ + + BUG_ON(list_is_last(&cursor->page->lru, &pagelist->head)); + cursor->page = list_entry_next(cursor->page, lru); + cursor->last_piece = cursor->resid <= PAGE_SIZE; + + return true; +} + +/* + * Message data is handled (sent or received) in pieces, where each + * piece resides on a single page. The network layer might not + * consume an entire piece at once. A data item's cursor keeps + * track of which piece is next to process and how much remains to + * be processed in that piece. It also tracks whether the current + * piece is the last one in the data item. + */ +static void __ceph_msg_data_cursor_init(struct ceph_msg_data_cursor *cursor) +{ + size_t length = cursor->total_resid; + + switch (cursor->data->type) { + case CEPH_MSG_DATA_PAGELIST: + ceph_msg_data_pagelist_cursor_init(cursor, length); + break; + case CEPH_MSG_DATA_PAGES: + ceph_msg_data_pages_cursor_init(cursor, length); + break; +#ifdef CONFIG_BLOCK + case CEPH_MSG_DATA_BIO: + ceph_msg_data_bio_cursor_init(cursor, length); + break; +#endif /* CONFIG_BLOCK */ + case CEPH_MSG_DATA_NONE: + default: + /* BUG(); */ + break; + } + cursor->need_crc = true; +} + +static void ceph_msg_data_cursor_init(struct ceph_msg *msg, size_t length) +{ + struct ceph_msg_data_cursor *cursor = &msg->cursor; + struct ceph_msg_data *data; + + BUG_ON(!length); + BUG_ON(length > msg->data_length); + BUG_ON(list_empty(&msg->data)); + + cursor->data_head = &msg->data; + cursor->total_resid = length; + data = list_first_entry(&msg->data, struct ceph_msg_data, links); + cursor->data = data; + + __ceph_msg_data_cursor_init(cursor); +} + +/* + * Return the page containing the next piece to process for a given + * data item, and supply the page offset and length of that piece. + * Indicate whether this is the last piece in this data item. + */ +static struct page *ceph_msg_data_next(struct ceph_msg_data_cursor *cursor, + size_t *page_offset, size_t *length, + bool *last_piece) +{ + struct page *page; + + switch (cursor->data->type) { + case CEPH_MSG_DATA_PAGELIST: + page = ceph_msg_data_pagelist_next(cursor, page_offset, length); + break; + case CEPH_MSG_DATA_PAGES: + page = ceph_msg_data_pages_next(cursor, page_offset, length); + break; +#ifdef CONFIG_BLOCK + case CEPH_MSG_DATA_BIO: + page = ceph_msg_data_bio_next(cursor, page_offset, length); + break; +#endif /* CONFIG_BLOCK */ + case CEPH_MSG_DATA_NONE: + default: + page = NULL; + break; + } + BUG_ON(!page); + BUG_ON(*page_offset + *length > PAGE_SIZE); + BUG_ON(!*length); + if (last_piece) + *last_piece = cursor->last_piece; + + return page; +} + +/* + * Returns true if the result moves the cursor on to the next piece + * of the data item. + */ +static bool ceph_msg_data_advance(struct ceph_msg_data_cursor *cursor, + size_t bytes) +{ + bool new_piece; + + BUG_ON(bytes > cursor->resid); + switch (cursor->data->type) { + case CEPH_MSG_DATA_PAGELIST: + new_piece = ceph_msg_data_pagelist_advance(cursor, bytes); + break; + case CEPH_MSG_DATA_PAGES: + new_piece = ceph_msg_data_pages_advance(cursor, bytes); + break; +#ifdef CONFIG_BLOCK + case CEPH_MSG_DATA_BIO: + new_piece = ceph_msg_data_bio_advance(cursor, bytes); + break; +#endif /* CONFIG_BLOCK */ + case CEPH_MSG_DATA_NONE: + default: + BUG(); + break; + } + cursor->total_resid -= bytes; + + if (!cursor->resid && cursor->total_resid) { + WARN_ON(!cursor->last_piece); + BUG_ON(list_is_last(&cursor->data->links, cursor->data_head)); + cursor->data = list_entry_next(cursor->data, links); + __ceph_msg_data_cursor_init(cursor); + new_piece = true; + } + cursor->need_crc = new_piece; + + return new_piece; +} + +static void prepare_message_data(struct ceph_msg *msg, u32 data_len) +{ + BUG_ON(!msg); + BUG_ON(!data_len); + + /* Initialize data cursor */ + + ceph_msg_data_cursor_init(msg, (size_t)data_len); +} + /* * Prepare footer for currently outgoing message, and finish things * off. Assumes out_kvec* are already valid.. we just add on to the end. @@ -516,6 +1183,8 @@ static void prepare_write_message_footer(struct ceph_connection *con) 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; @@ -534,7 +1203,7 @@ static void prepare_write_message(struct ceph_connection *con) 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; @@ -542,14 +1211,16 @@ static void prepare_write_message(struct ceph_connection *con) * 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); @@ -563,31 +1234,27 @@ static void prepare_write_message(struct ceph_connection *con) m->hdr.seq = cpu_to_le64(++con->out_seq); m->needs_out_seq = false; } -#ifdef CONFIG_BLOCK - else - m->bio_iter = NULL; -#endif + WARN_ON(m->data_length != le32_to_cpu(m->hdr.data_len)); - dout("prepare_write_message %p seq %lld type %d len %d+%d+%d %d pgs\n", + dout("prepare_write_message %p seq %lld type %d len %d+%d+%zd\n", m, con->out_seq, le16_to_cpu(m->hdr.type), le32_to_cpu(m->hdr.front_len), le32_to_cpu(m->hdr.middle_len), - le32_to_cpu(m->hdr.data_len), - m->nr_pages); + m->data_length); 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); @@ -597,28 +1264,21 @@ static void prepare_write_message(struct ceph_connection *con) 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_msg->footer.data_crc = 0; + if (m->data_length) { + prepare_message_data(con->out_msg, m->data_length); con->out_more = 1; /* data + footer will follow */ } else { /* no, queue up footer too and be done */ prepare_write_message_footer(con); } - set_bit(WRITE_PENDING, &con->state); + con_flag_set(con, CON_FLAG_WRITE_PENDING); } /* @@ -630,16 +1290,34 @@ static void prepare_write_ack(struct ceph_connection *con) 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); + con_flag_set(con, CON_FLAG_WRITE_PENDING); +} + +/* + * Prepare to share the seq during handshake + */ +static void prepare_write_seq(struct ceph_connection *con) +{ + dout("prepare_write_seq %p %llu -> %llu\n", con, + con->in_seq_acked, con->in_seq); + con->in_seq_acked = con->in_seq; + + con_out_kvec_reset(con); + + con->out_temp_ack = cpu_to_le64(con->in_seq_acked); + con_out_kvec_add(con, sizeof (con->out_temp_ack), + &con->out_temp_ack); + + con_flag_set(con, CON_FLAG_WRITE_PENDING); } /* @@ -648,9 +1326,9 @@ static void prepare_write_ack(struct ceph_connection *con) 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); + con_flag_set(con, CON_FLAG_WRITE_PENDING); } /* @@ -665,27 +1343,21 @@ static struct ceph_auth_handshake *get_connect_authorizer(struct ceph_connection 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); - auth = con->ops->get_authorizer(con, auth_proto, con->auth_retry); - mutex_lock(&con->mutex); if (IS_ERR(auth)) return auth; - if (test_bit(CLOSED, &con->state) || test_bit(OPENING, &con->state)) + if (con->state != CON_STATE_NEGOTIATING) return ERR_PTR(-EAGAIN); con->auth_reply_buf = auth->authorizer_reply_buf; con->auth_reply_buf_len = auth->authorizer_reply_buf_len; - - return auth; } @@ -694,12 +1366,12 @@ static struct ceph_auth_handshake *get_connect_authorizer(struct ceph_connection */ static void prepare_write_banner(struct ceph_connection *con) { - ceph_con_out_kvec_add(con, strlen(CEPH_BANNER), CEPH_BANNER); - ceph_con_out_kvec_add(con, sizeof (con->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); + con_flag_set(con, CON_FLAG_WRITE_PENDING); } static int prepare_write_connect(struct ceph_connection *con) @@ -742,14 +1414,14 @@ static int prepare_write_connect(struct ceph_connection *con) con->out_connect.authorizer_len = auth ? cpu_to_le32(auth->authorizer_buf_len) : 0; - ceph_con_out_kvec_add(con, sizeof (con->out_connect), + con_out_kvec_add(con, sizeof (con->out_connect), &con->out_connect); if (auth && auth->authorizer_buf_len) - ceph_con_out_kvec_add(con, 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); + con_flag_set(con, CON_FLAG_WRITE_PENDING); return 0; } @@ -797,31 +1469,19 @@ out: return ret; /* done! */ } -#ifdef CONFIG_BLOCK -static void init_bio_iter(struct bio *bio, struct bio **iter, int *seg) +static u32 ceph_crc32c_page(u32 crc, struct page *page, + unsigned int page_offset, + unsigned int length) { - if (!bio) { - *iter = NULL; - *seg = 0; - return; - } - *iter = bio; - *seg = bio->bi_idx; -} + char *kaddr; -static void iter_bio_next(struct bio **bio_iter, int *seg) -{ - if (*bio_iter == NULL) - return; - - BUG_ON(*seg >= (*bio_iter)->bi_vcnt); + kaddr = kmap(page); + BUG_ON(kaddr == NULL); + crc = crc32c(crc, kaddr + page_offset, length); + kunmap(page); - (*seg)++; - if (*seg == (*bio_iter)->bi_vcnt) - init_bio_iter((*bio_iter)->bi_next, bio_iter, seg); + return crc; } -#endif - /* * Write as much message data payload as we can. If we finish, queue * up the footer. @@ -829,121 +1489,61 @@ static void iter_bio_next(struct bio **bio_iter, int *seg) * 0 -> socket full, but more to do * <0 -> error */ -static int write_partial_msg_pages(struct ceph_connection *con) +static int write_partial_message_data(struct ceph_connection *con) { struct ceph_msg *msg = con->out_msg; - unsigned int data_len = le32_to_cpu(msg->hdr.data_len); - size_t len; + struct ceph_msg_data_cursor *cursor = &msg->cursor; bool do_datacrc = !con->msgr->nocrc; - int ret; - int total_max_write; - int in_trail = 0; - 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->out_msg_pos.page_pos); - -#ifdef CONFIG_BLOCK - if (msg->bio && !msg->bio_iter) - init_bio_iter(msg->bio, &msg->bio_iter, &msg->bio_seg); -#endif - - while (data_len > con->out_msg_pos.data_pos) { - struct page *page = NULL; - int max_write = PAGE_SIZE; - int bio_offset = 0; - - total_max_write = data_len - trail_len - - con->out_msg_pos.data_pos; - - /* - * if we are calculating the data crc (the default), we need - * to map the page. if our pages[] has been revoked, use the - * zero page. - */ - - /* have we reached the trail part of the data? */ - if (con->out_msg_pos.data_pos >= data_len - trail_len) { - in_trail = 1; - - 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) { - page = list_first_entry(&msg->pagelist->head, - struct page, lru); -#ifdef CONFIG_BLOCK - } else if (msg->bio) { - struct bio_vec *bv; + u32 crc; - bv = bio_iovec_idx(msg->bio_iter, msg->bio_seg); - page = bv->bv_page; - bio_offset = bv->bv_offset; - max_write = bv->bv_len; -#endif - } else { - page = zero_page; - } - len = min_t(int, max_write - con->out_msg_pos.page_pos, - total_max_write); - - 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); - 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); - con->out_msg_pos.did_page_crc = true; - } - ret = ceph_tcp_sendpage(con->sock, page, - con->out_msg_pos.page_pos + bio_offset, - len, 1); + dout("%s %p msg %p\n", __func__, con, msg); - if (do_datacrc) - kunmap(page); + if (list_empty(&msg->data)) + return -EINVAL; - if (ret <= 0) - goto out; + /* + * Iterate through each page that contains data to be + * written, and send as much as possible for each. + * + * If we are calculating the data crc (the default), we will + * need to map the page. If we have no pages, they have + * been revoked, so use the zero page. + */ + crc = do_datacrc ? le32_to_cpu(msg->footer.data_crc) : 0; + while (cursor->resid) { + struct page *page; + size_t page_offset; + size_t length; + bool last_piece; + bool need_crc; + int ret; + + page = ceph_msg_data_next(&msg->cursor, &page_offset, &length, + &last_piece); + ret = ceph_tcp_sendpage(con->sock, page, page_offset, + length, last_piece); + if (ret <= 0) { + if (do_datacrc) + msg->footer.data_crc = cpu_to_le32(crc); - 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 + return ret; } + if (do_datacrc && cursor->need_crc) + crc = ceph_crc32c_page(crc, page, page_offset, length); + need_crc = ceph_msg_data_advance(&msg->cursor, (size_t)ret); } - dout("write_partial_msg_pages %p msg %p done\n", con, msg); + dout("%s %p msg %p done\n", __func__, 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); + if (do_datacrc) + msg->footer.data_crc = cpu_to_le32(crc); + else + msg->footer.flags |= CEPH_MSG_FOOTER_NOCRC; + con_out_kvec_reset(con); prepare_write_message_footer(con); - ret = 1; -out: - return ret; + + return 1; /* must return > 0 to indicate success */ } /* @@ -956,7 +1556,7 @@ static int write_partial_skip(struct ceph_connection *con) while (con->out_skip > 0) { size_t size = min(con->out_skip, (int) PAGE_CACHE_SIZE); - ret = ceph_tcp_sendpage(con->sock, zero_page, 0, size, 1); + ret = ceph_tcp_sendpage(con->sock, zero_page, 0, size, true); if (ret <= 0) goto out; con->out_skip -= ret; @@ -987,6 +1587,13 @@ static void prepare_read_ack(struct ceph_connection *con) con->in_base_pos = 0; } +static void prepare_read_seq(struct ceph_connection *con) +{ + dout("prepare_read_seq %p\n", con); + con->in_base_pos = 0; + con->in_tag = CEPH_MSGR_TAG_SEQ; +} + static void prepare_read_tag(struct ceph_connection *con) { dout("prepare_read_tag %p\n", con); @@ -1278,7 +1885,9 @@ int ceph_parse_ips(const char *c, const char *end, port = (port * 10) + (*p - '0'); p++; } - if (port > 65535 || port == 0) + if (port == 0) + port = CEPH_MON_PORT; + else if (port > 65535) goto bad; } else { port = CEPH_MON_PORT; @@ -1351,27 +1960,15 @@ static int process_banner(struct ceph_connection *con) ceph_pr_addr(&con->msgr->inst.addr.in_addr)); } - set_bit(NEGOTIATING, &con->state); - prepare_read_connect(con); return 0; } -static void fail_protocol(struct ceph_connection *con) -{ - 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) { u64 sup_feat = con->msgr->supported_features; u64 req_feat = con->msgr->required_features; - u64 server_feat = le64_to_cpu(con->in_reply.features); + u64 server_feat = ceph_sanitize_features( + le64_to_cpu(con->in_reply.features)); int ret; dout("process_connect on %p tag %d\n", con, (int)con->in_tag); @@ -1384,7 +1981,7 @@ static int process_connect(struct ceph_connection *con) ceph_pr_addr(&con->peer_addr.in_addr), sup_feat, server_feat, server_feat & ~sup_feat); con->error_msg = "missing required protocol features"; - fail_protocol(con); + reset_connection(con); return -1; case CEPH_MSGR_TAG_BADPROTOVER: @@ -1395,7 +1992,7 @@ static int process_connect(struct ceph_connection *con) le32_to_cpu(con->out_connect.protocol_version), le32_to_cpu(con->in_reply.protocol_version)); con->error_msg = "protocol version mismatch"; - fail_protocol(con); + reset_connection(con); return -1; case CEPH_MSGR_TAG_BADAUTHORIZER: @@ -1406,8 +2003,7 @@ static int process_connect(struct ceph_connection *con) con->error_msg = "connect authorization failure"; return -1; } - con->auth_retry = 1; - ceph_con_out_kvec_reset(con); + con_out_kvec_reset(con); ret = prepare_write_connect(con); if (ret < 0) return ret; @@ -1423,12 +2019,12 @@ static int process_connect(struct ceph_connection *con) * dropped messages. */ dout("process_connect got RESET peer seq %u\n", - le32_to_cpu(con->in_connect.connect_seq)); + le32_to_cpu(con->in_reply.connect_seq)); pr_err("%s%lld %s connection reset\n", ENTITY_NAME(con->peer_name), ceph_pr_addr(&con->peer_addr.in_addr)); reset_connection(con); - ceph_con_out_kvec_reset(con); + con_out_kvec_reset(con); ret = prepare_write_connect(con); if (ret < 0) return ret; @@ -1440,8 +2036,7 @@ static int process_connect(struct ceph_connection *con) if (con->ops->peer_reset) con->ops->peer_reset(con); mutex_lock(&con->mutex); - if (test_bit(CLOSED, &con->state) || - test_bit(OPENING, &con->state)) + if (con->state != CON_STATE_NEGOTIATING) return -EAGAIN; break; @@ -1450,11 +2045,11 @@ static int process_connect(struct ceph_connection *con) * If we sent a smaller connect_seq than the peer has, try * again with a larger value. */ - dout("process_connect got RETRY my seq = %u, peer_seq = %u\n", + dout("process_connect got RETRY_SESSION my seq %u, peer %u\n", 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); - ceph_con_out_kvec_reset(con); + le32_to_cpu(con->in_reply.connect_seq)); + con->connect_seq = le32_to_cpu(con->in_reply.connect_seq); + con_out_kvec_reset(con); ret = prepare_write_connect(con); if (ret < 0) return ret; @@ -1468,16 +2063,17 @@ static int process_connect(struct ceph_connection *con) */ dout("process_connect got RETRY_GLOBAL my %u peer_gseq %u\n", con->peer_global_seq, - le32_to_cpu(con->in_connect.global_seq)); + le32_to_cpu(con->in_reply.global_seq)); get_global_seq(con->msgr, - le32_to_cpu(con->in_connect.global_seq)); - ceph_con_out_kvec_reset(con); + le32_to_cpu(con->in_reply.global_seq)); + con_out_kvec_reset(con); ret = prepare_write_connect(con); if (ret < 0) return ret; prepare_read_connect(con); break; + case CEPH_MSGR_TAG_SEQ: case CEPH_MSGR_TAG_READY: if (req_feat & ~server_feat) { pr_err("%s%lld %s protocol feature mismatch," @@ -1486,10 +2082,13 @@ static int process_connect(struct ceph_connection *con) ceph_pr_addr(&con->peer_addr.in_addr), req_feat, server_feat, req_feat & ~server_feat); con->error_msg = "missing required protocol features"; - fail_protocol(con); + reset_connection(con); return -1; } - clear_bit(CONNECTING, &con->state); + + WARN_ON(con->state != CON_STATE_NEGOTIATING); + con->state = CON_STATE_OPEN; + con->auth_retry = 0; /* we authenticated; clear flag */ con->peer_global_seq = le32_to_cpu(con->in_reply.global_seq); con->connect_seq++; con->peer_features = server_feat; @@ -1501,9 +2100,16 @@ static int process_connect(struct ceph_connection *con) le32_to_cpu(con->in_reply.connect_seq)); if (con->in_reply.flags & CEPH_MSG_CONNECT_LOSSY) - set_bit(LOSSYTX, &con->state); + con_flag_set(con, CON_FLAG_LOSSYTX); - prepare_read_tag(con); + con->delay = 0; /* reset backoff memory */ + + if (con->in_reply.tag == CEPH_MSGR_TAG_SEQ) { + prepare_write_seq(con); + prepare_read_seq(con); + } else { + prepare_read_tag(con); + } break; case CEPH_MSGR_TAG_WAIT: @@ -1537,7 +2143,6 @@ static int read_partial_ack(struct ceph_connection *con) return read_partial(con, end, size, &con->in_temp_ack); } - /* * We can finally discard anything that's been acked. */ @@ -1562,8 +2167,6 @@ static void process_ack(struct ceph_connection *con) } - - static int read_partial_message_section(struct ceph_connection *con, struct kvec *section, unsigned int sec_len, u32 *crc) @@ -1587,83 +2190,49 @@ static int read_partial_message_section(struct ceph_connection *con, return 1; } -static struct ceph_msg *ceph_alloc_msg(struct ceph_connection *con, - struct ceph_msg_header *hdr, - int *skip); - - -static int read_partial_message_pages(struct ceph_connection *con, - struct page **pages, - unsigned int data_len, bool do_datacrc) +static int read_partial_msg_data(struct ceph_connection *con) { - void *p; + struct ceph_msg *msg = con->in_msg; + struct ceph_msg_data_cursor *cursor = &msg->cursor; + const bool do_datacrc = !con->msgr->nocrc; + struct page *page; + size_t page_offset; + size_t length; + u32 crc = 0; int ret; - int left; - - left = min((int)(data_len - con->in_msg_pos.data_pos), - (int)(PAGE_SIZE - con->in_msg_pos.page_pos)); - /* (page) data */ - BUG_ON(pages == NULL); - p = kmap(pages[con->in_msg_pos.page]); - ret = ceph_tcp_recvmsg(con->sock, p + con->in_msg_pos.page_pos, - left); - if (ret > 0 && do_datacrc) - con->in_data_crc = - crc32c(con->in_data_crc, - p + con->in_msg_pos.page_pos, ret); - kunmap(pages[con->in_msg_pos.page]); - if (ret <= 0) - return ret; - con->in_msg_pos.data_pos += ret; - con->in_msg_pos.page_pos += ret; - if (con->in_msg_pos.page_pos == PAGE_SIZE) { - con->in_msg_pos.page_pos = 0; - con->in_msg_pos.page++; - } - - return ret; -} - -#ifdef CONFIG_BLOCK -static int read_partial_message_bio(struct ceph_connection *con, - struct bio **bio_iter, int *bio_seg, - unsigned int data_len, bool do_datacrc) -{ - struct bio_vec *bv = bio_iovec_idx(*bio_iter, *bio_seg); - void *p; - int ret, left; - if (IS_ERR(bv)) - return PTR_ERR(bv); + BUG_ON(!msg); + if (list_empty(&msg->data)) + return -EIO; - left = min((int)(data_len - con->in_msg_pos.data_pos), - (int)(bv->bv_len - con->in_msg_pos.page_pos)); + if (do_datacrc) + crc = con->in_data_crc; + while (cursor->resid) { + page = ceph_msg_data_next(&msg->cursor, &page_offset, &length, + NULL); + ret = ceph_tcp_recvpage(con->sock, page, page_offset, length); + if (ret <= 0) { + if (do_datacrc) + con->in_data_crc = crc; - p = kmap(bv->bv_page) + bv->bv_offset; + return ret; + } - ret = ceph_tcp_recvmsg(con->sock, p + con->in_msg_pos.page_pos, - left); - if (ret > 0 && do_datacrc) - con->in_data_crc = - crc32c(con->in_data_crc, - p + con->in_msg_pos.page_pos, ret); - kunmap(bv->bv_page); - if (ret <= 0) - return ret; - con->in_msg_pos.data_pos += ret; - con->in_msg_pos.page_pos += ret; - if (con->in_msg_pos.page_pos == bv->bv_len) { - con->in_msg_pos.page_pos = 0; - iter_bio_next(bio_iter, bio_seg); + if (do_datacrc) + crc = ceph_crc32c_page(crc, page, page_offset, ret); + (void) ceph_msg_data_advance(&msg->cursor, (size_t)ret); } + if (do_datacrc) + con->in_data_crc = crc; - return ret; + return 1; /* must return > 0 to indicate success */ } -#endif /* * read (part of) a message. */ +static int ceph_con_in_msg_alloc(struct ceph_connection *con, int *skip); + static int read_partial_message(struct ceph_connection *con) { struct ceph_msg *m = con->in_msg; @@ -1672,7 +2241,6 @@ static int read_partial_message(struct ceph_connection *con) int ret; unsigned int front_len, middle_len, data_len; bool do_datacrc = !con->msgr->nocrc; - int skip; u64 seq; u32 crc; @@ -1697,7 +2265,7 @@ static int read_partial_message(struct ceph_connection *con) if (front_len > CEPH_MSG_MAX_FRONT_LEN) return -EIO; middle_len = le32_to_cpu(con->in_hdr.middle_len); - if (middle_len > CEPH_MSG_MAX_DATA_LEN) + if (middle_len > CEPH_MSG_MAX_MIDDLE_LEN) return -EIO; data_len = le32_to_cpu(con->in_hdr.data_len); if (data_len > CEPH_MSG_MAX_DATA_LEN) @@ -1723,36 +2291,43 @@ static int read_partial_message(struct ceph_connection *con) /* allocate message? */ if (!con->in_msg) { + int skip = 0; + 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); + front_len, data_len); + ret = ceph_con_in_msg_alloc(con, &skip); + if (ret < 0) + return ret; + + BUG_ON(!con->in_msg ^ skip); + if (con->in_msg && data_len > con->in_msg->data_length) { + pr_warning("%s skipping long message (%u > %zd)\n", + __func__, data_len, con->in_msg->data_length); + ceph_msg_put(con->in_msg); + con->in_msg = NULL; + skip = 1; + } if (skip) { /* skip this message */ dout("alloc_msg said skip message\n"); - BUG_ON(con->in_msg); con->in_base_pos = -front_len - middle_len - data_len - sizeof(m->footer); con->in_tag = CEPH_MSGR_TAG_READY; con->in_seq++; return 0; } - if (!con->in_msg) { - con->error_msg = - "error allocating memory for incoming message"; - return -ENOMEM; - } + + BUG_ON(!con->in_msg); + BUG_ON(con->in_msg->con != con); m = con->in_msg; m->front.iov_len = 0; /* haven't read it yet */ if (m->middle) m->middle->vec.iov_len = 0; - con->in_msg_pos.page = 0; - if (m->pages) - con->in_msg_pos.page_pos = m->page_alignment; - else - con->in_msg_pos.page_pos = 0; - con->in_msg_pos.data_pos = 0; + /* prepare for data payload, if any */ + + if (data_len) + prepare_message_data(con->in_msg, data_len); } /* front */ @@ -1769,30 +2344,12 @@ static int read_partial_message(struct ceph_connection *con) if (ret <= 0) return ret; } -#ifdef CONFIG_BLOCK - if (m->bio && !m->bio_iter) - init_bio_iter(m->bio, &m->bio_iter, &m->bio_seg); -#endif /* (page) data */ - while (con->in_msg_pos.data_pos < data_len) { - if (m->pages) { - ret = read_partial_message_pages(con, m->pages, - data_len, do_datacrc); - if (ret <= 0) - return ret; -#ifdef CONFIG_BLOCK - } else if (m->bio) { - - ret = read_partial_message_bio(con, - &m->bio_iter, &m->bio_seg, - data_len, do_datacrc); - if (ret <= 0) - return ret; -#endif - } else { - BUG_ON(1); - } + if (data_len) { + ret = read_partial_msg_data(con); + if (ret <= 0) + return ret; } /* footer */ @@ -1837,8 +2394,11 @@ static void process_message(struct ceph_connection *con) { 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) @@ -1858,7 +2418,6 @@ static void process_message(struct ceph_connection *con) con->ops->dispatch(con, msg); mutex_lock(&con->mutex); - prepare_read_tag(con); } @@ -1870,22 +2429,19 @@ static int try_write(struct ceph_connection *con) { 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) { - ceph_con_out_kvec_reset(con); + if (con->state == CON_STATE_PREOPEN) { + BUG_ON(con->sock); + con->state = CON_STATE_CONNECTING; + + con_out_kvec_reset(con); prepare_write_banner(con); - ret = prepare_write_connect(con); - if (ret < 0) - goto out; prepare_read_banner(con); - set_bit(CONNECTING, &con->state); - clear_bit(NEGOTIATING, &con->state); BUG_ON(con->in_msg); con->in_tag = CEPH_MSGR_TAG_READY; @@ -1919,20 +2475,20 @@ more_kvec: goto do_next; } - ret = write_partial_msg_pages(con); + ret = write_partial_message_data(con); if (ret == 1) goto more_kvec; /* we need to send the footer, too! */ if (ret == 0) goto out; if (ret < 0) { - dout("try_write write_partial_msg_pages err %d\n", + dout("try_write write_partial_message_data err %d\n", ret); goto out; } } do_next: - if (!test_bit(CONNECTING, &con->state)) { + if (con->state == CON_STATE_OPEN) { /* is anything else pending? */ if (!list_empty(&con->out_queue)) { prepare_write_message(con); @@ -1942,14 +2498,14 @@ do_next: prepare_write_ack(con); goto more; } - if (test_and_clear_bit(KEEPALIVE_PENDING, &con->state)) { + if (con_flag_test_and_clear(con, CON_FLAG_KEEPALIVE_PENDING)) { prepare_write_keepalive(con); goto more; } } /* Nothing to do! */ - clear_bit(WRITE_PENDING, &con->state); + con_flag_clear(con, CON_FLAG_WRITE_PENDING); dout("try_write nothing else to write.\n"); ret = 0; out: @@ -1966,38 +2522,45 @@ static int try_read(struct ceph_connection *con) { int ret = -1; - if (!con->sock) - return 0; - - if (test_bit(STANDBY, &con->state)) +more: + dout("try_read start on %p state %lu\n", con, con->state); + if (con->state != CON_STATE_CONNECTING && + con->state != CON_STATE_NEGOTIATING && + con->state != CON_STATE_OPEN) return 0; - dout("try_read start on %p\n", con); + BUG_ON(!con->sock); -more: dout("try_read tag %d in_base_pos %d\n", (int)con->in_tag, con->in_base_pos); - /* - * process_connect and process_message drop and re-take - * con->mutex. make sure we handle a racing close or reopen. - */ - if (test_bit(CLOSED, &con->state) || - test_bit(OPENING, &con->state)) { - ret = -EAGAIN; + if (con->state == CON_STATE_CONNECTING) { + dout("try_read connecting\n"); + ret = read_partial_banner(con); + if (ret <= 0) + goto out; + ret = process_banner(con); + if (ret < 0) + goto out; + + con->state = CON_STATE_NEGOTIATING; + + /* + * Received banner is good, exchange connection info. + * Do not reset out_kvec, as sending our banner raced + * with receiving peer banner after connect completed. + */ + ret = prepare_write_connect(con); + if (ret < 0) + goto out; + prepare_read_connect(con); + + /* Send connection info before awaiting response */ goto out; } - if (test_bit(CONNECTING, &con->state)) { - if (!test_bit(NEGOTIATING, &con->state)) { - dout("try_read connecting\n"); - ret = read_partial_banner(con); - if (ret <= 0) - goto out; - ret = process_banner(con); - if (ret < 0) - goto out; - } + if (con->state == CON_STATE_NEGOTIATING) { + dout("try_read negotiating\n"); ret = read_partial_connect(con); if (ret <= 0) goto out; @@ -2007,6 +2570,8 @@ more: goto more; } + WARN_ON(con->state != CON_STATE_OPEN); + if (con->in_base_pos < 0) { /* * skipping + discarding content. @@ -2040,7 +2605,8 @@ more: prepare_read_ack(con); break; case CEPH_MSGR_TAG_CLOSE: - set_bit(CLOSED, &con->state); /* fixme */ + con_close_socket(con); + con->state = CON_STATE_CLOSED; goto out; default: goto bad_tag; @@ -2063,9 +2629,16 @@ more: if (con->in_tag == CEPH_MSGR_TAG_READY) goto more; process_message(con); + if (con->state == CON_STATE_OPEN) + prepare_read_tag(con); goto more; } - if (con->in_tag == CEPH_MSGR_TAG_ACK) { + if (con->in_tag == CEPH_MSGR_TAG_ACK || + con->in_tag == CEPH_MSGR_TAG_SEQ) { + /* + * the final handshake seq exchange is semantically + * equivalent to an ACK + */ ret = read_partial_ack(con); if (ret <= 0) goto out; @@ -2086,28 +2659,97 @@ bad_tag: /* - * Atomically queue work on a connection. Bump @con reference to - * avoid races with connection teardown. + * Atomically queue work on a connection after the specified delay. + * Bump @con reference to avoid races with connection teardown. + * Returns 0 if work was queued, or an error code otherwise. */ +static int queue_con_delay(struct ceph_connection *con, unsigned long delay) +{ + if (!con->ops->get(con)) { + dout("%s %p ref count 0\n", __func__, con); + + return -ENOENT; + } + + if (!queue_delayed_work(ceph_msgr_wq, &con->work, delay)) { + dout("%s %p - already queued\n", __func__, con); + con->ops->put(con); + + return -EBUSY; + } + + dout("%s %p %lu\n", __func__, con, delay); + + return 0; +} + static void queue_con(struct ceph_connection *con) { - if (test_bit(DEAD, &con->state)) { - dout("queue_con %p ignoring: DEAD\n", - con); - return; + (void) queue_con_delay(con, 0); +} + +static bool con_sock_closed(struct ceph_connection *con) +{ + if (!con_flag_test_and_clear(con, CON_FLAG_SOCK_CLOSED)) + return false; + +#define CASE(x) \ + case CON_STATE_ ## x: \ + con->error_msg = "socket closed (con state " #x ")"; \ + break; + + switch (con->state) { + CASE(CLOSED); + CASE(PREOPEN); + CASE(CONNECTING); + CASE(NEGOTIATING); + CASE(OPEN); + CASE(STANDBY); + default: + pr_warning("%s con %p unrecognized state %lu\n", + __func__, con, con->state); + con->error_msg = "unrecognized con state"; + BUG(); + break; } +#undef CASE - if (!con->ops->get(con)) { - dout("queue_con %p ref count 0\n", con); - return; + return true; +} + +static bool con_backoff(struct ceph_connection *con) +{ + int ret; + + if (!con_flag_test_and_clear(con, CON_FLAG_BACKOFF)) + return false; + + ret = queue_con_delay(con, round_jiffies_relative(con->delay)); + if (ret) { + dout("%s: con %p FAILED to back off %lu\n", __func__, + con, con->delay); + BUG_ON(ret == -ENOENT); + con_flag_set(con, CON_FLAG_BACKOFF); } - if (!queue_delayed_work(ceph_msgr_wq, &con->work, 0)) { - dout("queue_con %p - already queued\n", con); - con->ops->put(con); - } else { - dout("queue_con %p\n", con); + return true; +} + +/* Finish fault handling; con->mutex must *not* be held here */ + +static void con_fault_finish(struct ceph_connection *con) +{ + /* + * in case we faulted due to authentication, invalidate our + * current tickets so that we can get new ones. + */ + if (con->auth_retry && con->ops->invalidate_authorizer) { + dout("calling invalidate_authorizer()\n"); + con->ops->invalidate_authorizer(con); } + + if (con->ops->fault) + con->ops->fault(con); } /* @@ -2117,92 +2759,92 @@ static void con_work(struct work_struct *work) { struct ceph_connection *con = container_of(work, struct ceph_connection, work.work); - int ret; + bool fault; mutex_lock(&con->mutex); -restart: - if (test_and_clear_bit(BACKOFF, &con->state)) { - dout("con_work %p backing off\n", con); - if (queue_delayed_work(ceph_msgr_wq, &con->work, - round_jiffies_relative(con->delay))) { - dout("con_work %p backoff %lu\n", con, con->delay); - mutex_unlock(&con->mutex); - return; - } else { - con->ops->put(con); - dout("con_work %p FAILED to back off %lu\n", con, - con->delay); + while (true) { + int ret; + + if ((fault = con_sock_closed(con))) { + dout("%s: con %p SOCK_CLOSED\n", __func__, con); + break; + } + if (con_backoff(con)) { + dout("%s: con %p BACKOFF\n", __func__, con); + break; + } + if (con->state == CON_STATE_STANDBY) { + dout("%s: con %p STANDBY\n", __func__, con); + break; + } + if (con->state == CON_STATE_CLOSED) { + dout("%s: con %p CLOSED\n", __func__, con); + BUG_ON(con->sock); + break; + } + if (con->state == CON_STATE_PREOPEN) { + dout("%s: con %p PREOPEN\n", __func__, con); + BUG_ON(con->sock); } - } - if (test_bit(STANDBY, &con->state)) { - dout("con_work %p STANDBY\n", con); - goto done; - } - if (test_bit(CLOSED, &con->state)) { /* e.g. if we are replaced */ - dout("con_work CLOSED\n"); - con_close_socket(con); - goto done; - } - if (test_and_clear_bit(OPENING, &con->state)) { - /* reopen w/ new peer */ - dout("con_work OPENING\n"); - con_close_socket(con); - } + ret = try_read(con); + if (ret < 0) { + if (ret == -EAGAIN) + continue; + con->error_msg = "socket error on read"; + fault = true; + break; + } - if (test_and_clear_bit(SOCK_CLOSED, &con->state)) - goto fault; + ret = try_write(con); + if (ret < 0) { + if (ret == -EAGAIN) + continue; + con->error_msg = "socket error on write"; + fault = true; + } - ret = try_read(con); - if (ret == -EAGAIN) - goto restart; - if (ret < 0) - goto fault; + break; /* If we make it to here, we're done */ + } + if (fault) + con_fault(con); + mutex_unlock(&con->mutex); - ret = try_write(con); - if (ret == -EAGAIN) - goto restart; - if (ret < 0) - goto fault; + if (fault) + con_fault_finish(con); -done: - mutex_unlock(&con->mutex); -done_unlocked: con->ops->put(con); - return; - -fault: - mutex_unlock(&con->mutex); - ceph_fault(con); /* error/fault path */ - goto done_unlocked; } - /* * Generic error/fault handler. A retry mechanism is used with * exponential backoff */ -static void ceph_fault(struct ceph_connection *con) +static void con_fault(struct ceph_connection *con) { - pr_err("%s%lld %s %s\n", ENTITY_NAME(con->peer_name), + pr_warning("%s%lld %s %s\n", ENTITY_NAME(con->peer_name), ceph_pr_addr(&con->peer_addr.in_addr), con->error_msg); 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)) { - dout("fault on LOSSYTX channel\n"); - goto out; - } - - mutex_lock(&con->mutex); - if (test_bit(CLOSED, &con->state)) - goto out_unlock; + WARN_ON(con->state != CON_STATE_CONNECTING && + con->state != CON_STATE_NEGOTIATING && + con->state != CON_STATE_OPEN); con_close_socket(con); + if (con_flag_test(con, CON_FLAG_LOSSYTX)) { + dout("fault on LOSSYTX channel, marking CLOSED\n"); + con->state = CON_STATE_CLOSED; + return; + } + 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 */ @@ -2211,67 +2853,33 @@ static void ceph_fault(struct ceph_connection *con) /* 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)) { + !con_flag_test(con, CON_FLAG_KEEPALIVE_PENDING)) { dout("fault %p setting STANDBY clearing WRITE_PENDING\n", con); - clear_bit(WRITE_PENDING, &con->state); - set_bit(STANDBY, &con->state); + con_flag_clear(con, CON_FLAG_WRITE_PENDING); + con->state = CON_STATE_STANDBY; } else { /* retry after a delay. */ + con->state = CON_STATE_PREOPEN; if (con->delay == 0) con->delay = BASE_DELAY_INTERVAL; else if (con->delay < MAX_DELAY_INTERVAL) con->delay *= 2; - con->ops->get(con); - if (queue_delayed_work(ceph_msgr_wq, &con->work, - round_jiffies_relative(con->delay))) { - dout("fault queued %p delay %lu\n", con, con->delay); - } else { - con->ops->put(con); - dout("fault failed to queue %p delay %lu, backoff\n", - con, con->delay); - /* - * In many cases we see a socket state change - * while con_work is running and end up - * queuing (non-delayed) work, such that we - * can't backoff with a delay. Set a flag so - * that when con_work restarts we schedule the - * delay then. - */ - set_bit(BACKOFF, &con->state); - } - } - -out_unlock: - mutex_unlock(&con->mutex); -out: - /* - * in case we faulted due to authentication, invalidate our - * current tickets so that we can get new ones. - */ - if (con->auth_retry && con->ops->invalidate_authorizer) { - dout("calling invalidate_authorizer()\n"); - con->ops->invalidate_authorizer(con); + con_flag_set(con, CON_FLAG_BACKOFF); + queue_con(con); } - - if (con->ops->fault) - con->ops->fault(con); } /* - * 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, + u64 supported_features, + u64 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; @@ -2284,30 +2892,23 @@ struct ceph_messenger *ceph_messenger_create(struct ceph_entity_addr *myaddr, 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); + atomic_set(&msgr->stopping, 0); -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) { /* come back from STANDBY? */ - if (test_and_clear_bit(STANDBY, &con->state)) { - mutex_lock(&con->mutex); + if (con->state == CON_STATE_STANDBY) { dout("clear_standby %p and ++connect_seq\n", con); + con->state = CON_STATE_PREOPEN; con->connect_seq++; - WARN_ON(test_bit(WRITE_PENDING, &con->state)); - WARN_ON(test_bit(KEEPALIVE_PENDING, &con->state)); - mutex_unlock(&con->mutex); + WARN_ON(con_flag_test(con, CON_FLAG_WRITE_PENDING)); + WARN_ON(con_flag_test(con, CON_FLAG_KEEPALIVE_PENDING)); } } @@ -2316,21 +2917,24 @@ static void clear_standby(struct ceph_connection *con) */ void ceph_con_send(struct ceph_connection *con, struct ceph_msg *msg) { - if (test_bit(CLOSED, &con->state)) { - dout("con_send %p closed, dropping %p\n", con, msg); - ceph_msg_put(msg); - return; - } - /* set src+dst */ msg->hdr.src = con->msgr->inst.name; - BUG_ON(msg->front.iov_len != le32_to_cpu(msg->hdr.front_len)); - msg->needs_out_seq = true; - /* queue */ mutex_lock(&con->mutex); + + if (con->state == CON_STATE_CLOSED) { + dout("con_send %p closed, dropping %p\n", con, msg); + ceph_msg_put(msg); + mutex_unlock(&con->mutex); + return; + } + + 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, @@ -2339,12 +2943,13 @@ void ceph_con_send(struct ceph_connection *con, struct ceph_msg *msg) le32_to_cpu(msg->hdr.front_len), le32_to_cpu(msg->hdr.middle_len), le32_to_cpu(msg->hdr.data_len)); + + clear_standby(con); mutex_unlock(&con->mutex); /* 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 (con_flag_test_and_set(con, CON_FLAG_WRITE_PENDING) == 0) queue_con(con); } EXPORT_SYMBOL(ceph_con_send); @@ -2352,24 +2957,34 @@ 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); } @@ -2377,17 +2992,27 @@ void ceph_con_revoke(struct ceph_connection *con, struct ceph_msg *msg) /* * 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 - @@ -2398,8 +3023,8 @@ void ceph_con_revoke_message(struct ceph_connection *con, struct ceph_msg *msg) 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); } @@ -2410,13 +3035,97 @@ void ceph_con_revoke_message(struct ceph_connection *con, struct ceph_msg *msg) void ceph_con_keepalive(struct ceph_connection *con) { dout("con_keepalive %p\n", con); + mutex_lock(&con->mutex); clear_standby(con); - if (test_and_set_bit(KEEPALIVE_PENDING, &con->state) == 0 && - test_and_set_bit(WRITE_PENDING, &con->state) == 0) + mutex_unlock(&con->mutex); + if (con_flag_test_and_set(con, CON_FLAG_KEEPALIVE_PENDING) == 0 && + con_flag_test_and_set(con, CON_FLAG_WRITE_PENDING) == 0) queue_con(con); } EXPORT_SYMBOL(ceph_con_keepalive); +static struct ceph_msg_data *ceph_msg_data_create(enum ceph_msg_data_type type) +{ + struct ceph_msg_data *data; + + if (WARN_ON(!ceph_msg_data_type_valid(type))) + return NULL; + + data = kmem_cache_zalloc(ceph_msg_data_cache, GFP_NOFS); + if (data) + data->type = type; + INIT_LIST_HEAD(&data->links); + + return data; +} + +static void ceph_msg_data_destroy(struct ceph_msg_data *data) +{ + if (!data) + return; + + WARN_ON(!list_empty(&data->links)); + if (data->type == CEPH_MSG_DATA_PAGELIST) { + ceph_pagelist_release(data->pagelist); + kfree(data->pagelist); + } + kmem_cache_free(ceph_msg_data_cache, data); +} + +void ceph_msg_data_add_pages(struct ceph_msg *msg, struct page **pages, + size_t length, size_t alignment) +{ + struct ceph_msg_data *data; + + BUG_ON(!pages); + BUG_ON(!length); + + data = ceph_msg_data_create(CEPH_MSG_DATA_PAGES); + BUG_ON(!data); + data->pages = pages; + data->length = length; + data->alignment = alignment & ~PAGE_MASK; + + list_add_tail(&data->links, &msg->data); + msg->data_length += length; +} +EXPORT_SYMBOL(ceph_msg_data_add_pages); + +void ceph_msg_data_add_pagelist(struct ceph_msg *msg, + struct ceph_pagelist *pagelist) +{ + struct ceph_msg_data *data; + + BUG_ON(!pagelist); + BUG_ON(!pagelist->length); + + data = ceph_msg_data_create(CEPH_MSG_DATA_PAGELIST); + BUG_ON(!data); + data->pagelist = pagelist; + + list_add_tail(&data->links, &msg->data); + msg->data_length += pagelist->length; +} +EXPORT_SYMBOL(ceph_msg_data_add_pagelist); + +#ifdef CONFIG_BLOCK +void ceph_msg_data_add_bio(struct ceph_msg *msg, struct bio *bio, + size_t length) +{ + struct ceph_msg_data *data; + + BUG_ON(!bio); + + data = ceph_msg_data_create(CEPH_MSG_DATA_BIO); + BUG_ON(!data); + data->bio = bio; + data->bio_length = length; + + list_add_tail(&data->links, &msg->data); + msg->data_length += length; +} +EXPORT_SYMBOL(ceph_msg_data_add_bio); +#endif /* CONFIG_BLOCK */ /* * construct a new message with given type, size @@ -2427,53 +3136,21 @@ struct ceph_msg *ceph_msg_new(int type, int front_len, gfp_t flags, { struct ceph_msg *m; - m = kmalloc(sizeof(*m), flags); + m = kmem_cache_zalloc(ceph_msg_cache, flags); if (m == NULL) goto out; - kref_init(&m->kref); - INIT_LIST_HEAD(&m->list_head); - m->hdr.tid = 0; m->hdr.type = cpu_to_le16(type); m->hdr.priority = cpu_to_le16(CEPH_MSG_PRIO_DEFAULT); - m->hdr.version = 0; m->hdr.front_len = cpu_to_le32(front_len); - m->hdr.middle_len = 0; - m->hdr.data_len = 0; - m->hdr.data_off = 0; - m->hdr.reserved = 0; - m->footer.front_crc = 0; - m->footer.middle_crc = 0; - m->footer.data_crc = 0; - m->footer.flags = 0; - m->front_max = front_len; - m->front_is_vmalloc = false; - m->more_to_follow = false; - m->ack_stamp = 0; - m->pool = NULL; - /* middle */ - m->middle = NULL; - - /* data */ - m->nr_pages = 0; - m->page_alignment = 0; - m->pages = NULL; - m->pagelist = NULL; - m->bio = NULL; - m->bio_iter = NULL; - m->bio_seg = 0; - m->trail = NULL; + INIT_LIST_HEAD(&m->list_head); + kref_init(&m->kref); + INIT_LIST_HEAD(&m->data); /* front */ if (front_len) { - if (front_len > PAGE_CACHE_SIZE) { - m->front.iov_base = __vmalloc(front_len, flags, - PAGE_KERNEL); - m->front_is_vmalloc = true; - } else { - m->front.iov_base = kmalloc(front_len, flags); - } + m->front.iov_base = ceph_kvmalloc(front_len, flags); if (m->front.iov_base == NULL) { dout("ceph_msg_new can't allocate %d bytes\n", front_len); @@ -2482,7 +3159,7 @@ struct ceph_msg *ceph_msg_new(int type, int front_len, gfp_t flags, } else { m->front.iov_base = NULL; } - m->front.iov_len = front_len; + m->front_alloc_len = m->front.iov_len = front_len; dout("ceph_msg_new %p front %d\n", m, front_len); return m; @@ -2526,46 +3203,66 @@ static int ceph_alloc_middle(struct ceph_connection *con, struct ceph_msg *msg) } /* - * 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 0 on success, or a negative error code. + * + * On success, if we set *skip = 1: + * - the next message should be skipped and ignored. + * - con->in_msg == NULL + * or if we set *skip = 0: + * - con->in_msg is non-null. + * On error (ENOMEM, EAGAIN, ...), + * - con->in_msg == NULL */ -static struct ceph_msg *ceph_alloc_msg(struct ceph_connection *con, - struct ceph_msg_header *hdr, - int *skip) +static int ceph_con_in_msg_alloc(struct ceph_connection *con, int *skip) { - int type = le16_to_cpu(hdr->type); - int front_len = le32_to_cpu(hdr->front_len); + struct ceph_msg_header *hdr = &con->in_hdr; int middle_len = le32_to_cpu(hdr->middle_len); - struct ceph_msg *msg = NULL; - int ret; + struct ceph_msg *msg; + int ret = 0; - if (con->ops->alloc_msg) { - mutex_unlock(&con->mutex); - msg = con->ops->alloc_msg(con, hdr, skip); - mutex_lock(&con->mutex); - if (!msg || *skip) - return NULL; - } - if (!msg) { - *skip = 0; - msg = ceph_msg_new(type, front_len, GFP_NOFS, false); - if (!msg) { - pr_err("unable to allocate msg type %d len %d\n", - type, front_len); - return NULL; - } - msg->page_alignment = le16_to_cpu(hdr->data_off); + BUG_ON(con->in_msg != NULL); + BUG_ON(!con->ops->alloc_msg); + + mutex_unlock(&con->mutex); + msg = con->ops->alloc_msg(con, hdr, skip); + mutex_lock(&con->mutex); + if (con->state != CON_STATE_OPEN) { + if (msg) + ceph_msg_put(msg); + return -EAGAIN; } - memcpy(&msg->hdr, &con->in_hdr, sizeof(con->in_hdr)); + if (msg) { + BUG_ON(*skip); + con->in_msg = msg; + con->in_msg->con = con->ops->get(con); + BUG_ON(con->in_msg->con == NULL); + } else { + /* + * Null message pointer means either we should skip + * this message or we couldn't allocate memory. The + * former is not an error. + */ + if (*skip) + return 0; + con->error_msg = "error allocating memory for incoming message"; - if (middle_len && !msg->middle) { - ret = ceph_alloc_middle(con, msg); + return -ENOMEM; + } + memcpy(&con->in_msg->hdr, &con->in_hdr, sizeof(con->in_hdr)); + + 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 ret; } @@ -2575,11 +3272,8 @@ static struct ceph_msg *ceph_alloc_msg(struct ceph_connection *con, void ceph_msg_kfree(struct ceph_msg *m) { dout("msg_kfree %p\n", m); - if (m->front_is_vmalloc) - vfree(m->front.iov_base); - else - kfree(m->front.iov_base); - kfree(m); + ceph_kvfree(m->front.iov_base); + kmem_cache_free(ceph_msg_cache, m); } /* @@ -2588,6 +3282,9 @@ void ceph_msg_kfree(struct ceph_msg *m) void ceph_msg_last_put(struct kref *kref) { struct ceph_msg *m = container_of(kref, struct ceph_msg, kref); + LIST_HEAD(data); + struct list_head *links; + struct list_head *next; dout("ceph_msg_put last one on %p\n", m); WARN_ON(!list_empty(&m->list_head)); @@ -2597,16 +3294,16 @@ void ceph_msg_last_put(struct kref *kref) ceph_buffer_put(m->middle); m->middle = NULL; } - m->nr_pages = 0; - m->pages = NULL; - if (m->pagelist) { - ceph_pagelist_release(m->pagelist); - kfree(m->pagelist); - m->pagelist = NULL; - } + list_splice_init(&m->data, &data); + list_for_each_safe(links, next, &data) { + struct ceph_msg_data *data; - m->trail = NULL; + data = list_entry(links, struct ceph_msg_data, links); + list_del_init(links); + ceph_msg_data_destroy(data); + } + m->data_length = 0; if (m->pool) ceph_msgpool_put(m->pool, m); @@ -2617,8 +3314,8 @@ EXPORT_SYMBOL(ceph_msg_last_put); void ceph_msg_dump(struct ceph_msg *msg) { - pr_debug("msg_dump %p (front_max %d nr_pages %d)\n", msg, - msg->front_max, msg->nr_pages); + pr_debug("msg_dump %p (front_alloc_len %d length %zd)\n", msg, + msg->front_alloc_len, msg->data_length); print_hex_dump(KERN_DEBUG, "header: ", DUMP_PREFIX_OFFSET, 16, 1, &msg->hdr, sizeof(msg->hdr), true); |