diff options
Diffstat (limited to 'net/ceph')
-rw-r--r-- | net/ceph/ceph_common.c | 26 | ||||
-rw-r--r-- | net/ceph/crush/mapper.c | 13 | ||||
-rw-r--r-- | net/ceph/crypto.c | 1 | ||||
-rw-r--r-- | net/ceph/crypto.h | 3 | ||||
-rw-r--r-- | net/ceph/debugfs.c | 4 | ||||
-rw-r--r-- | net/ceph/messenger.c | 932 | ||||
-rw-r--r-- | net/ceph/mon_client.c | 127 | ||||
-rw-r--r-- | net/ceph/msgpool.c | 7 | ||||
-rw-r--r-- | net/ceph/osd_client.c | 77 | ||||
-rw-r--r-- | net/ceph/osdmap.c | 59 | ||||
-rw-r--r-- | net/ceph/pagelist.c | 14 |
11 files changed, 801 insertions, 462 deletions
diff --git a/net/ceph/ceph_common.c b/net/ceph/ceph_common.c index ba4323bce0e9..a8020293f342 100644 --- a/net/ceph/ceph_common.c +++ b/net/ceph/ceph_common.c @@ -17,6 +17,7 @@ #include <linux/string.h> +#include <linux/ceph/ceph_features.h> #include <linux/ceph/libceph.h> #include <linux/ceph/debugfs.h> #include <linux/ceph/decode.h> @@ -83,7 +84,6 @@ int ceph_check_fsid(struct ceph_client *client, struct ceph_fsid *fsid) return -1; } } else { - pr_info("client%lld fsid %pU\n", ceph_client_id(client), fsid); memcpy(&client->fsid, fsid, sizeof(*fsid)); } return 0; @@ -460,27 +460,23 @@ struct ceph_client *ceph_create_client(struct ceph_options *opt, void *private, client->auth_err = 0; client->extra_mon_dispatch = NULL; - client->supported_features = CEPH_FEATURE_SUPPORTED_DEFAULT | + client->supported_features = CEPH_FEATURES_SUPPORTED_DEFAULT | supported_features; - client->required_features = CEPH_FEATURE_REQUIRED_DEFAULT | + client->required_features = CEPH_FEATURES_REQUIRED_DEFAULT | required_features; /* msgr */ if (ceph_test_opt(client, MYIP)) myaddr = &client->options->my_addr; - client->msgr = ceph_messenger_create(myaddr, - client->supported_features, - client->required_features); - if (IS_ERR(client->msgr)) { - err = PTR_ERR(client->msgr); - goto fail; - } - client->msgr->nocrc = ceph_test_opt(client, NOCRC); + ceph_messenger_init(&client->msgr, myaddr, + client->supported_features, + client->required_features, + ceph_test_opt(client, NOCRC)); /* subsystems */ err = ceph_monc_init(&client->monc, client); if (err < 0) - goto fail_msgr; + goto fail; err = ceph_osdc_init(&client->osdc, client); if (err < 0) goto fail_monc; @@ -489,8 +485,6 @@ struct ceph_client *ceph_create_client(struct ceph_options *opt, void *private, fail_monc: ceph_monc_stop(&client->monc); -fail_msgr: - ceph_messenger_destroy(client->msgr); fail: kfree(client); return ERR_PTR(err); @@ -501,6 +495,8 @@ void ceph_destroy_client(struct ceph_client *client) { dout("destroy_client %p\n", client); + atomic_set(&client->msgr.stopping, 1); + /* unmount */ ceph_osdc_stop(&client->osdc); @@ -508,8 +504,6 @@ void ceph_destroy_client(struct ceph_client *client) ceph_debugfs_client_cleanup(client); - ceph_messenger_destroy(client->msgr); - ceph_destroy_options(client->options); kfree(client); diff --git a/net/ceph/crush/mapper.c b/net/ceph/crush/mapper.c index d7edc24333b8..35fce755ce10 100644 --- a/net/ceph/crush/mapper.c +++ b/net/ceph/crush/mapper.c @@ -306,7 +306,6 @@ static int crush_choose(const struct crush_map *map, int item = 0; int itemtype; int collide, reject; - const unsigned int orig_tries = 5; /* attempts before we fall back to search */ dprintk("CHOOSE%s bucket %d x %d outpos %d numrep %d\n", recurse_to_leaf ? "_LEAF" : "", bucket->id, x, outpos, numrep); @@ -351,8 +350,9 @@ static int crush_choose(const struct crush_map *map, reject = 1; goto reject; } - if (flocal >= (in->size>>1) && - flocal > orig_tries) + if (map->choose_local_fallback_tries > 0 && + flocal >= (in->size>>1) && + flocal > map->choose_local_fallback_tries) item = bucket_perm_choose(in, x, r); else item = crush_bucket_choose(in, x, r); @@ -422,13 +422,14 @@ reject: ftotal++; flocal++; - if (collide && flocal < 3) + if (collide && flocal <= map->choose_local_tries) /* retry locally a few times */ retry_bucket = 1; - else if (flocal <= in->size + orig_tries) + else if (map->choose_local_fallback_tries > 0 && + flocal <= in->size + map->choose_local_fallback_tries) /* exhaustive bucket search */ retry_bucket = 1; - else if (ftotal < 20) + else if (ftotal <= map->choose_total_tries) /* then retry descent */ retry_descent = 1; else diff --git a/net/ceph/crypto.c b/net/ceph/crypto.c index b780cb7947dd..9da7fdd3cd8a 100644 --- a/net/ceph/crypto.c +++ b/net/ceph/crypto.c @@ -466,6 +466,7 @@ void ceph_key_destroy(struct key *key) { struct ceph_crypto_key *ckey = key->payload.data; ceph_crypto_key_destroy(ckey); + kfree(ckey); } struct key_type key_type_ceph = { diff --git a/net/ceph/crypto.h b/net/ceph/crypto.h index 1919d1550d75..3572dc518bc9 100644 --- a/net/ceph/crypto.h +++ b/net/ceph/crypto.h @@ -16,7 +16,8 @@ struct ceph_crypto_key { static inline void ceph_crypto_key_destroy(struct ceph_crypto_key *key) { - kfree(key->key); + if (key) + kfree(key->key); } extern int ceph_crypto_key_clone(struct ceph_crypto_key *dst, diff --git a/net/ceph/debugfs.c b/net/ceph/debugfs.c index 54b531a01121..38b5dc1823d4 100644 --- a/net/ceph/debugfs.c +++ b/net/ceph/debugfs.c @@ -189,6 +189,9 @@ int ceph_debugfs_client_init(struct ceph_client *client) snprintf(name, sizeof(name), "%pU.client%lld", &client->fsid, client->monc.auth->global_id); + dout("ceph_debugfs_client_init %p %s\n", client, name); + + BUG_ON(client->debugfs_dir); client->debugfs_dir = debugfs_create_dir(name, ceph_debugfs_dir); if (!client->debugfs_dir) goto out; @@ -234,6 +237,7 @@ out: void ceph_debugfs_client_cleanup(struct ceph_client *client) { + dout("ceph_debugfs_client_cleanup %p\n", client); debugfs_remove(client->debugfs_osdmap); debugfs_remove(client->debugfs_monmap); debugfs_remove(client->osdc.debugfs_file); diff --git a/net/ceph/messenger.c b/net/ceph/messenger.c index 10255e81be79..24c5eea8c45b 100644 --- a/net/ceph/messenger.c +++ b/net/ceph/messenger.c @@ -29,6 +29,74 @@ * 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 tag bytes (protocol control messages) */ static char tag_msg = CEPH_MSGR_TAG_MSG; static char tag_ack = CEPH_MSGR_TAG_ACK; @@ -147,72 +215,130 @@ 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, int count_unused) { 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 (test_bit(CON_FLAG_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)) - 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); + set_bit(CON_FLAG_SOCK_CLOSED, &con->flags); + 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 +354,9 @@ 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 +388,7 @@ 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 +404,6 @@ static int ceph_tcp_connect(struct ceph_connection *con) return ret; } con->sock = sock; - return 0; } @@ -333,16 +459,24 @@ static int ceph_tcp_sendpage(struct socket *sock, struct page *page, */ 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. + */ + clear_bit(CON_FLAG_SOCK_CLOSED, &con->flags); + + con_sock_state_closed(con); return rc; } @@ -353,6 +487,10 @@ 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) @@ -372,8 +510,11 @@ static void reset_connection(struct ceph_connection *con) 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 +532,44 @@ 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; + + clear_bit(CON_FLAG_LOSSYTX, &con->flags); /* so we retry next connect */ + clear_bit(CON_FLAG_KEEPALIVE_PENDING, &con->flags); + clear_bit(CON_FLAG_WRITE_PENDING, &con->flags); + clear_bit(CON_FLAG_KEEPALIVE_PENDING, &con->flags); + clear_bit(CON_FLAG_BACKOFF, &con->flags); + 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); + + BUG_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 +583,26 @@ 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 +623,14 @@ 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 +644,53 @@ static void ceph_con_out_kvec_add(struct ceph_connection *con, con->out_kvec_bytes += size; } +#ifdef CONFIG_BLOCK +static void init_bio_iter(struct bio *bio, struct bio **iter, int *seg) +{ + if (!bio) { + *iter = NULL; + *seg = 0; + return; + } + *iter = bio; + *seg = bio->bi_idx; +} + +static void iter_bio_next(struct bio **bio_iter, int *seg) +{ + if (*bio_iter == NULL) + return; + + BUG_ON(*seg >= (*bio_iter)->bi_vcnt); + + (*seg)++; + if (*seg == (*bio_iter)->bi_vcnt) + init_bio_iter((*bio_iter)->bi_next, bio_iter, seg); +} +#endif + +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; +#ifdef CONFIG_BLOCK + if (msg->bio) + init_bio_iter(msg->bio, &msg->bio_iter, &msg->bio_seg); +#endif + 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. @@ -516,6 +700,8 @@ 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 +720,7 @@ 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 +728,16 @@ 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); @@ -576,18 +764,18 @@ static void prepare_write_message(struct ceph_connection *con) 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 +785,19 @@ 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_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(CON_FLAG_WRITE_PENDING, &con->flags); } /* @@ -630,16 +809,16 @@ 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); + set_bit(CON_FLAG_WRITE_PENDING, &con->flags); } /* @@ -648,9 +827,9 @@ 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); + set_bit(CON_FLAG_WRITE_PENDING, &con->flags); } /* @@ -665,27 +844,21 @@ 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 +867,12 @@ 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); + set_bit(CON_FLAG_WRITE_PENDING, &con->flags); } static int prepare_write_connect(struct ceph_connection *con) @@ -742,14 +915,14 @@ 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); + set_bit(CON_FLAG_WRITE_PENDING, &con->flags); return 0; } @@ -797,30 +970,34 @@ out: return ret; /* done! */ } -#ifdef CONFIG_BLOCK -static void init_bio_iter(struct bio *bio, struct bio **iter, int *seg) +static void out_msg_pos_next(struct ceph_connection *con, struct page *page, + size_t len, size_t sent, bool in_trail) { - if (!bio) { - *iter = NULL; - *seg = 0; - return; - } - *iter = bio; - *seg = bio->bi_idx; -} + struct ceph_msg *msg = con->out_msg; -static void iter_bio_next(struct bio **bio_iter, int *seg) -{ - if (*bio_iter == NULL) - return; + BUG_ON(!msg); + BUG_ON(!sent); - BUG_ON(*seg >= (*bio_iter)->bi_vcnt); + con->out_msg_pos.data_pos += sent; + con->out_msg_pos.page_pos += sent; + if (sent < len) + return; - (*seg)++; - if (*seg == (*bio_iter)->bi_vcnt) - init_bio_iter((*bio_iter)->bi_next, bio_iter, seg); -} + BUG_ON(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 @@ -837,41 +1014,36 @@ static int write_partial_msg_pages(struct ceph_connection *con) 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); + bool in_trail = false; + const size_t trail_len = (msg->trail ? msg->trail->length : 0); + const size_t trail_off = data_len - trail_len; 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 - if (msg->bio && !msg->bio_iter) - init_bio_iter(msg->bio, &msg->bio_iter, &msg->bio_seg); -#endif - + /* + * 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. + */ 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; + in_trail = in_trail || con->out_msg_pos.data_pos >= trail_off; + if (!in_trail) + total_max_write = trail_off - con->out_msg_pos.data_pos; + if (in_trail) { 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) { @@ -894,15 +1066,14 @@ static int write_partial_msg_pages(struct ceph_connection *con) 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 crc = 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); + crc = crc32c(crc, base, len); + msg->footer.data_crc = cpu_to_le32(crc); con->out_msg_pos.did_page_crc = true; } ret = ceph_tcp_sendpage(con->sock, page, @@ -915,31 +1086,15 @@ static int write_partial_msg_pages(struct ceph_connection *con) 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: @@ -1351,20 +1506,14 @@ 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); + BUG_ON(con->state != CON_STATE_NEGOTIATING); + con->state = CON_STATE_CLOSED; } static int process_connect(struct ceph_connection *con) @@ -1407,7 +1556,7 @@ static int process_connect(struct ceph_connection *con) 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; @@ -1428,7 +1577,7 @@ static int process_connect(struct ceph_connection *con) 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 +1589,7 @@ 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; @@ -1454,7 +1602,7 @@ static int process_connect(struct ceph_connection *con) le32_to_cpu(con->out_connect.connect_seq), le32_to_cpu(con->in_reply.connect_seq)); con->connect_seq = le32_to_cpu(con->in_reply.connect_seq); - ceph_con_out_kvec_reset(con); + con_out_kvec_reset(con); ret = prepare_write_connect(con); if (ret < 0) return ret; @@ -1471,7 +1619,7 @@ static int process_connect(struct ceph_connection *con) le32_to_cpu(con->in_reply.global_seq)); get_global_seq(con->msgr, le32_to_cpu(con->in_reply.global_seq)); - ceph_con_out_kvec_reset(con); + con_out_kvec_reset(con); ret = prepare_write_connect(con); if (ret < 0) return ret; @@ -1489,7 +1637,10 @@ static int process_connect(struct ceph_connection *con) fail_protocol(con); return -1; } - clear_bit(CONNECTING, &con->state); + + BUG_ON(con->state != CON_STATE_NEGOTIATING); + con->state = CON_STATE_OPEN; + con->peer_global_seq = le32_to_cpu(con->in_reply.global_seq); con->connect_seq++; con->peer_features = server_feat; @@ -1501,7 +1652,9 @@ 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); + set_bit(CON_FLAG_LOSSYTX, &con->flags); + + con->delay = 0; /* reset backoff memory */ prepare_read_tag(con); break; @@ -1587,10 +1740,7 @@ 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 ceph_con_in_msg_alloc(struct ceph_connection *con, int *skip); static int read_partial_message_pages(struct ceph_connection *con, struct page **pages, @@ -1633,9 +1783,6 @@ static int read_partial_message_bio(struct ceph_connection *con, void *p; int ret, left; - if (IS_ERR(bv)) - return PTR_ERR(bv); - left = min((int)(data_len - con->in_msg_pos.data_pos), (int)(bv->bv_len - con->in_msg_pos.page_pos)); @@ -1672,7 +1819,6 @@ 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; @@ -1723,10 +1869,13 @@ 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); + ret = ceph_con_in_msg_alloc(con, &skip); + if (ret < 0) + return ret; if (skip) { /* skip this message */ dout("alloc_msg said skip message\n"); @@ -1737,11 +1886,9 @@ static int read_partial_message(struct ceph_connection *con) 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) @@ -1753,6 +1900,11 @@ static int read_partial_message(struct ceph_connection *con) else con->in_msg_pos.page_pos = 0; con->in_msg_pos.data_pos = 0; + +#ifdef CONFIG_BLOCK + if (m->bio) + init_bio_iter(m->bio, &m->bio_iter, &m->bio_seg); +#endif } /* front */ @@ -1769,10 +1921,6 @@ 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) { @@ -1783,7 +1931,7 @@ static int read_partial_message(struct ceph_connection *con) return ret; #ifdef CONFIG_BLOCK } else if (m->bio) { - + BUG_ON(!m->bio_iter); ret = read_partial_message_bio(con, &m->bio_iter, &m->bio_seg, data_len, do_datacrc); @@ -1837,8 +1985,11 @@ 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 +2009,6 @@ static void process_message(struct ceph_connection *con) con->ops->dispatch(con, msg); mutex_lock(&con->mutex); - prepare_read_tag(con); } @@ -1870,22 +2020,19 @@ 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; @@ -1932,7 +2079,7 @@ more_kvec: } 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 +2089,15 @@ do_next: prepare_write_ack(con); goto more; } - if (test_and_clear_bit(KEEPALIVE_PENDING, &con->state)) { + if (test_and_clear_bit(CON_FLAG_KEEPALIVE_PENDING, + &con->flags)) { prepare_write_keepalive(con); goto more; } } /* Nothing to do! */ - clear_bit(WRITE_PENDING, &con->state); + clear_bit(CON_FLAG_WRITE_PENDING, &con->flags); dout("try_write nothing else to write.\n"); ret = 0; out: @@ -1966,38 +2114,46 @@ 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; + + BUG_ON(con->state != CON_STATE_CONNECTING); + 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 +2163,8 @@ more: goto more; } + BUG_ON(con->state != CON_STATE_OPEN); + if (con->in_base_pos < 0) { /* * skipping + discarding content. @@ -2040,7 +2198,8 @@ 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; @@ -2063,6 +2222,8 @@ 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) { @@ -2091,12 +2252,6 @@ bad_tag: */ 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; @@ -2121,7 +2276,26 @@ static void con_work(struct work_struct *work) mutex_lock(&con->mutex); restart: - if (test_and_clear_bit(BACKOFF, &con->state)) { + if (test_and_clear_bit(CON_FLAG_SOCK_CLOSED, &con->flags)) { + switch (con->state) { + case CON_STATE_CONNECTING: + con->error_msg = "connection failed"; + break; + case CON_STATE_NEGOTIATING: + con->error_msg = "negotiation failed"; + break; + case CON_STATE_OPEN: + con->error_msg = "socket closed"; + break; + default: + dout("unrecognized con state %d\n", (int)con->state); + con->error_msg = "unrecognized con state"; + BUG(); + } + goto fault; + } + + if (test_and_clear_bit(CON_FLAG_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))) { @@ -2135,35 +2309,35 @@ restart: } } - if (test_bit(STANDBY, &con->state)) { + if (con->state == CON_STATE_STANDBY) { 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); + if (con->state == CON_STATE_CLOSED) { + dout("con_work %p CLOSED\n", con); + BUG_ON(con->sock); goto done; } - if (test_and_clear_bit(OPENING, &con->state)) { - /* reopen w/ new peer */ + if (con->state == CON_STATE_PREOPEN) { dout("con_work OPENING\n"); - con_close_socket(con); + BUG_ON(con->sock); } - if (test_and_clear_bit(SOCK_CLOSED, &con->state)) - goto fault; - ret = try_read(con); if (ret == -EAGAIN) goto restart; - if (ret < 0) + if (ret < 0) { + con->error_msg = "socket error on read"; goto fault; + } ret = try_write(con); if (ret == -EAGAIN) goto restart; - if (ret < 0) + if (ret < 0) { + con->error_msg = "socket error on write"; goto fault; + } done: mutex_unlock(&con->mutex); @@ -2172,7 +2346,6 @@ done_unlocked: return; fault: - mutex_unlock(&con->mutex); ceph_fault(con); /* error/fault path */ goto done_unlocked; } @@ -2183,26 +2356,31 @@ fault: * exponential backoff */ static void ceph_fault(struct ceph_connection *con) + __releases(con->mutex) { pr_err("%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; + BUG_ON(con->state != CON_STATE_CONNECTING && + con->state != CON_STATE_NEGOTIATING && + con->state != CON_STATE_OPEN); con_close_socket(con); + if (test_bit(CON_FLAG_LOSSYTX, &con->flags)) { + dout("fault on LOSSYTX channel, marking CLOSED\n"); + con->state = CON_STATE_CLOSED; + goto out_unlock; + } + 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 */ @@ -2211,12 +2389,13 @@ 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)) { + !test_bit(CON_FLAG_KEEPALIVE_PENDING, &con->flags)) { dout("fault %p setting STANDBY clearing WRITE_PENDING\n", con); - clear_bit(WRITE_PENDING, &con->state); - set_bit(STANDBY, &con->state); + clear_bit(CON_FLAG_WRITE_PENDING, &con->flags); + 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) @@ -2237,13 +2416,12 @@ static void ceph_fault(struct ceph_connection *con) * that when con_work restarts we schedule the * delay then. */ - set_bit(BACKOFF, &con->state); + set_bit(CON_FLAG_BACKOFF, &con->flags); } } 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. @@ -2260,18 +2438,14 @@ out: /* - * 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; @@ -2284,30 +2458,23 @@ 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(test_bit(CON_FLAG_WRITE_PENDING, &con->flags)); + WARN_ON(test_bit(CON_FLAG_KEEPALIVE_PENDING, &con->flags)); } } @@ -2316,21 +2483,24 @@ 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 +2509,13 @@ 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 (test_and_set_bit(CON_FLAG_WRITE_PENDING, &con->flags) == 0) queue_con(con); } EXPORT_SYMBOL(ceph_con_send); @@ -2352,24 +2523,34 @@ 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 +2558,27 @@ 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 +2589,8 @@ 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); } @@ -2410,9 +2601,11 @@ 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 (test_and_set_bit(CON_FLAG_KEEPALIVE_PENDING, &con->flags) == 0 && + test_and_set_bit(CON_FLAG_WRITE_PENDING, &con->flags) == 0) queue_con(con); } EXPORT_SYMBOL(ceph_con_keepalive); @@ -2431,6 +2624,8 @@ struct ceph_msg *ceph_msg_new(int type, int front_len, gfp_t flags, if (m == NULL) goto out; kref_init(&m->kref); + + m->con = NULL; INIT_LIST_HEAD(&m->list_head); m->hdr.tid = 0; @@ -2526,46 +2721,77 @@ 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) { + struct ceph_msg_header *hdr = &con->in_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; + int ret = 0; + + BUG_ON(con->in_msg != NULL); if (con->ops->alloc_msg) { + struct ceph_msg *msg; + mutex_unlock(&con->mutex); msg = con->ops->alloc_msg(con, hdr, skip); mutex_lock(&con->mutex); - if (!msg || *skip) - return NULL; + if (con->state != CON_STATE_OPEN) { + ceph_msg_put(msg); + return -EAGAIN; + } + con->in_msg = msg; + 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; + return 0; + } + if (!con->in_msg) { + con->error_msg = + "error allocating memory for incoming message"; + return -ENOMEM; + } } - 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 -ENOMEM; } - 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 ret; } diff --git a/net/ceph/mon_client.c b/net/ceph/mon_client.c index d0649a9655be..900ea0f043fc 100644 --- a/net/ceph/mon_client.c +++ b/net/ceph/mon_client.c @@ -106,9 +106,9 @@ static void __send_prepared_auth_request(struct ceph_mon_client *monc, int len) monc->pending_auth = 1; monc->m_auth->front.iov_len = len; monc->m_auth->hdr.front_len = cpu_to_le32(len); - ceph_con_revoke(monc->con, monc->m_auth); + ceph_msg_revoke(monc->m_auth); ceph_msg_get(monc->m_auth); /* keep our ref */ - ceph_con_send(monc->con, monc->m_auth); + ceph_con_send(&monc->con, monc->m_auth); } /* @@ -117,8 +117,11 @@ static void __send_prepared_auth_request(struct ceph_mon_client *monc, int len) static void __close_session(struct ceph_mon_client *monc) { dout("__close_session closing mon%d\n", monc->cur_mon); - ceph_con_revoke(monc->con, monc->m_auth); - ceph_con_close(monc->con); + ceph_msg_revoke(monc->m_auth); + ceph_msg_revoke_incoming(monc->m_auth_reply); + ceph_msg_revoke(monc->m_subscribe); + ceph_msg_revoke_incoming(monc->m_subscribe_ack); + ceph_con_close(&monc->con); monc->cur_mon = -1; monc->pending_auth = 0; ceph_auth_reset(monc->auth); @@ -142,9 +145,8 @@ static int __open_session(struct ceph_mon_client *monc) monc->want_next_osdmap = !!monc->want_next_osdmap; dout("open_session mon%d opening\n", monc->cur_mon); - monc->con->peer_name.type = CEPH_ENTITY_TYPE_MON; - monc->con->peer_name.num = cpu_to_le64(monc->cur_mon); - ceph_con_open(monc->con, + ceph_con_open(&monc->con, + CEPH_ENTITY_TYPE_MON, monc->cur_mon, &monc->monmap->mon_inst[monc->cur_mon].addr); /* initiatiate authentication handshake */ @@ -226,8 +228,8 @@ static void __send_subscribe(struct ceph_mon_client *monc) msg->front.iov_len = p - msg->front.iov_base; msg->hdr.front_len = cpu_to_le32(msg->front.iov_len); - ceph_con_revoke(monc->con, msg); - ceph_con_send(monc->con, ceph_msg_get(msg)); + ceph_msg_revoke(msg); + ceph_con_send(&monc->con, ceph_msg_get(msg)); monc->sub_sent = jiffies | 1; /* never 0 */ } @@ -247,7 +249,7 @@ static void handle_subscribe_ack(struct ceph_mon_client *monc, if (monc->hunting) { pr_info("mon%d %s session established\n", monc->cur_mon, - ceph_pr_addr(&monc->con->peer_addr.in_addr)); + ceph_pr_addr(&monc->con.peer_addr.in_addr)); monc->hunting = false; } dout("handle_subscribe_ack after %d seconds\n", seconds); @@ -309,6 +311,17 @@ int ceph_monc_open_session(struct ceph_mon_client *monc) EXPORT_SYMBOL(ceph_monc_open_session); /* + * We require the fsid and global_id in order to initialize our + * debugfs dir. + */ +static bool have_debugfs_info(struct ceph_mon_client *monc) +{ + dout("have_debugfs_info fsid %d globalid %lld\n", + (int)monc->client->have_fsid, monc->auth->global_id); + return monc->client->have_fsid && monc->auth->global_id > 0; +} + +/* * The monitor responds with mount ack indicate mount success. The * included client ticket allows the client to talk to MDSs and OSDs. */ @@ -318,9 +331,12 @@ static void ceph_monc_handle_map(struct ceph_mon_client *monc, struct ceph_client *client = monc->client; struct ceph_monmap *monmap = NULL, *old = monc->monmap; void *p, *end; + int had_debugfs_info, init_debugfs = 0; mutex_lock(&monc->mutex); + had_debugfs_info = have_debugfs_info(monc); + dout("handle_monmap\n"); p = msg->front.iov_base; end = p + msg->front.iov_len; @@ -342,12 +358,22 @@ static void ceph_monc_handle_map(struct ceph_mon_client *monc, if (!client->have_fsid) { client->have_fsid = true; + if (!had_debugfs_info && have_debugfs_info(monc)) { + pr_info("client%lld fsid %pU\n", + ceph_client_id(monc->client), + &monc->client->fsid); + init_debugfs = 1; + } mutex_unlock(&monc->mutex); - /* - * do debugfs initialization without mutex to avoid - * creating a locking dependency - */ - ceph_debugfs_client_init(client); + + if (init_debugfs) { + /* + * do debugfs initialization without mutex to avoid + * creating a locking dependency + */ + ceph_debugfs_client_init(monc->client); + } + goto out_unlocked; } out: @@ -439,6 +465,7 @@ static struct ceph_msg *get_generic_reply(struct ceph_connection *con, m = NULL; } else { dout("get_generic_reply %lld got %p\n", tid, req->reply); + *skip = 0; m = ceph_msg_get(req->reply); /* * we don't need to track the connection reading into @@ -461,7 +488,7 @@ static int do_generic_request(struct ceph_mon_client *monc, req->request->hdr.tid = cpu_to_le64(req->tid); __insert_generic_request(monc, req); monc->num_generic_requests++; - ceph_con_send(monc->con, ceph_msg_get(req->request)); + ceph_con_send(&monc->con, ceph_msg_get(req->request)); mutex_unlock(&monc->mutex); err = wait_for_completion_interruptible(&req->completion); @@ -684,8 +711,9 @@ static void __resend_generic_request(struct ceph_mon_client *monc) for (p = rb_first(&monc->generic_request_tree); p; p = rb_next(p)) { req = rb_entry(p, struct ceph_mon_generic_request, node); - ceph_con_revoke(monc->con, req->request); - ceph_con_send(monc->con, ceph_msg_get(req->request)); + ceph_msg_revoke(req->request); + ceph_msg_revoke_incoming(req->reply); + ceph_con_send(&monc->con, ceph_msg_get(req->request)); } } @@ -705,7 +733,7 @@ static void delayed_work(struct work_struct *work) __close_session(monc); __open_session(monc); /* continue hunting */ } else { - ceph_con_keepalive(monc->con); + ceph_con_keepalive(&monc->con); __validate_auth(monc); @@ -760,19 +788,12 @@ int ceph_monc_init(struct ceph_mon_client *monc, struct ceph_client *cl) goto out; /* connection */ - monc->con = kmalloc(sizeof(*monc->con), GFP_KERNEL); - if (!monc->con) - goto out_monmap; - ceph_con_init(monc->client->msgr, monc->con); - monc->con->private = monc; - monc->con->ops = &mon_con_ops; - /* authentication */ monc->auth = ceph_auth_init(cl->options->name, cl->options->key); if (IS_ERR(monc->auth)) { err = PTR_ERR(monc->auth); - goto out_con; + goto out_monmap; } monc->auth->want_keys = CEPH_ENTITY_TYPE_AUTH | CEPH_ENTITY_TYPE_MON | @@ -801,6 +822,9 @@ int ceph_monc_init(struct ceph_mon_client *monc, struct ceph_client *cl) if (!monc->m_auth) goto out_auth_reply; + ceph_con_init(&monc->con, monc, &mon_con_ops, + &monc->client->msgr); + monc->cur_mon = -1; monc->hunting = true; monc->sub_renew_after = jiffies; @@ -824,8 +848,6 @@ out_subscribe_ack: ceph_msg_put(monc->m_subscribe_ack); out_auth: ceph_auth_destroy(monc->auth); -out_con: - monc->con->ops->put(monc->con); out_monmap: kfree(monc->monmap); out: @@ -841,10 +863,6 @@ void ceph_monc_stop(struct ceph_mon_client *monc) mutex_lock(&monc->mutex); __close_session(monc); - monc->con->private = NULL; - monc->con->ops->put(monc->con); - monc->con = NULL; - mutex_unlock(&monc->mutex); /* @@ -871,8 +889,10 @@ static void handle_auth_reply(struct ceph_mon_client *monc, { int ret; int was_auth = 0; + int had_debugfs_info, init_debugfs = 0; mutex_lock(&monc->mutex); + had_debugfs_info = have_debugfs_info(monc); if (monc->auth->ops) was_auth = monc->auth->ops->is_authenticated(monc->auth); monc->pending_auth = 0; @@ -888,14 +908,29 @@ static void handle_auth_reply(struct ceph_mon_client *monc, } else if (!was_auth && monc->auth->ops->is_authenticated(monc->auth)) { dout("authenticated, starting session\n"); - monc->client->msgr->inst.name.type = CEPH_ENTITY_TYPE_CLIENT; - monc->client->msgr->inst.name.num = + monc->client->msgr.inst.name.type = CEPH_ENTITY_TYPE_CLIENT; + monc->client->msgr.inst.name.num = cpu_to_le64(monc->auth->global_id); __send_subscribe(monc); __resend_generic_request(monc); } + + if (!had_debugfs_info && have_debugfs_info(monc)) { + pr_info("client%lld fsid %pU\n", + ceph_client_id(monc->client), + &monc->client->fsid); + init_debugfs = 1; + } mutex_unlock(&monc->mutex); + + if (init_debugfs) { + /* + * do debugfs initialization without mutex to avoid + * creating a locking dependency + */ + ceph_debugfs_client_init(monc->client); + } } static int __validate_auth(struct ceph_mon_client *monc) @@ -1000,6 +1035,8 @@ static struct ceph_msg *mon_alloc_msg(struct ceph_connection *con, case CEPH_MSG_MDS_MAP: case CEPH_MSG_OSD_MAP: m = ceph_msg_new(type, front_len, GFP_NOFS, false); + if (!m) + return NULL; /* ENOMEM--return skip == 0 */ break; } @@ -1029,7 +1066,7 @@ static void mon_fault(struct ceph_connection *con) if (!monc->hunting) pr_info("mon%d %s session lost, " "hunting for new mon\n", monc->cur_mon, - ceph_pr_addr(&monc->con->peer_addr.in_addr)); + ceph_pr_addr(&monc->con.peer_addr.in_addr)); __close_session(monc); if (!monc->hunting) { @@ -1044,9 +1081,23 @@ out: mutex_unlock(&monc->mutex); } +/* + * We can ignore refcounting on the connection struct, as all references + * will come from the messenger workqueue, which is drained prior to + * mon_client destruction. + */ +static struct ceph_connection *con_get(struct ceph_connection *con) +{ + return con; +} + +static void con_put(struct ceph_connection *con) +{ +} + static const struct ceph_connection_operations mon_con_ops = { - .get = ceph_con_get, - .put = ceph_con_put, + .get = con_get, + .put = con_put, .dispatch = dispatch, .fault = mon_fault, .alloc_msg = mon_alloc_msg, diff --git a/net/ceph/msgpool.c b/net/ceph/msgpool.c index 11d5f4196a73..ddec1c10ac80 100644 --- a/net/ceph/msgpool.c +++ b/net/ceph/msgpool.c @@ -12,7 +12,7 @@ static void *msgpool_alloc(gfp_t gfp_mask, void *arg) struct ceph_msgpool *pool = arg; struct ceph_msg *msg; - msg = ceph_msg_new(0, pool->front_len, gfp_mask, true); + msg = ceph_msg_new(pool->type, pool->front_len, gfp_mask, true); if (!msg) { dout("msgpool_alloc %s failed\n", pool->name); } else { @@ -32,10 +32,11 @@ static void msgpool_free(void *element, void *arg) ceph_msg_put(msg); } -int ceph_msgpool_init(struct ceph_msgpool *pool, +int ceph_msgpool_init(struct ceph_msgpool *pool, int type, int front_len, int size, bool blocking, const char *name) { dout("msgpool %s init\n", name); + pool->type = type; pool->front_len = front_len; pool->pool = mempool_create(size, msgpool_alloc, msgpool_free, pool); if (!pool->pool) @@ -61,7 +62,7 @@ struct ceph_msg *ceph_msgpool_get(struct ceph_msgpool *pool, WARN_ON(1); /* try to alloc a fresh message */ - return ceph_msg_new(0, front_len, GFP_NOFS, false); + return ceph_msg_new(pool->type, front_len, GFP_NOFS, false); } msg = mempool_alloc(pool->pool, GFP_NOFS); diff --git a/net/ceph/osd_client.c b/net/ceph/osd_client.c index ca59e66c9787..42119c05e82c 100644 --- a/net/ceph/osd_client.c +++ b/net/ceph/osd_client.c @@ -140,10 +140,9 @@ void ceph_osdc_release_request(struct kref *kref) if (req->r_request) ceph_msg_put(req->r_request); if (req->r_con_filling_msg) { - dout("release_request revoking pages %p from con %p\n", + dout("%s revoking pages %p from con %p\n", __func__, req->r_pages, req->r_con_filling_msg); - ceph_con_revoke_message(req->r_con_filling_msg, - req->r_reply); + ceph_msg_revoke_incoming(req->r_reply); req->r_con_filling_msg->ops->put(req->r_con_filling_msg); } if (req->r_reply) @@ -214,10 +213,13 @@ struct ceph_osd_request *ceph_osdc_alloc_request(struct ceph_osd_client *osdc, kref_init(&req->r_kref); init_completion(&req->r_completion); init_completion(&req->r_safe_completion); + rb_init_node(&req->r_node); INIT_LIST_HEAD(&req->r_unsafe_item); INIT_LIST_HEAD(&req->r_linger_item); INIT_LIST_HEAD(&req->r_linger_osd); INIT_LIST_HEAD(&req->r_req_lru_item); + INIT_LIST_HEAD(&req->r_osd_item); + req->r_flags = flags; WARN_ON((flags & (CEPH_OSD_FLAG_READ|CEPH_OSD_FLAG_WRITE)) == 0); @@ -243,6 +245,7 @@ struct ceph_osd_request *ceph_osdc_alloc_request(struct ceph_osd_client *osdc, } ceph_pagelist_init(req->r_trail); } + /* create request message; allow space for oid */ msg_size += MAX_OBJ_NAME_SIZE; if (snapc) @@ -256,7 +259,6 @@ struct ceph_osd_request *ceph_osdc_alloc_request(struct ceph_osd_client *osdc, return NULL; } - msg->hdr.type = cpu_to_le16(CEPH_MSG_OSD_OP); memset(msg->front.iov_base, 0, msg->front.iov_len); req->r_request = msg; @@ -624,7 +626,7 @@ static void osd_reset(struct ceph_connection *con) /* * Track open sessions with osds. */ -static struct ceph_osd *create_osd(struct ceph_osd_client *osdc) +static struct ceph_osd *create_osd(struct ceph_osd_client *osdc, int onum) { struct ceph_osd *osd; @@ -634,15 +636,13 @@ static struct ceph_osd *create_osd(struct ceph_osd_client *osdc) atomic_set(&osd->o_ref, 1); osd->o_osdc = osdc; + osd->o_osd = onum; INIT_LIST_HEAD(&osd->o_requests); INIT_LIST_HEAD(&osd->o_linger_requests); INIT_LIST_HEAD(&osd->o_osd_lru); osd->o_incarnation = 1; - ceph_con_init(osdc->client->msgr, &osd->o_con); - osd->o_con.private = osd; - osd->o_con.ops = &osd_con_ops; - osd->o_con.peer_name.type = CEPH_ENTITY_TYPE_OSD; + ceph_con_init(&osd->o_con, osd, &osd_con_ops, &osdc->client->msgr); INIT_LIST_HEAD(&osd->o_keepalive_item); return osd; @@ -688,7 +688,7 @@ static void __remove_osd(struct ceph_osd_client *osdc, struct ceph_osd *osd) static void remove_all_osds(struct ceph_osd_client *osdc) { - dout("__remove_old_osds %p\n", osdc); + dout("%s %p\n", __func__, osdc); mutex_lock(&osdc->request_mutex); while (!RB_EMPTY_ROOT(&osdc->osds)) { struct ceph_osd *osd = rb_entry(rb_first(&osdc->osds), @@ -752,7 +752,8 @@ static int __reset_osd(struct ceph_osd_client *osdc, struct ceph_osd *osd) ret = -EAGAIN; } else { ceph_con_close(&osd->o_con); - ceph_con_open(&osd->o_con, &osdc->osdmap->osd_addr[osd->o_osd]); + ceph_con_open(&osd->o_con, CEPH_ENTITY_TYPE_OSD, osd->o_osd, + &osdc->osdmap->osd_addr[osd->o_osd]); osd->o_incarnation++; } return ret; @@ -853,7 +854,7 @@ static void __unregister_request(struct ceph_osd_client *osdc, if (req->r_osd) { /* make sure the original request isn't in flight. */ - ceph_con_revoke(&req->r_osd->o_con, req->r_request); + ceph_msg_revoke(req->r_request); list_del_init(&req->r_osd_item); if (list_empty(&req->r_osd->o_requests) && @@ -880,7 +881,7 @@ static void __unregister_request(struct ceph_osd_client *osdc, static void __cancel_request(struct ceph_osd_request *req) { if (req->r_sent && req->r_osd) { - ceph_con_revoke(&req->r_osd->o_con, req->r_request); + ceph_msg_revoke(req->r_request); req->r_sent = 0; } } @@ -890,7 +891,9 @@ static void __register_linger_request(struct ceph_osd_client *osdc, { dout("__register_linger_request %p\n", req); list_add_tail(&req->r_linger_item, &osdc->req_linger); - list_add_tail(&req->r_linger_osd, &req->r_osd->o_linger_requests); + if (req->r_osd) + list_add_tail(&req->r_linger_osd, + &req->r_osd->o_linger_requests); } static void __unregister_linger_request(struct ceph_osd_client *osdc, @@ -998,18 +1001,18 @@ static int __map_request(struct ceph_osd_client *osdc, req->r_osd = __lookup_osd(osdc, o); if (!req->r_osd && o >= 0) { err = -ENOMEM; - req->r_osd = create_osd(osdc); + req->r_osd = create_osd(osdc, o); if (!req->r_osd) { list_move(&req->r_req_lru_item, &osdc->req_notarget); goto out; } dout("map_request osd %p is osd%d\n", req->r_osd, o); - req->r_osd->o_osd = o; - req->r_osd->o_con.peer_name.num = cpu_to_le64(o); __insert_osd(osdc, req->r_osd); - ceph_con_open(&req->r_osd->o_con, &osdc->osdmap->osd_addr[o]); + ceph_con_open(&req->r_osd->o_con, + CEPH_ENTITY_TYPE_OSD, o, + &osdc->osdmap->osd_addr[o]); } if (req->r_osd) { @@ -1304,8 +1307,9 @@ static void kick_requests(struct ceph_osd_client *osdc, int force_resend) dout("kick_requests %s\n", force_resend ? " (force resend)" : ""); mutex_lock(&osdc->request_mutex); - for (p = rb_first(&osdc->requests); p; p = rb_next(p)) { + for (p = rb_first(&osdc->requests); p; ) { req = rb_entry(p, struct ceph_osd_request, r_node); + p = rb_next(p); err = __map_request(osdc, req, force_resend); if (err < 0) continue; /* error */ @@ -1313,10 +1317,23 @@ static void kick_requests(struct ceph_osd_client *osdc, int force_resend) dout("%p tid %llu maps to no osd\n", req, req->r_tid); needmap++; /* request a newer map */ } else if (err > 0) { - dout("%p tid %llu requeued on osd%d\n", req, req->r_tid, - req->r_osd ? req->r_osd->o_osd : -1); - if (!req->r_linger) + if (!req->r_linger) { + dout("%p tid %llu requeued on osd%d\n", req, + req->r_tid, + req->r_osd ? req->r_osd->o_osd : -1); req->r_flags |= CEPH_OSD_FLAG_RETRY; + } + } + if (req->r_linger && list_empty(&req->r_linger_item)) { + /* + * register as a linger so that we will + * re-submit below and get a new tid + */ + dout("%p tid %llu restart on osd%d\n", + req, req->r_tid, + req->r_osd ? req->r_osd->o_osd : -1); + __register_linger_request(osdc, req); + __unregister_request(osdc, req); } } @@ -1391,7 +1408,7 @@ void ceph_osdc_handle_map(struct ceph_osd_client *osdc, struct ceph_msg *msg) epoch, maplen); newmap = osdmap_apply_incremental(&p, next, osdc->osdmap, - osdc->client->msgr); + &osdc->client->msgr); if (IS_ERR(newmap)) { err = PTR_ERR(newmap); goto bad; @@ -1839,11 +1856,12 @@ int ceph_osdc_init(struct ceph_osd_client *osdc, struct ceph_client *client) if (!osdc->req_mempool) goto out; - err = ceph_msgpool_init(&osdc->msgpool_op, OSD_OP_FRONT_LEN, 10, true, + err = ceph_msgpool_init(&osdc->msgpool_op, CEPH_MSG_OSD_OP, + OSD_OP_FRONT_LEN, 10, true, "osd_op"); if (err < 0) goto out_mempool; - err = ceph_msgpool_init(&osdc->msgpool_op_reply, + err = ceph_msgpool_init(&osdc->msgpool_op_reply, CEPH_MSG_OSD_OPREPLY, OSD_OPREPLY_FRONT_LEN, 10, true, "osd_op_reply"); if (err < 0) @@ -2019,15 +2037,15 @@ static struct ceph_msg *get_reply(struct ceph_connection *con, if (!req) { *skip = 1; m = NULL; - pr_info("get_reply unknown tid %llu from osd%d\n", tid, - osd->o_osd); + dout("get_reply unknown tid %llu from osd%d\n", tid, + osd->o_osd); goto out; } if (req->r_con_filling_msg) { - dout("get_reply revoking msg %p from old con %p\n", + dout("%s revoking msg %p from old con %p\n", __func__, req->r_reply, req->r_con_filling_msg); - ceph_con_revoke_message(req->r_con_filling_msg, req->r_reply); + ceph_msg_revoke_incoming(req->r_reply); req->r_con_filling_msg->ops->put(req->r_con_filling_msg); req->r_con_filling_msg = NULL; } @@ -2080,6 +2098,7 @@ static struct ceph_msg *alloc_msg(struct ceph_connection *con, int type = le16_to_cpu(hdr->type); int front = le32_to_cpu(hdr->front_len); + *skip = 0; switch (type) { case CEPH_MSG_OSD_MAP: case CEPH_MSG_WATCH_NOTIFY: diff --git a/net/ceph/osdmap.c b/net/ceph/osdmap.c index 81e3b84a77ef..3124b71a8883 100644 --- a/net/ceph/osdmap.c +++ b/net/ceph/osdmap.c @@ -135,6 +135,21 @@ bad: return -EINVAL; } +static int skip_name_map(void **p, void *end) +{ + int len; + ceph_decode_32_safe(p, end, len ,bad); + while (len--) { + int strlen; + *p += sizeof(u32); + ceph_decode_32_safe(p, end, strlen, bad); + *p += strlen; +} + return 0; +bad: + return -EINVAL; +} + static struct crush_map *crush_decode(void *pbyval, void *end) { struct crush_map *c; @@ -143,6 +158,7 @@ static struct crush_map *crush_decode(void *pbyval, void *end) void **p = &pbyval; void *start = pbyval; u32 magic; + u32 num_name_maps; dout("crush_decode %p to %p len %d\n", *p, end, (int)(end - *p)); @@ -150,6 +166,11 @@ static struct crush_map *crush_decode(void *pbyval, void *end) if (c == NULL) return ERR_PTR(-ENOMEM); + /* set tunables to default values */ + c->choose_local_tries = 2; + c->choose_local_fallback_tries = 5; + c->choose_total_tries = 19; + ceph_decode_need(p, end, 4*sizeof(u32), bad); magic = ceph_decode_32(p); if (magic != CRUSH_MAGIC) { @@ -297,7 +318,25 @@ static struct crush_map *crush_decode(void *pbyval, void *end) } /* ignore trailing name maps. */ + for (num_name_maps = 0; num_name_maps < 3; num_name_maps++) { + err = skip_name_map(p, end); + if (err < 0) + goto done; + } + + /* tunables */ + ceph_decode_need(p, end, 3*sizeof(u32), done); + c->choose_local_tries = ceph_decode_32(p); + c->choose_local_fallback_tries = ceph_decode_32(p); + c->choose_total_tries = ceph_decode_32(p); + dout("crush decode tunable choose_local_tries = %d", + c->choose_local_tries); + dout("crush decode tunable choose_local_fallback_tries = %d", + c->choose_local_fallback_tries); + dout("crush decode tunable choose_total_tries = %d", + c->choose_total_tries); +done: dout("crush_decode success\n"); return c; @@ -488,15 +527,16 @@ static int __decode_pool_names(void **p, void *end, struct ceph_osdmap *map) ceph_decode_32_safe(p, end, pool, bad); ceph_decode_32_safe(p, end, len, bad); dout(" pool %d len %d\n", pool, len); + ceph_decode_need(p, end, len, bad); pi = __lookup_pg_pool(&map->pg_pools, pool); if (pi) { + char *name = kstrndup(*p, len, GFP_NOFS); + + if (!name) + return -ENOMEM; kfree(pi->name); - pi->name = kmalloc(len + 1, GFP_NOFS); - if (pi->name) { - memcpy(pi->name, *p, len); - pi->name[len] = '\0'; - dout(" name is %s\n", pi->name); - } + pi->name = name; + dout(" name is %s\n", pi->name); } *p += len; } @@ -666,6 +706,9 @@ struct ceph_osdmap *osdmap_decode(void **p, void *end) ceph_decode_need(p, end, sizeof(u32) + sizeof(u64), bad); ceph_decode_copy(p, &pgid, sizeof(pgid)); n = ceph_decode_32(p); + err = -EINVAL; + if (n > (UINT_MAX - sizeof(*pg)) / sizeof(u32)) + goto bad; ceph_decode_need(p, end, n * sizeof(u32), bad); err = -ENOMEM; pg = kmalloc(sizeof(*pg) + n*sizeof(u32), GFP_NOFS); @@ -889,6 +932,10 @@ struct ceph_osdmap *osdmap_apply_incremental(void **p, void *end, (void) __remove_pg_mapping(&map->pg_temp, pgid); /* insert */ + if (pglen > (UINT_MAX - sizeof(*pg)) / sizeof(u32)) { + err = -EINVAL; + goto bad; + } pg = kmalloc(sizeof(*pg) + sizeof(u32)*pglen, GFP_NOFS); if (!pg) { err = -ENOMEM; diff --git a/net/ceph/pagelist.c b/net/ceph/pagelist.c index 13cb409a7bba..665cd23020ff 100644 --- a/net/ceph/pagelist.c +++ b/net/ceph/pagelist.c @@ -72,8 +72,7 @@ int ceph_pagelist_append(struct ceph_pagelist *pl, const void *buf, size_t len) } EXPORT_SYMBOL(ceph_pagelist_append); -/** - * Allocate enough pages for a pagelist to append the given amount +/* Allocate enough pages for a pagelist to append the given amount * of data without without allocating. * Returns: 0 on success, -ENOMEM on error. */ @@ -95,9 +94,7 @@ int ceph_pagelist_reserve(struct ceph_pagelist *pl, size_t space) } EXPORT_SYMBOL(ceph_pagelist_reserve); -/** - * Free any pages that have been preallocated. - */ +/* Free any pages that have been preallocated. */ int ceph_pagelist_free_reserve(struct ceph_pagelist *pl) { while (!list_empty(&pl->free_list)) { @@ -112,9 +109,7 @@ int ceph_pagelist_free_reserve(struct ceph_pagelist *pl) } EXPORT_SYMBOL(ceph_pagelist_free_reserve); -/** - * Create a truncation point. - */ +/* Create a truncation point. */ void ceph_pagelist_set_cursor(struct ceph_pagelist *pl, struct ceph_pagelist_cursor *c) { @@ -124,8 +119,7 @@ void ceph_pagelist_set_cursor(struct ceph_pagelist *pl, } EXPORT_SYMBOL(ceph_pagelist_set_cursor); -/** - * Truncate a pagelist to the given point. Move extra pages to reserve. +/* Truncate a pagelist to the given point. Move extra pages to reserve. * This won't sleep. * Returns: 0 on success, * -EINVAL if the pagelist doesn't match the trunc point pagelist |