diff options
Diffstat (limited to 'net')
48 files changed, 1551 insertions, 771 deletions
diff --git a/net/bridge/br_sysfs_if.c b/net/bridge/br_sysfs_if.c index 6229b62..13b36bd 100644 --- a/net/bridge/br_sysfs_if.c +++ b/net/bridge/br_sysfs_if.c @@ -27,7 +27,7 @@ struct brport_attribute { }; #define BRPORT_ATTR(_name,_mode,_show,_store) \ -struct brport_attribute brport_attr_##_name = { \ +const struct brport_attribute brport_attr_##_name = { \ .attr = {.name = __stringify(_name), \ .mode = _mode }, \ .show = _show, \ @@ -164,7 +164,7 @@ static BRPORT_ATTR(multicast_router, S_IRUGO | S_IWUSR, show_multicast_router, store_multicast_router); #endif -static struct brport_attribute *brport_attrs[] = { +static const struct brport_attribute *brport_attrs[] = { &brport_attr_path_cost, &brport_attr_priority, &brport_attr_port_id, @@ -241,7 +241,7 @@ const struct sysfs_ops brport_sysfs_ops = { int br_sysfs_addif(struct net_bridge_port *p) { struct net_bridge *br = p->br; - struct brport_attribute **a; + const struct brport_attribute **a; int err; err = sysfs_create_link(&p->kobj, &br->dev->dev.kobj, diff --git a/net/caif/caif_socket.c b/net/caif/caif_socket.c index 78f1cda..095259f 100644 --- a/net/caif/caif_socket.c +++ b/net/caif/caif_socket.c @@ -141,7 +141,7 @@ static int caif_queue_rcv_skb(struct sock *sk, struct sk_buff *skb) err = sk_filter(sk, skb); if (err) return err; - if (!sk_rmem_schedule(sk, skb->truesize) && rx_flow_is_on(cf_sk)) { + if (!sk_rmem_schedule(sk, skb, skb->truesize) && rx_flow_is_on(cf_sk)) { set_rx_flow_off(cf_sk); net_dbg_ratelimited("sending flow OFF due to rmem_schedule\n"); caif_flow_ctrl(sk, CAIF_MODEMCMD_FLOW_OFF_REQ); diff --git a/net/ceph/ceph_common.c b/net/ceph/ceph_common.c index ba4323b..69e38db 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> @@ -460,27 +461,23 @@ 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 +486,6 @@ 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 +496,8 @@ 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 +505,6 @@ 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 d7edc24..35fce75 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/messenger.c b/net/ceph/messenger.c index 10255e8..b979675 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 +915,15 @@ 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_reset(con); + 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 +971,34 @@ 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 +1015,36 @@ 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 +1067,14 @@ 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 +1087,15 @@ 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 +1507,14 @@ 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 +1557,6 @@ static int process_connect(struct ceph_connection *con) return -1; } con->auth_retry = 1; - ceph_con_out_kvec_reset(con); ret = prepare_write_connect(con); if (ret < 0) return ret; @@ -1428,7 +1577,6 @@ 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); ret = prepare_write_connect(con); if (ret < 0) return ret; @@ -1440,8 +1588,7 @@ 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 +1601,6 @@ 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); ret = prepare_write_connect(con); if (ret < 0) return ret; @@ -1471,7 +1617,6 @@ 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); ret = prepare_write_connect(con); if (ret < 0) return ret; @@ -1489,7 +1634,10 @@ 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 +1649,9 @@ 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 +1737,7 @@ 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 +1780,6 @@ 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 +1816,6 @@ 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 +1866,13 @@ 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 +1883,9 @@ 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 +1897,11 @@ 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 +1918,6 @@ 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 +1928,7 @@ 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 +1982,11 @@ 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 +2006,6 @@ static void process_message(struct ceph_connection *con) con->ops->dispatch(con, msg); mutex_lock(&con->mutex); - prepare_read_tag(con); } @@ -1870,22 +2017,19 @@ 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 +2076,7 @@ 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 +2086,15 @@ 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 +2111,42 @@ 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; + + /* Banner is good, exchange connection info */ + 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 +2156,8 @@ more: goto more; } + BUG_ON(con->state != CON_STATE_OPEN); + if (con->in_base_pos < 0) { /* * skipping + discarding content. @@ -2040,7 +2191,8 @@ 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 +2215,8 @@ 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 +2245,6 @@ 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 +2269,26 @@ 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 +2302,35 @@ 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 +2339,6 @@ done_unlocked: return; fault: - mutex_unlock(&con->mutex); ceph_fault(con); /* error/fault path */ goto done_unlocked; } @@ -2183,26 +2349,31 @@ 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 +2382,13 @@ 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 +2409,12 @@ 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 +2431,14 @@ 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 +2451,23 @@ 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 +2476,24 @@ 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 +2502,13 @@ 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 +2516,34 @@ 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 +2551,27 @@ 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 +2582,8 @@ 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 +2594,11 @@ 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 +2617,8 @@ 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 +2714,77 @@ 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 d0649a9..105d533 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); @@ -439,6 +441,7 @@ 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 +464,7 @@ 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 +687,9 @@ 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 +709,7 @@ 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 +764,12 @@ 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 +798,9 @@ 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 +824,6 @@ 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 +839,6 @@ 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); /* @@ -888,8 +882,8 @@ 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); @@ -1000,6 +994,8 @@ 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 +1025,7 @@ 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 +1040,23 @@ 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 11d5f41..ddec1c1 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 ca59e66..42119c0 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 81e3b84..3124b71 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/core/dev.c b/net/core/dev.c index 0ebaea1..0cb3fe8 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -1172,6 +1172,7 @@ static int __dev_open(struct net_device *dev) net_dmaengine_get(); dev_set_rx_mode(dev); dev_activate(dev); + add_device_randomness(dev->dev_addr, dev->addr_len); } return ret; @@ -3155,6 +3156,23 @@ void netdev_rx_handler_unregister(struct net_device *dev) } EXPORT_SYMBOL_GPL(netdev_rx_handler_unregister); +/* + * Limit the use of PFMEMALLOC reserves to those protocols that implement + * the special handling of PFMEMALLOC skbs. + */ +static bool skb_pfmemalloc_protocol(struct sk_buff *skb) +{ + switch (skb->protocol) { + case __constant_htons(ETH_P_ARP): + case __constant_htons(ETH_P_IP): + case __constant_htons(ETH_P_IPV6): + case __constant_htons(ETH_P_8021Q): + return true; + default: + return false; + } +} + static int __netif_receive_skb(struct sk_buff *skb) { struct packet_type *ptype, *pt_prev; @@ -3164,14 +3182,27 @@ static int __netif_receive_skb(struct sk_buff *skb) bool deliver_exact = false; int ret = NET_RX_DROP; __be16 type; + unsigned long pflags = current->flags; net_timestamp_check(!netdev_tstamp_prequeue, skb); trace_netif_receive_skb(skb); + /* + * PFMEMALLOC skbs are special, they should + * - be delivered to SOCK_MEMALLOC sockets only + * - stay away from userspace + * - have bounded memory usage + * + * Use PF_MEMALLOC as this saves us from propagating the allocation + * context down to all allocation sites. + */ + if (sk_memalloc_socks() && skb_pfmemalloc(skb)) + current->flags |= PF_MEMALLOC; + /* if we've gotten here through NAPI, check netpoll */ if (netpoll_receive_skb(skb)) - return NET_RX_DROP; + goto out; orig_dev = skb->dev; @@ -3191,7 +3222,7 @@ another_round: if (skb->protocol == cpu_to_be16(ETH_P_8021Q)) { skb = vlan_untag(skb); if (unlikely(!skb)) - goto out; + goto unlock; } #ifdef CONFIG_NET_CLS_ACT @@ -3201,6 +3232,9 @@ another_round: } #endif + if (sk_memalloc_socks() && skb_pfmemalloc(skb)) + goto skip_taps; + list_for_each_entry_rcu(ptype, &ptype_all, list) { if (!ptype->dev || ptype->dev == skb->dev) { if (pt_prev) @@ -3209,13 +3243,18 @@ another_round: } } +skip_taps: #ifdef CONFIG_NET_CLS_ACT skb = handle_ing(skb, &pt_prev, &ret, orig_dev); if (!skb) - goto out; + goto unlock; ncls: #endif + if (sk_memalloc_socks() && skb_pfmemalloc(skb) + && !skb_pfmemalloc_protocol(skb)) + goto drop; + rx_handler = rcu_dereference(skb->dev->rx_handler); if (vlan_tx_tag_present(skb)) { if (pt_prev) { @@ -3225,7 +3264,7 @@ ncls: if (vlan_do_receive(&skb, !rx_handler)) goto another_round; else if (unlikely(!skb)) - goto out; + goto unlock; } if (rx_handler) { @@ -3235,7 +3274,7 @@ ncls: } switch (rx_handler(&skb)) { case RX_HANDLER_CONSUMED: - goto out; + goto unlock; case RX_HANDLER_ANOTHER: goto another_round; case RX_HANDLER_EXACT: @@ -3268,6 +3307,7 @@ ncls: else ret = pt_prev->func(skb, skb->dev, pt_prev, orig_dev); } else { +drop: atomic_long_inc(&skb->dev->rx_dropped); kfree_skb(skb); /* Jamal, now you will not able to escape explaining @@ -3276,8 +3316,10 @@ ncls: ret = NET_RX_DROP; } -out: +unlock: rcu_read_unlock(); +out: + tsk_restore_flags(current, pflags, PF_MEMALLOC); return ret; } @@ -4801,6 +4843,7 @@ int dev_set_mac_address(struct net_device *dev, struct sockaddr *sa) err = ops->ndo_set_mac_address(dev, sa); if (!err) call_netdevice_notifiers(NETDEV_CHANGEADDR, dev); + add_device_randomness(dev->dev_addr, dev->addr_len); return err; } EXPORT_SYMBOL(dev_set_mac_address); @@ -5579,6 +5622,7 @@ int register_netdevice(struct net_device *dev) dev_init_scheduler(dev); dev_hold(dev); list_netdevice(dev); + add_device_randomness(dev->dev_addr, dev->addr_len); /* Notify protocols, that a new device appeared. */ ret = call_netdevice_notifiers(NETDEV_REGISTER, dev); diff --git a/net/core/filter.c b/net/core/filter.c index d4ce2dc..907efd2 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -83,6 +83,14 @@ int sk_filter(struct sock *sk, struct sk_buff *skb) int err; struct sk_filter *filter; + /* + * If the skb was allocated from pfmemalloc reserves, only + * allow SOCK_MEMALLOC sockets to use it as this socket is + * helping free memory + */ + if (skb_pfmemalloc(skb) && !sock_flag(sk, SOCK_MEMALLOC)) + return -ENOMEM; + err = security_sock_rcv_skb(sk, skb); if (err) return err; diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index 334b930..2c5a0a0 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -625,9 +625,13 @@ int rtnl_put_cacheinfo(struct sk_buff *skb, struct dst_entry *dst, u32 id, .rta_id = id, }; - if (expires) - ci.rta_expires = jiffies_to_clock_t(expires); + if (expires) { + unsigned long clock; + clock = jiffies_to_clock_t(abs(expires)); + clock = min_t(unsigned long, clock, INT_MAX); + ci.rta_expires = (expires > 0) ? clock : -clock; + } return nla_put(skb, RTA_CACHEINFO, sizeof(ci), &ci); } EXPORT_SYMBOL_GPL(rtnl_put_cacheinfo); @@ -659,6 +663,12 @@ static void set_operstate(struct net_device *dev, unsigned char transition) } } +static unsigned int rtnl_dev_get_flags(const struct net_device *dev) +{ + return (dev->flags & ~(IFF_PROMISC | IFF_ALLMULTI)) | + (dev->gflags & (IFF_PROMISC | IFF_ALLMULTI)); +} + static unsigned int rtnl_dev_combine_flags(const struct net_device *dev, const struct ifinfomsg *ifm) { @@ -667,7 +677,7 @@ static unsigned int rtnl_dev_combine_flags(const struct net_device *dev, /* bugwards compatibility: ifi_change == 0 is treated as ~0 */ if (ifm->ifi_change) flags = (flags & ifm->ifi_change) | - (dev->flags & ~ifm->ifi_change); + (rtnl_dev_get_flags(dev) & ~ifm->ifi_change); return flags; } @@ -1371,6 +1381,7 @@ static int do_setlink(struct net_device *dev, struct ifinfomsg *ifm, goto errout; send_addr_notify = 1; modified = 1; + add_device_randomness(dev->dev_addr, dev->addr_len); } if (tb[IFLA_MTU]) { diff --git a/net/core/skbuff.c b/net/core/skbuff.c index 368f65c..fe00d12 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -145,6 +145,43 @@ static void skb_under_panic(struct sk_buff *skb, int sz, void *here) BUG(); } + +/* + * kmalloc_reserve is a wrapper around kmalloc_node_track_caller that tells + * the caller if emergency pfmemalloc reserves are being used. If it is and + * the socket is later found to be SOCK_MEMALLOC then PFMEMALLOC reserves + * may be used. Otherwise, the packet data may be discarded until enough + * memory is free + */ +#define kmalloc_reserve(size, gfp, node, pfmemalloc) \ + __kmalloc_reserve(size, gfp, node, _RET_IP_, pfmemalloc) +void *__kmalloc_reserve(size_t size, gfp_t flags, int node, unsigned long ip, + bool *pfmemalloc) +{ + void *obj; + bool ret_pfmemalloc = false; + + /* + * Try a regular allocation, when that fails and we're not entitled + * to the reserves, fail. + */ + obj = kmalloc_node_track_caller(size, + flags | __GFP_NOMEMALLOC | __GFP_NOWARN, + node); + if (obj || !(gfp_pfmemalloc_allowed(flags))) + goto out; + + /* Try again but now we are using pfmemalloc reserves */ + ret_pfmemalloc = true; + obj = kmalloc_node_track_caller(size, flags, node); + +out: + if (pfmemalloc) + *pfmemalloc = ret_pfmemalloc; + + return obj; +} + /* Allocate a new skbuff. We do this ourselves so we can fill in a few * 'private' fields and also do memory statistics to find all the * [BEEP] leaks. @@ -155,8 +192,10 @@ static void skb_under_panic(struct sk_buff *skb, int sz, void *here) * __alloc_skb - allocate a network buffer * @size: size to allocate * @gfp_mask: allocation mask - * @fclone: allocate from fclone cache instead of head cache - * and allocate a cloned (child) skb + * @flags: If SKB_ALLOC_FCLONE is set, allocate from fclone cache + * instead of head cache and allocate a cloned (child) skb. + * If SKB_ALLOC_RX is set, __GFP_MEMALLOC will be used for + * allocations in case the data is required for writeback * @node: numa node to allocate memory on * * Allocate a new &sk_buff. The returned buffer has no headroom and a @@ -167,14 +206,19 @@ static void skb_under_panic(struct sk_buff *skb, int sz, void *here) * %GFP_ATOMIC. */ struct sk_buff *__alloc_skb(unsigned int size, gfp_t gfp_mask, - int fclone, int node) + int flags, int node) { struct kmem_cache *cache; struct skb_shared_info *shinfo; struct sk_buff *skb; u8 *data; + bool pfmemalloc; - cache = fclone ? skbuff_fclone_cache : skbuff_head_cache; + cache = (flags & SKB_ALLOC_FCLONE) + ? skbuff_fclone_cache : skbuff_head_cache; + + if (sk_memalloc_socks() && (flags & SKB_ALLOC_RX)) + gfp_mask |= __GFP_MEMALLOC; /* Get the HEAD */ skb = kmem_cache_alloc_node(cache, gfp_mask & ~__GFP_DMA, node); @@ -189,7 +233,7 @@ struct sk_buff *__alloc_skb(unsigned int size, gfp_t gfp_mask, */ size = SKB_DATA_ALIGN(size); size += SKB_DATA_ALIGN(sizeof(struct skb_shared_info)); - data = kmalloc_node_track_caller(size, gfp_mask, node); + data = kmalloc_reserve(size, gfp_mask, node, &pfmemalloc); if (!data) goto nodata; /* kmalloc(size) might give us more room than requested. @@ -207,6 +251,7 @@ struct sk_buff *__alloc_skb(unsigned int size, gfp_t gfp_mask, memset(skb, 0, offsetof(struct sk_buff, tail)); /* Account for allocated memory : skb + skb->head */ skb->truesize = SKB_TRUESIZE(size); + skb->pfmemalloc = pfmemalloc; atomic_set(&skb->users, 1); skb->head = data; skb->data = data; @@ -222,7 +267,7 @@ struct sk_buff *__alloc_skb(unsigned int size, gfp_t gfp_mask, atomic_set(&shinfo->dataref, 1); kmemcheck_annotate_variable(shinfo->destructor_arg); - if (fclone) { + if (flags & SKB_ALLOC_FCLONE) { struct sk_buff *child = skb + 1; atomic_t *fclone_ref = (atomic_t *) (child + 1); @@ -232,6 +277,7 @@ struct sk_buff *__alloc_skb(unsigned int size, gfp_t gfp_mask, atomic_set(fclone_ref, 1); child->fclone = SKB_FCLONE_UNAVAILABLE; + child->pfmemalloc = pfmemalloc; } out: return skb; @@ -302,14 +348,7 @@ static DEFINE_PER_CPU(struct netdev_alloc_cache, netdev_alloc_cache); #define NETDEV_PAGECNT_BIAS (PAGE_SIZE / SMP_CACHE_BYTES) -/** - * netdev_alloc_frag - allocate a page fragment - * @fragsz: fragment size - * - * Allocates a frag from a page for receive buffer. - * Uses GFP_ATOMIC allocations. - */ -void *netdev_alloc_frag(unsigned int fragsz) +static void *__netdev_alloc_frag(unsigned int fragsz, gfp_t gfp_mask) { struct netdev_alloc_cache *nc; void *data = NULL; @@ -319,7 +358,7 @@ void *netdev_alloc_frag(unsigned int fragsz) nc = &__get_cpu_var(netdev_alloc_cache); if (unlikely(!nc->page)) { refill: - nc->page = alloc_page(GFP_ATOMIC | __GFP_COLD); + nc->page = alloc_page(gfp_mask); if (unlikely(!nc->page)) goto end; recycle: @@ -343,6 +382,18 @@ end: local_irq_restore(flags); return data; } + +/** + * netdev_alloc_frag - allocate a page fragment + * @fragsz: fragment size + * + * Allocates a frag from a page for receive buffer. + * Uses GFP_ATOMIC allocations. + */ +void *netdev_alloc_frag(unsigned int fragsz) +{ + return __netdev_alloc_frag(fragsz, GFP_ATOMIC | __GFP_COLD); +} EXPORT_SYMBOL(netdev_alloc_frag); /** @@ -366,7 +417,12 @@ struct sk_buff *__netdev_alloc_skb(struct net_device *dev, SKB_DATA_ALIGN(sizeof(struct skb_shared_info)); if (fragsz <= PAGE_SIZE && !(gfp_mask & (__GFP_WAIT | GFP_DMA))) { - void *data = netdev_alloc_frag(fragsz); + void *data; + + if (sk_memalloc_socks()) + gfp_mask |= __GFP_MEMALLOC; + + data = __netdev_alloc_frag(fragsz, gfp_mask); if (likely(data)) { skb = build_skb(data, fragsz); @@ -374,7 +430,8 @@ struct sk_buff *__netdev_alloc_skb(struct net_device *dev, put_page(virt_to_head_page(data)); } } else { - skb = __alloc_skb(length + NET_SKB_PAD, gfp_mask, 0, NUMA_NO_NODE); + skb = __alloc_skb(length + NET_SKB_PAD, gfp_mask, + SKB_ALLOC_RX, NUMA_NO_NODE); } if (likely(skb)) { skb_reserve(skb, NET_SKB_PAD); @@ -656,6 +713,7 @@ static void __copy_skb_header(struct sk_buff *new, const struct sk_buff *old) #if IS_ENABLED(CONFIG_IP_VS) new->ipvs_property = old->ipvs_property; #endif + new->pfmemalloc = old->pfmemalloc; new->protocol = old->protocol; new->mark = old->mark; new->skb_iif = old->skb_iif; @@ -814,6 +872,9 @@ struct sk_buff *skb_clone(struct sk_buff *skb, gfp_t gfp_mask) n->fclone = SKB_FCLONE_CLONE; atomic_inc(fclone_ref); } else { + if (skb_pfmemalloc(skb)) + gfp_mask |= __GFP_MEMALLOC; + n = kmem_cache_alloc(skbuff_head_cache, gfp_mask); if (!n) return NULL; @@ -850,6 +911,13 @@ static void copy_skb_header(struct sk_buff *new, const struct sk_buff *old) skb_shinfo(new)->gso_type = skb_shinfo(old)->gso_type; } +static inline int skb_alloc_rx_flag(const struct sk_buff *skb) +{ + if (skb_pfmemalloc(skb)) + return SKB_ALLOC_RX; + return 0; +} + /** * skb_copy - create private copy of an sk_buff * @skb: buffer to copy @@ -871,7 +939,8 @@ struct sk_buff *skb_copy(const struct sk_buff *skb, gfp_t gfp_mask) { int headerlen = skb_headroom(skb); unsigned int size = skb_end_offset(skb) + skb->data_len; - struct sk_buff *n = alloc_skb(size, gfp_mask); + struct sk_buff *n = __alloc_skb(size, gfp_mask, + skb_alloc_rx_flag(skb), NUMA_NO_NODE); if (!n) return NULL; @@ -906,7 +975,8 @@ EXPORT_SYMBOL(skb_copy); struct sk_buff *__pskb_copy(struct sk_buff *skb, int headroom, gfp_t gfp_mask) { unsigned int size = skb_headlen(skb) + headroom; - struct sk_buff *n = alloc_skb(size, gfp_mask); + struct sk_buff *n = __alloc_skb(size, gfp_mask, + skb_alloc_rx_flag(skb), NUMA_NO_NODE); if (!n) goto out; @@ -979,8 +1049,10 @@ int pskb_expand_head(struct sk_buff *skb, int nhead, int ntail, size = SKB_DATA_ALIGN(size); - data = kmalloc(size + SKB_DATA_ALIGN(sizeof(struct skb_shared_info)), - gfp_mask); + if (skb_pfmemalloc(skb)) + gfp_mask |= __GFP_MEMALLOC; + data = kmalloc_reserve(size + SKB_DATA_ALIGN(sizeof(struct skb_shared_info)), + gfp_mask, NUMA_NO_NODE, NULL); if (!data) goto nodata; size = SKB_WITH_OVERHEAD(ksize(data)); @@ -1092,8 +1164,9 @@ struct sk_buff *skb_copy_expand(const struct sk_buff *skb, /* * Allocate the copy buffer */ - struct sk_buff *n = alloc_skb(newheadroom + skb->len + newtailroom, - gfp_mask); + struct sk_buff *n = __alloc_skb(newheadroom + skb->len + newtailroom, + gfp_mask, skb_alloc_rx_flag(skb), + NUMA_NO_NODE); int oldheadroom = skb_headroom(skb); int head_copy_len, head_copy_off; int off; @@ -2775,8 +2848,9 @@ struct sk_buff *skb_segment(struct sk_buff *skb, netdev_features_t features) skb_release_head_state(nskb); __skb_push(nskb, doffset); } else { - nskb = alloc_skb(hsize + doffset + headroom, - GFP_ATOMIC); + nskb = __alloc_skb(hsize + doffset + headroom, + GFP_ATOMIC, skb_alloc_rx_flag(skb), + NUMA_NO_NODE); if (unlikely(!nskb)) goto err; diff --git a/net/core/sock.c b/net/core/sock.c index 2676a88..6b654b3 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -142,7 +142,7 @@ static DEFINE_MUTEX(proto_list_mutex); static LIST_HEAD(proto_list); -#ifdef CONFIG_CGROUP_MEM_RES_CTLR_KMEM +#ifdef CONFIG_MEMCG_KMEM int mem_cgroup_sockets_init(struct mem_cgroup *memcg, struct cgroup_subsys *ss) { struct proto *proto; @@ -271,6 +271,61 @@ __u32 sysctl_rmem_default __read_mostly = SK_RMEM_MAX; int sysctl_optmem_max __read_mostly = sizeof(unsigned long)*(2*UIO_MAXIOV+512); EXPORT_SYMBOL(sysctl_optmem_max); +struct static_key memalloc_socks = STATIC_KEY_INIT_FALSE; +EXPORT_SYMBOL_GPL(memalloc_socks); + +/** + * sk_set_memalloc - sets %SOCK_MEMALLOC + * @sk: socket to set it on + * + * Set %SOCK_MEMALLOC on a socket for access to emergency reserves. + * It's the responsibility of the admin to adjust min_free_kbytes + * to meet the requirements + */ +void sk_set_memalloc(struct sock *sk) +{ + sock_set_flag(sk, SOCK_MEMALLOC); + sk->sk_allocation |= __GFP_MEMALLOC; + static_key_slow_inc(&memalloc_socks); +} +EXPORT_SYMBOL_GPL(sk_set_memalloc); + +void sk_clear_memalloc(struct sock *sk) +{ + sock_reset_flag(sk, SOCK_MEMALLOC); + sk->sk_allocation &= ~__GFP_MEMALLOC; + static_key_slow_dec(&memalloc_socks); + + /* + * SOCK_MEMALLOC is allowed to ignore rmem limits to ensure forward + * progress of swapping. However, if SOCK_MEMALLOC is cleared while + * it has rmem allocations there is a risk that the user of the + * socket cannot make forward progress due to exceeding the rmem + * limits. By rights, sk_clear_memalloc() should only be called + * on sockets being torn down but warn and reset the accounting if + * that assumption breaks. + */ + if (WARN_ON(sk->sk_forward_alloc)) + sk_mem_reclaim(sk); +} +EXPORT_SYMBOL_GPL(sk_clear_memalloc); + +int __sk_backlog_rcv(struct sock *sk, struct sk_buff *skb) +{ + int ret; + unsigned long pflags = current->flags; + + /* these should have been dropped before queueing */ + BUG_ON(!sock_flag(sk, SOCK_MEMALLOC)); + + current->flags |= PF_MEMALLOC; + ret = sk->sk_backlog_rcv(sk, skb); + tsk_restore_flags(current, pflags, PF_MEMALLOC); + + return ret; +} +EXPORT_SYMBOL(__sk_backlog_rcv); + #if defined(CONFIG_CGROUPS) #if !defined(CONFIG_NET_CLS_CGROUP) int net_cls_subsys_id = -1; @@ -353,7 +408,7 @@ int sock_queue_rcv_skb(struct sock *sk, struct sk_buff *skb) if (err) return err; - if (!sk_rmem_schedule(sk, skb->truesize)) { + if (!sk_rmem_schedule(sk, skb, skb->truesize)) { atomic_inc(&sk->sk_drops); return -ENOBUFS; } diff --git a/net/ipv4/Makefile b/net/ipv4/Makefile index ae2ccf2..15ca63e 100644 --- a/net/ipv4/Makefile +++ b/net/ipv4/Makefile @@ -49,7 +49,7 @@ obj-$(CONFIG_TCP_CONG_SCALABLE) += tcp_scalable.o obj-$(CONFIG_TCP_CONG_LP) += tcp_lp.o obj-$(CONFIG_TCP_CONG_YEAH) += tcp_yeah.o obj-$(CONFIG_TCP_CONG_ILLINOIS) += tcp_illinois.o -obj-$(CONFIG_CGROUP_MEM_RES_CTLR_KMEM) += tcp_memcontrol.o +obj-$(CONFIG_MEMCG_KMEM) += tcp_memcontrol.o obj-$(CONFIG_NETLABEL) += cipso_ipv4.o obj-$(CONFIG_XFRM) += xfrm4_policy.o xfrm4_state.o xfrm4_input.o \ diff --git a/net/ipv4/arp.c b/net/ipv4/arp.c index a0124eb..77e87af 100644 --- a/net/ipv4/arp.c +++ b/net/ipv4/arp.c @@ -827,7 +827,7 @@ static int arp_process(struct sk_buff *skb) } if (arp->ar_op == htons(ARPOP_REQUEST) && - ip_route_input(skb, tip, sip, 0, dev) == 0) { + ip_route_input_noref(skb, tip, sip, 0, dev) == 0) { rt = skb_rtable(skb); addr_type = rt->rt_type; diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c index 8732cc7..c43ae3f 100644 --- a/net/ipv4/fib_frontend.c +++ b/net/ipv4/fib_frontend.c @@ -1046,6 +1046,7 @@ static int fib_netdev_event(struct notifier_block *this, unsigned long event, vo if (event == NETDEV_UNREGISTER) { fib_disable_ip(dev, 2, -1); + rt_flush_dev(dev); return NOTIFY_DONE; } diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c index e55171f..da80dc1 100644 --- a/net/ipv4/fib_semantics.c +++ b/net/ipv4/fib_semantics.c @@ -140,6 +140,21 @@ const struct fib_prop fib_props[RTN_MAX + 1] = { }, }; +static void rt_fibinfo_free(struct rtable __rcu **rtp) +{ + struct rtable *rt = rcu_dereference_protected(*rtp, 1); + + if (!rt) + return; + + /* Not even needed : RCU_INIT_POINTER(*rtp, NULL); + * because we waited an RCU grace period before calling + * free_fib_info_rcu() + */ + + dst_free(&rt->dst); +} + static void free_nh_exceptions(struct fib_nh *nh) { struct fnhe_hash_bucket *hash = nh->nh_exceptions; @@ -153,6 +168,9 @@ static void free_nh_exceptions(struct fib_nh *nh) struct fib_nh_exception *next; next = rcu_dereference_protected(fnhe->fnhe_next, 1); + + rt_fibinfo_free(&fnhe->fnhe_rth); + kfree(fnhe); fnhe = next; @@ -161,6 +179,23 @@ static void free_nh_exceptions(struct fib_nh *nh) kfree(hash); } +static void rt_fibinfo_free_cpus(struct rtable __rcu * __percpu *rtp) +{ + int cpu; + + if (!rtp) + return; + + for_each_possible_cpu(cpu) { + struct rtable *rt; + + rt = rcu_dereference_protected(*per_cpu_ptr(rtp, cpu), 1); + if (rt) + dst_free(&rt->dst); + } + free_percpu(rtp); +} + /* Release a nexthop info record */ static void free_fib_info_rcu(struct rcu_head *head) { @@ -171,10 +206,8 @@ static void free_fib_info_rcu(struct rcu_head *head) dev_put(nexthop_nh->nh_dev); if (nexthop_nh->nh_exceptions) free_nh_exceptions(nexthop_nh); - if (nexthop_nh->nh_rth_output) - dst_release(&nexthop_nh->nh_rth_output->dst); - if (nexthop_nh->nh_rth_input) - dst_release(&nexthop_nh->nh_rth_input->dst); + rt_fibinfo_free_cpus(nexthop_nh->nh_pcpu_rth_output); + rt_fibinfo_free(&nexthop_nh->nh_rth_input); } endfor_nexthops(fi); release_net(fi->fib_net); @@ -804,6 +837,7 @@ struct fib_info *fib_create_info(struct fib_config *cfg) fi->fib_nhs = nhs; change_nexthops(fi) { nexthop_nh->nh_parent = fi; + nexthop_nh->nh_pcpu_rth_output = alloc_percpu(struct rtable __rcu *); } endfor_nexthops(fi) if (cfg->fc_mx) { diff --git a/net/ipv4/fib_trie.c b/net/ipv4/fib_trie.c index 18cbc15..f0cdb30 100644 --- a/net/ipv4/fib_trie.c +++ b/net/ipv4/fib_trie.c @@ -159,7 +159,6 @@ struct trie { #endif }; -static void put_child(struct trie *t, struct tnode *tn, int i, struct rt_trie_node *n); static void tnode_put_child_reorg(struct tnode *tn, int i, struct rt_trie_node *n, int wasfull); static struct rt_trie_node *resize(struct trie *t, struct tnode *tn); @@ -473,7 +472,7 @@ static struct tnode *tnode_new(t_key key, int pos, int bits) } pr_debug("AT %p s=%zu %zu\n", tn, sizeof(struct tnode), - sizeof(struct rt_trie_node) << bits); + sizeof(struct rt_trie_node *) << bits); return tn; } @@ -490,7 +489,7 @@ static inline int tnode_full(const struct tnode *tn, const struct rt_trie_node * return ((struct tnode *) n)->pos == tn->pos + tn->bits; } -static inline void put_child(struct trie *t, struct tnode *tn, int i, +static inline void put_child(struct tnode *tn, int i, struct rt_trie_node *n) { tnode_put_child_reorg(tn, i, n, -1); @@ -754,8 +753,8 @@ static struct tnode *inflate(struct trie *t, struct tnode *tn) goto nomem; } - put_child(t, tn, 2*i, (struct rt_trie_node *) left); - put_child(t, tn, 2*i+1, (struct rt_trie_node *) right); + put_child(tn, 2*i, (struct rt_trie_node *) left); + put_child(tn, 2*i+1, (struct rt_trie_node *) right); } } @@ -776,9 +775,9 @@ static struct tnode *inflate(struct trie *t, struct tnode *tn) if (tkey_extract_bits(node->key, oldtnode->pos + oldtnode->bits, 1) == 0) - put_child(t, tn, 2*i, node); + put_child(tn, 2*i, node); else - put_child(t, tn, 2*i+1, node); + put_child(tn, 2*i+1, node); continue; } @@ -786,8 +785,8 @@ static struct tnode *inflate(struct trie *t, struct tnode *tn) inode = (struct tnode *) node; if (inode->bits == 1) { - put_child(t, tn, 2*i, rtnl_dereference(inode->child[0])); - put_child(t, tn, 2*i+1, rtnl_dereference(inode->child[1])); + put_child(tn, 2*i, rtnl_dereference(inode->child[0])); + put_child(tn, 2*i+1, rtnl_dereference(inode->child[1])); tnode_free_safe(inode); continue; @@ -817,22 +816,22 @@ static struct tnode *inflate(struct trie *t, struct tnode *tn) */ left = (struct tnode *) tnode_get_child(tn, 2*i); - put_child(t, tn, 2*i, NULL); + put_child(tn, 2*i, NULL); BUG_ON(!left); right = (struct tnode *) tnode_get_child(tn, 2*i+1); - put_child(t, tn, 2*i+1, NULL); + put_child(tn, 2*i+1, NULL); BUG_ON(!right); size = tnode_child_length(left); for (j = 0; j < size; j++) { - put_child(t, left, j, rtnl_dereference(inode->child[j])); - put_child(t, right, j, rtnl_dereference(inode->child[j + size])); + put_child(left, j, rtnl_dereference(inode->child[j])); + put_child(right, j, rtnl_dereference(inode->child[j + size])); } - put_child(t, tn, 2*i, resize(t, left)); - put_child(t, tn, 2*i+1, resize(t, right)); + put_child(tn, 2*i, resize(t, left)); + put_child(tn, 2*i+1, resize(t, right)); tnode_free_safe(inode); } @@ -877,7 +876,7 @@ static struct tnode *halve(struct trie *t, struct tnode *tn) if (!newn) goto nomem; - put_child(t, tn, i/2, (struct rt_trie_node *)newn); + put_child(tn, i/2, (struct rt_trie_node *)newn); } } @@ -892,21 +891,21 @@ static struct tnode *halve(struct trie *t, struct tnode *tn) if (left == NULL) { if (right == NULL) /* Both are empty */ continue; - put_child(t, tn, i/2, right); + put_child(tn, i/2, right); continue; } if (right == NULL) { - put_child(t, tn, i/2, left); + put_child(tn, i/2, left); continue; } /* Two nonempty children */ newBinNode = (struct tnode *) tnode_get_child(tn, i/2); - put_child(t, tn, i/2, NULL); - put_child(t, newBinNode, 0, left); - put_child(t, newBinNode, 1, right); - put_child(t, tn, i/2, resize(t, newBinNode)); + put_child(tn, i/2, NULL); + put_child(newBinNode, 0, left); + put_child(newBinNode, 1, right); + put_child(tn, i/2, resize(t, newBinNode)); } tnode_free_safe(oldtnode); return tn; @@ -1125,7 +1124,7 @@ static struct list_head *fib_insert_node(struct trie *t, u32 key, int plen) node_set_parent((struct rt_trie_node *)l, tp); cindex = tkey_extract_bits(key, tp->pos, tp->bits); - put_child(t, tp, cindex, (struct rt_trie_node *)l); + put_child(tp, cindex, (struct rt_trie_node *)l); } else { /* Case 3: n is a LEAF or a TNODE and the key doesn't match. */ /* @@ -1155,12 +1154,12 @@ static struct list_head *fib_insert_node(struct trie *t, u32 key, int plen) node_set_parent((struct rt_trie_node *)tn, tp); missbit = tkey_extract_bits(key, newpos, 1); - put_child(t, tn, missbit, (struct rt_trie_node *)l); - put_child(t, tn, 1-missbit, n); + put_child(tn, missbit, (struct rt_trie_node *)l); + put_child(tn, 1-missbit, n); if (tp) { cindex = tkey_extract_bits(key, tp->pos, tp->bits); - put_child(t, tp, cindex, (struct rt_trie_node *)tn); + put_child(tp, cindex, (struct rt_trie_node *)tn); } else { rcu_assign_pointer(t->trie, (struct rt_trie_node *)tn); tp = tn; @@ -1619,7 +1618,7 @@ static void trie_leaf_remove(struct trie *t, struct leaf *l) if (tp) { t_key cindex = tkey_extract_bits(l->key, tp->pos, tp->bits); - put_child(t, tp, cindex, NULL); + put_child(tp, cindex, NULL); trie_rebalance(t, tp); } else RCU_INIT_POINTER(t->trie, NULL); diff --git a/net/ipv4/ip_fragment.c b/net/ipv4/ip_fragment.c index 7ad88e5..8d07c97 100644 --- a/net/ipv4/ip_fragment.c +++ b/net/ipv4/ip_fragment.c @@ -258,8 +258,8 @@ static void ip_expire(unsigned long arg) /* skb dst is stale, drop it, and perform route lookup again */ skb_dst_drop(head); iph = ip_hdr(head); - err = ip_route_input(head, iph->daddr, iph->saddr, - iph->tos, head->dev); + err = ip_route_input_noref(head, iph->daddr, iph->saddr, + iph->tos, head->dev); if (err) goto out_rcu_unlock; diff --git a/net/ipv4/ip_input.c b/net/ipv4/ip_input.c index 4ebc6fe..f1395a6 100644 --- a/net/ipv4/ip_input.c +++ b/net/ipv4/ip_input.c @@ -314,6 +314,7 @@ drop: } int sysctl_ip_early_demux __read_mostly = 1; +EXPORT_SYMBOL(sysctl_ip_early_demux); static int ip_rcv_finish(struct sk_buff *skb) { @@ -324,11 +325,12 @@ static int ip_rcv_finish(struct sk_buff *skb) const struct net_protocol *ipprot; int protocol = iph->protocol; - rcu_read_lock(); ipprot = rcu_dereference(inet_protos[protocol]); - if (ipprot && ipprot->early_demux) + if (ipprot && ipprot->early_demux) { ipprot->early_demux(skb); - rcu_read_unlock(); + /* must reload iph, skb->head might have changed */ + iph = ip_hdr(skb); + } } /* @@ -336,8 +338,8 @@ static int ip_rcv_finish(struct sk_buff *skb) * how the packet travels inside Linux networking. */ if (!skb_dst(skb)) { - int err = ip_route_input(skb, iph->daddr, iph->saddr, - iph->tos, skb->dev); + int err = ip_route_input_noref(skb, iph->daddr, iph->saddr, + iph->tos, skb->dev); if (unlikely(err)) { if (err == -EXDEV) NET_INC_STATS_BH(dev_net(skb->dev), diff --git a/net/ipv4/route.c b/net/ipv4/route.c index 6bcb8fc..c035251 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -147,6 +147,7 @@ static void ip_rt_update_pmtu(struct dst_entry *dst, struct sock *sk, struct sk_buff *skb, u32 mtu); static void ip_do_redirect(struct dst_entry *dst, struct sock *sk, struct sk_buff *skb); +static void ipv4_dst_destroy(struct dst_entry *dst); static void ipv4_dst_ifdown(struct dst_entry *dst, struct net_device *dev, int how) @@ -170,6 +171,7 @@ static struct dst_ops ipv4_dst_ops = { .default_advmss = ipv4_default_advmss, .mtu = ipv4_mtu, .cow_metrics = ipv4_cow_metrics, + .destroy = ipv4_dst_destroy, .ifdown = ipv4_dst_ifdown, .negative_advice = ipv4_negative_advice, .link_failure = ipv4_link_failure, @@ -444,7 +446,7 @@ static inline int ip_rt_proc_init(void) } #endif /* CONFIG_PROC_FS */ -static inline int rt_is_expired(struct rtable *rth) +static inline bool rt_is_expired(const struct rtable *rth) { return rth->rt_genid != rt_genid(dev_net(rth->dst.dev)); } @@ -587,11 +589,17 @@ static void ip_rt_build_flow_key(struct flowi4 *fl4, const struct sock *sk, build_sk_flow_key(fl4, sk); } -static DEFINE_SEQLOCK(fnhe_seqlock); +static inline void rt_free(struct rtable *rt) +{ + call_rcu(&rt->dst.rcu_head, dst_rcu_free); +} + +static DEFINE_SPINLOCK(fnhe_lock); static struct fib_nh_exception *fnhe_oldest(struct fnhe_hash_bucket *hash) { struct fib_nh_exception *fnhe, *oldest; + struct rtable *orig; oldest = rcu_dereference(hash->chain); for (fnhe = rcu_dereference(oldest->fnhe_next); fnhe; @@ -599,6 +607,11 @@ static struct fib_nh_exception *fnhe_oldest(struct fnhe_hash_bucket *hash) if (time_before(fnhe->fnhe_stamp, oldest->fnhe_stamp)) oldest = fnhe; } + orig = rcu_dereference(oldest->fnhe_rth); + if (orig) { + RCU_INIT_POINTER(oldest->fnhe_rth, NULL); + rt_free(orig); + } return oldest; } @@ -620,7 +633,7 @@ static void update_or_create_fnhe(struct fib_nh *nh, __be32 daddr, __be32 gw, int depth; u32 hval = fnhe_hashfun(daddr); - write_seqlock_bh(&fnhe_seqlock); + spin_lock_bh(&fnhe_lock); hash = nh->nh_exceptions; if (!hash) { @@ -667,7 +680,7 @@ static void update_or_create_fnhe(struct fib_nh *nh, __be32 daddr, __be32 gw, fnhe->fnhe_stamp = jiffies; out_unlock: - write_sequnlock_bh(&fnhe_seqlock); + spin_unlock_bh(&fnhe_lock); return; } @@ -1164,67 +1177,126 @@ static struct fib_nh_exception *find_exception(struct fib_nh *nh, __be32 daddr) return NULL; } -static void rt_bind_exception(struct rtable *rt, struct fib_nh_exception *fnhe, +static bool rt_bind_exception(struct rtable *rt, struct fib_nh_exception *fnhe, __be32 daddr) { - __be32 fnhe_daddr, gw; - unsigned long expires; - unsigned int seq; - u32 pmtu; - -restart: - seq = read_seqbegin(&fnhe_seqlock); - fnhe_daddr = fnhe->fnhe_daddr; - gw = fnhe->fnhe_gw; - pmtu = fnhe->fnhe_pmtu; - expires = fnhe->fnhe_expires; - if (read_seqretry(&fnhe_seqlock, seq)) - goto restart; - - if (daddr != fnhe_daddr) - return; + bool ret = false; + + spin_lock_bh(&fnhe_lock); - if (pmtu) { - unsigned long diff = expires - jiffies; + if (daddr == fnhe->fnhe_daddr) { + struct rtable *orig; - if (time_before(jiffies, expires)) { - rt->rt_pmtu = pmtu; - dst_set_expires(&rt->dst, diff); + if (fnhe->fnhe_pmtu) { + unsigned long expires = fnhe->fnhe_expires; + unsigned long diff = expires - jiffies; + + if (time_before(jiffies, expires)) { + rt->rt_pmtu = fnhe->fnhe_pmtu; + dst_set_expires(&rt->dst, diff); + } } + if (fnhe->fnhe_gw) { + rt->rt_flags |= RTCF_REDIRECTED; + rt->rt_gateway = fnhe->fnhe_gw; + } + + orig = rcu_dereference(fnhe->fnhe_rth); + rcu_assign_pointer(fnhe->fnhe_rth, rt); + if (orig) + rt_free(orig); + + fnhe->fnhe_stamp = jiffies; + ret = true; + } else { + /* Routes we intend to cache in nexthop exception have + * the DST_NOCACHE bit clear. However, if we are + * unsuccessful at storing this route into the cache + * we really need to set it. + */ + rt->dst.flags |= DST_NOCACHE; } - if (gw) { - rt->rt_flags |= RTCF_REDIRECTED; - rt->rt_gateway = gw; - } - fnhe->fnhe_stamp = jiffies; -} + spin_unlock_bh(&fnhe_lock); -static inline void rt_release_rcu(struct rcu_head *head) -{ - struct dst_entry *dst = container_of(head, struct dst_entry, rcu_head); - dst_release(dst); + return ret; } -static void rt_cache_route(struct fib_nh *nh, struct rtable *rt) +static bool rt_cache_route(struct fib_nh *nh, struct rtable *rt) { - struct rtable *orig, *prev, **p = &nh->nh_rth_output; - - if (rt_is_input_route(rt)) - p = &nh->nh_rth_input; + struct rtable *orig, *prev, **p; + bool ret = true; + if (rt_is_input_route(rt)) { + p = (struct rtable **)&nh->nh_rth_input; + } else { + if (!nh->nh_pcpu_rth_output) + goto nocache; + p = (struct rtable **)__this_cpu_ptr(nh->nh_pcpu_rth_output); + } orig = *p; prev = cmpxchg(p, orig, rt); if (prev == orig) { - dst_clone(&rt->dst); if (orig) - call_rcu_bh(&orig->dst.rcu_head, rt_release_rcu); + rt_free(orig); + } else { + /* Routes we intend to cache in the FIB nexthop have + * the DST_NOCACHE bit clear. However, if we are + * unsuccessful at storing this route into the cache + * we really need to set it. + */ +nocache: + rt->dst.flags |= DST_NOCACHE; + ret = false; } + + return ret; } -static bool rt_cache_valid(struct rtable *rt) +static DEFINE_SPINLOCK(rt_uncached_lock); +static LIST_HEAD(rt_uncached_list); + +static void rt_add_uncached_list(struct rtable *rt) { - return (rt && rt->dst.obsolete == DST_OBSOLETE_FORCE_CHK); + spin_lock_bh(&rt_uncached_lock); + list_add_tail(&rt->rt_uncached, &rt_uncached_list); + spin_unlock_bh(&rt_uncached_lock); +} + +static void ipv4_dst_destroy(struct dst_entry *dst) +{ + struct rtable *rt = (struct rtable *) dst; + + if (dst->flags & DST_NOCACHE) { + spin_lock_bh(&rt_uncached_lock); + list_del(&rt->rt_uncached); + spin_unlock_bh(&rt_uncached_lock); + } +} + +void rt_flush_dev(struct net_device *dev) +{ + if (!list_empty(&rt_uncached_list)) { + struct net *net = dev_net(dev); + struct rtable *rt; + + spin_lock_bh(&rt_uncached_lock); + list_for_each_entry(rt, &rt_uncached_list, rt_uncached) { + if (rt->dst.dev != dev) + continue; + rt->dst.dev = net->loopback_dev; + dev_hold(rt->dst.dev); + dev_put(dev); + } + spin_unlock_bh(&rt_uncached_lock); + } +} + +static bool rt_cache_valid(const struct rtable *rt) +{ + return rt && + rt->dst.obsolete == DST_OBSOLETE_FORCE_CHK && + !rt_is_expired(rt); } static void rt_set_nexthop(struct rtable *rt, __be32 daddr, @@ -1232,20 +1304,24 @@ static void rt_set_nexthop(struct rtable *rt, __be32 daddr, struct fib_nh_exception *fnhe, struct fib_info *fi, u16 type, u32 itag) { + bool cached = false; + if (fi) { struct fib_nh *nh = &FIB_RES_NH(*res); if (nh->nh_gw && nh->nh_scope == RT_SCOPE_LINK) rt->rt_gateway = nh->nh_gw; - if (unlikely(fnhe)) - rt_bind_exception(rt, fnhe, daddr); dst_init_metrics(&rt->dst, fi->fib_metrics, true); #ifdef CONFIG_IP_ROUTE_CLASSID rt->dst.tclassid = nh->nh_tclassid; #endif - if (!(rt->dst.flags & DST_HOST)) - rt_cache_route(nh, rt); + if (unlikely(fnhe)) + cached = rt_bind_exception(rt, fnhe, daddr); + else if (!(rt->dst.flags & DST_NOCACHE)) + cached = rt_cache_route(nh, rt); } + if (unlikely(!cached)) + rt_add_uncached_list(rt); #ifdef CONFIG_IP_ROUTE_CLASSID #ifdef CONFIG_IP_MULTIPLE_TABLES @@ -1259,7 +1335,7 @@ static struct rtable *rt_dst_alloc(struct net_device *dev, bool nopolicy, bool noxfrm, bool will_cache) { return dst_alloc(&ipv4_dst_ops, dev, 1, DST_OBSOLETE_FORCE_CHK, - (will_cache ? 0 : DST_HOST) | DST_NOCACHE | + (will_cache ? 0 : (DST_HOST | DST_NOCACHE)) | (nopolicy ? DST_NOPOLICY : 0) | (noxfrm ? DST_NOXFRM : 0)); } @@ -1312,6 +1388,7 @@ static int ip_route_input_mc(struct sk_buff *skb, __be32 daddr, __be32 saddr, rth->rt_iif = 0; rth->rt_pmtu = 0; rth->rt_gateway = 0; + INIT_LIST_HEAD(&rth->rt_uncached); if (our) { rth->dst.input= ip_local_deliver; rth->rt_flags |= RTCF_LOCAL; @@ -1364,8 +1441,7 @@ static void ip_handle_martian_source(struct net_device *dev, static int __mkroute_input(struct sk_buff *skb, const struct fib_result *res, struct in_device *in_dev, - __be32 daddr, __be32 saddr, u32 tos, - struct rtable **result) + __be32 daddr, __be32 saddr, u32 tos) { struct rtable *rth; int err; @@ -1414,9 +1490,9 @@ static int __mkroute_input(struct sk_buff *skb, do_cache = false; if (res->fi) { if (!itag) { - rth = FIB_RES_NH(*res).nh_rth_input; + rth = rcu_dereference(FIB_RES_NH(*res).nh_rth_input); if (rt_cache_valid(rth)) { - dst_hold(&rth->dst); + skb_dst_set_noref(skb, &rth->dst); goto out; } do_cache = true; @@ -1438,13 +1514,14 @@ static int __mkroute_input(struct sk_buff *skb, rth->rt_iif = 0; rth->rt_pmtu = 0; rth->rt_gateway = 0; + INIT_LIST_HEAD(&rth->rt_uncached); rth->dst.input = ip_forward; rth->dst.output = ip_output; rt_set_nexthop(rth, daddr, res, NULL, res->fi, res->type, itag); + skb_dst_set(skb, &rth->dst); out: - *result = rth; err = 0; cleanup: return err; @@ -1456,21 +1533,13 @@ static int ip_mkroute_input(struct sk_buff *skb, struct in_device *in_dev, __be32 daddr, __be32 saddr, u32 tos) { - struct rtable *rth = NULL; - int err; - #ifdef CONFIG_IP_ROUTE_MULTIPATH if (res->fi && res->fi->fib_nhs > 1) fib_select_multipath(res); #endif /* create a routing cache entry */ - err = __mkroute_input(skb, res, in_dev, daddr, saddr, tos, &rth); - if (err) - return err; - - skb_dst_set(skb, &rth->dst); - return 0; + return __mkroute_input(skb, res, in_dev, daddr, saddr, tos); } /* @@ -1584,10 +1653,11 @@ local_input: do_cache = false; if (res.fi) { if (!itag) { - rth = FIB_RES_NH(res).nh_rth_input; + rth = rcu_dereference(FIB_RES_NH(res).nh_rth_input); if (rt_cache_valid(rth)) { - dst_hold(&rth->dst); - goto set_and_out; + skb_dst_set_noref(skb, &rth->dst); + err = 0; + goto out; } do_cache = true; } @@ -1611,6 +1681,7 @@ local_input: rth->rt_iif = 0; rth->rt_pmtu = 0; rth->rt_gateway = 0; + INIT_LIST_HEAD(&rth->rt_uncached); if (res.type == RTN_UNREACHABLE) { rth->dst.input= ip_error; rth->dst.error= -err; @@ -1618,7 +1689,6 @@ local_input: } if (do_cache) rt_cache_route(&FIB_RES_NH(res), rth); -set_and_out: skb_dst_set(skb, &rth->dst); err = 0; goto out; @@ -1656,8 +1726,8 @@ martian_source_keep_err: goto out; } -int ip_route_input(struct sk_buff *skb, __be32 daddr, __be32 saddr, - u8 tos, struct net_device *dev) +int ip_route_input_noref(struct sk_buff *skb, __be32 daddr, __be32 saddr, + u8 tos, struct net_device *dev) { int res; @@ -1700,7 +1770,7 @@ int ip_route_input(struct sk_buff *skb, __be32 daddr, __be32 saddr, rcu_read_unlock(); return res; } -EXPORT_SYMBOL(ip_route_input); +EXPORT_SYMBOL(ip_route_input_noref); /* called with rcu_read_lock() */ static struct rtable *__mkroute_output(const struct fib_result *res, @@ -1750,19 +1820,23 @@ static struct rtable *__mkroute_output(const struct fib_result *res, fnhe = NULL; if (fi) { + struct rtable __rcu **prth; + fnhe = find_exception(&FIB_RES_NH(*res), fl4->daddr); - if (!fnhe) { - rth = FIB_RES_NH(*res).nh_rth_output; - if (rt_cache_valid(rth)) { - dst_hold(&rth->dst); - return rth; - } + if (fnhe) + prth = &fnhe->fnhe_rth; + else + prth = __this_cpu_ptr(FIB_RES_NH(*res).nh_pcpu_rth_output); + rth = rcu_dereference(*prth); + if (rt_cache_valid(rth)) { + dst_hold(&rth->dst); + return rth; } } rth = rt_dst_alloc(dev_out, IN_DEV_CONF_GET(in_dev, NOPOLICY), IN_DEV_CONF_GET(in_dev, NOXFRM), - fi && !fnhe); + fi); if (!rth) return ERR_PTR(-ENOBUFS); @@ -1775,6 +1849,7 @@ static struct rtable *__mkroute_output(const struct fib_result *res, rth->rt_iif = orig_oif ? : 0; rth->rt_pmtu = 0; rth->rt_gateway = 0; + INIT_LIST_HEAD(&rth->rt_uncached); RT_CACHE_STAT_INC(out_slow_tot); @@ -2054,6 +2129,8 @@ struct dst_entry *ipv4_blackhole_route(struct net *net, struct dst_entry *dst_or rt->rt_type = ort->rt_type; rt->rt_gateway = ort->rt_gateway; + INIT_LIST_HEAD(&rt->rt_uncached); + dst_free(new); } diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c index 5840c32..1b5ce96 100644 --- a/net/ipv4/sysctl_net_ipv4.c +++ b/net/ipv4/sysctl_net_ipv4.c @@ -184,7 +184,7 @@ static int ipv4_tcp_mem(ctl_table *ctl, int write, int ret; unsigned long vec[3]; struct net *net = current->nsproxy->net_ns; -#ifdef CONFIG_CGROUP_MEM_RES_CTLR_KMEM +#ifdef CONFIG_MEMCG_KMEM struct mem_cgroup *memcg; #endif @@ -203,7 +203,7 @@ static int ipv4_tcp_mem(ctl_table *ctl, int write, if (ret) return ret; -#ifdef CONFIG_CGROUP_MEM_RES_CTLR_KMEM +#ifdef CONFIG_MEMCG_KMEM rcu_read_lock(); memcg = mem_cgroup_from_task(current); @@ -784,13 +784,6 @@ static struct ctl_table ipv4_net_table[] = { .proc_handler = proc_dointvec }, { - .procname = "rt_cache_rebuild_count", - .data = &init_net.ipv4.sysctl_rt_cache_rebuild_count, - .maxlen = sizeof(int), - .mode = 0644, - .proc_handler = proc_dointvec - }, - { .procname = "ping_group_range", .data = &init_net.ipv4.sysctl_ping_group_range, .maxlen = sizeof(init_net.ipv4.sysctl_ping_group_range), @@ -829,8 +822,6 @@ static __net_init int ipv4_sysctl_init_net(struct net *net) table[5].data = &net->ipv4.sysctl_icmp_ratemask; table[6].data = - &net->ipv4.sysctl_rt_cache_rebuild_count; - table[7].data = &net->ipv4.sysctl_ping_group_range; } @@ -842,8 +833,6 @@ static __net_init int ipv4_sysctl_init_net(struct net *net) net->ipv4.sysctl_ping_group_range[0] = 1; net->ipv4.sysctl_ping_group_range[1] = 0; - net->ipv4.sysctl_rt_cache_rebuild_count = 4; - tcp_init_mem(net); net->ipv4.ipv4_hdr = register_net_sysctl(net, "net/ipv4", table); diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 581ecf0..e7e6eea 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -2681,7 +2681,10 @@ static int do_tcp_setsockopt(struct sock *sk, int level, /* Cap the max timeout in ms TCP will retry/retrans * before giving up and aborting (ETIMEDOUT) a connection. */ - icsk->icsk_user_timeout = msecs_to_jiffies(val); + if (val < 0) + err = -EINVAL; + else + icsk->icsk_user_timeout = msecs_to_jiffies(val); break; default: err = -ENOPROTOOPT; diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 3e07a64..2fd2bc9 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -4351,19 +4351,20 @@ static void tcp_ofo_queue(struct sock *sk) static bool tcp_prune_ofo_queue(struct sock *sk); static int tcp_prune_queue(struct sock *sk); -static int tcp_try_rmem_schedule(struct sock *sk, unsigned int size) +static int tcp_try_rmem_schedule(struct sock *sk, struct sk_buff *skb, + unsigned int size) { if (atomic_read(&sk->sk_rmem_alloc) > sk->sk_rcvbuf || - !sk_rmem_schedule(sk, size)) { + !sk_rmem_schedule(sk, skb, size)) { if (tcp_prune_queue(sk) < 0) return -1; - if (!sk_rmem_schedule(sk, size)) { + if (!sk_rmem_schedule(sk, skb, size)) { if (!tcp_prune_ofo_queue(sk)) return -1; - if (!sk_rmem_schedule(sk, size)) + if (!sk_rmem_schedule(sk, skb, size)) return -1; } } @@ -4418,7 +4419,7 @@ static void tcp_data_queue_ofo(struct sock *sk, struct sk_buff *skb) TCP_ECN_check_ce(tp, skb); - if (unlikely(tcp_try_rmem_schedule(sk, skb->truesize))) { + if (unlikely(tcp_try_rmem_schedule(sk, skb, skb->truesize))) { NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPOFODROP); __kfree_skb(skb); return; @@ -4552,17 +4553,17 @@ static int __must_check tcp_queue_rcv(struct sock *sk, struct sk_buff *skb, int int tcp_send_rcvq(struct sock *sk, struct msghdr *msg, size_t size) { - struct sk_buff *skb; + struct sk_buff *skb = NULL; struct tcphdr *th; bool fragstolen; - if (tcp_try_rmem_schedule(sk, size + sizeof(*th))) - goto err; - skb = alloc_skb(size + sizeof(*th), sk->sk_allocation); if (!skb) goto err; + if (tcp_try_rmem_schedule(sk, skb, size + sizeof(*th))) + goto err_free; + th = (struct tcphdr *)skb_put(skb, sizeof(*th)); skb_reset_transport_header(skb); memset(th, 0, sizeof(*th)); @@ -4633,7 +4634,7 @@ static void tcp_data_queue(struct sock *sk, struct sk_buff *skb) if (eaten <= 0) { queue_and_out: if (eaten < 0 && - tcp_try_rmem_schedule(sk, skb->truesize)) + tcp_try_rmem_schedule(sk, skb, skb->truesize)) goto drop; eaten = tcp_queue_rcv(sk, skb, 0, &fragstolen); @@ -5475,7 +5476,9 @@ int tcp_rcv_established(struct sock *sk, struct sk_buff *skb, if (tp->copied_seq == tp->rcv_nxt && len - tcp_header_len <= tp->ucopy.len) { #ifdef CONFIG_NET_DMA - if (tcp_dma_try_early_copy(sk, skb, tcp_header_len)) { + if (tp->ucopy.task == current && + sock_owned_by_user(sk) && + tcp_dma_try_early_copy(sk, skb, tcp_header_len)) { copied_early = 1; eaten = 1; } @@ -5602,7 +5605,7 @@ void tcp_finish_connect(struct sock *sk, struct sk_buff *skb) tcp_set_state(sk, TCP_ESTABLISHED); if (skb != NULL) { - sk->sk_rx_dst = dst_clone(skb_dst(skb)); + inet_sk_rx_dst_set(sk, skb); security_inet_conn_established(sk, skb); } diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index 3e30548..42b2a6a 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -1617,21 +1617,19 @@ int tcp_v4_do_rcv(struct sock *sk, struct sk_buff *skb) #endif if (sk->sk_state == TCP_ESTABLISHED) { /* Fast path */ + struct dst_entry *dst = sk->sk_rx_dst; + sock_rps_save_rxhash(sk, skb); - if (sk->sk_rx_dst) { - struct dst_entry *dst = sk->sk_rx_dst; - if (dst->ops->check(dst, 0) == NULL) { + if (dst) { + if (inet_sk(sk)->rx_dst_ifindex != skb->skb_iif || + dst->ops->check(dst, 0) == NULL) { dst_release(dst); sk->sk_rx_dst = NULL; } } - if (unlikely(sk->sk_rx_dst == NULL)) { - struct inet_sock *icsk = inet_sk(sk); - struct rtable *rt = skb_rtable(skb); + if (unlikely(sk->sk_rx_dst == NULL)) + inet_sk_rx_dst_set(sk, skb); - sk->sk_rx_dst = dst_clone(&rt->dst); - icsk->rx_dst_ifindex = inet_iif(skb); - } if (tcp_rcv_established(sk, skb, tcp_hdr(skb), skb->len)) { rsk = sk; goto reset; @@ -1686,7 +1684,6 @@ void tcp_v4_early_demux(struct sk_buff *skb) struct net *net = dev_net(skb->dev); const struct iphdr *iph; const struct tcphdr *th; - struct net_device *dev; struct sock *sk; if (skb->pkt_type != PACKET_HOST) @@ -1701,24 +1698,20 @@ void tcp_v4_early_demux(struct sk_buff *skb) if (th->doff < sizeof(struct tcphdr) / 4) return; - if (!pskb_may_pull(skb, ip_hdrlen(skb) + th->doff * 4)) - return; - - dev = skb->dev; sk = __inet_lookup_established(net, &tcp_hashinfo, iph->saddr, th->source, iph->daddr, ntohs(th->dest), - dev->ifindex); + skb->skb_iif); if (sk) { skb->sk = sk; skb->destructor = sock_edemux; if (sk->sk_state != TCP_TIME_WAIT) { struct dst_entry *dst = sk->sk_rx_dst; - struct inet_sock *icsk = inet_sk(sk); + if (dst) dst = dst_check(dst, 0); if (dst && - icsk->rx_dst_ifindex == dev->ifindex) + inet_sk(sk)->rx_dst_ifindex == skb->skb_iif) skb_dst_set_noref(skb, dst); } } @@ -2640,7 +2633,7 @@ struct proto tcp_prot = { .compat_setsockopt = compat_tcp_setsockopt, .compat_getsockopt = compat_tcp_getsockopt, #endif -#ifdef CONFIG_CGROUP_MEM_RES_CTLR_KMEM +#ifdef CONFIG_MEMCG_KMEM .init_cgroup = tcp_init_cgroup, .destroy_cgroup = tcp_destroy_cgroup, .proto_cgroup = tcp_proto_cgroup, diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c index 5912ac3..232a90c 100644 --- a/net/ipv4/tcp_minisocks.c +++ b/net/ipv4/tcp_minisocks.c @@ -387,7 +387,7 @@ struct sock *tcp_create_openreq_child(struct sock *sk, struct request_sock *req, struct tcp_sock *oldtp = tcp_sk(sk); struct tcp_cookie_values *oldcvp = oldtp->cookie_values; - newsk->sk_rx_dst = dst_clone(skb_dst(skb)); + inet_sk_rx_dst_set(newsk, skb); /* TCP Cookie Transactions require space for the cookie pair, * as it differs for each connection. There is no need to diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index 33cd065..3f1bcff 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -2045,7 +2045,8 @@ void __tcp_push_pending_frames(struct sock *sk, unsigned int cur_mss, if (unlikely(sk->sk_state == TCP_CLOSE)) return; - if (tcp_write_xmit(sk, cur_mss, nonagle, 0, GFP_ATOMIC)) + if (tcp_write_xmit(sk, cur_mss, nonagle, 0, + sk_gfp_atomic(sk, GFP_ATOMIC))) tcp_check_probe_timer(sk); } @@ -2666,7 +2667,8 @@ struct sk_buff *tcp_make_synack(struct sock *sk, struct dst_entry *dst, if (cvp != NULL && cvp->s_data_constant && cvp->s_data_desired) s_data_desired = cvp->s_data_desired; - skb = alloc_skb(MAX_TCP_HEADER + 15 + s_data_desired, GFP_ATOMIC); + skb = alloc_skb(MAX_TCP_HEADER + 15 + s_data_desired, + sk_gfp_atomic(sk, GFP_ATOMIC)); if (unlikely(!skb)) { dst_release(dst); return NULL; @@ -3064,7 +3066,7 @@ void tcp_send_ack(struct sock *sk) * tcp_transmit_skb() will set the ownership to this * sock. */ - buff = alloc_skb(MAX_TCP_HEADER, GFP_ATOMIC); + buff = alloc_skb(MAX_TCP_HEADER, sk_gfp_atomic(sk, GFP_ATOMIC)); if (buff == NULL) { inet_csk_schedule_ack(sk); inet_csk(sk)->icsk_ack.ato = TCP_ATO_MIN; @@ -3079,7 +3081,7 @@ void tcp_send_ack(struct sock *sk) /* Send it off, this clears delayed acks for us. */ TCP_SKB_CB(buff)->when = tcp_time_stamp; - tcp_transmit_skb(sk, buff, 0, GFP_ATOMIC); + tcp_transmit_skb(sk, buff, 0, sk_gfp_atomic(sk, GFP_ATOMIC)); } /* This routine sends a packet with an out of date sequence @@ -3099,7 +3101,7 @@ static int tcp_xmit_probe_skb(struct sock *sk, int urgent) struct sk_buff *skb; /* We don't queue it, tcp_transmit_skb() sets ownership. */ - skb = alloc_skb(MAX_TCP_HEADER, GFP_ATOMIC); + skb = alloc_skb(MAX_TCP_HEADER, sk_gfp_atomic(sk, GFP_ATOMIC)); if (skb == NULL) return -1; diff --git a/net/ipv4/xfrm4_input.c b/net/ipv4/xfrm4_input.c index 58d23a5..06814b6 100644 --- a/net/ipv4/xfrm4_input.c +++ b/net/ipv4/xfrm4_input.c @@ -27,8 +27,8 @@ static inline int xfrm4_rcv_encap_finish(struct sk_buff *skb) if (skb_dst(skb) == NULL) { const struct iphdr *iph = ip_hdr(skb); - if (ip_route_input(skb, iph->daddr, iph->saddr, - iph->tos, skb->dev)) + if (ip_route_input_noref(skb, iph->daddr, iph->saddr, + iph->tos, skb->dev)) goto drop; } return dst_input(skb); diff --git a/net/ipv4/xfrm4_policy.c b/net/ipv4/xfrm4_policy.c index c628184..681ea2f 100644 --- a/net/ipv4/xfrm4_policy.c +++ b/net/ipv4/xfrm4_policy.c @@ -92,6 +92,7 @@ static int xfrm4_fill_dst(struct xfrm_dst *xdst, struct net_device *dev, xdst->u.rt.rt_type = rt->rt_type; xdst->u.rt.rt_gateway = rt->rt_gateway; xdst->u.rt.rt_pmtu = rt->rt_pmtu; + INIT_LIST_HEAD(&xdst->u.rt.rt_uncached); return 0; } diff --git a/net/ipv6/ip6_input.c b/net/ipv6/ip6_input.c index 5ab923e..a52d864 100644 --- a/net/ipv6/ip6_input.c +++ b/net/ipv6/ip6_input.c @@ -47,9 +47,16 @@ -inline int ip6_rcv_finish( struct sk_buff *skb) +int ip6_rcv_finish(struct sk_buff *skb) { - if (skb_dst(skb) == NULL) + if (sysctl_ip_early_demux && !skb_dst(skb)) { + const struct inet6_protocol *ipprot; + + ipprot = rcu_dereference(inet6_protos[ipv6_hdr(skb)->nexthdr]); + if (ipprot && ipprot->early_demux) + ipprot->early_demux(skb); + } + if (!skb_dst(skb)) ip6_route_input(skb); return dst_input(skb); diff --git a/net/ipv6/route.c b/net/ipv6/route.c index cf02cb9..8e80fd2 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -2480,12 +2480,8 @@ static int rt6_fill_node(struct net *net, goto nla_put_failure; if (nla_put_u32(skb, RTA_PRIORITY, rt->rt6i_metric)) goto nla_put_failure; - if (!(rt->rt6i_flags & RTF_EXPIRES)) - expires = 0; - else if (rt->dst.expires - jiffies < INT_MAX) - expires = rt->dst.expires - jiffies; - else - expires = INT_MAX; + + expires = (rt->rt6i_flags & RTF_EXPIRES) ? rt->dst.expires - jiffies : 0; if (rtnl_put_cacheinfo(skb, &rt->dst, 0, expires, rt->dst.error) < 0) goto nla_put_failure; diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index f49476e..c66b90f 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -1299,7 +1299,8 @@ static struct sock * tcp_v6_syn_recv_sock(struct sock *sk, struct sk_buff *skb, /* Clone pktoptions received with SYN */ newnp->pktoptions = NULL; if (treq->pktopts != NULL) { - newnp->pktoptions = skb_clone(treq->pktopts, GFP_ATOMIC); + newnp->pktoptions = skb_clone(treq->pktopts, + sk_gfp_atomic(sk, GFP_ATOMIC)); consume_skb(treq->pktopts); treq->pktopts = NULL; if (newnp->pktoptions) @@ -1349,7 +1350,8 @@ static struct sock * tcp_v6_syn_recv_sock(struct sock *sk, struct sk_buff *skb, * across. Shucks. */ tcp_md5_do_add(newsk, (union tcp_md5_addr *)&newnp->daddr, - AF_INET6, key->key, key->keylen, GFP_ATOMIC); + AF_INET6, key->key, key->keylen, + sk_gfp_atomic(sk, GFP_ATOMIC)); } #endif @@ -1442,7 +1444,7 @@ static int tcp_v6_do_rcv(struct sock *sk, struct sk_buff *skb) --ANK (980728) */ if (np->rxopt.all) - opt_skb = skb_clone(skb, GFP_ATOMIC); + opt_skb = skb_clone(skb, sk_gfp_atomic(sk, GFP_ATOMIC)); if (sk->sk_state == TCP_ESTABLISHED) { /* Fast path */ sock_rps_save_rxhash(sk, skb); @@ -1674,6 +1676,43 @@ do_time_wait: goto discard_it; } +static void tcp_v6_early_demux(struct sk_buff *skb) +{ + const struct ipv6hdr *hdr; + const struct tcphdr *th; + struct sock *sk; + + if (skb->pkt_type != PACKET_HOST) + return; + + if (!pskb_may_pull(skb, skb_transport_offset(skb) + sizeof(struct tcphdr))) + return; + + hdr = ipv6_hdr(skb); + th = tcp_hdr(skb); + + if (th->doff < sizeof(struct tcphdr) / 4) + return; + + sk = __inet6_lookup_established(dev_net(skb->dev), &tcp_hashinfo, + &hdr->saddr, th->source, + &hdr->daddr, ntohs(th->dest), + inet6_iif(skb)); + if (sk) { + skb->sk = sk; + skb->destructor = sock_edemux; + if (sk->sk_state != TCP_TIME_WAIT) { + struct dst_entry *dst = sk->sk_rx_dst; + struct inet_sock *icsk = inet_sk(sk); + if (dst) + dst = dst_check(dst, 0); + if (dst && + icsk->rx_dst_ifindex == inet6_iif(skb)) + skb_dst_set_noref(skb, dst); + } + } +} + static struct timewait_sock_ops tcp6_timewait_sock_ops = { .twsk_obj_size = sizeof(struct tcp6_timewait_sock), .twsk_unique = tcp_twsk_unique, @@ -1978,12 +2017,13 @@ struct proto tcpv6_prot = { .compat_setsockopt = compat_tcp_setsockopt, .compat_getsockopt = compat_tcp_getsockopt, #endif -#ifdef CONFIG_CGROUP_MEM_RES_CTLR_KMEM +#ifdef CONFIG_MEMCG_KMEM .proto_cgroup = tcp_proto_cgroup, #endif }; static const struct inet6_protocol tcpv6_protocol = { + .early_demux = tcp_v6_early_demux, .handler = tcp_v6_rcv, .err_handler = tcp_v6_err, .gso_send_check = tcp_v6_gso_send_check, diff --git a/net/mac80211/led.c b/net/mac80211/led.c index 1bf7903..bcffa69 100644 --- a/net/mac80211/led.c +++ b/net/mac80211/led.c @@ -276,7 +276,7 @@ static void ieee80211_stop_tpt_led_trig(struct ieee80211_local *local) read_lock(&tpt_trig->trig.leddev_list_lock); list_for_each_entry(led_cdev, &tpt_trig->trig.led_cdevs, trig_list) - led_brightness_set(led_cdev, LED_OFF); + led_set_brightness(led_cdev, LED_OFF); read_unlock(&tpt_trig->trig.leddev_list_lock); } diff --git a/net/openvswitch/actions.c b/net/openvswitch/actions.c index 320fa0e..f3f96ba 100644 --- a/net/openvswitch/actions.c +++ b/net/openvswitch/actions.c @@ -325,9 +325,6 @@ static int sample(struct datapath *dp, struct sk_buff *skb, } } - if (!acts_list) - return 0; - return do_execute_actions(dp, skb, nla_data(acts_list), nla_len(acts_list), true); } diff --git a/net/sctp/ulpevent.c b/net/sctp/ulpevent.c index 33d8947..10c018a 100644 --- a/net/sctp/ulpevent.c +++ b/net/sctp/ulpevent.c @@ -702,7 +702,8 @@ struct sctp_ulpevent *sctp_ulpevent_make_rcvmsg(struct sctp_association *asoc, if (rx_count >= asoc->base.sk->sk_rcvbuf) { if ((asoc->base.sk->sk_userlocks & SOCK_RCVBUF_LOCK) || - (!sk_rmem_schedule(asoc->base.sk, chunk->skb->truesize))) + (!sk_rmem_schedule(asoc->base.sk, chunk->skb, + chunk->skb->truesize))) goto fail; } diff --git a/net/sunrpc/Kconfig b/net/sunrpc/Kconfig index 9fe8857..03d03e3 100644 --- a/net/sunrpc/Kconfig +++ b/net/sunrpc/Kconfig @@ -21,6 +21,11 @@ config SUNRPC_XPRT_RDMA If unsure, say N. +config SUNRPC_SWAP + bool + depends on SUNRPC + select NETVM + config RPCSEC_GSS_KRB5 tristate "Secure RPC: Kerberos V mechanism" depends on SUNRPC && CRYPTO diff --git a/net/sunrpc/auth.c b/net/sunrpc/auth.c index 727e506..b5c067b 100644 --- a/net/sunrpc/auth.c +++ b/net/sunrpc/auth.c @@ -13,6 +13,7 @@ #include <linux/errno.h> #include <linux/hash.h> #include <linux/sunrpc/clnt.h> +#include <linux/sunrpc/gss_api.h> #include <linux/spinlock.h> #ifdef RPC_DEBUG @@ -122,6 +123,59 @@ rpcauth_unregister(const struct rpc_authops *ops) } EXPORT_SYMBOL_GPL(rpcauth_unregister); +/** + * rpcauth_list_flavors - discover registered flavors and pseudoflavors + * @array: array to fill in + * @size: size of "array" + * + * Returns the number of array items filled in, or a negative errno. + * + * The returned array is not sorted by any policy. Callers should not + * rely on the order of the items in the returned array. + */ +int +rpcauth_list_flavors(rpc_authflavor_t *array, int size) +{ + rpc_authflavor_t flavor; + int result = 0; + + spin_lock(&rpc_authflavor_lock); + for (flavor = 0; flavor < RPC_AUTH_MAXFLAVOR; flavor++) { + const struct rpc_authops *ops = auth_flavors[flavor]; + rpc_authflavor_t pseudos[4]; + int i, len; + + if (result >= size) { + result = -ENOMEM; + break; + } + + if (ops == NULL) + continue; + if (ops->list_pseudoflavors == NULL) { + array[result++] = ops->au_flavor; + continue; + } + len = ops->list_pseudoflavors(pseudos, ARRAY_SIZE(pseudos)); + if (len < 0) { + result = len; + break; + } + for (i = 0; i < len; i++) { + if (result >= size) { + result = -ENOMEM; + break; + } + array[result++] = pseudos[i]; + } + } + spin_unlock(&rpc_authflavor_lock); + + dprintk("RPC: %s returns %d\n", __func__, result); + return result; +} +EXPORT_SYMBOL_GPL(rpcauth_list_flavors); + struct rpc_auth * rpcauth_create(rpc_authflavor_t pseudoflavor, struct rpc_clnt *clnt) { diff --git a/net/sunrpc/auth_gss/auth_gss.c b/net/sunrpc/auth_gss/auth_gss.c index d3ad81f..34c5220 100644 --- a/net/sunrpc/auth_gss/auth_gss.c +++ b/net/sunrpc/auth_gss/auth_gss.c @@ -1619,6 +1619,7 @@ static const struct rpc_authops authgss_ops = { .crcreate = gss_create_cred, .pipes_create = gss_pipes_dentries_create, .pipes_destroy = gss_pipes_dentries_destroy, + .list_pseudoflavors = gss_mech_list_pseudoflavors, }; static const struct rpc_credops gss_credops = { diff --git a/net/sunrpc/auth_gss/gss_mech_switch.c b/net/sunrpc/auth_gss/gss_mech_switch.c index 782bfe1..b174fcd 100644 --- a/net/sunrpc/auth_gss/gss_mech_switch.c +++ b/net/sunrpc/auth_gss/gss_mech_switch.c @@ -239,14 +239,28 @@ gss_mech_get_by_pseudoflavor(u32 pseudoflavor) EXPORT_SYMBOL_GPL(gss_mech_get_by_pseudoflavor); -int gss_mech_list_pseudoflavors(rpc_authflavor_t *array_ptr) +/** + * gss_mech_list_pseudoflavors - Discover registered GSS pseudoflavors + * @array: array to fill in + * @size: size of "array" + * + * Returns the number of array items filled in, or a negative errno. + * + * The returned array is not sorted by any policy. Callers should not + * rely on the order of the items in the returned array. + */ +int gss_mech_list_pseudoflavors(rpc_authflavor_t *array_ptr, int size) { struct gss_api_mech *pos = NULL; int j, i = 0; spin_lock(®istered_mechs_lock); list_for_each_entry(pos, ®istered_mechs, gm_list) { - for (j=0; j < pos->gm_pf_num; j++) { + for (j = 0; j < pos->gm_pf_num; j++) { + if (i >= size) { + spin_unlock(®istered_mechs_lock); + return -ENOMEM; + } array_ptr[i++] = pos->gm_pfs[j].pseudoflavor; } } @@ -254,8 +268,6 @@ int gss_mech_list_pseudoflavors(rpc_authflavor_t *array_ptr) return i; } -EXPORT_SYMBOL_GPL(gss_mech_list_pseudoflavors); - u32 gss_svc_to_pseudoflavor(struct gss_api_mech *gm, u32 service) { diff --git a/net/sunrpc/cache.c b/net/sunrpc/cache.c index 47ad266..2afd2a8 100644 --- a/net/sunrpc/cache.c +++ b/net/sunrpc/cache.c @@ -1349,8 +1349,11 @@ static int c_show(struct seq_file *m, void *p) if (cache_check(cd, cp, NULL)) /* cache_check does a cache_put on failure */ seq_printf(m, "# "); - else + else { + if (cache_is_expired(cd, cp)) + seq_printf(m, "# "); cache_put(cp, cd); + } return cd->cache_show(m, cd, cp); } diff --git a/net/sunrpc/clnt.c b/net/sunrpc/clnt.c index 00eb859..fa48c60 100644 --- a/net/sunrpc/clnt.c +++ b/net/sunrpc/clnt.c @@ -717,6 +717,15 @@ void rpc_task_set_client(struct rpc_task *task, struct rpc_clnt *clnt) atomic_inc(&clnt->cl_count); if (clnt->cl_softrtry) task->tk_flags |= RPC_TASK_SOFT; + if (sk_memalloc_socks()) { + struct rpc_xprt *xprt; + + rcu_read_lock(); + xprt = rcu_dereference(clnt->cl_xprt); + if (xprt->swapper) + task->tk_flags |= RPC_TASK_SWAPPER; + rcu_read_unlock(); + } /* Add to the client's list of all tasks */ spin_lock(&clnt->cl_lock); list_add_tail(&task->tk_task, &clnt->cl_tasks); @@ -1844,12 +1853,13 @@ call_timeout(struct rpc_task *task) return; } if (RPC_IS_SOFT(task)) { - if (clnt->cl_chatty) + if (clnt->cl_chatty) { rcu_read_lock(); printk(KERN_NOTICE "%s: server %s not responding, timed out\n", clnt->cl_protname, rcu_dereference(clnt->cl_xprt)->servername); rcu_read_unlock(); + } if (task->tk_flags & RPC_TASK_TIMEOUT) rpc_exit(task, -ETIMEDOUT); else diff --git a/net/sunrpc/rpcb_clnt.c b/net/sunrpc/rpcb_clnt.c index 92509ff..a70acae 100644 --- a/net/sunrpc/rpcb_clnt.c +++ b/net/sunrpc/rpcb_clnt.c @@ -251,7 +251,7 @@ static int rpcb_create_local_unix(struct net *net) if (IS_ERR(clnt)) { dprintk("RPC: failed to create AF_LOCAL rpcbind " "client (errno %ld).\n", PTR_ERR(clnt)); - result = -PTR_ERR(clnt); + result = PTR_ERR(clnt); goto out; } @@ -298,7 +298,7 @@ static int rpcb_create_local_net(struct net *net) if (IS_ERR(clnt)) { dprintk("RPC: failed to create local rpcbind " "client (errno %ld).\n", PTR_ERR(clnt)); - result = -PTR_ERR(clnt); + result = PTR_ERR(clnt); goto out; } diff --git a/net/sunrpc/sched.c b/net/sunrpc/sched.c index 994cfea..128494e 100644 --- a/net/sunrpc/sched.c +++ b/net/sunrpc/sched.c @@ -300,8 +300,9 @@ EXPORT_SYMBOL_GPL(__rpc_wait_for_completion_task); /* * Make an RPC task runnable. * - * Note: If the task is ASYNC, this must be called with - * the spinlock held to protect the wait queue operation. + * Note: If the task is ASYNC, and is being made runnable after sitting on an + * rpc_wait_queue, this must be called with the queue spinlock held to protect + * the wait queue operation. */ static void rpc_make_runnable(struct rpc_task *task) { @@ -790,7 +791,9 @@ void rpc_execute(struct rpc_task *task) static void rpc_async_schedule(struct work_struct *work) { + current->flags |= PF_FSTRANS; __rpc_execute(container_of(work, struct rpc_task, u.tk_work)); + current->flags &= ~PF_FSTRANS; } /** @@ -812,7 +815,10 @@ static void rpc_async_schedule(struct work_struct *work) void *rpc_malloc(struct rpc_task *task, size_t size) { struct rpc_buffer *buf; - gfp_t gfp = RPC_IS_SWAPPER(task) ? GFP_ATOMIC : GFP_NOWAIT; + gfp_t gfp = GFP_NOWAIT; + + if (RPC_IS_SWAPPER(task)) + gfp |= __GFP_MEMALLOC; size += sizeof(struct rpc_buffer); if (size <= RPC_BUFFER_MAXSIZE) @@ -886,7 +892,7 @@ static void rpc_init_task(struct rpc_task *task, const struct rpc_task_setup *ta static struct rpc_task * rpc_alloc_task(void) { - return (struct rpc_task *)mempool_alloc(rpc_task_mempool, GFP_NOFS); + return (struct rpc_task *)mempool_alloc(rpc_task_mempool, GFP_NOIO); } /* diff --git a/net/sunrpc/xdr.c b/net/sunrpc/xdr.c index 0cf1655..0afba1b 100644 --- a/net/sunrpc/xdr.c +++ b/net/sunrpc/xdr.c @@ -129,34 +129,6 @@ xdr_terminate_string(struct xdr_buf *buf, const u32 len) EXPORT_SYMBOL_GPL(xdr_terminate_string); void -xdr_encode_pages(struct xdr_buf *xdr, struct page **pages, unsigned int base, - unsigned int len) -{ - struct kvec *tail = xdr->tail; - u32 *p; - - xdr->pages = pages; - xdr->page_base = base; - xdr->page_len = len; - - p = (u32 *)xdr->head[0].iov_base + XDR_QUADLEN(xdr->head[0].iov_len); - tail->iov_base = p; - tail->iov_len = 0; - - if (len & 3) { - unsigned int pad = 4 - (len & 3); - - *p = 0; - tail->iov_base = (char *)p + (len & 3); - tail->iov_len = pad; - len += pad; - } - xdr->buflen += len; - xdr->len += len; -} -EXPORT_SYMBOL_GPL(xdr_encode_pages); - -void xdr_inline_pages(struct xdr_buf *xdr, unsigned int offset, struct page **pages, unsigned int base, unsigned int len) { @@ -457,6 +429,16 @@ xdr_shift_buf(struct xdr_buf *buf, size_t len) EXPORT_SYMBOL_GPL(xdr_shift_buf); /** + * xdr_stream_pos - Return the current offset from the start of the xdr_stream + * @xdr: pointer to struct xdr_stream + */ +unsigned int xdr_stream_pos(const struct xdr_stream *xdr) +{ + return (unsigned int)(XDR_QUADLEN(xdr->buf->len) - xdr->nwords) << 2; +} +EXPORT_SYMBOL_GPL(xdr_stream_pos); + +/** * xdr_init_encode - Initialize a struct xdr_stream for sending data. * @xdr: pointer to xdr_stream struct * @buf: pointer to XDR buffer in which to encode data @@ -556,13 +538,11 @@ void xdr_write_pages(struct xdr_stream *xdr, struct page **pages, unsigned int b EXPORT_SYMBOL_GPL(xdr_write_pages); static void xdr_set_iov(struct xdr_stream *xdr, struct kvec *iov, - __be32 *p, unsigned int len) + unsigned int len) { if (len > iov->iov_len) len = iov->iov_len; - if (p == NULL) - p = (__be32*)iov->iov_base; - xdr->p = p; + xdr->p = (__be32*)iov->iov_base; xdr->end = (__be32*)(iov->iov_base + len); xdr->iov = iov; xdr->page_ptr = NULL; @@ -609,7 +589,7 @@ static void xdr_set_next_page(struct xdr_stream *xdr) newbase -= xdr->buf->page_base; if (xdr_set_page_base(xdr, newbase, PAGE_SIZE) < 0) - xdr_set_iov(xdr, xdr->buf->tail, NULL, xdr->buf->len); + xdr_set_iov(xdr, xdr->buf->tail, xdr->buf->len); } static bool xdr_set_next_buffer(struct xdr_stream *xdr) @@ -618,7 +598,7 @@ static bool xdr_set_next_buffer(struct xdr_stream *xdr) xdr_set_next_page(xdr); else if (xdr->iov == xdr->buf->head) { if (xdr_set_page_base(xdr, 0, PAGE_SIZE) < 0) - xdr_set_iov(xdr, xdr->buf->tail, NULL, xdr->buf->len); + xdr_set_iov(xdr, xdr->buf->tail, xdr->buf->len); } return xdr->p != xdr->end; } @@ -634,10 +614,15 @@ void xdr_init_decode(struct xdr_stream *xdr, struct xdr_buf *buf, __be32 *p) xdr->buf = buf; xdr->scratch.iov_base = NULL; xdr->scratch.iov_len = 0; + xdr->nwords = XDR_QUADLEN(buf->len); if (buf->head[0].iov_len != 0) - xdr_set_iov(xdr, buf->head, p, buf->len); + xdr_set_iov(xdr, buf->head, buf->len); else if (buf->page_len != 0) xdr_set_page_base(xdr, 0, buf->len); + if (p != NULL && p > xdr->p && xdr->end >= p) { + xdr->nwords -= p - xdr->p; + xdr->p = p; + } } EXPORT_SYMBOL_GPL(xdr_init_decode); @@ -662,12 +647,14 @@ EXPORT_SYMBOL_GPL(xdr_init_decode_pages); static __be32 * __xdr_inline_decode(struct xdr_stream *xdr, size_t nbytes) { + unsigned int nwords = XDR_QUADLEN(nbytes); __be32 *p = xdr->p; - __be32 *q = p + XDR_QUADLEN(nbytes); + __be32 *q = p + nwords; - if (unlikely(q > xdr->end || q < p)) + if (unlikely(nwords > xdr->nwords || q > xdr->end || q < p)) return NULL; xdr->p = q; + xdr->nwords -= nwords; return p; } @@ -734,6 +721,31 @@ __be32 * xdr_inline_decode(struct xdr_stream *xdr, size_t nbytes) } EXPORT_SYMBOL_GPL(xdr_inline_decode); +static unsigned int xdr_align_pages(struct xdr_stream *xdr, unsigned int len) +{ + struct xdr_buf *buf = xdr->buf; + struct kvec *iov; + unsigned int nwords = XDR_QUADLEN(len); + unsigned int cur = xdr_stream_pos(xdr); + + if (xdr->nwords == 0) + return 0; + if (nwords > xdr->nwords) { + nwords = xdr->nwords; + len = nwords << 2; + } + /* Realign pages to current pointer position */ + iov = buf->head; + if (iov->iov_len > cur) + xdr_shrink_bufhead(buf, iov->iov_len - cur); + + /* Truncate page data and move it into the tail */ + if (buf->page_len > len) + xdr_shrink_pagelen(buf, buf->page_len - len); + xdr->nwords = XDR_QUADLEN(buf->len - cur); + return len; +} + /** * xdr_read_pages - Ensure page-based XDR data to decode is aligned at current pointer position * @xdr: pointer to xdr_stream struct @@ -742,39 +754,37 @@ EXPORT_SYMBOL_GPL(xdr_inline_decode); * Moves data beyond the current pointer position from the XDR head[] buffer * into the page list. Any data that lies beyond current position + "len" * bytes is moved into the XDR tail[]. + * + * Returns the number of XDR encoded bytes now contained in the pages */ -void xdr_read_pages(struct xdr_stream *xdr, unsigned int len) +unsigned int xdr_read_pages(struct xdr_stream *xdr, unsigned int len) { struct xdr_buf *buf = xdr->buf; struct kvec *iov; - ssize_t shift; + unsigned int nwords; unsigned int end; - int padding; + unsigned int padding; - /* Realign pages to current pointer position */ - iov = buf->head; - shift = iov->iov_len + (char *)iov->iov_base - (char *)xdr->p; - if (shift > 0) - xdr_shrink_bufhead(buf, shift); - - /* Truncate page data and move it into the tail */ - if (buf->page_len > len) - xdr_shrink_pagelen(buf, buf->page_len - len); - padding = (XDR_QUADLEN(len) << 2) - len; + len = xdr_align_pages(xdr, len); + if (len == 0) + return 0; + nwords = XDR_QUADLEN(len); + padding = (nwords << 2) - len; xdr->iov = iov = buf->tail; /* Compute remaining message length. */ - end = iov->iov_len; - shift = buf->buflen - buf->len; - if (shift < end) - end -= shift; - else if (shift > 0) - end = 0; + end = ((xdr->nwords - nwords) << 2) + padding; + if (end > iov->iov_len) + end = iov->iov_len; + /* * Position current pointer at beginning of tail, and * set remaining message length. */ xdr->p = (__be32 *)((char *)iov->iov_base + padding); xdr->end = (__be32 *)((char *)iov->iov_base + end); + xdr->page_ptr = NULL; + xdr->nwords = XDR_QUADLEN(end - padding); + return len; } EXPORT_SYMBOL_GPL(xdr_read_pages); @@ -790,12 +800,13 @@ EXPORT_SYMBOL_GPL(xdr_read_pages); */ void xdr_enter_page(struct xdr_stream *xdr, unsigned int len) { - xdr_read_pages(xdr, len); + len = xdr_align_pages(xdr, len); /* * Position current pointer at beginning of tail, and * set remaining message length. */ - xdr_set_page_base(xdr, 0, len); + if (len != 0) + xdr_set_page_base(xdr, 0, len); } EXPORT_SYMBOL_GPL(xdr_enter_page); diff --git a/net/sunrpc/xprtrdma/transport.c b/net/sunrpc/xprtrdma/transport.c index b446e10..06cdbff 100644 --- a/net/sunrpc/xprtrdma/transport.c +++ b/net/sunrpc/xprtrdma/transport.c @@ -200,6 +200,7 @@ xprt_rdma_connect_worker(struct work_struct *work) int rc = 0; if (!xprt->shutdown) { + current->flags |= PF_FSTRANS; xprt_clear_connected(xprt); dprintk("RPC: %s: %sconnect\n", __func__, @@ -212,10 +213,10 @@ xprt_rdma_connect_worker(struct work_struct *work) out: xprt_wake_pending_tasks(xprt, rc); - out_clear: dprintk("RPC: %s: exit\n", __func__); xprt_clear_connecting(xprt); + current->flags &= ~PF_FSTRANS; } /* diff --git a/net/sunrpc/xprtsock.c b/net/sunrpc/xprtsock.c index 62d0dac..4005672 100644 --- a/net/sunrpc/xprtsock.c +++ b/net/sunrpc/xprtsock.c @@ -1892,6 +1892,8 @@ static void xs_local_setup_socket(struct work_struct *work) if (xprt->shutdown) goto out; + current->flags |= PF_FSTRANS; + clear_bit(XPRT_CONNECTION_ABORT, &xprt->state); status = __sock_create(xprt->xprt_net, AF_LOCAL, SOCK_STREAM, 0, &sock, 1); @@ -1925,7 +1927,47 @@ static void xs_local_setup_socket(struct work_struct *work) out: xprt_clear_connecting(xprt); xprt_wake_pending_tasks(xprt, status); + current->flags &= ~PF_FSTRANS; +} + +#ifdef CONFIG_SUNRPC_SWAP +static void xs_set_memalloc(struct rpc_xprt *xprt) +{ + struct sock_xprt *transport = container_of(xprt, struct sock_xprt, + xprt); + + if (xprt->swapper) + sk_set_memalloc(transport->inet); +} + +/** + * xs_swapper - Tag this transport as being used for swap. + * @xprt: transport to tag + * @enable: enable/disable + * + */ +int xs_swapper(struct rpc_xprt *xprt, int enable) +{ + struct sock_xprt *transport = container_of(xprt, struct sock_xprt, + xprt); + int err = 0; + + if (enable) { + xprt->swapper++; + xs_set_memalloc(xprt); + } else if (xprt->swapper) { + xprt->swapper--; + sk_clear_memalloc(transport->inet); + } + + return err; +} +EXPORT_SYMBOL_GPL(xs_swapper); +#else +static void xs_set_memalloc(struct rpc_xprt *xprt) +{ } +#endif static void xs_udp_finish_connecting(struct rpc_xprt *xprt, struct socket *sock) { @@ -1951,6 +1993,8 @@ static void xs_udp_finish_connecting(struct rpc_xprt *xprt, struct socket *sock) transport->sock = sock; transport->inet = sk; + xs_set_memalloc(xprt); + write_unlock_bh(&sk->sk_callback_lock); } xs_udp_do_set_buffer_size(xprt); @@ -1967,6 +2011,8 @@ static void xs_udp_setup_socket(struct work_struct *work) if (xprt->shutdown) goto out; + current->flags |= PF_FSTRANS; + /* Start by resetting any existing state */ xs_reset_transport(transport); sock = xs_create_sock(xprt, transport, @@ -1985,6 +2031,7 @@ static void xs_udp_setup_socket(struct work_struct *work) out: xprt_clear_connecting(xprt); xprt_wake_pending_tasks(xprt, status); + current->flags &= ~PF_FSTRANS; } /* @@ -2075,6 +2122,8 @@ static int xs_tcp_finish_connecting(struct rpc_xprt *xprt, struct socket *sock) if (!xprt_bound(xprt)) goto out; + xs_set_memalloc(xprt); + /* Tell the socket layer to start connecting... */ xprt->stat.connect_count++; xprt->stat.connect_start = jiffies; @@ -2110,6 +2159,8 @@ static void xs_tcp_setup_socket(struct work_struct *work) if (xprt->shutdown) goto out; + current->flags |= PF_FSTRANS; + if (!sock) { clear_bit(XPRT_CONNECTION_ABORT, &xprt->state); sock = xs_create_sock(xprt, transport, @@ -2159,6 +2210,7 @@ static void xs_tcp_setup_socket(struct work_struct *work) case -EINPROGRESS: case -EALREADY: xprt_clear_connecting(xprt); + current->flags &= ~PF_FSTRANS; return; case -EINVAL: /* Happens, for instance, if the user specified a link @@ -2171,6 +2223,7 @@ out_eagain: out: xprt_clear_connecting(xprt); xprt_wake_pending_tasks(xprt, status); + current->flags &= ~PF_FSTRANS; } /** diff --git a/net/wanrouter/wanmain.c b/net/wanrouter/wanmain.c index 788a12c..2ab7850 100644 --- a/net/wanrouter/wanmain.c +++ b/net/wanrouter/wanmain.c @@ -602,36 +602,31 @@ static int wanrouter_device_new_if(struct wan_device *wandev, * successfully, add it to the interface list. */ - if (dev->name == NULL) { - err = -EINVAL; - } else { +#ifdef WANDEBUG + printk(KERN_INFO "%s: registering interface %s...\n", + wanrouter_modname, dev->name); +#endif - #ifdef WANDEBUG - printk(KERN_INFO "%s: registering interface %s...\n", - wanrouter_modname, dev->name); - #endif - - err = register_netdev(dev); - if (!err) { - struct net_device *slave = NULL; - unsigned long smp_flags=0; - - lock_adapter_irq(&wandev->lock, &smp_flags); - - if (wandev->dev == NULL) { - wandev->dev = dev; - } else { - for (slave=wandev->dev; - DEV_TO_SLAVE(slave); - slave = DEV_TO_SLAVE(slave)) - DEV_TO_SLAVE(slave) = dev; - } - ++wandev->ndev; - - unlock_adapter_irq(&wandev->lock, &smp_flags); - err = 0; /* done !!! */ - goto out; + err = register_netdev(dev); + if (!err) { + struct net_device *slave = NULL; + unsigned long smp_flags=0; + + lock_adapter_irq(&wandev->lock, &smp_flags); + + if (wandev->dev == NULL) { + wandev->dev = dev; + } else { + for (slave=wandev->dev; + DEV_TO_SLAVE(slave); + slave = DEV_TO_SLAVE(slave)) + DEV_TO_SLAVE(slave) = dev; } + ++wandev->ndev; + + unlock_adapter_irq(&wandev->lock, &smp_flags); + err = 0; /* done !!! */ + goto out; } if (wandev->del_if) wandev->del_if(wandev, dev); |