summaryrefslogtreecommitdiff
path: root/net/rxrpc
diff options
context:
space:
mode:
Diffstat (limited to 'net/rxrpc')
-rw-r--r--net/rxrpc/af_rxrpc.c19
-rw-r--r--net/rxrpc/ar-internal.h60
-rw-r--r--net/rxrpc/call_accept.c68
-rw-r--r--net/rxrpc/call_object.c7
-rw-r--r--net/rxrpc/conn_client.c14
-rw-r--r--net/rxrpc/conn_event.c26
-rw-r--r--net/rxrpc/conn_object.c21
-rw-r--r--net/rxrpc/input.c331
-rw-r--r--net/rxrpc/local_event.c2
-rw-r--r--net/rxrpc/local_object.c62
-rw-r--r--net/rxrpc/net_ns.c3
-rw-r--r--net/rxrpc/output.c67
-rw-r--r--net/rxrpc/peer_event.c64
-rw-r--r--net/rxrpc/peer_object.c77
-rw-r--r--net/rxrpc/proc.c126
-rw-r--r--net/rxrpc/protocol.h15
-rw-r--r--net/rxrpc/recvmsg.c43
-rw-r--r--net/rxrpc/skbuff.c15
-rw-r--r--net/rxrpc/utils.c23
19 files changed, 627 insertions, 416 deletions
diff --git a/net/rxrpc/af_rxrpc.c b/net/rxrpc/af_rxrpc.c
index ac44d8afffb1..64362d078da8 100644
--- a/net/rxrpc/af_rxrpc.c
+++ b/net/rxrpc/af_rxrpc.c
@@ -97,7 +97,8 @@ static int rxrpc_validate_address(struct rxrpc_sock *rx,
srx->transport_len > len)
return -EINVAL;
- if (srx->transport.family != rx->family)
+ if (srx->transport.family != rx->family &&
+ srx->transport.family == AF_INET && rx->family != AF_INET6)
return -EAFNOSUPPORT;
switch (srx->transport.family) {
@@ -385,6 +386,20 @@ u32 rxrpc_kernel_check_life(struct socket *sock, struct rxrpc_call *call)
EXPORT_SYMBOL(rxrpc_kernel_check_life);
/**
+ * rxrpc_kernel_get_epoch - Retrieve the epoch value from a call.
+ * @sock: The socket the call is on
+ * @call: The call to query
+ *
+ * Allow a kernel service to retrieve the epoch value from a service call to
+ * see if the client at the other end rebooted.
+ */
+u32 rxrpc_kernel_get_epoch(struct socket *sock, struct rxrpc_call *call)
+{
+ return call->conn->proto.epoch;
+}
+EXPORT_SYMBOL(rxrpc_kernel_get_epoch);
+
+/**
* rxrpc_kernel_check_call - Check a call's state
* @sock: The socket the call is on
* @call: The call to check
@@ -741,7 +756,7 @@ static __poll_t rxrpc_poll(struct file *file, struct socket *sock,
struct rxrpc_sock *rx = rxrpc_sk(sk);
__poll_t mask;
- sock_poll_wait(file, wait);
+ sock_poll_wait(file, sock, wait);
mask = 0;
/* the socket is readable if there are any messages waiting on the Rx
diff --git a/net/rxrpc/ar-internal.h b/net/rxrpc/ar-internal.h
index 41be33c9eecf..382196e57a26 100644
--- a/net/rxrpc/ar-internal.h
+++ b/net/rxrpc/ar-internal.h
@@ -40,17 +40,12 @@ struct rxrpc_crypt {
struct rxrpc_connection;
/*
- * Mark applied to socket buffers.
+ * Mark applied to socket buffers in skb->mark. skb->priority is used
+ * to pass supplementary information.
*/
enum rxrpc_skb_mark {
- RXRPC_SKB_MARK_DATA, /* data message */
- RXRPC_SKB_MARK_FINAL_ACK, /* final ACK received message */
- RXRPC_SKB_MARK_BUSY, /* server busy message */
- RXRPC_SKB_MARK_REMOTE_ABORT, /* remote abort message */
- RXRPC_SKB_MARK_LOCAL_ABORT, /* local abort message */
- RXRPC_SKB_MARK_NET_ERROR, /* network error message */
- RXRPC_SKB_MARK_LOCAL_ERROR, /* local error message */
- RXRPC_SKB_MARK_NEW_CALL, /* local error message */
+ RXRPC_SKB_MARK_REJECT_BUSY, /* Reject with BUSY */
+ RXRPC_SKB_MARK_REJECT_ABORT, /* Reject with ABORT (code in skb->priority) */
};
/*
@@ -293,7 +288,6 @@ struct rxrpc_peer {
struct hlist_node hash_link;
struct rxrpc_local *local;
struct hlist_head error_targets; /* targets for net error distribution */
- struct work_struct error_distributor;
struct rb_root service_conns; /* Service connections */
struct list_head keepalive_link; /* Link in net->peer_keepalive[] */
time64_t last_tx_at; /* Last time packet sent here */
@@ -304,12 +298,11 @@ struct rxrpc_peer {
unsigned int maxdata; /* data size (MTU - hdrsize) */
unsigned short hdrsize; /* header size (IP + UDP + RxRPC) */
int debug_id; /* debug ID for printks */
- int error_report; /* Net (+0) or local (+1000000) to distribute */
-#define RXRPC_LOCAL_ERROR_OFFSET 1000000
struct sockaddr_rxrpc srx; /* remote address */
/* calculated RTT cache */
#define RXRPC_RTT_CACHE_SIZE 32
+ spinlock_t rtt_input_lock; /* RTT lock for input routine */
ktime_t rtt_last_req; /* Time of last RTT request */
u64 rtt; /* Current RTT estimate (in nS) */
u64 rtt_sum; /* Sum of cache contents */
@@ -450,19 +443,29 @@ struct rxrpc_connection {
spinlock_t state_lock; /* state-change lock */
enum rxrpc_conn_cache_state cache_state;
enum rxrpc_conn_proto_state state; /* current state of connection */
- u32 local_abort; /* local abort code */
- u32 remote_abort; /* remote abort code */
+ u32 abort_code; /* Abort code of connection abort */
int debug_id; /* debug ID for printks */
atomic_t serial; /* packet serial number counter */
unsigned int hi_serial; /* highest serial number received */
u32 security_nonce; /* response re-use preventer */
- u16 service_id; /* Service ID, possibly upgraded */
+ u32 service_id; /* Service ID, possibly upgraded */
u8 size_align; /* data size alignment (for security) */
u8 security_size; /* security header size */
u8 security_ix; /* security type */
u8 out_clientflag; /* RXRPC_CLIENT_INITIATED if we are client */
+ short error; /* Local error code */
};
+static inline bool rxrpc_to_server(const struct rxrpc_skb_priv *sp)
+{
+ return sp->hdr.flags & RXRPC_CLIENT_INITIATED;
+}
+
+static inline bool rxrpc_to_client(const struct rxrpc_skb_priv *sp)
+{
+ return !rxrpc_to_server(sp);
+}
+
/*
* Flags in call->flags.
*/
@@ -633,6 +636,8 @@ struct rxrpc_call {
bool tx_phase; /* T if transmission phase, F if receive phase */
u8 nr_jumbo_bad; /* Number of jumbo dups/exceeds-windows */
+ spinlock_t input_lock; /* Lock for packet input to this call */
+
/* receive-phase ACK management */
u8 ackr_reason; /* reason to ACK */
u16 ackr_skew; /* skew on packet being ACK'd */
@@ -717,7 +722,7 @@ extern struct workqueue_struct *rxrpc_workqueue;
int rxrpc_service_prealloc(struct rxrpc_sock *, gfp_t);
void rxrpc_discard_prealloc(struct rxrpc_sock *);
struct rxrpc_call *rxrpc_new_incoming_call(struct rxrpc_local *,
- struct rxrpc_connection *,
+ struct rxrpc_sock *,
struct sk_buff *);
void rxrpc_accept_incoming_calls(struct rxrpc_local *);
struct rxrpc_call *rxrpc_accept_call(struct rxrpc_sock *, unsigned long,
@@ -887,8 +892,9 @@ extern unsigned long rxrpc_conn_idle_client_fast_expiry;
extern struct idr rxrpc_client_conn_ids;
void rxrpc_destroy_client_conn_ids(void);
-int rxrpc_connect_call(struct rxrpc_call *, struct rxrpc_conn_parameters *,
- struct sockaddr_rxrpc *, gfp_t);
+int rxrpc_connect_call(struct rxrpc_sock *, struct rxrpc_call *,
+ struct rxrpc_conn_parameters *, struct sockaddr_rxrpc *,
+ gfp_t);
void rxrpc_expose_client_call(struct rxrpc_call *);
void rxrpc_disconnect_client_call(struct rxrpc_call *);
void rxrpc_put_client_conn(struct rxrpc_connection *);
@@ -908,7 +914,8 @@ extern unsigned int rxrpc_closed_conn_expiry;
struct rxrpc_connection *rxrpc_alloc_connection(gfp_t);
struct rxrpc_connection *rxrpc_find_connection_rcu(struct rxrpc_local *,
- struct sk_buff *);
+ struct sk_buff *,
+ struct rxrpc_peer **);
void __rxrpc_disconnect_call(struct rxrpc_connection *, struct rxrpc_call *);
void rxrpc_disconnect_call(struct rxrpc_call *);
void rxrpc_kill_connection(struct rxrpc_connection *);
@@ -960,7 +967,7 @@ void rxrpc_unpublish_service_conn(struct rxrpc_connection *);
/*
* input.c
*/
-void rxrpc_data_ready(struct sock *);
+int rxrpc_input_packet(struct sock *, struct sk_buff *);
/*
* insecure.c
@@ -1031,7 +1038,6 @@ void rxrpc_send_keepalive(struct rxrpc_peer *);
* peer_event.c
*/
void rxrpc_error_report(struct sock *);
-void rxrpc_peer_error_distributor(struct work_struct *);
void rxrpc_peer_add_rtt(struct rxrpc_call *, enum rxrpc_rtt_rx_trace,
rxrpc_serial_t, rxrpc_serial_t, ktime_t, ktime_t);
void rxrpc_peer_keepalive_worker(struct work_struct *);
@@ -1041,22 +1047,22 @@ void rxrpc_peer_keepalive_worker(struct work_struct *);
*/
struct rxrpc_peer *rxrpc_lookup_peer_rcu(struct rxrpc_local *,
const struct sockaddr_rxrpc *);
-struct rxrpc_peer *rxrpc_lookup_peer(struct rxrpc_local *,
+struct rxrpc_peer *rxrpc_lookup_peer(struct rxrpc_sock *, struct rxrpc_local *,
struct sockaddr_rxrpc *, gfp_t);
struct rxrpc_peer *rxrpc_alloc_peer(struct rxrpc_local *, gfp_t);
-struct rxrpc_peer *rxrpc_lookup_incoming_peer(struct rxrpc_local *,
- struct rxrpc_peer *);
+void rxrpc_new_incoming_peer(struct rxrpc_sock *, struct rxrpc_local *,
+ struct rxrpc_peer *);
void rxrpc_destroy_all_peers(struct rxrpc_net *);
struct rxrpc_peer *rxrpc_get_peer(struct rxrpc_peer *);
struct rxrpc_peer *rxrpc_get_peer_maybe(struct rxrpc_peer *);
void rxrpc_put_peer(struct rxrpc_peer *);
-void __rxrpc_queue_peer_error(struct rxrpc_peer *);
/*
* proc.c
*/
extern const struct seq_operations rxrpc_call_seq_ops;
extern const struct seq_operations rxrpc_connection_seq_ops;
+extern const struct seq_operations rxrpc_peer_seq_ops;
/*
* recvmsg.c
@@ -1093,7 +1099,6 @@ void rxrpc_new_skb(struct sk_buff *, enum rxrpc_skb_trace);
void rxrpc_see_skb(struct sk_buff *, enum rxrpc_skb_trace);
void rxrpc_get_skb(struct sk_buff *, enum rxrpc_skb_trace);
void rxrpc_free_skb(struct sk_buff *, enum rxrpc_skb_trace);
-void rxrpc_lose_skb(struct sk_buff *, enum rxrpc_skb_trace);
void rxrpc_purge_queue(struct sk_buff_head *);
/*
@@ -1110,8 +1115,7 @@ static inline void rxrpc_sysctl_exit(void) {}
/*
* utils.c
*/
-int rxrpc_extract_addr_from_skb(struct rxrpc_local *, struct sockaddr_rxrpc *,
- struct sk_buff *);
+int rxrpc_extract_addr_from_skb(struct sockaddr_rxrpc *, struct sk_buff *);
static inline bool before(u32 seq1, u32 seq2)
{
diff --git a/net/rxrpc/call_accept.c b/net/rxrpc/call_accept.c
index 9d1e298b784c..44860505246d 100644
--- a/net/rxrpc/call_accept.c
+++ b/net/rxrpc/call_accept.c
@@ -249,11 +249,11 @@ void rxrpc_discard_prealloc(struct rxrpc_sock *rx)
*/
static struct rxrpc_call *rxrpc_alloc_incoming_call(struct rxrpc_sock *rx,
struct rxrpc_local *local,
+ struct rxrpc_peer *peer,
struct rxrpc_connection *conn,
struct sk_buff *skb)
{
struct rxrpc_backlog *b = rx->backlog;
- struct rxrpc_peer *peer, *xpeer;
struct rxrpc_call *call;
unsigned short call_head, conn_head, peer_head;
unsigned short call_tail, conn_tail, peer_tail;
@@ -276,21 +276,18 @@ static struct rxrpc_call *rxrpc_alloc_incoming_call(struct rxrpc_sock *rx,
return NULL;
if (!conn) {
- /* No connection. We're going to need a peer to start off
- * with. If one doesn't yet exist, use a spare from the
- * preallocation set. We dump the address into the spare in
- * anticipation - and to save on stack space.
- */
- xpeer = b->peer_backlog[peer_tail];
- if (rxrpc_extract_addr_from_skb(local, &xpeer->srx, skb) < 0)
- return NULL;
-
- peer = rxrpc_lookup_incoming_peer(local, xpeer);
- if (peer == xpeer) {
+ if (peer && !rxrpc_get_peer_maybe(peer))
+ peer = NULL;
+ if (!peer) {
+ peer = b->peer_backlog[peer_tail];
+ if (rxrpc_extract_addr_from_skb(&peer->srx, skb) < 0)
+ return NULL;
b->peer_backlog[peer_tail] = NULL;
smp_store_release(&b->peer_backlog_tail,
(peer_tail + 1) &
(RXRPC_BACKLOG_MAX - 1));
+
+ rxrpc_new_incoming_peer(rx, local, peer);
}
/* Now allocate and set up the connection */
@@ -335,45 +332,38 @@ static struct rxrpc_call *rxrpc_alloc_incoming_call(struct rxrpc_sock *rx,
* The call is returned with the user access mutex held.
*/
struct rxrpc_call *rxrpc_new_incoming_call(struct rxrpc_local *local,
- struct rxrpc_connection *conn,
+ struct rxrpc_sock *rx,
struct sk_buff *skb)
{
struct rxrpc_skb_priv *sp = rxrpc_skb(skb);
- struct rxrpc_sock *rx;
+ struct rxrpc_connection *conn;
+ struct rxrpc_peer *peer = NULL;
struct rxrpc_call *call;
- u16 service_id = sp->hdr.serviceId;
_enter("");
- /* Get the socket providing the service */
- rx = rcu_dereference(local->service);
- if (rx && (service_id == rx->srx.srx_service ||
- service_id == rx->second_service))
- goto found_service;
-
- trace_rxrpc_abort(0, "INV", sp->hdr.cid, sp->hdr.callNumber, sp->hdr.seq,
- RX_INVALID_OPERATION, EOPNOTSUPP);
- skb->mark = RXRPC_SKB_MARK_LOCAL_ABORT;
- skb->priority = RX_INVALID_OPERATION;
- _leave(" = NULL [service]");
- return NULL;
-
-found_service:
spin_lock(&rx->incoming_lock);
if (rx->sk.sk_state == RXRPC_SERVER_LISTEN_DISABLED ||
rx->sk.sk_state == RXRPC_CLOSE) {
trace_rxrpc_abort(0, "CLS", sp->hdr.cid, sp->hdr.callNumber,
sp->hdr.seq, RX_INVALID_OPERATION, ESHUTDOWN);
- skb->mark = RXRPC_SKB_MARK_LOCAL_ABORT;
+ skb->mark = RXRPC_SKB_MARK_REJECT_ABORT;
skb->priority = RX_INVALID_OPERATION;
_leave(" = NULL [close]");
call = NULL;
goto out;
}
- call = rxrpc_alloc_incoming_call(rx, local, conn, skb);
+ /* The peer, connection and call may all have sprung into existence due
+ * to a duplicate packet being handled on another CPU in parallel, so
+ * we have to recheck the routing. However, we're now holding
+ * rx->incoming_lock, so the values should remain stable.
+ */
+ conn = rxrpc_find_connection_rcu(local, skb, &peer);
+
+ call = rxrpc_alloc_incoming_call(rx, local, peer, conn, skb);
if (!call) {
- skb->mark = RXRPC_SKB_MARK_BUSY;
+ skb->mark = RXRPC_SKB_MARK_REJECT_BUSY;
_leave(" = NULL [busy]");
call = NULL;
goto out;
@@ -413,20 +403,22 @@ found_service:
case RXRPC_CONN_SERVICE:
write_lock(&call->state_lock);
- if (rx->discard_new_call)
- call->state = RXRPC_CALL_SERVER_RECV_REQUEST;
- else
- call->state = RXRPC_CALL_SERVER_ACCEPTING;
+ if (call->state < RXRPC_CALL_COMPLETE) {
+ if (rx->discard_new_call)
+ call->state = RXRPC_CALL_SERVER_RECV_REQUEST;
+ else
+ call->state = RXRPC_CALL_SERVER_ACCEPTING;
+ }
write_unlock(&call->state_lock);
break;
case RXRPC_CONN_REMOTELY_ABORTED:
rxrpc_set_call_completion(call, RXRPC_CALL_REMOTELY_ABORTED,
- conn->remote_abort, -ECONNABORTED);
+ conn->abort_code, conn->error);
break;
case RXRPC_CONN_LOCALLY_ABORTED:
rxrpc_abort_call("CON", call, sp->hdr.seq,
- conn->local_abort, -ECONNABORTED);
+ conn->abort_code, conn->error);
break;
default:
BUG();
diff --git a/net/rxrpc/call_object.c b/net/rxrpc/call_object.c
index 9486293fef5c..8f1a8f85b1f9 100644
--- a/net/rxrpc/call_object.c
+++ b/net/rxrpc/call_object.c
@@ -138,6 +138,7 @@ struct rxrpc_call *rxrpc_alloc_call(struct rxrpc_sock *rx, gfp_t gfp,
init_waitqueue_head(&call->waitq);
spin_lock_init(&call->lock);
spin_lock_init(&call->notify_lock);
+ spin_lock_init(&call->input_lock);
rwlock_init(&call->state_lock);
atomic_set(&call->usage, 1);
call->debug_id = debug_id;
@@ -287,7 +288,7 @@ struct rxrpc_call *rxrpc_new_client_call(struct rxrpc_sock *rx,
/* Set up or get a connection record and set the protocol parameters,
* including channel number and call ID.
*/
- ret = rxrpc_connect_call(call, cp, srx, gfp);
+ ret = rxrpc_connect_call(rx, call, cp, srx, gfp);
if (ret < 0)
goto error;
@@ -339,7 +340,7 @@ int rxrpc_retry_client_call(struct rxrpc_sock *rx,
/* Set up or get a connection record and set the protocol parameters,
* including channel number and call ID.
*/
- ret = rxrpc_connect_call(call, cp, srx, gfp);
+ ret = rxrpc_connect_call(rx, call, cp, srx, gfp);
if (ret < 0)
goto error;
@@ -400,7 +401,7 @@ void rxrpc_incoming_call(struct rxrpc_sock *rx,
rcu_assign_pointer(conn->channels[chan].call, call);
spin_lock(&conn->params.peer->lock);
- hlist_add_head(&call->error_link, &conn->params.peer->error_targets);
+ hlist_add_head_rcu(&call->error_link, &conn->params.peer->error_targets);
spin_unlock(&conn->params.peer->lock);
_net("CALL incoming %d on CONN %d", call->debug_id, call->conn->debug_id);
diff --git a/net/rxrpc/conn_client.c b/net/rxrpc/conn_client.c
index f8f37188a932..521189f4b666 100644
--- a/net/rxrpc/conn_client.c
+++ b/net/rxrpc/conn_client.c
@@ -276,7 +276,8 @@ dont_reuse:
* If we return with a connection, the call will be on its waiting list. It's
* left to the caller to assign a channel and wake up the call.
*/
-static int rxrpc_get_client_conn(struct rxrpc_call *call,
+static int rxrpc_get_client_conn(struct rxrpc_sock *rx,
+ struct rxrpc_call *call,
struct rxrpc_conn_parameters *cp,
struct sockaddr_rxrpc *srx,
gfp_t gfp)
@@ -289,7 +290,7 @@ static int rxrpc_get_client_conn(struct rxrpc_call *call,
_enter("{%d,%lx},", call->debug_id, call->user_call_ID);
- cp->peer = rxrpc_lookup_peer(cp->local, srx, gfp);
+ cp->peer = rxrpc_lookup_peer(rx, cp->local, srx, gfp);
if (!cp->peer)
goto error;
@@ -683,7 +684,8 @@ out:
* find a connection for a call
* - called in process context with IRQs enabled
*/
-int rxrpc_connect_call(struct rxrpc_call *call,
+int rxrpc_connect_call(struct rxrpc_sock *rx,
+ struct rxrpc_call *call,
struct rxrpc_conn_parameters *cp,
struct sockaddr_rxrpc *srx,
gfp_t gfp)
@@ -696,7 +698,7 @@ int rxrpc_connect_call(struct rxrpc_call *call,
rxrpc_discard_expired_client_conns(&rxnet->client_conn_reaper);
rxrpc_cull_active_client_conns(rxnet);
- ret = rxrpc_get_client_conn(call, cp, srx, gfp);
+ ret = rxrpc_get_client_conn(rx, call, cp, srx, gfp);
if (ret < 0)
goto out;
@@ -710,8 +712,8 @@ int rxrpc_connect_call(struct rxrpc_call *call,
}
spin_lock_bh(&call->conn->params.peer->lock);
- hlist_add_head(&call->error_link,
- &call->conn->params.peer->error_targets);
+ hlist_add_head_rcu(&call->error_link,
+ &call->conn->params.peer->error_targets);
spin_unlock_bh(&call->conn->params.peer->lock);
out:
diff --git a/net/rxrpc/conn_event.c b/net/rxrpc/conn_event.c
index 6df56ce68861..b6fca8ebb117 100644
--- a/net/rxrpc/conn_event.c
+++ b/net/rxrpc/conn_event.c
@@ -126,7 +126,7 @@ static void rxrpc_conn_retransmit_call(struct rxrpc_connection *conn,
switch (chan->last_type) {
case RXRPC_PACKET_TYPE_ABORT:
- _proto("Tx ABORT %%%u { %d } [re]", serial, conn->local_abort);
+ _proto("Tx ABORT %%%u { %d } [re]", serial, conn->abort_code);
break;
case RXRPC_PACKET_TYPE_ACK:
trace_rxrpc_tx_ack(chan->call_debug_id, serial,
@@ -153,13 +153,12 @@ static void rxrpc_conn_retransmit_call(struct rxrpc_connection *conn,
* pass a connection-level abort onto all calls on that connection
*/
static void rxrpc_abort_calls(struct rxrpc_connection *conn,
- enum rxrpc_call_completion compl,
- u32 abort_code, int error)
+ enum rxrpc_call_completion compl)
{
struct rxrpc_call *call;
int i;
- _enter("{%d},%x", conn->debug_id, abort_code);
+ _enter("{%d},%x", conn->debug_id, conn->abort_code);
spin_lock(&conn->channel_lock);
@@ -172,9 +171,11 @@ static void rxrpc_abort_calls(struct rxrpc_connection *conn,
trace_rxrpc_abort(call->debug_id,
"CON", call->cid,
call->call_id, 0,
- abort_code, error);
+ conn->abort_code,
+ conn->error);
if (rxrpc_set_call_completion(call, compl,
- abort_code, error))
+ conn->abort_code,
+ conn->error))
rxrpc_notify_socket(call);
}
}
@@ -207,10 +208,12 @@ static int rxrpc_abort_connection(struct rxrpc_connection *conn,
return 0;
}
+ conn->error = error;
+ conn->abort_code = abort_code;
conn->state = RXRPC_CONN_LOCALLY_ABORTED;
spin_unlock_bh(&conn->state_lock);
- rxrpc_abort_calls(conn, RXRPC_CALL_LOCALLY_ABORTED, abort_code, error);
+ rxrpc_abort_calls(conn, RXRPC_CALL_LOCALLY_ABORTED);
msg.msg_name = &conn->params.peer->srx.transport;
msg.msg_namelen = conn->params.peer->srx.transport_len;
@@ -229,7 +232,7 @@ static int rxrpc_abort_connection(struct rxrpc_connection *conn,
whdr._rsvd = 0;
whdr.serviceId = htons(conn->service_id);
- word = htonl(conn->local_abort);
+ word = htonl(conn->abort_code);
iov[0].iov_base = &whdr;
iov[0].iov_len = sizeof(whdr);
@@ -240,7 +243,7 @@ static int rxrpc_abort_connection(struct rxrpc_connection *conn,
serial = atomic_inc_return(&conn->serial);
whdr.serial = htonl(serial);
- _proto("Tx CONN ABORT %%%u { %d }", serial, conn->local_abort);
+ _proto("Tx CONN ABORT %%%u { %d }", serial, conn->abort_code);
ret = kernel_sendmsg(conn->params.local->socket, &msg, iov, 2, len);
if (ret < 0) {
@@ -315,9 +318,10 @@ static int rxrpc_process_event(struct rxrpc_connection *conn,
abort_code = ntohl(wtmp);
_proto("Rx ABORT %%%u { ac=%d }", sp->hdr.serial, abort_code);
+ conn->error = -ECONNABORTED;
+ conn->abort_code = abort_code;
conn->state = RXRPC_CONN_REMOTELY_ABORTED;
- rxrpc_abort_calls(conn, RXRPC_CALL_REMOTELY_ABORTED,
- abort_code, -ECONNABORTED);
+ rxrpc_abort_calls(conn, RXRPC_CALL_REMOTELY_ABORTED);
return -ECONNABORTED;
case RXRPC_PACKET_TYPE_CHALLENGE:
diff --git a/net/rxrpc/conn_object.c b/net/rxrpc/conn_object.c
index 77440a356b14..c332722820c2 100644
--- a/net/rxrpc/conn_object.c
+++ b/net/rxrpc/conn_object.c
@@ -69,10 +69,14 @@ struct rxrpc_connection *rxrpc_alloc_connection(gfp_t gfp)
* If successful, a pointer to the connection is returned, but no ref is taken.
* NULL is returned if there is no match.
*
+ * When searching for a service call, if we find a peer but no connection, we
+ * return that through *_peer in case we need to create a new service call.
+ *
* The caller must be holding the RCU read lock.
*/
struct rxrpc_connection *rxrpc_find_connection_rcu(struct rxrpc_local *local,
- struct sk_buff *skb)
+ struct sk_buff *skb,
+ struct rxrpc_peer **_peer)
{
struct rxrpc_connection *conn;
struct rxrpc_conn_proto k;
@@ -82,14 +86,12 @@ struct rxrpc_connection *rxrpc_find_connection_rcu(struct rxrpc_local *local,
_enter(",%x", sp->hdr.cid & RXRPC_CIDMASK);
- if (rxrpc_extract_addr_from_skb(local, &srx, skb) < 0)
+ if (rxrpc_extract_addr_from_skb(&srx, skb) < 0)
goto not_found;
- k.epoch = sp->hdr.epoch;
- k.cid = sp->hdr.cid & RXRPC_CIDMASK;
-
- /* We may have to handle mixing IPv4 and IPv6 */
- if (srx.transport.family != local->srx.transport.family) {
+ if (srx.transport.family != local->srx.transport.family &&
+ (srx.transport.family == AF_INET &&
+ local->srx.transport.family != AF_INET6)) {
pr_warn_ratelimited("AF_RXRPC: Protocol mismatch %u not %u\n",
srx.transport.family,
local->srx.transport.family);
@@ -99,7 +101,7 @@ struct rxrpc_connection *rxrpc_find_connection_rcu(struct rxrpc_local *local,
k.epoch = sp->hdr.epoch;
k.cid = sp->hdr.cid & RXRPC_CIDMASK;
- if (sp->hdr.flags & RXRPC_CLIENT_INITIATED) {
+ if (rxrpc_to_server(sp)) {
/* We need to look up service connections by the full protocol
* parameter set. We look up the peer first as an intermediate
* step and then the connection from the peer's tree.
@@ -107,6 +109,7 @@ struct rxrpc_connection *rxrpc_find_connection_rcu(struct rxrpc_local *local,
peer = rxrpc_lookup_peer_rcu(local, &srx);
if (!peer)
goto not_found;
+ *_peer = peer;
conn = rxrpc_find_service_conn_rcu(peer, skb);
if (!conn || atomic_read(&conn->usage) == 0)
goto not_found;
@@ -214,7 +217,7 @@ void rxrpc_disconnect_call(struct rxrpc_call *call)
call->peer->cong_cwnd = call->cong_cwnd;
spin_lock_bh(&conn->params.peer->lock);
- hlist_del_init(&call->error_link);
+ hlist_del_rcu(&call->error_link);
spin_unlock_bh(&conn->params.peer->lock);
if (rxrpc_is_client_call(call))
diff --git a/net/rxrpc/input.c b/net/rxrpc/input.c
index cfdc199c6351..9128aa0e40aa 100644
--- a/net/rxrpc/input.c
+++ b/net/rxrpc/input.c
@@ -216,10 +216,11 @@ static void rxrpc_send_ping(struct rxrpc_call *call, struct sk_buff *skb,
/*
* Apply a hard ACK by advancing the Tx window.
*/
-static void rxrpc_rotate_tx_window(struct rxrpc_call *call, rxrpc_seq_t to,
+static bool rxrpc_rotate_tx_window(struct rxrpc_call *call, rxrpc_seq_t to,
struct rxrpc_ack_summary *summary)
{
struct sk_buff *skb, *list = NULL;
+ bool rot_last = false;
int ix;
u8 annotation;
@@ -243,15 +244,17 @@ static void rxrpc_rotate_tx_window(struct rxrpc_call *call, rxrpc_seq_t to,
skb->next = list;
list = skb;
- if (annotation & RXRPC_TX_ANNO_LAST)
+ if (annotation & RXRPC_TX_ANNO_LAST) {
set_bit(RXRPC_CALL_TX_LAST, &call->flags);
+ rot_last = true;
+ }
if ((annotation & RXRPC_TX_ANNO_MASK) != RXRPC_TX_ANNO_ACK)
summary->nr_rot_new_acks++;
}
spin_unlock(&call->lock);
- trace_rxrpc_transmit(call, (test_bit(RXRPC_CALL_TX_LAST, &call->flags) ?
+ trace_rxrpc_transmit(call, (rot_last ?
rxrpc_transmit_rotate_last :
rxrpc_transmit_rotate));
wake_up(&call->waitq);
@@ -259,9 +262,11 @@ static void rxrpc_rotate_tx_window(struct rxrpc_call *call, rxrpc_seq_t to,
while (list) {
skb = list;
list = skb->next;
- skb->next = NULL;
+ skb_mark_not_on_list(skb);
rxrpc_free_skb(skb, rxrpc_skb_tx_freed);
}
+
+ return rot_last;
}
/*
@@ -273,23 +278,26 @@ static void rxrpc_rotate_tx_window(struct rxrpc_call *call, rxrpc_seq_t to,
static bool rxrpc_end_tx_phase(struct rxrpc_call *call, bool reply_begun,
const char *abort_why)
{
+ unsigned int state;
ASSERT(test_bit(RXRPC_CALL_TX_LAST, &call->flags));
write_lock(&call->state_lock);
- switch (call->state) {
+ state = call->state;
+ switch (state) {
case RXRPC_CALL_CLIENT_SEND_REQUEST:
case RXRPC_CALL_CLIENT_AWAIT_REPLY:
if (reply_begun)
- call->state = RXRPC_CALL_CLIENT_RECV_REPLY;
+ call->state = state = RXRPC_CALL_CLIENT_RECV_REPLY;
else
- call->state = RXRPC_CALL_CLIENT_AWAIT_REPLY;
+ call->state = state = RXRPC_CALL_CLIENT_AWAIT_REPLY;
break;
case RXRPC_CALL_SERVER_AWAIT_ACK:
__rxrpc_call_completed(call);
rxrpc_notify_socket(call);
+ state = call->state;
break;
default:
@@ -297,11 +305,10 @@ static bool rxrpc_end_tx_phase(struct rxrpc_call *call, bool reply_begun,
}
write_unlock(&call->state_lock);
- if (call->state == RXRPC_CALL_CLIENT_AWAIT_REPLY) {
+ if (state == RXRPC_CALL_CLIENT_AWAIT_REPLY)
trace_rxrpc_transmit(call, rxrpc_transmit_await_reply);
- } else {
+ else
trace_rxrpc_transmit(call, rxrpc_transmit_end);
- }
_leave(" = ok");
return true;
@@ -332,11 +339,11 @@ static bool rxrpc_receiving_reply(struct rxrpc_call *call)
trace_rxrpc_timer(call, rxrpc_timer_init_for_reply, now);
}
- if (!test_bit(RXRPC_CALL_TX_LAST, &call->flags))
- rxrpc_rotate_tx_window(call, top, &summary);
if (!test_bit(RXRPC_CALL_TX_LAST, &call->flags)) {
- rxrpc_proto_abort("TXL", call, top);
- return false;
+ if (!rxrpc_rotate_tx_window(call, top, &summary)) {
+ rxrpc_proto_abort("TXL", call, top);
+ return false;
+ }
}
if (!rxrpc_end_tx_phase(call, true, "ETD"))
return false;
@@ -452,13 +459,15 @@ static void rxrpc_input_data(struct rxrpc_call *call, struct sk_buff *skb,
}
}
+ spin_lock(&call->input_lock);
+
/* Received data implicitly ACKs all of the request packets we sent
* when we're acting as a client.
*/
if ((state == RXRPC_CALL_CLIENT_SEND_REQUEST ||
state == RXRPC_CALL_CLIENT_AWAIT_REPLY) &&
!rxrpc_receiving_reply(call))
- return;
+ goto unlock;
call->ackr_prev_seq = seq;
@@ -488,12 +497,16 @@ next_subpacket:
if (flags & RXRPC_LAST_PACKET) {
if (test_bit(RXRPC_CALL_RX_LAST, &call->flags) &&
- seq != call->rx_top)
- return rxrpc_proto_abort("LSN", call, seq);
+ seq != call->rx_top) {
+ rxrpc_proto_abort("LSN", call, seq);
+ goto unlock;
+ }
} else {
if (test_bit(RXRPC_CALL_RX_LAST, &call->flags) &&
- after_eq(seq, call->rx_top))
- return rxrpc_proto_abort("LSA", call, seq);
+ after_eq(seq, call->rx_top)) {
+ rxrpc_proto_abort("LSA", call, seq);
+ goto unlock;
+ }
}
trace_rxrpc_rx_data(call->debug_id, seq, serial, flags, annotation);
@@ -560,8 +573,10 @@ next_subpacket:
skip:
offset += len;
if (flags & RXRPC_JUMBO_PACKET) {
- if (skb_copy_bits(skb, offset, &flags, 1) < 0)
- return rxrpc_proto_abort("XJF", call, seq);
+ if (skb_copy_bits(skb, offset, &flags, 1) < 0) {
+ rxrpc_proto_abort("XJF", call, seq);
+ goto unlock;
+ }
offset += sizeof(struct rxrpc_jumbo_header);
seq++;
serial++;
@@ -601,6 +616,9 @@ ack:
trace_rxrpc_notify_socket(call->debug_id, serial);
rxrpc_notify_socket(call);
}
+
+unlock:
+ spin_unlock(&call->input_lock);
_leave(" [queued]");
}
@@ -622,13 +640,14 @@ static void rxrpc_input_requested_ack(struct rxrpc_call *call,
if (!skb)
continue;
+ sent_at = skb->tstamp;
+ smp_rmb(); /* Read timestamp before serial. */
sp = rxrpc_skb(skb);
if (sp->hdr.serial != orig_serial)
continue;
- smp_rmb();
- sent_at = skb->tstamp;
goto found;
}
+
return;
found:
@@ -686,15 +705,14 @@ static void rxrpc_input_ping_response(struct rxrpc_call *call,
ping_time = call->ping_time;
smp_rmb();
- ping_serial = call->ping_serial;
+ ping_serial = READ_ONCE(call->ping_serial);
if (orig_serial == call->acks_lost_ping)
rxrpc_input_check_for_lost_ack(call);
- if (!test_bit(RXRPC_CALL_PINGING, &call->flags) ||
- before(orig_serial, ping_serial))
+ if (before(orig_serial, ping_serial) ||
+ !test_and_clear_bit(RXRPC_CALL_PINGING, &call->flags))
return;
- clear_bit(RXRPC_CALL_PINGING, &call->flags);
if (after(orig_serial, ping_serial))
return;
@@ -860,15 +878,32 @@ static void rxrpc_input_ack(struct rxrpc_call *call, struct sk_buff *skb,
rxrpc_propose_ack_respond_to_ack);
}
+ /* Discard any out-of-order or duplicate ACKs. */
+ if (before_eq(sp->hdr.serial, call->acks_latest))
+ return;
+
+ buf.info.rxMTU = 0;
ioffset = offset + nr_acks + 3;
- if (skb->len >= ioffset + sizeof(buf.info)) {
- if (skb_copy_bits(skb, ioffset, &buf.info, sizeof(buf.info)) < 0)
- return rxrpc_proto_abort("XAI", call, 0);
+ if (skb->len >= ioffset + sizeof(buf.info) &&
+ skb_copy_bits(skb, ioffset, &buf.info, sizeof(buf.info)) < 0)
+ return rxrpc_proto_abort("XAI", call, 0);
+
+ spin_lock(&call->input_lock);
+
+ /* Discard any out-of-order or duplicate ACKs. */
+ if (before_eq(sp->hdr.serial, call->acks_latest))
+ goto out;
+ call->acks_latest_ts = skb->tstamp;
+ call->acks_latest = sp->hdr.serial;
+
+ /* Parse rwind and mtu sizes if provided. */
+ if (buf.info.rxMTU)
rxrpc_input_ackinfo(call, skb, &buf.info);
- }
- if (first_soft_ack == 0)
- return rxrpc_proto_abort("AK0", call, 0);
+ if (first_soft_ack == 0) {
+ rxrpc_proto_abort("AK0", call, 0);
+ goto out;
+ }
/* Ignore ACKs unless we are or have just been transmitting. */
switch (READ_ONCE(call->state)) {
@@ -878,39 +913,35 @@ static void rxrpc_input_ack(struct rxrpc_call *call, struct sk_buff *skb,
case RXRPC_CALL_SERVER_AWAIT_ACK:
break;
default:
- return;
- }
-
- /* Discard any out-of-order or duplicate ACKs. */
- if (before_eq(sp->hdr.serial, call->acks_latest)) {
- _debug("discard ACK %d <= %d",
- sp->hdr.serial, call->acks_latest);
- return;
+ goto out;
}
- call->acks_latest_ts = skb->tstamp;
- call->acks_latest = sp->hdr.serial;
if (before(hard_ack, call->tx_hard_ack) ||
- after(hard_ack, call->tx_top))
- return rxrpc_proto_abort("AKW", call, 0);
- if (nr_acks > call->tx_top - hard_ack)
- return rxrpc_proto_abort("AKN", call, 0);
+ after(hard_ack, call->tx_top)) {
+ rxrpc_proto_abort("AKW", call, 0);
+ goto out;
+ }
+ if (nr_acks > call->tx_top - hard_ack) {
+ rxrpc_proto_abort("AKN", call, 0);
+ goto out;
+ }
- if (after(hard_ack, call->tx_hard_ack))
- rxrpc_rotate_tx_window(call, hard_ack, &summary);
+ if (after(hard_ack, call->tx_hard_ack)) {
+ if (rxrpc_rotate_tx_window(call, hard_ack, &summary)) {
+ rxrpc_end_tx_phase(call, false, "ETA");
+ goto out;
+ }
+ }
if (nr_acks > 0) {
- if (skb_copy_bits(skb, offset, buf.acks, nr_acks) < 0)
- return rxrpc_proto_abort("XSA", call, 0);
+ if (skb_copy_bits(skb, offset, buf.acks, nr_acks) < 0) {
+ rxrpc_proto_abort("XSA", call, 0);
+ goto out;
+ }
rxrpc_input_soft_acks(call, buf.acks, first_soft_ack, nr_acks,
&summary);
}
- if (test_bit(RXRPC_CALL_TX_LAST, &call->flags)) {
- rxrpc_end_tx_phase(call, false, "ETA");
- return;
- }
-
if (call->rxtx_annotations[call->tx_top & RXRPC_RXTX_BUFF_MASK] &
RXRPC_TX_ANNO_LAST &&
summary.nr_acks == call->tx_top - hard_ack &&
@@ -919,7 +950,9 @@ static void rxrpc_input_ack(struct rxrpc_call *call, struct sk_buff *skb,
false, true,
rxrpc_propose_ack_ping_for_lost_reply);
- return rxrpc_congestion_management(call, skb, &summary, acked_serial);
+ rxrpc_congestion_management(call, skb, &summary, acked_serial);
+out:
+ spin_unlock(&call->input_lock);
}
/*
@@ -932,9 +965,12 @@ static void rxrpc_input_ackall(struct rxrpc_call *call, struct sk_buff *skb)
_proto("Rx ACKALL %%%u", sp->hdr.serial);
- rxrpc_rotate_tx_window(call, call->tx_top, &summary);
- if (test_bit(RXRPC_CALL_TX_LAST, &call->flags))
+ spin_lock(&call->input_lock);
+
+ if (rxrpc_rotate_tx_window(call, call->tx_top, &summary))
rxrpc_end_tx_phase(call, false, "ETL");
+
+ spin_unlock(&call->input_lock);
}
/*
@@ -1017,18 +1053,19 @@ static void rxrpc_input_call_packet(struct rxrpc_call *call,
}
/*
- * Handle a new call on a channel implicitly completing the preceding call on
- * that channel.
+ * Handle a new service call on a channel implicitly completing the preceding
+ * call on that channel. This does not apply to client conns.
*
* TODO: If callNumber > call_id + 1, renegotiate security.
*/
-static void rxrpc_input_implicit_end_call(struct rxrpc_connection *conn,
+static void rxrpc_input_implicit_end_call(struct rxrpc_sock *rx,
+ struct rxrpc_connection *conn,
struct rxrpc_call *call)
{
switch (READ_ONCE(call->state)) {
case RXRPC_CALL_SERVER_AWAIT_ACK:
rxrpc_call_completed(call);
- break;
+ /* Fall through */
case RXRPC_CALL_COMPLETE:
break;
default:
@@ -1036,11 +1073,13 @@ static void rxrpc_input_implicit_end_call(struct rxrpc_connection *conn,
set_bit(RXRPC_CALL_EV_ABORT, &call->events);
rxrpc_queue_call(call);
}
+ trace_rxrpc_improper_term(call);
break;
}
- trace_rxrpc_improper_term(call);
+ spin_lock(&rx->incoming_lock);
__rxrpc_disconnect_call(conn, call);
+ spin_unlock(&rx->incoming_lock);
rxrpc_notify_socket(call);
}
@@ -1119,43 +1158,29 @@ int rxrpc_extract_header(struct rxrpc_skb_priv *sp, struct sk_buff *skb)
* The socket is locked by the caller and this prevents the socket from being
* shut down and the local endpoint from going away, thus sk_user_data will not
* be cleared until this function returns.
+ *
+ * Called with the RCU read lock held from the IP layer via UDP.
*/
-void rxrpc_data_ready(struct sock *udp_sk)
+int rxrpc_input_packet(struct sock *udp_sk, struct sk_buff *skb)
{
struct rxrpc_connection *conn;
struct rxrpc_channel *chan;
- struct rxrpc_call *call;
+ struct rxrpc_call *call = NULL;
struct rxrpc_skb_priv *sp;
struct rxrpc_local *local = udp_sk->sk_user_data;
- struct sk_buff *skb;
+ struct rxrpc_peer *peer = NULL;
+ struct rxrpc_sock *rx = NULL;
unsigned int channel;
- int ret, skew;
+ int skew = 0;
_enter("%p", udp_sk);
- ASSERT(!irqs_disabled());
-
- skb = skb_recv_udp(udp_sk, 0, 1, &ret);
- if (!skb) {
- if (ret == -EAGAIN)
- return;
- _debug("UDP socket error %d", ret);
- return;
- }
+ if (skb->tstamp == 0)
+ skb->tstamp = ktime_get_real();
rxrpc_new_skb(skb, rxrpc_skb_rx_received);
- _net("recv skb %p", skb);
-
- /* we'll probably need to checksum it (didn't call sock_recvmsg) */
- if (skb_checksum_complete(skb)) {
- rxrpc_free_skb(skb, rxrpc_skb_rx_freed);
- __UDP_INC_STATS(&init_net, UDP_MIB_INERRORS, 0);
- _leave(" [CSUM failed]");
- return;
- }
-
- __UDP_INC_STATS(&init_net, UDP_MIB_INDATAGRAMS, 0);
+ skb_pull(skb, sizeof(struct udphdr));
/* The UDP protocol already released all skb resources;
* we are free to add our own data there.
@@ -1170,69 +1195,104 @@ void rxrpc_data_ready(struct sock *udp_sk)
static int lose;
if ((lose++ & 7) == 7) {
trace_rxrpc_rx_lose(sp);
- rxrpc_lose_skb(skb, rxrpc_skb_rx_lost);
- return;
+ rxrpc_free_skb(skb, rxrpc_skb_rx_lost);
+ return 0;
}
}
+ if (skb->tstamp == 0)
+ skb->tstamp = ktime_get_real();
trace_rxrpc_rx_packet(sp);
- _net("Rx RxRPC %s ep=%x call=%x:%x",
- sp->hdr.flags & RXRPC_CLIENT_INITIATED ? "ToServer" : "ToClient",
- sp->hdr.epoch, sp->hdr.cid, sp->hdr.callNumber);
-
- if (sp->hdr.type >= RXRPC_N_PACKET_TYPES ||
- !((RXRPC_SUPPORTED_PACKET_TYPES >> sp->hdr.type) & 1)) {
- _proto("Rx Bad Packet Type %u", sp->hdr.type);
- goto bad_message;
- }
-
switch (sp->hdr.type) {
case RXRPC_PACKET_TYPE_VERSION:
- if (!(sp->hdr.flags & RXRPC_CLIENT_INITIATED))
+ if (rxrpc_to_client(sp))
goto discard;
rxrpc_post_packet_to_local(local, skb);
goto out;
case RXRPC_PACKET_TYPE_BUSY:
- if (sp->hdr.flags & RXRPC_CLIENT_INITIATED)
+ if (rxrpc_to_server(sp))
goto discard;
/* Fall through */
+ case RXRPC_PACKET_TYPE_ACK:
+ case RXRPC_PACKET_TYPE_ACKALL:
+ if (sp->hdr.callNumber == 0)
+ goto bad_message;
+ /* Fall through */
+ case RXRPC_PACKET_TYPE_ABORT:
+ break;
case RXRPC_PACKET_TYPE_DATA:
- if (sp->hdr.callNumber == 0)
+ if (sp->hdr.callNumber == 0 ||
+ sp->hdr.seq == 0)
goto bad_message;
if (sp->hdr.flags & RXRPC_JUMBO_PACKET &&
!rxrpc_validate_jumbo(skb))
goto bad_message;
break;
+ case RXRPC_PACKET_TYPE_CHALLENGE:
+ if (rxrpc_to_server(sp))
+ goto discard;
+ break;
+ case RXRPC_PACKET_TYPE_RESPONSE:
+ if (rxrpc_to_client(sp))
+ goto discard;
+ break;
+
/* Packet types 9-11 should just be ignored. */
case RXRPC_PACKET_TYPE_PARAMS:
case RXRPC_PACKET_TYPE_10:
case RXRPC_PACKET_TYPE_11:
goto discard;
+
+ default:
+ _proto("Rx Bad Packet Type %u", sp->hdr.type);
+ goto bad_message;
}
- rcu_read_lock();
+ if (sp->hdr.serviceId == 0)
+ goto bad_message;
+
+ if (rxrpc_to_server(sp)) {
+ /* Weed out packets to services we're not offering. Packets
+ * that would begin a call are explicitly rejected and the rest
+ * are just discarded.
+ */
+ rx = rcu_dereference(local->service);
+ if (!rx || (sp->hdr.serviceId != rx->srx.srx_service &&
+ sp->hdr.serviceId != rx->second_service)) {
+ if (sp->hdr.type == RXRPC_PACKET_TYPE_DATA &&
+ sp->hdr.seq == 1)
+ goto unsupported_service;
+ goto discard;
+ }
+ }
- conn = rxrpc_find_connection_rcu(local, skb);
+ conn = rxrpc_find_connection_rcu(local, skb, &peer);
if (conn) {
if (sp->hdr.securityIndex != conn->security_ix)
goto wrong_security;
if (sp->hdr.serviceId != conn->service_id) {
- if (!test_bit(RXRPC_CONN_PROBING_FOR_UPGRADE, &conn->flags) ||
- conn->service_id != conn->params.service_id)
+ int old_id;
+
+ if (!test_bit(RXRPC_CONN_PROBING_FOR_UPGRADE, &conn->flags))
+ goto reupgrade;
+ old_id = cmpxchg(&conn->service_id, conn->params.service_id,
+ sp->hdr.serviceId);
+
+ if (old_id != conn->params.service_id &&
+ old_id != sp->hdr.serviceId)
goto reupgrade;
- conn->service_id = sp->hdr.serviceId;
}
if (sp->hdr.callNumber == 0) {
/* Connection-level packet */
_debug("CONN %p {%d}", conn, conn->debug_id);
rxrpc_post_packet_to_conn(conn, skb);
- goto out_unlock;
+ goto out;
}
/* Note the serial number skew here */
@@ -1251,19 +1311,19 @@ void rxrpc_data_ready(struct sock *udp_sk)
/* Ignore really old calls */
if (sp->hdr.callNumber < chan->last_call)
- goto discard_unlock;
+ goto discard;
if (sp->hdr.callNumber == chan->last_call) {
if (chan->call ||
sp->hdr.type == RXRPC_PACKET_TYPE_ABORT)
- goto discard_unlock;
+ goto discard;
/* For the previous service call, if completed
* successfully, we discard all further packets.
*/
if (rxrpc_conn_is_service(conn) &&
chan->last_type == RXRPC_PACKET_TYPE_ACK)
- goto discard_unlock;
+ goto discard;
/* But otherwise we need to retransmit the final packet
* from data cached in the connection record.
@@ -1274,18 +1334,16 @@ void rxrpc_data_ready(struct sock *udp_sk)
sp->hdr.serial,
sp->hdr.flags, 0);
rxrpc_post_packet_to_conn(conn, skb);
- goto out_unlock;
+ goto out;
}
call = rcu_dereference(chan->call);
if (sp->hdr.callNumber > chan->call_id) {
- if (!(sp->hdr.flags & RXRPC_CLIENT_INITIATED)) {
- rcu_read_unlock();
+ if (rxrpc_to_client(sp))
goto reject_packet;
- }
if (call)
- rxrpc_input_implicit_end_call(conn, call);
+ rxrpc_input_implicit_end_call(rx, conn, call);
call = NULL;
}
@@ -1297,66 +1355,57 @@ void rxrpc_data_ready(struct sock *udp_sk)
if (!test_bit(RXRPC_CALL_RX_HEARD, &call->flags))
set_bit(RXRPC_CALL_RX_HEARD, &call->flags);
}
- } else {
- skew = 0;
- call = NULL;
}
if (!call || atomic_read(&call->usage) == 0) {
- if (!(sp->hdr.type & RXRPC_CLIENT_INITIATED) ||
- sp->hdr.callNumber == 0 ||
+ if (rxrpc_to_client(sp) ||
sp->hdr.type != RXRPC_PACKET_TYPE_DATA)
- goto bad_message_unlock;
+ goto bad_message;
if (sp->hdr.seq != 1)
- goto discard_unlock;
- call = rxrpc_new_incoming_call(local, conn, skb);
- if (!call) {
- rcu_read_unlock();
+ goto discard;
+ call = rxrpc_new_incoming_call(local, rx, skb);
+ if (!call)
goto reject_packet;
- }
rxrpc_send_ping(call, skb, skew);
mutex_unlock(&call->user_mutex);
}
rxrpc_input_call_packet(call, skb, skew);
- goto discard_unlock;
+ goto discard;
-discard_unlock:
- rcu_read_unlock();
discard:
rxrpc_free_skb(skb, rxrpc_skb_rx_freed);
out:
trace_rxrpc_rx_done(0, 0);
- return;
-
-out_unlock:
- rcu_read_unlock();
- goto out;
+ return 0;
wrong_security:
- rcu_read_unlock();
trace_rxrpc_abort(0, "SEC", sp->hdr.cid, sp->hdr.callNumber, sp->hdr.seq,
RXKADINCONSISTENCY, EBADMSG);
skb->priority = RXKADINCONSISTENCY;
goto post_abort;
+unsupported_service:
+ trace_rxrpc_abort(0, "INV", sp->hdr.cid, sp->hdr.callNumber, sp->hdr.seq,
+ RX_INVALID_OPERATION, EOPNOTSUPP);
+ skb->priority = RX_INVALID_OPERATION;
+ goto post_abort;
+
reupgrade:
- rcu_read_unlock();
trace_rxrpc_abort(0, "UPG", sp->hdr.cid, sp->hdr.callNumber, sp->hdr.seq,
RX_PROTOCOL_ERROR, EBADMSG);
goto protocol_error;
-bad_message_unlock:
- rcu_read_unlock();
bad_message:
trace_rxrpc_abort(0, "BAD", sp->hdr.cid, sp->hdr.callNumber, sp->hdr.seq,
RX_PROTOCOL_ERROR, EBADMSG);
protocol_error:
skb->priority = RX_PROTOCOL_ERROR;
post_abort:
- skb->mark = RXRPC_SKB_MARK_LOCAL_ABORT;
+ skb->mark = RXRPC_SKB_MARK_REJECT_ABORT;
reject_packet:
trace_rxrpc_rx_done(skb->mark, skb->priority);
rxrpc_reject_packet(local, skb);
_leave(" [badmsg]");
+ return 0;
}
diff --git a/net/rxrpc/local_event.c b/net/rxrpc/local_event.c
index 13bd8a4dfac7..927ead43df42 100644
--- a/net/rxrpc/local_event.c
+++ b/net/rxrpc/local_event.c
@@ -39,7 +39,7 @@ static void rxrpc_send_version_request(struct rxrpc_local *local,
_enter("");
- if (rxrpc_extract_addr_from_skb(local, &srx, skb) < 0)
+ if (rxrpc_extract_addr_from_skb(&srx, skb) < 0)
return;
msg.msg_name = &srx.transport;
diff --git a/net/rxrpc/local_object.c b/net/rxrpc/local_object.c
index 777c3ed4cfc0..0906e51d3cfb 100644
--- a/net/rxrpc/local_object.c
+++ b/net/rxrpc/local_object.c
@@ -19,6 +19,7 @@
#include <linux/ip.h>
#include <linux/hashtable.h>
#include <net/sock.h>
+#include <net/udp.h>
#include <net/af_rxrpc.h>
#include "ar-internal.h"
@@ -108,7 +109,7 @@ static struct rxrpc_local *rxrpc_alloc_local(struct rxrpc_net *rxnet,
*/
static int rxrpc_open_socket(struct rxrpc_local *local, struct net *net)
{
- struct sock *sock;
+ struct sock *usk;
int ret, opt;
_enter("%p{%d,%d}",
@@ -122,6 +123,28 @@ static int rxrpc_open_socket(struct rxrpc_local *local, struct net *net)
return ret;
}
+ /* set the socket up */
+ usk = local->socket->sk;
+ inet_sk(usk)->mc_loop = 0;
+
+ /* Enable CHECKSUM_UNNECESSARY to CHECKSUM_COMPLETE conversion */
+ inet_inc_convert_csum(usk);
+
+ rcu_assign_sk_user_data(usk, local);
+
+ udp_sk(usk)->encap_type = UDP_ENCAP_RXRPC;
+ udp_sk(usk)->encap_rcv = rxrpc_input_packet;
+ udp_sk(usk)->encap_destroy = NULL;
+ udp_sk(usk)->gro_receive = NULL;
+ udp_sk(usk)->gro_complete = NULL;
+
+ udp_encap_enable();
+#if IS_ENABLED(CONFIG_AF_RXRPC_IPV6)
+ if (local->srx.transport.family == AF_INET6)
+ udpv6_encap_enable();
+#endif
+ usk->sk_error_report = rxrpc_error_report;
+
/* if a local address was supplied then bind it */
if (local->srx.transport_len > sizeof(sa_family_t)) {
_debug("bind");
@@ -135,10 +158,10 @@ static int rxrpc_open_socket(struct rxrpc_local *local, struct net *net)
}
switch (local->srx.transport.family) {
- case AF_INET:
- /* we want to receive ICMP errors */
+ case AF_INET6:
+ /* we want to receive ICMPv6 errors */
opt = 1;
- ret = kernel_setsockopt(local->socket, SOL_IP, IP_RECVERR,
+ ret = kernel_setsockopt(local->socket, SOL_IPV6, IPV6_RECVERR,
(char *) &opt, sizeof(opt));
if (ret < 0) {
_debug("setsockopt failed");
@@ -146,19 +169,22 @@ static int rxrpc_open_socket(struct rxrpc_local *local, struct net *net)
}
/* we want to set the don't fragment bit */
- opt = IP_PMTUDISC_DO;
- ret = kernel_setsockopt(local->socket, SOL_IP, IP_MTU_DISCOVER,
+ opt = IPV6_PMTUDISC_DO;
+ ret = kernel_setsockopt(local->socket, SOL_IPV6, IPV6_MTU_DISCOVER,
(char *) &opt, sizeof(opt));
if (ret < 0) {
_debug("setsockopt failed");
goto error;
}
- break;
- case AF_INET6:
+ /* Fall through and set IPv4 options too otherwise we don't get
+ * errors from IPv4 packets sent through the IPv6 socket.
+ */
+
+ case AF_INET:
/* we want to receive ICMP errors */
opt = 1;
- ret = kernel_setsockopt(local->socket, SOL_IPV6, IPV6_RECVERR,
+ ret = kernel_setsockopt(local->socket, SOL_IP, IP_RECVERR,
(char *) &opt, sizeof(opt));
if (ret < 0) {
_debug("setsockopt failed");
@@ -166,24 +192,28 @@ static int rxrpc_open_socket(struct rxrpc_local *local, struct net *net)
}
/* we want to set the don't fragment bit */
- opt = IPV6_PMTUDISC_DO;
- ret = kernel_setsockopt(local->socket, SOL_IPV6, IPV6_MTU_DISCOVER,
+ opt = IP_PMTUDISC_DO;
+ ret = kernel_setsockopt(local->socket, SOL_IP, IP_MTU_DISCOVER,
(char *) &opt, sizeof(opt));
if (ret < 0) {
_debug("setsockopt failed");
goto error;
}
+
+ /* We want receive timestamps. */
+ opt = 1;
+ ret = kernel_setsockopt(local->socket, SOL_SOCKET, SO_TIMESTAMPNS,
+ (char *)&opt, sizeof(opt));
+ if (ret < 0) {
+ _debug("setsockopt failed");
+ goto error;
+ }
break;
default:
BUG();
}
- /* set the socket up */
- sock = local->socket->sk;
- sock->sk_user_data = local;
- sock->sk_data_ready = rxrpc_data_ready;
- sock->sk_error_report = rxrpc_error_report;
_leave(" = 0");
return 0;
diff --git a/net/rxrpc/net_ns.c b/net/rxrpc/net_ns.c
index 417d80867c4f..fd7eba8467fa 100644
--- a/net/rxrpc/net_ns.c
+++ b/net/rxrpc/net_ns.c
@@ -102,6 +102,9 @@ static __net_init int rxrpc_init_net(struct net *net)
proc_create_net("conns", 0444, rxnet->proc_net,
&rxrpc_connection_seq_ops,
sizeof(struct seq_net_private));
+ proc_create_net("peers", 0444, rxnet->proc_net,
+ &rxrpc_peer_seq_ops,
+ sizeof(struct seq_net_private));
return 0;
err_proc:
diff --git a/net/rxrpc/output.c b/net/rxrpc/output.c
index ccf5de160444..189418888839 100644
--- a/net/rxrpc/output.c
+++ b/net/rxrpc/output.c
@@ -124,7 +124,6 @@ int rxrpc_send_ack_packet(struct rxrpc_call *call, bool ping,
struct kvec iov[2];
rxrpc_serial_t serial;
rxrpc_seq_t hard_ack, top;
- ktime_t now;
size_t len, n;
int ret;
u8 reason;
@@ -196,9 +195,7 @@ int rxrpc_send_ack_packet(struct rxrpc_call *call, bool ping,
/* We need to stick a time in before we send the packet in case
* the reply gets back before kernel_sendmsg() completes - but
* asking UDP to send the packet can take a relatively long
- * time, so we update the time after, on the assumption that
- * the packet transmission is more likely to happen towards the
- * end of the kernel_sendmsg() call.
+ * time.
*/
call->ping_time = ktime_get_real();
set_bit(RXRPC_CALL_PINGING, &call->flags);
@@ -206,9 +203,6 @@ int rxrpc_send_ack_packet(struct rxrpc_call *call, bool ping,
}
ret = kernel_sendmsg(conn->params.local->socket, &msg, iov, 2, len);
- now = ktime_get_real();
- if (ping)
- call->ping_time = now;
conn->params.peer->last_tx_at = ktime_get_seconds();
if (ret < 0)
trace_rxrpc_tx_fail(call->debug_id, serial, ret,
@@ -363,8 +357,14 @@ int rxrpc_send_data_packet(struct rxrpc_call *call, struct sk_buff *skb,
/* If our RTT cache needs working on, request an ACK. Also request
* ACKs if a DATA packet appears to have been lost.
+ *
+ * However, we mustn't request an ACK on the last reply packet of a
+ * service call, lest OpenAFS incorrectly send us an ACK with some
+ * soft-ACKs in it and then never follow up with a proper hard ACK.
*/
- if (!(sp->hdr.flags & RXRPC_LAST_PACKET) &&
+ if ((!(sp->hdr.flags & RXRPC_LAST_PACKET) ||
+ rxrpc_to_server(sp)
+ ) &&
(test_and_clear_bit(RXRPC_CALL_EV_ACK_LOST, &call->events) ||
retrans ||
call->cong_mode == RXRPC_CALL_SLOW_START ||
@@ -378,11 +378,13 @@ int rxrpc_send_data_packet(struct rxrpc_call *call, struct sk_buff *skb,
if ((lose++ & 7) == 7) {
ret = 0;
lost = true;
- goto done;
}
}
- _proto("Tx DATA %%%u { #%u }", serial, sp->hdr.seq);
+ trace_rxrpc_tx_data(call, sp->hdr.seq, serial, whdr.flags,
+ retrans, lost);
+ if (lost)
+ goto done;
/* send the packet with the don't fragment bit set if we currently
* think it's small enough */
@@ -390,6 +392,11 @@ int rxrpc_send_data_packet(struct rxrpc_call *call, struct sk_buff *skb,
goto send_fragmentable;
down_read(&conn->params.local->defrag_sem);
+
+ sp->hdr.serial = serial;
+ smp_wmb(); /* Set serial before timestamp */
+ skb->tstamp = ktime_get_real();
+
/* send the packet by UDP
* - returns -EMSGSIZE if UDP would have to fragment the packet
* to go out of the interface
@@ -410,15 +417,9 @@ int rxrpc_send_data_packet(struct rxrpc_call *call, struct sk_buff *skb,
goto send_fragmentable;
done:
- trace_rxrpc_tx_data(call, sp->hdr.seq, serial, whdr.flags,
- retrans, lost);
if (ret >= 0) {
- ktime_t now = ktime_get_real();
- skb->tstamp = now;
- smp_wmb();
- sp->hdr.serial = serial;
if (whdr.flags & RXRPC_REQUEST_ACK) {
- call->peer->rtt_last_req = now;
+ call->peer->rtt_last_req = skb->tstamp;
trace_rxrpc_rtt_tx(call, rxrpc_rtt_tx_data, serial);
if (call->peer->rtt_usage > 1) {
unsigned long nowj = jiffies, ack_lost_at;
@@ -457,6 +458,10 @@ send_fragmentable:
down_write(&conn->params.local->defrag_sem);
+ sp->hdr.serial = serial;
+ smp_wmb(); /* Set serial before timestamp */
+ skb->tstamp = ktime_get_real();
+
switch (conn->params.local->srx.transport.family) {
case AF_INET:
opt = IP_PMTUDISC_DONT;
@@ -519,7 +524,7 @@ void rxrpc_reject_packets(struct rxrpc_local *local)
struct kvec iov[2];
size_t size;
__be32 code;
- int ret;
+ int ret, ioc;
_enter("%d", local->debug_id);
@@ -527,7 +532,6 @@ void rxrpc_reject_packets(struct rxrpc_local *local)
iov[0].iov_len = sizeof(whdr);
iov[1].iov_base = &code;
iov[1].iov_len = sizeof(code);
- size = sizeof(whdr) + sizeof(code);
msg.msg_name = &srx.transport;
msg.msg_control = NULL;
@@ -535,16 +539,30 @@ void rxrpc_reject_packets(struct rxrpc_local *local)
msg.msg_flags = 0;
memset(&whdr, 0, sizeof(whdr));
- whdr.type = RXRPC_PACKET_TYPE_ABORT;
while ((skb = skb_dequeue(&local->reject_queue))) {
rxrpc_see_skb(skb, rxrpc_skb_rx_seen);
sp = rxrpc_skb(skb);
- if (rxrpc_extract_addr_from_skb(local, &srx, skb) == 0) {
- msg.msg_namelen = srx.transport_len;
-
+ switch (skb->mark) {
+ case RXRPC_SKB_MARK_REJECT_BUSY:
+ whdr.type = RXRPC_PACKET_TYPE_BUSY;
+ size = sizeof(whdr);
+ ioc = 1;
+ break;
+ case RXRPC_SKB_MARK_REJECT_ABORT:
+ whdr.type = RXRPC_PACKET_TYPE_ABORT;
code = htonl(skb->priority);
+ size = sizeof(whdr) + sizeof(code);
+ ioc = 2;
+ break;
+ default:
+ rxrpc_free_skb(skb, rxrpc_skb_rx_freed);
+ continue;
+ }
+
+ if (rxrpc_extract_addr_from_skb(&srx, skb) == 0) {
+ msg.msg_namelen = srx.transport_len;
whdr.epoch = htonl(sp->hdr.epoch);
whdr.cid = htonl(sp->hdr.cid);
@@ -554,7 +572,8 @@ void rxrpc_reject_packets(struct rxrpc_local *local)
whdr.flags ^= RXRPC_CLIENT_INITIATED;
whdr.flags &= RXRPC_CLIENT_INITIATED;
- ret = kernel_sendmsg(local->socket, &msg, iov, 2, size);
+ ret = kernel_sendmsg(local->socket, &msg,
+ iov, ioc, size);
if (ret < 0)
trace_rxrpc_tx_fail(local->debug_id, 0, ret,
rxrpc_tx_point_reject);
diff --git a/net/rxrpc/peer_event.c b/net/rxrpc/peer_event.c
index 4f9da2f51c69..bc05af89fc38 100644
--- a/net/rxrpc/peer_event.c
+++ b/net/rxrpc/peer_event.c
@@ -23,6 +23,8 @@
#include "ar-internal.h"
static void rxrpc_store_error(struct rxrpc_peer *, struct sock_exterr_skb *);
+static void rxrpc_distribute_error(struct rxrpc_peer *, int,
+ enum rxrpc_call_completion);
/*
* Find the peer associated with an ICMP packet.
@@ -45,6 +47,8 @@ static struct rxrpc_peer *rxrpc_lookup_peer_icmp_rcu(struct rxrpc_local *local,
*/
switch (srx->transport.family) {
case AF_INET:
+ srx->transport_len = sizeof(srx->transport.sin);
+ srx->transport.family = AF_INET;
srx->transport.sin.sin_port = serr->port;
switch (serr->ee.ee_origin) {
case SO_EE_ORIGIN_ICMP:
@@ -68,20 +72,20 @@ static struct rxrpc_peer *rxrpc_lookup_peer_icmp_rcu(struct rxrpc_local *local,
#ifdef CONFIG_AF_RXRPC_IPV6
case AF_INET6:
- srx->transport.sin6.sin6_port = serr->port;
switch (serr->ee.ee_origin) {
case SO_EE_ORIGIN_ICMP6:
_net("Rx ICMP6");
+ srx->transport.sin6.sin6_port = serr->port;
memcpy(&srx->transport.sin6.sin6_addr,
skb_network_header(skb) + serr->addr_offset,
sizeof(struct in6_addr));
break;
case SO_EE_ORIGIN_ICMP:
_net("Rx ICMP on v6 sock");
- srx->transport.sin6.sin6_addr.s6_addr32[0] = 0;
- srx->transport.sin6.sin6_addr.s6_addr32[1] = 0;
- srx->transport.sin6.sin6_addr.s6_addr32[2] = htonl(0xffff);
- memcpy(srx->transport.sin6.sin6_addr.s6_addr + 12,
+ srx->transport_len = sizeof(srx->transport.sin);
+ srx->transport.family = AF_INET;
+ srx->transport.sin.sin_port = serr->port;
+ memcpy(&srx->transport.sin.sin_addr,
skb_network_header(skb) + serr->addr_offset,
sizeof(struct in_addr));
break;
@@ -193,9 +197,8 @@ void rxrpc_error_report(struct sock *sk)
rxrpc_store_error(peer, serr);
rcu_read_unlock();
rxrpc_free_skb(skb, rxrpc_skb_rx_freed);
+ rxrpc_put_peer(peer);
- /* The ref we obtained is passed off to the work item */
- __rxrpc_queue_peer_error(peer);
_leave("");
}
@@ -205,6 +208,7 @@ void rxrpc_error_report(struct sock *sk)
static void rxrpc_store_error(struct rxrpc_peer *peer,
struct sock_exterr_skb *serr)
{
+ enum rxrpc_call_completion compl = RXRPC_CALL_NETWORK_ERROR;
struct sock_extended_err *ee;
int err;
@@ -255,7 +259,7 @@ static void rxrpc_store_error(struct rxrpc_peer *peer,
case SO_EE_ORIGIN_NONE:
case SO_EE_ORIGIN_LOCAL:
_proto("Rx Received local error { error=%d }", err);
- err += RXRPC_LOCAL_ERROR_OFFSET;
+ compl = RXRPC_CALL_LOCAL_ERROR;
break;
case SO_EE_ORIGIN_ICMP6:
@@ -264,48 +268,23 @@ static void rxrpc_store_error(struct rxrpc_peer *peer,
break;
}
- peer->error_report = err;
+ rxrpc_distribute_error(peer, err, compl);
}
/*
- * Distribute an error that occurred on a peer
+ * Distribute an error that occurred on a peer.
*/
-void rxrpc_peer_error_distributor(struct work_struct *work)
+static void rxrpc_distribute_error(struct rxrpc_peer *peer, int error,
+ enum rxrpc_call_completion compl)
{
- struct rxrpc_peer *peer =
- container_of(work, struct rxrpc_peer, error_distributor);
struct rxrpc_call *call;
- enum rxrpc_call_completion compl;
- int error;
-
- _enter("");
-
- error = READ_ONCE(peer->error_report);
- if (error < RXRPC_LOCAL_ERROR_OFFSET) {
- compl = RXRPC_CALL_NETWORK_ERROR;
- } else {
- compl = RXRPC_CALL_LOCAL_ERROR;
- error -= RXRPC_LOCAL_ERROR_OFFSET;
- }
- _debug("ISSUE ERROR %s %d", rxrpc_call_completions[compl], error);
-
- spin_lock_bh(&peer->lock);
-
- while (!hlist_empty(&peer->error_targets)) {
- call = hlist_entry(peer->error_targets.first,
- struct rxrpc_call, error_link);
- hlist_del_init(&call->error_link);
+ hlist_for_each_entry_rcu(call, &peer->error_targets, error_link) {
rxrpc_see_call(call);
-
- if (rxrpc_set_call_completion(call, compl, 0, -error))
+ if (call->state < RXRPC_CALL_COMPLETE &&
+ rxrpc_set_call_completion(call, compl, 0, -error))
rxrpc_notify_socket(call);
}
-
- spin_unlock_bh(&peer->lock);
-
- rxrpc_put_peer(peer);
- _leave("");
}
/*
@@ -325,6 +304,8 @@ void rxrpc_peer_add_rtt(struct rxrpc_call *call, enum rxrpc_rtt_rx_trace why,
if (rtt < 0)
return;
+ spin_lock(&peer->rtt_input_lock);
+
/* Replace the oldest datum in the RTT buffer */
sum -= peer->rtt_cache[cursor];
sum += rtt;
@@ -336,6 +317,8 @@ void rxrpc_peer_add_rtt(struct rxrpc_call *call, enum rxrpc_rtt_rx_trace why,
peer->rtt_usage = usage;
}
+ spin_unlock(&peer->rtt_input_lock);
+
/* Now recalculate the average */
if (usage == RXRPC_RTT_CACHE_SIZE) {
avg = sum / RXRPC_RTT_CACHE_SIZE;
@@ -344,6 +327,7 @@ void rxrpc_peer_add_rtt(struct rxrpc_call *call, enum rxrpc_rtt_rx_trace why,
do_div(avg, usage);
}
+ /* Don't need to update this under lock */
peer->rtt = avg;
trace_rxrpc_rtt_rx(call, why, send_serial, resp_serial, rtt,
usage, avg);
diff --git a/net/rxrpc/peer_object.c b/net/rxrpc/peer_object.c
index 1dc7648e3eff..5691b7d266ca 100644
--- a/net/rxrpc/peer_object.c
+++ b/net/rxrpc/peer_object.c
@@ -124,11 +124,9 @@ static struct rxrpc_peer *__rxrpc_lookup_peer_rcu(
struct rxrpc_net *rxnet = local->rxnet;
hash_for_each_possible_rcu(rxnet->peer_hash, peer, hash_link, hash_key) {
- if (rxrpc_peer_cmp_key(peer, local, srx, hash_key) == 0) {
- if (atomic_read(&peer->usage) == 0)
- return NULL;
+ if (rxrpc_peer_cmp_key(peer, local, srx, hash_key) == 0 &&
+ atomic_read(&peer->usage) > 0)
return peer;
- }
}
return NULL;
@@ -155,8 +153,10 @@ struct rxrpc_peer *rxrpc_lookup_peer_rcu(struct rxrpc_local *local,
* assess the MTU size for the network interface through which this peer is
* reached
*/
-static void rxrpc_assess_MTU_size(struct rxrpc_peer *peer)
+static void rxrpc_assess_MTU_size(struct rxrpc_sock *rx,
+ struct rxrpc_peer *peer)
{
+ struct net *net = sock_net(&rx->sk);
struct dst_entry *dst;
struct rtable *rt;
struct flowi fl;
@@ -171,7 +171,7 @@ static void rxrpc_assess_MTU_size(struct rxrpc_peer *peer)
switch (peer->srx.transport.family) {
case AF_INET:
rt = ip_route_output_ports(
- &init_net, fl4, NULL,
+ net, fl4, NULL,
peer->srx.transport.sin.sin_addr.s_addr, 0,
htons(7000), htons(7001), IPPROTO_UDP, 0, 0);
if (IS_ERR(rt)) {
@@ -190,7 +190,7 @@ static void rxrpc_assess_MTU_size(struct rxrpc_peer *peer)
sizeof(struct in6_addr));
fl6->fl6_dport = htons(7001);
fl6->fl6_sport = htons(7000);
- dst = ip6_route_output(&init_net, NULL, fl6);
+ dst = ip6_route_output(net, NULL, fl6);
if (dst->error) {
_leave(" [route err %d]", dst->error);
return;
@@ -222,11 +222,10 @@ struct rxrpc_peer *rxrpc_alloc_peer(struct rxrpc_local *local, gfp_t gfp)
atomic_set(&peer->usage, 1);
peer->local = local;
INIT_HLIST_HEAD(&peer->error_targets);
- INIT_WORK(&peer->error_distributor,
- &rxrpc_peer_error_distributor);
peer->service_conns = RB_ROOT;
seqlock_init(&peer->service_conn_lock);
spin_lock_init(&peer->lock);
+ spin_lock_init(&peer->rtt_input_lock);
peer->debug_id = atomic_inc_return(&rxrpc_debug_id);
if (RXRPC_TX_SMSS > 2190)
@@ -244,10 +243,11 @@ struct rxrpc_peer *rxrpc_alloc_peer(struct rxrpc_local *local, gfp_t gfp)
/*
* Initialise peer record.
*/
-static void rxrpc_init_peer(struct rxrpc_peer *peer, unsigned long hash_key)
+static void rxrpc_init_peer(struct rxrpc_sock *rx, struct rxrpc_peer *peer,
+ unsigned long hash_key)
{
peer->hash_key = hash_key;
- rxrpc_assess_MTU_size(peer);
+ rxrpc_assess_MTU_size(rx, peer);
peer->mtu = peer->if_mtu;
peer->rtt_last_req = ktime_get_real();
@@ -279,7 +279,8 @@ static void rxrpc_init_peer(struct rxrpc_peer *peer, unsigned long hash_key)
/*
* Set up a new peer.
*/
-static struct rxrpc_peer *rxrpc_create_peer(struct rxrpc_local *local,
+static struct rxrpc_peer *rxrpc_create_peer(struct rxrpc_sock *rx,
+ struct rxrpc_local *local,
struct sockaddr_rxrpc *srx,
unsigned long hash_key,
gfp_t gfp)
@@ -291,7 +292,7 @@ static struct rxrpc_peer *rxrpc_create_peer(struct rxrpc_local *local,
peer = rxrpc_alloc_peer(local, gfp);
if (peer) {
memcpy(&peer->srx, srx, sizeof(*srx));
- rxrpc_init_peer(peer, hash_key);
+ rxrpc_init_peer(rx, peer, hash_key);
}
_leave(" = %p", peer);
@@ -299,40 +300,31 @@ static struct rxrpc_peer *rxrpc_create_peer(struct rxrpc_local *local,
}
/*
- * Set up a new incoming peer. The address is prestored in the preallocated
- * peer.
+ * Set up a new incoming peer. There shouldn't be any other matching peers
+ * since we've already done a search in the list from the non-reentrant context
+ * (the data_ready handler) that is the only place we can add new peers.
*/
-struct rxrpc_peer *rxrpc_lookup_incoming_peer(struct rxrpc_local *local,
- struct rxrpc_peer *prealloc)
+void rxrpc_new_incoming_peer(struct rxrpc_sock *rx, struct rxrpc_local *local,
+ struct rxrpc_peer *peer)
{
- struct rxrpc_peer *peer;
struct rxrpc_net *rxnet = local->rxnet;
unsigned long hash_key;
- hash_key = rxrpc_peer_hash_key(local, &prealloc->srx);
- prealloc->local = local;
- rxrpc_init_peer(prealloc, hash_key);
+ hash_key = rxrpc_peer_hash_key(local, &peer->srx);
+ peer->local = local;
+ rxrpc_init_peer(rx, peer, hash_key);
spin_lock(&rxnet->peer_hash_lock);
-
- /* Need to check that we aren't racing with someone else */
- peer = __rxrpc_lookup_peer_rcu(local, &prealloc->srx, hash_key);
- if (peer && !rxrpc_get_peer_maybe(peer))
- peer = NULL;
- if (!peer) {
- peer = prealloc;
- hash_add_rcu(rxnet->peer_hash, &peer->hash_link, hash_key);
- list_add_tail(&peer->keepalive_link, &rxnet->peer_keepalive_new);
- }
-
+ hash_add_rcu(rxnet->peer_hash, &peer->hash_link, hash_key);
+ list_add_tail(&peer->keepalive_link, &rxnet->peer_keepalive_new);
spin_unlock(&rxnet->peer_hash_lock);
- return peer;
}
/*
* obtain a remote transport endpoint for the specified address
*/
-struct rxrpc_peer *rxrpc_lookup_peer(struct rxrpc_local *local,
+struct rxrpc_peer *rxrpc_lookup_peer(struct rxrpc_sock *rx,
+ struct rxrpc_local *local,
struct sockaddr_rxrpc *srx, gfp_t gfp)
{
struct rxrpc_peer *peer, *candidate;
@@ -352,7 +344,7 @@ struct rxrpc_peer *rxrpc_lookup_peer(struct rxrpc_local *local,
/* The peer is not yet present in hash - create a candidate
* for a new record and then redo the search.
*/
- candidate = rxrpc_create_peer(local, srx, hash_key, gfp);
+ candidate = rxrpc_create_peer(rx, local, srx, hash_key, gfp);
if (!candidate) {
_leave(" = NULL [nomem]");
return NULL;
@@ -416,21 +408,6 @@ struct rxrpc_peer *rxrpc_get_peer_maybe(struct rxrpc_peer *peer)
}
/*
- * Queue a peer record. This passes the caller's ref to the workqueue.
- */
-void __rxrpc_queue_peer_error(struct rxrpc_peer *peer)
-{
- const void *here = __builtin_return_address(0);
- int n;
-
- n = atomic_read(&peer->usage);
- if (rxrpc_queue_work(&peer->error_distributor))
- trace_rxrpc_peer(peer, rxrpc_peer_queued_error, n, here);
- else
- rxrpc_put_peer(peer);
-}
-
-/*
* Discard a peer record.
*/
static void __rxrpc_put_peer(struct rxrpc_peer *peer)
diff --git a/net/rxrpc/proc.c b/net/rxrpc/proc.c
index 9805e3b85c36..c7d976859d40 100644
--- a/net/rxrpc/proc.c
+++ b/net/rxrpc/proc.c
@@ -212,3 +212,129 @@ const struct seq_operations rxrpc_connection_seq_ops = {
.stop = rxrpc_connection_seq_stop,
.show = rxrpc_connection_seq_show,
};
+
+/*
+ * generate a list of extant virtual peers in /proc/net/rxrpc/peers
+ */
+static int rxrpc_peer_seq_show(struct seq_file *seq, void *v)
+{
+ struct rxrpc_peer *peer;
+ time64_t now;
+ char lbuff[50], rbuff[50];
+
+ if (v == SEQ_START_TOKEN) {
+ seq_puts(seq,
+ "Proto Local "
+ " Remote "
+ " Use CW MTU LastUse RTT Rc\n"
+ );
+ return 0;
+ }
+
+ peer = list_entry(v, struct rxrpc_peer, hash_link);
+
+ sprintf(lbuff, "%pISpc", &peer->local->srx.transport);
+
+ sprintf(rbuff, "%pISpc", &peer->srx.transport);
+
+ now = ktime_get_seconds();
+ seq_printf(seq,
+ "UDP %-47.47s %-47.47s %3u"
+ " %3u %5u %6llus %12llu %2u\n",
+ lbuff,
+ rbuff,
+ atomic_read(&peer->usage),
+ peer->cong_cwnd,
+ peer->mtu,
+ now - peer->last_tx_at,
+ peer->rtt,
+ peer->rtt_cursor);
+
+ return 0;
+}
+
+static void *rxrpc_peer_seq_start(struct seq_file *seq, loff_t *_pos)
+ __acquires(rcu)
+{
+ struct rxrpc_net *rxnet = rxrpc_net(seq_file_net(seq));
+ unsigned int bucket, n;
+ unsigned int shift = 32 - HASH_BITS(rxnet->peer_hash);
+ void *p;
+
+ rcu_read_lock();
+
+ if (*_pos >= UINT_MAX)
+ return NULL;
+
+ n = *_pos & ((1U << shift) - 1);
+ bucket = *_pos >> shift;
+ for (;;) {
+ if (bucket >= HASH_SIZE(rxnet->peer_hash)) {
+ *_pos = UINT_MAX;
+ return NULL;
+ }
+ if (n == 0) {
+ if (bucket == 0)
+ return SEQ_START_TOKEN;
+ *_pos += 1;
+ n++;
+ }
+
+ p = seq_hlist_start_rcu(&rxnet->peer_hash[bucket], n - 1);
+ if (p)
+ return p;
+ bucket++;
+ n = 1;
+ *_pos = (bucket << shift) | n;
+ }
+}
+
+static void *rxrpc_peer_seq_next(struct seq_file *seq, void *v, loff_t *_pos)
+{
+ struct rxrpc_net *rxnet = rxrpc_net(seq_file_net(seq));
+ unsigned int bucket, n;
+ unsigned int shift = 32 - HASH_BITS(rxnet->peer_hash);
+ void *p;
+
+ if (*_pos >= UINT_MAX)
+ return NULL;
+
+ bucket = *_pos >> shift;
+
+ p = seq_hlist_next_rcu(v, &rxnet->peer_hash[bucket], _pos);
+ if (p)
+ return p;
+
+ for (;;) {
+ bucket++;
+ n = 1;
+ *_pos = (bucket << shift) | n;
+
+ if (bucket >= HASH_SIZE(rxnet->peer_hash)) {
+ *_pos = UINT_MAX;
+ return NULL;
+ }
+ if (n == 0) {
+ *_pos += 1;
+ n++;
+ }
+
+ p = seq_hlist_start_rcu(&rxnet->peer_hash[bucket], n - 1);
+ if (p)
+ return p;
+ }
+}
+
+static void rxrpc_peer_seq_stop(struct seq_file *seq, void *v)
+ __releases(rcu)
+{
+ rcu_read_unlock();
+}
+
+
+const struct seq_operations rxrpc_peer_seq_ops = {
+ .start = rxrpc_peer_seq_start,
+ .next = rxrpc_peer_seq_next,
+ .stop = rxrpc_peer_seq_stop,
+ .show = rxrpc_peer_seq_show,
+};
diff --git a/net/rxrpc/protocol.h b/net/rxrpc/protocol.h
index 93da73bf7098..f9cb83c938f3 100644
--- a/net/rxrpc/protocol.h
+++ b/net/rxrpc/protocol.h
@@ -50,7 +50,6 @@ struct rxrpc_wire_header {
#define RXRPC_PACKET_TYPE_10 10 /* Ignored */
#define RXRPC_PACKET_TYPE_11 11 /* Ignored */
#define RXRPC_PACKET_TYPE_VERSION 13 /* version string request */
-#define RXRPC_N_PACKET_TYPES 14 /* number of packet types (incl type 0) */
uint8_t flags; /* packet flags */
#define RXRPC_CLIENT_INITIATED 0x01 /* signifies a packet generated by a client */
@@ -72,20 +71,6 @@ struct rxrpc_wire_header {
} __packed;
-#define RXRPC_SUPPORTED_PACKET_TYPES ( \
- (1 << RXRPC_PACKET_TYPE_DATA) | \
- (1 << RXRPC_PACKET_TYPE_ACK) | \
- (1 << RXRPC_PACKET_TYPE_BUSY) | \
- (1 << RXRPC_PACKET_TYPE_ABORT) | \
- (1 << RXRPC_PACKET_TYPE_ACKALL) | \
- (1 << RXRPC_PACKET_TYPE_CHALLENGE) | \
- (1 << RXRPC_PACKET_TYPE_RESPONSE) | \
- /*(1 << RXRPC_PACKET_TYPE_DEBUG) | */ \
- (1 << RXRPC_PACKET_TYPE_PARAMS) | \
- (1 << RXRPC_PACKET_TYPE_10) | \
- (1 << RXRPC_PACKET_TYPE_11) | \
- (1 << RXRPC_PACKET_TYPE_VERSION))
-
/*****************************************************************************/
/*
* jumbo packet secondary header
diff --git a/net/rxrpc/recvmsg.c b/net/rxrpc/recvmsg.c
index 816b19a78809..eaf19ebaa964 100644
--- a/net/rxrpc/recvmsg.c
+++ b/net/rxrpc/recvmsg.c
@@ -715,3 +715,46 @@ call_complete:
goto out;
}
EXPORT_SYMBOL(rxrpc_kernel_recv_data);
+
+/**
+ * rxrpc_kernel_get_reply_time - Get timestamp on first reply packet
+ * @sock: The socket that the call exists on
+ * @call: The call to query
+ * @_ts: Where to put the timestamp
+ *
+ * Retrieve the timestamp from the first DATA packet of the reply if it is
+ * in the ring. Returns true if successful, false if not.
+ */
+bool rxrpc_kernel_get_reply_time(struct socket *sock, struct rxrpc_call *call,
+ ktime_t *_ts)
+{
+ struct sk_buff *skb;
+ rxrpc_seq_t hard_ack, top, seq;
+ bool success = false;
+
+ mutex_lock(&call->user_mutex);
+
+ if (READ_ONCE(call->state) != RXRPC_CALL_CLIENT_RECV_REPLY)
+ goto out;
+
+ hard_ack = call->rx_hard_ack;
+ if (hard_ack != 0)
+ goto out;
+
+ seq = hard_ack + 1;
+ top = smp_load_acquire(&call->rx_top);
+ if (after(seq, top))
+ goto out;
+
+ skb = call->rxtx_buffer[seq & RXRPC_RXTX_BUFF_MASK];
+ if (!skb)
+ goto out;
+
+ *_ts = skb_get_ktime(skb);
+ success = true;
+
+out:
+ mutex_unlock(&call->user_mutex);
+ return success;
+}
+EXPORT_SYMBOL(rxrpc_kernel_get_reply_time);
diff --git a/net/rxrpc/skbuff.c b/net/rxrpc/skbuff.c
index b8985d01876a..913dca65cc65 100644
--- a/net/rxrpc/skbuff.c
+++ b/net/rxrpc/skbuff.c
@@ -69,21 +69,6 @@ void rxrpc_free_skb(struct sk_buff *skb, enum rxrpc_skb_trace op)
}
/*
- * Note the injected loss of a socket buffer.
- */
-void rxrpc_lose_skb(struct sk_buff *skb, enum rxrpc_skb_trace op)
-{
- const void *here = __builtin_return_address(0);
- if (skb) {
- int n;
- CHECK_SLAB_OKAY(&skb->users);
- n = atomic_dec_return(select_skb_count(op));
- trace_rxrpc_skb(skb, op, refcount_read(&skb->users), n, here);
- kfree_skb(skb);
- }
-}
-
-/*
* Clear a queue of socket buffers.
*/
void rxrpc_purge_queue(struct sk_buff_head *list)
diff --git a/net/rxrpc/utils.c b/net/rxrpc/utils.c
index e801171fa351..ff7af71c4b49 100644
--- a/net/rxrpc/utils.c
+++ b/net/rxrpc/utils.c
@@ -17,28 +17,17 @@
/*
* Fill out a peer address from a socket buffer containing a packet.
*/
-int rxrpc_extract_addr_from_skb(struct rxrpc_local *local,
- struct sockaddr_rxrpc *srx,
- struct sk_buff *skb)
+int rxrpc_extract_addr_from_skb(struct sockaddr_rxrpc *srx, struct sk_buff *skb)
{
memset(srx, 0, sizeof(*srx));
switch (ntohs(skb->protocol)) {
case ETH_P_IP:
- if (local->srx.transport.family == AF_INET6) {
- srx->transport_type = SOCK_DGRAM;
- srx->transport_len = sizeof(srx->transport.sin6);
- srx->transport.sin6.sin6_family = AF_INET6;
- srx->transport.sin6.sin6_port = udp_hdr(skb)->source;
- srx->transport.sin6.sin6_addr.s6_addr32[2] = htonl(0xffff);
- srx->transport.sin6.sin6_addr.s6_addr32[3] = ip_hdr(skb)->saddr;
- } else {
- srx->transport_type = SOCK_DGRAM;
- srx->transport_len = sizeof(srx->transport.sin);
- srx->transport.sin.sin_family = AF_INET;
- srx->transport.sin.sin_port = udp_hdr(skb)->source;
- srx->transport.sin.sin_addr.s_addr = ip_hdr(skb)->saddr;
- }
+ srx->transport_type = SOCK_DGRAM;
+ srx->transport_len = sizeof(srx->transport.sin);
+ srx->transport.sin.sin_family = AF_INET;
+ srx->transport.sin.sin_port = udp_hdr(skb)->source;
+ srx->transport.sin.sin_addr.s_addr = ip_hdr(skb)->saddr;
return 0;
#ifdef CONFIG_AF_RXRPC_IPV6
generated by cgit (git 2.34.1) at 2024-06-08 21:53:23 +0000