Update Linux to v5.4.148
Sourced from [1]
[1] https://cdn.kernel.org/pub/linux/kernel/v5.x/linux-5.4.148.tar.gz
Change-Id: Ib3d26c5ba9b022e2e03533005c4fed4d7c30b61b
Signed-off-by: Olivier Deprez <olivier.deprez@arm.com>
diff --git a/net/rxrpc/Makefile b/net/rxrpc/Makefile
index 6ffb7e9..ddd0f95 100644
--- a/net/rxrpc/Makefile
+++ b/net/rxrpc/Makefile
@@ -25,6 +25,7 @@
peer_event.o \
peer_object.o \
recvmsg.o \
+ rtt.o \
security.o \
sendmsg.o \
skbuff.o \
diff --git a/net/rxrpc/af_rxrpc.c b/net/rxrpc/af_rxrpc.c
index d72ddb6..9bacec6 100644
--- a/net/rxrpc/af_rxrpc.c
+++ b/net/rxrpc/af_rxrpc.c
@@ -194,6 +194,7 @@
service_in_use:
write_unlock(&local->services_lock);
rxrpc_unuse_local(local);
+ rxrpc_put_local(local);
ret = -EADDRINUSE;
error_unlock:
release_sock(&rx->sk);
@@ -284,7 +285,7 @@
gfp_t gfp,
rxrpc_notify_rx_t notify_rx,
bool upgrade,
- bool intr,
+ enum rxrpc_interruptibility interruptibility,
unsigned int debug_id)
{
struct rxrpc_conn_parameters cp;
@@ -309,7 +310,7 @@
memset(&p, 0, sizeof(p));
p.user_call_ID = user_call_ID;
p.tx_total_len = tx_total_len;
- p.intr = intr;
+ p.interruptibility = interruptibility;
memset(&cp, 0, sizeof(cp));
cp.local = rx->local;
@@ -370,45 +371,18 @@
* rxrpc_kernel_check_life - Check to see whether a call is still alive
* @sock: The socket the call is on
* @call: The call to check
- * @_life: Where to store the life value
*
- * Allow a kernel service to find out whether a call is still alive - ie. we're
- * getting ACKs from the server. Passes back in *_life a number representing
- * the life state which can be compared to that returned by a previous call and
- * return true if the call is still alive.
- *
- * If the life state stalls, rxrpc_kernel_probe_life() should be called and
- * then 2RTT waited.
+ * Allow a kernel service to find out whether a call is still alive -
+ * ie. whether it has completed.
*/
bool rxrpc_kernel_check_life(const struct socket *sock,
- const struct rxrpc_call *call,
- u32 *_life)
+ const struct rxrpc_call *call)
{
- *_life = call->acks_latest;
return call->state != RXRPC_CALL_COMPLETE;
}
EXPORT_SYMBOL(rxrpc_kernel_check_life);
/**
- * rxrpc_kernel_probe_life - Poke the peer to see if it's still alive
- * @sock: The socket the call is on
- * @call: The call to check
- *
- * In conjunction with rxrpc_kernel_check_life(), allow a kernel service to
- * find out whether a call is still alive by pinging it. This should cause the
- * life state to be bumped in about 2*RTT.
- *
- * The must be called in TASK_RUNNING state on pain of might_sleep() objecting.
- */
-void rxrpc_kernel_probe_life(struct socket *sock, struct rxrpc_call *call)
-{
- rxrpc_propose_ACK(call, RXRPC_ACK_PING, 0, true, false,
- rxrpc_propose_ack_ping_for_check_life);
- rxrpc_send_ack_packet(call, true, NULL);
-}
-EXPORT_SYMBOL(rxrpc_kernel_probe_life);
-
-/**
* rxrpc_kernel_get_epoch - Retrieve the epoch value from a call.
* @sock: The socket the call is on
* @call: The call to query
@@ -899,6 +873,7 @@
rxrpc_purge_queue(&sk->sk_receive_queue);
rxrpc_unuse_local(rx->local);
+ rxrpc_put_local(rx->local);
rx->local = NULL;
key_put(rx->key);
rx->key = NULL;
@@ -1001,7 +976,7 @@
goto error_security;
}
- ret = register_pernet_subsys(&rxrpc_net_ops);
+ ret = register_pernet_device(&rxrpc_net_ops);
if (ret)
goto error_pernet;
@@ -1046,7 +1021,7 @@
error_sock:
proto_unregister(&rxrpc_proto);
error_proto:
- unregister_pernet_subsys(&rxrpc_net_ops);
+ unregister_pernet_device(&rxrpc_net_ops);
error_pernet:
rxrpc_exit_security();
error_security:
@@ -1068,7 +1043,7 @@
unregister_key_type(&key_type_rxrpc);
sock_unregister(PF_RXRPC);
proto_unregister(&rxrpc_proto);
- unregister_pernet_subsys(&rxrpc_net_ops);
+ unregister_pernet_device(&rxrpc_net_ops);
ASSERTCMP(atomic_read(&rxrpc_n_tx_skbs), ==, 0);
ASSERTCMP(atomic_read(&rxrpc_n_rx_skbs), ==, 0);
diff --git a/net/rxrpc/ar-internal.h b/net/rxrpc/ar-internal.h
index 7c7d10f..9fe264b 100644
--- a/net/rxrpc/ar-internal.h
+++ b/net/rxrpc/ar-internal.h
@@ -7,6 +7,7 @@
#include <linux/atomic.h>
#include <linux/seqlock.h>
+#include <linux/win_minmax.h>
#include <net/net_namespace.h>
#include <net/netns/generic.h>
#include <net/sock.h>
@@ -209,6 +210,7 @@
struct rxrpc_security {
const char *name; /* name of this service */
u8 security_index; /* security type provided */
+ u32 no_key_abort; /* Abort code indicating no key */
/* Initialise a security service */
int (*init)(void);
@@ -310,11 +312,14 @@
#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 */
- u64 rtt_cache[RXRPC_RTT_CACHE_SIZE]; /* Determined RTT cache */
- u8 rtt_cursor; /* next entry at which to insert */
- u8 rtt_usage; /* amount of cache actually used */
+ unsigned int rtt_count; /* Number of samples we've got */
+
+ u32 srtt_us; /* smoothed round trip time << 3 in usecs */
+ u32 mdev_us; /* medium deviation */
+ u32 mdev_max_us; /* maximal mdev for the last rtt period */
+ u32 rttvar_us; /* smoothed mdev_max */
+ u32 rto_j; /* Retransmission timeout in jiffies */
+ u8 backoff; /* Backoff timeout */
u8 cong_cwnd; /* Congestion window size */
};
@@ -488,7 +493,7 @@
RXRPC_CALL_BEGAN_RX_TIMER, /* We began the expect_rx_by timer */
RXRPC_CALL_RX_HEARD, /* The peer responded at least once to this call */
RXRPC_CALL_RX_UNDERRUN, /* Got data underrun */
- RXRPC_CALL_IS_INTR, /* The call is interruptible */
+ RXRPC_CALL_DISCONNECTED, /* The call has been disconnected */
};
/*
@@ -596,6 +601,7 @@
atomic_t usage;
u16 service_id; /* service ID */
u8 security_ix; /* Security type */
+ enum rxrpc_interruptibility interruptibility; /* At what point call may be interrupted */
u32 call_id; /* call ID on connection */
u32 cid; /* connection ID plus channel index */
int debug_id; /* debug ID for printks */
@@ -673,7 +679,6 @@
/* transmission-phase ACK management */
ktime_t acks_latest_ts; /* Timestamp of latest ACK received */
- rxrpc_serial_t acks_latest; /* serial number of latest ACK received */
rxrpc_seq_t acks_lowest_nak; /* Lowest NACK in the buffer (or ==tx_hard_ack) */
rxrpc_seq_t acks_lost_top; /* tx_top at the time lost-ack ping sent */
rxrpc_serial_t acks_lost_ping; /* Serial number of probe ACK */
@@ -719,7 +724,7 @@
u32 normal; /* Max time since last call packet (msec) */
} timeouts;
u8 nr_timeouts; /* Number of timeouts specified */
- bool intr; /* The call is interruptible */
+ enum rxrpc_interruptibility interruptibility; /* How is interruptible is the call? */
};
struct rxrpc_send_params {
@@ -977,8 +982,9 @@
struct rxrpc_connection *rxrpc_find_service_conn_rcu(struct rxrpc_peer *,
struct sk_buff *);
struct rxrpc_connection *rxrpc_prealloc_service_connection(struct rxrpc_net *, gfp_t);
-void rxrpc_new_incoming_connection(struct rxrpc_sock *,
- struct rxrpc_connection *, struct sk_buff *);
+void rxrpc_new_incoming_connection(struct rxrpc_sock *, struct rxrpc_connection *,
+ const struct rxrpc_security *, struct key *,
+ struct sk_buff *);
void rxrpc_unpublish_service_conn(struct rxrpc_connection *);
/*
@@ -1019,6 +1025,16 @@
void rxrpc_queue_local(struct rxrpc_local *);
void rxrpc_destroy_all_locals(struct rxrpc_net *);
+static inline bool __rxrpc_unuse_local(struct rxrpc_local *local)
+{
+ return atomic_dec_return(&local->active_users) == 0;
+}
+
+static inline bool __rxrpc_use_local(struct rxrpc_local *local)
+{
+ return atomic_fetch_add_unless(&local->active_users, 1, 0) != 0;
+}
+
/*
* misc.c
*/
@@ -1029,7 +1045,6 @@
extern unsigned int rxrpc_rx_window_size;
extern unsigned int rxrpc_rx_mtu;
extern unsigned int rxrpc_rx_jumbo_max;
-extern unsigned long rxrpc_resend_timeout;
extern const s8 rxrpc_ack_priority[];
@@ -1057,8 +1072,6 @@
* peer_event.c
*/
void rxrpc_error_report(struct sock *);
-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 *);
/*
@@ -1091,6 +1104,14 @@
int rxrpc_recvmsg(struct socket *, struct msghdr *, size_t, int);
/*
+ * rtt.c
+ */
+void rxrpc_peer_add_rtt(struct rxrpc_call *, enum rxrpc_rtt_rx_trace,
+ rxrpc_serial_t, rxrpc_serial_t, ktime_t, ktime_t);
+unsigned long rxrpc_get_rto_backoff(struct rxrpc_peer *, bool);
+void rxrpc_peer_init_rtt(struct rxrpc_peer *);
+
+/*
* rxkad.c
*/
#ifdef CONFIG_RXKAD
@@ -1103,7 +1124,9 @@
int __init rxrpc_init_security(void);
void rxrpc_exit_security(void);
int rxrpc_init_client_conn_security(struct rxrpc_connection *);
-int rxrpc_init_server_conn_security(struct rxrpc_connection *);
+bool rxrpc_look_up_server_security(struct rxrpc_local *, struct rxrpc_sock *,
+ const struct rxrpc_security **, struct key **,
+ struct sk_buff *);
/*
* sendmsg.c
diff --git a/net/rxrpc/call_accept.c b/net/rxrpc/call_accept.c
index 135bf5c..55fb374 100644
--- a/net/rxrpc/call_accept.c
+++ b/net/rxrpc/call_accept.c
@@ -22,6 +22,11 @@
#include <net/ip.h>
#include "ar-internal.h"
+static void rxrpc_dummy_notify(struct sock *sk, struct rxrpc_call *call,
+ unsigned long user_call_ID)
+{
+}
+
/*
* Preallocate a single service call, connection and peer and, if possible,
* give them a user ID and attach the user's side of the ID to them.
@@ -202,6 +207,7 @@
tail = b->peer_backlog_tail;
while (CIRC_CNT(head, tail, size) > 0) {
struct rxrpc_peer *peer = b->peer_backlog[tail];
+ rxrpc_put_local(peer->local);
kfree(peer);
tail = (tail + 1) & (size - 1);
}
@@ -228,6 +234,8 @@
if (rx->discard_new_call) {
_debug("discard %lx", call->user_call_ID);
rx->discard_new_call(call, call->user_call_ID);
+ if (call->notify_rx)
+ call->notify_rx = rxrpc_dummy_notify;
rxrpc_put_call(call, rxrpc_call_put_kernel);
}
rxrpc_call_completed(call);
@@ -240,6 +248,22 @@
}
/*
+ * Ping the other end to fill our RTT cache and to retrieve the rwind
+ * and MTU parameters.
+ */
+static void rxrpc_send_ping(struct rxrpc_call *call, struct sk_buff *skb)
+{
+ struct rxrpc_skb_priv *sp = rxrpc_skb(skb);
+ ktime_t now = skb->tstamp;
+
+ if (call->peer->rtt_count < 3 ||
+ ktime_before(ktime_add_ms(call->peer->rtt_last_req, 1000), now))
+ rxrpc_propose_ACK(call, RXRPC_ACK_PING, sp->hdr.serial,
+ true, true,
+ rxrpc_propose_ack_ping_for_params);
+}
+
+/*
* Allocate a new incoming call from the prealloc pool, along with a connection
* and a peer as necessary.
*/
@@ -247,6 +271,8 @@
struct rxrpc_local *local,
struct rxrpc_peer *peer,
struct rxrpc_connection *conn,
+ const struct rxrpc_security *sec,
+ struct key *key,
struct sk_buff *skb)
{
struct rxrpc_backlog *b = rx->backlog;
@@ -294,7 +320,7 @@
conn->params.local = rxrpc_get_local(local);
conn->params.peer = peer;
rxrpc_see_connection(conn);
- rxrpc_new_incoming_connection(rx, conn, skb);
+ rxrpc_new_incoming_connection(rx, conn, sec, key, skb);
} else {
rxrpc_get_connection(conn);
}
@@ -333,9 +359,11 @@
struct sk_buff *skb)
{
struct rxrpc_skb_priv *sp = rxrpc_skb(skb);
+ const struct rxrpc_security *sec = NULL;
struct rxrpc_connection *conn;
struct rxrpc_peer *peer = NULL;
- struct rxrpc_call *call;
+ struct rxrpc_call *call = NULL;
+ struct key *key = NULL;
_enter("");
@@ -346,9 +374,7 @@
sp->hdr.seq, RX_INVALID_OPERATION, ESHUTDOWN);
skb->mark = RXRPC_SKB_MARK_REJECT_ABORT;
skb->priority = RX_INVALID_OPERATION;
- _leave(" = NULL [close]");
- call = NULL;
- goto out;
+ goto no_call;
}
/* The peer, connection and call may all have sprung into existence due
@@ -358,29 +384,19 @@
*/
conn = rxrpc_find_connection_rcu(local, skb, &peer);
- call = rxrpc_alloc_incoming_call(rx, local, peer, conn, skb);
+ if (!conn && !rxrpc_look_up_server_security(local, rx, &sec, &key, skb))
+ goto no_call;
+
+ call = rxrpc_alloc_incoming_call(rx, local, peer, conn, sec, key, skb);
+ key_put(key);
if (!call) {
skb->mark = RXRPC_SKB_MARK_REJECT_BUSY;
- _leave(" = NULL [busy]");
- call = NULL;
- goto out;
+ goto no_call;
}
trace_rxrpc_receive(call, rxrpc_receive_incoming,
sp->hdr.serial, sp->hdr.seq);
- /* Lock the call to prevent rxrpc_kernel_send/recv_data() and
- * sendmsg()/recvmsg() inconveniently stealing the mutex once the
- * notification is generated.
- *
- * The BUG should never happen because the kernel should be well
- * behaved enough not to access the call before the first notification
- * event and userspace is prevented from doing so until the state is
- * appropriate.
- */
- if (!mutex_trylock(&call->user_mutex))
- BUG();
-
/* Make the call live. */
rxrpc_incoming_call(rx, call, skb);
conn = call->conn;
@@ -421,6 +437,9 @@
BUG();
}
spin_unlock(&conn->state_lock);
+ spin_unlock(&rx->incoming_lock);
+
+ rxrpc_send_ping(call, skb);
if (call->state == RXRPC_CALL_SERVER_ACCEPTING)
rxrpc_notify_socket(call);
@@ -433,9 +452,12 @@
rxrpc_put_call(call, rxrpc_call_put);
_leave(" = %p{%d}", call, call->debug_id);
-out:
- spin_unlock(&rx->incoming_lock);
return call;
+
+no_call:
+ spin_unlock(&rx->incoming_lock);
+ _leave(" = NULL [%u]", skb->mark);
+ return NULL;
}
/*
diff --git a/net/rxrpc/call_event.c b/net/rxrpc/call_event.c
index cedbbb3..9ff85ee 100644
--- a/net/rxrpc/call_event.c
+++ b/net/rxrpc/call_event.c
@@ -111,8 +111,8 @@
} else {
unsigned long now = jiffies, ack_at;
- if (call->peer->rtt_usage > 0)
- ack_at = nsecs_to_jiffies(call->peer->rtt);
+ if (call->peer->srtt_us != 0)
+ ack_at = usecs_to_jiffies(call->peer->srtt_us >> 3);
else
ack_at = expiry;
@@ -157,24 +157,18 @@
static void rxrpc_resend(struct rxrpc_call *call, unsigned long now_j)
{
struct sk_buff *skb;
- unsigned long resend_at;
+ unsigned long resend_at, rto_j;
rxrpc_seq_t cursor, seq, top;
- ktime_t now, max_age, oldest, ack_ts, timeout, min_timeo;
+ ktime_t now, max_age, oldest, ack_ts;
int ix;
u8 annotation, anno_type, retrans = 0, unacked = 0;
_enter("{%d,%d}", call->tx_hard_ack, call->tx_top);
- if (call->peer->rtt_usage > 1)
- timeout = ns_to_ktime(call->peer->rtt * 3 / 2);
- else
- timeout = ms_to_ktime(rxrpc_resend_timeout);
- min_timeo = ns_to_ktime((1000000000 / HZ) * 4);
- if (ktime_before(timeout, min_timeo))
- timeout = min_timeo;
+ rto_j = call->peer->rto_j;
now = ktime_get_real();
- max_age = ktime_sub(now, timeout);
+ max_age = ktime_sub(now, jiffies_to_usecs(rto_j));
spin_lock_bh(&call->lock);
@@ -219,7 +213,7 @@
}
resend_at = nsecs_to_jiffies(ktime_to_ns(ktime_sub(now, oldest)));
- resend_at += jiffies + rxrpc_resend_timeout;
+ resend_at += jiffies + rto_j;
WRITE_ONCE(call->resend_at, resend_at);
if (unacked)
@@ -234,7 +228,7 @@
rxrpc_timer_set_for_resend);
spin_unlock_bh(&call->lock);
ack_ts = ktime_sub(now, call->acks_latest_ts);
- if (ktime_to_ns(ack_ts) < call->peer->rtt)
+ if (ktime_to_us(ack_ts) < (call->peer->srtt_us >> 3))
goto out;
rxrpc_propose_ACK(call, RXRPC_ACK_PING, 0, true, false,
rxrpc_propose_ack_ping_for_lost_ack);
@@ -254,7 +248,18 @@
if (anno_type != RXRPC_TX_ANNO_RETRANS)
continue;
+ /* We need to reset the retransmission state, but we need to do
+ * so before we drop the lock as a new ACK/NAK may come in and
+ * confuse things
+ */
+ annotation &= ~RXRPC_TX_ANNO_MASK;
+ annotation |= RXRPC_TX_ANNO_UNACK | RXRPC_TX_ANNO_RESENT;
+ call->rxtx_annotations[ix] = annotation;
+
skb = call->rxtx_buffer[ix];
+ if (!skb)
+ continue;
+
rxrpc_get_skb(skb, rxrpc_skb_got);
spin_unlock_bh(&call->lock);
@@ -268,24 +273,6 @@
rxrpc_free_skb(skb, rxrpc_skb_freed);
spin_lock_bh(&call->lock);
-
- /* We need to clear the retransmit state, but there are two
- * things we need to be aware of: A new ACK/NAK might have been
- * received and the packet might have been hard-ACK'd (in which
- * case it will no longer be in the buffer).
- */
- if (after(seq, call->tx_hard_ack)) {
- annotation = call->rxtx_annotations[ix];
- anno_type = annotation & RXRPC_TX_ANNO_MASK;
- if (anno_type == RXRPC_TX_ANNO_RETRANS ||
- anno_type == RXRPC_TX_ANNO_NAK) {
- annotation &= ~RXRPC_TX_ANNO_MASK;
- annotation |= RXRPC_TX_ANNO_UNACK;
- }
- annotation |= RXRPC_TX_ANNO_RESENT;
- call->rxtx_annotations[ix] = annotation;
- }
-
if (after(call->tx_hard_ack, seq))
seq = call->tx_hard_ack;
}
diff --git a/net/rxrpc/call_object.c b/net/rxrpc/call_object.c
index a31c18c..f8233bc 100644
--- a/net/rxrpc/call_object.c
+++ b/net/rxrpc/call_object.c
@@ -237,8 +237,7 @@
return call;
}
- if (p->intr)
- __set_bit(RXRPC_CALL_IS_INTR, &call->flags);
+ call->interruptibility = p->interruptibility;
call->tx_total_len = p->tx_total_len;
trace_rxrpc_call(call->debug_id, rxrpc_call_new_client,
atomic_read(&call->usage),
@@ -289,7 +288,7 @@
*/
ret = rxrpc_connect_call(rx, call, cp, srx, gfp);
if (ret < 0)
- goto error;
+ goto error_attached_to_socket;
trace_rxrpc_call(call->debug_id, rxrpc_call_connected,
atomic_read(&call->usage), here, NULL);
@@ -309,18 +308,29 @@
error_dup_user_ID:
write_unlock(&rx->call_lock);
release_sock(&rx->sk);
- ret = -EEXIST;
-
-error:
__rxrpc_set_call_completion(call, RXRPC_CALL_LOCAL_ERROR,
- RX_CALL_DEAD, ret);
+ RX_CALL_DEAD, -EEXIST);
trace_rxrpc_call(call->debug_id, rxrpc_call_error,
- atomic_read(&call->usage), here, ERR_PTR(ret));
+ atomic_read(&call->usage), here, ERR_PTR(-EEXIST));
rxrpc_release_call(rx, call);
mutex_unlock(&call->user_mutex);
rxrpc_put_call(call, rxrpc_call_put);
- _leave(" = %d", ret);
- return ERR_PTR(ret);
+ _leave(" = -EEXIST");
+ return ERR_PTR(-EEXIST);
+
+ /* We got an error, but the call is attached to the socket and is in
+ * need of release. However, we might now race with recvmsg() when
+ * completing the call queues it. Return 0 from sys_sendmsg() and
+ * leave the error to recvmsg() to deal with.
+ */
+error_attached_to_socket:
+ trace_rxrpc_call(call->debug_id, rxrpc_call_error,
+ atomic_read(&call->usage), here, ERR_PTR(ret));
+ set_bit(RXRPC_CALL_DISCONNECTED, &call->flags);
+ __rxrpc_set_call_completion(call, RXRPC_CALL_LOCAL_ERROR,
+ RX_CALL_DEAD, ret);
+ _leave(" = c=%08x [err]", call->debug_id);
+ return call;
}
/*
@@ -493,12 +503,10 @@
_debug("RELEASE CALL %p (%d CONN %p)", call, call->debug_id, conn);
- if (conn)
+ if (conn && !test_bit(RXRPC_CALL_DISCONNECTED, &call->flags))
rxrpc_disconnect_call(call);
if (call->security)
call->security->free_call_crypto(call);
-
- rxrpc_cleanup_ring(call);
_leave("");
}
@@ -562,13 +570,14 @@
}
/*
- * Final call destruction under RCU.
+ * Final call destruction - but must be done in process context.
*/
-static void rxrpc_rcu_destroy_call(struct rcu_head *rcu)
+static void rxrpc_destroy_call(struct work_struct *work)
{
- struct rxrpc_call *call = container_of(rcu, struct rxrpc_call, rcu);
+ struct rxrpc_call *call = container_of(work, struct rxrpc_call, processor);
struct rxrpc_net *rxnet = call->rxnet;
+ rxrpc_put_connection(call->conn);
rxrpc_put_peer(call->peer);
kfree(call->rxtx_buffer);
kfree(call->rxtx_annotations);
@@ -578,6 +587,22 @@
}
/*
+ * Final call destruction under RCU.
+ */
+static void rxrpc_rcu_destroy_call(struct rcu_head *rcu)
+{
+ struct rxrpc_call *call = container_of(rcu, struct rxrpc_call, rcu);
+
+ if (in_softirq()) {
+ INIT_WORK(&call->processor, rxrpc_destroy_call);
+ if (!rxrpc_queue_work(&call->processor))
+ BUG();
+ } else {
+ rxrpc_destroy_call(&call->processor);
+ }
+}
+
+/*
* clean up a call
*/
void rxrpc_cleanup_call(struct rxrpc_call *call)
@@ -590,7 +615,6 @@
ASSERTCMP(call->state, ==, RXRPC_CALL_COMPLETE);
ASSERT(test_bit(RXRPC_CALL_RELEASED, &call->flags));
- ASSERTCMP(call->conn, ==, NULL);
rxrpc_cleanup_ring(call);
rxrpc_free_skb(call->tx_pending, rxrpc_skb_cleaned);
diff --git a/net/rxrpc/conn_client.c b/net/rxrpc/conn_client.c
index 376370c..f2a1a5d 100644
--- a/net/rxrpc/conn_client.c
+++ b/net/rxrpc/conn_client.c
@@ -655,13 +655,20 @@
add_wait_queue_exclusive(&call->waitq, &myself);
for (;;) {
- if (test_bit(RXRPC_CALL_IS_INTR, &call->flags))
+ switch (call->interruptibility) {
+ case RXRPC_INTERRUPTIBLE:
+ case RXRPC_PREINTERRUPTIBLE:
set_current_state(TASK_INTERRUPTIBLE);
- else
+ break;
+ case RXRPC_UNINTERRUPTIBLE:
+ default:
set_current_state(TASK_UNINTERRUPTIBLE);
+ break;
+ }
if (call->call_id)
break;
- if (test_bit(RXRPC_CALL_IS_INTR, &call->flags) &&
+ if ((call->interruptibility == RXRPC_INTERRUPTIBLE ||
+ call->interruptibility == RXRPC_PREINTERRUPTIBLE) &&
signal_pending(current)) {
ret = -ERESTARTSYS;
break;
@@ -785,6 +792,7 @@
u32 cid;
spin_lock(&conn->channel_lock);
+ set_bit(RXRPC_CALL_DISCONNECTED, &call->flags);
cid = call->cid;
if (cid) {
@@ -792,7 +800,6 @@
chan = &conn->channels[channel];
}
trace_rxrpc_client(conn, channel, rxrpc_client_chan_disconnect);
- call->conn = NULL;
/* Calls that have never actually been assigned a channel can simply be
* discarded. If the conn didn't get used either, it will follow
@@ -908,7 +915,6 @@
spin_unlock(&rxnet->client_conn_cache_lock);
out_2:
spin_unlock(&conn->channel_lock);
- rxrpc_put_connection(conn);
_leave("");
return;
diff --git a/net/rxrpc/conn_event.c b/net/rxrpc/conn_event.c
index a1ceef4..b586468 100644
--- a/net/rxrpc/conn_event.c
+++ b/net/rxrpc/conn_event.c
@@ -341,18 +341,18 @@
return ret;
spin_lock(&conn->channel_lock);
- spin_lock(&conn->state_lock);
+ spin_lock_bh(&conn->state_lock);
if (conn->state == RXRPC_CONN_SERVICE_CHALLENGING) {
conn->state = RXRPC_CONN_SERVICE;
- spin_unlock(&conn->state_lock);
+ spin_unlock_bh(&conn->state_lock);
for (loop = 0; loop < RXRPC_MAXCALLS; loop++)
rxrpc_call_is_secure(
rcu_dereference_protected(
conn->channels[loop].call,
lockdep_is_held(&conn->channel_lock)));
} else {
- spin_unlock(&conn->state_lock);
+ spin_unlock_bh(&conn->state_lock);
}
spin_unlock(&conn->channel_lock);
@@ -376,21 +376,7 @@
_enter("{%d}", conn->debug_id);
ASSERT(conn->security_ix != 0);
-
- if (!conn->params.key) {
- _debug("set up security");
- ret = rxrpc_init_server_conn_security(conn);
- switch (ret) {
- case 0:
- break;
- case -ENOENT:
- abort_code = RX_CALL_DEAD;
- goto abort;
- default:
- abort_code = RXKADNOAUTH;
- goto abort;
- }
- }
+ ASSERT(conn->server_key);
if (conn->security->issue_challenge(conn) < 0) {
abort_code = RX_CALL_DEAD;
@@ -452,16 +438,12 @@
/*
* connection-level event processor
*/
-void rxrpc_process_connection(struct work_struct *work)
+static void rxrpc_do_process_connection(struct rxrpc_connection *conn)
{
- struct rxrpc_connection *conn =
- container_of(work, struct rxrpc_connection, processor);
struct sk_buff *skb;
u32 abort_code = RX_PROTOCOL_ERROR;
int ret;
- rxrpc_see_connection(conn);
-
if (test_and_clear_bit(RXRPC_CONN_EV_CHALLENGE, &conn->events))
rxrpc_secure_connection(conn);
@@ -489,18 +471,32 @@
}
}
-out:
- rxrpc_put_connection(conn);
- _leave("");
return;
requeue_and_leave:
skb_queue_head(&conn->rx_queue, skb);
- goto out;
+ return;
protocol_error:
if (rxrpc_abort_connection(conn, ret, abort_code) < 0)
goto requeue_and_leave;
rxrpc_free_skb(skb, rxrpc_skb_freed);
- goto out;
+ return;
+}
+
+void rxrpc_process_connection(struct work_struct *work)
+{
+ struct rxrpc_connection *conn =
+ container_of(work, struct rxrpc_connection, processor);
+
+ rxrpc_see_connection(conn);
+
+ if (__rxrpc_use_local(conn->params.local)) {
+ rxrpc_do_process_connection(conn);
+ rxrpc_unuse_local(conn->params.local);
+ }
+
+ rxrpc_put_connection(conn);
+ _leave("");
+ return;
}
diff --git a/net/rxrpc/conn_object.c b/net/rxrpc/conn_object.c
index 38d718e..8cbe0bf 100644
--- a/net/rxrpc/conn_object.c
+++ b/net/rxrpc/conn_object.c
@@ -212,9 +212,11 @@
call->peer->cong_cwnd = call->cong_cwnd;
- spin_lock_bh(&conn->params.peer->lock);
- hlist_del_rcu(&call->error_link);
- spin_unlock_bh(&conn->params.peer->lock);
+ if (!hlist_unhashed(&call->error_link)) {
+ spin_lock_bh(&call->peer->lock);
+ hlist_del_rcu(&call->error_link);
+ spin_unlock_bh(&call->peer->lock);
+ }
if (rxrpc_is_client_call(call))
return rxrpc_disconnect_client_call(call);
@@ -223,9 +225,8 @@
__rxrpc_disconnect_call(conn, call);
spin_unlock(&conn->channel_lock);
- call->conn = NULL;
+ set_bit(RXRPC_CALL_DISCONNECTED, &call->flags);
conn->idle_timestamp = jiffies;
- rxrpc_put_connection(conn);
}
/*
diff --git a/net/rxrpc/conn_service.c b/net/rxrpc/conn_service.c
index 123d6ce..21da48e 100644
--- a/net/rxrpc/conn_service.c
+++ b/net/rxrpc/conn_service.c
@@ -148,6 +148,8 @@
*/
void rxrpc_new_incoming_connection(struct rxrpc_sock *rx,
struct rxrpc_connection *conn,
+ const struct rxrpc_security *sec,
+ struct key *key,
struct sk_buff *skb)
{
struct rxrpc_skb_priv *sp = rxrpc_skb(skb);
@@ -160,6 +162,8 @@
conn->service_id = sp->hdr.serviceId;
conn->security_ix = sp->hdr.securityIndex;
conn->out_clientflag = 0;
+ conn->security = sec;
+ conn->server_key = key_get(key);
if (conn->security_ix)
conn->state = RXRPC_CONN_SERVICE_UNSECURED;
else
diff --git a/net/rxrpc/input.c b/net/rxrpc/input.c
index 157be1f..916d1f4 100644
--- a/net/rxrpc/input.c
+++ b/net/rxrpc/input.c
@@ -91,11 +91,11 @@
/* We analyse the number of packets that get ACK'd per RTT
* period and increase the window if we managed to fill it.
*/
- if (call->peer->rtt_usage == 0)
+ if (call->peer->rtt_count == 0)
goto out;
if (ktime_before(skb->tstamp,
- ktime_add_ns(call->cong_tstamp,
- call->peer->rtt)))
+ ktime_add_us(call->cong_tstamp,
+ call->peer->srtt_us >> 3)))
goto out_no_clear_ca;
change = rxrpc_cong_rtt_window_end;
call->cong_tstamp = skb->tstamp;
@@ -193,22 +193,6 @@
}
/*
- * Ping the other end to fill our RTT cache and to retrieve the rwind
- * and MTU parameters.
- */
-static void rxrpc_send_ping(struct rxrpc_call *call, struct sk_buff *skb)
-{
- struct rxrpc_skb_priv *sp = rxrpc_skb(skb);
- ktime_t now = skb->tstamp;
-
- if (call->peer->rtt_usage < 3 ||
- ktime_before(ktime_add_ms(call->peer->rtt_last_req, 1000), now))
- rxrpc_propose_ACK(call, RXRPC_ACK_PING, sp->hdr.serial,
- true, true,
- rxrpc_propose_ack_ping_for_params);
-}
-
-/*
* Apply a hard ACK by advancing the Tx window.
*/
static bool rxrpc_rotate_tx_window(struct rxrpc_call *call, rxrpc_seq_t to,
@@ -429,7 +413,7 @@
{
struct rxrpc_skb_priv *sp = rxrpc_skb(skb);
enum rxrpc_call_state state;
- unsigned int j;
+ unsigned int j, nr_subpackets;
rxrpc_serial_t serial = sp->hdr.serial, ack_serial = 0;
rxrpc_seq_t seq0 = sp->hdr.seq, hard_ack;
bool immediate_ack = false, jumbo_bad = false;
@@ -447,7 +431,7 @@
return;
}
- if (call->state == RXRPC_CALL_SERVER_RECV_REQUEST) {
+ if (state == RXRPC_CALL_SERVER_RECV_REQUEST) {
unsigned long timo = READ_ONCE(call->next_req_timo);
unsigned long now, expect_req_by;
@@ -473,7 +457,8 @@
call->ackr_prev_seq = seq0;
hard_ack = READ_ONCE(call->rx_hard_ack);
- if (sp->nr_subpackets > 1) {
+ nr_subpackets = sp->nr_subpackets;
+ if (nr_subpackets > 1) {
if (call->nr_jumbo_bad > 3) {
ack = RXRPC_ACK_NOSPACE;
ack_serial = serial;
@@ -481,11 +466,11 @@
}
}
- for (j = 0; j < sp->nr_subpackets; j++) {
+ for (j = 0; j < nr_subpackets; j++) {
rxrpc_serial_t serial = sp->hdr.serial + j;
rxrpc_seq_t seq = seq0 + j;
unsigned int ix = seq & RXRPC_RXTX_BUFF_MASK;
- bool terminal = (j == sp->nr_subpackets - 1);
+ bool terminal = (j == nr_subpackets - 1);
bool last = terminal && (sp->rx_flags & RXRPC_SKB_INCL_LAST);
u8 flags, annotation = j;
@@ -522,7 +507,7 @@
}
if (call->rxtx_buffer[ix]) {
- rxrpc_input_dup_data(call, seq, sp->nr_subpackets > 1,
+ rxrpc_input_dup_data(call, seq, nr_subpackets > 1,
&jumbo_bad);
if (ack != RXRPC_ACK_DUPLICATE) {
ack = RXRPC_ACK_DUPLICATE;
@@ -580,6 +565,7 @@
* ring.
*/
skb = NULL;
+ sp = NULL;
}
if (last) {
@@ -613,10 +599,8 @@
false, true,
rxrpc_propose_ack_input_data);
- if (seq0 == READ_ONCE(call->rx_hard_ack) + 1) {
- trace_rxrpc_notify_socket(call->debug_id, serial);
- rxrpc_notify_socket(call);
- }
+ trace_rxrpc_notify_socket(call->debug_id, serial);
+ rxrpc_notify_socket(call);
unlock:
spin_unlock(&call->input_lock);
@@ -739,13 +723,12 @@
ntohl(ackinfo->rxMTU), ntohl(ackinfo->maxMTU),
rwind, ntohl(ackinfo->jumbo_max));
+ if (rwind > RXRPC_RXTX_BUFF_SIZE - 1)
+ rwind = RXRPC_RXTX_BUFF_SIZE - 1;
if (call->tx_winsize != rwind) {
- if (rwind > RXRPC_RXTX_BUFF_SIZE - 1)
- rwind = RXRPC_RXTX_BUFF_SIZE - 1;
if (rwind > call->tx_winsize)
wake = true;
- trace_rxrpc_rx_rwind_change(call, sp->hdr.serial,
- ntohl(ackinfo->rwind), wake);
+ trace_rxrpc_rx_rwind_change(call, sp->hdr.serial, rwind, wake);
call->tx_winsize = rwind;
}
@@ -819,6 +802,30 @@
}
/*
+ * Return true if the ACK is valid - ie. it doesn't appear to have regressed
+ * with respect to the ack state conveyed by preceding ACKs.
+ */
+static bool rxrpc_is_ack_valid(struct rxrpc_call *call,
+ rxrpc_seq_t first_pkt, rxrpc_seq_t prev_pkt)
+{
+ rxrpc_seq_t base = READ_ONCE(call->ackr_first_seq);
+
+ if (after(first_pkt, base))
+ return true; /* The window advanced */
+
+ if (before(first_pkt, base))
+ return false; /* firstPacket regressed */
+
+ if (after_eq(prev_pkt, call->ackr_prev_seq))
+ return true; /* previousPacket hasn't regressed. */
+
+ /* Some rx implementations put a serial number in previousPacket. */
+ if (after_eq(prev_pkt, base + call->tx_winsize))
+ return false;
+ return true;
+}
+
+/*
* Process an ACK packet.
*
* ack.firstPacket is the sequence number of the first soft-ACK'd/NAK'd packet
@@ -837,7 +844,7 @@
struct rxrpc_ackinfo info;
u8 acks[RXRPC_MAXACKS];
} buf;
- rxrpc_serial_t acked_serial;
+ rxrpc_serial_t ack_serial, acked_serial;
rxrpc_seq_t first_soft_ack, hard_ack, prev_pkt;
int nr_acks, offset, ioffset;
@@ -850,6 +857,7 @@
}
offset += sizeof(buf.ack);
+ ack_serial = sp->hdr.serial;
acked_serial = ntohl(buf.ack.serial);
first_soft_ack = ntohl(buf.ack.firstPacket);
prev_pkt = ntohl(buf.ack.previousPacket);
@@ -858,32 +866,35 @@
summary.ack_reason = (buf.ack.reason < RXRPC_ACK__INVALID ?
buf.ack.reason : RXRPC_ACK__INVALID);
- trace_rxrpc_rx_ack(call, sp->hdr.serial, acked_serial,
+ trace_rxrpc_rx_ack(call, ack_serial, acked_serial,
first_soft_ack, prev_pkt,
summary.ack_reason, nr_acks);
if (buf.ack.reason == RXRPC_ACK_PING_RESPONSE)
rxrpc_input_ping_response(call, skb->tstamp, acked_serial,
- sp->hdr.serial);
+ ack_serial);
if (buf.ack.reason == RXRPC_ACK_REQUESTED)
rxrpc_input_requested_ack(call, skb->tstamp, acked_serial,
- sp->hdr.serial);
+ ack_serial);
if (buf.ack.reason == RXRPC_ACK_PING) {
- _proto("Rx ACK %%%u PING Request", sp->hdr.serial);
+ _proto("Rx ACK %%%u PING Request", ack_serial);
rxrpc_propose_ACK(call, RXRPC_ACK_PING_RESPONSE,
- sp->hdr.serial, true, true,
+ ack_serial, true, true,
rxrpc_propose_ack_respond_to_ping);
} else if (sp->hdr.flags & RXRPC_REQUEST_ACK) {
rxrpc_propose_ACK(call, RXRPC_ACK_REQUESTED,
- sp->hdr.serial, true, true,
+ ack_serial, true, true,
rxrpc_propose_ack_respond_to_ack);
}
/* Discard any out-of-order or duplicate ACKs (outside lock). */
- if (before(first_soft_ack, call->ackr_first_seq) ||
- before(prev_pkt, call->ackr_prev_seq))
+ if (!rxrpc_is_ack_valid(call, first_soft_ack, prev_pkt)) {
+ trace_rxrpc_rx_discard_ack(call->debug_id, ack_serial,
+ first_soft_ack, call->ackr_first_seq,
+ prev_pkt, call->ackr_prev_seq);
return;
+ }
buf.info.rxMTU = 0;
ioffset = offset + nr_acks + 3;
@@ -894,11 +905,13 @@
spin_lock(&call->input_lock);
/* Discard any out-of-order or duplicate ACKs (inside lock). */
- if (before(first_soft_ack, call->ackr_first_seq) ||
- before(prev_pkt, call->ackr_prev_seq))
+ if (!rxrpc_is_ack_valid(call, first_soft_ack, prev_pkt)) {
+ trace_rxrpc_rx_discard_ack(call->debug_id, ack_serial,
+ first_soft_ack, call->ackr_first_seq,
+ prev_pkt, call->ackr_prev_seq);
goto out;
+ }
call->acks_latest_ts = skb->tstamp;
- call->acks_latest = sp->hdr.serial;
call->ackr_first_seq = first_soft_ack;
call->ackr_prev_seq = prev_pkt;
@@ -953,7 +966,7 @@
RXRPC_TX_ANNO_LAST &&
summary.nr_acks == call->tx_top - hard_ack &&
rxrpc_is_client_call(call))
- rxrpc_propose_ACK(call, RXRPC_ACK_PING, sp->hdr.serial,
+ rxrpc_propose_ACK(call, RXRPC_ACK_PING, ack_serial,
false, true,
rxrpc_propose_ack_ping_for_lost_reply);
@@ -1396,8 +1409,6 @@
call = rxrpc_new_incoming_call(local, rx, skb);
if (!call)
goto reject_packet;
- rxrpc_send_ping(call, skb);
- mutex_unlock(&call->user_mutex);
}
/* Process a call packet; this either discards or passes on the ref
diff --git a/net/rxrpc/key.c b/net/rxrpc/key.c
index 6c3f35f..2b26c4d 100644
--- a/net/rxrpc/key.c
+++ b/net/rxrpc/key.c
@@ -31,7 +31,7 @@
static void rxrpc_destroy(struct key *);
static void rxrpc_destroy_s(struct key *);
static void rxrpc_describe(const struct key *, struct seq_file *);
-static long rxrpc_read(const struct key *, char __user *, size_t);
+static long rxrpc_read(const struct key *, char *, size_t);
/*
* rxrpc defined keys take an arbitrary string as the description and an
@@ -903,7 +903,7 @@
_enter("");
- if (optlen <= 0 || optlen > PAGE_SIZE - 1)
+ if (optlen <= 0 || optlen > PAGE_SIZE - 1 || rx->securities)
return -EINVAL;
description = memdup_user_nul(optval, optlen);
@@ -941,7 +941,7 @@
if (IS_ERR(description))
return PTR_ERR(description);
- key = request_key_net(&key_type_keyring, description, sock_net(&rx->sk), NULL);
+ key = request_key(&key_type_keyring, description, NULL);
if (IS_ERR(key)) {
kfree(description);
_leave(" = %ld", PTR_ERR(key));
@@ -1042,12 +1042,12 @@
* - this returns the result in XDR form
*/
static long rxrpc_read(const struct key *key,
- char __user *buffer, size_t buflen)
+ char *buffer, size_t buflen)
{
const struct rxrpc_key_token *token;
const struct krb5_principal *princ;
size_t size;
- __be32 __user *xdr, *oldxdr;
+ __be32 *xdr, *oldxdr;
u32 cnlen, toksize, ntoks, tok, zero;
u16 toksizes[AFSTOKEN_MAX];
int loop;
@@ -1073,7 +1073,7 @@
switch (token->security_index) {
case RXRPC_SECURITY_RXKAD:
- toksize += 9 * 4; /* viceid, kvno, key*2 + len, begin,
+ toksize += 8 * 4; /* viceid, kvno, key*2, begin,
* end, primary, tktlen */
toksize += RND(token->kad->ticket_len);
break;
@@ -1108,8 +1108,9 @@
break;
default: /* we have a ticket we can't encode */
- BUG();
- continue;
+ pr_err("Unsupported key token type (%u)\n",
+ token->security_index);
+ return -ENOPKG;
}
_debug("token[%u]: toksize=%u", ntoks, toksize);
@@ -1124,30 +1125,33 @@
if (!buffer || buflen < size)
return size;
- xdr = (__be32 __user *) buffer;
+ xdr = (__be32 *)buffer;
zero = 0;
#define ENCODE(x) \
do { \
- __be32 y = htonl(x); \
- if (put_user(y, xdr++) < 0) \
- goto fault; \
+ *xdr++ = htonl(x); \
} while(0)
#define ENCODE_DATA(l, s) \
do { \
u32 _l = (l); \
ENCODE(l); \
- if (copy_to_user(xdr, (s), _l) != 0) \
- goto fault; \
- if (_l & 3 && \
- copy_to_user((u8 __user *)xdr + _l, &zero, 4 - (_l & 3)) != 0) \
- goto fault; \
+ memcpy(xdr, (s), _l); \
+ if (_l & 3) \
+ memcpy((u8 *)xdr + _l, &zero, 4 - (_l & 3)); \
+ xdr += (_l + 3) >> 2; \
+ } while(0)
+#define ENCODE_BYTES(l, s) \
+ do { \
+ u32 _l = (l); \
+ memcpy(xdr, (s), _l); \
+ if (_l & 3) \
+ memcpy((u8 *)xdr + _l, &zero, 4 - (_l & 3)); \
xdr += (_l + 3) >> 2; \
} while(0)
#define ENCODE64(x) \
do { \
__be64 y = cpu_to_be64(x); \
- if (copy_to_user(xdr, &y, 8) != 0) \
- goto fault; \
+ memcpy(xdr, &y, 8); \
xdr += 8 >> 2; \
} while(0)
#define ENCODE_STR(s) \
@@ -1171,7 +1175,7 @@
case RXRPC_SECURITY_RXKAD:
ENCODE(token->kad->vice_id);
ENCODE(token->kad->kvno);
- ENCODE_DATA(8, token->kad->session_key);
+ ENCODE_BYTES(8, token->kad->session_key);
ENCODE(token->kad->start);
ENCODE(token->kad->expiry);
ENCODE(token->kad->primary_flag);
@@ -1221,8 +1225,9 @@
break;
default:
- BUG();
- break;
+ pr_err("Unsupported key token type (%u)\n",
+ token->security_index);
+ return -ENOPKG;
}
ASSERTCMP((unsigned long)xdr - (unsigned long)oldxdr, ==,
@@ -1238,8 +1243,4 @@
ASSERTCMP((char __user *) xdr - buffer, ==, size);
_leave(" = %zu", size);
return size;
-
-fault:
- _leave(" = -EFAULT");
- return -EFAULT;
}
diff --git a/net/rxrpc/local_object.c b/net/rxrpc/local_object.c
index 3658726..01135e5 100644
--- a/net/rxrpc/local_object.c
+++ b/net/rxrpc/local_object.c
@@ -165,15 +165,6 @@
goto error;
}
- /* we want to set the don't fragment bit */
- 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;
- }
-
/* Fall through and set IPv4 options too otherwise we don't get
* errors from IPv4 packets sent through the IPv6 socket.
*/
@@ -364,11 +355,14 @@
void rxrpc_put_local(struct rxrpc_local *local)
{
const void *here = __builtin_return_address(0);
+ unsigned int debug_id;
int n;
if (local) {
+ debug_id = local->debug_id;
+
n = atomic_dec_return(&local->usage);
- trace_rxrpc_local(local->debug_id, rxrpc_local_put, n, here);
+ trace_rxrpc_local(debug_id, rxrpc_local_put, n, here);
if (n == 0)
call_rcu(&local->rcu, rxrpc_local_rcu);
@@ -380,14 +374,11 @@
*/
struct rxrpc_local *rxrpc_use_local(struct rxrpc_local *local)
{
- unsigned int au;
-
local = rxrpc_get_local_maybe(local);
if (!local)
return NULL;
- au = atomic_fetch_add_unless(&local->active_users, 1, 0);
- if (au == 0) {
+ if (!__rxrpc_use_local(local)) {
rxrpc_put_local(local);
return NULL;
}
@@ -401,14 +392,11 @@
*/
void rxrpc_unuse_local(struct rxrpc_local *local)
{
- unsigned int au;
-
if (local) {
- au = atomic_dec_return(&local->active_users);
- if (au == 0)
+ if (__rxrpc_unuse_local(local)) {
+ rxrpc_get_local(local);
rxrpc_queue_local(local);
- else
- rxrpc_put_local(local);
+ }
}
}
@@ -465,7 +453,7 @@
do {
again = false;
- if (atomic_read(&local->active_users) == 0) {
+ if (!__rxrpc_use_local(local)) {
rxrpc_local_destroyer(local);
break;
}
@@ -479,6 +467,8 @@
rxrpc_process_local_events(local);
again = true;
}
+
+ __rxrpc_unuse_local(local);
} while (again);
rxrpc_put_local(local);
diff --git a/net/rxrpc/misc.c b/net/rxrpc/misc.c
index 214405f..d4144fd 100644
--- a/net/rxrpc/misc.c
+++ b/net/rxrpc/misc.c
@@ -63,11 +63,6 @@
*/
unsigned int rxrpc_rx_jumbo_max = 4;
-/*
- * Time till packet resend (in milliseconds).
- */
-unsigned long rxrpc_resend_timeout = 4 * HZ;
-
const s8 rxrpc_ack_priority[] = {
[0] = 0,
[RXRPC_ACK_DELAY] = 1,
diff --git a/net/rxrpc/output.c b/net/rxrpc/output.c
index 935bb60..f8b632a 100644
--- a/net/rxrpc/output.c
+++ b/net/rxrpc/output.c
@@ -129,7 +129,7 @@
int rxrpc_send_ack_packet(struct rxrpc_call *call, bool ping,
rxrpc_serial_t *_serial)
{
- struct rxrpc_connection *conn = NULL;
+ struct rxrpc_connection *conn;
struct rxrpc_ack_buffer *pkt;
struct msghdr msg;
struct kvec iov[2];
@@ -139,18 +139,14 @@
int ret;
u8 reason;
- spin_lock_bh(&call->lock);
- if (call->conn)
- conn = rxrpc_get_connection_maybe(call->conn);
- spin_unlock_bh(&call->lock);
- if (!conn)
+ if (test_bit(RXRPC_CALL_DISCONNECTED, &call->flags))
return -ECONNRESET;
pkt = kzalloc(sizeof(*pkt), GFP_KERNEL);
- if (!pkt) {
- rxrpc_put_connection(conn);
+ if (!pkt)
return -ENOMEM;
- }
+
+ conn = call->conn;
msg.msg_name = &call->peer->srx.transport;
msg.msg_namelen = call->peer->srx.transport_len;
@@ -244,7 +240,6 @@
}
out:
- rxrpc_put_connection(conn);
kfree(pkt);
return ret;
}
@@ -254,7 +249,7 @@
*/
int rxrpc_send_abort_packet(struct rxrpc_call *call)
{
- struct rxrpc_connection *conn = NULL;
+ struct rxrpc_connection *conn;
struct rxrpc_abort_buffer pkt;
struct msghdr msg;
struct kvec iov[1];
@@ -271,13 +266,11 @@
test_bit(RXRPC_CALL_TX_LAST, &call->flags))
return 0;
- spin_lock_bh(&call->lock);
- if (call->conn)
- conn = rxrpc_get_connection_maybe(call->conn);
- spin_unlock_bh(&call->lock);
- if (!conn)
+ if (test_bit(RXRPC_CALL_DISCONNECTED, &call->flags))
return -ECONNRESET;
+ conn = call->conn;
+
msg.msg_name = &call->peer->srx.transport;
msg.msg_namelen = call->peer->srx.transport_len;
msg.msg_control = NULL;
@@ -312,8 +305,6 @@
trace_rxrpc_tx_packet(call->debug_id, &pkt.whdr,
rxrpc_tx_point_call_abort);
rxrpc_tx_backoff(call, ret);
-
- rxrpc_put_connection(conn);
return ret;
}
@@ -378,7 +369,7 @@
(test_and_clear_bit(RXRPC_CALL_EV_ACK_LOST, &call->events) ||
retrans ||
call->cong_mode == RXRPC_CALL_SLOW_START ||
- (call->peer->rtt_usage < 3 && sp->hdr.seq & 1) ||
+ (call->peer->rtt_count < 3 && sp->hdr.seq & 1) ||
ktime_before(ktime_add_ms(call->peer->rtt_last_req, 1000),
ktime_get_real())))
whdr.flags |= RXRPC_REQUEST_ACK;
@@ -432,13 +423,10 @@
if (whdr.flags & RXRPC_REQUEST_ACK) {
call->peer->rtt_last_req = skb->tstamp;
trace_rxrpc_rtt_tx(call, rxrpc_rtt_tx_data, serial);
- if (call->peer->rtt_usage > 1) {
+ if (call->peer->rtt_count > 1) {
unsigned long nowj = jiffies, ack_lost_at;
- ack_lost_at = nsecs_to_jiffies(2 * call->peer->rtt);
- if (ack_lost_at < 1)
- ack_lost_at = 1;
-
+ ack_lost_at = rxrpc_get_rto_backoff(call->peer, retrans);
ack_lost_at += nowj;
WRITE_ONCE(call->ack_lost_at, ack_lost_at);
rxrpc_reduce_call_timer(call, ack_lost_at, nowj,
@@ -483,42 +471,22 @@
skb->tstamp = ktime_get_real();
switch (conn->params.local->srx.transport.family) {
+ case AF_INET6:
case AF_INET:
opt = IP_PMTUDISC_DONT;
- ret = kernel_setsockopt(conn->params.local->socket,
- SOL_IP, IP_MTU_DISCOVER,
- (char *)&opt, sizeof(opt));
- if (ret == 0) {
- ret = kernel_sendmsg(conn->params.local->socket, &msg,
- iov, 2, len);
- conn->params.peer->last_tx_at = ktime_get_seconds();
+ kernel_setsockopt(conn->params.local->socket,
+ SOL_IP, IP_MTU_DISCOVER,
+ (char *)&opt, sizeof(opt));
+ ret = kernel_sendmsg(conn->params.local->socket, &msg,
+ iov, 2, len);
+ conn->params.peer->last_tx_at = ktime_get_seconds();
- opt = IP_PMTUDISC_DO;
- kernel_setsockopt(conn->params.local->socket, SOL_IP,
- IP_MTU_DISCOVER,
- (char *)&opt, sizeof(opt));
- }
+ opt = IP_PMTUDISC_DO;
+ kernel_setsockopt(conn->params.local->socket,
+ SOL_IP, IP_MTU_DISCOVER,
+ (char *)&opt, sizeof(opt));
break;
-#ifdef CONFIG_AF_RXRPC_IPV6
- case AF_INET6:
- opt = IPV6_PMTUDISC_DONT;
- ret = kernel_setsockopt(conn->params.local->socket,
- SOL_IPV6, IPV6_MTU_DISCOVER,
- (char *)&opt, sizeof(opt));
- if (ret == 0) {
- ret = kernel_sendmsg(conn->params.local->socket, &msg,
- iov, 2, len);
- conn->params.peer->last_tx_at = ktime_get_seconds();
-
- opt = IPV6_PMTUDISC_DO;
- kernel_setsockopt(conn->params.local->socket,
- SOL_IPV6, IPV6_MTU_DISCOVER,
- (char *)&opt, sizeof(opt));
- }
- break;
-#endif
-
default:
BUG();
}
diff --git a/net/rxrpc/peer_event.c b/net/rxrpc/peer_event.c
index 48f67a9..b1449d9 100644
--- a/net/rxrpc/peer_event.c
+++ b/net/rxrpc/peer_event.c
@@ -296,52 +296,6 @@
}
/*
- * Add RTT information to cache. This is called in softirq mode and has
- * exclusive access to the peer RTT data.
- */
-void rxrpc_peer_add_rtt(struct rxrpc_call *call, enum rxrpc_rtt_rx_trace why,
- rxrpc_serial_t send_serial, rxrpc_serial_t resp_serial,
- ktime_t send_time, ktime_t resp_time)
-{
- struct rxrpc_peer *peer = call->peer;
- s64 rtt;
- u64 sum = peer->rtt_sum, avg;
- u8 cursor = peer->rtt_cursor, usage = peer->rtt_usage;
-
- rtt = ktime_to_ns(ktime_sub(resp_time, send_time));
- 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;
- peer->rtt_cache[cursor] = rtt;
- peer->rtt_cursor = (cursor + 1) & (RXRPC_RTT_CACHE_SIZE - 1);
- peer->rtt_sum = sum;
- if (usage < RXRPC_RTT_CACHE_SIZE) {
- usage++;
- 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;
- } else {
- avg = sum;
- 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);
-}
-
-/*
* Perform keep-alive pings.
*/
static void rxrpc_peer_keepalive_dispatch(struct rxrpc_net *rxnet,
@@ -364,27 +318,31 @@
if (!rxrpc_get_peer_maybe(peer))
continue;
- spin_unlock_bh(&rxnet->peer_hash_lock);
+ if (__rxrpc_use_local(peer->local)) {
+ spin_unlock_bh(&rxnet->peer_hash_lock);
- keepalive_at = peer->last_tx_at + RXRPC_KEEPALIVE_TIME;
- slot = keepalive_at - base;
- _debug("%02x peer %u t=%d {%pISp}",
- cursor, peer->debug_id, slot, &peer->srx.transport);
+ keepalive_at = peer->last_tx_at + RXRPC_KEEPALIVE_TIME;
+ slot = keepalive_at - base;
+ _debug("%02x peer %u t=%d {%pISp}",
+ cursor, peer->debug_id, slot, &peer->srx.transport);
- if (keepalive_at <= base ||
- keepalive_at > base + RXRPC_KEEPALIVE_TIME) {
- rxrpc_send_keepalive(peer);
- slot = RXRPC_KEEPALIVE_TIME;
+ if (keepalive_at <= base ||
+ keepalive_at > base + RXRPC_KEEPALIVE_TIME) {
+ rxrpc_send_keepalive(peer);
+ slot = RXRPC_KEEPALIVE_TIME;
+ }
+
+ /* A transmission to this peer occurred since last we
+ * examined it so put it into the appropriate future
+ * bucket.
+ */
+ slot += cursor;
+ slot &= mask;
+ spin_lock_bh(&rxnet->peer_hash_lock);
+ list_add_tail(&peer->keepalive_link,
+ &rxnet->peer_keepalive[slot & mask]);
+ rxrpc_unuse_local(peer->local);
}
-
- /* A transmission to this peer occurred since last we examined
- * it so put it into the appropriate future bucket.
- */
- slot += cursor;
- slot &= mask;
- spin_lock_bh(&rxnet->peer_hash_lock);
- list_add_tail(&peer->keepalive_link,
- &rxnet->peer_keepalive[slot & mask]);
rxrpc_put_peer_locked(peer);
}
diff --git a/net/rxrpc/peer_object.c b/net/rxrpc/peer_object.c
index 64830d8..e011594 100644
--- a/net/rxrpc/peer_object.c
+++ b/net/rxrpc/peer_object.c
@@ -224,6 +224,8 @@
spin_lock_init(&peer->rtt_input_lock);
peer->debug_id = atomic_inc_return(&rxrpc_debug_id);
+ rxrpc_peer_init_rtt(peer);
+
if (RXRPC_TX_SMSS > 2190)
peer->cong_cwnd = 2;
else if (RXRPC_TX_SMSS > 1095)
@@ -495,14 +497,24 @@
EXPORT_SYMBOL(rxrpc_kernel_get_peer);
/**
- * rxrpc_kernel_get_rtt - Get a call's peer RTT
+ * rxrpc_kernel_get_srtt - Get a call's peer smoothed RTT
* @sock: The socket on which the call is in progress.
* @call: The call to query
+ * @_srtt: Where to store the SRTT value.
*
- * Get the call's peer RTT.
+ * Get the call's peer smoothed RTT in uS.
*/
-u64 rxrpc_kernel_get_rtt(struct socket *sock, struct rxrpc_call *call)
+bool rxrpc_kernel_get_srtt(struct socket *sock, struct rxrpc_call *call,
+ u32 *_srtt)
{
- return call->peer->rtt;
+ struct rxrpc_peer *peer = call->peer;
+
+ if (peer->rtt_count == 0) {
+ *_srtt = 1000000; /* 1S */
+ return false;
+ }
+
+ *_srtt = call->peer->srtt_us >> 3;
+ return true;
}
-EXPORT_SYMBOL(rxrpc_kernel_get_rtt);
+EXPORT_SYMBOL(rxrpc_kernel_get_srtt);
diff --git a/net/rxrpc/proc.c b/net/rxrpc/proc.c
index b9d053e..543afd9 100644
--- a/net/rxrpc/proc.c
+++ b/net/rxrpc/proc.c
@@ -68,7 +68,7 @@
"Proto Local "
" Remote "
" SvID ConnID CallID End Use State Abort "
- " UserID TxSeq TW RxSeq RW RxSerial RxTimo\n");
+ " DebugId TxSeq TW RxSeq RW RxSerial RxTimo\n");
return 0;
}
@@ -100,7 +100,7 @@
rx_hard_ack = READ_ONCE(call->rx_hard_ack);
seq_printf(seq,
"UDP %-47.47s %-47.47s %4x %08x %08x %s %3u"
- " %-8.8s %08x %lx %08x %02x %08x %02x %08x %06lx\n",
+ " %-8.8s %08x %08x %08x %02x %08x %02x %08x %06lx\n",
lbuff,
rbuff,
call->service_id,
@@ -110,7 +110,7 @@
atomic_read(&call->usage),
rxrpc_call_states[call->state],
call->abort_code,
- call->user_call_ID,
+ call->debug_id,
tx_hard_ack, READ_ONCE(call->tx_top) - tx_hard_ack,
rx_hard_ack, READ_ONCE(call->rx_top) - rx_hard_ack,
call->rx_serial,
@@ -222,7 +222,7 @@
seq_puts(seq,
"Proto Local "
" Remote "
- " Use CW MTU LastUse RTT Rc\n"
+ " Use CW MTU LastUse RTT RTO\n"
);
return 0;
}
@@ -236,15 +236,15 @@
now = ktime_get_seconds();
seq_printf(seq,
"UDP %-47.47s %-47.47s %3u"
- " %3u %5u %6llus %12llu %2u\n",
+ " %3u %5u %6llus %8u %8u\n",
lbuff,
rbuff,
atomic_read(&peer->usage),
peer->cong_cwnd,
peer->mtu,
now - peer->last_tx_at,
- peer->rtt,
- peer->rtt_cursor);
+ peer->srtt_us >> 3,
+ jiffies_to_usecs(peer->rto_j));
return 0;
}
diff --git a/net/rxrpc/recvmsg.c b/net/rxrpc/recvmsg.c
index 8578c39..4f48e3b 100644
--- a/net/rxrpc/recvmsg.c
+++ b/net/rxrpc/recvmsg.c
@@ -464,7 +464,7 @@
list_empty(&rx->recvmsg_q) &&
rx->sk.sk_state != RXRPC_SERVER_LISTENING) {
release_sock(&rx->sk);
- return -ENODATA;
+ return -EAGAIN;
}
if (list_empty(&rx->recvmsg_q)) {
@@ -541,7 +541,7 @@
goto error_unlock_call;
}
- if (msg->msg_name) {
+ if (msg->msg_name && call->peer) {
struct sockaddr_rxrpc *srx = msg->msg_name;
size_t len = sizeof(call->peer->srx);
diff --git a/net/rxrpc/rtt.c b/net/rxrpc/rtt.c
new file mode 100644
index 0000000..928d8b3
--- /dev/null
+++ b/net/rxrpc/rtt.c
@@ -0,0 +1,195 @@
+// SPDX-License-Identifier: GPL-2.0
+/* RTT/RTO calculation.
+ *
+ * Adapted from TCP for AF_RXRPC by David Howells (dhowells@redhat.com)
+ *
+ * https://tools.ietf.org/html/rfc6298
+ * https://tools.ietf.org/html/rfc1122#section-4.2.3.1
+ * http://ccr.sigcomm.org/archive/1995/jan95/ccr-9501-partridge87.pdf
+ */
+
+#include <linux/net.h>
+#include "ar-internal.h"
+
+#define RXRPC_RTO_MAX ((unsigned)(120 * HZ))
+#define RXRPC_TIMEOUT_INIT ((unsigned)(1*HZ)) /* RFC6298 2.1 initial RTO value */
+#define rxrpc_jiffies32 ((u32)jiffies) /* As rxrpc_jiffies32 */
+#define rxrpc_min_rtt_wlen 300 /* As sysctl_tcp_min_rtt_wlen */
+
+static u32 rxrpc_rto_min_us(struct rxrpc_peer *peer)
+{
+ return 200;
+}
+
+static u32 __rxrpc_set_rto(const struct rxrpc_peer *peer)
+{
+ return _usecs_to_jiffies((peer->srtt_us >> 3) + peer->rttvar_us);
+}
+
+static u32 rxrpc_bound_rto(u32 rto)
+{
+ return min(rto, RXRPC_RTO_MAX);
+}
+
+/*
+ * Called to compute a smoothed rtt estimate. The data fed to this
+ * routine either comes from timestamps, or from segments that were
+ * known _not_ to have been retransmitted [see Karn/Partridge
+ * Proceedings SIGCOMM 87]. The algorithm is from the SIGCOMM 88
+ * piece by Van Jacobson.
+ * NOTE: the next three routines used to be one big routine.
+ * To save cycles in the RFC 1323 implementation it was better to break
+ * it up into three procedures. -- erics
+ */
+static void rxrpc_rtt_estimator(struct rxrpc_peer *peer, long sample_rtt_us)
+{
+ long m = sample_rtt_us; /* RTT */
+ u32 srtt = peer->srtt_us;
+
+ /* The following amusing code comes from Jacobson's
+ * article in SIGCOMM '88. Note that rtt and mdev
+ * are scaled versions of rtt and mean deviation.
+ * This is designed to be as fast as possible
+ * m stands for "measurement".
+ *
+ * On a 1990 paper the rto value is changed to:
+ * RTO = rtt + 4 * mdev
+ *
+ * Funny. This algorithm seems to be very broken.
+ * These formulae increase RTO, when it should be decreased, increase
+ * too slowly, when it should be increased quickly, decrease too quickly
+ * etc. I guess in BSD RTO takes ONE value, so that it is absolutely
+ * does not matter how to _calculate_ it. Seems, it was trap
+ * that VJ failed to avoid. 8)
+ */
+ if (srtt != 0) {
+ m -= (srtt >> 3); /* m is now error in rtt est */
+ srtt += m; /* rtt = 7/8 rtt + 1/8 new */
+ if (m < 0) {
+ m = -m; /* m is now abs(error) */
+ m -= (peer->mdev_us >> 2); /* similar update on mdev */
+ /* This is similar to one of Eifel findings.
+ * Eifel blocks mdev updates when rtt decreases.
+ * This solution is a bit different: we use finer gain
+ * for mdev in this case (alpha*beta).
+ * Like Eifel it also prevents growth of rto,
+ * but also it limits too fast rto decreases,
+ * happening in pure Eifel.
+ */
+ if (m > 0)
+ m >>= 3;
+ } else {
+ m -= (peer->mdev_us >> 2); /* similar update on mdev */
+ }
+
+ peer->mdev_us += m; /* mdev = 3/4 mdev + 1/4 new */
+ if (peer->mdev_us > peer->mdev_max_us) {
+ peer->mdev_max_us = peer->mdev_us;
+ if (peer->mdev_max_us > peer->rttvar_us)
+ peer->rttvar_us = peer->mdev_max_us;
+ }
+ } else {
+ /* no previous measure. */
+ srtt = m << 3; /* take the measured time to be rtt */
+ peer->mdev_us = m << 1; /* make sure rto = 3*rtt */
+ peer->rttvar_us = max(peer->mdev_us, rxrpc_rto_min_us(peer));
+ peer->mdev_max_us = peer->rttvar_us;
+ }
+
+ peer->srtt_us = max(1U, srtt);
+}
+
+/*
+ * Calculate rto without backoff. This is the second half of Van Jacobson's
+ * routine referred to above.
+ */
+static void rxrpc_set_rto(struct rxrpc_peer *peer)
+{
+ u32 rto;
+
+ /* 1. If rtt variance happened to be less 50msec, it is hallucination.
+ * It cannot be less due to utterly erratic ACK generation made
+ * at least by solaris and freebsd. "Erratic ACKs" has _nothing_
+ * to do with delayed acks, because at cwnd>2 true delack timeout
+ * is invisible. Actually, Linux-2.4 also generates erratic
+ * ACKs in some circumstances.
+ */
+ rto = __rxrpc_set_rto(peer);
+
+ /* 2. Fixups made earlier cannot be right.
+ * If we do not estimate RTO correctly without them,
+ * all the algo is pure shit and should be replaced
+ * with correct one. It is exactly, which we pretend to do.
+ */
+
+ /* NOTE: clamping at RXRPC_RTO_MIN is not required, current algo
+ * guarantees that rto is higher.
+ */
+ peer->rto_j = rxrpc_bound_rto(rto);
+}
+
+static void rxrpc_ack_update_rtt(struct rxrpc_peer *peer, long rtt_us)
+{
+ if (rtt_us < 0)
+ return;
+
+ //rxrpc_update_rtt_min(peer, rtt_us);
+ rxrpc_rtt_estimator(peer, rtt_us);
+ rxrpc_set_rto(peer);
+
+ /* RFC6298: only reset backoff on valid RTT measurement. */
+ peer->backoff = 0;
+}
+
+/*
+ * Add RTT information to cache. This is called in softirq mode and has
+ * exclusive access to the peer RTT data.
+ */
+void rxrpc_peer_add_rtt(struct rxrpc_call *call, enum rxrpc_rtt_rx_trace why,
+ rxrpc_serial_t send_serial, rxrpc_serial_t resp_serial,
+ ktime_t send_time, ktime_t resp_time)
+{
+ struct rxrpc_peer *peer = call->peer;
+ s64 rtt_us;
+
+ rtt_us = ktime_to_us(ktime_sub(resp_time, send_time));
+ if (rtt_us < 0)
+ return;
+
+ spin_lock(&peer->rtt_input_lock);
+ rxrpc_ack_update_rtt(peer, rtt_us);
+ if (peer->rtt_count < 3)
+ peer->rtt_count++;
+ spin_unlock(&peer->rtt_input_lock);
+
+ trace_rxrpc_rtt_rx(call, why, send_serial, resp_serial,
+ peer->srtt_us >> 3, peer->rto_j);
+}
+
+/*
+ * Get the retransmission timeout to set in jiffies, backing it off each time
+ * we retransmit.
+ */
+unsigned long rxrpc_get_rto_backoff(struct rxrpc_peer *peer, bool retrans)
+{
+ u64 timo_j;
+ u8 backoff = READ_ONCE(peer->backoff);
+
+ timo_j = peer->rto_j;
+ timo_j <<= backoff;
+ if (retrans && timo_j * 2 <= RXRPC_RTO_MAX)
+ WRITE_ONCE(peer->backoff, backoff + 1);
+
+ if (timo_j < 1)
+ timo_j = 1;
+
+ return timo_j;
+}
+
+void rxrpc_peer_init_rtt(struct rxrpc_peer *peer)
+{
+ peer->rto_j = RXRPC_TIMEOUT_INIT;
+ peer->mdev_us = jiffies_to_usecs(RXRPC_TIMEOUT_INIT);
+ peer->backoff = 0;
+ //minmax_reset(&peer->rtt_min, rxrpc_jiffies32, ~0U);
+}
diff --git a/net/rxrpc/rxkad.c b/net/rxrpc/rxkad.c
index 8d8aa3c..52a24d4 100644
--- a/net/rxrpc/rxkad.c
+++ b/net/rxrpc/rxkad.c
@@ -648,9 +648,9 @@
u32 serial;
int ret;
- _enter("{%d,%x}", conn->debug_id, key_serial(conn->params.key));
+ _enter("{%d,%x}", conn->debug_id, key_serial(conn->server_key));
- ret = key_validate(conn->params.key);
+ ret = key_validate(conn->server_key);
if (ret < 0)
return ret;
@@ -1148,7 +1148,7 @@
ret = rxkad_decrypt_ticket(conn, skb, ticket, ticket_len, &session_key,
&expiry, _abort_code);
if (ret < 0)
- goto temporary_error_free_resp;
+ goto temporary_error_free_ticket;
/* use the session key from inside the ticket to decrypt the
* response */
@@ -1230,7 +1230,6 @@
temporary_error_free_ticket:
kfree(ticket);
-temporary_error_free_resp:
kfree(response);
temporary_error:
/* Ignore the response packet if we got a temporary error such as
@@ -1293,6 +1292,7 @@
const struct rxrpc_security rxkad = {
.name = "rxkad",
.security_index = RXRPC_SECURITY_RXKAD,
+ .no_key_abort = RXKADUNKNOWNKEY,
.init = rxkad_init,
.exit = rxkad_exit,
.init_connection_security = rxkad_init_connection_security,
diff --git a/net/rxrpc/security.c b/net/rxrpc/security.c
index a4c47d2..9b1fb9e 100644
--- a/net/rxrpc/security.c
+++ b/net/rxrpc/security.c
@@ -101,62 +101,58 @@
}
/*
- * initialise the security on a server connection
+ * Find the security key for a server connection.
*/
-int rxrpc_init_server_conn_security(struct rxrpc_connection *conn)
+bool rxrpc_look_up_server_security(struct rxrpc_local *local, struct rxrpc_sock *rx,
+ const struct rxrpc_security **_sec,
+ struct key **_key,
+ struct sk_buff *skb)
{
const struct rxrpc_security *sec;
- struct rxrpc_local *local = conn->params.local;
- struct rxrpc_sock *rx;
- struct key *key;
- key_ref_t kref;
+ struct rxrpc_skb_priv *sp = rxrpc_skb(skb);
+ key_ref_t kref = NULL;
char kdesc[5 + 1 + 3 + 1];
_enter("");
- sprintf(kdesc, "%u:%u", conn->service_id, conn->security_ix);
+ sprintf(kdesc, "%u:%u", sp->hdr.serviceId, sp->hdr.securityIndex);
- sec = rxrpc_security_lookup(conn->security_ix);
+ sec = rxrpc_security_lookup(sp->hdr.securityIndex);
if (!sec) {
- _leave(" = -ENOKEY [lookup]");
- return -ENOKEY;
+ trace_rxrpc_abort(0, "SVS",
+ sp->hdr.cid, sp->hdr.callNumber, sp->hdr.seq,
+ RX_INVALID_OPERATION, EKEYREJECTED);
+ skb->mark = RXRPC_SKB_MARK_REJECT_ABORT;
+ skb->priority = RX_INVALID_OPERATION;
+ return false;
}
- /* find the service */
- read_lock(&local->services_lock);
- rx = rcu_dereference_protected(local->service,
- lockdep_is_held(&local->services_lock));
- if (rx && (rx->srx.srx_service == conn->service_id ||
- rx->second_service == conn->service_id))
- goto found_service;
+ if (sp->hdr.securityIndex == RXRPC_SECURITY_NONE)
+ goto out;
- /* the service appears to have died */
- read_unlock(&local->services_lock);
- _leave(" = -ENOENT");
- return -ENOENT;
-
-found_service:
if (!rx->securities) {
- read_unlock(&local->services_lock);
- _leave(" = -ENOKEY");
- return -ENOKEY;
+ trace_rxrpc_abort(0, "SVR",
+ sp->hdr.cid, sp->hdr.callNumber, sp->hdr.seq,
+ RX_INVALID_OPERATION, EKEYREJECTED);
+ skb->mark = RXRPC_SKB_MARK_REJECT_ABORT;
+ skb->priority = RX_INVALID_OPERATION;
+ return false;
}
/* look through the service's keyring */
kref = keyring_search(make_key_ref(rx->securities, 1UL),
&key_type_rxrpc_s, kdesc, true);
if (IS_ERR(kref)) {
- read_unlock(&local->services_lock);
- _leave(" = %ld [search]", PTR_ERR(kref));
- return PTR_ERR(kref);
+ trace_rxrpc_abort(0, "SVK",
+ sp->hdr.cid, sp->hdr.callNumber, sp->hdr.seq,
+ sec->no_key_abort, EKEYREJECTED);
+ skb->mark = RXRPC_SKB_MARK_REJECT_ABORT;
+ skb->priority = sec->no_key_abort;
+ return false;
}
- key = key_ref_to_ptr(kref);
- read_unlock(&local->services_lock);
-
- conn->server_key = key;
- conn->security = sec;
-
- _leave(" = 0");
- return 0;
+out:
+ *_sec = sec;
+ *_key = key_ref_to_ptr(kref);
+ return true;
}
diff --git a/net/rxrpc/sendmsg.c b/net/rxrpc/sendmsg.c
index 813fd68..1a340eb 100644
--- a/net/rxrpc/sendmsg.c
+++ b/net/rxrpc/sendmsg.c
@@ -18,6 +18,21 @@
#include "ar-internal.h"
/*
+ * Return true if there's sufficient Tx queue space.
+ */
+static bool rxrpc_check_tx_space(struct rxrpc_call *call, rxrpc_seq_t *_tx_win)
+{
+ unsigned int win_size =
+ min_t(unsigned int, call->tx_winsize,
+ call->cong_cwnd + call->cong_extra);
+ rxrpc_seq_t tx_win = READ_ONCE(call->tx_hard_ack);
+
+ if (_tx_win)
+ *_tx_win = tx_win;
+ return call->tx_top - tx_win < win_size;
+}
+
+/*
* Wait for space to appear in the Tx queue or a signal to occur.
*/
static int rxrpc_wait_for_tx_window_intr(struct rxrpc_sock *rx,
@@ -26,9 +41,7 @@
{
for (;;) {
set_current_state(TASK_INTERRUPTIBLE);
- if (call->tx_top - call->tx_hard_ack <
- min_t(unsigned int, call->tx_winsize,
- call->cong_cwnd + call->cong_extra))
+ if (rxrpc_check_tx_space(call, NULL))
return 0;
if (call->state >= RXRPC_CALL_COMPLETE)
@@ -49,40 +62,36 @@
* Wait for space to appear in the Tx queue uninterruptibly, but with
* a timeout of 2*RTT if no progress was made and a signal occurred.
*/
-static int rxrpc_wait_for_tx_window_nonintr(struct rxrpc_sock *rx,
+static int rxrpc_wait_for_tx_window_waitall(struct rxrpc_sock *rx,
struct rxrpc_call *call)
{
rxrpc_seq_t tx_start, tx_win;
- signed long rtt2, timeout;
- u64 rtt;
+ signed long rtt, timeout;
- rtt = READ_ONCE(call->peer->rtt);
- rtt2 = nsecs_to_jiffies64(rtt) * 2;
- if (rtt2 < 1)
- rtt2 = 1;
+ rtt = READ_ONCE(call->peer->srtt_us) >> 3;
+ rtt = usecs_to_jiffies(rtt) * 2;
+ if (rtt < 2)
+ rtt = 2;
- timeout = rtt2;
+ timeout = rtt;
tx_start = READ_ONCE(call->tx_hard_ack);
for (;;) {
set_current_state(TASK_UNINTERRUPTIBLE);
tx_win = READ_ONCE(call->tx_hard_ack);
- if (call->tx_top - tx_win <
- min_t(unsigned int, call->tx_winsize,
- call->cong_cwnd + call->cong_extra))
+ if (rxrpc_check_tx_space(call, &tx_win))
return 0;
if (call->state >= RXRPC_CALL_COMPLETE)
return call->error;
- if (test_bit(RXRPC_CALL_IS_INTR, &call->flags) &&
- timeout == 0 &&
+ if (timeout == 0 &&
tx_win == tx_start && signal_pending(current))
return -EINTR;
if (tx_win != tx_start) {
- timeout = rtt2;
+ timeout = rtt;
tx_start = tx_win;
}
@@ -92,6 +101,26 @@
}
/*
+ * Wait for space to appear in the Tx queue uninterruptibly.
+ */
+static int rxrpc_wait_for_tx_window_nonintr(struct rxrpc_sock *rx,
+ struct rxrpc_call *call,
+ long *timeo)
+{
+ for (;;) {
+ set_current_state(TASK_UNINTERRUPTIBLE);
+ if (rxrpc_check_tx_space(call, NULL))
+ return 0;
+
+ if (call->state >= RXRPC_CALL_COMPLETE)
+ return call->error;
+
+ trace_rxrpc_transmit(call, rxrpc_transmit_wait);
+ *timeo = schedule_timeout(*timeo);
+ }
+}
+
+/*
* wait for space to appear in the transmit/ACK window
* - caller holds the socket locked
*/
@@ -108,10 +137,19 @@
add_wait_queue(&call->waitq, &myself);
- if (waitall)
- ret = rxrpc_wait_for_tx_window_nonintr(rx, call);
- else
- ret = rxrpc_wait_for_tx_window_intr(rx, call, timeo);
+ switch (call->interruptibility) {
+ case RXRPC_INTERRUPTIBLE:
+ if (waitall)
+ ret = rxrpc_wait_for_tx_window_waitall(rx, call);
+ else
+ ret = rxrpc_wait_for_tx_window_intr(rx, call, timeo);
+ break;
+ case RXRPC_PREINTERRUPTIBLE:
+ case RXRPC_UNINTERRUPTIBLE:
+ default:
+ ret = rxrpc_wait_for_tx_window_nonintr(rx, call, timeo);
+ break;
+ }
remove_wait_queue(&call->waitq, &myself);
set_current_state(TASK_RUNNING);
@@ -232,16 +270,9 @@
_debug("need instant resend %d", ret);
rxrpc_instant_resend(call, ix);
} else {
- unsigned long now = jiffies, resend_at;
+ unsigned long now = jiffies;
+ unsigned long resend_at = now + call->peer->rto_j;
- if (call->peer->rtt_usage > 1)
- resend_at = nsecs_to_jiffies(call->peer->rtt * 3 / 2);
- else
- resend_at = rxrpc_resend_timeout;
- if (resend_at < 1)
- resend_at = 1;
-
- resend_at += now;
WRITE_ONCE(call->resend_at, resend_at);
rxrpc_reduce_call_timer(call, resend_at, now,
rxrpc_timer_set_for_send);
@@ -275,7 +306,7 @@
/* this should be in poll */
sk_clear_bit(SOCKWQ_ASYNC_NOSPACE, sk);
- if (sk->sk_err || (sk->sk_shutdown & SEND_SHUTDOWN))
+ if (sk->sk_shutdown & SEND_SHUTDOWN)
return -EPIPE;
more = msg->msg_flags & MSG_MORE;
@@ -302,9 +333,7 @@
_debug("alloc");
- if (call->tx_top - call->tx_hard_ack >=
- min_t(unsigned int, call->tx_winsize,
- call->cong_cwnd + call->cong_extra)) {
+ if (!rxrpc_check_tx_space(call, NULL)) {
ret = -EAGAIN;
if (msg->msg_flags & MSG_DONTWAIT)
goto maybe_error;
@@ -619,7 +648,7 @@
.call.tx_total_len = -1,
.call.user_call_ID = 0,
.call.nr_timeouts = 0,
- .call.intr = true,
+ .call.interruptibility = RXRPC_INTERRUPTIBLE,
.abort_code = 0,
.command = RXRPC_CMD_SEND_DATA,
.exclusive = false,
@@ -654,6 +683,9 @@
if (IS_ERR(call))
return PTR_ERR(call);
/* ... and we have the call lock. */
+ ret = 0;
+ if (READ_ONCE(call->state) == RXRPC_CALL_COMPLETE)
+ goto out_put_unlock;
} else {
switch (READ_ONCE(call->state)) {
case RXRPC_CALL_UNINITIALISED:
diff --git a/net/rxrpc/sysctl.c b/net/rxrpc/sysctl.c
index 2bbb381..18dade4 100644
--- a/net/rxrpc/sysctl.c
+++ b/net/rxrpc/sysctl.c
@@ -71,15 +71,6 @@
.extra1 = (void *)&one_jiffy,
.extra2 = (void *)&max_jiffies,
},
- {
- .procname = "resend_timeout",
- .data = &rxrpc_resend_timeout,
- .maxlen = sizeof(unsigned long),
- .mode = 0644,
- .proc_handler = proc_doulongvec_ms_jiffies_minmax,
- .extra1 = (void *)&one_jiffy,
- .extra2 = (void *)&max_jiffies,
- },
/* Non-time values */
{