rxrpc: Rewrite the data and ack handling code
Rewrite the data and ack handling code such that:
(1) Parsing of received ACK and ABORT packets and the distribution and the
filing of DATA packets happens entirely within the data_ready context
called from the UDP socket. This allows us to process and discard ACK
and ABORT packets much more quickly (they're no longer stashed on a
queue for a background thread to process).
(2) We avoid calling skb_clone(), pskb_pull() and pskb_trim(). We instead
keep track of the offset and length of the content of each packet in
the sk_buff metadata. This means we don't do any allocation in the
receive path.
(3) Jumbo DATA packet parsing is now done in data_ready context. Rather
than cloning the packet once for each subpacket and pulling/trimming
it, we file the packet multiple times with an annotation for each
indicating which subpacket is there. From that we can directly
calculate the offset and length.
(4) A call's receive queue can be accessed without taking locks (memory
barriers do have to be used, though).
(5) Incoming calls are set up from preallocated resources and immediately
made live. They can than have packets queued upon them and ACKs
generated. If insufficient resources exist, DATA packet #1 is given a
BUSY reply and other DATA packets are discarded).
(6) sk_buffs no longer take a ref on their parent call.
To make this work, the following changes are made:
(1) Each call's receive buffer is now a circular buffer of sk_buff
pointers (rxtx_buffer) rather than a number of sk_buff_heads spread
between the call and the socket. This permits each sk_buff to be in
the buffer multiple times. The receive buffer is reused for the
transmit buffer.
(2) A circular buffer of annotations (rxtx_annotations) is kept parallel
to the data buffer. Transmission phase annotations indicate whether a
buffered packet has been ACK'd or not and whether it needs
retransmission.
Receive phase annotations indicate whether a slot holds a whole packet
or a jumbo subpacket and, if the latter, which subpacket. They also
note whether the packet has been decrypted in place.
(3) DATA packet window tracking is much simplified. Each phase has just
two numbers representing the window (rx_hard_ack/rx_top and
tx_hard_ack/tx_top).
The hard_ack number is the sequence number before base of the window,
representing the last packet the other side says it has consumed.
hard_ack starts from 0 and the first packet is sequence number 1.
The top number is the sequence number of the highest-numbered packet
residing in the buffer. Packets between hard_ack+1 and top are
soft-ACK'd to indicate they've been received, but not yet consumed.
Four macros, before(), before_eq(), after() and after_eq() are added
to compare sequence numbers within the window. This allows for the
top of the window to wrap when the hard-ack sequence number gets close
to the limit.
Two flags, RXRPC_CALL_RX_LAST and RXRPC_CALL_TX_LAST, are added also
to indicate when rx_top and tx_top point at the packets with the
LAST_PACKET bit set, indicating the end of the phase.
(4) Calls are queued on the socket 'receive queue' rather than packets.
This means that we don't need have to invent dummy packets to queue to
indicate abnormal/terminal states and we don't have to keep metadata
packets (such as ABORTs) around
(5) The offset and length of a (sub)packet's content are now passed to
the verify_packet security op. This is currently expected to decrypt
the packet in place and validate it.
However, there's now nowhere to store the revised offset and length of
the actual data within the decrypted blob (there may be a header and
padding to skip) because an sk_buff may represent multiple packets, so
a locate_data security op is added to retrieve these details from the
sk_buff content when needed.
(6) recvmsg() now has to handle jumbo subpackets, where each subpacket is
individually secured and needs to be individually decrypted. The code
to do this is broken out into rxrpc_recvmsg_data() and shared with the
kernel API. It now iterates over the call's receive buffer rather
than walking the socket receive queue.
Additional changes:
(1) The timers are condensed to a single timer that is set for the soonest
of three timeouts (delayed ACK generation, DATA retransmission and
call lifespan).
(2) Transmission of ACK and ABORT packets is effected immediately from
process-context socket ops/kernel API calls that cause them instead of
them being punted off to a background work item. The data_ready
handler still has to defer to the background, though.
(3) A shutdown op is added to the AF_RXRPC socket so that the AFS
filesystem can shut down the socket and flush its own work items
before closing the socket to deal with any in-progress service calls.
Future additional changes that will need to be considered:
(1) Make sure that a call doesn't hog the front of the queue by receiving
data from the network as fast as userspace is consuming it to the
exclusion of other calls.
(2) Transmit delayed ACKs from within recvmsg() when we've consumed
sufficiently more packets to avoid the background work item needing to
run.
Signed-off-by: David Howells <dhowells@redhat.com>
diff --git a/net/rxrpc/call_event.c b/net/rxrpc/call_event.c
index af88ad7..2b976e7 100644
--- a/net/rxrpc/call_event.c
+++ b/net/rxrpc/call_event.c
@@ -22,1257 +22,286 @@
#include "ar-internal.h"
/*
+ * Set the timer
+ */
+static void rxrpc_set_timer(struct rxrpc_call *call)
+{
+ unsigned long t, now = jiffies;
+
+ _enter("{%ld,%ld,%ld:%ld}",
+ call->ack_at - now, call->resend_at - now, call->expire_at - now,
+ call->timer.expires - now);
+
+ read_lock_bh(&call->state_lock);
+
+ if (call->state < RXRPC_CALL_COMPLETE) {
+ t = call->ack_at;
+ if (time_before(call->resend_at, t))
+ t = call->resend_at;
+ if (time_before(call->expire_at, t))
+ t = call->expire_at;
+ if (!timer_pending(&call->timer) ||
+ time_before(t, call->timer.expires)) {
+ _debug("set timer %ld", t - now);
+ mod_timer(&call->timer, t);
+ }
+ }
+ read_unlock_bh(&call->state_lock);
+}
+
+/*
* propose an ACK be sent
*/
-void __rxrpc_propose_ACK(struct rxrpc_call *call, u8 ack_reason,
- u16 skew, u32 serial, bool immediate)
+static void __rxrpc_propose_ACK(struct rxrpc_call *call, u8 ack_reason,
+ u16 skew, u32 serial, bool immediate,
+ bool background)
{
- unsigned long expiry;
+ unsigned long now, ack_at, expiry = rxrpc_soft_ack_delay;
s8 prior = rxrpc_ack_priority[ack_reason];
- ASSERTCMP(prior, >, 0);
-
_enter("{%d},%s,%%%x,%u",
call->debug_id, rxrpc_acks(ack_reason), serial, immediate);
- if (prior < rxrpc_ack_priority[call->ackr_reason]) {
- if (immediate)
- goto cancel_timer;
- return;
- }
-
- /* update DELAY, IDLE, REQUESTED and PING_RESPONSE ACK serial
- * numbers */
- if (prior == rxrpc_ack_priority[call->ackr_reason]) {
- if (prior <= 4) {
- call->ackr_skew = skew;
+ /* Update DELAY, IDLE, REQUESTED and PING_RESPONSE ACK serial
+ * numbers, but we don't alter the timeout.
+ */
+ _debug("prior %u %u vs %u %u",
+ ack_reason, prior,
+ call->ackr_reason, rxrpc_ack_priority[call->ackr_reason]);
+ if (ack_reason == call->ackr_reason) {
+ if (RXRPC_ACK_UPDATEABLE & (1 << ack_reason)) {
call->ackr_serial = serial;
+ call->ackr_skew = skew;
}
- if (immediate)
- goto cancel_timer;
- return;
+ if (!immediate)
+ return;
+ } else if (prior > rxrpc_ack_priority[call->ackr_reason]) {
+ call->ackr_reason = ack_reason;
+ call->ackr_serial = serial;
+ call->ackr_skew = skew;
}
- call->ackr_reason = ack_reason;
- call->ackr_serial = serial;
-
switch (ack_reason) {
+ case RXRPC_ACK_REQUESTED:
+ if (rxrpc_requested_ack_delay < expiry)
+ expiry = rxrpc_requested_ack_delay;
+ if (serial == 1)
+ immediate = false;
+ break;
+
case RXRPC_ACK_DELAY:
- _debug("run delay timer");
- expiry = rxrpc_soft_ack_delay;
- goto run_timer;
+ if (rxrpc_soft_ack_delay < expiry)
+ expiry = rxrpc_soft_ack_delay;
+ break;
case RXRPC_ACK_IDLE:
- if (!immediate) {
- _debug("run defer timer");
+ if (rxrpc_soft_ack_delay < expiry)
expiry = rxrpc_idle_ack_delay;
- goto run_timer;
- }
- goto cancel_timer;
-
- case RXRPC_ACK_REQUESTED:
- expiry = rxrpc_requested_ack_delay;
- if (!expiry)
- goto cancel_timer;
- if (!immediate || serial == 1) {
- _debug("run defer timer");
- goto run_timer;
- }
+ break;
default:
- _debug("immediate ACK");
- goto cancel_timer;
+ immediate = true;
+ break;
}
-run_timer:
- expiry += jiffies;
- if (!timer_pending(&call->ack_timer) ||
- time_after(call->ack_timer.expires, expiry))
- mod_timer(&call->ack_timer, expiry);
- return;
-
-cancel_timer:
- _debug("cancel timer %%%u", serial);
- try_to_del_timer_sync(&call->ack_timer);
- read_lock_bh(&call->state_lock);
- if (call->state < RXRPC_CALL_COMPLETE &&
- !test_and_set_bit(RXRPC_CALL_EV_ACK, &call->events))
- rxrpc_queue_call(call);
- read_unlock_bh(&call->state_lock);
+ now = jiffies;
+ if (test_bit(RXRPC_CALL_EV_ACK, &call->events)) {
+ _debug("already scheduled");
+ } else if (immediate || expiry == 0) {
+ _debug("immediate ACK %lx", call->events);
+ if (!test_and_set_bit(RXRPC_CALL_EV_ACK, &call->events) &&
+ background)
+ rxrpc_queue_call(call);
+ } else {
+ ack_at = now + expiry;
+ _debug("deferred ACK %ld < %ld", expiry, call->ack_at - now);
+ if (time_before(ack_at, call->ack_at)) {
+ call->ack_at = ack_at;
+ rxrpc_set_timer(call);
+ }
+ }
}
/*
* propose an ACK be sent, locking the call structure
*/
void rxrpc_propose_ACK(struct rxrpc_call *call, u8 ack_reason,
- u16 skew, u32 serial, bool immediate)
+ u16 skew, u32 serial, bool immediate, bool background)
{
- s8 prior = rxrpc_ack_priority[ack_reason];
-
- if (prior > rxrpc_ack_priority[call->ackr_reason]) {
- spin_lock_bh(&call->lock);
- __rxrpc_propose_ACK(call, ack_reason, skew, serial, immediate);
- spin_unlock_bh(&call->lock);
- }
+ spin_lock_bh(&call->lock);
+ __rxrpc_propose_ACK(call, ack_reason, skew, serial,
+ immediate, background);
+ spin_unlock_bh(&call->lock);
}
/*
- * set the resend timer
- */
-static void rxrpc_set_resend(struct rxrpc_call *call, u8 resend,
- unsigned long resend_at)
-{
- read_lock_bh(&call->state_lock);
- if (call->state == RXRPC_CALL_COMPLETE)
- resend = 0;
-
- if (resend & 1) {
- _debug("SET RESEND");
- set_bit(RXRPC_CALL_EV_RESEND, &call->events);
- }
-
- if (resend & 2) {
- _debug("MODIFY RESEND TIMER");
- set_bit(RXRPC_CALL_RUN_RTIMER, &call->flags);
- mod_timer(&call->resend_timer, resend_at);
- } else {
- _debug("KILL RESEND TIMER");
- del_timer_sync(&call->resend_timer);
- clear_bit(RXRPC_CALL_EV_RESEND_TIMER, &call->events);
- clear_bit(RXRPC_CALL_RUN_RTIMER, &call->flags);
- }
- read_unlock_bh(&call->state_lock);
-}
-
-/*
- * resend packets
+ * Perform retransmission of NAK'd and unack'd packets.
*/
static void rxrpc_resend(struct rxrpc_call *call)
{
struct rxrpc_wire_header *whdr;
struct rxrpc_skb_priv *sp;
- struct sk_buff *txb;
- unsigned long *p_txb, resend_at;
- bool stop;
- int loop;
- u8 resend;
-
- _enter("{%d,%d,%d,%d},",
- call->acks_hard, call->acks_unacked,
- atomic_read(&call->sequence),
- CIRC_CNT(call->acks_head, call->acks_tail, call->acks_winsz));
-
- stop = false;
- resend = 0;
- resend_at = 0;
-
- for (loop = call->acks_tail;
- loop != call->acks_head || stop;
- loop = (loop + 1) & (call->acks_winsz - 1)
- ) {
- p_txb = call->acks_window + loop;
- smp_read_barrier_depends();
- if (*p_txb & 1)
- continue;
-
- txb = (struct sk_buff *) *p_txb;
- sp = rxrpc_skb(txb);
-
- if (sp->need_resend) {
- sp->need_resend = false;
-
- /* each Tx packet has a new serial number */
- sp->hdr.serial = atomic_inc_return(&call->conn->serial);
-
- whdr = (struct rxrpc_wire_header *)txb->head;
- whdr->serial = htonl(sp->hdr.serial);
-
- _proto("Tx DATA %%%u { #%d }",
- sp->hdr.serial, sp->hdr.seq);
- if (rxrpc_send_data_packet(call->conn, txb) < 0) {
- stop = true;
- sp->resend_at = jiffies + 3;
- } else {
- if (rxrpc_is_client_call(call))
- rxrpc_expose_client_call(call);
- sp->resend_at =
- jiffies + rxrpc_resend_timeout;
- }
- }
-
- if (time_after_eq(jiffies + 1, sp->resend_at)) {
- sp->need_resend = true;
- resend |= 1;
- } else if (resend & 2) {
- if (time_before(sp->resend_at, resend_at))
- resend_at = sp->resend_at;
- } else {
- resend_at = sp->resend_at;
- resend |= 2;
- }
- }
-
- rxrpc_set_resend(call, resend, resend_at);
- _leave("");
-}
-
-/*
- * handle resend timer expiry
- */
-static void rxrpc_resend_timer(struct rxrpc_call *call)
-{
- struct rxrpc_skb_priv *sp;
- struct sk_buff *txb;
- unsigned long *p_txb, resend_at;
- int loop;
- u8 resend;
-
- _enter("%d,%d,%d",
- call->acks_tail, call->acks_unacked, call->acks_head);
-
- if (call->state == RXRPC_CALL_COMPLETE)
- return;
-
- resend = 0;
- resend_at = 0;
-
- for (loop = call->acks_unacked;
- loop != call->acks_head;
- loop = (loop + 1) & (call->acks_winsz - 1)
- ) {
- p_txb = call->acks_window + loop;
- smp_read_barrier_depends();
- txb = (struct sk_buff *) (*p_txb & ~1);
- sp = rxrpc_skb(txb);
-
- ASSERT(!(*p_txb & 1));
-
- if (sp->need_resend) {
- ;
- } else if (time_after_eq(jiffies + 1, sp->resend_at)) {
- sp->need_resend = true;
- resend |= 1;
- } else if (resend & 2) {
- if (time_before(sp->resend_at, resend_at))
- resend_at = sp->resend_at;
- } else {
- resend_at = sp->resend_at;
- resend |= 2;
- }
- }
-
- rxrpc_set_resend(call, resend, resend_at);
- _leave("");
-}
-
-/*
- * process soft ACKs of our transmitted packets
- * - these indicate packets the peer has or has not received, but hasn't yet
- * given to the consumer, and so can still be discarded and re-requested
- */
-static int rxrpc_process_soft_ACKs(struct rxrpc_call *call,
- struct rxrpc_ackpacket *ack,
- struct sk_buff *skb)
-{
- struct rxrpc_skb_priv *sp;
- struct sk_buff *txb;
- unsigned long *p_txb, resend_at;
- int loop;
- u8 sacks[RXRPC_MAXACKS], resend;
-
- _enter("{%d,%d},{%d},",
- call->acks_hard,
- CIRC_CNT(call->acks_head, call->acks_tail, call->acks_winsz),
- ack->nAcks);
-
- if (skb_copy_bits(skb, 0, sacks, ack->nAcks) < 0)
- goto protocol_error;
-
- resend = 0;
- resend_at = 0;
- for (loop = 0; loop < ack->nAcks; loop++) {
- p_txb = call->acks_window;
- p_txb += (call->acks_tail + loop) & (call->acks_winsz - 1);
- smp_read_barrier_depends();
- txb = (struct sk_buff *) (*p_txb & ~1);
- sp = rxrpc_skb(txb);
-
- switch (sacks[loop]) {
- case RXRPC_ACK_TYPE_ACK:
- sp->need_resend = false;
- *p_txb |= 1;
- break;
- case RXRPC_ACK_TYPE_NACK:
- sp->need_resend = true;
- *p_txb &= ~1;
- resend = 1;
- break;
- default:
- _debug("Unsupported ACK type %d", sacks[loop]);
- goto protocol_error;
- }
- }
-
- smp_mb();
- call->acks_unacked = (call->acks_tail + loop) & (call->acks_winsz - 1);
-
- /* anything not explicitly ACK'd is implicitly NACK'd, but may just not
- * have been received or processed yet by the far end */
- for (loop = call->acks_unacked;
- loop != call->acks_head;
- loop = (loop + 1) & (call->acks_winsz - 1)
- ) {
- p_txb = call->acks_window + loop;
- smp_read_barrier_depends();
- txb = (struct sk_buff *) (*p_txb & ~1);
- sp = rxrpc_skb(txb);
-
- if (*p_txb & 1) {
- /* packet must have been discarded */
- sp->need_resend = true;
- *p_txb &= ~1;
- resend |= 1;
- } else if (sp->need_resend) {
- ;
- } else if (time_after_eq(jiffies + 1, sp->resend_at)) {
- sp->need_resend = true;
- resend |= 1;
- } else if (resend & 2) {
- if (time_before(sp->resend_at, resend_at))
- resend_at = sp->resend_at;
- } else {
- resend_at = sp->resend_at;
- resend |= 2;
- }
- }
-
- rxrpc_set_resend(call, resend, resend_at);
- _leave(" = 0");
- return 0;
-
-protocol_error:
- _leave(" = -EPROTO");
- return -EPROTO;
-}
-
-/*
- * discard hard-ACK'd packets from the Tx window
- */
-static void rxrpc_rotate_tx_window(struct rxrpc_call *call, u32 hard)
-{
- unsigned long _skb;
- int tail = call->acks_tail, old_tail;
- int win = CIRC_CNT(call->acks_head, tail, call->acks_winsz);
-
- _enter("{%u,%u},%u", call->acks_hard, win, hard);
-
- ASSERTCMP(hard - call->acks_hard, <=, win);
-
- while (call->acks_hard < hard) {
- smp_read_barrier_depends();
- _skb = call->acks_window[tail] & ~1;
- rxrpc_free_skb((struct sk_buff *) _skb);
- old_tail = tail;
- tail = (tail + 1) & (call->acks_winsz - 1);
- call->acks_tail = tail;
- if (call->acks_unacked == old_tail)
- call->acks_unacked = tail;
- call->acks_hard++;
- }
-
- wake_up(&call->waitq);
-}
-
-/*
- * clear the Tx window in the event of a failure
- */
-static void rxrpc_clear_tx_window(struct rxrpc_call *call)
-{
- rxrpc_rotate_tx_window(call, atomic_read(&call->sequence));
-}
-
-/*
- * drain the out of sequence received packet queue into the packet Rx queue
- */
-static int rxrpc_drain_rx_oos_queue(struct rxrpc_call *call)
-{
- struct rxrpc_skb_priv *sp;
struct sk_buff *skb;
- bool terminal;
- int ret;
+ rxrpc_seq_t cursor, seq, top;
+ unsigned long resend_at, now;
+ int ix;
+ u8 annotation;
- _enter("{%d,%d}", call->rx_data_post, call->rx_first_oos);
+ _enter("{%d,%d}", call->tx_hard_ack, call->tx_top);
spin_lock_bh(&call->lock);
- ret = -ECONNRESET;
- if (test_bit(RXRPC_CALL_RELEASED, &call->flags))
- goto socket_unavailable;
+ cursor = call->tx_hard_ack;
+ top = call->tx_top;
+ ASSERT(before_eq(cursor, top));
+ if (cursor == top)
+ goto out_unlock;
- skb = skb_dequeue(&call->rx_oos_queue);
- if (skb) {
+ /* Scan the packet list without dropping the lock and decide which of
+ * the packets in the Tx buffer we're going to resend and what the new
+ * resend timeout will be.
+ */
+ now = jiffies;
+ resend_at = now + rxrpc_resend_timeout;
+ seq = cursor + 1;
+ do {
+ ix = seq & RXRPC_RXTX_BUFF_MASK;
+ annotation = call->rxtx_annotations[ix];
+ if (annotation == RXRPC_TX_ANNO_ACK)
+ continue;
+
+ skb = call->rxtx_buffer[ix];
rxrpc_see_skb(skb);
sp = rxrpc_skb(skb);
- _debug("drain OOS packet %d [%d]",
- sp->hdr.seq, call->rx_first_oos);
-
- if (sp->hdr.seq != call->rx_first_oos) {
- skb_queue_head(&call->rx_oos_queue, skb);
- call->rx_first_oos = rxrpc_skb(skb)->hdr.seq;
- _debug("requeue %p {%u}", skb, call->rx_first_oos);
- } else {
- skb->mark = RXRPC_SKB_MARK_DATA;
- terminal = ((sp->hdr.flags & RXRPC_LAST_PACKET) &&
- !(sp->hdr.flags & RXRPC_CLIENT_INITIATED));
- ret = rxrpc_queue_rcv_skb(call, skb, true, terminal);
- BUG_ON(ret < 0);
- _debug("drain #%u", call->rx_data_post);
- call->rx_data_post++;
-
- /* find out what the next packet is */
- skb = skb_peek(&call->rx_oos_queue);
- rxrpc_see_skb(skb);
- if (skb)
- call->rx_first_oos = rxrpc_skb(skb)->hdr.seq;
- else
- call->rx_first_oos = 0;
- _debug("peek %p {%u}", skb, call->rx_first_oos);
+ if (annotation == RXRPC_TX_ANNO_UNACK) {
+ if (time_after(sp->resend_at, now)) {
+ if (time_before(sp->resend_at, resend_at))
+ resend_at = sp->resend_at;
+ continue;
+ }
}
- }
- ret = 0;
-socket_unavailable:
- spin_unlock_bh(&call->lock);
- _leave(" = %d", ret);
- return ret;
-}
+ /* Okay, we need to retransmit a packet. */
+ call->rxtx_annotations[ix] = RXRPC_TX_ANNO_RETRANS;
+ seq++;
+ } while (before_eq(seq, top));
-/*
- * insert an out of sequence packet into the buffer
- */
-static void rxrpc_insert_oos_packet(struct rxrpc_call *call,
- struct sk_buff *skb)
-{
- struct rxrpc_skb_priv *sp, *psp;
- struct sk_buff *p;
- u32 seq;
+ call->resend_at = resend_at;
- sp = rxrpc_skb(skb);
- seq = sp->hdr.seq;
- _enter(",,{%u}", seq);
+ /* Now go through the Tx window and perform the retransmissions. We
+ * have to drop the lock for each send. If an ACK comes in whilst the
+ * lock is dropped, it may clear some of the retransmission markers for
+ * packets that it soft-ACKs.
+ */
+ seq = cursor + 1;
+ do {
+ ix = seq & RXRPC_RXTX_BUFF_MASK;
+ annotation = call->rxtx_annotations[ix];
+ if (annotation != RXRPC_TX_ANNO_RETRANS)
+ continue;
- skb->destructor = rxrpc_packet_destructor;
- ASSERTCMP(sp->call, ==, NULL);
- sp->call = call;
- rxrpc_get_call_for_skb(call, skb);
-
- /* insert into the buffer in sequence order */
- spin_lock_bh(&call->lock);
-
- skb_queue_walk(&call->rx_oos_queue, p) {
- psp = rxrpc_skb(p);
- if (psp->hdr.seq > seq) {
- _debug("insert oos #%u before #%u", seq, psp->hdr.seq);
- skb_insert(p, skb, &call->rx_oos_queue);
- goto inserted;
- }
- }
-
- _debug("append oos #%u", seq);
- skb_queue_tail(&call->rx_oos_queue, skb);
-inserted:
-
- /* we might now have a new front to the queue */
- if (call->rx_first_oos == 0 || seq < call->rx_first_oos)
- call->rx_first_oos = seq;
-
- read_lock(&call->state_lock);
- if (call->state < RXRPC_CALL_COMPLETE &&
- call->rx_data_post == call->rx_first_oos) {
- _debug("drain rx oos now");
- set_bit(RXRPC_CALL_EV_DRAIN_RX_OOS, &call->events);
- }
- read_unlock(&call->state_lock);
-
- spin_unlock_bh(&call->lock);
- _leave(" [stored #%u]", call->rx_first_oos);
-}
-
-/*
- * clear the Tx window on final ACK reception
- */
-static void rxrpc_zap_tx_window(struct rxrpc_call *call)
-{
- struct rxrpc_skb_priv *sp;
- struct sk_buff *skb;
- unsigned long _skb, *acks_window;
- u8 winsz = call->acks_winsz;
- int tail;
-
- acks_window = call->acks_window;
- call->acks_window = NULL;
-
- while (CIRC_CNT(call->acks_head, call->acks_tail, winsz) > 0) {
- tail = call->acks_tail;
- smp_read_barrier_depends();
- _skb = acks_window[tail] & ~1;
- smp_mb();
- call->acks_tail = (call->acks_tail + 1) & (winsz - 1);
-
- skb = (struct sk_buff *) _skb;
+ skb = call->rxtx_buffer[ix];
+ rxrpc_get_skb(skb);
+ spin_unlock_bh(&call->lock);
sp = rxrpc_skb(skb);
- _debug("+++ clear Tx %u", sp->hdr.seq);
+
+ /* Each Tx packet needs a new serial number */
+ sp->hdr.serial = atomic_inc_return(&call->conn->serial);
+
+ whdr = (struct rxrpc_wire_header *)skb->head;
+ whdr->serial = htonl(sp->hdr.serial);
+
+ if (rxrpc_send_data_packet(call->conn, skb) < 0) {
+ call->resend_at = now + 2;
+ rxrpc_free_skb(skb);
+ return;
+ }
+
+ if (rxrpc_is_client_call(call))
+ rxrpc_expose_client_call(call);
+ sp->resend_at = now + rxrpc_resend_timeout;
+
rxrpc_free_skb(skb);
- }
-
- kfree(acks_window);
-}
-
-/*
- * process the extra information that may be appended to an ACK packet
- */
-static void rxrpc_extract_ackinfo(struct rxrpc_call *call, struct sk_buff *skb,
- unsigned int latest, int nAcks)
-{
- struct rxrpc_ackinfo ackinfo;
- struct rxrpc_peer *peer;
- unsigned int mtu;
-
- if (skb_copy_bits(skb, nAcks + 3, &ackinfo, sizeof(ackinfo)) < 0) {
- _leave(" [no ackinfo]");
- return;
- }
-
- _proto("Rx ACK %%%u Info { rx=%u max=%u rwin=%u jm=%u }",
- latest,
- ntohl(ackinfo.rxMTU), ntohl(ackinfo.maxMTU),
- ntohl(ackinfo.rwind), ntohl(ackinfo.jumbo_max));
-
- mtu = min(ntohl(ackinfo.rxMTU), ntohl(ackinfo.maxMTU));
-
- peer = call->peer;
- if (mtu < peer->maxdata) {
- spin_lock_bh(&peer->lock);
- peer->maxdata = mtu;
- peer->mtu = mtu + peer->hdrsize;
- spin_unlock_bh(&peer->lock);
- _net("Net MTU %u (maxdata %u)", peer->mtu, peer->maxdata);
- }
-}
-
-/*
- * process packets in the reception queue
- */
-static int rxrpc_process_rx_queue(struct rxrpc_call *call,
- u32 *_abort_code)
-{
- struct rxrpc_ackpacket ack;
- struct rxrpc_skb_priv *sp;
- struct sk_buff *skb;
- bool post_ACK;
- int latest;
- u32 hard, tx;
-
- _enter("");
-
-process_further:
- skb = skb_dequeue(&call->rx_queue);
- if (!skb)
- return -EAGAIN;
-
- rxrpc_see_skb(skb);
- _net("deferred skb %p", skb);
-
- sp = rxrpc_skb(skb);
-
- _debug("process %s [st %d]", rxrpc_pkts[sp->hdr.type], call->state);
-
- post_ACK = false;
-
- switch (sp->hdr.type) {
- /* data packets that wind up here have been received out of
- * order, need security processing or are jumbo packets */
- case RXRPC_PACKET_TYPE_DATA:
- _proto("OOSQ DATA %%%u { #%u }", sp->hdr.serial, sp->hdr.seq);
-
- /* secured packets must be verified and possibly decrypted */
- if (call->conn->security->verify_packet(call, skb,
- sp->hdr.seq,
- sp->hdr.cksum) < 0)
- goto protocol_error;
-
- rxrpc_insert_oos_packet(call, skb);
- goto process_further;
-
- /* partial ACK to process */
- case RXRPC_PACKET_TYPE_ACK:
- if (skb_copy_bits(skb, 0, &ack, sizeof(ack)) < 0) {
- _debug("extraction failure");
- goto protocol_error;
- }
- if (!skb_pull(skb, sizeof(ack)))
- BUG();
-
- latest = sp->hdr.serial;
- hard = ntohl(ack.firstPacket);
- tx = atomic_read(&call->sequence);
-
- _proto("Rx ACK %%%u { m=%hu f=#%u p=#%u s=%%%u r=%s n=%u }",
- latest,
- ntohs(ack.maxSkew),
- hard,
- ntohl(ack.previousPacket),
- ntohl(ack.serial),
- rxrpc_acks(ack.reason),
- ack.nAcks);
-
- rxrpc_extract_ackinfo(call, skb, latest, ack.nAcks);
-
- if (ack.reason == RXRPC_ACK_PING) {
- _proto("Rx ACK %%%u PING Request", latest);
- rxrpc_propose_ACK(call, RXRPC_ACK_PING_RESPONSE,
- skb->priority, sp->hdr.serial, true);
- }
-
- /* discard any out-of-order or duplicate ACKs */
- if (latest - call->acks_latest <= 0) {
- _debug("discard ACK %d <= %d",
- latest, call->acks_latest);
- goto discard;
- }
- call->acks_latest = latest;
-
- if (call->state != RXRPC_CALL_CLIENT_SEND_REQUEST &&
- call->state != RXRPC_CALL_CLIENT_AWAIT_REPLY &&
- call->state != RXRPC_CALL_SERVER_SEND_REPLY &&
- call->state != RXRPC_CALL_SERVER_AWAIT_ACK)
- goto discard;
-
- _debug("Tx=%d H=%u S=%d", tx, call->acks_hard, call->state);
-
- if (hard > 0) {
- if (hard - 1 > tx) {
- _debug("hard-ACK'd packet %d not transmitted"
- " (%d top)",
- hard - 1, tx);
- goto protocol_error;
- }
-
- if ((call->state == RXRPC_CALL_CLIENT_AWAIT_REPLY ||
- call->state == RXRPC_CALL_SERVER_AWAIT_ACK) &&
- hard > tx) {
- call->acks_hard = tx;
- goto all_acked;
- }
-
- smp_rmb();
- rxrpc_rotate_tx_window(call, hard - 1);
- }
-
- if (ack.nAcks > 0) {
- if (hard - 1 + ack.nAcks > tx) {
- _debug("soft-ACK'd packet %d+%d not"
- " transmitted (%d top)",
- hard - 1, ack.nAcks, tx);
- goto protocol_error;
- }
-
- if (rxrpc_process_soft_ACKs(call, &ack, skb) < 0)
- goto protocol_error;
- }
- goto discard;
-
- /* complete ACK to process */
- case RXRPC_PACKET_TYPE_ACKALL:
- goto all_acked;
-
- /* abort and busy are handled elsewhere */
- case RXRPC_PACKET_TYPE_BUSY:
- case RXRPC_PACKET_TYPE_ABORT:
- BUG();
-
- /* connection level events - also handled elsewhere */
- case RXRPC_PACKET_TYPE_CHALLENGE:
- case RXRPC_PACKET_TYPE_RESPONSE:
- case RXRPC_PACKET_TYPE_DEBUG:
- BUG();
- }
-
- /* if we've had a hard ACK that covers all the packets we've sent, then
- * that ends that phase of the operation */
-all_acked:
- write_lock_bh(&call->state_lock);
- _debug("ack all %d", call->state);
-
- switch (call->state) {
- case RXRPC_CALL_CLIENT_AWAIT_REPLY:
- call->state = RXRPC_CALL_CLIENT_RECV_REPLY;
- break;
- case RXRPC_CALL_SERVER_AWAIT_ACK:
- _debug("srv complete");
- __rxrpc_call_completed(call);
- post_ACK = true;
- break;
- case RXRPC_CALL_CLIENT_SEND_REQUEST:
- case RXRPC_CALL_SERVER_RECV_REQUEST:
- goto protocol_error_unlock; /* can't occur yet */
- default:
- write_unlock_bh(&call->state_lock);
- goto discard; /* assume packet left over from earlier phase */
- }
-
- write_unlock_bh(&call->state_lock);
-
- /* if all the packets we sent are hard-ACK'd, then we can discard
- * whatever we've got left */
- _debug("clear Tx %d",
- CIRC_CNT(call->acks_head, call->acks_tail, call->acks_winsz));
-
- del_timer_sync(&call->resend_timer);
- clear_bit(RXRPC_CALL_RUN_RTIMER, &call->flags);
- clear_bit(RXRPC_CALL_EV_RESEND_TIMER, &call->events);
-
- if (call->acks_window)
- rxrpc_zap_tx_window(call);
-
- if (post_ACK) {
- /* post the final ACK message for userspace to pick up */
- _debug("post ACK");
- skb->mark = RXRPC_SKB_MARK_FINAL_ACK;
- sp->call = call;
- rxrpc_get_call_for_skb(call, skb);
spin_lock_bh(&call->lock);
- if (rxrpc_queue_rcv_skb(call, skb, true, true) < 0)
- BUG();
- spin_unlock_bh(&call->lock);
- goto process_further;
- }
-discard:
- rxrpc_free_skb(skb);
- goto process_further;
+ /* 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) &&
+ (call->rxtx_annotations[ix] == RXRPC_TX_ANNO_RETRANS ||
+ call->rxtx_annotations[ix] == RXRPC_TX_ANNO_NAK))
+ call->rxtx_annotations[ix] = RXRPC_TX_ANNO_UNACK;
-protocol_error_unlock:
- write_unlock_bh(&call->state_lock);
-protocol_error:
- rxrpc_free_skb(skb);
- _leave(" = -EPROTO");
- return -EPROTO;
+ if (after(call->tx_hard_ack, seq))
+ seq = call->tx_hard_ack;
+ seq++;
+ } while (before_eq(seq, top));
+
+out_unlock:
+ spin_unlock_bh(&call->lock);
+ _leave("");
}
/*
- * post a message to the socket Rx queue for recvmsg() to pick up
- */
-static int rxrpc_post_message(struct rxrpc_call *call, u32 mark, u32 error,
- bool fatal)
-{
- struct rxrpc_skb_priv *sp;
- struct sk_buff *skb;
- int ret;
-
- _enter("{%d,%lx},%u,%u,%d",
- call->debug_id, call->flags, mark, error, fatal);
-
- /* remove timers and things for fatal messages */
- if (fatal) {
- del_timer_sync(&call->resend_timer);
- del_timer_sync(&call->ack_timer);
- clear_bit(RXRPC_CALL_RUN_RTIMER, &call->flags);
- }
-
- if (mark != RXRPC_SKB_MARK_NEW_CALL &&
- !test_bit(RXRPC_CALL_HAS_USERID, &call->flags)) {
- _leave("[no userid]");
- return 0;
- }
-
- if (!test_bit(RXRPC_CALL_TERMINAL_MSG, &call->flags)) {
- skb = alloc_skb(0, GFP_NOFS);
- if (!skb)
- return -ENOMEM;
-
- rxrpc_new_skb(skb);
-
- skb->mark = mark;
-
- sp = rxrpc_skb(skb);
- memset(sp, 0, sizeof(*sp));
- sp->error = error;
- sp->call = call;
- rxrpc_get_call_for_skb(call, skb);
-
- spin_lock_bh(&call->lock);
- ret = rxrpc_queue_rcv_skb(call, skb, true, fatal);
- spin_unlock_bh(&call->lock);
- BUG_ON(ret < 0);
- }
-
- return 0;
-}
-
-/*
- * Handle background processing of incoming call packets and ACK / abort
- * generation. A ref on the call is donated to us by whoever queued the work
- * item.
+ * Handle retransmission and deferred ACK/abort generation.
*/
void rxrpc_process_call(struct work_struct *work)
{
struct rxrpc_call *call =
container_of(work, struct rxrpc_call, processor);
- struct rxrpc_wire_header whdr;
- struct rxrpc_ackpacket ack;
- struct rxrpc_ackinfo ackinfo;
- struct msghdr msg;
- struct kvec iov[5];
- enum rxrpc_call_event genbit;
- unsigned long bits;
- __be32 data, pad;
- size_t len;
- bool requeue = false;
- int loop, nbit, ioc, ret, mtu;
- u32 serial, abort_code = RX_PROTOCOL_ERROR;
- u8 *acks = NULL;
+ unsigned long now;
rxrpc_see_call(call);
//printk("\n--------------------\n");
- _enter("{%d,%s,%lx} [%lu]",
- call->debug_id, rxrpc_call_states[call->state], call->events,
- (jiffies - call->creation_jif) / (HZ / 10));
+ _enter("{%d,%s,%lx}",
+ call->debug_id, rxrpc_call_states[call->state], call->events);
- if (call->state >= RXRPC_CALL_COMPLETE) {
- rxrpc_put_call(call, rxrpc_call_put);
- return;
+recheck_state:
+ if (test_and_clear_bit(RXRPC_CALL_EV_ABORT, &call->events)) {
+ rxrpc_send_call_packet(call, RXRPC_PACKET_TYPE_ABORT);
+ goto recheck_state;
}
- if (!call->conn)
- goto skip_msg_init;
-
- /* there's a good chance we're going to have to send a message, so set
- * one up in advance */
- msg.msg_name = &call->peer->srx.transport;
- msg.msg_namelen = call->peer->srx.transport_len;
- msg.msg_control = NULL;
- msg.msg_controllen = 0;
- msg.msg_flags = 0;
-
- whdr.epoch = htonl(call->conn->proto.epoch);
- whdr.cid = htonl(call->cid);
- whdr.callNumber = htonl(call->call_id);
- whdr.seq = 0;
- whdr.type = RXRPC_PACKET_TYPE_ACK;
- whdr.flags = call->conn->out_clientflag;
- whdr.userStatus = 0;
- whdr.securityIndex = call->conn->security_ix;
- whdr._rsvd = 0;
- whdr.serviceId = htons(call->service_id);
-
- memset(iov, 0, sizeof(iov));
- iov[0].iov_base = &whdr;
- iov[0].iov_len = sizeof(whdr);
-skip_msg_init:
-
- /* deal with events of a final nature */
- if (test_bit(RXRPC_CALL_EV_RCVD_ERROR, &call->events)) {
- enum rxrpc_skb_mark mark;
-
- clear_bit(RXRPC_CALL_EV_CONN_ABORT, &call->events);
- clear_bit(RXRPC_CALL_EV_REJECT_BUSY, &call->events);
- clear_bit(RXRPC_CALL_EV_ABORT, &call->events);
-
- if (call->completion == RXRPC_CALL_NETWORK_ERROR) {
- mark = RXRPC_SKB_MARK_NET_ERROR;
- _debug("post net error %d", call->error);
- } else {
- mark = RXRPC_SKB_MARK_LOCAL_ERROR;
- _debug("post net local error %d", call->error);
- }
-
- if (rxrpc_post_message(call, mark, call->error, true) < 0)
- goto no_mem;
- clear_bit(RXRPC_CALL_EV_RCVD_ERROR, &call->events);
- goto kill_ACKs;
+ if (call->state == RXRPC_CALL_COMPLETE) {
+ del_timer_sync(&call->timer);
+ goto out_put;
}
- if (test_bit(RXRPC_CALL_EV_CONN_ABORT, &call->events)) {
- ASSERTCMP(call->state, ==, RXRPC_CALL_COMPLETE);
-
- clear_bit(RXRPC_CALL_EV_REJECT_BUSY, &call->events);
- clear_bit(RXRPC_CALL_EV_ABORT, &call->events);
-
- _debug("post conn abort");
-
- if (rxrpc_post_message(call, RXRPC_SKB_MARK_LOCAL_ERROR,
- call->error, true) < 0)
- goto no_mem;
- clear_bit(RXRPC_CALL_EV_CONN_ABORT, &call->events);
- goto kill_ACKs;
- }
-
- if (test_bit(RXRPC_CALL_EV_REJECT_BUSY, &call->events)) {
- whdr.type = RXRPC_PACKET_TYPE_BUSY;
- genbit = RXRPC_CALL_EV_REJECT_BUSY;
- goto send_message;
- }
-
- if (test_bit(RXRPC_CALL_EV_ABORT, &call->events)) {
- ASSERTCMP(call->state, ==, RXRPC_CALL_COMPLETE);
-
- if (rxrpc_post_message(call, RXRPC_SKB_MARK_LOCAL_ERROR,
- call->error, true) < 0)
- goto no_mem;
- whdr.type = RXRPC_PACKET_TYPE_ABORT;
- data = htonl(call->abort_code);
- iov[1].iov_base = &data;
- iov[1].iov_len = sizeof(data);
- genbit = RXRPC_CALL_EV_ABORT;
- goto send_message;
- }
-
- if (test_bit(RXRPC_CALL_EV_ACK_FINAL, &call->events)) {
- genbit = RXRPC_CALL_EV_ACK_FINAL;
-
- ack.bufferSpace = htons(8);
- ack.maxSkew = 0;
- ack.serial = 0;
- ack.reason = RXRPC_ACK_IDLE;
- ack.nAcks = 0;
- call->ackr_reason = 0;
-
- spin_lock_bh(&call->lock);
- ack.serial = htonl(call->ackr_serial);
- ack.previousPacket = htonl(call->ackr_prev_seq);
- ack.firstPacket = htonl(call->rx_data_eaten + 1);
- spin_unlock_bh(&call->lock);
-
- pad = 0;
-
- iov[1].iov_base = &ack;
- iov[1].iov_len = sizeof(ack);
- iov[2].iov_base = &pad;
- iov[2].iov_len = 3;
- iov[3].iov_base = &ackinfo;
- iov[3].iov_len = sizeof(ackinfo);
- goto send_ACK;
- }
-
- if (call->events & ((1 << RXRPC_CALL_EV_RCVD_BUSY) |
- (1 << RXRPC_CALL_EV_RCVD_ABORT))
- ) {
- u32 mark;
-
- if (test_bit(RXRPC_CALL_EV_RCVD_ABORT, &call->events))
- mark = RXRPC_SKB_MARK_REMOTE_ABORT;
- else
- mark = RXRPC_SKB_MARK_BUSY;
-
- _debug("post abort/busy");
- rxrpc_clear_tx_window(call);
- if (rxrpc_post_message(call, mark, ECONNABORTED, true) < 0)
- goto no_mem;
-
- clear_bit(RXRPC_CALL_EV_RCVD_BUSY, &call->events);
- clear_bit(RXRPC_CALL_EV_RCVD_ABORT, &call->events);
- goto kill_ACKs;
- }
-
- if (test_and_clear_bit(RXRPC_CALL_EV_RCVD_ACKALL, &call->events)) {
- _debug("do implicit ackall");
- rxrpc_clear_tx_window(call);
- }
-
- if (test_bit(RXRPC_CALL_EV_LIFE_TIMER, &call->events)) {
+ now = jiffies;
+ if (time_after_eq(now, call->expire_at)) {
rxrpc_abort_call("EXP", call, 0, RX_CALL_TIMEOUT, ETIME);
-
- _debug("post timeout");
- if (rxrpc_post_message(call, RXRPC_SKB_MARK_LOCAL_ERROR,
- ETIME, true) < 0)
- goto no_mem;
-
- clear_bit(RXRPC_CALL_EV_LIFE_TIMER, &call->events);
- goto kill_ACKs;
+ set_bit(RXRPC_CALL_EV_ABORT, &call->events);
}
- /* deal with assorted inbound messages */
- if (!skb_queue_empty(&call->rx_queue)) {
- ret = rxrpc_process_rx_queue(call, &abort_code);
- switch (ret) {
- case 0:
- case -EAGAIN:
- break;
- case -ENOMEM:
- goto no_mem;
- case -EKEYEXPIRED:
- case -EKEYREJECTED:
- case -EPROTO:
- rxrpc_abort_call("PRO", call, 0, abort_code, -ret);
- goto kill_ACKs;
+ if (test_and_clear_bit(RXRPC_CALL_EV_ACK, &call->events) ||
+ time_after_eq(now, call->ack_at)) {
+ call->ack_at = call->expire_at;
+ if (call->ackr_reason) {
+ rxrpc_send_call_packet(call, RXRPC_PACKET_TYPE_ACK);
+ goto recheck_state;
}
}
- /* handle resending */
- if (test_and_clear_bit(RXRPC_CALL_EV_RESEND_TIMER, &call->events))
- rxrpc_resend_timer(call);
- if (test_and_clear_bit(RXRPC_CALL_EV_RESEND, &call->events))
+ if (test_and_clear_bit(RXRPC_CALL_EV_RESEND, &call->events) ||
+ time_after_eq(now, call->resend_at)) {
rxrpc_resend(call);
-
- /* consider sending an ordinary ACK */
- if (test_bit(RXRPC_CALL_EV_ACK, &call->events)) {
- _debug("send ACK: window: %d - %d { %lx }",
- call->rx_data_eaten, call->ackr_win_top,
- call->ackr_window[0]);
-
- if (call->state > RXRPC_CALL_SERVER_ACK_REQUEST &&
- call->ackr_reason != RXRPC_ACK_PING_RESPONSE) {
- /* ACK by sending reply DATA packet in this state */
- clear_bit(RXRPC_CALL_EV_ACK, &call->events);
- goto maybe_reschedule;
- }
-
- genbit = RXRPC_CALL_EV_ACK;
-
- acks = kzalloc(call->ackr_win_top - call->rx_data_eaten,
- GFP_NOFS);
- if (!acks)
- goto no_mem;
-
- //hdr.flags = RXRPC_SLOW_START_OK;
- ack.bufferSpace = htons(8);
- ack.maxSkew = 0;
-
- spin_lock_bh(&call->lock);
- ack.reason = call->ackr_reason;
- ack.serial = htonl(call->ackr_serial);
- ack.previousPacket = htonl(call->ackr_prev_seq);
- ack.firstPacket = htonl(call->rx_data_eaten + 1);
-
- ack.nAcks = 0;
- for (loop = 0; loop < RXRPC_ACKR_WINDOW_ASZ; loop++) {
- nbit = loop * BITS_PER_LONG;
- for (bits = call->ackr_window[loop]; bits; bits >>= 1
- ) {
- _debug("- l=%d n=%d b=%lx", loop, nbit, bits);
- if (bits & 1) {
- acks[nbit] = RXRPC_ACK_TYPE_ACK;
- ack.nAcks = nbit + 1;
- }
- nbit++;
- }
- }
- call->ackr_reason = 0;
- spin_unlock_bh(&call->lock);
-
- pad = 0;
-
- iov[1].iov_base = &ack;
- iov[1].iov_len = sizeof(ack);
- iov[2].iov_base = acks;
- iov[2].iov_len = ack.nAcks;
- iov[3].iov_base = &pad;
- iov[3].iov_len = 3;
- iov[4].iov_base = &ackinfo;
- iov[4].iov_len = sizeof(ackinfo);
-
- switch (ack.reason) {
- case RXRPC_ACK_REQUESTED:
- case RXRPC_ACK_DUPLICATE:
- case RXRPC_ACK_OUT_OF_SEQUENCE:
- case RXRPC_ACK_EXCEEDS_WINDOW:
- case RXRPC_ACK_NOSPACE:
- case RXRPC_ACK_PING:
- case RXRPC_ACK_PING_RESPONSE:
- goto send_ACK_with_skew;
- case RXRPC_ACK_DELAY:
- case RXRPC_ACK_IDLE:
- goto send_ACK;
- }
+ goto recheck_state;
}
- /* handle completion of security negotiations on an incoming
- * connection */
- if (test_and_clear_bit(RXRPC_CALL_EV_SECURED, &call->events)) {
- _debug("secured");
- spin_lock_bh(&call->lock);
-
- if (call->state == RXRPC_CALL_SERVER_SECURING) {
- struct rxrpc_sock *rx;
- _debug("securing");
- rcu_read_lock();
- rx = rcu_dereference(call->socket);
- if (rx) {
- write_lock(&rx->call_lock);
- if (!test_bit(RXRPC_CALL_RELEASED, &call->flags)) {
- _debug("not released");
- call->state = RXRPC_CALL_SERVER_ACCEPTING;
- list_move_tail(&call->accept_link,
- &rx->acceptq);
- }
- write_unlock(&rx->call_lock);
- }
- rcu_read_unlock();
- read_lock(&call->state_lock);
- if (call->state < RXRPC_CALL_COMPLETE)
- set_bit(RXRPC_CALL_EV_POST_ACCEPT, &call->events);
- read_unlock(&call->state_lock);
- }
-
- spin_unlock_bh(&call->lock);
- if (!test_bit(RXRPC_CALL_EV_POST_ACCEPT, &call->events))
- goto maybe_reschedule;
- }
-
- /* post a notification of an acceptable connection to the app */
- if (test_bit(RXRPC_CALL_EV_POST_ACCEPT, &call->events)) {
- _debug("post accept");
- if (rxrpc_post_message(call, RXRPC_SKB_MARK_NEW_CALL,
- 0, false) < 0)
- goto no_mem;
- clear_bit(RXRPC_CALL_EV_POST_ACCEPT, &call->events);
- goto maybe_reschedule;
- }
-
- /* handle incoming call acceptance */
- if (test_and_clear_bit(RXRPC_CALL_EV_ACCEPTED, &call->events)) {
- _debug("accepted");
- ASSERTCMP(call->rx_data_post, ==, 0);
- call->rx_data_post = 1;
- read_lock_bh(&call->state_lock);
- if (call->state < RXRPC_CALL_COMPLETE)
- set_bit(RXRPC_CALL_EV_DRAIN_RX_OOS, &call->events);
- read_unlock_bh(&call->state_lock);
- }
-
- /* drain the out of sequence received packet queue into the packet Rx
- * queue */
- if (test_and_clear_bit(RXRPC_CALL_EV_DRAIN_RX_OOS, &call->events)) {
- while (call->rx_data_post == call->rx_first_oos)
- if (rxrpc_drain_rx_oos_queue(call) < 0)
- break;
- goto maybe_reschedule;
- }
+ rxrpc_set_timer(call);
/* other events may have been raised since we started checking */
- goto maybe_reschedule;
-
-send_ACK_with_skew:
- ack.maxSkew = htons(call->ackr_skew);
-send_ACK:
- mtu = call->peer->if_mtu;
- mtu -= call->peer->hdrsize;
- ackinfo.maxMTU = htonl(mtu);
- ackinfo.rwind = htonl(rxrpc_rx_window_size);
-
- /* permit the peer to send us jumbo packets if it wants to */
- ackinfo.rxMTU = htonl(rxrpc_rx_mtu);
- ackinfo.jumbo_max = htonl(rxrpc_rx_jumbo_max);
-
- serial = atomic_inc_return(&call->conn->serial);
- whdr.serial = htonl(serial);
- _proto("Tx ACK %%%u { m=%hu f=#%u p=#%u s=%%%u r=%s n=%u }",
- serial,
- ntohs(ack.maxSkew),
- ntohl(ack.firstPacket),
- ntohl(ack.previousPacket),
- ntohl(ack.serial),
- rxrpc_acks(ack.reason),
- ack.nAcks);
-
- del_timer_sync(&call->ack_timer);
- if (ack.nAcks > 0)
- set_bit(RXRPC_CALL_TX_SOFT_ACK, &call->flags);
- goto send_message_2;
-
-send_message:
- _debug("send message");
-
- serial = atomic_inc_return(&call->conn->serial);
- whdr.serial = htonl(serial);
- _proto("Tx %s %%%u", rxrpc_pkts[whdr.type], serial);
-send_message_2:
-
- len = iov[0].iov_len;
- ioc = 1;
- if (iov[4].iov_len) {
- ioc = 5;
- len += iov[4].iov_len;
- len += iov[3].iov_len;
- len += iov[2].iov_len;
- len += iov[1].iov_len;
- } else if (iov[3].iov_len) {
- ioc = 4;
- len += iov[3].iov_len;
- len += iov[2].iov_len;
- len += iov[1].iov_len;
- } else if (iov[2].iov_len) {
- ioc = 3;
- len += iov[2].iov_len;
- len += iov[1].iov_len;
- } else if (iov[1].iov_len) {
- ioc = 2;
- len += iov[1].iov_len;
- }
-
- ret = kernel_sendmsg(call->conn->params.local->socket,
- &msg, iov, ioc, len);
- if (ret < 0) {
- _debug("sendmsg failed: %d", ret);
- if (call->state < RXRPC_CALL_COMPLETE)
- requeue = true;
- goto error;
- }
-
- switch (genbit) {
- case RXRPC_CALL_EV_ABORT:
- clear_bit(genbit, &call->events);
- clear_bit(RXRPC_CALL_EV_RCVD_ABORT, &call->events);
- goto kill_ACKs;
-
- case RXRPC_CALL_EV_ACK_FINAL:
- rxrpc_call_completed(call);
- goto kill_ACKs;
-
- default:
- clear_bit(genbit, &call->events);
- switch (call->state) {
- case RXRPC_CALL_CLIENT_AWAIT_REPLY:
- case RXRPC_CALL_CLIENT_RECV_REPLY:
- case RXRPC_CALL_SERVER_RECV_REQUEST:
- case RXRPC_CALL_SERVER_ACK_REQUEST:
- _debug("start ACK timer");
- rxrpc_propose_ACK(call, RXRPC_ACK_DELAY,
- call->ackr_skew, call->ackr_serial,
- false);
- default:
- break;
- }
- goto maybe_reschedule;
- }
-
-kill_ACKs:
- del_timer_sync(&call->ack_timer);
- clear_bit(RXRPC_CALL_EV_ACK, &call->events);
-
-maybe_reschedule:
- if (call->events || !skb_queue_empty(&call->rx_queue)) {
- if (call->state < RXRPC_CALL_COMPLETE)
- requeue = true;
- }
-
-error:
- kfree(acks);
-
- if ((requeue || call->events) && !work_pending(&call->processor)) {
- _debug("jumpstart %x", call->conn->proto.cid);
+ if (call->events && call->state < RXRPC_CALL_COMPLETE) {
__rxrpc_queue_call(call);
- } else {
- rxrpc_put_call(call, rxrpc_call_put);
+ goto out;
}
+out_put:
+ rxrpc_put_call(call, rxrpc_call_put);
+out:
_leave("");
- return;
-
-no_mem:
- _debug("out of memory");
- goto maybe_reschedule;
}