diff options
Diffstat (limited to 'net/rxrpc/input.c')
| -rw-r--r-- | net/rxrpc/input.c | 1943 |
1 files changed, 895 insertions, 1048 deletions
diff --git a/net/rxrpc/input.c b/net/rxrpc/input.c index 299ac98e9754..24aceb183c2c 100644 --- a/net/rxrpc/input.c +++ b/net/rxrpc/input.c @@ -1,114 +1,94 @@ // SPDX-License-Identifier: GPL-2.0-or-later -/* RxRPC packet reception +/* Processing of received RxRPC packets * - * Copyright (C) 2007, 2016 Red Hat, Inc. All Rights Reserved. + * Copyright (C) 2020 Red Hat, Inc. All Rights Reserved. * Written by David Howells (dhowells@redhat.com) */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt -#include <linux/module.h> -#include <linux/net.h> -#include <linux/skbuff.h> -#include <linux/errqueue.h> -#include <linux/udp.h> -#include <linux/in.h> -#include <linux/in6.h> -#include <linux/icmp.h> -#include <linux/gfp.h> -#include <net/sock.h> -#include <net/af_rxrpc.h> -#include <net/ip.h> -#include <net/udp.h> -#include <net/net_namespace.h> #include "ar-internal.h" -static void rxrpc_proto_abort(const char *why, - struct rxrpc_call *call, rxrpc_seq_t seq) +/* Override priority when generating ACKs for received DATA */ +static const u8 rxrpc_ack_priority[RXRPC_ACK__INVALID] = { + [RXRPC_ACK_IDLE] = 1, + [RXRPC_ACK_DELAY] = 2, + [RXRPC_ACK_REQUESTED] = 3, + [RXRPC_ACK_DUPLICATE] = 4, + [RXRPC_ACK_EXCEEDS_WINDOW] = 5, + [RXRPC_ACK_NOSPACE] = 6, + [RXRPC_ACK_OUT_OF_SEQUENCE] = 7, +}; + +static void rxrpc_proto_abort(struct rxrpc_call *call, rxrpc_seq_t seq, + enum rxrpc_abort_reason why) { - if (rxrpc_abort_call(why, call, seq, RX_PROTOCOL_ERROR, -EBADMSG)) { - set_bit(RXRPC_CALL_EV_ABORT, &call->events); - rxrpc_queue_call(call); - } + rxrpc_abort_call(call, seq, RX_PROTOCOL_ERROR, -EBADMSG, why); } /* - * Do TCP-style congestion management [RFC 5681]. + * Do TCP-style congestion management [RFC5681]. */ static void rxrpc_congestion_management(struct rxrpc_call *call, - struct sk_buff *skb, - struct rxrpc_ack_summary *summary, - rxrpc_serial_t acked_serial) + struct rxrpc_ack_summary *summary) { - enum rxrpc_congest_change change = rxrpc_cong_no_change; - unsigned int cumulative_acks = call->cong_cumul_acks; - unsigned int cwnd = call->cong_cwnd; - bool resend = false; - - summary->flight_size = - (call->tx_top - call->tx_hard_ack) - summary->nr_acks; + summary->change = rxrpc_cong_no_change; + summary->in_flight = rxrpc_tx_in_flight(call); if (test_and_clear_bit(RXRPC_CALL_RETRANS_TIMEOUT, &call->flags)) { summary->retrans_timeo = true; - call->cong_ssthresh = max_t(unsigned int, - summary->flight_size / 2, 2); - cwnd = 1; - if (cwnd >= call->cong_ssthresh && - call->cong_mode == RXRPC_CALL_SLOW_START) { - call->cong_mode = RXRPC_CALL_CONGEST_AVOIDANCE; - call->cong_tstamp = skb->tstamp; - cumulative_acks = 0; + call->cong_ssthresh = umax(summary->in_flight / 2, 2); + call->cong_cwnd = 1; + if (call->cong_cwnd >= call->cong_ssthresh && + call->cong_ca_state == RXRPC_CA_SLOW_START) { + call->cong_ca_state = RXRPC_CA_CONGEST_AVOIDANCE; + call->cong_tstamp = call->acks_latest_ts; + call->cong_cumul_acks = 0; } } - cumulative_acks += summary->nr_new_acks; - cumulative_acks += summary->nr_rot_new_acks; - if (cumulative_acks > 255) - cumulative_acks = 255; - - summary->mode = call->cong_mode; - summary->cwnd = call->cong_cwnd; - summary->ssthresh = call->cong_ssthresh; - summary->cumulative_acks = cumulative_acks; - summary->dup_acks = call->cong_dup_acks; + call->cong_cumul_acks += summary->nr_new_sacks; + call->cong_cumul_acks += summary->nr_new_hacks; + if (call->cong_cumul_acks > 255) + call->cong_cumul_acks = 255; - switch (call->cong_mode) { - case RXRPC_CALL_SLOW_START: - if (summary->nr_nacks > 0) + switch (call->cong_ca_state) { + case RXRPC_CA_SLOW_START: + if (call->acks_nr_snacks > 0) goto packet_loss_detected; - if (summary->cumulative_acks > 0) - cwnd += 1; - if (cwnd >= call->cong_ssthresh) { - call->cong_mode = RXRPC_CALL_CONGEST_AVOIDANCE; - call->cong_tstamp = skb->tstamp; + if (call->cong_cumul_acks > 0) + call->cong_cwnd += 1; + if (call->cong_cwnd >= call->cong_ssthresh) { + call->cong_ca_state = RXRPC_CA_CONGEST_AVOIDANCE; + call->cong_tstamp = call->acks_latest_ts; } goto out; - case RXRPC_CALL_CONGEST_AVOIDANCE: - if (summary->nr_nacks > 0) + case RXRPC_CA_CONGEST_AVOIDANCE: + if (call->acks_nr_snacks > 0) goto packet_loss_detected; /* 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_count == 0) + if (call->rtt_count == 0) goto out; - if (ktime_before(skb->tstamp, + if (ktime_before(call->acks_latest_ts, ktime_add_us(call->cong_tstamp, - call->peer->srtt_us >> 3))) + call->srtt_us >> 3))) goto out_no_clear_ca; - change = rxrpc_cong_rtt_window_end; - call->cong_tstamp = skb->tstamp; - if (cumulative_acks >= cwnd) - cwnd++; + summary->change = rxrpc_cong_rtt_window_end; + call->cong_tstamp = call->acks_latest_ts; + if (call->cong_cumul_acks >= call->cong_cwnd) + call->cong_cwnd++; goto out; - case RXRPC_CALL_PACKET_LOSS: - if (summary->nr_nacks == 0) + case RXRPC_CA_PACKET_LOSS: + if (call->acks_nr_snacks == 0) goto resume_normality; - if (summary->new_low_nack) { - change = rxrpc_cong_new_low_nack; + if (summary->new_low_snack) { + summary->change = rxrpc_cong_new_low_nack; call->cong_dup_acks = 1; if (call->cong_extra > 1) call->cong_extra = 1; @@ -119,31 +99,35 @@ static void rxrpc_congestion_management(struct rxrpc_call *call, if (call->cong_dup_acks < 3) goto send_extra_data; - change = rxrpc_cong_begin_retransmission; - call->cong_mode = RXRPC_CALL_FAST_RETRANSMIT; - call->cong_ssthresh = max_t(unsigned int, - summary->flight_size / 2, 2); - cwnd = call->cong_ssthresh + 3; + summary->change = rxrpc_cong_begin_retransmission; + call->cong_ca_state = RXRPC_CA_FAST_RETRANSMIT; + call->cong_ssthresh = umax(summary->in_flight / 2, 2); + call->cong_cwnd = call->cong_ssthresh + 3; call->cong_extra = 0; call->cong_dup_acks = 0; - resend = true; + summary->need_retransmit = true; + summary->in_fast_or_rto_recovery = true; goto out; - case RXRPC_CALL_FAST_RETRANSMIT: - if (!summary->new_low_nack) { - if (summary->nr_new_acks == 0) - cwnd += 1; + case RXRPC_CA_FAST_RETRANSMIT: + rxrpc_tlp_init(call); + summary->in_fast_or_rto_recovery = true; + if (!summary->new_low_snack) { + if (summary->nr_new_sacks == 0) + call->cong_cwnd += 1; call->cong_dup_acks++; if (call->cong_dup_acks == 2) { - change = rxrpc_cong_retransmit_again; + summary->change = rxrpc_cong_retransmit_again; call->cong_dup_acks = 0; - resend = true; + summary->need_retransmit = true; } } else { - change = rxrpc_cong_progress; - cwnd = call->cong_ssthresh; - if (summary->nr_nacks == 0) + summary->change = rxrpc_cong_progress; + call->cong_cwnd = call->cong_ssthresh; + if (call->acks_nr_snacks == 0) { + summary->exiting_fast_or_rto_recovery = true; goto resume_normality; + } } goto out; @@ -153,29 +137,25 @@ static void rxrpc_congestion_management(struct rxrpc_call *call, } resume_normality: - change = rxrpc_cong_cleared_nacks; + summary->change = rxrpc_cong_cleared_nacks; call->cong_dup_acks = 0; call->cong_extra = 0; - call->cong_tstamp = skb->tstamp; - if (cwnd < call->cong_ssthresh) - call->cong_mode = RXRPC_CALL_SLOW_START; + call->cong_tstamp = call->acks_latest_ts; + if (call->cong_cwnd < call->cong_ssthresh) + call->cong_ca_state = RXRPC_CA_SLOW_START; else - call->cong_mode = RXRPC_CALL_CONGEST_AVOIDANCE; + call->cong_ca_state = RXRPC_CA_CONGEST_AVOIDANCE; out: - cumulative_acks = 0; + call->cong_cumul_acks = 0; out_no_clear_ca: - if (cwnd >= RXRPC_RXTX_BUFF_SIZE - 1) - cwnd = RXRPC_RXTX_BUFF_SIZE - 1; - call->cong_cwnd = cwnd; - call->cong_cumul_acks = cumulative_acks; - trace_rxrpc_congest(call, summary, acked_serial, change); - if (resend && !test_and_set_bit(RXRPC_CALL_EV_RESEND, &call->events)) - rxrpc_queue_call(call); + if (call->cong_cwnd >= RXRPC_TX_MAX_WINDOW) + call->cong_cwnd = RXRPC_TX_MAX_WINDOW; + trace_rxrpc_congest(call, summary); return; packet_loss_detected: - change = rxrpc_cong_saw_nack; - call->cong_mode = RXRPC_CALL_PACKET_LOSS; + summary->change = rxrpc_cong_saw_nack; + call->cong_ca_state = RXRPC_CA_PACKET_LOSS; call->cong_dup_acks = 0; goto send_extra_data; @@ -183,9 +163,8 @@ send_extra_data: /* Send some previously unsent DATA if we have some to advance the ACK * state. */ - if (call->rxtx_annotations[call->tx_top & RXRPC_RXTX_BUFF_MASK] & - RXRPC_TX_ANNO_LAST || - summary->nr_acks != call->tx_top - call->tx_hard_ack) { + if (test_bit(RXRPC_CALL_TX_LAST, &call->flags) || + call->acks_nr_sacks != call->tx_top - call->tx_bottom) { call->cong_extra++; wake_up(&call->waitq); } @@ -193,58 +172,169 @@ send_extra_data: } /* + * Degrade the congestion window if we haven't transmitted a packet for >1RTT. + */ +void rxrpc_congestion_degrade(struct rxrpc_call *call) +{ + ktime_t rtt, now, time_since; + + if (call->cong_ca_state != RXRPC_CA_SLOW_START && + call->cong_ca_state != RXRPC_CA_CONGEST_AVOIDANCE) + return; + if (__rxrpc_call_state(call) == RXRPC_CALL_CLIENT_AWAIT_REPLY) + return; + + rtt = ns_to_ktime(call->srtt_us * (NSEC_PER_USEC / 8)); + now = ktime_get_real(); + time_since = ktime_sub(now, call->tx_last_sent); + if (ktime_before(time_since, rtt)) + return; + + trace_rxrpc_reset_cwnd(call, time_since, rtt); + rxrpc_inc_stat(call->rxnet, stat_tx_data_cwnd_reset); + call->tx_last_sent = now; + call->cong_ca_state = RXRPC_CA_SLOW_START; + call->cong_ssthresh = umax(call->cong_ssthresh, call->cong_cwnd * 3 / 4); + call->cong_cwnd = umax(call->cong_cwnd / 2, RXRPC_MIN_CWND); +} + +/* + * Add an RTT sample derived from an ACK'd DATA packet. + */ +static void rxrpc_add_data_rtt_sample(struct rxrpc_call *call, + struct rxrpc_ack_summary *summary, + struct rxrpc_txqueue *tq, + int ix) +{ + ktime_t xmit_ts = ktime_add_us(tq->xmit_ts_base, tq->segment_xmit_ts[ix]); + + rxrpc_call_add_rtt(call, rxrpc_rtt_rx_data_ack, -1, + summary->acked_serial, summary->ack_serial, + xmit_ts, call->acks_latest_ts); + __clear_bit(ix, &tq->rtt_samples); /* Prevent repeat RTT sample */ +} + +/* * Apply a hard ACK by advancing the Tx window. */ static bool rxrpc_rotate_tx_window(struct rxrpc_call *call, rxrpc_seq_t to, struct rxrpc_ack_summary *summary) { - struct sk_buff *skb, *list = NULL; - bool rot_last = false; - int ix; - u8 annotation; + struct rxrpc_txqueue *tq = call->tx_queue; + rxrpc_seq_t seq = call->tx_bottom + 1; + bool rot_last = false, trace = false; + + _enter("%x,%x", call->tx_bottom, to); + + trace_rxrpc_tx_rotate(call, seq, to); + trace_rxrpc_tq(call, tq, seq, rxrpc_tq_rotate); - if (call->acks_lowest_nak == call->tx_hard_ack) { + if (call->acks_lowest_nak == call->tx_bottom) { call->acks_lowest_nak = to; - } else if (before_eq(call->acks_lowest_nak, to)) { - summary->new_low_nack = true; + } else if (after(to, call->acks_lowest_nak)) { + summary->new_low_snack = true; call->acks_lowest_nak = to; } - spin_lock(&call->lock); + /* We may have a left over fully-consumed buffer at the front that we + * couldn't drop before (rotate_and_keep below). + */ + if (seq == call->tx_qbase + RXRPC_NR_TXQUEUE) { + call->tx_qbase += RXRPC_NR_TXQUEUE; + call->tx_queue = tq->next; + trace_rxrpc_tq(call, tq, seq, rxrpc_tq_rotate_and_free); + kfree(tq); + tq = call->tx_queue; + } - while (before(call->tx_hard_ack, to)) { - call->tx_hard_ack++; - ix = call->tx_hard_ack & RXRPC_RXTX_BUFF_MASK; - skb = call->rxtx_buffer[ix]; - annotation = call->rxtx_annotations[ix]; - rxrpc_see_skb(skb, rxrpc_skb_rotated); - call->rxtx_buffer[ix] = NULL; - call->rxtx_annotations[ix] = 0; - skb->next = list; - list = skb; + do { + unsigned int ix = seq - call->tx_qbase; - if (annotation & RXRPC_TX_ANNO_LAST) { + _debug("tq=%x seq=%x i=%d f=%x", tq->qbase, seq, ix, tq->bufs[ix]->flags); + if (tq->bufs[ix]->flags & RXRPC_LAST_PACKET) { set_bit(RXRPC_CALL_TX_LAST, &call->flags); rot_last = true; } - if ((annotation & RXRPC_TX_ANNO_MASK) != RXRPC_TX_ANNO_ACK) - summary->nr_rot_new_acks++; - } - spin_unlock(&call->lock); + if (summary->acked_serial == tq->segment_serial[ix] && + test_bit(ix, &tq->rtt_samples)) + rxrpc_add_data_rtt_sample(call, summary, tq, ix); + + if (ix == tq->nr_reported_acks) { + /* Packet directly hard ACK'd. */ + tq->nr_reported_acks++; + rxrpc_input_rack_one(call, summary, tq, ix); + if (seq == call->tlp_seq) + summary->tlp_probe_acked = true; + summary->nr_new_hacks++; + __set_bit(ix, &tq->segment_acked); + trace_rxrpc_rotate(call, tq, summary, seq, rxrpc_rotate_trace_hack); + } else if (test_bit(ix, &tq->segment_acked)) { + /* Soft ACK -> hard ACK. */ + call->acks_nr_sacks--; + trace_rxrpc_rotate(call, tq, summary, seq, rxrpc_rotate_trace_sack); + } else { + /* Soft NAK -> hard ACK. */ + call->acks_nr_snacks--; + rxrpc_input_rack_one(call, summary, tq, ix); + if (seq == call->tlp_seq) + summary->tlp_probe_acked = true; + summary->nr_new_hacks++; + __set_bit(ix, &tq->segment_acked); + trace_rxrpc_rotate(call, tq, summary, seq, rxrpc_rotate_trace_snak); + } - trace_rxrpc_transmit(call, (rot_last ? - rxrpc_transmit_rotate_last : - rxrpc_transmit_rotate)); - wake_up(&call->waitq); + call->tx_nr_sent--; + if (__test_and_clear_bit(ix, &tq->segment_lost)) + call->tx_nr_lost--; + if (__test_and_clear_bit(ix, &tq->segment_retransmitted)) + call->tx_nr_resent--; + __clear_bit(ix, &tq->ever_retransmitted); + + rxrpc_put_txbuf(tq->bufs[ix], rxrpc_txbuf_put_rotated); + tq->bufs[ix] = NULL; + + WRITE_ONCE(call->tx_bottom, seq); + trace_rxrpc_txqueue(call, (rot_last ? + rxrpc_txqueue_rotate_last : + rxrpc_txqueue_rotate)); + + seq++; + trace = true; + if (!(seq & RXRPC_TXQ_MASK)) { + trace_rxrpc_rack_update(call, summary); + trace = false; + prefetch(tq->next); + if (tq != call->tx_qtail) { + call->tx_qbase += RXRPC_NR_TXQUEUE; + call->tx_queue = tq->next; + trace_rxrpc_tq(call, tq, seq, rxrpc_tq_rotate_and_free); + kfree(tq); + tq = call->tx_queue; + } else { + trace_rxrpc_tq(call, tq, seq, rxrpc_tq_rotate_and_keep); + tq = NULL; + break; + } + } + + } while (before_eq(seq, to)); - while (list) { - skb = list; - list = skb->next; - skb_mark_not_on_list(skb); - rxrpc_free_skb(skb, rxrpc_skb_freed); + if (trace) + trace_rxrpc_rack_update(call, summary); + + if (rot_last) { + set_bit(RXRPC_CALL_TX_ALL_ACKED, &call->flags); + if (tq) { + trace_rxrpc_tq(call, tq, seq, rxrpc_tq_rotate_and_free); + kfree(tq); + call->tx_queue = NULL; + } } + _debug("%x,%x,%x,%d", to, call->tx_bottom, call->tx_top, rot_last); + + wake_up(&call->waitq); return rot_last; } @@ -254,47 +344,39 @@ static bool rxrpc_rotate_tx_window(struct rxrpc_call *call, rxrpc_seq_t to, * This occurs when we get an ACKALL packet, the first DATA packet of a reply, * or a final ACK packet. */ -static bool rxrpc_end_tx_phase(struct rxrpc_call *call, bool reply_begun, - const char *abort_why) +static void rxrpc_end_tx_phase(struct rxrpc_call *call, bool reply_begun, + enum rxrpc_abort_reason abort_why) { - unsigned int state; - ASSERT(test_bit(RXRPC_CALL_TX_LAST, &call->flags)); - write_lock(&call->state_lock); + call->rack_timer_mode = RXRPC_CALL_RACKTIMER_OFF; + call->rack_timo_at = KTIME_MAX; + trace_rxrpc_rack_timer(call, 0, false); + trace_rxrpc_timer_can(call, rxrpc_timer_trace_rack_off + call->rack_timer_mode); - state = call->state; - switch (state) { + switch (__rxrpc_call_state(call)) { case RXRPC_CALL_CLIENT_SEND_REQUEST: case RXRPC_CALL_CLIENT_AWAIT_REPLY: - if (reply_begun) - call->state = state = RXRPC_CALL_CLIENT_RECV_REPLY; - else - call->state = state = RXRPC_CALL_CLIENT_AWAIT_REPLY; + if (reply_begun) { + rxrpc_set_call_state(call, RXRPC_CALL_CLIENT_RECV_REPLY); + trace_rxrpc_txqueue(call, rxrpc_txqueue_end); + break; + } + + rxrpc_set_call_state(call, RXRPC_CALL_CLIENT_AWAIT_REPLY); + trace_rxrpc_txqueue(call, rxrpc_txqueue_await_reply); break; case RXRPC_CALL_SERVER_AWAIT_ACK: - __rxrpc_call_completed(call); - state = call->state; + rxrpc_call_completed(call); + trace_rxrpc_txqueue(call, rxrpc_txqueue_end); break; default: - goto bad_state; + kdebug("end_tx %s", rxrpc_call_states[__rxrpc_call_state(call)]); + rxrpc_proto_abort(call, call->tx_top, abort_why); + break; } - - write_unlock(&call->state_lock); - if (state == RXRPC_CALL_CLIENT_AWAIT_REPLY) - trace_rxrpc_transmit(call, rxrpc_transmit_await_reply); - else - trace_rxrpc_transmit(call, rxrpc_transmit_end); - _leave(" = ok"); - return true; - -bad_state: - write_unlock(&call->state_lock); - kdebug("end_tx %s", rxrpc_call_states[call->state]); - rxrpc_proto_abort(abort_why, call, call->tx_top); - return false; } /* @@ -303,453 +385,568 @@ bad_state: static bool rxrpc_receiving_reply(struct rxrpc_call *call) { struct rxrpc_ack_summary summary = { 0 }; - unsigned long now, timo; rxrpc_seq_t top = READ_ONCE(call->tx_top); if (call->ackr_reason) { - spin_lock_bh(&call->lock); - call->ackr_reason = 0; - spin_unlock_bh(&call->lock); - now = jiffies; - timo = now + MAX_JIFFY_OFFSET; - WRITE_ONCE(call->resend_at, timo); - WRITE_ONCE(call->ack_at, timo); - trace_rxrpc_timer(call, rxrpc_timer_init_for_reply, now); + call->delay_ack_at = KTIME_MAX; + trace_rxrpc_timer_can(call, rxrpc_timer_trace_delayed_ack); } if (!test_bit(RXRPC_CALL_TX_LAST, &call->flags)) { if (!rxrpc_rotate_tx_window(call, top, &summary)) { - rxrpc_proto_abort("TXL", call, top); + rxrpc_proto_abort(call, top, rxrpc_eproto_early_reply); return false; } } - if (!rxrpc_end_tx_phase(call, true, "ETD")) - return false; - call->tx_phase = false; + + rxrpc_end_tx_phase(call, true, rxrpc_eproto_unexpected_reply); return true; } /* - * Scan a data packet to validate its structure and to work out how many - * subpackets it contains. - * - * A jumbo packet is a collection of consecutive packets glued together with - * little headers between that indicate how to change the initial header for - * each subpacket. - * - * RXRPC_JUMBO_PACKET must be set on all but the last subpacket - and all but - * the last are RXRPC_JUMBO_DATALEN in size. The last subpacket may be of any - * size. + * End the packet reception phase. */ -static bool rxrpc_validate_data(struct sk_buff *skb) +static void rxrpc_end_rx_phase(struct rxrpc_call *call, rxrpc_serial_t serial) { - struct rxrpc_skb_priv *sp = rxrpc_skb(skb); - unsigned int offset = sizeof(struct rxrpc_wire_header); - unsigned int len = skb->len; - u8 flags = sp->hdr.flags; + rxrpc_seq_t whigh = READ_ONCE(call->rx_highest_seq); - for (;;) { - if (flags & RXRPC_REQUEST_ACK) - __set_bit(sp->nr_subpackets, sp->rx_req_ack); - sp->nr_subpackets++; + _enter("%d,%s", call->debug_id, rxrpc_call_states[__rxrpc_call_state(call)]); - if (!(flags & RXRPC_JUMBO_PACKET)) - break; + trace_rxrpc_receive(call, rxrpc_receive_end, 0, whigh); - if (len - offset < RXRPC_JUMBO_SUBPKTLEN) - goto protocol_error; - if (flags & RXRPC_LAST_PACKET) - goto protocol_error; - offset += RXRPC_JUMBO_DATALEN; - if (skb_copy_bits(skb, offset, &flags, 1) < 0) - goto protocol_error; - offset += sizeof(struct rxrpc_jumbo_header); - } + switch (__rxrpc_call_state(call)) { + case RXRPC_CALL_CLIENT_RECV_REPLY: + rxrpc_propose_delay_ACK(call, serial, rxrpc_propose_ack_terminal_ack); + rxrpc_call_completed(call); + break; - if (flags & RXRPC_LAST_PACKET) - sp->rx_flags |= RXRPC_SKB_INCL_LAST; - return true; + case RXRPC_CALL_SERVER_RECV_REQUEST: + rxrpc_set_call_state(call, RXRPC_CALL_SERVER_ACK_REQUEST); + call->expect_req_by = KTIME_MAX; + rxrpc_propose_delay_ACK(call, serial, rxrpc_propose_ack_processing_op); + break; -protocol_error: - return false; + default: + break; + } +} + +static void rxrpc_input_update_ack_window(struct rxrpc_call *call, + rxrpc_seq_t window, rxrpc_seq_t wtop) +{ + call->ackr_window = window; + call->ackr_wtop = wtop; } /* - * Handle reception of a duplicate packet. - * - * We have to take care to avoid an attack here whereby we're given a series of - * jumbograms, each with a sequence number one before the preceding one and - * filled up to maximum UDP size. If they never send us the first packet in - * the sequence, they can cause us to have to hold on to around 2MiB of kernel - * space until the call times out. - * - * We limit the space usage by only accepting three duplicate jumbo packets per - * call. After that, we tell the other side we're no longer accepting jumbos - * (that information is encoded in the ACK packet). + * Push a DATA packet onto the Rx queue. */ -static void rxrpc_input_dup_data(struct rxrpc_call *call, rxrpc_seq_t seq, - bool is_jumbo, bool *_jumbo_bad) +static void rxrpc_input_queue_data(struct rxrpc_call *call, struct sk_buff *skb, + rxrpc_seq_t window, rxrpc_seq_t wtop, + enum rxrpc_receive_trace why) { - /* Discard normal packets that are duplicates. */ - if (is_jumbo) - return; + struct rxrpc_skb_priv *sp = rxrpc_skb(skb); + bool last = sp->hdr.flags & RXRPC_LAST_PACKET; - /* Skip jumbo subpackets that are duplicates. When we've had three or - * more partially duplicate jumbo packets, we refuse to take any more - * jumbos for this call. - */ - if (!*_jumbo_bad) { - call->nr_jumbo_bad++; - *_jumbo_bad = true; - } + spin_lock_irq(&call->recvmsg_queue.lock); + + __skb_queue_tail(&call->recvmsg_queue, skb); + rxrpc_input_update_ack_window(call, window, wtop); + trace_rxrpc_receive(call, last ? why + 1 : why, sp->hdr.serial, sp->hdr.seq); + if (last) + /* Change the state inside the lock so that recvmsg syncs + * correctly with it and using sendmsg() to send a reply + * doesn't race. + */ + rxrpc_end_rx_phase(call, sp->hdr.serial); + + spin_unlock_irq(&call->recvmsg_queue.lock); } /* - * Process a DATA packet, adding the packet to the Rx ring. The caller's - * packet ref must be passed on or discarded. + * Process a DATA packet. */ -static void rxrpc_input_data(struct rxrpc_call *call, struct sk_buff *skb) +static void rxrpc_input_data_one(struct rxrpc_call *call, struct sk_buff *skb, + bool *_notify, rxrpc_serial_t *_ack_serial, int *_ack_reason) { struct rxrpc_skb_priv *sp = rxrpc_skb(skb); - enum rxrpc_call_state state; - 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; - u8 ack = 0; - - _enter("{%u,%u},{%u,%u}", - call->rx_hard_ack, call->rx_top, skb->len, seq0); - - _proto("Rx DATA %%%u { #%u f=%02x n=%u }", - sp->hdr.serial, seq0, sp->hdr.flags, sp->nr_subpackets); - - state = READ_ONCE(call->state); - if (state >= RXRPC_CALL_COMPLETE) { - rxrpc_free_skb(skb, rxrpc_skb_freed); - return; - } - - if (call->state == RXRPC_CALL_SERVER_RECV_REQUEST) { - unsigned long timo = READ_ONCE(call->next_req_timo); - unsigned long now, expect_req_by; - - if (timo) { - now = jiffies; - expect_req_by = now + timo; - WRITE_ONCE(call->expect_req_by, expect_req_by); - rxrpc_reduce_call_timer(call, expect_req_by, now, - rxrpc_timer_set_for_idle); + struct sk_buff *oos; + rxrpc_serial_t serial = sp->hdr.serial; + unsigned int sack = call->ackr_sack_base; + rxrpc_seq_t window = call->ackr_window; + rxrpc_seq_t wtop = call->ackr_wtop; + rxrpc_seq_t wlimit = window + call->rx_winsize - 1; + rxrpc_seq_t seq = sp->hdr.seq; + bool last = sp->hdr.flags & RXRPC_LAST_PACKET; + int ack_reason = -1; + + rxrpc_inc_stat(call->rxnet, stat_rx_data); + if (sp->hdr.flags & RXRPC_REQUEST_ACK) + rxrpc_inc_stat(call->rxnet, stat_rx_data_reqack); + if (sp->hdr.flags & RXRPC_JUMBO_PACKET) + rxrpc_inc_stat(call->rxnet, stat_rx_data_jumbo); + + if (last) { + if (test_and_set_bit(RXRPC_CALL_RX_LAST, &call->flags) && + seq + 1 != wtop) + return rxrpc_proto_abort(call, seq, rxrpc_eproto_different_last); + } else { + if (test_bit(RXRPC_CALL_RX_LAST, &call->flags) && + after_eq(seq, wtop)) { + pr_warn("Packet beyond last: c=%x q=%x window=%x-%x wlimit=%x\n", + call->debug_id, seq, window, wtop, wlimit); + return rxrpc_proto_abort(call, seq, rxrpc_eproto_data_after_last); } } - spin_lock(&call->input_lock); + if (after(seq, call->rx_highest_seq)) + call->rx_highest_seq = seq; - /* Received data implicitly ACKs all of the request packets we sent - * when we're acting as a client. - */ - if ((state == RXRPC_CALL_CLIENT_SEND_REQUEST || - state == RXRPC_CALL_CLIENT_AWAIT_REPLY) && - !rxrpc_receiving_reply(call)) - goto unlock; - - call->ackr_prev_seq = seq0; - hard_ack = READ_ONCE(call->rx_hard_ack); - - nr_subpackets = sp->nr_subpackets; - if (nr_subpackets > 1) { - if (call->nr_jumbo_bad > 3) { - ack = RXRPC_ACK_NOSPACE; - ack_serial = serial; - goto ack; - } + trace_rxrpc_rx_data(call->debug_id, seq, serial, sp->hdr.flags); + + if (before(seq, window)) { + ack_reason = RXRPC_ACK_DUPLICATE; + goto send_ack; + } + if (after(seq, wlimit)) { + ack_reason = RXRPC_ACK_EXCEEDS_WINDOW; + goto send_ack; } - 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 == nr_subpackets - 1); - bool last = terminal && (sp->rx_flags & RXRPC_SKB_INCL_LAST); - u8 flags, annotation = j; - - _proto("Rx DATA+%u %%%u { #%x t=%u l=%u }", - j, serial, seq, terminal, last); - - if (last) { - if (test_bit(RXRPC_CALL_RX_LAST, &call->flags) && - seq != call->rx_top) { - rxrpc_proto_abort("LSN", call, seq); - goto unlock; - } + /* Queue the packet. */ + if (seq == window) { + if (sp->hdr.flags & RXRPC_REQUEST_ACK) + ack_reason = RXRPC_ACK_REQUESTED; + /* Send an immediate ACK if we fill in a hole */ + else if (!skb_queue_empty(&call->rx_oos_queue)) + ack_reason = RXRPC_ACK_DELAY; + + window++; + if (after(window, wtop)) { + trace_rxrpc_sack(call, seq, sack, rxrpc_sack_none); + wtop = window; } else { - if (test_bit(RXRPC_CALL_RX_LAST, &call->flags) && - after_eq(seq, call->rx_top)) { - rxrpc_proto_abort("LSA", call, seq); - goto unlock; - } + trace_rxrpc_sack(call, seq, sack, rxrpc_sack_advance); + sack = (sack + 1) % RXRPC_SACK_SIZE; } - flags = 0; - if (last) - flags |= RXRPC_LAST_PACKET; - if (!terminal) - flags |= RXRPC_JUMBO_PACKET; - if (test_bit(j, sp->rx_req_ack)) - flags |= RXRPC_REQUEST_ACK; - trace_rxrpc_rx_data(call->debug_id, seq, serial, flags, annotation); - - if (before_eq(seq, hard_ack)) { - ack = RXRPC_ACK_DUPLICATE; - ack_serial = serial; - continue; - } - if (call->rxtx_buffer[ix]) { - rxrpc_input_dup_data(call, seq, nr_subpackets > 1, - &jumbo_bad); - if (ack != RXRPC_ACK_DUPLICATE) { - ack = RXRPC_ACK_DUPLICATE; - ack_serial = serial; - } - immediate_ack = true; - continue; - } + rxrpc_get_skb(skb, rxrpc_skb_get_to_recvmsg); - if (after(seq, hard_ack + call->rx_winsize)) { - ack = RXRPC_ACK_EXCEEDS_WINDOW; - ack_serial = serial; - if (flags & RXRPC_JUMBO_PACKET) { - if (!jumbo_bad) { - call->nr_jumbo_bad++; - jumbo_bad = true; - } - } + rxrpc_input_queue_data(call, skb, window, wtop, rxrpc_receive_queue); + *_notify = true; - goto ack; - } + while ((oos = skb_peek(&call->rx_oos_queue))) { + struct rxrpc_skb_priv *osp = rxrpc_skb(oos); - if (flags & RXRPC_REQUEST_ACK && !ack) { - ack = RXRPC_ACK_REQUESTED; - ack_serial = serial; - } + if (after(osp->hdr.seq, window)) + break; - /* Queue the packet. We use a couple of memory barriers here as need - * to make sure that rx_top is perceived to be set after the buffer - * pointer and that the buffer pointer is set after the annotation and - * the skb data. - * - * Barriers against rxrpc_recvmsg_data() and rxrpc_rotate_rx_window() - * and also rxrpc_fill_out_ack(). - */ - if (!terminal) - rxrpc_get_skb(skb, rxrpc_skb_got); - call->rxtx_annotations[ix] = annotation; - smp_wmb(); - call->rxtx_buffer[ix] = skb; - if (after(seq, call->rx_top)) { - smp_store_release(&call->rx_top, seq); - } else if (before(seq, call->rx_top)) { - /* Send an immediate ACK if we fill in a hole */ - if (!ack) { - ack = RXRPC_ACK_DELAY; - ack_serial = serial; - } - immediate_ack = true; + __skb_unlink(oos, &call->rx_oos_queue); + last = osp->hdr.flags & RXRPC_LAST_PACKET; + seq = osp->hdr.seq; + call->ackr_sack_table[sack] = 0; + trace_rxrpc_sack(call, seq, sack, rxrpc_sack_fill); + sack = (sack + 1) % RXRPC_SACK_SIZE; + + window++; + rxrpc_input_queue_data(call, oos, window, wtop, + rxrpc_receive_queue_oos); } - if (terminal) { - /* From this point on, we're not allowed to touch the - * packet any longer as its ref now belongs to the Rx - * ring. - */ - skb = NULL; - sp = NULL; + call->ackr_sack_base = sack; + } else { + unsigned int slot; + + ack_reason = RXRPC_ACK_OUT_OF_SEQUENCE; + + slot = seq - window; + sack = (sack + slot) % RXRPC_SACK_SIZE; + + if (call->ackr_sack_table[sack % RXRPC_SACK_SIZE]) { + ack_reason = RXRPC_ACK_DUPLICATE; + goto send_ack; } - if (last) { - set_bit(RXRPC_CALL_RX_LAST, &call->flags); - if (!ack) { - ack = RXRPC_ACK_DELAY; - ack_serial = serial; - } - trace_rxrpc_receive(call, rxrpc_receive_queue_last, serial, seq); - } else { - trace_rxrpc_receive(call, rxrpc_receive_queue, serial, seq); + call->ackr_sack_table[sack % RXRPC_SACK_SIZE] |= 1; + trace_rxrpc_sack(call, seq, sack, rxrpc_sack_oos); + + if (after(seq + 1, wtop)) { + wtop = seq + 1; + rxrpc_input_update_ack_window(call, window, wtop); } - if (after_eq(seq, call->rx_expect_next)) { - if (after(seq, call->rx_expect_next)) { - _net("OOS %u > %u", seq, call->rx_expect_next); - ack = RXRPC_ACK_OUT_OF_SEQUENCE; - ack_serial = serial; + skb_queue_walk(&call->rx_oos_queue, oos) { + struct rxrpc_skb_priv *osp = rxrpc_skb(oos); + + if (after(osp->hdr.seq, seq)) { + rxrpc_get_skb(skb, rxrpc_skb_get_to_recvmsg_oos); + __skb_queue_before(&call->rx_oos_queue, oos, skb); + goto oos_queued; } - call->rx_expect_next = seq + 1; } - } - -ack: - if (ack) - rxrpc_propose_ACK(call, ack, ack_serial, - immediate_ack, true, - rxrpc_propose_ack_input_data); - else - rxrpc_propose_ACK(call, RXRPC_ACK_DELAY, serial, - false, true, - rxrpc_propose_ack_input_data); - trace_rxrpc_notify_socket(call->debug_id, serial); - rxrpc_notify_socket(call); + rxrpc_get_skb(skb, rxrpc_skb_get_to_recvmsg_oos); + __skb_queue_tail(&call->rx_oos_queue, skb); + oos_queued: + trace_rxrpc_receive(call, last ? rxrpc_receive_oos_last : rxrpc_receive_oos, + sp->hdr.serial, sp->hdr.seq); + } -unlock: - spin_unlock(&call->input_lock); - rxrpc_free_skb(skb, rxrpc_skb_freed); - _leave(" [queued]"); +send_ack: + if (ack_reason >= 0) { + if (rxrpc_ack_priority[ack_reason] > rxrpc_ack_priority[*_ack_reason]) { + *_ack_serial = serial; + *_ack_reason = ack_reason; + } else if (rxrpc_ack_priority[ack_reason] == rxrpc_ack_priority[*_ack_reason] && + ack_reason == RXRPC_ACK_REQUESTED) { + *_ack_serial = serial; + *_ack_reason = ack_reason; + } + } } /* - * Process a requested ACK. + * Split a jumbo packet and file the bits separately. */ -static void rxrpc_input_requested_ack(struct rxrpc_call *call, - ktime_t resp_time, - rxrpc_serial_t orig_serial, - rxrpc_serial_t ack_serial) +static bool rxrpc_input_split_jumbo(struct rxrpc_call *call, struct sk_buff *skb) { - struct rxrpc_skb_priv *sp; - struct sk_buff *skb; - ktime_t sent_at; - int ix; + struct rxrpc_jumbo_header jhdr; + struct rxrpc_skb_priv *sp = rxrpc_skb(skb), *jsp; + struct sk_buff *jskb; + rxrpc_serial_t ack_serial = 0; + unsigned int offset = sizeof(struct rxrpc_wire_header); + unsigned int len = skb->len - offset; + bool notify = false; + int ack_reason = 0, count = 1, stat_ix; - for (ix = 0; ix < RXRPC_RXTX_BUFF_SIZE; ix++) { - skb = call->rxtx_buffer[ix]; - if (!skb) - continue; + while (sp->hdr.flags & RXRPC_JUMBO_PACKET) { + if (len < RXRPC_JUMBO_SUBPKTLEN) + goto protocol_error; + if (sp->hdr.flags & RXRPC_LAST_PACKET) + goto protocol_error; + if (skb_copy_bits(skb, offset + RXRPC_JUMBO_DATALEN, + &jhdr, sizeof(jhdr)) < 0) + goto protocol_error; - sent_at = skb->tstamp; - smp_rmb(); /* Read timestamp before serial. */ - sp = rxrpc_skb(skb); - if (sp->hdr.serial != orig_serial) - continue; - goto found; + jskb = skb_clone(skb, GFP_NOFS); + if (!jskb) { + kdebug("couldn't clone"); + return false; + } + rxrpc_new_skb(jskb, rxrpc_skb_new_jumbo_subpacket); + jsp = rxrpc_skb(jskb); + jsp->offset = offset; + jsp->len = RXRPC_JUMBO_DATALEN; + rxrpc_input_data_one(call, jskb, ¬ify, &ack_serial, &ack_reason); + rxrpc_free_skb(jskb, rxrpc_skb_put_jumbo_subpacket); + + sp->hdr.flags = jhdr.flags; + sp->hdr._rsvd = ntohs(jhdr._rsvd); + sp->hdr.seq++; + sp->hdr.serial++; + offset += RXRPC_JUMBO_SUBPKTLEN; + len -= RXRPC_JUMBO_SUBPKTLEN; + count++; } - return; + sp->offset = offset; + sp->len = len; + rxrpc_input_data_one(call, skb, ¬ify, &ack_serial, &ack_reason); + + stat_ix = umin(count, ARRAY_SIZE(call->rxnet->stat_rx_jumbo)) - 1; + atomic_inc(&call->rxnet->stat_rx_jumbo[stat_ix]); -found: - rxrpc_peer_add_rtt(call, rxrpc_rtt_rx_requested_ack, - orig_serial, ack_serial, sent_at, resp_time); + if (ack_reason > 0) { + rxrpc_send_ACK(call, ack_reason, ack_serial, + rxrpc_propose_ack_input_data); + } else { + call->ackr_nr_unacked++; + rxrpc_propose_delay_ACK(call, sp->hdr.serial, + rxrpc_propose_ack_input_data); + } + if (notify && !test_bit(RXRPC_CALL_CONN_CHALLENGING, &call->flags)) { + trace_rxrpc_notify_socket(call->debug_id, sp->hdr.serial); + rxrpc_notify_socket(call); + } + return true; + +protocol_error: + return false; } /* - * Process the response to a ping that we sent to find out if we lost an ACK. - * - * If we got back a ping response that indicates a lower tx_top than what we - * had at the time of the ping transmission, we adjudge all the DATA packets - * sent between the response tx_top and the ping-time tx_top to have been lost. + * Process a DATA packet, adding the packet to the Rx ring. The caller's + * packet ref must be passed on or discarded. */ -static void rxrpc_input_check_for_lost_ack(struct rxrpc_call *call) +static void rxrpc_input_data(struct rxrpc_call *call, struct sk_buff *skb) { - rxrpc_seq_t top, bottom, seq; - bool resend = false; - - spin_lock_bh(&call->lock); - - bottom = call->tx_hard_ack + 1; - top = call->acks_lost_top; - if (before(bottom, top)) { - for (seq = bottom; before_eq(seq, top); seq++) { - int ix = seq & RXRPC_RXTX_BUFF_MASK; - u8 annotation = call->rxtx_annotations[ix]; - u8 anno_type = annotation & RXRPC_TX_ANNO_MASK; - - if (anno_type != RXRPC_TX_ANNO_UNACK) - continue; - annotation &= ~RXRPC_TX_ANNO_MASK; - annotation |= RXRPC_TX_ANNO_RETRANS; - call->rxtx_annotations[ix] = annotation; - resend = true; + struct rxrpc_skb_priv *sp = rxrpc_skb(skb); + rxrpc_serial_t serial = sp->hdr.serial; + rxrpc_seq_t seq0 = sp->hdr.seq; + + _enter("{%x,%x,%x},{%u,%x}", + call->ackr_window, call->ackr_wtop, call->rx_highest_seq, + skb->len, seq0); + + if (__rxrpc_call_is_complete(call)) + return; + + switch (__rxrpc_call_state(call)) { + case RXRPC_CALL_CLIENT_SEND_REQUEST: + case RXRPC_CALL_CLIENT_AWAIT_REPLY: + /* Received data implicitly ACKs all of the request + * packets we sent when we're acting as a client. + */ + if (!rxrpc_receiving_reply(call)) + goto out_notify; + break; + + case RXRPC_CALL_SERVER_RECV_REQUEST: { + unsigned long timo = READ_ONCE(call->next_req_timo); + + if (timo) { + ktime_t delay = ms_to_ktime(timo); + + call->expect_req_by = ktime_add(ktime_get_real(), delay); + trace_rxrpc_timer_set(call, delay, rxrpc_timer_trace_idle); } + break; } - spin_unlock_bh(&call->lock); + default: + break; + } + + if (!rxrpc_input_split_jumbo(call, skb)) { + rxrpc_proto_abort(call, sp->hdr.seq, rxrpc_badmsg_bad_jumbo); + goto out_notify; + } + return; - if (resend && !test_and_set_bit(RXRPC_CALL_EV_RESEND, &call->events)) - rxrpc_queue_call(call); +out_notify: + trace_rxrpc_notify_socket(call->debug_id, serial); + rxrpc_notify_socket(call); + _leave(" [queued]"); } /* - * Process a ping response. + * See if there's a cached RTT probe to complete. */ -static void rxrpc_input_ping_response(struct rxrpc_call *call, - ktime_t resp_time, - rxrpc_serial_t orig_serial, - rxrpc_serial_t ack_serial) +static void rxrpc_complete_rtt_probe(struct rxrpc_call *call, + ktime_t resp_time, + rxrpc_serial_t acked_serial, + rxrpc_serial_t ack_serial, + enum rxrpc_rtt_rx_trace type) { - rxrpc_serial_t ping_serial; - ktime_t ping_time; + rxrpc_serial_t orig_serial; + unsigned long avail; + ktime_t sent_at; + bool matched = false; + int i; + + avail = READ_ONCE(call->rtt_avail); + smp_rmb(); /* Read avail bits before accessing data. */ - ping_time = call->ping_time; - smp_rmb(); - ping_serial = READ_ONCE(call->ping_serial); + for (i = 0; i < ARRAY_SIZE(call->rtt_serial); i++) { + if (!test_bit(i + RXRPC_CALL_RTT_PEND_SHIFT, &avail)) + continue; - if (orig_serial == call->acks_lost_ping) - rxrpc_input_check_for_lost_ack(call); + sent_at = call->rtt_sent_at[i]; + orig_serial = call->rtt_serial[i]; - if (before(orig_serial, ping_serial) || - !test_and_clear_bit(RXRPC_CALL_PINGING, &call->flags)) - return; - if (after(orig_serial, ping_serial)) - return; + if (orig_serial == acked_serial) { + clear_bit(i + RXRPC_CALL_RTT_PEND_SHIFT, &call->rtt_avail); + smp_mb(); /* Read data before setting avail bit */ + set_bit(i, &call->rtt_avail); + rxrpc_call_add_rtt(call, type, i, acked_serial, ack_serial, + sent_at, resp_time); + matched = true; + } - rxrpc_peer_add_rtt(call, rxrpc_rtt_rx_ping_response, - orig_serial, ack_serial, ping_time, resp_time); + /* If a later serial is being acked, then mark this slot as + * being available. + */ + if (after(acked_serial, orig_serial)) { + trace_rxrpc_rtt_rx(call, rxrpc_rtt_rx_obsolete, i, + orig_serial, acked_serial, 0, 0, 0); + clear_bit(i + RXRPC_CALL_RTT_PEND_SHIFT, &call->rtt_avail); + smp_wmb(); + set_bit(i, &call->rtt_avail); + } + } + + if (!matched) + trace_rxrpc_rtt_rx(call, rxrpc_rtt_rx_lost, 9, 0, acked_serial, 0, 0, 0); } /* * Process the extra information that may be appended to an ACK packet */ -static void rxrpc_input_ackinfo(struct rxrpc_call *call, struct sk_buff *skb, - struct rxrpc_ackinfo *ackinfo) +static void rxrpc_input_ack_trailer(struct rxrpc_call *call, struct sk_buff *skb, + struct rxrpc_acktrailer *trailer) { struct rxrpc_skb_priv *sp = rxrpc_skb(skb); - struct rxrpc_peer *peer; - unsigned int mtu; + struct rxrpc_peer *peer = call->peer; + unsigned int max_data, capacity; bool wake = false; - u32 rwind = ntohl(ackinfo->rwind); - - _proto("Rx ACK %%%u Info { rx=%u max=%u rwin=%u jm=%u }", - sp->hdr.serial, - ntohl(ackinfo->rxMTU), ntohl(ackinfo->maxMTU), - rwind, ntohl(ackinfo->jumbo_max)); + u32 max_mtu = ntohl(trailer->maxMTU); + //u32 if_mtu = ntohl(trailer->ifMTU); + u32 rwind = ntohl(trailer->rwind); + u32 jumbo_max = ntohl(trailer->jumbo_max); + if (rwind > RXRPC_TX_MAX_WINDOW) + rwind = RXRPC_TX_MAX_WINDOW; 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; } - if (call->cong_ssthresh > rwind) - call->cong_ssthresh = rwind; + max_mtu = clamp(max_mtu, 500, 65535); + peer->ackr_max_data = max_mtu; + + if (max_mtu < peer->max_data) { + trace_rxrpc_pmtud_reduce(peer, sp->hdr.serial, max_mtu, + rxrpc_pmtud_reduce_ack); + peer->max_data = max_mtu; + } - mtu = min(ntohl(ackinfo->rxMTU), ntohl(ackinfo->maxMTU)); + max_data = umin(max_mtu, peer->max_data); + capacity = max_data; + capacity += sizeof(struct rxrpc_jumbo_header); /* First subpacket has main hdr, not jumbo */ + capacity /= sizeof(struct rxrpc_jumbo_header) + RXRPC_JUMBO_DATALEN; - 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); + if (jumbo_max == 0) { + /* The peer says it supports pmtu discovery */ + peer->ackr_adv_pmtud = true; + } else { + peer->ackr_adv_pmtud = false; + capacity = clamp(capacity, 1, jumbo_max); } + call->tx_jumbo_max = capacity; + if (wake) wake_up(&call->waitq); } +#if defined(CONFIG_X86) && __GNUC__ && !defined(__clang__) +/* Clang doesn't support the %z constraint modifier */ +#define shiftr_adv_rotr(shift_from, rotate_into) ({ \ + asm(" shr%z1 %1\n" \ + " inc %0\n" \ + " rcr%z2 %2\n" \ + : "+d"(shift_from), "+m"(*(shift_from)), "+rm"(rotate_into) \ + ); \ + }) +#else +#define shiftr_adv_rotr(shift_from, rotate_into) ({ \ + typeof(rotate_into) __bit0 = *(shift_from) & 1; \ + *(shift_from) >>= 1; \ + shift_from++; \ + rotate_into >>= 1; \ + rotate_into |= __bit0 << (sizeof(rotate_into) * 8 - 1); \ + }) +#endif + +/* + * Deal with RTT samples from soft ACKs. + */ +static void rxrpc_input_soft_rtt(struct rxrpc_call *call, + struct rxrpc_ack_summary *summary, + struct rxrpc_txqueue *tq) +{ + for (int ix = 0; ix < RXRPC_NR_TXQUEUE; ix++) + if (summary->acked_serial == tq->segment_serial[ix]) + return rxrpc_add_data_rtt_sample(call, summary, tq, ix); +} + +/* + * Process a batch of soft ACKs specific to a transmission queue segment. + */ +static void rxrpc_input_soft_ack_tq(struct rxrpc_call *call, + struct rxrpc_ack_summary *summary, + struct rxrpc_txqueue *tq, + unsigned long extracted_acks, + int nr_reported, + rxrpc_seq_t seq, + rxrpc_seq_t *lowest_nak) +{ + unsigned long old_reported = 0, flipped, new_acks = 0; + unsigned long a_to_n, n_to_a = 0; + int new, a, n; + + if (tq->nr_reported_acks > 0) + old_reported = ~0UL >> (RXRPC_NR_TXQUEUE - tq->nr_reported_acks); + + _enter("{%x,%lx,%d},%lx,%d,%x", + tq->qbase, tq->segment_acked, tq->nr_reported_acks, + extracted_acks, nr_reported, seq); + + _debug("[%x]", tq->qbase); + _debug("tq %16lx %u", tq->segment_acked, tq->nr_reported_acks); + _debug("sack %16lx %u", extracted_acks, nr_reported); + + /* See how many previously logged ACKs/NAKs have flipped. */ + flipped = (tq->segment_acked ^ extracted_acks) & old_reported; + if (flipped) { + n_to_a = ~tq->segment_acked & flipped; /* Old NAK -> ACK */ + a_to_n = tq->segment_acked & flipped; /* Old ACK -> NAK */ + a = hweight_long(n_to_a); + n = hweight_long(a_to_n); + _debug("flip %16lx", flipped); + _debug("ntoa %16lx %d", n_to_a, a); + _debug("aton %16lx %d", a_to_n, n); + call->acks_nr_sacks += a - n; + call->acks_nr_snacks += n - a; + summary->nr_new_sacks += a; + summary->nr_new_snacks += n; + } + + /* See how many new ACKs/NAKs have been acquired. */ + new = nr_reported - tq->nr_reported_acks; + if (new > 0) { + new_acks = extracted_acks & ~old_reported; + if (new_acks) { + a = hweight_long(new_acks); + n = new - a; + _debug("new_a %16lx new=%d a=%d n=%d", new_acks, new, a, n); + call->acks_nr_sacks += a; + call->acks_nr_snacks += n; + summary->nr_new_sacks += a; + summary->nr_new_snacks += n; + } else { + call->acks_nr_snacks += new; + summary->nr_new_snacks += new; + } + } + + tq->nr_reported_acks = nr_reported; + tq->segment_acked = extracted_acks; + trace_rxrpc_apply_acks(call, tq); + + if (extracted_acks != ~0UL) { + rxrpc_seq_t lowest = seq + ffz(extracted_acks); + + if (before(lowest, *lowest_nak)) + *lowest_nak = lowest; + } + + if (summary->acked_serial) + rxrpc_input_soft_rtt(call, summary, tq); + + new_acks |= n_to_a; + if (new_acks) + rxrpc_input_rack(call, summary, tq, new_acks); + + if (call->tlp_serial && + rxrpc_seq_in_txq(tq, call->tlp_seq) && + test_bit(call->tlp_seq - tq->qbase, &new_acks)) + summary->tlp_probe_acked = true; +} + /* * Process individual soft ACKs. * @@ -759,46 +956,67 @@ static void rxrpc_input_ackinfo(struct rxrpc_call *call, struct sk_buff *skb, * the timer on the basis that the peer might just not have processed them at * the time the ACK was sent. */ -static void rxrpc_input_soft_acks(struct rxrpc_call *call, u8 *acks, - rxrpc_seq_t seq, int nr_acks, - struct rxrpc_ack_summary *summary) +static void rxrpc_input_soft_acks(struct rxrpc_call *call, + struct rxrpc_ack_summary *summary, + struct sk_buff *skb) { - int ix; - u8 annotation, anno_type; - - for (; nr_acks > 0; nr_acks--, seq++) { - ix = seq & RXRPC_RXTX_BUFF_MASK; - annotation = call->rxtx_annotations[ix]; - anno_type = annotation & RXRPC_TX_ANNO_MASK; - annotation &= ~RXRPC_TX_ANNO_MASK; - switch (*acks++) { - case RXRPC_ACK_TYPE_ACK: - summary->nr_acks++; - if (anno_type == RXRPC_TX_ANNO_ACK) - continue; - summary->nr_new_acks++; - call->rxtx_annotations[ix] = - RXRPC_TX_ANNO_ACK | annotation; - break; - case RXRPC_ACK_TYPE_NACK: - if (!summary->nr_nacks && - call->acks_lowest_nak != seq) { - call->acks_lowest_nak = seq; - summary->new_low_nack = true; - } - summary->nr_nacks++; - if (anno_type == RXRPC_TX_ANNO_NAK) - continue; - summary->nr_new_nacks++; - if (anno_type == RXRPC_TX_ANNO_RETRANS) - continue; - call->rxtx_annotations[ix] = - RXRPC_TX_ANNO_NAK | annotation; - break; - default: - return rxrpc_proto_abort("SFT", call, 0); + struct rxrpc_skb_priv *sp = rxrpc_skb(skb); + struct rxrpc_txqueue *tq = call->tx_queue; + unsigned long extracted = ~0UL; + unsigned int nr = 0; + rxrpc_seq_t seq = call->acks_hard_ack + 1; + rxrpc_seq_t lowest_nak = seq + sp->ack.nr_acks; + u8 *acks = skb->data + sizeof(struct rxrpc_wire_header) + sizeof(struct rxrpc_ackpacket); + + _enter("%x,%x,%u", tq->qbase, seq, sp->ack.nr_acks); + + while (after(seq, tq->qbase + RXRPC_NR_TXQUEUE - 1)) + tq = tq->next; + + for (unsigned int i = 0; i < sp->ack.nr_acks; i++) { + /* Decant ACKs until we hit a txqueue boundary. */ + shiftr_adv_rotr(acks, extracted); + if (i == 256) { + acks -= i; + i = 0; } + seq++; + nr++; + if ((seq & RXRPC_TXQ_MASK) != 0) + continue; + + _debug("bound %16lx %u", extracted, nr); + + rxrpc_input_soft_ack_tq(call, summary, tq, extracted, RXRPC_NR_TXQUEUE, + seq - RXRPC_NR_TXQUEUE, &lowest_nak); + extracted = ~0UL; + nr = 0; + tq = tq->next; + prefetch(tq); } + + if (nr) { + unsigned int nr_reported = seq & RXRPC_TXQ_MASK; + + extracted >>= RXRPC_NR_TXQUEUE - nr_reported; + _debug("tail %16lx %u", extracted, nr_reported); + rxrpc_input_soft_ack_tq(call, summary, tq, extracted, nr_reported, + seq & ~RXRPC_TXQ_MASK, &lowest_nak); + } + + /* We *can* have more nacks than we did - the peer is permitted to drop + * packets it has soft-acked and re-request them. Further, it is + * possible for the nack distribution to change whilst the number of + * nacks stays the same or goes down. + */ + if (lowest_nak != call->acks_lowest_nak) { + call->acks_lowest_nak = lowest_nak; + summary->new_low_snack = true; + } + + _debug("summary A=%d+%d N=%d+%d", + call->acks_nr_sacks, summary->nr_new_sacks, + call->acks_nr_snacks, summary->nr_new_snacks); } /* @@ -806,21 +1024,21 @@ static void rxrpc_input_soft_acks(struct rxrpc_call *call, u8 *acks, * 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 hard_ack, rxrpc_seq_t prev_pkt) { - rxrpc_seq_t base = READ_ONCE(call->ackr_first_seq); + rxrpc_seq_t base = READ_ONCE(call->acks_hard_ack); - if (after(first_pkt, base)) + if (after(hard_ack, base)) return true; /* The window advanced */ - if (before(first_pkt, base)) + if (before(hard_ack, base)) return false; /* firstPacket regressed */ - if (after_eq(prev_pkt, call->ackr_prev_seq)) + if (after_eq(prev_pkt, call->acks_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)) + if (after(prev_pkt, base + call->tx_winsize)) return false; return true; } @@ -838,140 +1056,148 @@ static bool rxrpc_is_ack_valid(struct rxrpc_call *call, static void rxrpc_input_ack(struct rxrpc_call *call, struct sk_buff *skb) { struct rxrpc_ack_summary summary = { 0 }; + struct rxrpc_acktrailer trailer; struct rxrpc_skb_priv *sp = rxrpc_skb(skb); - union { - struct rxrpc_ackpacket ack; - struct rxrpc_ackinfo info; - u8 acks[RXRPC_MAXACKS]; - } buf; - rxrpc_serial_t acked_serial; rxrpc_seq_t first_soft_ack, hard_ack, prev_pkt; int nr_acks, offset, ioffset; _enter(""); - offset = sizeof(struct rxrpc_wire_header); - if (skb_copy_bits(skb, offset, &buf.ack, sizeof(buf.ack)) < 0) { - _debug("extraction failure"); - return rxrpc_proto_abort("XAK", call, 0); + offset = sizeof(struct rxrpc_wire_header) + sizeof(struct rxrpc_ackpacket); + + summary.ack_serial = sp->hdr.serial; + first_soft_ack = sp->ack.first_ack; + prev_pkt = sp->ack.prev_ack; + nr_acks = sp->ack.nr_acks; + hard_ack = first_soft_ack - 1; + summary.acked_serial = sp->ack.acked_serial; + summary.ack_reason = (sp->ack.reason < RXRPC_ACK__INVALID ? + sp->ack.reason : RXRPC_ACK__INVALID); + + trace_rxrpc_rx_ack(call, sp); + rxrpc_inc_stat(call->rxnet, stat_rx_acks[summary.ack_reason]); + prefetch(call->tx_queue); + + /* If we get an EXCEEDS_WINDOW ACK from the server, it probably + * indicates that the client address changed due to NAT. The server + * lost the call because it switched to a different peer. + */ + if (unlikely(summary.ack_reason == RXRPC_ACK_EXCEEDS_WINDOW) && + hard_ack == 0 && + prev_pkt == 0 && + rxrpc_is_client_call(call)) { + rxrpc_set_call_completion(call, RXRPC_CALL_REMOTELY_ABORTED, + 0, -ENETRESET); + goto send_response; } - offset += sizeof(buf.ack); - - acked_serial = ntohl(buf.ack.serial); - first_soft_ack = ntohl(buf.ack.firstPacket); - prev_pkt = ntohl(buf.ack.previousPacket); - hard_ack = first_soft_ack - 1; - nr_acks = buf.ack.nAcks; - 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, - 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); - if (buf.ack.reason == RXRPC_ACK_REQUESTED) - rxrpc_input_requested_ack(call, skb->tstamp, acked_serial, - sp->hdr.serial); - - if (buf.ack.reason == RXRPC_ACK_PING) { - _proto("Rx ACK %%%u PING Request", sp->hdr.serial); - rxrpc_propose_ACK(call, RXRPC_ACK_PING_RESPONSE, - sp->hdr.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, - rxrpc_propose_ack_respond_to_ack); + + /* If we get an OUT_OF_SEQUENCE ACK from the server, that can also + * indicate a change of address. However, we can retransmit the call + * if we still have it buffered to the beginning. + */ + if (unlikely(summary.ack_reason == RXRPC_ACK_OUT_OF_SEQUENCE) && + hard_ack == 0 && + prev_pkt == 0 && + call->tx_bottom == 0 && + rxrpc_is_client_call(call)) { + rxrpc_set_call_completion(call, RXRPC_CALL_REMOTELY_ABORTED, + 0, -ENETRESET); + goto send_response; } /* Discard any out-of-order or duplicate ACKs (outside lock). */ - if (!rxrpc_is_ack_valid(call, first_soft_ack, prev_pkt)) { - trace_rxrpc_rx_discard_ack(call->debug_id, sp->hdr.serial, - first_soft_ack, call->ackr_first_seq, - prev_pkt, call->ackr_prev_seq); - return; + if (!rxrpc_is_ack_valid(call, hard_ack, prev_pkt)) { + trace_rxrpc_rx_discard_ack(call, summary.ack_serial, hard_ack, prev_pkt); + goto send_response; /* Still respond if requested. */ } - buf.info.rxMTU = 0; + trailer.maxMTU = 0; ioffset = offset + nr_acks + 3; - if (skb->len >= ioffset + sizeof(buf.info) && - skb_copy_bits(skb, ioffset, &buf.info, sizeof(buf.info)) < 0) - return rxrpc_proto_abort("XAI", call, 0); - - spin_lock(&call->input_lock); - - /* Discard any out-of-order or duplicate ACKs (inside lock). */ - if (!rxrpc_is_ack_valid(call, first_soft_ack, prev_pkt)) { - trace_rxrpc_rx_discard_ack(call->debug_id, sp->hdr.serial, - first_soft_ack, call->ackr_first_seq, - prev_pkt, call->ackr_prev_seq); - goto out; + if (skb->len >= ioffset + sizeof(trailer) && + skb_copy_bits(skb, ioffset, &trailer, sizeof(trailer)) < 0) + return rxrpc_proto_abort(call, 0, rxrpc_badmsg_short_ack_trailer); + + if (nr_acks > 0) + skb_condense(skb); + + call->acks_latest_ts = ktime_get_real(); + call->acks_hard_ack = hard_ack; + call->acks_prev_seq = prev_pkt; + + if (summary.acked_serial) { + switch (summary.ack_reason) { + case RXRPC_ACK_PING_RESPONSE: + rxrpc_complete_rtt_probe(call, call->acks_latest_ts, + summary.acked_serial, summary.ack_serial, + rxrpc_rtt_rx_ping_response); + break; + default: + if (after(summary.acked_serial, call->acks_highest_serial)) + call->acks_highest_serial = summary.acked_serial; + summary.rtt_sample_avail = true; + break; + } } - call->acks_latest_ts = skb->tstamp; - - call->ackr_first_seq = first_soft_ack; - call->ackr_prev_seq = prev_pkt; /* Parse rwind and mtu sizes if provided. */ - if (buf.info.rxMTU) - rxrpc_input_ackinfo(call, skb, &buf.info); + if (trailer.maxMTU) + rxrpc_input_ack_trailer(call, skb, &trailer); - if (first_soft_ack == 0) { - rxrpc_proto_abort("AK0", call, 0); - goto out; - } + if (hard_ack + 1 == 0) + return rxrpc_proto_abort(call, 0, rxrpc_eproto_ackr_zero); /* Ignore ACKs unless we are or have just been transmitting. */ - switch (READ_ONCE(call->state)) { + switch (__rxrpc_call_state(call)) { case RXRPC_CALL_CLIENT_SEND_REQUEST: case RXRPC_CALL_CLIENT_AWAIT_REPLY: case RXRPC_CALL_SERVER_SEND_REPLY: case RXRPC_CALL_SERVER_AWAIT_ACK: break; default: - goto out; + goto send_response; } - if (before(hard_ack, call->tx_hard_ack) || - after(hard_ack, call->tx_top)) { - rxrpc_proto_abort("AKW", call, 0); - goto out; - } - if (nr_acks > call->tx_top - hard_ack) { - rxrpc_proto_abort("AKN", call, 0); - goto out; - } + if (before(hard_ack, call->tx_bottom) || + after(hard_ack, call->tx_top)) + return rxrpc_proto_abort(call, 0, rxrpc_eproto_ackr_outside_window); + if (nr_acks > call->tx_top - hard_ack) + return rxrpc_proto_abort(call, 0, rxrpc_eproto_ackr_sack_overflow); - if (after(hard_ack, call->tx_hard_ack)) { + if (after(hard_ack, call->tx_bottom)) { if (rxrpc_rotate_tx_window(call, hard_ack, &summary)) { - rxrpc_end_tx_phase(call, false, "ETA"); - goto out; + rxrpc_end_tx_phase(call, false, rxrpc_eproto_unexpected_ack); + goto send_response; } } if (nr_acks > 0) { - if (skb_copy_bits(skb, offset, buf.acks, nr_acks) < 0) { - rxrpc_proto_abort("XSA", call, 0); - goto out; - } - rxrpc_input_soft_acks(call, buf.acks, first_soft_ack, nr_acks, - &summary); + if (offset > (int)skb->len - nr_acks) + return rxrpc_proto_abort(call, 0, rxrpc_eproto_ackr_short_sack); + rxrpc_input_soft_acks(call, &summary, skb); } - if (call->rxtx_annotations[call->tx_top & RXRPC_RXTX_BUFF_MASK] & - RXRPC_TX_ANNO_LAST && - summary.nr_acks == call->tx_top - hard_ack && + if (test_bit(RXRPC_CALL_TX_LAST, &call->flags) && + call->acks_nr_sacks == call->tx_top - hard_ack && rxrpc_is_client_call(call)) - rxrpc_propose_ACK(call, RXRPC_ACK_PING, sp->hdr.serial, - false, true, - rxrpc_propose_ack_ping_for_lost_reply); + rxrpc_propose_ping(call, summary.ack_serial, + rxrpc_propose_ack_ping_for_lost_reply); - rxrpc_congestion_management(call, skb, &summary, acked_serial); -out: - spin_unlock(&call->input_lock); + /* Drive the congestion management algorithm first and then RACK-TLP as + * the latter depends on the state/change in state in the former. + */ + rxrpc_congestion_management(call, &summary); + rxrpc_rack_detect_loss_and_arm_timer(call, &summary); + rxrpc_tlp_process_ack(call, &summary); + if (call->tlp_serial && after_eq(summary.acked_serial, call->tlp_serial)) + call->tlp_serial = 0; + +send_response: + if (summary.ack_reason == RXRPC_ACK_PING) + rxrpc_send_ACK(call, RXRPC_ACK_PING_RESPONSE, summary.ack_serial, + rxrpc_propose_ack_respond_to_ping); + else if (sp->hdr.flags & RXRPC_REQUEST_ACK) + rxrpc_send_ACK(call, RXRPC_ACK_REQUESTED, summary.ack_serial, + rxrpc_propose_ack_respond_to_ack); } /* @@ -980,16 +1206,9 @@ out: static void rxrpc_input_ackall(struct rxrpc_call *call, struct sk_buff *skb) { struct rxrpc_ack_summary summary = { 0 }; - struct rxrpc_skb_priv *sp = rxrpc_skb(skb); - - _proto("Rx ACKALL %%%u", sp->hdr.serial); - - spin_lock(&call->input_lock); if (rxrpc_rotate_tx_window(call, call->tx_top, &summary)) - rxrpc_end_tx_phase(call, false, "ETL"); - - spin_unlock(&call->input_lock); + rxrpc_end_tx_phase(call, false, rxrpc_eproto_unexpected_ackall); } /* @@ -998,78 +1217,61 @@ static void rxrpc_input_ackall(struct rxrpc_call *call, struct sk_buff *skb) static void rxrpc_input_abort(struct rxrpc_call *call, struct sk_buff *skb) { struct rxrpc_skb_priv *sp = rxrpc_skb(skb); - __be32 wtmp; - u32 abort_code = RX_CALL_DEAD; - - _enter(""); - - if (skb->len >= 4 && - skb_copy_bits(skb, sizeof(struct rxrpc_wire_header), - &wtmp, sizeof(wtmp)) >= 0) - abort_code = ntohl(wtmp); - - trace_rxrpc_rx_abort(call, sp->hdr.serial, abort_code); - _proto("Rx ABORT %%%u { %x }", sp->hdr.serial, abort_code); + trace_rxrpc_rx_abort(call, sp->hdr.serial, skb->priority); rxrpc_set_call_completion(call, RXRPC_CALL_REMOTELY_ABORTED, - abort_code, -ECONNABORTED); + skb->priority, -ECONNABORTED); } /* * Process an incoming call packet. */ -static void rxrpc_input_call_packet(struct rxrpc_call *call, - struct sk_buff *skb) +void rxrpc_input_call_packet(struct rxrpc_call *call, struct sk_buff *skb) { struct rxrpc_skb_priv *sp = rxrpc_skb(skb); unsigned long timo; _enter("%p,%p", call, skb); + if (sp->hdr.serviceId != call->dest_srx.srx_service) + call->dest_srx.srx_service = sp->hdr.serviceId; + if ((int)sp->hdr.serial - (int)call->rx_serial > 0) + call->rx_serial = sp->hdr.serial; + if (!test_bit(RXRPC_CALL_RX_HEARD, &call->flags)) + set_bit(RXRPC_CALL_RX_HEARD, &call->flags); + timo = READ_ONCE(call->next_rx_timo); if (timo) { - unsigned long now = jiffies, expect_rx_by; + ktime_t delay = ms_to_ktime(timo); - expect_rx_by = now + timo; - WRITE_ONCE(call->expect_rx_by, expect_rx_by); - rxrpc_reduce_call_timer(call, expect_rx_by, now, - rxrpc_timer_set_for_normal); + call->expect_rx_by = ktime_add(ktime_get_real(), delay); + trace_rxrpc_timer_set(call, delay, rxrpc_timer_trace_expect_rx); } switch (sp->hdr.type) { case RXRPC_PACKET_TYPE_DATA: - rxrpc_input_data(call, skb); - goto no_free; + return rxrpc_input_data(call, skb); case RXRPC_PACKET_TYPE_ACK: - rxrpc_input_ack(call, skb); - break; + return rxrpc_input_ack(call, skb); case RXRPC_PACKET_TYPE_BUSY: - _proto("Rx BUSY %%%u", sp->hdr.serial); - /* Just ignore BUSY packets from the server; the retry and * lifespan timers will take care of business. BUSY packets * from the client don't make sense. */ - break; + return; case RXRPC_PACKET_TYPE_ABORT: - rxrpc_input_abort(call, skb); - break; + return rxrpc_input_abort(call, skb); case RXRPC_PACKET_TYPE_ACKALL: - rxrpc_input_ackall(call, skb); - break; + return rxrpc_input_ackall(call, skb); default: break; } - - rxrpc_free_skb(skb, rxrpc_skb_freed); -no_free: - _leave(""); } /* @@ -1078,375 +1280,20 @@ no_free: * * TODO: If callNumber > call_id + 1, renegotiate security. */ -static void rxrpc_input_implicit_end_call(struct rxrpc_sock *rx, - struct rxrpc_connection *conn, - struct rxrpc_call *call) +void rxrpc_implicit_end_call(struct rxrpc_call *call, struct sk_buff *skb) { - switch (READ_ONCE(call->state)) { + switch (__rxrpc_call_state(call)) { case RXRPC_CALL_SERVER_AWAIT_ACK: rxrpc_call_completed(call); - /* Fall through */ + fallthrough; case RXRPC_CALL_COMPLETE: break; default: - if (rxrpc_abort_call("IMP", call, 0, RX_CALL_DEAD, -ESHUTDOWN)) { - set_bit(RXRPC_CALL_EV_ABORT, &call->events); - rxrpc_queue_call(call); - } + rxrpc_abort_call(call, 0, RX_CALL_DEAD, -ESHUTDOWN, + rxrpc_eproto_improper_term); trace_rxrpc_improper_term(call); break; } - spin_lock(&rx->incoming_lock); - __rxrpc_disconnect_call(conn, call); - spin_unlock(&rx->incoming_lock); -} - -/* - * post connection-level events to the connection - * - this includes challenges, responses, some aborts and call terminal packet - * retransmission. - */ -static void rxrpc_post_packet_to_conn(struct rxrpc_connection *conn, - struct sk_buff *skb) -{ - _enter("%p,%p", conn, skb); - - skb_queue_tail(&conn->rx_queue, skb); - rxrpc_queue_conn(conn); -} - -/* - * post endpoint-level events to the local endpoint - * - this includes debug and version messages - */ -static void rxrpc_post_packet_to_local(struct rxrpc_local *local, - struct sk_buff *skb) -{ - _enter("%p,%p", local, skb); - - if (rxrpc_get_local_maybe(local)) { - skb_queue_tail(&local->event_queue, skb); - rxrpc_queue_local(local); - } else { - rxrpc_free_skb(skb, rxrpc_skb_freed); - } -} - -/* - * put a packet up for transport-level abort - */ -static void rxrpc_reject_packet(struct rxrpc_local *local, struct sk_buff *skb) -{ - CHECK_SLAB_OKAY(&local->usage); - - if (rxrpc_get_local_maybe(local)) { - skb_queue_tail(&local->reject_queue, skb); - rxrpc_queue_local(local); - } else { - rxrpc_free_skb(skb, rxrpc_skb_freed); - } -} - -/* - * Extract the wire header from a packet and translate the byte order. - */ -static noinline -int rxrpc_extract_header(struct rxrpc_skb_priv *sp, struct sk_buff *skb) -{ - struct rxrpc_wire_header whdr; - - /* dig out the RxRPC connection details */ - if (skb_copy_bits(skb, 0, &whdr, sizeof(whdr)) < 0) { - trace_rxrpc_rx_eproto(NULL, sp->hdr.serial, - tracepoint_string("bad_hdr")); - return -EBADMSG; - } - - memset(sp, 0, sizeof(*sp)); - sp->hdr.epoch = ntohl(whdr.epoch); - sp->hdr.cid = ntohl(whdr.cid); - sp->hdr.callNumber = ntohl(whdr.callNumber); - sp->hdr.seq = ntohl(whdr.seq); - sp->hdr.serial = ntohl(whdr.serial); - sp->hdr.flags = whdr.flags; - sp->hdr.type = whdr.type; - sp->hdr.userStatus = whdr.userStatus; - sp->hdr.securityIndex = whdr.securityIndex; - sp->hdr._rsvd = ntohs(whdr._rsvd); - sp->hdr.serviceId = ntohs(whdr.serviceId); - return 0; -} - -/* - * handle data received on the local endpoint - * - may be called in interrupt context - * - * [!] Note that as this is called from the encap_rcv hook, the socket is not - * held locked by the caller and nothing prevents sk_user_data on the UDP from - * being cleared in the middle of processing this function. - * - * Called with the RCU read lock held from the IP layer via UDP. - */ -int rxrpc_input_packet(struct sock *udp_sk, struct sk_buff *skb) -{ - struct rxrpc_local *local = rcu_dereference_sk_user_data(udp_sk); - struct rxrpc_connection *conn; - struct rxrpc_channel *chan; - struct rxrpc_call *call = NULL; - struct rxrpc_skb_priv *sp; - struct rxrpc_peer *peer = NULL; - struct rxrpc_sock *rx = NULL; - unsigned int channel; - - _enter("%p", udp_sk); - - if (unlikely(!local)) { - kfree_skb(skb); - return 0; - } - if (skb->tstamp == 0) - skb->tstamp = ktime_get_real(); - - rxrpc_new_skb(skb, rxrpc_skb_received); - - skb_pull(skb, sizeof(struct udphdr)); - - /* The UDP protocol already released all skb resources; - * we are free to add our own data there. - */ - sp = rxrpc_skb(skb); - - /* dig out the RxRPC connection details */ - if (rxrpc_extract_header(sp, skb) < 0) - goto bad_message; - - if (IS_ENABLED(CONFIG_AF_RXRPC_INJECT_LOSS)) { - static int lose; - if ((lose++ & 7) == 7) { - trace_rxrpc_rx_lose(sp); - rxrpc_free_skb(skb, rxrpc_skb_lost); - return 0; - } - } - - if (skb->tstamp == 0) - skb->tstamp = ktime_get_real(); - trace_rxrpc_rx_packet(sp); - - switch (sp->hdr.type) { - case RXRPC_PACKET_TYPE_VERSION: - if (rxrpc_to_client(sp)) - goto discard; - rxrpc_post_packet_to_local(local, skb); - goto out; - - case RXRPC_PACKET_TYPE_BUSY: - if (rxrpc_to_server(sp)) - goto discard; - /* Fall through */ - case RXRPC_PACKET_TYPE_ACK: - case RXRPC_PACKET_TYPE_ACKALL: - if (sp->hdr.callNumber == 0) - goto bad_message; - /* Fall through */ - case RXRPC_PACKET_TYPE_ABORT: - break; - - case RXRPC_PACKET_TYPE_DATA: - if (sp->hdr.callNumber == 0 || - sp->hdr.seq == 0) - goto bad_message; - if (!rxrpc_validate_data(skb)) - goto bad_message; - - /* Unshare the packet so that it can be modified for in-place - * decryption. - */ - if (sp->hdr.securityIndex != 0) { - struct sk_buff *nskb = skb_unshare(skb, GFP_ATOMIC); - if (!nskb) { - rxrpc_eaten_skb(skb, rxrpc_skb_unshared_nomem); - goto out; - } - - if (nskb != skb) { - rxrpc_eaten_skb(skb, rxrpc_skb_received); - skb = nskb; - rxrpc_new_skb(skb, rxrpc_skb_unshared); - sp = rxrpc_skb(skb); - } - } - break; - - case RXRPC_PACKET_TYPE_CHALLENGE: - if (rxrpc_to_server(sp)) - goto discard; - break; - case RXRPC_PACKET_TYPE_RESPONSE: - if (rxrpc_to_client(sp)) - goto discard; - break; - - /* Packet types 9-11 should just be ignored. */ - case RXRPC_PACKET_TYPE_PARAMS: - case RXRPC_PACKET_TYPE_10: - case RXRPC_PACKET_TYPE_11: - goto discard; - - default: - _proto("Rx Bad Packet Type %u", sp->hdr.type); - goto bad_message; - } - - if (sp->hdr.serviceId == 0) - goto bad_message; - - if (rxrpc_to_server(sp)) { - /* Weed out packets to services we're not offering. Packets - * that would begin a call are explicitly rejected and the rest - * are just discarded. - */ - rx = rcu_dereference(local->service); - if (!rx || (sp->hdr.serviceId != rx->srx.srx_service && - sp->hdr.serviceId != rx->second_service)) { - if (sp->hdr.type == RXRPC_PACKET_TYPE_DATA && - sp->hdr.seq == 1) - goto unsupported_service; - goto discard; - } - } - - conn = rxrpc_find_connection_rcu(local, skb, &peer); - if (conn) { - if (sp->hdr.securityIndex != conn->security_ix) - goto wrong_security; - - if (sp->hdr.serviceId != conn->service_id) { - int old_id; - - if (!test_bit(RXRPC_CONN_PROBING_FOR_UPGRADE, &conn->flags)) - goto reupgrade; - old_id = cmpxchg(&conn->service_id, conn->params.service_id, - sp->hdr.serviceId); - - if (old_id != conn->params.service_id && - old_id != sp->hdr.serviceId) - goto reupgrade; - } - - if (sp->hdr.callNumber == 0) { - /* Connection-level packet */ - _debug("CONN %p {%d}", conn, conn->debug_id); - rxrpc_post_packet_to_conn(conn, skb); - goto out; - } - - if ((int)sp->hdr.serial - (int)conn->hi_serial > 0) - conn->hi_serial = sp->hdr.serial; - - /* Call-bound packets are routed by connection channel. */ - channel = sp->hdr.cid & RXRPC_CHANNELMASK; - chan = &conn->channels[channel]; - - /* Ignore really old calls */ - if (sp->hdr.callNumber < chan->last_call) - goto discard; - - if (sp->hdr.callNumber == chan->last_call) { - if (chan->call || - sp->hdr.type == RXRPC_PACKET_TYPE_ABORT) - goto discard; - - /* For the previous service call, if completed - * successfully, we discard all further packets. - */ - if (rxrpc_conn_is_service(conn) && - chan->last_type == RXRPC_PACKET_TYPE_ACK) - goto discard; - - /* But otherwise we need to retransmit the final packet - * from data cached in the connection record. - */ - if (sp->hdr.type == RXRPC_PACKET_TYPE_DATA) - trace_rxrpc_rx_data(chan->call_debug_id, - sp->hdr.seq, - sp->hdr.serial, - sp->hdr.flags, 0); - rxrpc_post_packet_to_conn(conn, skb); - goto out; - } - - call = rcu_dereference(chan->call); - - if (sp->hdr.callNumber > chan->call_id) { - if (rxrpc_to_client(sp)) - goto reject_packet; - if (call) - rxrpc_input_implicit_end_call(rx, conn, call); - call = NULL; - } - - if (call) { - if (sp->hdr.serviceId != call->service_id) - call->service_id = sp->hdr.serviceId; - if ((int)sp->hdr.serial - (int)call->rx_serial > 0) - call->rx_serial = sp->hdr.serial; - if (!test_bit(RXRPC_CALL_RX_HEARD, &call->flags)) - set_bit(RXRPC_CALL_RX_HEARD, &call->flags); - } - } - - if (!call || atomic_read(&call->usage) == 0) { - if (rxrpc_to_client(sp) || - sp->hdr.type != RXRPC_PACKET_TYPE_DATA) - goto bad_message; - if (sp->hdr.seq != 1) - goto discard; - call = rxrpc_new_incoming_call(local, rx, skb); - if (!call) - goto reject_packet; - } - - /* Process a call packet; this either discards or passes on the ref - * elsewhere. - */ - rxrpc_input_call_packet(call, skb); - goto out; - -discard: - rxrpc_free_skb(skb, rxrpc_skb_freed); -out: - trace_rxrpc_rx_done(0, 0); - return 0; - -wrong_security: - trace_rxrpc_abort(0, "SEC", sp->hdr.cid, sp->hdr.callNumber, sp->hdr.seq, - RXKADINCONSISTENCY, EBADMSG); - skb->priority = RXKADINCONSISTENCY; - goto post_abort; - -unsupported_service: - trace_rxrpc_abort(0, "INV", sp->hdr.cid, sp->hdr.callNumber, sp->hdr.seq, - RX_INVALID_OPERATION, EOPNOTSUPP); - skb->priority = RX_INVALID_OPERATION; - goto post_abort; - -reupgrade: - trace_rxrpc_abort(0, "UPG", sp->hdr.cid, sp->hdr.callNumber, sp->hdr.seq, - RX_PROTOCOL_ERROR, EBADMSG); - goto protocol_error; - -bad_message: - trace_rxrpc_abort(0, "BAD", sp->hdr.cid, sp->hdr.callNumber, sp->hdr.seq, - RX_PROTOCOL_ERROR, EBADMSG); -protocol_error: - skb->priority = RX_PROTOCOL_ERROR; -post_abort: - skb->mark = RXRPC_SKB_MARK_REJECT_ABORT; -reject_packet: - trace_rxrpc_rx_done(skb->mark, skb->priority); - rxrpc_reject_packet(local, skb); - _leave(" [badmsg]"); - return 0; + rxrpc_input_call_event(call); } |
