diff options
author | David Howells <dhowells@redhat.com> | 2007-04-26 15:48:28 -0700 |
---|---|---|
committer | David S. Miller <davem@davemloft.net> | 2007-04-26 15:48:28 -0700 |
commit | 17926a79320afa9b95df6b977b40cca6d8713cea (patch) | |
tree | 5cedff43b69520ad17b86783d3752053686ec99c /net/rxrpc/ar-ack.c | |
parent | e19dff1fdd99a25819af74cf0710e147fff4fd3a (diff) |
[AF_RXRPC]: Provide secure RxRPC sockets for use by userspace and kernel both
Provide AF_RXRPC sockets that can be used to talk to AFS servers, or serve
answers to AFS clients. KerberosIV security is fully supported. The patches
and some example test programs can be found in:
http://people.redhat.com/~dhowells/rxrpc/
This will eventually replace the old implementation of kernel-only RxRPC
currently resident in net/rxrpc/.
Signed-off-by: David Howells <dhowells@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Diffstat (limited to 'net/rxrpc/ar-ack.c')
-rw-r--r-- | net/rxrpc/ar-ack.c | 1250 |
1 files changed, 1250 insertions, 0 deletions
diff --git a/net/rxrpc/ar-ack.c b/net/rxrpc/ar-ack.c new file mode 100644 index 000000000000..8f7764eca96c --- /dev/null +++ b/net/rxrpc/ar-ack.c @@ -0,0 +1,1250 @@ +/* Management of Tx window, Tx resend, ACKs and out-of-sequence reception + * + * Copyright (C) 2007 Red Hat, Inc. All Rights Reserved. + * Written by David Howells (dhowells@redhat.com) + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; either version + * 2 of the License, or (at your option) any later version. + */ + +#include <linux/module.h> +#include <linux/circ_buf.h> +#include <linux/net.h> +#include <linux/skbuff.h> +#include <linux/udp.h> +#include <net/sock.h> +#include <net/af_rxrpc.h> +#include "ar-internal.h" + +static unsigned rxrpc_ack_defer = 1; + +static const char *rxrpc_acks[] = { + "---", "REQ", "DUP", "OOS", "WIN", "MEM", "PNG", "PNR", "DLY", "IDL", + "-?-" +}; + +static const s8 rxrpc_ack_priority[] = { + [0] = 0, + [RXRPC_ACK_DELAY] = 1, + [RXRPC_ACK_REQUESTED] = 2, + [RXRPC_ACK_IDLE] = 3, + [RXRPC_ACK_PING_RESPONSE] = 4, + [RXRPC_ACK_DUPLICATE] = 5, + [RXRPC_ACK_OUT_OF_SEQUENCE] = 6, + [RXRPC_ACK_EXCEEDS_WINDOW] = 7, + [RXRPC_ACK_NOSPACE] = 8, +}; + +/* + * propose an ACK be sent + */ +void __rxrpc_propose_ACK(struct rxrpc_call *call, uint8_t ack_reason, + __be32 serial, bool immediate) +{ + unsigned long expiry; + s8 prior = rxrpc_ack_priority[ack_reason]; + + ASSERTCMP(prior, >, 0); + + _enter("{%d},%s,%%%x,%u", + call->debug_id, rxrpc_acks[ack_reason], ntohl(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_serial = serial; + if (immediate) + goto cancel_timer; + return; + } + + call->ackr_reason = ack_reason; + call->ackr_serial = serial; + + switch (ack_reason) { + case RXRPC_ACK_DELAY: + _debug("run delay timer"); + call->ack_timer.expires = jiffies + rxrpc_ack_timeout * HZ; + add_timer(&call->ack_timer); + return; + + case RXRPC_ACK_IDLE: + if (!immediate) { + _debug("run defer timer"); + expiry = 1; + goto run_timer; + } + goto cancel_timer; + + case RXRPC_ACK_REQUESTED: + if (!rxrpc_ack_defer) + goto cancel_timer; + if (!immediate || serial == cpu_to_be32(1)) { + _debug("run defer timer"); + expiry = rxrpc_ack_defer; + goto run_timer; + } + + default: + _debug("immediate ACK"); + goto cancel_timer; + } + +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", ntohl(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_ACK, &call->events)) + schedule_work(&call->processor); + read_unlock_bh(&call->state_lock); +} + +/* + * propose an ACK be sent, locking the call structure + */ +void rxrpc_propose_ACK(struct rxrpc_call *call, uint8_t ack_reason, + __be32 serial, bool immediate) +{ + 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, serial, immediate); + 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_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_RESEND_TIMER, &call->events); + clear_bit(RXRPC_CALL_RUN_RTIMER, &call->flags); + } + read_unlock_bh(&call->state_lock); +} + +/* + * resend packets + */ +static void rxrpc_resend(struct rxrpc_call *call) +{ + struct rxrpc_skb_priv *sp; + struct rxrpc_header *hdr; + struct sk_buff *txb; + unsigned long *p_txb, resend_at; + int loop, stop; + 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 = 0; + 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 = 0; + + /* each Tx packet has a new serial number */ + sp->hdr.serial = + htonl(atomic_inc_return(&call->conn->serial)); + + hdr = (struct rxrpc_header *) txb->head; + hdr->serial = sp->hdr.serial; + + _proto("Tx DATA %%%u { #%d }", + ntohl(sp->hdr.serial), ntohl(sp->hdr.seq)); + if (rxrpc_send_packet(call->conn->trans, txb) < 0) { + stop = 0; + sp->resend_at = jiffies + 3; + } else { + sp->resend_at = + jiffies + rxrpc_resend_timeout * HZ; + } + } + + if (time_after_eq(jiffies + 1, sp->resend_at)) { + sp->need_resend = 1; + 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); + + 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 = 1; + 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 = 0; + *p_txb |= 1; + break; + case RXRPC_ACK_TYPE_NACK: + sp->need_resend = 1; + *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 = 1; + *p_txb &= ~1; + resend |= 1; + } else if (sp->need_resend) { + ; + } else if (time_after_eq(jiffies + 1, sp->resend_at)) { + sp->need_resend = 1; + 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) +{ + struct rxrpc_skb_priv *sp; + 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; + sp = rxrpc_skb((struct sk_buff *) _skb); + 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->tx_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; + + _enter("{%d,%d}", call->rx_data_post, call->rx_first_oos); + + spin_lock_bh(&call->lock); + + ret = -ECONNRESET; + if (test_bit(RXRPC_CALL_RELEASED, &call->flags)) + goto socket_unavailable; + + skb = skb_dequeue(&call->rx_oos_queue); + if (skb) { + sp = rxrpc_skb(skb); + + _debug("drain OOS packet %d [%d]", + ntohl(sp->hdr.seq), call->rx_first_oos); + + if (ntohl(sp->hdr.seq) != call->rx_first_oos) { + skb_queue_head(&call->rx_oos_queue, skb); + call->rx_first_oos = ntohl(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); + if (skb) + call->rx_first_oos = + ntohl(rxrpc_skb(skb)->hdr.seq); + else + call->rx_first_oos = 0; + _debug("peek %p {%u}", skb, call->rx_first_oos); + } + } + + ret = 0; +socket_unavailable: + spin_unlock_bh(&call->lock); + _leave(" = %d", ret); + return ret; +} + +/* + * 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; + + sp = rxrpc_skb(skb); + seq = ntohl(sp->hdr.seq); + _enter(",,{%u}", seq); + + skb->destructor = rxrpc_packet_destructor; + ASSERTCMP(sp->call, ==, NULL); + sp->call = call; + rxrpc_get_call(call); + + /* 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 (ntohl(psp->hdr.seq) > seq) { + _debug("insert oos #%u before #%u", + seq, ntohl(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_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; + uint8_t 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; + sp = rxrpc_skb(skb); + _debug("+++ clear Tx %u", ntohl(sp->hdr.seq)); + rxrpc_free_skb(skb); + } + + kfree(acks_window); +} + +/* + * 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; + + _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 }", + ntohl(sp->hdr.serial), ntohl(sp->hdr.seq)); + + /* secured packets must be verified and possibly decrypted */ + if (rxrpc_verify_packet(call, skb, _abort_code) < 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 = ntohl(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); + + if (ack.reason == RXRPC_ACK_PING) { + _proto("Rx ACK %%%u PING Request", latest); + rxrpc_propose_ACK(call, RXRPC_ACK_PING_RESPONSE, + 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) + 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"); + call->state = RXRPC_CALL_COMPLETE; + 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_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(call); + 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; + +protocol_error_unlock: + write_unlock_bh(&call->state_lock); +protocol_error: + rxrpc_free_skb(skb); + _leave(" = -EPROTO"); + return -EPROTO; +} + +/* + * 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(call); + + spin_lock_bh(&call->lock); + ret = rxrpc_queue_rcv_skb(call, skb, true, fatal); + spin_unlock_bh(&call->lock); + if (ret < 0) + BUG(); + } + + return 0; +} + +/* + * handle background processing of incoming call packets and ACK / abort + * generation + */ +void rxrpc_process_call(struct work_struct *work) +{ + struct rxrpc_call *call = + container_of(work, struct rxrpc_call, processor); + struct rxrpc_ackpacket ack; + struct rxrpc_ackinfo ackinfo; + struct rxrpc_header hdr; + struct msghdr msg; + struct kvec iov[5]; + unsigned long bits; + __be32 data; + size_t len; + int genbit, loop, nbit, ioc, ret; + u32 abort_code = RX_PROTOCOL_ERROR; + u8 *acks = NULL; + + //printk("\n--------------------\n"); + _enter("{%d,%s,%lx} [%lu]", + call->debug_id, rxrpc_call_states[call->state], call->events, + (jiffies - call->creation_jif) / (HZ / 10)); + + if (test_and_set_bit(RXRPC_CALL_PROC_BUSY, &call->flags)) { + _debug("XXXXXXXXXXXXX RUNNING ON MULTIPLE CPUS XXXXXXXXXXXXX"); + return; + } + + /* there's a good chance we're going to have to send a message, so set + * one up in advance */ + msg.msg_name = &call->conn->trans->peer->srx.transport.sin; + msg.msg_namelen = sizeof(call->conn->trans->peer->srx.transport.sin); + msg.msg_control = NULL; + msg.msg_controllen = 0; + msg.msg_flags = 0; + + hdr.epoch = call->conn->epoch; + hdr.cid = call->cid; + hdr.callNumber = call->call_id; + hdr.seq = 0; + hdr.type = RXRPC_PACKET_TYPE_ACK; + hdr.flags = call->conn->out_clientflag; + hdr.userStatus = 0; + hdr.securityIndex = call->conn->security_ix; + hdr._rsvd = 0; + hdr.serviceId = call->conn->service_id; + + memset(iov, 0, sizeof(iov)); + iov[0].iov_base = &hdr; + iov[0].iov_len = sizeof(hdr); + + /* deal with events of a final nature */ + if (test_bit(RXRPC_CALL_RELEASE, &call->events)) { + rxrpc_release_call(call); + clear_bit(RXRPC_CALL_RELEASE, &call->events); + } + + if (test_bit(RXRPC_CALL_RCVD_ERROR, &call->events)) { + int error; + + clear_bit(RXRPC_CALL_CONN_ABORT, &call->events); + clear_bit(RXRPC_CALL_REJECT_BUSY, &call->events); + clear_bit(RXRPC_CALL_ABORT, &call->events); + + error = call->conn->trans->peer->net_error; + _debug("post net error %d", error); + + if (rxrpc_post_message(call, RXRPC_SKB_MARK_NET_ERROR, + error, true) < 0) + goto no_mem; + clear_bit(RXRPC_CALL_RCVD_ERROR, &call->events); + goto kill_ACKs; + } + + if (test_bit(RXRPC_CALL_CONN_ABORT, &call->events)) { + ASSERTCMP(call->state, >, RXRPC_CALL_COMPLETE); + + clear_bit(RXRPC_CALL_REJECT_BUSY, &call->events); + clear_bit(RXRPC_CALL_ABORT, &call->events); + + _debug("post conn abort"); + + if (rxrpc_post_message(call, RXRPC_SKB_MARK_LOCAL_ERROR, + call->conn->error, true) < 0) + goto no_mem; + clear_bit(RXRPC_CALL_CONN_ABORT, &call->events); + goto kill_ACKs; + } + + if (test_bit(RXRPC_CALL_REJECT_BUSY, &call->events)) { + hdr.type = RXRPC_PACKET_TYPE_BUSY; + genbit = RXRPC_CALL_REJECT_BUSY; + goto send_message; + } + + if (test_bit(RXRPC_CALL_ABORT, &call->events)) { + ASSERTCMP(call->state, >, RXRPC_CALL_COMPLETE); + + if (rxrpc_post_message(call, RXRPC_SKB_MARK_LOCAL_ERROR, + ECONNABORTED, true) < 0) + goto no_mem; + hdr.type = RXRPC_PACKET_TYPE_ABORT; + data = htonl(call->abort_code); + iov[1].iov_base = &data; + iov[1].iov_len = sizeof(data); + genbit = RXRPC_CALL_ABORT; + goto send_message; + } + + if (test_bit(RXRPC_CALL_ACK_FINAL, &call->events)) { + hdr.type = RXRPC_PACKET_TYPE_ACKALL; + genbit = RXRPC_CALL_ACK_FINAL; + goto send_message; + } + + if (call->events & ((1 << RXRPC_CALL_RCVD_BUSY) | + (1 << RXRPC_CALL_RCVD_ABORT)) + ) { + u32 mark; + + if (test_bit(RXRPC_CALL_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_RCVD_BUSY, &call->events); + clear_bit(RXRPC_CALL_RCVD_ABORT, &call->events); + goto kill_ACKs; + } + + if (test_and_clear_bit(RXRPC_CALL_RCVD_ACKALL, &call->events)) { + _debug("do implicit ackall"); + rxrpc_clear_tx_window(call); + } + + if (test_bit(RXRPC_CALL_LIFE_TIMER, &call->events)) { + write_lock_bh(&call->state_lock); + if (call->state <= RXRPC_CALL_COMPLETE) { + call->state = RXRPC_CALL_LOCALLY_ABORTED; + call->abort_code = RX_CALL_TIMEOUT; + set_bit(RXRPC_CALL_ABORT, &call->events); + } + write_unlock_bh(&call->state_lock); + + _debug("post timeout"); + if (rxrpc_post_message(call, RXRPC_SKB_MARK_LOCAL_ERROR, + ETIME, true) < 0) + goto no_mem; + + clear_bit(RXRPC_CALL_LIFE_TIMER, &call->events); + goto kill_ACKs; + } + + /* deal with assorted inbound messages */ + if (!skb_queue_empty(&call->rx_queue)) { + switch (rxrpc_process_rx_queue(call, &abort_code)) { + case 0: + case -EAGAIN: + break; + case -ENOMEM: + goto no_mem; + case -EKEYEXPIRED: + case -EKEYREJECTED: + case -EPROTO: + rxrpc_abort_call(call, abort_code); + goto kill_ACKs; + } + } + + /* handle resending */ + if (test_and_clear_bit(RXRPC_CALL_RESEND_TIMER, &call->events)) + rxrpc_resend_timer(call); + if (test_and_clear_bit(RXRPC_CALL_RESEND, &call->events)) + rxrpc_resend(call); + + /* consider sending an ordinary ACK */ + if (test_bit(RXRPC_CALL_ACK, &call->events)) { + __be32 pad; + + _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_ACK, &call->events); + goto maybe_reschedule; + } + + genbit = RXRPC_CALL_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; + ack.serial = 0; + ack.reason = 0; + + ackinfo.rxMTU = htonl(5692); +// ackinfo.rxMTU = htonl(call->conn->trans->peer->maxdata); + ackinfo.maxMTU = htonl(call->conn->trans->peer->maxdata); + ackinfo.rwind = htonl(32); + ackinfo.jumbo_max = htonl(4); + + spin_lock_bh(&call->lock); + ack.reason = call->ackr_reason; + ack.serial = call->ackr_serial; + ack.previousPacket = 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; + } + } + + /* handle completion of security negotiations on an incoming + * connection */ + if (test_and_clear_bit(RXRPC_CALL_SECURED, &call->events)) { + _debug("secured"); + spin_lock_bh(&call->lock); + + if (call->state == RXRPC_CALL_SERVER_SECURING) { + _debug("securing"); + write_lock(&call->conn->lock); + if (!test_bit(RXRPC_CALL_RELEASED, &call->flags) && + !test_bit(RXRPC_CALL_RELEASE, &call->events)) { + _debug("not released"); + call->state = RXRPC_CALL_SERVER_ACCEPTING; + list_move_tail(&call->accept_link, + &call->socket->acceptq); + } + write_unlock(&call->conn->lock); + read_lock(&call->state_lock); + if (call->state < RXRPC_CALL_COMPLETE) + set_bit(RXRPC_CALL_POST_ACCEPT, &call->events); + read_unlock(&call->state_lock); + } + + spin_unlock_bh(&call->lock); + if (!test_bit(RXRPC_CALL_POST_ACCEPT, &call->events)) + goto maybe_reschedule; + } + + /* post a notification of an acceptable connection to the app */ + if (test_bit(RXRPC_CALL_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_POST_ACCEPT, &call->events); + goto maybe_reschedule; + } + + /* handle incoming call acceptance */ + if (test_and_clear_bit(RXRPC_CALL_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_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_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; + } + + /* other events may have been raised since we started checking */ + goto maybe_reschedule; + +send_ACK_with_skew: + ack.maxSkew = htons(atomic_read(&call->conn->hi_serial) - + ntohl(ack.serial)); +send_ACK: + hdr.serial = htonl(atomic_inc_return(&call->conn->serial)); + _proto("Tx ACK %%%u { m=%hu f=#%u p=#%u s=%%%u r=%s n=%u }", + ntohl(hdr.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"); + + hdr.serial = htonl(atomic_inc_return(&call->conn->serial)); + _proto("Tx %s %%%u", rxrpc_pkts[hdr.type], ntohl(hdr.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->trans->local->socket, + &msg, iov, ioc, len); + if (ret < 0) { + _debug("sendmsg failed: %d", ret); + read_lock_bh(&call->state_lock); |