summaryrefslogtreecommitdiffhomepage
path: root/src/receive.c
AgeCommit message (Collapse)Author
2017-11-10allowedips: rename from routingtableJason A. Donenfeld
Makes it more clear that this _not_ a routing table replacement. Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
2017-11-10receive: hoist fpu outside of receive loopJason A. Donenfeld
Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
2017-10-31global: use fewer BUG_ONsJason A. Donenfeld
Suggested-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
2017-10-31global: style nitsJason A. Donenfeld
Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
2017-10-31global: accept decent check_patch.pl suggestionsJason A. Donenfeld
Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
2017-10-31stats: more robust accountingJason A. Donenfeld
Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
2017-10-17receive: improve control flowJason A. Donenfeld
Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
2017-10-11receive: disable bh before using stats seq lockJason A. Donenfeld
Otherwise we might get a situation like this: CPU0 CPU1 ---- ---- lock(tstats lock); local_irq_disable(); lock(queue lock); lock(tstats lock); <Interrupt> lock(queue lock); CPU1 is waiting for CPU0 to release tstats lock. But CPU0, in the interrupt handler, is waiting for CPU1 to release queue lock. The solution is to disable interrupts on CPU0, so that this can't happen. Note that this only affects 32-bit, since u64_stats_update_begin nops out on native 64-bit platforms. Reported-by: René van Dorst <opensource@vdorst.com> Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
2017-10-06socket: gcc inlining makes this fasterJason A. Donenfeld
Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
2017-10-06receive: do not consider 0 jiffies as being setJason A. Donenfeld
This causes tests to fail if run within the first 5 minutes. We also move to jiffies 64, so that there's low chance of wrapping in case handshakes are spread far apart. Reported-by: René van Dorst <opensource@vdorst.com> Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
2017-10-05queueing: move from ctx to cbJason A. Donenfeld
Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
2017-10-05receive: do not store endpoint in ctxJason A. Donenfeld
Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
2017-10-05queueing: use ptr_ring instead of linked listsJason A. Donenfeld
Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
2017-10-05receive: we're not planning on turning that into a while loop nowJason A. Donenfeld
Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
2017-10-03receive: use local keypair, not ctx keypair in error pathJason A. Donenfeld
Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
2017-10-03global: add space around variable declarationsJason A. Donenfeld
Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
2017-10-03receive: simplify message type validationJason A. Donenfeld
Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
2017-10-02receive: do not consider netfilter drop a real dropJason A. Donenfeld
Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
2017-09-26receive: mark function staticJason A. Donenfeld
Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
2017-09-19queueing: rename cpumask functionJason A. Donenfeld
Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
2017-09-19queueing: no need to memzero structJason A. Donenfeld
Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
2017-09-19receive: use netif_receive_skb instead of netif_rxJason A. Donenfeld
netif_rx queues things up to a per-cpu backlog, whereas netif_receive_skb immediately delivers the packet to the underlying network device and mostly never fails. In the event where decrypting packets is actually happening faster than the networking subsystem receive them -- like with 65k packets with UDPv6 in `make test-qemu` -- then this backlog fills up and we wind up dropping some packets. This is fine and not all together terrible, but it does raise the question of why we bothered spending CPU cycles decrypting those packets if they were just going to be dropped anyway. So, moving from netif_rx to netif_receive_skb means that whatever time netif_receive_skb needs winds up slowing down the dequeuing of decryption packets, which in turn means the decryption receive queue fills up sooner, so that we drop packets before decryption, rather than after, thus saving precious CPU cycles. Potential downsides of this include not keeping the cache hot, or not inundating the network subsystem with as many packets per second as possible, but in preliminary benchmarks, no difference has yet been observed. Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
2017-09-18queue: entirely rework parallel systemJason A. Donenfeld
This removes our dependency on padata and moves to a different mode of multiprocessing that is more efficient. This began as Samuel Holland's GSoC project and was gradually reworked/redesigned/rebased into this present commit, which is a combination of his initial contribution and my subsequent rewriting and redesigning. Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
2017-09-16send: no need to check for NULL since ref is validJason A. Donenfeld
Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
2017-08-04noise: infer initiator or not from handshake stateJason A. Donenfeld
Suggested-by: Mathias Hall-Andersen <mathias@hall-andersen.dk> Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
2017-08-04timers: rename confusingly named functions and variablesJason A. Donenfeld
Suggested-by: Mathias Hall-Andersen <mathias@hall-andersen.dk> Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
2017-08-04receive: move lastminute guard into timer eventJason A. Donenfeld
Suggested-by: Mathias Hall-Andersen <mathias@hall-andersen.dk> Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
2017-08-01recieve: pskb_trim already checks lengthJason A. Donenfeld
Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
2017-08-01receive: single line if styleJason A. Donenfeld
Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
2017-07-28recieve: cleanup variable usageJason A. Donenfeld
Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
2017-07-20global: use pointer to net_deviceJason A. Donenfeld
DaveM prefers it to be this way per [1]. [1] http://www.spinics.net/lists/netdev/msg443992.html Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
2017-06-29receive: cleanup error handlersJason A. Donenfeld
Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
2017-06-29receive: pull IP header into headJason A. Donenfeld
Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
2017-06-29receive: fix off-by-one in packet length checkingJason A. Donenfeld
This caused certain packets to be rejected that shouldn't be rejected, in the case of certain scatter-gather ethernet drivers doing GRO pulling right up to the UDP bounds but not beyond. This caused certain TCP connections to fail. Thanks very much to Reuben for providing access to the machine to debug this regression. Reported-by: Reuben Martin <reuben.m@gmail.com> Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
2017-06-26global: cleanup IP header checkingJason A. Donenfeld
This way is more correct and ensures we're within the skb head. Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
2017-06-24receive: extend rate limiting to 1 second after under load detectionJason A. Donenfeld
Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
2017-06-01receive: trim incoming packets to IP header lengthJason A. Donenfeld
Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
2017-05-31timers: reset retry-attempt counter when not retryingJason A. Donenfeld
Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
2017-05-31timers: the completion of a handshake also is on key confirmationJason A. Donenfeld
Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
2017-05-31debug: print interface name in dmesgJason A. Donenfeld
Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
2017-05-30handshake: process in parallelJason A. Donenfeld
Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
2017-04-09receive: netif_rx consumesJason A. Donenfeld
Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
2017-04-08data: cleanup parallel workqueue and use two max_activeJason A. Donenfeld
Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
2017-04-04data: simplify flowJason A. Donenfeld
Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
2017-04-04locking: always use _bhJason A. Donenfeld
All locks are potentially between user context and softirq, which means we need to take the _bh variant. Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
2017-03-20data: big refactoringJason A. Donenfeld
Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
2017-02-27receive: last_rx use is discouraged and removed in recent kernelsJason A. Donenfeld
Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
2017-01-10Update copyrightJason A. Donenfeld
Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
2016-12-13peer: don't use sockaddr_storage to reduce memory usageJason A. Donenfeld
Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
2016-12-11receive: simplify ip header checking logicJason A. Donenfeld
Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>