aboutsummaryrefslogtreecommitdiffstatshomepage
path: root/src (follow)
Commit message (Collapse)AuthorAgeFilesLines
* [BROKEN] mpmc_ptr_ring: Rely on null pointers to avoid p_tailjn/mpmc-nullJonathan Neuschäfer2018-06-211-38/+23
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | This should fix a performance problem when two (or more) producers run on the same CPU. [ TODO: more text ] previously: Thread A Thread B producer_head=1 write item <preemptive context switch> producer_head=2 write item <stalled because producer_tail is still 0> <preemptive context switch> producer_tail=1 producer_head=3 write item <stalled because producer_tail is still 1> ... with this patch: Thread A Thread B producer_head=1 write item <preemptive context switch> producer_head=2 write item producer_head=3 write item producer_head=4 write item producer_head=5 write item <preemptive context switch> producer_head=6 write item producer_head=7 write item ...
* mpmc_ptr_ring: add {,un}likely() annotationsThomas Gschwantner2018-06-211-3/+3
|
* mpmc_ptr_ring: use atomic_try_cmpxchg()Thomas Gschwantner2018-06-203-12/+37
|
* mpmc_ptr_ring: Fix a wordJonathan Neuschäfer2018-06-171-1/+1
| | | | Signed-off-by: Jonathan Neuschäfer <j.neuschaefer@gmx.net>
* selftest/mpmc_ring: Add more __init/__initdata annotationsJonathan Neuschäfer2018-06-141-3/+3
| | | | | The main function, mpmc_ring_selftest, is already marked with __init, but the callback functions and the ring pointer were not.
* selftest/mpmc_ring: Remove const qualifier from mpmc_ptr_ring_produce argumentJonathan Neuschäfer2018-06-121-1/+1
| | | | | | | | | | | mpmc_ptr_ring_produce takes a void*. This fixes the following warning: net/wireguard/selftest/mpmc_ring.h: In function ‘producer_function’: net/wireguard/selftest/mpmc_ring.h:43:38: warning: passing argument 2 of ‘mpmc_ptr_ring_produce’ disc] while (mpmc_ptr_ring_produce(ring, (const void *) count)) ^
* mpmc_ptr_ring: Include all necessary headersJonathan Neuschäfer2018-06-121-0/+11
| | | | | | | | | | | | | | | | | | | | mpmc_ptr_ring.h should include the headers that it needs explicitly. This commit adds the following: - <asm/barrier.h>: smp_rmb, smp_wmb, smp_mb__before_atomic - <linux/atomic.h>: atomic_t, atomic_read, atomic_set, atomic_cmpxchg, atomic_inc - <linux/cache.h>: ____cacheline_aligned_in_smp - <linux/compiler.h>: READ_ONCE, WRITE_ONCE - <linux/errno.h>: ENOMEM - <linux/log2.h>: is_power_of_2 - <linux/processor.h>: cpu_relax - <linux/slab.h>: kcalloc, kfree - <linux/stddef.h>: NULL I'm not sure if all of them are really needed because I wasn't about to provoke a compile error due to the missing includes. Signed-off-by: Jonathan Neuschäfer <j.neuschaefer@gmx.net>
* mpmc_ptr_ring: Fix some style detailsJonathan Neuschäfer2018-06-122-1/+2
|
* mpmc_ptr_ring: add selftestThomas Gschwantner2018-06-114-1/+125
|
* mpmc_ptr_ring: calculate mask once and store itThomas Gschwantner2018-06-101-3/+5
|
* mpmc_ptr_ring: use unsigned int instead of size_tThomas Gschwantner2018-06-101-10/+10
| | | | | | | | For producers/consumers we use atomic_t which is really int, so size_t could either be too large, wasting memory, or too small (unlikely). For size, we also want to be using unsigned int, since the mask that we derive from it is ANDed with producer/consumer.
* mpmc_ptr_ring: add include guardThomas Gschwantner2018-06-101-0/+6
|
* mpmc_ptr_ring: Switch to smp_[rw]mb()Jonathan Neuschäfer2018-06-081-8/+8
| | | | | | | | | | | | | | From https://www.kernel.org/doc/Documentation/memory-barriers.txt: > SMP memory barriers are reduced to compiler barriers on uniprocessor > compiled systems because it is assumed that a CPU will appear to be > self-consistent, and will order overlapping accesses correctly with > respect to itself. Since we only order CPU memory accesses with the memory barriers in mpmc_ptr_ring.h, smp_[rw]mb() should be sufficient. Signed-off-by: Jonathan Neuschäfer <j.neuschaefer@gmx.net>
* messages: Ensure that there are more queue slots than CPUsJonathan Neuschäfer2018-06-042-1/+9
| | | | | | | I'm not completely sure about this. It also doesn't fix all the errors: sometimes the test suite reports that it fails to send packets.
* mpmc_ptr_ring: Place producer_head and producer_tail in the same cachelineJonathan Neuschäfer2018-06-041-5/+3
| | | | | They are updated together, so it doesn't make much sense to keep them separate in the cache.
* mpmc_ptr_ring: Use atomic_t instead of atomic_long_tJonathan Neuschäfer2018-06-041-20/+20
| | | | The index range doesn't get large enough to warrant 64-bit indices.
* mpmc_ptr_ring: Eliminate false sharing in struct mpmc_ptr_ringJonathan Neuschäfer2018-06-041-3/+3
|
* mpmc_ptr_ring: Reduce the memory barrier usageJonathan Neuschäfer2018-06-041-26/+22
|
* mpmc_ptr_ring: Fix the remaining crashJonathan Neuschäfer2018-06-041-2/+2
|
* [WIP] Implement a lock-free MPMC ring bufferJonathan Neuschäfer2018-06-046-17/+225
| | | | | | | | TODO: actually use the right memory barriers in the right places TODO: eliminate false sharing between mpmc_ptr_ring members TODO: reconsider atomic_long_t vs. atomic_t, vs. the type of size in _init() TODO: sprinkle likely/unlikely on some branches FIXME: it still crashes
* wg-quick: android: change name of intentJason A. Donenfeld2018-06-041-1/+1
|
* chacha20: add missing include to headerJason A. Donenfeld2018-06-021-0/+1
|
* wg-quick: android: delay setting users until endJason A. Donenfeld2018-05-311-1/+6
| | | | | | | `ndc users add` eventually invokes SOCK_DESTROY on user sockets, causing them to reconnect. By delaying this until after routes are set, we ensure that the sockets reconnect using the tunnel, rather than the old route.
* version: bump snapshot0.0.20180531Jason A. Donenfeld2018-05-312-2/+2
|
* qemu: bump default versionJason A. Donenfeld2018-05-311-1/+1
|
* tools: constanter time encodingJason A. Donenfeld2018-05-311-15/+21
|
* device: do not assume dst is always validJason A. Donenfeld2018-05-311-1/+1
| | | | | | The new flow offloading feature at the moment does not set the dst. We have a patch pending to fix this upstream, but in the meantime, work around it here.
* poly1305: mips: compute S on flyRené van Dorst2018-05-311-31/+22
| | | | | | This reduces memory access and the total opaque size. Signed-off-by: René van Dorst <opensource@vdorst.com>
* chacha20poly1305: test for authtag failureJason A. Donenfeld2018-05-311-3/+21
|
* chacha20poly1305: test scattergather functions tooJason A. Donenfeld2018-05-311-2/+44
|
* crypto: consistent constificationJason A. Donenfeld2018-05-316-23/+23
|
* wg-quick: darwin: set DNS servers after delay on route changeJason A. Donenfeld2018-05-311-2/+6
| | | | | | This works around a race condition in macOS's network daemons, while also adding one in the form of possibly calling kill -ALRM on a stale PID; unfortunately bash can't wait from a trap.
* chacha20poly1305: combine stack variables into unionJason A. Donenfeld2018-05-312-62/+64
|
* chacha20poly1305: split up into separate filesJason A. Donenfeld2018-05-3110-627/+740
|
* curve25519: x86_64: make symbol staticJason A. Donenfeld2018-05-291-2/+2
|
* curve25519: x86_64: satisfy sparseJason A. Donenfeld2018-05-291-260/+260
|
* wg-quick: freebsd: configure as p2p linkJason A. Donenfeld2018-05-271-3/+5
|
* wg-quick: darwin: add multiple IP addressesJason A. Donenfeld2018-05-271-2/+2
|
* wg-quick: determine IPs when saving interfaceJason A. Donenfeld2018-05-273-12/+14
|
* compat: don't clash with get_random_u32 backportsJason A. Donenfeld2018-05-241-3/+2
| | | | | | Our previous heuristic wasn't good enough, since CopperheadOS backported CANARY_MASK without backporting get_random_u32, as Qualcomm did, so now we just entirely rename all invocations of the function.
* version: bump snapshot0.0.20180524Jason A. Donenfeld2018-05-242-2/+2
|
* wg-quick: freebsd: work around security vulnerabilities in bashJason A. Donenfeld2018-05-241-7/+29
|
* wg-quick: allow enumeration of socket filesJason A. Donenfeld2018-05-232-2/+2
| | | | | These OSes have an unpriv'd ifconfig, so this isn't an even larger info leak.
* wg-quick: better bash completion for non-renaming OSesJason A. Donenfeld2018-05-231-5/+14
|
* wg-quick: support FreeBSD/Darwin search pathJason A. Donenfeld2018-05-234-16/+39
|
* tools: always pass -v as first argument to installJason A. Donenfeld2018-05-231-7/+7
| | | | This lets crippled OSes sed out our -v more easily.
* wg-quick: openbsd: add new implementationJason A. Donenfeld2018-05-221-0/+451
|
* wg-quick: freebsd: add new implementationJason A. Donenfeld2018-05-222-16/+434
|
* wg-quick: darwin: do not remove routes when no real interfaceJason A. Donenfeld2018-05-221-0/+1
|
* wg-quick: darwin: rename namefile environment variableJason A. Donenfeld2018-05-221-1/+1
| | | | This paves the way for an openbsd implementation.