Commit message (Collapse) | Author | Files | Lines | ||
---|---|---|---|---|---|
2018-06-21 | mpmc_ptr_ring: add {,un}likely() annotations | Thomas Gschwantner | 1 | -3/+3 | |
2018-06-20 | mpmc_ptr_ring: use atomic_try_cmpxchg() | Thomas Gschwantner | 3 | -12/+37 | |
2018-06-17 | mpmc_ptr_ring: Fix a word | Jonathan Neuschäfer | 1 | -1/+1 | |
Signed-off-by: Jonathan Neuschäfer <j.neuschaefer@gmx.net> | |||||
2018-06-14 | selftest/mpmc_ring: Add more __init/__initdata annotations | Jonathan Neuschäfer | 1 | -3/+3 | |
The main function, mpmc_ring_selftest, is already marked with __init, but the callback functions and the ring pointer were not. | |||||
2018-06-12 | selftest/mpmc_ring: Remove const qualifier from mpmc_ptr_ring_produce argument | Jonathan Neuschäfer | 1 | -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)) ^ | |||||
2018-06-12 | mpmc_ptr_ring: Include all necessary headers | Jonathan Neuschäfer | 1 | -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> | |||||
2018-06-12 | mpmc_ptr_ring: Fix some style details | Jonathan Neuschäfer | 2 | -1/+2 | |
2018-06-11 | mpmc_ptr_ring: add selftest | Thomas Gschwantner | 4 | -1/+125 | |
2018-06-10 | mpmc_ptr_ring: calculate mask once and store it | Thomas Gschwantner | 1 | -3/+5 | |
2018-06-10 | mpmc_ptr_ring: use unsigned int instead of size_t | Thomas Gschwantner | 1 | -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. | |||||
2018-06-10 | mpmc_ptr_ring: add include guard | Thomas Gschwantner | 1 | -0/+6 | |
2018-06-08 | mpmc_ptr_ring: Switch to smp_[rw]mb() | Jonathan Neuschäfer | 1 | -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> | |||||
2018-06-04 | messages: Ensure that there are more queue slots than CPUs | Jonathan Neuschäfer | 2 | -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. | |||||
2018-06-04 | mpmc_ptr_ring: Place producer_head and producer_tail in the same cacheline | Jonathan Neuschäfer | 1 | -5/+3 | |
They are updated together, so it doesn't make much sense to keep them separate in the cache. | |||||
2018-06-04 | mpmc_ptr_ring: Use atomic_t instead of atomic_long_t | Jonathan Neuschäfer | 1 | -20/+20 | |
The index range doesn't get large enough to warrant 64-bit indices. | |||||
2018-06-04 | mpmc_ptr_ring: Eliminate false sharing in struct mpmc_ptr_ring | Jonathan Neuschäfer | 1 | -3/+3 | |
2018-06-04 | mpmc_ptr_ring: Reduce the memory barrier usage | Jonathan Neuschäfer | 1 | -26/+22 | |
2018-06-04 | mpmc_ptr_ring: Fix the remaining crash | Jonathan Neuschäfer | 1 | -2/+2 | |
2018-06-04 | [WIP] Implement a lock-free MPMC ring buffer | Jonathan Neuschäfer | 6 | -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 | |||||
2018-06-04 | wg-quick: android: change name of intent | Jason A. Donenfeld | 1 | -1/+1 | |
2018-06-02 | chacha20: add missing include to header | Jason A. Donenfeld | 1 | -0/+1 | |
2018-05-31 | wg-quick: android: delay setting users until end | Jason A. Donenfeld | 1 | -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. | |||||
2018-05-31 | version: bump snapshot0.0.20180531 | Jason A. Donenfeld | 2 | -2/+2 | |
2018-05-31 | qemu: bump default version | Jason A. Donenfeld | 1 | -1/+1 | |
2018-05-31 | tools: constanter time encoding | Jason A. Donenfeld | 2 | -22/+28 | |
2018-05-31 | device: do not assume dst is always valid | Jason A. Donenfeld | 1 | -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. | |||||
2018-05-31 | poly1305: mips: compute S on fly | René van Dorst | 1 | -31/+22 | |
This reduces memory access and the total opaque size. Signed-off-by: René van Dorst <opensource@vdorst.com> | |||||
2018-05-31 | chacha20poly1305: test for authtag failure | Jason A. Donenfeld | 1 | -3/+21 | |
2018-05-31 | chacha20poly1305: test scattergather functions too | Jason A. Donenfeld | 1 | -2/+44 | |
2018-05-31 | crypto: consistent constification | Jason A. Donenfeld | 6 | -23/+23 | |
2018-05-31 | wg-quick: darwin: set DNS servers after delay on route change | Jason A. Donenfeld | 1 | -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. | |||||
2018-05-31 | chacha20poly1305: combine stack variables into union | Jason A. Donenfeld | 2 | -62/+64 | |
2018-05-31 | chacha20poly1305: split up into separate files | Jason A. Donenfeld | 10 | -627/+740 | |
2018-05-29 | curve25519: x86_64: make symbol static | Jason A. Donenfeld | 1 | -2/+2 | |
2018-05-29 | curve25519: x86_64: satisfy sparse | Jason A. Donenfeld | 1 | -260/+260 | |
2018-05-27 | wg-quick: freebsd: configure as p2p link | Jason A. Donenfeld | 1 | -3/+5 | |
2018-05-27 | wg-quick: darwin: add multiple IP addresses | Jason A. Donenfeld | 1 | -2/+2 | |
2018-05-27 | wg-quick: determine IPs when saving interface | Jason A. Donenfeld | 3 | -12/+14 | |
2018-05-24 | compat: don't clash with get_random_u32 backports | Jason A. Donenfeld | 1 | -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. | |||||
2018-05-24 | version: bump snapshot0.0.20180524 | Jason A. Donenfeld | 2 | -2/+2 | |
2018-05-24 | wg-quick: freebsd: work around security vulnerabilities in bash | Jason A. Donenfeld | 1 | -7/+29 | |
2018-05-23 | wg-quick: allow enumeration of socket files | Jason A. Donenfeld | 2 | -2/+2 | |
These OSes have an unpriv'd ifconfig, so this isn't an even larger info leak. | |||||
2018-05-23 | wg-quick: better bash completion for non-renaming OSes | Jason A. Donenfeld | 1 | -5/+14 | |
2018-05-23 | wg-quick: support FreeBSD/Darwin search path | Jason A. Donenfeld | 4 | -16/+39 | |
2018-05-23 | tools: always pass -v as first argument to install | Jason A. Donenfeld | 1 | -7/+7 | |
This lets crippled OSes sed out our -v more easily. |