aboutsummaryrefslogtreecommitdiffstatshomepage
path: root/src/data.c (follow)
Commit message (Collapse)AuthorAgeFilesLines
* data: simplify no-keypair failure caseSamuel Holland2017-07-201-5/+2
| | | | Signed-off-by: Samuel Holland <samuel@sholland.org>
* data: use KMEM_CACHE macroJason A. Donenfeld2017-07-201-2/+2
| | | | Suggested-by: Samuel Holland <samuel@sholland.org>
* global: use pointer to net_deviceJason A. Donenfeld2017-07-201-1/+1
| | | | | | DaveM prefers it to be this way per [1]. [1] http://www.spinics.net/lists/netdev/msg443992.html
* counter: use correct unit for indicesJason A. Donenfeld2017-07-061-3/+3
| | | | | Even though redundant bits == bits per long, we're indexing into something that uses longs as its unit, so this is correct.
* main: annotate init/exit functions to save memoryJason A. Donenfeld2017-06-241-1/+1
|
* receive: trim incoming packets to IP header lengthJason A. Donenfeld2017-06-011-1/+1
|
* debug: print interface name in dmesgJason A. Donenfeld2017-05-311-1/+1
|
* data: enable BH during parallel crypto on ARM/NEONJason A. Donenfeld2017-05-311-0/+12
| | | | | | padata disables it, but in order to use SIMD on ARM, we can't be in an interrupt. We only do this on ARM since it adds jitter to the performance.
* style: spaces after for loopsJason A. Donenfeld2017-05-301-2/+2
|
* data: alloca is actually as dangerous as they sayJason A. Donenfeld2017-04-091-6/+4
| | | | | | | | | | | | | It turns out that calling alloca from an inline function means that the memory isn't ever deallocated until the caller function exits, which means we were using tons of stack space for every iteration of the call. So, we hard code the sg array. While 128 seems like a reasonable number, we actually wind up using "MAX_SKB_FRAGS * 2 + 1". An skb has its data segment, so that's 1. Then it has its frags, which are MAX_SKB_FRAGS at max. Then it has its frag list, which, so far as I can tell, are potentially unbounded. So we just hope it's no more than MAX_SKB_FRAGS, and so we plan for at most two of those.
* data: cleanup parallel workqueue and use two max_activeJason A. Donenfeld2017-04-081-2/+2
|
* data: simplify flowJason A. Donenfeld2017-04-041-81/+36
|
* chacha20poly1305: check return values of sgopsJason A. Donenfeld2017-04-041-5/+5
|
* locking: always use _bhJason A. Donenfeld2017-04-041-6/+6
| | | | | All locks are potentially between user context and softirq, which means we need to take the _bh variant.
* data: big refactoringJason A. Donenfeld2017-03-201-96/+71
|
* data: transition to skb_reset_tc for 4.11Jason A. Donenfeld2017-02-271-3/+1
|
* Use __read_mostly attribute when possibleJason A. Donenfeld2017-01-131-2/+2
|
* Update copyrightJason A. Donenfeld2017-01-101-1/+1
|
* messages: increase header by 3 bytes for alignmentJason A. Donenfeld2016-12-161-1/+1
|
* types: enforce consistencyJason A. Donenfeld2016-12-161-5/+5
|
* global: move to consistent use of uN instead of uintN_t for kernel codeJason A. Donenfeld2016-12-111-8/+8
|
* data: reset tc when resetting skbJason A. Donenfeld2016-12-091-0/+6
|
* headers: cleanup noticesJason A. Donenfeld2016-11-211-1/+1
|
* various: nits from willyJason A. Donenfeld2016-11-151-4/+2
|
* socket: keep track of src address in sending packetsJason A. Donenfeld2016-11-151-8/+8
|
* data: only uses kmem_cache for parallismJason A. Donenfeld2016-11-061-0/+2
|
* data: squelch compiler warning on PARALLEL=nJason A. Donenfeld2016-11-061-1/+1
|
* data: we care about per-peer, not per-device, inflight encryptionsJason A. Donenfeld2016-11-061-1/+4
|
* data: use a memory cache for parallel ctxJason A. Donenfeld2016-11-041-60/+81
|
* data: keep FPU on when possibleJason A. Donenfeld2016-11-041-7/+5
|
* send: queue bundles on same CPUJason A. Donenfeld2016-11-041-54/+95
|
* data: use smaller typesJason A. Donenfeld2016-11-041-6/+6
|
* data: take reference to peerJason A. Donenfeld2016-11-041-1/+8
|
* data: do not allow usage of keypair just before hash removalJason A. Donenfeld2016-11-011-4/+2
|
* data: reset all packet fields like tun.cJason A. Donenfeld2016-10-231-2/+2
|
* send: only avoid parallel path when there aren't inflight jobsJason A. Donenfeld2016-10-021-1/+1
| | | | Otherwise we get packet reordering.
* Rework headers and includesJason A. Donenfeld2016-09-291-3/+5
|
* selftest: move to subfolderJason A. Donenfeld2016-08-021-88/+1
|
* tests: make fatalJason A. Donenfeld2016-06-251-1/+2
|
* nonce: switch to RFC6479 to better support packet reorderingJason A. Donenfeld2016-06-251-58/+86
| | | | | With packets hitting multiple cores, a 64bit backtrack was too small. This algorithm increases our backtrack to 1984bits.
* Initial commitJason A. Donenfeld2016-06-251-0/+477
Copyright © 1996 – 2023 Jason A. Donenfeld. All Rights Reverse Engineered.