aboutsummaryrefslogtreecommitdiffstats
Commit message (Collapse)AuthorAgeFilesLines
...
| * NEWS: Add aesni plugin newsMartin Willi2015-04-151-0/+6
| |
| * aesni: Avoid loading AES/GHASH round keys into local variablesMartin Willi2015-04-156-1568/+1244
| | | | | | | | | | | | | | | | | | | | The performance impact is not measurable, as the compiler loads these variables in xmm registers in unrolled loops anyway. However, we avoid loading these sensitive keys onto the stack. This happens for larger key schedules, where the register count is insufficient. If that key material is not on the stack, we can avoid to wipe it explicitly after crypto operations.
| * aesni: Align all class instances to 16 byte boundariesMartin Willi2015-04-157-14/+14
| | | | | | | | | | | | While the required members are aligned in the struct as required, on 32-bit platforms the allocator aligns the structures itself to 8 bytes only. This results in non-aligned struct members, and invalid memory accesses.
| * utils: Provide aligning variants of INIT/INIT_EXTRA macrosMartin Willi2015-04-151-0/+29
| |
| * unit-tests: Pass stringyfied assertion statement as non-format string argumentMartin Willi2015-04-151-3/+3
| | | | | | | | | | | | If the assertion contains a modulo (%) operation, test_fail_msg() handles this as printf() format specifier. Pass the assertion string as argument for an explicit "%s" in the format string, instead.
| * utils: Add malloc/free wrappers returning aligned dataMartin Willi2015-04-153-0/+101
| | | | | | | | | | | | | | | | | | | | | | | | | | While we could use posix_memalign(3), that is not fully portable. Further, it might be difficult on some platforms to properly catch it in leak-detective, which results in invalid free()s when releasing such memory. We instead use a simple wrapper, which allocates larger data, and saves the padding size in the allocated header. This requires that memory is released using a dedicated function. To reduce the risk of invalid free() when working on corrupted data, we fill up all the padding with the padding length, and verify it during free_align().
| * aesni: Calculate GHASH for 4 blocks of associated data in parallelMartin Willi2015-04-151-2/+18
| | | | | | | | | | While associated data is usually not that large, in some specific cases this can bring a significant performance boost.
| * aesni: Calculate GHASH for 4 blocks of encryption data in parallelMartin Willi2015-04-151-40/+180
| | | | | | | | Increases performance by another ~30%.
| * aesni: Use 4-way parallel en/decryption in GCMMartin Willi2015-04-151-132/+635
| | | | | | | | Increases overall performance by ~25%.
| * aesni: Use dedicated key size specific en-/decryption functions in GCMMartin Willi2015-04-151-24/+353
| | | | | | | | | | This gives not much more than ~5% increase in performance, but allows us to improve further.
| * aesni: Add a GCM AEAD based on the AES-NI key scheduleMartin Willi2015-04-154-1/+627
| |
| * aesni: Implement CMAC mode to provide a signer/prfMartin Willi2015-04-154-0/+441
| | | | | | | | | | Compared to the cmac plugin using AESNI-CBC as backend, this improves performance of AES-CMAC by ~45%.
| * aesni: Implement XCBC mode to provide a signer/prfMartin Willi2015-04-154-0/+436
| | | | | | | | | | Compared to the xcbc plugin using AESNI-CBC as backend, this improves performance of AES-XCBC by ~45%.
| * aesni: Partially use separate code paths for different key sizes in CCMMartin Willi2015-04-151-33/+438
| | | | | | | | Due to the serial nature of the CBC mac, this brings only a marginal speedup.
| * aesni: Add a CCM AEAD reusing the key scheduleMartin Willi2015-04-154-0/+645
| |
| * aesni: Use 4-way parallel AES-NI instructions for CTR en/decryptionMartin Willi2015-04-151-115/+354
| | | | | | | | | | | | | | CTR can be parallelized, and we do so by queueing instructions to the processor pipeline. While we have enough registers for 128-bit decryption, the register count is insufficient to hold all variables with larger key sizes. Nonetheless is 4-way parallelism faster, depending on key size between ~10% and ~25%.
| * aesni: Use dedicated round count specific encryption functions in CTR modeMartin Willi2015-04-151-23/+243
| | | | | | | | | | This allows us to unroll loops and hold the key schedule in local (register) variables. This brings an impressive speedup of ~45%.
| * aesni: Implement a AES-NI based CTR crypter using the key scheduleMartin Willi2015-04-154-0/+278
| |
| * aesni: Use 4-way parallel AES-NI instructions for CBC decryptionMartin Willi2015-04-151-66/+314
| | | | | | | | | | | | | | CBC decryption can be parallelized, and we do so by queueing instructions to the processor pipeline. While we have enough registers for 128-bit decryption, the register count is insufficient to hold all variables with larger key sizes. Nonetheless is 4-way parallelism faster, roughly by ~8%.
| * aesni: Use separate en-/decryption CBC code paths for different key sizesMartin Willi2015-04-151-22/+290
| | | | | | | | | | | | This allows us to unroll loops, and use local (register) variables for the key schedule. This improves performance slightly for encryption, but a lot for reorderable decryption (>30%).
| * aesni: Implement a AES-NI based CBC crypter using the key scheduleMartin Willi2015-04-154-0/+293
| |
| * aesni: Implement 256-bit key scheduleMartin Willi2015-04-151-0/+77
| |
| * aesni: Implement 192-bit key scheduleMartin Willi2015-04-151-0/+81
| |
| * aesni: Implement 128-bit key scheduleMartin Willi2015-04-151-0/+45
| |
| * aesni: Add a common key schedule class for AESMartin Willi2015-04-153-0/+165
| |
| * aesni: Provide a plugin stub for AES-NI instruction based crypto primitivesMartin Willi2015-04-155-0/+152
| |
| * utils: Provide an INIT_EXTRA() macro, that allocates extra data to INIT()Martin Willi2015-04-151-0/+15
| |
| * test-vectors: Add some self-made additional AES-GCM test vectorsMartin Willi2015-04-152-0/+157
| | | | | | | | | | We missed test vectors for 192/256-bit key vectors for ICV8/12, and should also have some for larger associated data chunk.
| * test-vectors: Define some additional CCM test vectorsMartin Willi2015-04-152-1/+84
| | | | | | | | | | | | We don't have any where plain or associated data is not a multiple of the block size, but it is likely to find bugs here. Also, we miss some ICV12 test vectors using 128- and 192-bit key sizes.
| * crypto-tester: Use the plugin feature key size to benchmark crypters/aeadsMartin Willi2015-04-154-21/+29
| | | | | | | | | | | | We previously didn't pass the key size during algorithm registration, but this resulted in benchmarking with the "default" key size the crypter uses when passing 0 as key size.
| * crypt-burn: Support burning signersMartin Willi2015-04-151-0/+53
| |
| * crypt-burn: Add a encryption buffer command line argumentMartin Willi2015-04-151-9/+14
| |
| * crypt-burn: Set a defined key, as some backends require thatMartin Willi2015-04-151-4/+10
| |
| * crypt-burn: Refactor to separate burn methodsMartin Willi2015-04-151-74/+116
| |
| * crypt-burn: Accept a PLUGINS env var to configure plugins to loadMartin Willi2015-04-151-3/+2
|/
* vici: Relicense libvici.h under MITMartin Willi2015-04-141-9/+20
| | | | | | libvici currently relies on libstrongswan, and therefore is bound to the GPLv2. But to allow alternatively licensed reimplementations without copyleft based on the same interface, we liberate the header.
* utils: Define MAX_(U)INT_TYPE to the maximum size integer type availableMartin Willi2015-04-141-0/+6
|
* utils: Typedef int128_t and u_int128_t types if supportedMartin Willi2015-04-141-0/+11
|
* configure: Check for __int128 type supportMartin Willi2015-04-141-0/+11
|
* Merge branch 'const-memeq'Martin Willi2015-04-1442-61/+580
|\ | | | | | | | | Introduce constant time memory comparing functions for cryptographic purposes, and a tool to test such functions or crypto transforms relying on them.
| * utils: Use chunk_equals_const() for all cryptographic purposesMartin Willi2015-04-1423-38/+33
| |
| * utils: Add a constant time chunk_equals() variant for cryptographic purposesMartin Willi2015-04-143-1/+87
| |
| * utils: Use memeq_const() for all cryptographic purposesMartin Willi2015-04-1412-22/+14
| |
| * utils: Add a constant time memeq() variant for cryptographic purposesMartin Willi2015-04-144-1/+79
| |
| * scripts: Add a tool that tries to guess MAC/ICV values using validation timesMartin Willi2015-04-143-1/+369
|/ | | | | | | | | | | | | | | | | | | This tool shows that it is trivial to re-construct the value memcmp() compares against by just measuring the time the non-time-constant memcmp() requires to fail. It also shows that even when running without any network latencies it gets very difficult to reconstruct MAC/ICV values, as the time variances due to the crypto routines are large enough that it gets difficult to measure the time that memcmp() actually requires after computing the MAC. However, the faster/time constant an algorithm is, the more likely is a successful attack. When using AES-NI, it is possible to reconstruct (parts of) a valid MAC with this tool, for example with AES-GCM. While this is all theoretical, and way more difficult to exploit with network jitter, it nonetheless shows that we should replace any use of memcmp/memeq() with a constant-time alternative in all sensitive places.
* Merge branch 'cpu-features'Martin Willi2015-04-136-134/+244
|\ | | | | | | | | Centralize all uses of CPUID to a cpu_feature class, which in theory can support optional features of non-x86/x64 as well using architecture specific code.
| * rdrand: Reuse CPU feature detection to check for RDRAND instructionsMartin Willi2015-04-131-51/+4
| |
| * padlock: Reuse common CPU feature detection to check for Padlock featuresMartin Willi2015-04-131-80/+17
| |
| * cpu-feature: Support Via Padlock security featuresMartin Willi2015-04-132-0/+56
| |
| * cpu-feature: Add a common class to query available CPU featuresMartin Willi2015-04-134-3/+167
|/ | | | Currently supported is x86/x64 via cpuid() for some common features.
generated by cgit v1.2.3 (git 2.25.1) at 2025-08-11 23:21:33 +0000