- 04 Aug, 2015 1 commit
-
-
Colin Ian King authored
Trival change, fix spelling mistake 'aquire' -> 'acquire' in dev_err message. Signed-off-by:
Colin Ian King <colin.king@canonical.com> Signed-off-by:
Herbert Xu <herbert@gondor.apana.org.au>
-
- 31 Jul, 2015 1 commit
-
-
Horia Geant? authored
The encap shared descriptor was changed to use the new IV convention. In the process some commands were shifted, making the output length zero, caam effectively writing garbage in dst. While here, update the decap descriptor to execute the "write" commands before the "read"s (as it previously was). This makes sure the input fifo is drained before becoming full. Fixes: 46218750 ("crypto: caam - Use new IV convention") Signed-off-by:
Horia Geant? <horia.geanta@freescale.com> Signed-off-by:
Tudor Ambarus <tudor.ambarus@freescale.com> Signed-off-by:
Herbert Xu <herbert@gondor.apana.org.au>
-
- 30 Jul, 2015 3 commits
-
-
Dan Streetman authored
Change my IBM email to my personal IEEE email. I'm leaving IBM, so my email there won't work anymore. This changes the owner to my personal email, so I can still get cc'ed on patches, until someone at IBM sends a patch to take it over. Signed-off-by:
Dan Streetman <ddstreet@ieee.org> Signed-off-by:
Herbert Xu <herbert@gondor.apana.org.au>
-
Dan Streetman authored
One of the debug messages in the NX 842 PowerNV driver is missing the required be32_to_cpu() wrapper when accessing the __be32 field csb->count. Add the wrapper so the message will show the correct count. Signed-off-by:
Dan Streetman <ddstreet@ieee.org> Signed-off-by:
Herbert Xu <herbert@gondor.apana.org.au>
-
Dan Streetman authored
Return success instead of error if compression succeeds but the output is larger than the input. It's unlikely that the caller will use the compressed data since it's larger than the original uncompressed data, but there was no error and returning an error code is incorrect. Further, for testing small input buffers, the output is likely to be larger than the input and success needs to be returned to verify the test. Signed-off-by:
Dan Streetman <ddstreet@ieee.org> Signed-off-by:
Herbert Xu <herbert@gondor.apana.org.au>
-
- 28 Jul, 2015 6 commits
-
-
Bruce Allan authored
There's no need to iterate through the list for instances in the accel_table since the number of devices is already known in this file. Signed-off-by:
Bruce Allan <bruce.w.allan@intel.com> Signed-off-by:
Tadeusz Struk <tadeusz.struk@intel.com> Signed-off-by:
Herbert Xu <herbert@gondor.apana.org.au>
-
Kees Cook authored
Since the API for jent_panic() does not include format string parameters, adjust the call to panic() to use a literal string to avoid any future callers from leaking format strings into the panic message. Signed-off-by:
Kees Cook <keescook@chromium.org> Acked-by:
Stephan Mueller <smueller@chronox.de> Signed-off-by:
Herbert Xu <herbert@gondor.apana.org.au>
-
Ahsan Atta authored
Signed-off-by:
Ahsan Atta <ahsan.atta@intel.com> Signed-off-by:
Tadeusz Struk <tadeusz.struk@intel.com> Signed-off-by:
Herbert Xu <herbert@gondor.apana.org.au>
-
Bruce Allan authored
Signed-off-by:
Bruce Allan <bruce.w.allan@intel.com> Signed-off-by:
Tadeusz Struk <tadeusz.struk@intel.com> Signed-off-by:
Herbert Xu <herbert@gondor.apana.org.au>
-
Bruce Allan authored
The subject macro mistakenly compares the passed-in ring size in bytes with ADF_RING_SIZE_4K which is 0x6 (an internal representation of 4KB) rather than comparing with the intended value of 4096. Signed-off-by:
Bruce Allan <bruce.w.allan@intel.com> Signed-off-by:
Tadeusz Struk <tadeusz.struk@intel.com> Signed-off-by:
Herbert Xu <herbert@gondor.apana.org.au>
-
Bruce Allan authored
The element pci_dev_id in the struct adf_hw_device_data is redundant since the PCI device id can be retrieved from the struct pci_dev. Signed-off-by:
Bruce Allan <bruce.w.allan@intel.com> Signed-off-by:
Tadeusz Struk <tadeusz.struk@intel.com> Signed-off-by:
Herbert Xu <herbert@gondor.apana.org.au>
-
- 23 Jul, 2015 9 commits
-
-
Dan Streetman authored
Remove the common 'platform' registration module, and move the crypto compression driver registration into each of the pSeries and PowerNV platform NX 842 drivers. Change the nx-842.c code into simple common functions that each platform driver uses to perform constraints-based buffer changes, i.e. realigning and/or resizing buffers to match the driver's hardware requirements. The common 'platform' module was my mistake to create - since each platform driver will only load/operate when running on its own platform (i.e. a pSeries platform or a PowerNV platform), they can directly register with the crypto subsystem, using the same alg and driver name. This removes unneeded complexity. Signed-off-by:
Dan Streetman <ddstreet@ieee.org> Signed-off-by:
Herbert Xu <herbert@gondor.apana.org.au>
-
Dan Streetman authored
The last commit merged nx-842.c's code into nx-842-crypto.c. It did not rename nx-842-crypto.c to nx-842.c, in order to let the patch more clearly show what was merged. This just renames nx-842-crypto.c to nx-842.c, with no changes to its code. Signed-off-by:
Dan Streetman <ddstreet@ieee.org> Signed-off-by:
Herbert Xu <herbert@gondor.apana.org.au>
-
Dan Streetman authored
Merge the nx-842.c code into nx-842-crypto.c. This allows later patches to remove the 'platform' driver, and instead allow each platform driver to directly register with the crypto compression api. Signed-off-by:
Dan Streetman <ddstreet@ieee.org> Signed-off-by:
Herbert Xu <herbert@gondor.apana.org.au>
-
Dan Streetman authored
Replace the duplicated finishing code (set destination buffer length and set return code to 0) in the case of decompressing a buffer with no header with a goto to the success case of decompressing a buffer with a header. This is a trivial change that allows both success cases to use common code, and includes the pr_debug() msg in both cases as well. Signed-off-by:
Dan Streetman <ddstreet@ieee.org> Signed-off-by:
Herbert Xu <herbert@gondor.apana.org.au>
-
Dan Streetman authored
Don't register the pSeries driver when parsing the device tree returns ENODEV. The nx842_probe() function in the pSeries driver returns error instead of registering as a crypto compression driver, when it receives an error return value from the nx842_OF_upd() function that probes the device tree nodes, except when ENODEV is returned. However ENODEV should not be a special case and the driver should not register when there is no hw device, or the hw device is disabled. Signed-off-by:
Dan Streetman <ddstreet@ieee.org> Signed-off-by:
Herbert Xu <herbert@gondor.apana.org.au>
-
Dan Streetman authored
Move the kzalloc() calls in nx842_probe() and nx842_OF_upd() to the top of the functions, before taking the devdata spinlock. Since kzalloc() without GFP_ATOMIC can sleep, it can't be called while holding a spinlock. Move the calls to before taking the lock. Signed-off-by:
Dan Streetman <ddstreet@ieee.org> Signed-off-by:
Herbert Xu <herbert@gondor.apana.org.au>
-
Dan Streetman authored
Remove the 'status' field from the pSeries NX driver data. The 'status' field isn't used by the driver at all; it simply checks the devicetree status node at initialization, and returns success if 'okay' and failure otherwise. Signed-off-by:
Dan Streetman <ddstreet@ieee.org> Signed-off-by:
Herbert Xu <herbert@gondor.apana.org.au>
-
Dan Streetman authored
Remove the __init and __exit modifiers from the VIO driver probe and remove functions. The driver functions should not be marked __init/__exit because they can/will be called during runtime, not only at module init and exit. Signed-off-by:
Dan Streetman <ddstreet@ieee.org> Signed-off-by:
Herbert Xu <herbert@gondor.apana.org.au>
-
Tadeusz Struk authored
When multiple devices are present in the system the driver attempts to register the same algorithm many times. Changes in v2: - use proper synchronization mechanizm between register and unregister Signed-off-by:
Tadeusz Struk <tadeusz.struk@intel.com> Signed-off-by:
Herbert Xu <herbert@gondor.apana.org.au>
-
- 21 Jul, 2015 2 commits
-
-
Tadeusz Struk authored
The condition checking allowed key length was invalid. Reported-by:
Dan Carpenter <dan.carpenter@oracle.com> Signed-off-by:
Tadeusz Struk <tadeusz.struk@intel.com> Signed-off-by:
Herbert Xu <herbert@gondor.apana.org.au>
-
Tadeusz Struk authored
The condition checking allowed key length was invalid. Reported-by:
Dan Carpenter <dan.carpenter@oracle.com> Signed-off-by:
Tadeusz Struk <tadeusz.struk@intel.com> Signed-off-by:
Herbert Xu <herbert@gondor.apana.org.au>
-
- 20 Jul, 2015 9 commits
-
-
LABBE Corentin authored
Signed-off-by:
LABBE Corentin <clabbe.montjoie@gmail.com> Signed-off-by:
Herbert Xu <herbert@gondor.apana.org.au>
-
LABBE Corentin authored
Add support for the Security System included in Allwinner SoC A20. The Security System is a hardware cryptographic accelerator that support: - MD5 and SHA1 hash algorithms - AES block cipher in CBC/ECB mode with 128/196/256bits keys. - DES and 3DES block cipher in CBC/ECB mode Signed-off-by:
LABBE Corentin <clabbe.montjoie@gmail.com> Signed-off-by:
Herbert Xu <herbert@gondor.apana.org.au>
-
LABBE Corentin authored
This patch adds documentation for Device-Tree bindings for the Security System cryptographic accelerator driver. Signed-off-by:
LABBE Corentin <clabbe.montjoie@gmail.com> Signed-off-by:
Herbert Xu <herbert@gondor.apana.org.au>
-
LABBE Corentin authored
The Security System is a hardware cryptographic accelerator that support AES/MD5/SHA1/DES/3DES/PRNG algorithms. It could be found on many Allwinner SoC. This patch enable the Security System on the Allwinner A20 SoC Device-tree. Signed-off-by:
LABBE Corentin <clabbe.montjoie@gmail.com> Signed-off-by:
Herbert Xu <herbert@gondor.apana.org.au>
-
LABBE Corentin authored
The Security System is a hardware cryptographic accelerator that support AES/MD5/SHA1/DES/3DES/PRNG algorithms. It could be found on many Allwinner SoC. This patch enable the Security System on the Allwinner A10 SoC Device-tree. Signed-off-by:
LABBE Corentin <clabbe.montjoie@gmail.com> Signed-off-by:
Herbert Xu <herbert@gondor.apana.org.au>
-
Tudor Ambarus authored
An implicit truncation is done when using a variable of 64 bits in MATH command: warning: large integer implicitly truncated to unsigned type [-Woverflow] Silence the compiler by feeding it with an explicit truncated value. Signed-off-by:
Tudor Ambarus <tudor.ambarus@freescale.com> Signed-off-by:
Horia Geant? <horia.geanta@freescale.com> Signed-off-by:
Herbert Xu <herbert@gondor.apana.org.au>
-
Horia Geant? authored
When successful, the descriptor that performs RNG initialization is allowed to return a status code of 7000_0000h, since last command in the descriptor is a JUMP HALT. Signed-off-by:
Horia Geant? <horia.geanta@freescale.com> Signed-off-by:
Herbert Xu <herbert@gondor.apana.org.au>
-
Horia Geant? authored
HW coherency won't work properly for CAAM write transactions if AWCACHE is left to default (POR) value - 4'b0001. It has to be programmed to 4'b0010, i.e. AXI3 Cacheable bit set. For platforms that have HW coherency support: -PPC-based: the update has no effect; CAAM coherency already works due to the IOMMU (PAMU) driver setting the correct memory coherency attributes -ARM-based: the update fixes cache coherency issues, since IOMMU (SMMU) driver is not programmed to behave similar to PAMU Signed-off-by:
Horia Geant? <horia.geanta@freescale.com> Signed-off-by:
Herbert Xu <herbert@gondor.apana.org.au>
-
Alex Porosanu authored
In order to ensure that the ERA property is properly read from DT on all platforms, of_property_read* function needs to be used. Signed-off-by:
Alex Porosanu <alexandru.porosanu@freescale.com> Signed-off-by:
Horia Geant? <horia.geanta@freescale.com> Signed-off-by:
Herbert Xu <herbert@gondor.apana.org.au>
-
- 17 Jul, 2015 9 commits
-
-
Martin Willi authored
Extends the x86_64 Poly1305 authenticator by a function processing four consecutive Poly1305 blocks in parallel using AVX2 instructions. For large messages, throughput increases by ~15-45% compared to two block SSE2: testing speed of poly1305 (poly1305-simd) test 0 ( 96 byte blocks, 16 bytes per update, 6 updates): 3809514 opers/sec, 365713411 bytes/sec test 1 ( 96 byte blocks, 32 bytes per update, 3 updates): 5973423 opers/sec, 573448627 bytes/sec test 2 ( 96 byte blocks, 96 bytes per update, 1 updates): 9446779 opers/sec, 906890803 bytes/sec test 3 ( 288 byte blocks, 16 bytes per update, 18 updates): 1364814 opers/sec, 393066691 bytes/sec test 4 ( 288 byte blocks, 32 bytes per update, 9 updates): 2045780 opers/sec, 589184697 bytes/sec test 5 ( 288 byte blocks, 288 bytes per update, 1 updates): 3711946 opers/sec, 1069040592 bytes/sec test 6 ( 1056 byte blocks, 32 bytes per update, 33 updates): 573686 opers/sec, 605812732 bytes/sec test 7 ( 1056 byte blocks, 1056 bytes per update, 1 updates): 1647802 opers/sec, 1740079440 bytes/sec test 8 ( 2080 byte blocks, 32 bytes per update, 65 updates): 292970 opers/sec, 609378224 bytes/sec test 9 ( 2080 byte blocks, 2080 bytes per update, 1 updates): 943229 opers/sec, 1961916528 bytes/sec test 10 ( 4128 byte blocks, 4128 bytes per update, 1 updates): 494623 opers/sec, 2041804569 bytes/sec test 11 ( 8224 byte blocks, 8224 bytes per update, 1 updates): 254045 opers/sec, 2089271014 bytes/sec testing speed of poly1305 (poly1305-simd) test 0 ( 96 byte blocks, 16 bytes per update, 6 updates): 3826224 opers/sec, 367317552 bytes/sec test 1 ( 96 byte blocks, 32 bytes per update, 3 updates): 5948638 opers/sec, 571069267 bytes/sec test 2 ( 96 byte blocks, 96 bytes per update, 1 updates): 9439110 opers/sec, 906154627 bytes/sec test 3 ( 288 byte blocks, 16 bytes per update, 18 updates): 1367756 opers/sec, 393913872 bytes/sec test 4 ( 288 byte blocks, 32 bytes per update, 9 updates): 2056881 opers/sec, 592381958 bytes/sec test 5 ( 288 byte blocks, 288 bytes per update, 1 updates): 3711153 opers/sec, 1068812179 bytes/sec test 6 ( 1056 byte blocks, 32 bytes per update, 33 updates): 574940 opers/sec, 607136745 bytes/sec test 7 ( 1056 byte blocks, 1056 bytes per update, 1 updates): 1948830 opers/sec, 2057964585 bytes/sec test 8 ( 2080 byte blocks, 32 bytes per update, 65 updates): 293308 opers/sec, 610082096 bytes/sec test 9 ( 2080 byte blocks, 2080 bytes per update, 1 updates): 1235224 opers/sec, 2569267792 bytes/sec test 10 ( 4128 byte blocks, 4128 bytes per update, 1 updates): 684405 opers/sec, 2825226316 bytes/sec test 11 ( 8224 byte blocks, 8224 bytes per update, 1 updates): 367101 opers/sec, 3019039446 bytes/sec Benchmark results from a Core i5-4670T. Signed-off-by:
Martin Willi <martin@strongswan.org> Signed-off-by:
Herbert Xu <herbert@gondor.apana.org.au>
-
Martin Willi authored
Extends the x86_64 SSE2 Poly1305 authenticator by a function processing two consecutive Poly1305 blocks in parallel using a derived key r^2. Loop unrolling can be more effectively mapped to SSE instructions, further increasing throughput. For large messages, throughput increases by ~45-65% compared to single block SSE2: testing speed of poly1305 (poly1305-simd) test 0 ( 96 byte blocks, 16 bytes per update, 6 updates): 3790063 opers/sec, 363846076 bytes/sec test 1 ( 96 byte blocks, 32 bytes per update, 3 updates): 5913378 opers/sec, 567684355 bytes/sec test 2 ( 96 byte blocks, 96 bytes per update, 1 updates): 9352574 opers/sec, 897847104 bytes/sec test 3 ( 288 byte blocks, 16 bytes per update, 18 updates): 1362145 opers/sec, 392297990 bytes/sec test 4 ( 288 byte blocks, 32 bytes per update, 9 updates): 2007075 opers/sec, 578037628 bytes/sec test 5 ( 288 byte blocks, 288 bytes per update, 1 updates): 3709811 opers/sec, 1068425798 bytes/sec test 6 ( 1056 byte blocks, 32 bytes per update, 33 updates): 566272 opers/sec, 597984182 bytes/sec test 7 ( 1056 byte blocks, 1056 bytes per update, 1 updates): 1111657 opers/sec, 1173910108 bytes/sec test 8 ( 2080 byte blocks, 32 bytes per update, 65 updates): 288857 opers/sec, 600823808 bytes/sec test 9 ( 2080 byte blocks, 2080 bytes per update, 1 updates): 590746 opers/sec, 1228751888 bytes/sec test 10 ( 4128 byte blocks, 4128 bytes per update, 1 updates): 301825 opers/sec, 1245936902 bytes/sec test 11 ( 8224 byte blocks, 8224 bytes per update, 1 updates): 153075 opers/sec, 1258896201 bytes/sec testing speed of poly1305 (poly1305-simd) test 0 ( 96 byte blocks, 16 bytes per update, 6 updates): 3809514 opers/sec, 365713411 bytes/sec test 1 ( 96 byte blocks, 32 bytes per update, 3 updates): 5973423 opers/sec, 573448627 bytes/sec test 2 ( 96 byte blocks, 96 bytes per update, 1 updates): 9446779 opers/sec, 906890803 bytes/sec test 3 ( 288 byte blocks, 16 bytes per update, 18 updates): 1364814 opers/sec, 393066691 bytes/sec test 4 ( 288 byte blocks, 32 bytes per update, 9 updates): 2045780 opers/sec, 589184697 bytes/sec test 5 ( 288 byte blocks, 288 bytes per update, 1 updates): 3711946 opers/sec, 1069040592 bytes/sec test 6 ( 1056 byte blocks, 32 bytes per update, 33 updates): 573686 opers/sec, 605812732 bytes/sec test 7 ( 1056 byte blocks, 1056 bytes per update, 1 updates): 1647802 opers/sec, 1740079440 bytes/sec test 8 ( 2080 byte blocks, 32 bytes per update, 65 updates): 292970 opers/sec, 609378224 bytes/sec test 9 ( 2080 byte blocks, 2080 bytes per update, 1 updates): 943229 opers/sec, 1961916528 bytes/sec test 10 ( 4128 byte blocks, 4128 bytes per update, 1 updates): 494623 opers/sec, 2041804569 bytes/sec test 11 ( 8224 byte blocks, 8224 bytes per update, 1 updates): 254045 opers/sec, 2089271014 bytes/sec Benchmark results from a Core i5-4670T. Signed-off-by:
Martin Willi <martin@strongswan.org> Signed-off-by:
Herbert Xu <herbert@gondor.apana.org.au>
-
Martin Willi authored
Implements an x86_64 assembler driver for the Poly1305 authenticator. This single block variant holds the 130-bit integer in 5 32-bit words, but uses SSE to do two multiplications/additions in parallel. When calling updates with small blocks, the overhead for kernel_fpu_begin/ kernel_fpu_end() negates the perfmance gain. We therefore use the poly1305-generic fallback for small updates. For large messages, throughput increases by ~5-10% compared to poly1305-generic: testing speed of poly1305 (poly1305-generic) test 0 ( 96 byte blocks, 16 bytes per update, 6 updates): 4080026 opers/sec, 391682496 bytes/sec test 1 ( 96 byte blocks, 32 bytes per update, 3 updates): 6221094 opers/sec, 597225024 bytes/sec test 2 ( 96 byte blocks, 96 bytes per update, 1 updates): 9609750 opers/sec, 922536057 bytes/sec test 3 ( 288 byte blocks, 16 bytes per update, 18 updates): 1459379 opers/sec, 420301267 bytes/sec test 4 ( 288 byte blocks, 32 bytes per update, 9 updates): 2115179 opers/sec, 609171609 bytes/sec test 5 ( 288 byte blocks, 288 bytes per update, 1 updates): 3729874 opers/sec, 1074203856 bytes/sec test 6 ( 1056 byte blocks, 32 bytes per update, 33 updates): 593000 opers/sec, 626208000 bytes/sec test 7 ( 1056 byte blocks, 1056 bytes per update, 1 updates): 1081536 opers/sec, 1142102332 bytes/sec test 8 ( 2080 byte blocks, 32 bytes per update, 65 updates): 302077 opers/sec, 628320576 bytes/sec test 9 ( 2080 byte blocks, 2080 bytes per update, 1 updates): 554384 opers/sec, 1153120176 bytes/sec test 10 ( 4128 byte blocks, 4128 bytes per update, 1 updates): 278715 opers/sec, 1150536345 bytes/sec test 11 ( 8224 byte blocks, 8224 bytes per update, 1 updates): 140202 opers/sec, 1153022070 bytes/sec testing speed of poly1305 (poly1305-simd) test 0 ( 96 byte blocks, 16 bytes per update, 6 updates): 3790063 opers/sec, 363846076 bytes/sec test 1 ( 96 byte blocks, 32 bytes per update, 3 updates): 5913378 opers/sec, 567684355 bytes/sec test 2 ( 96 byte blocks, 96 bytes per update, 1 updates): 9352574 opers/sec, 897847104 bytes/sec test 3 ( 288 byte blocks, 16 bytes per update, 18 updates): 1362145 opers/sec, 392297990 bytes/sec test 4 ( 288 byte blocks, 32 bytes per update, 9 updates): 2007075 opers/sec, 578037628 bytes/sec test 5 ( 288 byte blocks, 288 bytes per update, 1 updates): 3709811 opers/sec, 1068425798 bytes/sec test 6 ( 1056 byte blocks, 32 bytes per update, 33 updates): 566272 opers/sec, 597984182 bytes/sec test 7 ( 1056 byte blocks, 1056 bytes per update, 1 updates): 1111657 opers/sec, 1173910108 bytes/sec test 8 ( 2080 byte blocks, 32 bytes per update, 65 updates): 288857 opers/sec, 600823808 bytes/sec test 9 ( 2080 byte blocks, 2080 bytes per update, 1 updates): 590746 opers/sec, 1228751888 bytes/sec test 10 ( 4128 byte blocks, 4128 bytes per update, 1 updates): 301825 opers/sec, 1245936902 bytes/sec test 11 ( 8224 byte blocks, 8224 bytes per update, 1 updates): 153075 opers/sec, 1258896201 bytes/sec Benchmark results from a Core i5-4670T. Signed-off-by:
Martin Willi <martin@strongswan.org> Signed-off-by:
Herbert Xu <herbert@gondor.apana.org.au>
-
Martin Willi authored
As architecture specific drivers need a software fallback, export Poly1305 init/update/final functions together with some helpers in a header file. Signed-off-by:
Martin Willi <martin@strongswan.org> Signed-off-by:
Herbert Xu <herbert@gondor.apana.org.au>
-
Martin Willi authored
The AVX2 variant of ChaCha20 is used only for messages with >= 512 bytes length. With the existing test vectors, the implementation could not be tested. Due that lack of such a long official test vector, this one is self-generated using chacha20-generic. Signed-off-by:
Martin Willi <martin@strongswan.org> Signed-off-by:
Herbert Xu <herbert@gondor.apana.org.au>
-
Martin Willi authored
Extends the x86_64 ChaCha20 implementation by a function processing eight ChaCha20 blocks in parallel using AVX2. For large messages, throughput increases by ~55-70% compared to four block SSSE3: testing speed of chacha20 (chacha20-simd) encryption test 0 (256 bit key, 16 byte blocks): 42249230 operations in 10 seconds (675987680 bytes) test 1 (256 bit key, 64 byte blocks): 46441641 operations in 10 seconds (2972265024 bytes) test 2 (256 bit key, 256 byte blocks): 33028112 operations in 10 seconds (8455196672 bytes) test 3 (256 bit key, 1024 byte blocks): 11568759 operations in 10 seconds (11846409216 bytes) test 4 (256 bit key, 8192 byte blocks): 1448761 operations in 10 seconds (11868250112 bytes) testing speed of chacha20 (chacha20-simd) encryption test 0 (256 bit key, 16 byte blocks): 41999675 operations in 10 seconds (671994800 bytes) test 1 (256 bit key, 64 byte blocks): 45805908 operations in 10 seconds (2931578112 bytes) test 2 (256 bit key, 256 byte blocks): 32814947 operations in 10 seconds (8400626432 bytes) test 3 (256 bit key, 1024 byte blocks): 19777167 operations in 10 seconds (20251819008 bytes) test 4 (256 bit key, 8192 byte blocks): 2279321 operations in 10 seconds (18672197632 bytes) Benchmark results from a Core i5-4670T. Signed-off-by:
Martin Willi <martin@strongswan.org> Signed-off-by:
Herbert Xu <herbert@gondor.apana.org.au>
-
Martin Willi authored
Extends the x86_64 SSSE3 ChaCha20 implementation by a function processing four ChaCha20 blocks in parallel. This avoids the word shuffling needed in the single block variant, further increasing throughput. For large messages, throughput increases by ~110% compared to single block SSSE3: testing speed of chacha20 (chacha20-simd) encryption test 0 (256 bit key, 16 byte blocks): 43141886 operations in 10 seconds (690270176 bytes) test 1 (256 bit key, 64 byte blocks): 46845874 operations in 10 seconds (2998135936 bytes) test 2 (256 bit key, 256 byte blocks): 18458512 operations in 10 seconds (4725379072 bytes) test 3 (256 bit key, 1024 byte blocks): 5360533 operations in 10 seconds (5489185792 bytes) test 4 (256 bit key, 8192 byte blocks): 692846 operations in 10 seconds (5675794432 bytes) testing speed of chacha20 (chacha20-simd) encryption test 0 (256 bit key, 16 byte blocks): 42249230 operations in 10 seconds (675987680 bytes) test 1 (256 bit key, 64 byte blocks): 46441641 operations in 10 seconds (2972265024 bytes) test 2 (256 bit key, 256 byte blocks): 33028112 operations in 10 seconds (8455196672 bytes) test 3 (256 bit key, 1024 byte blocks): 11568759 operations in 10 seconds (11846409216 bytes) test 4 (256 bit key, 8192 byte blocks): 1448761 operations in 10 seconds (11868250112 bytes) Benchmark results from a Core i5-4670T. Signed-off-by:
Martin Willi <martin@strongswan.org> Signed-off-by:
Herbert Xu <herbert@gondor.apana.org.au>
-
Martin Willi authored
Implements an x86_64 assembler driver for the ChaCha20 stream cipher. This single block variant works on a single state matrix using SSE instructions. It requires SSSE3 due the use of pshufb for efficient 8/16-bit rotate operations. For large messages, throughput increases by ~65% compared to chacha20-generic: testing speed of chacha20 (chacha20-generic) encryption test 0 (256 bit key, 16 byte blocks): 45089207 operations in 10 seconds (721427312 bytes) test 1 (256 bit key, 64 byte blocks): 43839521 operations in 10 seconds (2805729344 bytes) test 2 (256 bit key, 256 byte blocks): 12702056 operations in 10 seconds (3251726336 bytes) test 3 (256 bit key, 1024 byte blocks): 3371173 operations in 10 seconds (3452081152 bytes) test 4 (256 bit key, 8192 byte blocks): 422468 operations in 10 seconds (3460857856 bytes) testing speed of chacha20 (chacha20-simd) encryption test 0 (256 bit key, 16 byte blocks): 43141886 operations in 10 seconds (690270176 bytes) test 1 (256 bit key, 64 byte blocks): 46845874 operations in 10 seconds (2998135936 bytes) test 2 (256 bit key, 256 byte blocks): 18458512 operations in 10 seconds (4725379072 bytes) test 3 (256 bit key, 1024 byte blocks): 5360533 operations in 10 seconds (5489185792 bytes) test 4 (256 bit key, 8192 byte blocks): 692846 operations in 10 seconds (5675794432 bytes) Benchmark results from a Core i5-4670T. Signed-off-by:
Martin Willi <martin@strongswan.org> Signed-off-by:
Herbert Xu <herbert@gondor.apana.org.au>
-
Martin Willi authored
As architecture specific drivers need a software fallback, export a ChaCha20 en-/decryption function together with some helpers in a header file. Signed-off-by:
Martin Willi <martin@strongswan.org> Signed-off-by:
Herbert Xu <herbert@gondor.apana.org.au>
-