summaryrefslogtreecommitdiff
path: root/arch/x86/crypto/aes_ctrby8_avx-x86_64.S
diff options
context:
space:
mode:
authorMathias Krause <minipli@googlemail.com>2014-09-28 22:23:59 +0200
committerHerbert Xu <herbert@gondor.apana.org.au>2014-10-02 14:35:03 +0800
commit80dca4734b3561be59879b02bce359b6f661e921 (patch)
tree4822ed2121ea7371691ab6a5b14e5e42584a7ae8 /arch/x86/crypto/aes_ctrby8_avx-x86_64.S
parent7a1ae9c0ce39d839044745956f08eabbea00d420 (diff)
crypto: aesni - fix counter overflow handling in "by8" variant
The "by8" CTR AVX implementation fails to propperly handle counter overflows. That was the reason it got disabled in commit 7da4b29d496b ("crypto: aesni - disable "by8" AVX CTR optimization"). Fix the overflow handling by incrementing the counter block as a double quad word, i.e. a 128 bit, and testing for overflows afterwards. We need to use VPTEST to do so as VPADD* does not set the flags itself and silently drops the carry bit. As this change adds branches to the hot path, minor performance regressions might be a side effect. But, OTOH, we now have a conforming implementation -- the preferable goal. A tcrypt test on a SandyBridge system (i7-2620M) showed almost identical numbers for the old and this version with differences within the noise range. A dm-crypt test with the fixed version gave even slightly better results for this version. So the performance impact might not be as big as expected. Tested-by: Romain Francoise <romain@orebokech.com> Signed-off-by: Mathias Krause <minipli@googlemail.com> Cc: Chandramouli Narayanan <mouli@linux.intel.com> Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
Diffstat (limited to 'arch/x86/crypto/aes_ctrby8_avx-x86_64.S')
-rw-r--r--arch/x86/crypto/aes_ctrby8_avx-x86_64.S17
1 files changed, 15 insertions, 2 deletions
diff --git a/arch/x86/crypto/aes_ctrby8_avx-x86_64.S b/arch/x86/crypto/aes_ctrby8_avx-x86_64.S
index f091f122ed24..a029bc744244 100644
--- a/arch/x86/crypto/aes_ctrby8_avx-x86_64.S
+++ b/arch/x86/crypto/aes_ctrby8_avx-x86_64.S
@@ -108,6 +108,10 @@
byteswap_const:
.octa 0x000102030405060708090A0B0C0D0E0F
+ddq_low_msk:
+ .octa 0x0000000000000000FFFFFFFFFFFFFFFF
+ddq_high_add_1:
+ .octa 0x00000000000000010000000000000000
ddq_add_1:
.octa 0x00000000000000000000000000000001
ddq_add_2:
@@ -169,7 +173,12 @@ ddq_add_8:
.rept (by - 1)
club DDQ_DATA, i
club XDATA, i
- vpaddd var_ddq_add(%rip), xcounter, var_xdata
+ vpaddq var_ddq_add(%rip), xcounter, var_xdata
+ vptest ddq_low_msk(%rip), var_xdata
+ jnz 1f
+ vpaddq ddq_high_add_1(%rip), var_xdata, var_xdata
+ vpaddq ddq_high_add_1(%rip), xcounter, xcounter
+ 1:
vpshufb xbyteswap, var_xdata, var_xdata
.set i, (i +1)
.endr
@@ -178,7 +187,11 @@ ddq_add_8:
vpxor xkey0, xdata0, xdata0
club DDQ_DATA, by
- vpaddd var_ddq_add(%rip), xcounter, xcounter
+ vpaddq var_ddq_add(%rip), xcounter, xcounter
+ vptest ddq_low_msk(%rip), xcounter
+ jnz 1f
+ vpaddq ddq_high_add_1(%rip), xcounter, xcounter
+ 1:
.set i, 1
.rept (by - 1)