@@ -488,8 +488,7 @@ _final_ghash_mul\@:
vpand %xmm1, %xmm2, %xmm2
vpshufb SHUF_MASK(%rip), %xmm2, %xmm2
vpxor %xmm2, %xmm14, %xmm14
- #GHASH computation for the last <16 Byte block
- \GHASH_MUL %xmm14, %xmm13, %xmm0, %xmm10, %xmm11, %xmm5, %xmm6
+
vmovdqu %xmm14, AadHash(arg2)
sub %r13, %r11
add $16, %r11
@@ -500,8 +499,7 @@ _final_ghash_mul\@:
vpand %xmm1, %xmm9, %xmm9 # mask out top 16-r13 bytes of xmm9
vpshufb SHUF_MASK(%rip), %xmm9, %xmm9
vpxor %xmm9, %xmm14, %xmm14
- #GHASH computation for the last <16 Byte block
- \GHASH_MUL %xmm14, %xmm13, %xmm0, %xmm10, %xmm11, %xmm5, %xmm6
+
vmovdqu %xmm14, AadHash(arg2)
sub %r13, %r11
add $16, %r11
@@ -541,6 +539,14 @@ _multiple_of_16_bytes\@:
vmovdqu AadHash(arg2), %xmm14
vmovdqu HashKey(arg2), %xmm13
+ mov PBlockLen(arg2), %r12
+ cmp $0, %r12
+ je _partial_done\@
+
+ #GHASH computation for the last <16 Byte block
+ \GHASH_MUL %xmm14, %xmm13, %xmm0, %xmm10, %xmm11, %xmm5, %xmm6
+
+_partial_done\@:
mov AadLen(arg2), %r12 # r12 = aadLen (number of bytes)
shl $3, %r12 # convert into number of bits
vmovd %r12d, %xmm15 # len(A) in xmm15
Prepare to handle partial blocks between scatter/gather calls. For the last partial block, we only want to calculate the aadhash in GCM_COMPLETE, and a new partial block macro will handle both aadhash update and encrypting partial blocks between calls. Signed-off-by: Dave Watson <davejwatson@fb.com> --- arch/x86/crypto/aesni-intel_avx-x86_64.S | 14 ++++++++++---- 1 file changed, 10 insertions(+), 4 deletions(-)