Skip to content

[TEST] x86_64: 32-byte align stack scratch in rej_uniform and keccak_f1600_x4_avx2 #1682

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Draft
mkannwischer wants to merge 1 commit into
base: main
Choose a base branch
from
+16 −4
Draft

[TEST] x86_64: 32-byte align stack scratch in rej_uniform and keccak_f1600_x4_avx2 #1682

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
10 changes: 8 additions & 2 deletions mlkem/src/fips202/native/x86_64/src/keccak_f1600_x4_avx2_asm.S
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -18,7 +18,11 @@
MLK_ASM_FN_SYMBOL(keccak_f1600_x4_avx2_asm)

.cfi_startproc
subq $0x300, %rsp # imm = 0x300
pushq %rbp
.cfi_adjust_cfa_offset 8
movq %rsp, %rbp
subq $0x300, %rsp
andq $-32, %rsp
.cfi_adjust_cfa_offset 0x300
vmovdqu (%rdi), %ymm0
vmovdqu 0xc8(%rdi), %ymm3
Expand Down Expand Up @@ -437,8 +441,10 @@ LLkeccak_f1600_x4_avx2:
vmovhpd %xmm3, 0x188(%rdi)
vmovq %xmm15, 0x250(%rdi)
vmovhpd %xmm15, 0x318(%rdi)
addq $0x300, %rsp # imm = 0x300
movq %rbp, %rsp
.cfi_adjust_cfa_offset -0x300
popq %rbp
.cfi_adjust_cfa_offset -8
retq
.cfi_endproc

Expand Down
10 changes: 8 additions & 2 deletions mlkem/src/native/x86_64/src/rej_uniform_avx2_asm.S
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -34,7 +34,11 @@
MLK_ASM_FN_SYMBOL(rej_uniform_avx2_asm)

.cfi_startproc
subq $0x210, %rsp # imm = 0x210
pushq %rbp
.cfi_adjust_cfa_offset 8
movq %rsp, %rbp
subq $0x210, %rsp
andq $-32, %rsp
.cfi_adjust_cfa_offset 0x210
xorl %eax, %eax
testq %rdx, %rdx
Expand Down Expand Up @@ -88,8 +92,10 @@ Lrej_uniform_asm_final_copy:
rep movsb (%rsi), %es:(%rdi)

Lrej_uniform_asm_end:
addq $0x210, %rsp # imm = 0x210
movq %rbp, %rsp
.cfi_adjust_cfa_offset -0x210
popq %rbp
.cfi_adjust_cfa_offset -8
retq
.cfi_endproc

Expand Down
Loading