Prefer RIP-relative addressing where possible, which removes the need for boot time relocation fixups. Signed-off-by: Ard Biesheuvel <ardb@xxxxxxxxxx> --- arch/x86/crypto/sha256-avx2-asm.S | 18 ++++++++++++------ 1 file changed, 12 insertions(+), 6 deletions(-) diff --git a/arch/x86/crypto/sha256-avx2-asm.S b/arch/x86/crypto/sha256-avx2-asm.S index 3eada94168526665..e2a4024fb0a3f5d5 100644 --- a/arch/x86/crypto/sha256-avx2-asm.S +++ b/arch/x86/crypto/sha256-avx2-asm.S @@ -589,19 +589,23 @@ last_block_enter: .align 16 loop1: - vpaddd K256+0*32(SRND), X0, XFER + leaq K256+0*32(%rip), INP ## reuse INP as scratch reg + vpaddd (INP, SRND), X0, XFER vmovdqa XFER, 0*32+_XFER(%rsp, SRND) FOUR_ROUNDS_AND_SCHED _XFER + 0*32 - vpaddd K256+1*32(SRND), X0, XFER + leaq K256+1*32(%rip), INP + vpaddd (INP, SRND), X0, XFER vmovdqa XFER, 1*32+_XFER(%rsp, SRND) FOUR_ROUNDS_AND_SCHED _XFER + 1*32 - vpaddd K256+2*32(SRND), X0, XFER + leaq K256+2*32(%rip), INP + vpaddd (INP, SRND), X0, XFER vmovdqa XFER, 2*32+_XFER(%rsp, SRND) FOUR_ROUNDS_AND_SCHED _XFER + 2*32 - vpaddd K256+3*32(SRND), X0, XFER + leaq K256+3*32(%rip), INP + vpaddd (INP, SRND), X0, XFER vmovdqa XFER, 3*32+_XFER(%rsp, SRND) FOUR_ROUNDS_AND_SCHED _XFER + 3*32 @@ -611,11 +615,13 @@ loop1: loop2: ## Do last 16 rounds with no scheduling - vpaddd K256+0*32(SRND), X0, XFER + leaq K256+0*32(%rip), INP + vpaddd (INP, SRND), X0, XFER vmovdqa XFER, 0*32+_XFER(%rsp, SRND) DO_4ROUNDS _XFER + 0*32 - vpaddd K256+1*32(SRND), X1, XFER + leaq K256+1*32(%rip), INP + vpaddd (INP, SRND), X1, XFER vmovdqa XFER, 1*32+_XFER(%rsp, SRND) DO_4ROUNDS _XFER + 1*32 add $2*32, SRND -- 2.39.2
