The following commit has been merged into the objtool/core branch of tip: Commit-ID: ec063e090bd6487097d459bb4272508b78448270 Gitweb: https://git.kernel.org/tip/ec063e090bd6487097d459bb4272508b78448270 Author: Josh Poimboeuf <jpoimboe@xxxxxxxxxx> AuthorDate: Wed, 24 Feb 2021 10:29:24 -06:00 Committer: Josh Poimboeuf <jpoimboe@xxxxxxxxxx> CommitterDate: Mon, 19 Apr 2021 12:36:36 -05:00 x86/crypto/sha512-avx2: Standardize stack alignment prologue Use a more standard prologue for saving the stack pointer before realigning the stack. This enables ORC unwinding by allowing objtool to understand the stack realignment. Signed-off-by: Josh Poimboeuf <jpoimboe@xxxxxxxxxx> Tested-by: Ard Biesheuvel <ardb@xxxxxxxxxx> Acked-by: Ard Biesheuvel <ardb@xxxxxxxxxx> Tested-by: Sami Tolvanen <samitolvanen@xxxxxxxxxx> Acked-by: Peter Zijlstra (Intel) <peterz@xxxxxxxxxxxxx> Acked-by: Herbert Xu <herbert@xxxxxxxxxxxxxxxxxxx> Link: https://lore.kernel.org/r/b1a7b29fcfc65d60a3b6e77ef75f4762a5b8488d.1614182415.git.jpoimboe@xxxxxxxxxx --- arch/x86/crypto/sha512-avx2-asm.S | 42 ++++++++++++++---------------- 1 file changed, 20 insertions(+), 22 deletions(-) diff --git a/arch/x86/crypto/sha512-avx2-asm.S b/arch/x86/crypto/sha512-avx2-asm.S index 3a44bdc..072cb0f 100644 --- a/arch/x86/crypto/sha512-avx2-asm.S +++ b/arch/x86/crypto/sha512-avx2-asm.S @@ -102,17 +102,13 @@ SRND_SIZE = 1*8 INP_SIZE = 1*8 INPEND_SIZE = 1*8 CTX_SIZE = 1*8 -RSPSAVE_SIZE = 1*8 -GPRSAVE_SIZE = 5*8 frame_XFER = 0 frame_SRND = frame_XFER + XFER_SIZE frame_INP = frame_SRND + SRND_SIZE frame_INPEND = frame_INP + INP_SIZE frame_CTX = frame_INPEND + INPEND_SIZE -frame_RSPSAVE = frame_CTX + CTX_SIZE -frame_GPRSAVE = frame_RSPSAVE + RSPSAVE_SIZE -frame_size = frame_GPRSAVE + GPRSAVE_SIZE +frame_size = frame_CTX + CTX_SIZE ## assume buffers not aligned #define VMOVDQ vmovdqu @@ -570,18 +566,18 @@ frame_size = frame_GPRSAVE + GPRSAVE_SIZE # "blocks" is the message length in SHA512 blocks ######################################################################## SYM_FUNC_START(sha512_transform_rorx) + # Save GPRs + push %rbx + push %r12 + push %r13 + push %r14 + push %r15 + # Allocate Stack Space - mov %rsp, %rax + push %rbp + mov %rsp, %rbp sub $frame_size, %rsp and $~(0x20 - 1), %rsp - mov %rax, frame_RSPSAVE(%rsp) - - # Save GPRs - mov %rbx, 8*0+frame_GPRSAVE(%rsp) - mov %r12, 8*1+frame_GPRSAVE(%rsp) - mov %r13, 8*2+frame_GPRSAVE(%rsp) - mov %r14, 8*3+frame_GPRSAVE(%rsp) - mov %r15, 8*4+frame_GPRSAVE(%rsp) shl $7, NUM_BLKS # convert to bytes jz done_hash @@ -672,15 +668,17 @@ loop2: done_hash: -# Restore GPRs - mov 8*0+frame_GPRSAVE(%rsp), %rbx - mov 8*1+frame_GPRSAVE(%rsp), %r12 - mov 8*2+frame_GPRSAVE(%rsp), %r13 - mov 8*3+frame_GPRSAVE(%rsp), %r14 - mov 8*4+frame_GPRSAVE(%rsp), %r15 - # Restore Stack Pointer - mov frame_RSPSAVE(%rsp), %rsp + mov %rbp, %rsp + pop %rbp + + # Restore GPRs + pop %r15 + pop %r14 + pop %r13 + pop %r12 + pop %rbx + ret SYM_FUNC_END(sha512_transform_rorx)
|