linux/lib/crypto/sparc/sha256_asm.S
Eric Biggers a32e93e100 lib/crypto: sparc: Move arch/sparc/lib/crypto/ into lib/crypto/
Move the contents of arch/sparc/lib/crypto/ into lib/crypto/sparc/.

The new code organization makes a lot more sense for how this code
actually works and is developed.  In particular, it makes it possible to
build each algorithm as a single module, with better inlining and dead
code elimination.  For a more detailed explanation, see the patchset
which did this for the CRC library code:
https://lore.kernel.org/r/20250607200454.73587-1-ebiggers@kernel.org/.
Also see the patchset which did this for SHA-512:
https://lore.kernel.org/linux-crypto/20250616014019.415791-1-ebiggers@kernel.org/

This is just a preparatory commit, which does the move to get the files
into their new location but keeps them building the same way as before.
Later commits will make the actual improvements to the way the
arch-optimized code is integrated for each algorithm.

Acked-by: Ard Biesheuvel <ardb@kernel.org>
Reviewed-by: Martin K. Petersen <martin.petersen@oracle.com>
Reviewed-by: Sohil Mehta <sohil.mehta@intel.com>
Link: https://lore.kernel.org/r/20250619191908.134235-8-ebiggers@kernel.org
Signed-off-by: Eric Biggers <ebiggers@kernel.org>
2025-06-30 09:26:20 -07:00

78 lines
1.5 KiB
ArmAsm

/* SPDX-License-Identifier: GPL-2.0 */
#include <linux/linkage.h>
#include <asm/opcodes.h>
#include <asm/visasm.h>
ENTRY(sha256_sparc64_transform)
/* %o0 = state, %o1 = data, %o2 = nblocks */
VISEntryHalf
ld [%o0 + 0x00], %f0
ld [%o0 + 0x04], %f1
ld [%o0 + 0x08], %f2
ld [%o0 + 0x0c], %f3
ld [%o0 + 0x10], %f4
ld [%o0 + 0x14], %f5
andcc %o1, 0x7, %g0
ld [%o0 + 0x18], %f6
bne,pn %xcc, 10f
ld [%o0 + 0x1c], %f7
1:
ldd [%o1 + 0x00], %f8
ldd [%o1 + 0x08], %f10
ldd [%o1 + 0x10], %f12
ldd [%o1 + 0x18], %f14
ldd [%o1 + 0x20], %f16
ldd [%o1 + 0x28], %f18
ldd [%o1 + 0x30], %f20
ldd [%o1 + 0x38], %f22
SHA256
subcc %o2, 1, %o2
bne,pt %xcc, 1b
add %o1, 0x40, %o1
5:
st %f0, [%o0 + 0x00]
st %f1, [%o0 + 0x04]
st %f2, [%o0 + 0x08]
st %f3, [%o0 + 0x0c]
st %f4, [%o0 + 0x10]
st %f5, [%o0 + 0x14]
st %f6, [%o0 + 0x18]
st %f7, [%o0 + 0x1c]
retl
VISExitHalf
10:
alignaddr %o1, %g0, %o1
ldd [%o1 + 0x00], %f10
1:
ldd [%o1 + 0x08], %f12
ldd [%o1 + 0x10], %f14
ldd [%o1 + 0x18], %f16
ldd [%o1 + 0x20], %f18
ldd [%o1 + 0x28], %f20
ldd [%o1 + 0x30], %f22
ldd [%o1 + 0x38], %f24
ldd [%o1 + 0x40], %f26
faligndata %f10, %f12, %f8
faligndata %f12, %f14, %f10
faligndata %f14, %f16, %f12
faligndata %f16, %f18, %f14
faligndata %f18, %f20, %f16
faligndata %f20, %f22, %f18
faligndata %f22, %f24, %f20
faligndata %f24, %f26, %f22
SHA256
subcc %o2, 1, %o2
fsrc2 %f26, %f10
bne,pt %xcc, 1b
add %o1, 0x40, %o1
ba,a,pt %xcc, 5b
ENDPROC(sha256_sparc64_transform)