lib/crypto: powerpc: Move arch/powerpc/lib/crypto/ into lib/crypto/

Move the contents of arch/powerpc/lib/crypto/ into lib/crypto/powerpc/.

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/20250619191908.134235-5-ebiggers@kernel.org
Signed-off-by: Eric Biggers <ebiggers@kernel.org>

10 files changed, 2533 insertions, 1 deletions

diff --git a/lib/crypto/Kconfig b/lib/crypto/Kconfig
index 43c44316fbbd..f4f9a70dd089 100644
--- a/lib/crypto/Kconfig
+++ b/lib/crypto/Kconfig
@@ -199,7 +199,7 @@ if MIPS
 source "lib/crypto/mips/Kconfig"
 endif
 if PPC
-source "arch/powerpc/lib/crypto/Kconfig"
+source "lib/crypto/powerpc/Kconfig"
 endif
 if RISCV
 source "arch/riscv/lib/crypto/Kconfig"
diff --git a/lib/crypto/Makefile b/lib/crypto/Makefile
index f54d2f3edc40..f5f1dcec2f89 100644
--- a/lib/crypto/Makefile
+++ b/lib/crypto/Makefile
@@ -110,3 +110,4 @@ libsm3-y					:= sm3.o
 obj-$(CONFIG_ARM) += arm/
 obj-$(CONFIG_ARM64) += arm64/
 obj-$(CONFIG_MIPS) += mips/
+obj-$(CONFIG_PPC) += powerpc/
diff --git a/lib/crypto/powerpc/Kconfig b/lib/crypto/powerpc/Kconfig
new file mode 100644
index 000000000000..3f9e1bbd9905
--- /dev/null
+++ b/lib/crypto/powerpc/Kconfig
@@ -0,0 +1,22 @@
+# SPDX-License-Identifier: GPL-2.0-only
+
+config CRYPTO_CHACHA20_P10
+	tristate
+	depends on PPC64 && CPU_LITTLE_ENDIAN && VSX
+	default CRYPTO_LIB_CHACHA
+	select CRYPTO_LIB_CHACHA_GENERIC
+	select CRYPTO_ARCH_HAVE_LIB_CHACHA
+
+config CRYPTO_POLY1305_P10
+	tristate
+	depends on PPC64 && CPU_LITTLE_ENDIAN && VSX
+	depends on BROKEN # Needs to be fixed to work in softirq context
+	default CRYPTO_LIB_POLY1305
+	select CRYPTO_ARCH_HAVE_LIB_POLY1305
+	select CRYPTO_LIB_POLY1305_GENERIC
+
+config CRYPTO_SHA256_PPC_SPE
+	tristate
+	depends on SPE
+	default CRYPTO_LIB_SHA256
+	select CRYPTO_ARCH_HAVE_LIB_SHA256
diff --git a/lib/crypto/powerpc/Makefile b/lib/crypto/powerpc/Makefile
new file mode 100644
index 000000000000..27f231f8e334
--- /dev/null
+++ b/lib/crypto/powerpc/Makefile
@@ -0,0 +1,10 @@
+# SPDX-License-Identifier: GPL-2.0-only
+
+obj-$(CONFIG_CRYPTO_CHACHA20_P10) += chacha-p10-crypto.o
+chacha-p10-crypto-y := chacha-p10-glue.o chacha-p10le-8x.o
+
+obj-$(CONFIG_CRYPTO_POLY1305_P10) += poly1305-p10-crypto.o
+poly1305-p10-crypto-y := poly1305-p10-glue.o poly1305-p10le_64.o
+
+obj-$(CONFIG_CRYPTO_SHA256_PPC_SPE) += sha256-ppc-spe.o
+sha256-ppc-spe-y := sha256.o sha256-spe-asm.o
diff --git a/lib/crypto/powerpc/chacha-p10-glue.c b/lib/crypto/powerpc/chacha-p10-glue.c
new file mode 100644
index 000000000000..fcd23c6f1590
--- /dev/null
+++ b/lib/crypto/powerpc/chacha-p10-glue.c
@@ -0,0 +1,100 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * ChaCha stream cipher (P10 accelerated)
+ *
+ * Copyright 2023- IBM Corp. All rights reserved.
+ */
+
+#include <crypto/chacha.h>
+#include <crypto/internal/simd.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/cpufeature.h>
+#include <linux/sizes.h>
+#include <asm/simd.h>
+#include <asm/switch_to.h>
+
+asmlinkage void chacha_p10le_8x(const struct chacha_state *state, u8 *dst,
+				const u8 *src, unsigned int len, int nrounds);
+
+static __ro_after_init DEFINE_STATIC_KEY_FALSE(have_p10);
+
+static void vsx_begin(void)
+{
+	preempt_disable();
+	enable_kernel_vsx();
+}
+
+static void vsx_end(void)
+{
+	disable_kernel_vsx();
+	preempt_enable();
+}
+
+static void chacha_p10_do_8x(struct chacha_state *state, u8 *dst, const u8 *src,
+			     unsigned int bytes, int nrounds)
+{
+	unsigned int l = bytes & ~0x0FF;
+
+	if (l > 0) {
+		chacha_p10le_8x(state, dst, src, l, nrounds);
+		bytes -= l;
+		src += l;
+		dst += l;
+		state->x[12] += l / CHACHA_BLOCK_SIZE;
+	}
+
+	if (bytes > 0)
+		chacha_crypt_generic(state, dst, src, bytes, nrounds);
+}
+
+void hchacha_block_arch(const struct chacha_state *state,
+			u32 out[HCHACHA_OUT_WORDS], int nrounds)
+{
+	hchacha_block_generic(state, out, nrounds);
+}
+EXPORT_SYMBOL(hchacha_block_arch);
+
+void chacha_crypt_arch(struct chacha_state *state, u8 *dst, const u8 *src,
+		       unsigned int bytes, int nrounds)
+{
+	if (!static_branch_likely(&have_p10) || bytes <= CHACHA_BLOCK_SIZE ||
+	    !crypto_simd_usable())
+		return chacha_crypt_generic(state, dst, src, bytes, nrounds);
+
+	do {
+		unsigned int todo = min_t(unsigned int, bytes, SZ_4K);
+
+		vsx_begin();
+		chacha_p10_do_8x(state, dst, src, todo, nrounds);
+		vsx_end();
+
+		bytes -= todo;
+		src += todo;
+		dst += todo;
+	} while (bytes);
+}
+EXPORT_SYMBOL(chacha_crypt_arch);
+
+bool chacha_is_arch_optimized(void)
+{
+	return static_key_enabled(&have_p10);
+}
+EXPORT_SYMBOL(chacha_is_arch_optimized);
+
+static int __init chacha_p10_init(void)
+{
+	if (cpu_has_feature(CPU_FTR_ARCH_31))
+		static_branch_enable(&have_p10);
+	return 0;
+}
+subsys_initcall(chacha_p10_init);
+
+static void __exit chacha_p10_exit(void)
+{
+}
+module_exit(chacha_p10_exit);
+
+MODULE_DESCRIPTION("ChaCha stream cipher (P10 accelerated)");
+MODULE_AUTHOR("Danny Tsen <dtsen@linux.ibm.com>");
+MODULE_LICENSE("GPL v2");
diff --git a/lib/crypto/powerpc/chacha-p10le-8x.S b/lib/crypto/powerpc/chacha-p10le-8x.S
new file mode 100644
index 000000000000..b29562bd5d40
--- /dev/null
+++ b/lib/crypto/powerpc/chacha-p10le-8x.S
@@ -0,0 +1,840 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+#
+# Accelerated chacha20 implementation for ppc64le.
+#
+# Copyright 2023- IBM Corp. All rights reserved
+#
+#===================================================================================
+# Written by Danny Tsen <dtsen@us.ibm.com>
+#
+# do rounds,  8 quarter rounds
+# 1.  a += b; d ^= a; d <<<= 16;
+# 2.  c += d; b ^= c; b <<<= 12;
+# 3.  a += b; d ^= a; d <<<= 8;
+# 4.  c += d; b ^= c; b <<<= 7
+#
+# row1 = (row1 + row2),  row4 = row1 xor row4,  row4 rotate each word by 16
+# row3 = (row3 + row4),  row2 = row3 xor row2,  row2 rotate each word by 12
+# row1 = (row1 + row2), row4 = row1 xor row4,  row4 rotate each word by 8
+# row3 = (row3 + row4), row2 = row3 xor row2,  row2 rotate each word by 7
+#
+# 4 blocks (a b c d)
+#
+# a0 b0 c0 d0
+# a1 b1 c1 d1
+# ...
+# a4 b4 c4 d4
+# ...
+# a8 b8 c8 d8
+# ...
+# a12 b12 c12 d12
+# a13 ...
+# a14 ...
+# a15 b15 c15 d15
+#
+# Column round (v0, v4,  v8, v12, v1, v5,  v9, v13, v2, v6, v10, v14, v3, v7, v11, v15)
+# Diagnal round (v0, v5, v10, v15, v1, v6, v11, v12, v2, v7,  v8, v13, v3, v4,  v9, v14)
+#
+
+#include <asm/ppc_asm.h>
+#include <asm/asm-offsets.h>
+#include <asm/asm-compat.h>
+#include <linux/linkage.h>
+
+.machine	"any"
+.text
+
+.macro	SAVE_GPR GPR OFFSET FRAME
+	std	\GPR,\OFFSET(\FRAME)
+.endm
+
+.macro	SAVE_VRS VRS OFFSET FRAME
+	li	16, \OFFSET
+	stvx	\VRS, 16, \FRAME
+.endm
+
+.macro	SAVE_VSX VSX OFFSET FRAME
+	li	16, \OFFSET
+	stxvx	\VSX, 16, \FRAME
+.endm
+
+.macro	RESTORE_GPR GPR OFFSET FRAME
+	ld	\GPR,\OFFSET(\FRAME)
+.endm
+
+.macro	RESTORE_VRS VRS OFFSET FRAME
+	li	16, \OFFSET
+	lvx	\VRS, 16, \FRAME
+.endm
+
+.macro	RESTORE_VSX VSX OFFSET FRAME
+	li	16, \OFFSET
+	lxvx	\VSX, 16, \FRAME
+.endm
+
+.macro SAVE_REGS
+	mflr 0
+	std 0, 16(1)
+	stdu 1,-752(1)
+
+	SAVE_GPR 14, 112, 1
+	SAVE_GPR 15, 120, 1
+	SAVE_GPR 16, 128, 1
+	SAVE_GPR 17, 136, 1
+	SAVE_GPR 18, 144, 1
+	SAVE_GPR 19, 152, 1
+	SAVE_GPR 20, 160, 1
+	SAVE_GPR 21, 168, 1
+	SAVE_GPR 22, 176, 1
+	SAVE_GPR 23, 184, 1
+	SAVE_GPR 24, 192, 1
+	SAVE_GPR 25, 200, 1
+	SAVE_GPR 26, 208, 1
+	SAVE_GPR 27, 216, 1
+	SAVE_GPR 28, 224, 1
+	SAVE_GPR 29, 232, 1
+	SAVE_GPR 30, 240, 1
+	SAVE_GPR 31, 248, 1
+
+	addi	9, 1, 256
+	SAVE_VRS 20, 0, 9
+	SAVE_VRS 21, 16, 9
+	SAVE_VRS 22, 32, 9
+	SAVE_VRS 23, 48, 9
+	SAVE_VRS 24, 64, 9
+	SAVE_VRS 25, 80, 9
+	SAVE_VRS 26, 96, 9
+	SAVE_VRS 27, 112, 9
+	SAVE_VRS 28, 128, 9
+	SAVE_VRS 29, 144, 9
+	SAVE_VRS 30, 160, 9
+	SAVE_VRS 31, 176, 9
+
+	SAVE_VSX 14, 192, 9
+	SAVE_VSX 15, 208, 9
+	SAVE_VSX 16, 224, 9
+	SAVE_VSX 17, 240, 9
+	SAVE_VSX 18, 256, 9
+	SAVE_VSX 19, 272, 9
+	SAVE_VSX 20, 288, 9
+	SAVE_VSX 21, 304, 9
+	SAVE_VSX 22, 320, 9
+	SAVE_VSX 23, 336, 9
+	SAVE_VSX 24, 352, 9
+	SAVE_VSX 25, 368, 9
+	SAVE_VSX 26, 384, 9
+	SAVE_VSX 27, 400, 9
+	SAVE_VSX 28, 416, 9
+	SAVE_VSX 29, 432, 9
+	SAVE_VSX 30, 448, 9
+	SAVE_VSX 31, 464, 9
+.endm # SAVE_REGS
+
+.macro RESTORE_REGS
+	addi	9, 1, 256
+	RESTORE_VRS 20, 0, 9
+	RESTORE_VRS 21, 16, 9
+	RESTORE_VRS 22, 32, 9
+	RESTORE_VRS 23, 48, 9
+	RESTORE_VRS 24, 64, 9
+	RESTORE_VRS 25, 80, 9
+	RESTORE_VRS 26, 96, 9
+	RESTORE_VRS 27, 112, 9
+	RESTORE_VRS 28, 128, 9
+	RESTORE_VRS 29, 144, 9
+	RESTORE_VRS 30, 160, 9
+	RESTORE_VRS 31, 176, 9
+
+	RESTORE_VSX 14, 192, 9
+	RESTORE_VSX 15, 208, 9
+	RESTORE_VSX 16, 224, 9
+	RESTORE_VSX 17, 240, 9
+	RESTORE_VSX 18, 256, 9
+	RESTORE_VSX 19, 272, 9
+	RESTORE_VSX 20, 288, 9
+	RESTORE_VSX 21, 304, 9
+	RESTORE_VSX 22, 320, 9
+	RESTORE_VSX 23, 336, 9
+	RESTORE_VSX 24, 352, 9
+	RESTORE_VSX 25, 368, 9
+	RESTORE_VSX 26, 384, 9
+	RESTORE_VSX 27, 400, 9
+	RESTORE_VSX 28, 416, 9
+	RESTORE_VSX 29, 432, 9
+	RESTORE_VSX 30, 448, 9
+	RESTORE_VSX 31, 464, 9
+
+	RESTORE_GPR 14, 112, 1
+	RESTORE_GPR 15, 120, 1
+	RESTORE_GPR 16, 128, 1
+	RESTORE_GPR 17, 136, 1
+	RESTORE_GPR 18, 144, 1
+	RESTORE_GPR 19, 152, 1
+	RESTORE_GPR 20, 160, 1
+	RESTORE_GPR 21, 168, 1
+	RESTORE_GPR 22, 176, 1
+	RESTORE_GPR 23, 184, 1
+	RESTORE_GPR 24, 192, 1
+	RESTORE_GPR 25, 200, 1
+	RESTORE_GPR 26, 208, 1
+	RESTORE_GPR 27, 216, 1
+	RESTORE_GPR 28, 224, 1
+	RESTORE_GPR 29, 232, 1
+	RESTORE_GPR 30, 240, 1
+	RESTORE_GPR 31, 248, 1
+
+	addi    1, 1, 752
+	ld 0, 16(1)
+	mtlr 0
+.endm # RESTORE_REGS
+
+.macro QT_loop_8x
+	# QR(v0, v4,  v8, v12, v1, v5,  v9, v13, v2, v6, v10, v14, v3, v7, v11, v15)
+	xxlor	0, 32+25, 32+25
+	xxlor	32+25, 20, 20
+	vadduwm 0, 0, 4
+	vadduwm 1, 1, 5
+	vadduwm 2, 2, 6
+	vadduwm 3, 3, 7
+	  vadduwm 16, 16, 20
+	  vadduwm 17, 17, 21
+	  vadduwm 18, 18, 22
+	  vadduwm 19, 19, 23
+
+	  vpermxor 12, 12, 0, 25
+	  vpermxor 13, 13, 1, 25
+	  vpermxor 14, 14, 2, 25
+	  vpermxor 15, 15, 3, 25
+	  vpermxor 28, 28, 16, 25
+	  vpermxor 29, 29, 17, 25
+	  vpermxor 30, 30, 18, 25
+	  vpermxor 31, 31, 19, 25
+	xxlor	32+25, 0, 0
+	vadduwm 8, 8, 12
+	vadduwm 9, 9, 13
+	vadduwm 10, 10, 14
+	vadduwm 11, 11, 15
+	  vadduwm 24, 24, 28
+	  vadduwm 25, 25, 29
+	  vadduwm 26, 26, 30
+	  vadduwm 27, 27, 31
+	vxor 4, 4, 8
+	vxor 5, 5, 9
+	vxor 6, 6, 10
+	vxor 7, 7, 11
+	  vxor 20, 20, 24
+	  vxor 21, 21, 25
+	  vxor 22, 22, 26
+	  vxor 23, 23, 27
+
+	xxlor	0, 32+25, 32+25
+	xxlor	32+25, 21, 21
+	vrlw 4, 4, 25  #
+	vrlw 5, 5, 25
+	vrlw 6, 6, 25
+	vrlw 7, 7, 25
+	  vrlw 20, 20, 25  #
+	  vrlw 21, 21, 25
+	  vrlw 22, 22, 25
+	  vrlw 23, 23, 25
+	xxlor	32+25, 0, 0
+	vadduwm 0, 0, 4
+	vadduwm 1, 1, 5
+	vadduwm 2, 2, 6
+	vadduwm 3, 3, 7
+	  vadduwm 16, 16, 20
+	  vadduwm 17, 17, 21
+	  vadduwm 18, 18, 22
+	  vadduwm 19, 19, 23
+
+	xxlor	0, 32+25, 32+25
+	xxlor	32+25, 22, 22
+	  vpermxor 12, 12, 0, 25
+	  vpermxor 13, 13, 1, 25
+	  vpermxor 14, 14, 2, 25
+	  vpermxor 15, 15, 3, 25
+	  vpermxor 28, 28, 16, 25
+	  vpermxor 29, 29, 17, 25
+	  vpermxor 30, 30, 18, 25
+	  vpermxor 31, 31, 19, 25
+	xxlor	32+25, 0, 0
+	vadduwm 8, 8, 12
+	vadduwm 9, 9, 13
+	vadduwm 10, 10, 14
+	vadduwm 11, 11, 15
+	  vadduwm 24, 24, 28
+	  vadduwm 25, 25, 29
+	  vadduwm 26, 26, 30
+	  vadduwm 27, 27, 31
+	xxlor	0, 32+28, 32+28
+	xxlor	32+28, 23, 23
+	vxor 4, 4, 8
+	vxor 5, 5, 9
+	vxor 6, 6, 10
+	vxor 7, 7, 11
+	  vxor 20, 20, 24
+	  vxor 21, 21, 25
+	  vxor 22, 22, 26
+	  vxor 23, 23, 27
+	vrlw 4, 4, 28  #
+	vrlw 5, 5, 28
+	vrlw 6, 6, 28
+	vrlw 7, 7, 28
+	  vrlw 20, 20, 28  #
+	  vrlw 21, 21, 28
+	  vrlw 22, 22, 28
+	  vrlw 23, 23, 28
+	xxlor	32+28, 0, 0
+
+	# QR(v0, v5, v10, v15, v1, v6, v11, v12, v2, v7,  v8, v13, v3, v4,  v9, v14)
+	xxlor	0, 32+25, 32+25
+	xxlor	32+25, 20, 20
+	vadduwm 0, 0, 5
+	vadduwm 1, 1, 6
+	vadduwm 2, 2, 7
+	vadduwm 3, 3, 4
+	  vadduwm 16, 16, 21
+	  vadduwm 17, 17, 22
+	  vadduwm 18, 18, 23
+	  vadduwm 19, 19, 20
+
+	  vpermxor 15, 15, 0, 25
+	  vpermxor 12, 12, 1, 25
+	  vpermxor 13, 13, 2, 25
+	  vpermxor 14, 14, 3, 25
+	  vpermxor 31, 31, 16, 25
+	  vpermxor 28, 28, 17, 25
+	  vpermxor 29, 29, 18, 25
+	  vpermxor 30, 30, 19, 25
+
+	xxlor	32+25, 0, 0
+	vadduwm 10, 10, 15
+	vadduwm 11, 11, 12
+	vadduwm 8, 8, 13
+	vadduwm 9, 9, 14
+	  vadduwm 26, 26, 31
+	  vadduwm 27, 27, 28
+	  vadduwm 24, 24, 29
+	  vadduwm 25, 25, 30
+	vxor 5, 5, 10
+	vxor 6, 6, 11
+	vxor 7, 7, 8
+	vxor 4, 4, 9
+	  vxor 21, 21, 26
+	  vxor 22, 22, 27
+	  vxor 23, 23, 24
+	  vxor 20, 20, 25
+
+	xxlor	0, 32+25, 32+25
+	xxlor	32+25, 21, 21
+	vrlw 5, 5, 25
+	vrlw 6, 6, 25
+	vrlw 7, 7, 25
+	vrlw 4, 4, 25
+	  vrlw 21, 21, 25
+	  vrlw 22, 22, 25
+	  vrlw 23, 23, 25
+	  vrlw 20, 20, 25
+	xxlor	32+25, 0, 0
+
+	vadduwm 0, 0, 5
+	vadduwm 1, 1, 6
+	vadduwm 2, 2, 7
+	vadduwm 3, 3, 4
+	  vadduwm 16, 16, 21
+	  vadduwm 17, 17, 22
+	  vadduwm 18, 18, 23
+	  vadduwm 19, 19, 20
+
+	xxlor	0, 32+25, 32+25
+	xxlor	32+25, 22, 22
+	  vpermxor 15, 15, 0, 25
+	  vpermxor 12, 12, 1, 25
+	  vpermxor 13, 13, 2, 25
+	  vpermxor 14, 14, 3, 25
+	  vpermxor 31, 31, 16, 25
+	  vpermxor 28, 28, 17, 25
+	  vpermxor 29, 29, 18, 25
+	  vpermxor 30, 30, 19, 25
+	xxlor	32+25, 0, 0
+
+	vadduwm 10, 10, 15
+	vadduwm 11, 11, 12
+	vadduwm 8, 8, 13
+	vadduwm 9, 9, 14
+	  vadduwm 26, 26, 31
+	  vadduwm 27, 27, 28
+	  vadduwm 24, 24, 29
+	  vadduwm 25, 25, 30
+
+	xxlor	0, 32+28, 32+28
+	xxlor	32+28, 23, 23
+	vxor 5, 5, 10
+	vxor 6, 6, 11
+	vxor 7, 7, 8
+	vxor 4, 4, 9
+	  vxor 21, 21, 26
+	  vxor 22, 22, 27
+	  vxor 23, 23, 24
+	  vxor 20, 20, 25
+	vrlw 5, 5, 28
+	vrlw 6, 6, 28
+	vrlw 7, 7, 28
+	vrlw 4, 4, 28
+	  vrlw 21, 21, 28
+	  vrlw 22, 22, 28
+	  vrlw 23, 23, 28
+	  vrlw 20, 20, 28
+	xxlor	32+28, 0, 0
+.endm
+
+.macro QT_loop_4x
+	# QR(v0, v4,  v8, v12, v1, v5,  v9, v13, v2, v6, v10, v14, v3, v7, v11, v15)
+	vadduwm 0, 0, 4
+	vadduwm 1, 1, 5
+	vadduwm 2, 2, 6
+	vadduwm 3, 3, 7
+	  vpermxor 12, 12, 0, 20
+	  vpermxor 13, 13, 1, 20
+	  vpermxor 14, 14, 2, 20
+	  vpermxor 15, 15, 3, 20
+	vadduwm 8, 8, 12
+	vadduwm 9, 9, 13
+	vadduwm 10, 10, 14
+	vadduwm 11, 11, 15
+	vxor 4, 4, 8
+	vxor 5, 5, 9
+	vxor 6, 6, 10
+	vxor 7, 7, 11
+	vrlw 4, 4, 21
+	vrlw 5, 5, 21
+	vrlw 6, 6, 21
+	vrlw 7, 7, 21
+	vadduwm 0, 0, 4
+	vadduwm 1, 1, 5
+	vadduwm 2, 2, 6
+	vadduwm 3, 3, 7
+	  vpermxor 12, 12, 0, 22
+	  vpermxor 13, 13, 1, 22
+	  vpermxor 14, 14, 2, 22
+	  vpermxor 15, 15, 3, 22
+	vadduwm 8, 8, 12
+	vadduwm 9, 9, 13
+	vadduwm 10, 10, 14
+	vadduwm 11, 11, 15
+	vxor 4, 4, 8
+	vxor 5, 5, 9
+	vxor 6, 6, 10
+	vxor 7, 7, 11
+	vrlw 4, 4, 23
+	vrlw 5, 5, 23
+	vrlw 6, 6, 23
+	vrlw 7, 7, 23
+
+	# QR(v0, v5, v10, v15, v1, v6, v11, v12, v2, v7,  v8, v13, v3, v4,  v9, v14)
+	vadduwm 0, 0, 5
+	vadduwm 1, 1, 6
+	vadduwm 2, 2, 7
+	vadduwm 3, 3, 4
+	  vpermxor 15, 15, 0, 20
+	  vpermxor 12, 12, 1, 20
+	  vpermxor 13, 13, 2, 20
+	  vpermxor 14, 14, 3, 20
+	vadduwm 10, 10, 15
+	vadduwm 11, 11, 12
+	vadduwm 8, 8, 13
+	vadduwm 9, 9, 14
+	vxor 5, 5, 10
+	vxor 6, 6, 11
+	vxor 7, 7, 8
+	vxor 4, 4, 9
+	vrlw 5, 5, 21
+	vrlw 6, 6, 21
+	vrlw 7, 7, 21
+	vrlw 4, 4, 21
+	vadduwm 0, 0, 5
+	vadduwm 1, 1, 6
+	vadduwm 2, 2, 7
+	vadduwm 3, 3, 4
+	  vpermxor 15, 15, 0, 22
+	  vpermxor 12, 12, 1, 22
+	  vpermxor 13, 13, 2, 22
+	  vpermxor 14, 14, 3, 22
+	vadduwm 10, 10, 15
+	vadduwm 11, 11, 12
+	vadduwm 8, 8, 13
+	vadduwm 9, 9, 14
+	vxor 5, 5, 10
+	vxor 6, 6, 11
+	vxor 7, 7, 8
+	vxor 4, 4, 9
+	vrlw 5, 5, 23
+	vrlw 6, 6, 23
+	vrlw 7, 7, 23
+	vrlw 4, 4, 23
+.endm
+
+# Transpose
+.macro TP_4x a0 a1 a2 a3
+	xxmrghw  10, 32+\a0, 32+\a1	# a0, a1, b0, b1
+	xxmrghw  11, 32+\a2, 32+\a3	# a2, a3, b2, b3
+	xxmrglw  12, 32+\a0, 32+\a1	# c0, c1, d0, d1
+	xxmrglw  13, 32+\a2, 32+\a3	# c2, c3, d2, d3
+	xxpermdi	32+\a0, 10, 11, 0	# a0, a1, a2, a3
+	xxpermdi	32+\a1, 10, 11, 3	# b0, b1, b2, b3
+	xxpermdi	32+\a2, 12, 13, 0	# c0, c1, c2, c3
+	xxpermdi	32+\a3, 12, 13, 3	# d0, d1, d2, d3
+.endm
+
+# key stream = working state + state
+.macro Add_state S
+	vadduwm \S+0, \S+0, 16-\S
+	vadduwm \S+4, \S+4, 17-\S
+	vadduwm \S+8, \S+8, 18-\S
+	vadduwm \S+12, \S+12, 19-\S
+
+	vadduwm \S+1, \S+1, 16-\S
+	vadduwm \S+5, \S+5, 17-\S
+	vadduwm \S+9, \S+9, 18-\S
+	vadduwm \S+13, \S+13, 19-\S
+
+	vadduwm \S+2, \S+2, 16-\S
+	vadduwm \S+6, \S+6, 17-\S
+	vadduwm \S+10, \S+10, 18-\S
+	vadduwm \S+14, \S+14, 19-\S
+
+	vadduwm	\S+3, \S+3, 16-\S
+	vadduwm	\S+7, \S+7, 17-\S
+	vadduwm	\S+11, \S+11, 18-\S
+	vadduwm	\S+15, \S+15, 19-\S
+.endm
+
+#
+# write 256 bytes
+#
+.macro Write_256 S
+	add 9, 14, 5
+	add 16, 14, 4
+	lxvw4x 0, 0, 9
+	lxvw4x 1, 17, 9
+	lxvw4x 2, 18, 9
+	lxvw4x 3, 19, 9
+	lxvw4x 4, 20, 9
+	lxvw4x 5, 21, 9
+	lxvw4x 6, 22, 9
+	lxvw4x 7, 23, 9
+	lxvw4x 8, 24, 9
+	lxvw4x 9, 25, 9
+	lxvw4x 10, 26, 9
+	lxvw4x 11, 27, 9
+	lxvw4x 12, 28, 9
+	lxvw4x 13, 29, 9
+	lxvw4x 14, 30, 9
+	lxvw4x 15, 31, 9
+
+	xxlxor \S+32, \S+32, 0
+	xxlxor \S+36, \S+36, 1
+	xxlxor \S+40, \S+40, 2
+	xxlxor \S+44, \S+44, 3
+	xxlxor \S+33, \S+33, 4
+	xxlxor \S+37, \S+37, 5
+	xxlxor \S+41, \S+41, 6
+	xxlxor \S+45, \S+45, 7
+	xxlxor \S+34, \S+34, 8
+	xxlxor \S+38, \S+38, 9
+	xxlxor \S+42, \S+42, 10
+	xxlxor \S+46, \S+46, 11
+	xxlxor \S+35, \S+35, 12
+	xxlxor \S+39, \S+39, 13
+	xxlxor \S+43, \S+43, 14
+	xxlxor \S+47, \S+47, 15
+
+	stxvw4x \S+32, 0, 16
+	stxvw4x \S+36, 17, 16
+	stxvw4x \S+40, 18, 16
+	stxvw4x \S+44, 19, 16
+
+	stxvw4x \S+33, 20, 16
+	stxvw4x \S+37, 21, 16
+	stxvw4x \S+41, 22, 16
+	stxvw4x \S+45, 23, 16
+
+	stxvw4x \S+34, 24, 16
+	stxvw4x \S+38, 25, 16
+	stxvw4x \S+42, 26, 16
+	stxvw4x \S+46, 27, 16
+
+	stxvw4x \S+35, 28, 16
+	stxvw4x \S+39, 29, 16
+	stxvw4x \S+43, 30, 16
+	stxvw4x \S+47, 31, 16
+
+.endm
+
+#
+# void chacha_p10le_8x(const struct chacha_state *state, u8 *dst, const u8 *src,
+#		       unsigned int len, int nrounds);
+#
+SYM_FUNC_START(chacha_p10le_8x)
+.align 5
+	cmpdi	6, 0
+	ble	Out_no_chacha
+
+	SAVE_REGS
+
+	# r17 - r31 mainly for Write_256 macro.
+	li	17, 16
+	li	18, 32
+	li	19, 48
+	li	20, 64
+	li	21, 80
+	li	22, 96
+	li	23, 112
+	li	24, 128
+	li	25, 144
+	li	26, 160
+	li	27, 176
+	li	28, 192
+	li	29, 208
+	li	30, 224
+	li	31, 240
+
+	mr 15, 6			# len
+	li 14, 0			# offset to inp and outp
+
+        lxvw4x	48, 0, 3		#  vr16, constants
+	lxvw4x	49, 17, 3		#  vr17, key 1
+	lxvw4x	50, 18, 3		#  vr18, key 2
+	lxvw4x	51, 19, 3		#  vr19, counter, nonce
+
+	# create (0, 1, 2, 3) counters
+	vspltisw 0, 0
+	vspltisw 1, 1
+	vspltisw 2, 2
+	vspltisw 3, 3
+	vmrghw	4, 0, 1
+	vmrglw	5, 2, 3
+	vsldoi	30, 4, 5, 8		# vr30 counter, 4 (0, 1, 2, 3)
+
+	vspltisw 21, 12
+	vspltisw 23, 7
+
+	addis	11, 2, permx@toc@ha
+	addi	11, 11, permx@toc@l
+	lxvw4x	32+20, 0, 11
+	lxvw4x	32+22, 17, 11
+
+	sradi	8, 7, 1
+
+	mtctr 8
+
+	# save constants to vsx
+	xxlor	16, 48, 48
+	xxlor	17, 49, 49
+	xxlor	18, 50, 50
+	xxlor	19, 51, 51
+
+	vspltisw 25, 4
+	vspltisw 26, 8
+
+	xxlor	25, 32+26, 32+26
+	xxlor	24, 32+25, 32+25
+
+	vadduwm	31, 30, 25		# counter = (0, 1, 2, 3) + (4, 4, 4, 4)
+	xxlor	30, 32+30, 32+30
+	xxlor	31, 32+31, 32+31
+
+	xxlor	20, 32+20, 32+20
+	xxlor	21, 32+21, 32+21
+	xxlor	22, 32+22, 32+22
+	xxlor	23, 32+23, 32+23
+
+	cmpdi	6, 512
+	blt	Loop_last
+
+Loop_8x:
+	xxspltw  32+0, 16, 0
+	xxspltw  32+1, 16, 1
+	xxspltw  32+2, 16, 2
+	xxspltw  32+3, 16, 3
+
+	xxspltw  32+4, 17, 0
+	xxspltw  32+5, 17, 1
+	xxspltw  32+6, 17, 2
+	xxspltw  32+7, 17, 3
+	xxspltw  32+8, 18, 0
+	xxspltw  32+9, 18, 1
+	xxspltw  32+10, 18, 2
+	xxspltw  32+11, 18, 3
+	xxspltw  32+12, 19, 0
+	xxspltw  32+13, 19, 1
+	xxspltw  32+14, 19, 2
+	xxspltw  32+15, 19, 3
+	vadduwm	12, 12, 30	# increase counter
+
+	xxspltw  32+16, 16, 0
+	xxspltw  32+17, 16, 1
+	xxspltw  32+18, 16, 2
+	xxspltw  32+19, 16, 3
+
+	xxspltw  32+20, 17, 0
+	xxspltw  32+21, 17, 1
+	xxspltw  32+22, 17, 2
+	xxspltw  32+23, 17, 3
+	xxspltw  32+24, 18, 0
+	xxspltw  32+25, 18, 1
+	xxspltw  32+26, 18, 2
+	xxspltw  32+27, 18, 3
+	xxspltw  32+28, 19, 0
+	xxspltw  32+29, 19, 1
+	vadduwm	28, 28, 31	# increase counter
+	xxspltw  32+30, 19, 2
+	xxspltw  32+31, 19, 3
+
+.align 5
+quarter_loop_8x:
+	QT_loop_8x
+
+	bdnz	quarter_loop_8x
+
+	xxlor	0, 32+30, 32+30
+	xxlor	32+30, 30, 30
+	vadduwm	12, 12, 30
+	xxlor	32+30, 0, 0
+	TP_4x 0, 1, 2, 3
+	TP_4x 4, 5, 6, 7
+	TP_4x 8, 9, 10, 11
+	TP_4x 12, 13, 14, 15
+
+	xxlor	0, 48, 48
+	xxlor	1, 49, 49
+	xxlor	2, 50, 50
+	xxlor	3, 51, 51
+	xxlor	48, 16, 16
+	xxlor	49, 17, 17
+	xxlor	50, 18, 18
+	xxlor	51, 19, 19
+	Add_state 0
+	xxlor	48, 0, 0
+	xxlor	49, 1, 1
+	xxlor	50, 2, 2
+	xxlor	51, 3, 3
+	Write_256 0
+	addi	14, 14, 256	# offset +=256
+	addi	15, 15, -256	# len -=256
+
+	xxlor	5, 32+31, 32+31
+	xxlor	32+31, 31, 31
+	vadduwm	28, 28, 31
+	xxlor	32+31, 5, 5
+	TP_4x 16+0, 16+1, 16+2, 16+3
+	TP_4x 16+4, 16+5, 16+6, 16+7
+	TP_4x 16+8, 16+9, 16+10, 16+11
+	TP_4x 16+12, 16+13, 16+14, 16+15
+
+	xxlor	32, 16, 16
+	xxlor	33, 17, 17
+	xxlor	34, 18, 18
+	xxlor	35, 19, 19
+	Add_state 16
+	Write_256 16
+	addi	14, 14, 256	# offset +=256
+	addi	15, 15, -256	# len +=256
+
+	xxlor	32+24, 24, 24
+	xxlor	32+25, 25, 25
+	xxlor	32+30, 30, 30
+	vadduwm	30, 30, 25
+	vadduwm	31, 30, 24
+	xxlor	30, 32+30, 32+30
+	xxlor	31, 32+31, 32+31
+
+	cmpdi	15, 0
+	beq	Out_loop
+
+	cmpdi	15, 512
+	blt	Loop_last
+
+	mtctr 8
+	b Loop_8x
+
+Loop_last:
+        lxvw4x	48, 0, 3		#  vr16, constants
+	lxvw4x	49, 17, 3		#  vr17, key 1
+	lxvw4x	50, 18, 3		#  vr18, key 2
+	lxvw4x	51, 19, 3		#  vr19, counter, nonce
+
+	vspltisw 21, 12
+	vspltisw 23, 7
+	addis	11, 2, permx@toc@ha
+	addi	11, 11, permx@toc@l
+	lxvw4x	32+20, 0, 11
+	lxvw4x	32+22, 17, 11
+
+	sradi	8, 7, 1
+	mtctr 8
+
+Loop_4x:
+	vspltw  0, 16, 0
+	vspltw  1, 16, 1
+	vspltw  2, 16, 2
+	vspltw  3, 16, 3
+
+	vspltw  4, 17, 0
+	vspltw  5, 17, 1
+	vspltw  6, 17, 2
+	vspltw  7, 17, 3
+	vspltw  8, 18, 0
+	vspltw  9, 18, 1
+	vspltw  10, 18, 2
+	vspltw  11, 18, 3
+	vspltw  12, 19, 0
+	vadduwm	12, 12, 30	# increase counter
+	vspltw  13, 19, 1
+	vspltw  14, 19, 2
+	vspltw  15, 19, 3
+
+.align 5
+quarter_loop:
+	QT_loop_4x
+
+	bdnz	quarter_loop
+
+	vadduwm	12, 12, 30
+	TP_4x 0, 1, 2, 3
+	TP_4x 4, 5, 6, 7
+	TP_4x 8, 9, 10, 11
+	TP_4x 12, 13, 14, 15
+
+	Add_state 0
+	Write_256 0
+	addi	14, 14, 256	# offset += 256
+	addi	15, 15, -256	# len += 256
+
+	# Update state counter
+	vspltisw 25, 4
+	vadduwm	30, 30, 25
+
+	cmpdi	15, 0
+	beq	Out_loop
+	cmpdi	15, 256
+	blt	Out_loop
+
+	mtctr 8
+	b Loop_4x
+
+Out_loop:
+	RESTORE_REGS
+	blr
+
+Out_no_chacha:
+	li	3, 0
+	blr
+SYM_FUNC_END(chacha_p10le_8x)
+
+SYM_DATA_START_LOCAL(PERMX)
+.align 5
+permx:
+.long 0x22330011, 0x66774455, 0xaabb8899, 0xeeffccdd
+.long 0x11223300, 0x55667744, 0x99aabb88, 0xddeeffcc
+SYM_DATA_END(PERMX)
diff --git a/lib/crypto/powerpc/poly1305-p10-glue.c b/lib/crypto/powerpc/poly1305-p10-glue.c
new file mode 100644
index 000000000000..3f1664a724b6
--- /dev/null
+++ b/lib/crypto/powerpc/poly1305-p10-glue.c
@@ -0,0 +1,96 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Poly1305 authenticator algorithm, RFC7539.
+ *
+ * Copyright 2023- IBM Corp. All rights reserved.
+ */
+#include <asm/switch_to.h>
+#include <crypto/internal/poly1305.h>
+#include <linux/cpufeature.h>
+#include <linux/jump_label.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/unaligned.h>
+
+asmlinkage void poly1305_p10le_4blocks(struct poly1305_block_state *state, const u8 *m, u32 mlen);
+asmlinkage void poly1305_64s(struct poly1305_block_state *state, const u8 *m, u32 mlen, int highbit);
+asmlinkage void poly1305_emit_64(const struct poly1305_state *state, const u32 nonce[4], u8 digest[POLY1305_DIGEST_SIZE]);
+
+static __ro_after_init DEFINE_STATIC_KEY_FALSE(have_p10);
+
+static void vsx_begin(void)
+{
+	preempt_disable();
+	enable_kernel_vsx();
+}
+
+static void vsx_end(void)
+{
+	disable_kernel_vsx();
+	preempt_enable();
+}
+
+void poly1305_block_init_arch(struct poly1305_block_state *dctx,
+			      const u8 raw_key[POLY1305_BLOCK_SIZE])
+{
+	if (!static_key_enabled(&have_p10))
+		return poly1305_block_init_generic(dctx, raw_key);
+
+	dctx->h = (struct poly1305_state){};
+	dctx->core_r.key.r64[0] = get_unaligned_le64(raw_key + 0);
+	dctx->core_r.key.r64[1] = get_unaligned_le64(raw_key + 8);
+}
+EXPORT_SYMBOL_GPL(poly1305_block_init_arch);
+
+void poly1305_blocks_arch(struct poly1305_block_state *state, const u8 *src,
+			  unsigned int len, u32 padbit)
+{
+	if (!static_key_enabled(&have_p10))
+		return poly1305_blocks_generic(state, src, len, padbit);
+	vsx_begin();
+	if (len >= POLY1305_BLOCK_SIZE * 4) {
+		poly1305_p10le_4blocks(state, src, len);
+		src += len - (len % (POLY1305_BLOCK_SIZE * 4));
+		len %= POLY1305_BLOCK_SIZE * 4;
+	}
+	while (len >= POLY1305_BLOCK_SIZE) {
+		poly1305_64s(state, src, POLY1305_BLOCK_SIZE, padbit);
+		len -= POLY1305_BLOCK_SIZE;
+		src += POLY1305_BLOCK_SIZE;
+	}
+	vsx_end();
+}
+EXPORT_SYMBOL_GPL(poly1305_blocks_arch);
+
+void poly1305_emit_arch(const struct poly1305_state *state,
+			u8 digest[POLY1305_DIGEST_SIZE],
+			const u32 nonce[4])
+{
+	if (!static_key_enabled(&have_p10))
+		return poly1305_emit_generic(state, digest, nonce);
+	poly1305_emit_64(state, nonce, digest);
+}
+EXPORT_SYMBOL_GPL(poly1305_emit_arch);
+
+bool poly1305_is_arch_optimized(void)
+{
+	return static_key_enabled(&have_p10);
+}
+EXPORT_SYMBOL(poly1305_is_arch_optimized);
+
+static int __init poly1305_p10_init(void)
+{
+	if (cpu_has_feature(CPU_FTR_ARCH_31))
+		static_branch_enable(&have_p10);
+	return 0;
+}
+subsys_initcall(poly1305_p10_init);
+
+static void __exit poly1305_p10_exit(void)
+{
+}
+module_exit(poly1305_p10_exit);
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Danny Tsen <dtsen@linux.ibm.com>");
+MODULE_DESCRIPTION("Optimized Poly1305 for P10");
diff --git a/lib/crypto/powerpc/poly1305-p10le_64.S b/lib/crypto/powerpc/poly1305-p10le_64.S
new file mode 100644
index 000000000000..a3c1987f1ecd
--- /dev/null
+++ b/lib/crypto/powerpc/poly1305-p10le_64.S
@@ -0,0 +1,1075 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+#
+# Accelerated poly1305 implementation for ppc64le.
+#
+# Copyright 2023- IBM Corp. All rights reserved
+#
+#===================================================================================
+# Written by Danny Tsen <dtsen@us.ibm.com>
+#
+# Poly1305 - this version mainly using vector/VSX/Scalar
+#  - 26 bits limbs
+#  - Handle multiple 64 byte blcok.
+#
+# Block size 16 bytes
+# key = (r, s)
+# clamp r &= 0x0FFFFFFC0FFFFFFC 0x0FFFFFFC0FFFFFFF
+# p = 2^130 - 5
+# a += m
+# a = (r + a) % p
+# a += s
+#
+# Improve performance by breaking down polynominal to the sum of products with
+#     h4 = m1 * r⁴ + m2 * r³ + m3 * r² + m4 * r
+#
+#  07/22/21 - this revison based on the above sum of products.  Setup r^4, r^3, r^2, r and s3, s2, s1, s0
+#             to 9 vectors for multiplications.
+#
+# setup r^4, r^3, r^2, r vectors
+#    vs    [r^1, r^3, r^2, r^4]
+#    vs0 = [r0,.....]
+#    vs1 = [r1,.....]
+#    vs2 = [r2,.....]
+#    vs3 = [r3,.....]
+#    vs4 = [r4,.....]
+#    vs5 = [r1*5,...]
+#    vs6 = [r2*5,...]
+#    vs7 = [r2*5,...]
+#    vs8 = [r4*5,...]
+#
+#  Each word in a vector consists a member of a "r/s" in [a * r/s].
+#
+# r0, r4*5, r3*5, r2*5, r1*5;
+# r1, r0,   r4*5, r3*5, r2*5;
+# r2, r1,   r0,   r4*5, r3*5;
+# r3, r2,   r1,   r0,   r4*5;
+# r4, r3,   r2,   r1,   r0  ;
+#
+#
+# poly1305_p10le_4blocks( uint8_t *k, uint32_t mlen, uint8_t *m)
+#  k = 32 bytes key
+#  r3 = k (r, s)
+#  r4 = mlen
+#  r5 = m
+#
+#include <asm/ppc_asm.h>
+#include <asm/asm-offsets.h>
+#include <asm/asm-compat.h>
+#include <linux/linkage.h>
+
+.machine "any"
+
+.text
+
+.macro	SAVE_GPR GPR OFFSET FRAME
+	std	\GPR,\OFFSET(\FRAME)
+.endm
+
+.macro	SAVE_VRS VRS OFFSET FRAME
+	li	16, \OFFSET
+	stvx	\VRS, 16, \FRAME
+.endm
+
+.macro	SAVE_VSX VSX OFFSET FRAME
+	li	16, \OFFSET
+	stxvx	\VSX, 16, \FRAME
+.endm
+
+.macro	RESTORE_GPR GPR OFFSET FRAME
+	ld	\GPR,\OFFSET(\FRAME)
+.endm
+
+.macro	RESTORE_VRS VRS OFFSET FRAME
+	li	16, \OFFSET
+	lvx	\VRS, 16, \FRAME
+.endm
+
+.macro	RESTORE_VSX VSX OFFSET FRAME
+	li	16, \OFFSET
+	lxvx	\VSX, 16, \FRAME
+.endm
+
+.macro SAVE_REGS
+	mflr 0
+	std 0, 16(1)
+	stdu 1,-752(1)
+
+	SAVE_GPR 14, 112, 1
+	SAVE_GPR 15, 120, 1
+	SAVE_GPR 16, 128, 1
+	SAVE_GPR 17, 136, 1
+	SAVE_GPR 18, 144, 1
+	SAVE_GPR 19, 152, 1
+	SAVE_GPR 20, 160, 1
+	SAVE_GPR 21, 168, 1
+	SAVE_GPR 22, 176, 1
+	SAVE_GPR 23, 184, 1
+	SAVE_GPR 24, 192, 1
+	SAVE_GPR 25, 200, 1
+	SAVE_GPR 26, 208, 1
+	SAVE_GPR 27, 216, 1
+	SAVE_GPR 28, 224, 1
+	SAVE_GPR 29, 232, 1
+	SAVE_GPR 30, 240, 1
+	SAVE_GPR 31, 248, 1
+
+	addi	9, 1, 256
+	SAVE_VRS 20, 0, 9
+	SAVE_VRS 21, 16, 9
+	SAVE_VRS 22, 32, 9
+	SAVE_VRS 23, 48, 9
+	SAVE_VRS 24, 64, 9
+	SAVE_VRS 25, 80, 9
+	SAVE_VRS 26, 96, 9
+	SAVE_VRS 27, 112, 9
+	SAVE_VRS 28, 128, 9
+	SAVE_VRS 29, 144, 9
+	SAVE_VRS 30, 160, 9
+	SAVE_VRS 31, 176, 9
+
+	SAVE_VSX 14, 192, 9
+	SAVE_VSX 15, 208, 9
+	SAVE_VSX 16, 224, 9
+	SAVE_VSX 17, 240, 9
+	SAVE_VSX 18, 256, 9
+	SAVE_VSX 19, 272, 9
+	SAVE_VSX 20, 288, 9
+	SAVE_VSX 21, 304, 9
+	SAVE_VSX 22, 320, 9
+	SAVE_VSX 23, 336, 9
+	SAVE_VSX 24, 352, 9
+	SAVE_VSX 25, 368, 9
+	SAVE_VSX 26, 384, 9
+	SAVE_VSX 27, 400, 9
+	SAVE_VSX 28, 416, 9
+	SAVE_VSX 29, 432, 9
+	SAVE_VSX 30, 448, 9
+	SAVE_VSX 31, 464, 9
+.endm # SAVE_REGS
+
+.macro RESTORE_REGS
+	addi	9, 1, 256
+	RESTORE_VRS 20, 0, 9
+	RESTORE_VRS 21, 16, 9
+	RESTORE_VRS 22, 32, 9
+	RESTORE_VRS 23, 48, 9
+	RESTORE_VRS 24, 64, 9
+	RESTORE_VRS 25, 80, 9
+	RESTORE_VRS 26, 96, 9
+	RESTORE_VRS 27, 112, 9
+	RESTORE_VRS 28, 128, 9
+	RESTORE_VRS 29, 144, 9
+	RESTORE_VRS 30, 160, 9
+	RESTORE_VRS 31, 176, 9
+
+	RESTORE_VSX 14, 192, 9
+	RESTORE_VSX 15, 208, 9
+	RESTORE_VSX 16, 224, 9
+	RESTORE_VSX 17, 240, 9
+	RESTORE_VSX 18, 256, 9
+	RESTORE_VSX 19, 272, 9
+	RESTORE_VSX 20, 288, 9
+	RESTORE_VSX 21, 304, 9
+	RESTORE_VSX 22, 320, 9
+	RESTORE_VSX 23, 336, 9
+	RESTORE_VSX 24, 352, 9
+	RESTORE_VSX 25, 368, 9
+	RESTORE_VSX 26, 384, 9
+	RESTORE_VSX 27, 400, 9
+	RESTORE_VSX 28, 416, 9
+	RESTORE_VSX 29, 432, 9
+	RESTORE_VSX 30, 448, 9
+	RESTORE_VSX 31, 464, 9
+
+	RESTORE_GPR 14, 112, 1
+	RESTORE_GPR 15, 120, 1
+	RESTORE_GPR 16, 128, 1
+	RESTORE_GPR 17, 136, 1
+	RESTORE_GPR 18, 144, 1
+	RESTORE_GPR 19, 152, 1
+	RESTORE_GPR 20, 160, 1
+	RESTORE_GPR 21, 168, 1
+	RESTORE_GPR 22, 176, 1
+	RESTORE_GPR 23, 184, 1
+	RESTORE_GPR 24, 192, 1
+	RESTORE_GPR 25, 200, 1
+	RESTORE_GPR 26, 208, 1
+	RESTORE_GPR 27, 216, 1
+	RESTORE_GPR 28, 224, 1
+	RESTORE_GPR 29, 232, 1
+	RESTORE_GPR 30, 240, 1
+	RESTORE_GPR 31, 248, 1
+
+	addi    1, 1, 752
+	ld 0, 16(1)
+	mtlr 0
+.endm # RESTORE_REGS
+
+#
+# p[0] = a0*r0 + a1*r4*5 + a2*r3*5 + a3*r2*5 + a4*r1*5;
+# p[1] = a0*r1 + a1*r0   + a2*r4*5 + a3*r3*5 + a4*r2*5;
+# p[2] = a0*r2 + a1*r1   + a2*r0   + a3*r4*5 + a4*r3*5;
+# p[3] = a0*r3 + a1*r2   + a2*r1   + a3*r0   + a4*r4*5;
+# p[4] = a0*r4 + a1*r3   + a2*r2   + a3*r1   + a4*r0  ;
+#
+#    [r^2, r^3, r^1, r^4]
+#    [m3,  m2,  m4,  m1]
+#
+# multiply odd and even words
+.macro mul_odd
+	vmulouw	14, 4, 26
+	vmulouw	10, 5, 3
+	vmulouw	11, 6, 2
+	vmulouw	12, 7, 1
+	vmulouw	13, 8, 0
+	vmulouw	15, 4, 27
+	vaddudm	14, 14, 10
+	vaddudm	14, 14, 11
+	vmulouw	10, 5, 26
+	vmulouw	11, 6, 3
+	vaddudm	14, 14, 12
+	vaddudm	14, 14, 13	# x0
+	vaddudm	15, 15, 10
+	vaddudm	15, 15, 11
+	vmulouw	12, 7, 2
+	vmulouw	13, 8, 1
+	vaddudm	15, 15, 12
+	vaddudm	15, 15, 13	# x1
+	vmulouw	16, 4, 28
+	vmulouw	10, 5, 27
+	vmulouw	11, 6, 26
+	vaddudm	16, 16, 10
+	vaddudm	16, 16, 11
+	vmulouw	12, 7, 3
+	vmulouw	13, 8, 2
+	vaddudm	16, 16, 12
+	vaddudm	16, 16, 13	# x2
+	vmulouw	17, 4, 29
+	vmulouw	10, 5, 28
+	vmulouw	11, 6, 27
+	vaddudm	17, 17, 10
+	vaddudm	17, 17, 11
+	vmulouw	12, 7, 26
+	vmulouw	13, 8, 3
+	vaddudm	17, 17, 12
+	vaddudm	17, 17, 13	# x3
+	vmulouw	18, 4, 30
+	vmulouw	10, 5, 29
+	vmulouw	11, 6, 28
+	vaddudm	18, 18, 10
+	vaddudm	18, 18, 11
+	vmulouw	12, 7, 27
+	vmulouw	13, 8, 26
+	vaddudm	18, 18, 12
+	vaddudm	18, 18, 13	# x4
+.endm
+
+.macro mul_even
+	vmuleuw	9, 4, 26
+	vmuleuw	10, 5, 3
+	vmuleuw	11, 6, 2
+	vmuleuw	12, 7, 1
+	vmuleuw	13, 8, 0
+	vaddudm	14, 14, 9
+	vaddudm	14, 14, 10
+	vaddudm	14, 14, 11
+	vaddudm	14, 14, 12
+	vaddudm	14, 14, 13	# x0
+
+	vmuleuw	9, 4, 27
+	vmuleuw	10, 5, 26
+	vmuleuw	11, 6, 3
+	vmuleuw	12, 7, 2
+	vmuleuw	13, 8, 1
+	vaddudm	15, 15, 9
+	vaddudm	15, 15, 10
+	vaddudm	15, 15, 11
+	vaddudm	15, 15, 12
+	vaddudm	15, 15, 13	# x1
+
+	vmuleuw	9, 4, 28
+	vmuleuw	10, 5, 27
+	vmuleuw	11, 6, 26
+	vmuleuw	12, 7, 3
+	vmuleuw	13, 8, 2
+	vaddudm	16, 16, 9
+	vaddudm	16, 16, 10
+	vaddudm	16, 16, 11
+	vaddudm	16, 16, 12
+	vaddudm	16, 16, 13	# x2
+
+	vmuleuw	9, 4, 29
+	vmuleuw	10, 5, 28
+	vmuleuw	11, 6, 27
+	vmuleuw	12, 7, 26
+	vmuleuw	13, 8, 3
+	vaddudm	17, 17, 9
+	vaddudm	17, 17, 10
+	vaddudm	17, 17, 11
+	vaddudm	17, 17, 12
+	vaddudm	17, 17, 13	# x3
+
+	vmuleuw	9, 4, 30
+	vmuleuw	10, 5, 29
+	vmuleuw	11, 6, 28
+	vmuleuw	12, 7, 27
+	vmuleuw	13, 8, 26
+	vaddudm	18, 18, 9
+	vaddudm	18, 18, 10
+	vaddudm	18, 18, 11
+	vaddudm	18, 18, 12
+	vaddudm	18, 18, 13	# x4
+.endm
+
+#
+# poly1305_setup_r
+#
+# setup r^4, r^3, r^2, r vectors
+#    [r, r^3, r^2, r^4]
+#    vs0 = [r0,...]
+#    vs1 = [r1,...]
+#    vs2 = [r2,...]
+#    vs3 = [r3,...]
+#    vs4 = [r4,...]
+#    vs5 = [r4*5,...]
+#    vs6 = [r3*5,...]
+#    vs7 = [r2*5,...]
+#    vs8 = [r1*5,...]
+#
+# r0, r4*5, r3*5, r2*5, r1*5;
+# r1, r0,   r4*5, r3*5, r2*5;
+# r2, r1,   r0,   r4*5, r3*5;
+# r3, r2,   r1,   r0,   r4*5;
+# r4, r3,   r2,   r1,   r0  ;
+#
+.macro poly1305_setup_r
+
+	# save r
+	xxlor	26, 58, 58
+	xxlor	27, 59, 59
+	xxlor	28, 60, 60
+	xxlor	29, 61, 61
+	xxlor	30, 62, 62
+
+	xxlxor	31, 31, 31
+
+#    [r, r^3, r^2, r^4]
+	# compute r^2
+	vmr	4, 26
+	vmr	5, 27
+	vmr	6, 28
+	vmr	7, 29
+	vmr	8, 30
+	bl	do_mul		# r^2 r^1
+	xxpermdi 58, 58, 36, 0x3		# r0
+	xxpermdi 59, 59, 37, 0x3		# r1
+	xxpermdi 60, 60, 38, 0x3		# r2
+	xxpermdi 61, 61, 39, 0x3		# r3
+	xxpermdi 62, 62, 40, 0x3		# r4
+	xxpermdi 36, 36, 36, 0x3
+	xxpermdi 37, 37, 37, 0x3
+	xxpermdi 38, 38, 38, 0x3
+	xxpermdi 39, 39, 39, 0x3
+	xxpermdi 40, 40, 40, 0x3
+	vspltisb 13, 2
+	vsld	9, 27, 13
+	vsld	10, 28, 13
+	vsld	11, 29, 13
+	vsld	12, 30, 13
+	vaddudm	0, 9, 27
+	vaddudm	1, 10, 28
+	vaddudm	2, 11, 29
+	vaddudm	3, 12, 30
+
+	bl	do_mul		# r^4 r^3
+	vmrgow	26, 26, 4
+	vmrgow	27, 27, 5
+	vmrgow	28, 28, 6
+	vmrgow	29, 29, 7
+	vmrgow	30, 30, 8
+	vspltisb 13, 2
+	vsld	9, 27, 13
+	vsld	10, 28, 13
+	vsld	11, 29, 13
+	vsld	12, 30, 13
+	vaddudm	0, 9, 27
+	vaddudm	1, 10, 28
+	vaddudm	2, 11, 29
+	vaddudm	3, 12, 30
+
+	# r^2 r^4
+	xxlor	0, 58, 58
+	xxlor	1, 59, 59
+	xxlor	2, 60, 60
+	xxlor	3, 61, 61
+	xxlor	4, 62, 62
+	xxlor	5, 32, 32
+	xxlor	6, 33, 33
+	xxlor	7, 34, 34
+	xxlor	8, 35, 35
+
+	vspltw	9, 26, 3
+	vspltw	10, 26, 2
+	vmrgow	26, 10, 9
+	vspltw	9, 27, 3
+	vspltw	10, 27, 2
+	vmrgow	27, 10, 9
+	vspltw	9, 28, 3
+	vspltw	10, 28, 2
+	vmrgow	28, 10, 9
+	vspltw	9, 29, 3
+	vspltw	10, 29, 2
+	vmrgow	29, 10, 9
+	vspltw	9, 30, 3
+	vspltw	10, 30, 2
+	vmrgow	30, 10, 9
+
+	vsld	9, 27, 13
+	vsld	10, 28, 13
+	vsld	11, 29, 13
+	vsld	12, 30, 13
+	vaddudm	0, 9, 27
+	vaddudm	1, 10, 28
+	vaddudm	2, 11, 29
+	vaddudm	3, 12, 30
+.endm
+
+SYM_FUNC_START_LOCAL(do_mul)
+	mul_odd
+
+	# do reduction ( h %= p )
+	# carry reduction
+	vspltisb 9, 2
+	vsrd	10, 14, 31
+	vsrd	11, 17, 31
+	vand	7, 17, 25
+	vand	4, 14, 25
+	vaddudm	18, 18, 11
+	vsrd	12, 18, 31
+	vaddudm	15, 15, 10
+
+	vsrd	11, 15, 31
+	vand	8, 18, 25
+	vand	5, 15, 25
+	vaddudm	4, 4, 12
+	vsld	10, 12, 9
+	vaddudm	6, 16, 11
+
+	vsrd	13, 6, 31
+	vand	6, 6, 25
+	vaddudm	4, 4, 10
+	vsrd	10, 4, 31
+	vaddudm	7, 7, 13
+
+	vsrd	11, 7, 31
+	vand	7, 7, 25
+	vand	4, 4, 25
+	vaddudm	5, 5, 10
+	vaddudm	8, 8, 11
+	blr
+SYM_FUNC_END(do_mul)
+
+#
+# init key
+#
+.macro do_poly1305_init
+	addis	10, 2, rmask@toc@ha
+	addi	10, 10, rmask@toc@l
+
+	ld	11, 0(10)
+	ld	12, 8(10)
+
+	li	14, 16
+	li	15, 32
+	addis	10, 2, cnum@toc@ha
+	addi	10, 10, cnum@toc@l
+	lvx	25, 0, 10	# v25 - mask
+	lvx	31, 14, 10	# v31 = 1a
+	lvx	19, 15, 10	# v19 = 1 << 24
+	lxv	24, 48(10)	# vs24
+	lxv	25, 64(10)	# vs25
+
+	# initialize
+	# load key from r3 to vectors
+	ld	9, 24(3)
+	ld	10, 32(3)
+	and.	9, 9, 11
+	and.	10, 10, 12
+
+	# break 26 bits
+	extrdi	14, 9, 26, 38
+	extrdi	15, 9, 26, 12
+	extrdi	16, 9, 12, 0
+	mtvsrdd	58, 0, 14
+	insrdi	16, 10, 14, 38
+	mtvsrdd	59, 0, 15
+	extrdi	17, 10, 26, 24
+	mtvsrdd	60, 0, 16
+	extrdi	18, 10, 24, 0
+	mtvsrdd	61, 0, 17
+	mtvsrdd	62, 0, 18
+
+	# r1 = r1 * 5, r2 = r2 * 5, r3 = r3 * 5, r4 = r4 * 5
+	li	9, 5
+	mtvsrdd	36, 0, 9
+	vmulouw	0, 27, 4		# v0 = rr0
+	vmulouw	1, 28, 4		# v1 = rr1
+	vmulouw	2, 29, 4		# v2 = rr2
+	vmulouw	3, 30, 4		# v3 = rr3
+.endm
+
+#
+# poly1305_p10le_4blocks( uint8_t *k, uint32_t mlen, uint8_t *m)
+#  k = 32 bytes key
+#  r3 = k (r, s)
+#  r4 = mlen
+#  r5 = m
+#
+SYM_FUNC_START(poly1305_p10le_4blocks)
+.align 5
+	cmpdi	5, 64
+	blt	Out_no_poly1305
+
+	SAVE_REGS
+
+	do_poly1305_init
+
+	li	21, 0	# counter to message
+
+	poly1305_setup_r
+
+	# load previous H state
+	# break/convert r6 to 26 bits
+	ld	9, 0(3)
+	ld	10, 8(3)
+	ld	19, 16(3)
+	sldi	19, 19, 24
+	mtvsrdd	41, 0, 19
+	extrdi	14, 9, 26, 38
+	extrdi	15, 9, 26, 12
+	extrdi	16, 9, 12, 0
+	mtvsrdd	36, 0, 14
+	insrdi	16, 10, 14, 38
+	mtvsrdd	37, 0, 15
+	extrdi	17, 10, 26, 24
+	mtvsrdd	38, 0, 16
+	extrdi	18, 10, 24, 0
+	mtvsrdd	39, 0, 17
+	mtvsrdd	40, 0, 18
+	vor	8, 8, 9
+
+	# input m1 m2
+	add	20, 4, 21
+	xxlor	49, 24, 24
+	xxlor	50, 25, 25
+	lxvw4x	43, 0, 20
+	addi	17, 20, 16
+	lxvw4x	44, 0, 17
+	vperm	14, 11, 12, 17
+	vperm	15, 11, 12, 18
+	vand	9, 14, 25	# a0
+	vsrd	10, 14, 31	# >> 26
+	vsrd	11, 10, 31	# 12 bits left
+	vand	10, 10, 25	# a1
+	vspltisb 13, 12
+	vand	16, 15, 25
+	vsld	12, 16, 13
+	vor	11, 11, 12
+	vand	11, 11, 25	# a2
+	vspltisb 13, 14
+	vsrd	12, 15, 13	# >> 14
+	vsrd	13, 12, 31	# >> 26, a4
+	vand	12, 12, 25	# a3
+
+	vaddudm	20, 4, 9
+	vaddudm	21, 5, 10
+	vaddudm	22, 6, 11
+	vaddudm	23, 7, 12
+	vaddudm	24, 8, 13
+
+	# m3 m4
+	addi	17, 17, 16
+	lxvw4x	43, 0, 17
+	addi	17, 17, 16
+	lxvw4x	44, 0, 17
+	vperm	14, 11, 12, 17
+	vperm	15, 11, 12, 18
+	vand	9, 14, 25	# a0
+	vsrd	10, 14, 31	# >> 26
+	vsrd	11, 10, 31	# 12 bits left
+	vand	10, 10, 25	# a1
+	vspltisb 13, 12
+	vand	16, 15, 25
+	vsld	12, 16, 13
+	vspltisb 13, 14
+	vor	11, 11, 12
+	vand	11, 11, 25	# a2
+	vsrd	12, 15, 13	# >> 14
+	vsrd	13, 12, 31	# >> 26, a4
+	vand	12, 12, 25	# a3
+
+	# Smash 4 message blocks into 5 vectors of [m4,  m2,  m3,  m1]
+	vmrgow	4, 9, 20
+	vmrgow	5, 10, 21
+	vmrgow	6, 11, 22
+	vmrgow	7, 12, 23
+	vmrgow	8, 13, 24
+	vaddudm	8, 8, 19
+
+	addi	5, 5, -64	# len -= 64
+	addi	21, 21, 64	# offset += 64
+
+	li      9, 64
+	divdu   31, 5, 9
+
+	cmpdi	31, 0
+	ble	Skip_block_loop
+
+	mtctr	31
+
+# h4 =   m1 * r⁴ + m2 * r³ + m3 * r² + m4 * r
+# Rewrite the polynominal sum of product as follows,
+# h1 = (h0 + m1) * r^2,	h2 = (h0 + m2) * r^2
+# h3 = (h1 + m3) * r^2,	h4 = (h2 + m4) * r^2  --> (h0 + m1) r*4 + (h3 + m3) r^2, (h0 + m2) r^4 + (h0 + m4) r^2
+#  .... Repeat
+# h5 = (h3 + m5) * r^2,	h6 = (h4 + m6) * r^2  -->
+# h7 = (h5 + m7) * r^2,	h8 = (h6 + m8) * r^1  --> m5 * r^4 + m6 * r^3 + m7 * r^2 + m8 * r
+#
+loop_4blocks:
+
+	# Multiply odd words and even words
+	mul_odd
+	mul_even
+	# carry reduction
+	vspltisb 9, 2
+	vsrd	10, 14, 31
+	vsrd	11, 17, 31
+	vand	7, 17, 25
+	vand	4, 14, 25
+	vaddudm	18, 18, 11
+	vsrd	12, 18, 31
+	vaddudm	15, 15, 10
+
+	vsrd	11, 15, 31
+	vand	8, 18, 25
+	vand	5, 15, 25
+	vaddudm	4, 4, 12
+	vsld	10, 12, 9
+	vaddudm	6, 16, 11
+
+	vsrd	13, 6, 31
+	vand	6, 6, 25
+	vaddudm	4, 4, 10
+	vsrd	10, 4, 31
+	vaddudm	7, 7, 13
+
+	vsrd	11, 7, 31
+	vand	7, 7, 25
+	vand	4, 4, 25
+	vaddudm	5, 5, 10
+	vaddudm	8, 8, 11
+
+	# input m1  m2  m3  m4
+	add	20, 4, 21
+	xxlor	49, 24, 24
+	xxlor	50, 25, 25
+	lxvw4x	43, 0, 20
+	addi	17, 20, 16
+	lxvw4x	44, 0, 17
+	vperm	14, 11, 12, 17
+	vperm	15, 11, 12, 18
+	addi	17, 17, 16
+	lxvw4x	43, 0, 17
+	addi	17, 17, 16
+	lxvw4x	44, 0, 17
+	vperm	17, 11, 12, 17
+	vperm	18, 11, 12, 18
+
+	vand	20, 14, 25	# a0
+	vand	9, 17, 25	# a0
+	vsrd	21, 14, 31	# >> 26
+	vsrd	22, 21, 31	# 12 bits left
+	vsrd	10, 17, 31	# >> 26
+	vsrd	11, 10, 31	# 12 bits left
+
+	vand	21, 21, 25	# a1
+	vand	10, 10, 25	# a1
+
+	vspltisb 13, 12
+	vand	16, 15, 25
+	vsld	23, 16, 13
+	vor	22, 22, 23
+	vand	22, 22, 25	# a2
+	vand	16, 18, 25
+	vsld	12, 16, 13
+	vor	11, 11, 12
+	vand	11, 11, 25	# a2
+	vspltisb 13, 14
+	vsrd	23, 15, 13	# >> 14
+	vsrd	24, 23, 31	# >> 26, a4
+	vand	23, 23, 25	# a3
+	vsrd	12, 18, 13	# >> 14
+	vsrd	13, 12, 31	# >> 26, a4
+	vand	12, 12, 25	# a3
+
+	vaddudm	4, 4, 20
+	vaddudm	5, 5, 21
+	vaddudm	6, 6, 22
+	vaddudm	7, 7, 23
+	vaddudm	8, 8, 24
+
+	# Smash 4 message blocks into 5 vectors of [m4,  m2,  m3,  m1]
+	vmrgow	4, 9, 4
+	vmrgow	5, 10, 5
+	vmrgow	6, 11, 6
+	vmrgow	7, 12, 7
+	vmrgow	8, 13, 8
+	vaddudm	8, 8, 19
+
+	addi	5, 5, -64	# len -= 64
+	addi	21, 21, 64	# offset += 64
+
+	bdnz	loop_4blocks
+
+Skip_block_loop:
+	xxlor	58, 0, 0
+	xxlor	59, 1, 1
+	xxlor	60, 2, 2
+	xxlor	61, 3, 3
+	xxlor	62, 4, 4
+	xxlor	32, 5, 5
+	xxlor	33, 6, 6
+	xxlor	34, 7, 7
+	xxlor	35, 8, 8
+
+	# Multiply odd words and even words
+	mul_odd
+	mul_even
+
+	# Sum the products.
+	xxpermdi 41, 31, 46, 0
+	xxpermdi 42, 31, 47, 0
+	vaddudm	4, 14, 9
+	xxpermdi 36, 31, 36, 3
+	vaddudm	5, 15, 10
+	xxpermdi 37, 31, 37, 3
+	xxpermdi 43, 31, 48, 0
+	vaddudm	6, 16, 11
+	xxpermdi 38, 31, 38, 3
+	xxpermdi 44, 31, 49, 0
+	vaddudm	7, 17, 12
+	xxpermdi 39, 31, 39, 3
+	xxpermdi 45, 31, 50, 0
+	vaddudm	8, 18, 13
+	xxpermdi 40, 31, 40, 3
+
+	# carry reduction
+	vspltisb 9, 2
+	vsrd	10, 4, 31
+	vsrd	11, 7, 31
+	vand	7, 7, 25
+	vand	4, 4, 25
+	vaddudm	8, 8, 11
+	vsrd	12, 8, 31
+	vaddudm	5, 5, 10
+
+	vsrd	11, 5, 31
+	vand	8, 8, 25
+	vand	5, 5, 25
+	vaddudm	4, 4, 12
+	vsld	10, 12, 9
+	vaddudm	6, 6, 11
+
+	vsrd	13, 6, 31
+	vand	6, 6, 25
+	vaddudm	4, 4, 10
+	vsrd	10, 4, 31
+	vaddudm	7, 7, 13
+
+	vsrd	11, 7, 31
+	vand	7, 7, 25
+	vand	4, 4, 25
+	vaddudm	5, 5, 10
+	vsrd	10, 5, 31
+	vand	5, 5, 25
+	vaddudm	6, 6, 10
+	vaddudm	8, 8, 11
+
+	b	do_final_update
+
+do_final_update:
+	# combine 26 bit limbs
+	# v4, v5, v6, v7 and v8 are 26 bit vectors
+	vsld	5, 5, 31
+	vor	20, 4, 5
+	vspltisb 11, 12
+	vsrd	12, 6, 11
+	vsld	6, 6, 31
+	vsld	6, 6, 31
+	vor	20, 20, 6
+	vspltisb 11, 14
+	vsld	7, 7, 11
+	vor	21, 7, 12
+	mfvsrld	16, 40		# save last 2 bytes
+	vsld	8, 8, 11
+	vsld	8, 8, 31
+	vor	21, 21, 8
+	mfvsrld	17, 52
+	mfvsrld	19, 53
+	srdi	16, 16, 24
+
+	std	17, 0(3)
+	std	19, 8(3)
+	stw	16, 16(3)
+
+Out_loop:
+	li	3, 0
+
+	RESTORE_REGS
+
+	blr
+
+Out_no_poly1305:
+	li	3, 0
+	blr
+SYM_FUNC_END(poly1305_p10le_4blocks)
+
+#
+# =======================================================================
+# The following functions implement 64 x 64 bits multiplication poly1305.
+#
+SYM_FUNC_START_LOCAL(Poly1305_init_64)
+	#  mask 0x0FFFFFFC0FFFFFFC
+	#  mask 0x0FFFFFFC0FFFFFFF
+	addis	10, 2, rmask@toc@ha
+	addi	10, 10, rmask@toc@l
+	ld	11, 0(10)
+	ld	12, 8(10)
+
+	# initialize
+	# load key from r3
+	ld	9, 24(3)
+	ld	10, 32(3)
+	and.	9, 9, 11	# cramp mask r0
+	and.	10, 10, 12	# cramp mask r1
+
+        srdi    21, 10, 2
+        add     19, 21, 10      # s1: r19 - (r1 >> 2) *5
+
+        # setup r and s
+        li      25, 0
+	mtvsrdd 32+0, 9, 19	# r0, s1
+	mtvsrdd 32+1, 10, 9	# r1, r0
+	mtvsrdd 32+2, 19, 25	# s1
+	mtvsrdd 32+3, 9, 25	# r0
+
+	blr
+SYM_FUNC_END(Poly1305_init_64)
+
+# Poly1305_mult
+# v6 = (h0, h1), v8 = h2
+# v0 = (r0, s1), v1 = (r1, r0), v2 = s1, v3 = r0
+#
+# Output: v7, v10, v11
+#
+SYM_FUNC_START_LOCAL(Poly1305_mult)
+	#
+	#	d0 = h0 * r0 + h1 * s1
+	vmsumudm	7, 6, 0, 9		# h0 * r0, h1 * s1
+
+	#	d1 = h0 * r1 + h1 * r0 + h2 * s1
+	vmsumudm	11, 6, 1, 9		# h0 * r1, h1 * r0
+	vmsumudm	10, 8, 2, 11		# d1 += h2 * s1
+
+	#       d2 = r0
+	vmsumudm	11, 8, 3, 9		# d2 = h2 * r0
+	blr
+SYM_FUNC_END(Poly1305_mult)
+
+#
+# carry reduction
+# h %=p
+#
+# Input: v7, v10, v11
+# Output: r27, r28, r29
+#
+SYM_FUNC_START_LOCAL(Carry_reduction)
+	mfvsrld	27, 32+7
+	mfvsrld	28, 32+10
+	mfvsrld	29, 32+11
+	mfvsrd	20, 32+7	# h0.h
+	mfvsrd	21, 32+10	# h1.h
+
+	addc	28, 28, 20
+	adde	29, 29, 21
+	srdi	22, 29, 0x2
+	sldi	23, 22, 0x2
+	add	23, 23, 22	# (h2 & 3) * 5
+	addc	27, 27, 23	# h0
+	addze	28, 28		# h1
+	andi.	29, 29, 0x3	# h2
+	blr
+SYM_FUNC_END(Carry_reduction)
+
+#
+# poly1305 multiplication
+# h *= r, h %= p
+#	d0 = h0 * r0 + h1 * s1
+#	d1 = h0 * r1 + h1 * r0 + h2 * s1
+#       d2 = h0 * r0
+#
+#
+# unsigned int poly1305_test_64s(unisgned char *state, const byte *src, size_t len, highbit)
+#   - no highbit if final leftover block (highbit = 0)
+#
+SYM_FUNC_START(poly1305_64s)
+	cmpdi	5, 0
+	ble	Out_no_poly1305_64
+
+	mflr 0
+	std 0, 16(1)
+	stdu 1,-400(1)
+
+	SAVE_GPR 14, 112, 1
+	SAVE_GPR 15, 120, 1
+	SAVE_GPR 16, 128, 1
+	SAVE_GPR 17, 136, 1
+	SAVE_GPR 18, 144, 1
+	SAVE_GPR 19, 152, 1
+	SAVE_GPR 20, 160, 1
+	SAVE_GPR 21, 168, 1
+	SAVE_GPR 22, 176, 1
+	SAVE_GPR 23, 184, 1
+	SAVE_GPR 24, 192, 1
+	SAVE_GPR 25, 200, 1
+	SAVE_GPR 26, 208, 1
+	SAVE_GPR 27, 216, 1
+	SAVE_GPR 28, 224, 1
+	SAVE_GPR 29, 232, 1
+	SAVE_GPR 30, 240, 1
+	SAVE_GPR 31, 248, 1
+
+	# Init poly1305
+	bl Poly1305_init_64
+
+	li 25, 0			# offset to inp and outp
+
+	add 11, 25, 4
+
+	# load h
+	# h0, h1, h2?
+        ld	27, 0(3)
+        ld	28, 8(3)
+        lwz	29, 16(3)
+
+        li      30, 16
+        divdu   31, 5, 30
+
+        mtctr   31
+
+        mr      24, 6		# highbit
+
+Loop_block_64:
+	vxor	9, 9, 9
+
+	ld	20, 0(11)
+	ld	21, 8(11)
+	addi	11, 11, 16
+
+	addc	27, 27, 20
+	adde	28, 28, 21
+	adde	29, 29, 24
+
+	li	22, 0
+	mtvsrdd	32+6, 27, 28	# h0, h1
+	mtvsrdd	32+8, 29, 22	# h2
+
+	bl	Poly1305_mult
+
+	bl	Carry_reduction
+
+	bdnz	Loop_block_64
+
+	std	27, 0(3)
+	std	28, 8(3)
+	stw	29, 16(3)
+
+	li	3, 0
+
+	RESTORE_GPR 14, 112, 1
+	RESTORE_GPR 15, 120, 1
+	RESTORE_GPR 16, 128, 1
+	RESTORE_GPR 17, 136, 1
+	RESTORE_GPR 18, 144, 1
+	RESTORE_GPR 19, 152, 1
+	RESTORE_GPR 20, 160, 1
+	RESTORE_GPR 21, 168, 1
+	RESTORE_GPR 22, 176, 1
+	RESTORE_GPR 23, 184, 1
+	RESTORE_GPR 24, 192, 1
+	RESTORE_GPR 25, 200, 1
+	RESTORE_GPR 26, 208, 1
+	RESTORE_GPR 27, 216, 1
+	RESTORE_GPR 28, 224, 1
+	RESTORE_GPR 29, 232, 1
+	RESTORE_GPR 30, 240, 1
+	RESTORE_GPR 31, 248, 1
+
+	addi    1, 1, 400
+	ld 0, 16(1)
+	mtlr 0
+
+	blr
+
+Out_no_poly1305_64:
+	li	3, 0
+	blr
+SYM_FUNC_END(poly1305_64s)
+
+#
+# Input: r3 = h, r4 = s, r5 = mac
+# mac = h + s
+#
+SYM_FUNC_START(poly1305_emit_64)
+	ld	10, 0(3)
+	ld	11, 8(3)
+	ld	12, 16(3)
+
+	# compare modulus
+	# h + 5 + (-p)
+	mr	6, 10
+	mr	7, 11
+	mr	8, 12
+	addic.	6, 6, 5
+	addze	7, 7
+	addze	8, 8
+	srdi	9, 8, 2		# overflow?
+	cmpdi	9, 0
+	beq	Skip_h64
+	mr	10, 6
+	mr	11, 7
+	mr	12, 8
+
+Skip_h64:
+	ld	6, 0(4)
+	ld	7, 8(4)
+	addc	10, 10, 6
+	adde	11, 11, 7
+	addze	12, 12
+
+	std	10, 0(5)
+	std	11, 8(5)
+	blr
+SYM_FUNC_END(poly1305_emit_64)
+
+SYM_DATA_START_LOCAL(RMASK)
+.align 5
+rmask:
+.byte	0xff, 0xff, 0xff, 0x0f, 0xfc, 0xff, 0xff, 0x0f, 0xfc, 0xff, 0xff, 0x0f, 0xfc, 0xff, 0xff, 0x0f
+cnum:
+.long	0x03ffffff, 0x00000000, 0x03ffffff, 0x00000000
+.long	0x1a, 0x00, 0x1a, 0x00
+.long	0x01000000, 0x01000000, 0x01000000, 0x01000000
+.long	0x00010203, 0x04050607, 0x10111213, 0x14151617
+.long	0x08090a0b, 0x0c0d0e0f, 0x18191a1b, 0x1c1d1e1f
+SYM_DATA_END(RMASK)
diff --git a/lib/crypto/powerpc/sha256-spe-asm.S b/lib/crypto/powerpc/sha256-spe-asm.S
new file mode 100644
index 000000000000..cd99d71dae34
--- /dev/null
+++ b/lib/crypto/powerpc/sha256-spe-asm.S
@@ -0,0 +1,318 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+/*
+ * Fast SHA-256 implementation for SPE instruction set (PPC)
+ *
+ * This code makes use of the SPE SIMD instruction set as defined in
+ * http://cache.freescale.com/files/32bit/doc/ref_manual/SPEPIM.pdf
+ * Implementation is based on optimization guide notes from
+ * http://cache.freescale.com/files/32bit/doc/app_note/AN2665.pdf
+ *
+ * Copyright (c) 2015 Markus Stockhausen <stockhausen@collogia.de>
+ */
+
+#include <asm/ppc_asm.h>
+#include <asm/asm-offsets.h>
+
+#define rHP	r3	/* pointer to hash values in memory		*/
+#define rKP	r24	/* pointer to round constants			*/
+#define rWP	r4	/* pointer to input data			*/
+
+#define rH0	r5	/* 8 32 bit hash values in 8 registers		*/
+#define rH1	r6
+#define rH2	r7
+#define rH3	r8
+#define rH4	r9
+#define rH5	r10
+#define rH6	r11
+#define rH7	r12
+
+#define rW0	r14	/* 64 bit registers. 16 words in 8 registers	*/
+#define rW1	r15
+#define rW2	r16
+#define rW3	r17
+#define rW4	r18
+#define rW5	r19
+#define rW6	r20
+#define rW7	r21
+
+#define rT0	r22	/* 64 bit temporaries 				*/
+#define rT1	r23
+#define rT2	r0	/* 32 bit temporaries				*/
+#define rT3	r25
+
+#define CMP_KN_LOOP
+#define CMP_KC_LOOP \
+	cmpwi		rT1,0;
+
+#define INITIALIZE \
+	stwu		r1,-128(r1);	/* create stack frame		*/ \
+	evstdw		r14,8(r1);	/* We must save non volatile	*/ \
+	evstdw		r15,16(r1);	/* registers. Take the chance	*/ \
+	evstdw		r16,24(r1);	/* and save the SPE part too	*/ \
+	evstdw		r17,32(r1);					   \
+	evstdw		r18,40(r1);					   \
+	evstdw		r19,48(r1);					   \
+	evstdw		r20,56(r1);					   \
+	evstdw		r21,64(r1);					   \
+	evstdw		r22,72(r1);					   \
+	evstdw		r23,80(r1);					   \
+	stw		r24,88(r1);	/* save normal registers	*/ \
+	stw		r25,92(r1);
+
+
+#define FINALIZE \
+	evldw		r14,8(r1);	/* restore SPE registers	*/ \
+	evldw		r15,16(r1);					   \
+	evldw		r16,24(r1);					   \
+	evldw		r17,32(r1);					   \
+	evldw		r18,40(r1);					   \
+	evldw		r19,48(r1);					   \
+	evldw		r20,56(r1);					   \
+	evldw		r21,64(r1);					   \
+	evldw		r22,72(r1);					   \
+	evldw		r23,80(r1);					   \
+	lwz		r24,88(r1);	/* restore normal registers	*/ \
+	lwz		r25,92(r1);					   \
+	xor		r0,r0,r0;					   \
+	stw		r0,8(r1);	/* Delete sensitive data	*/ \
+	stw		r0,16(r1);	/* that we might have pushed	*/ \
+	stw		r0,24(r1);	/* from other context that runs	*/ \
+	stw		r0,32(r1);	/* the same code. Assume that	*/ \
+	stw		r0,40(r1);	/* the lower part of the GPRs	*/ \
+	stw		r0,48(r1);	/* was already overwritten on	*/ \
+	stw		r0,56(r1);	/* the way down to here		*/ \
+	stw		r0,64(r1);					   \
+	stw		r0,72(r1);					   \
+	stw		r0,80(r1);					   \
+	addi		r1,r1,128;	/* cleanup stack frame		*/
+
+#ifdef __BIG_ENDIAN__
+#define LOAD_DATA(reg, off) \
+	lwz		reg,off(rWP);	/* load data			*/
+#define NEXT_BLOCK \
+	addi		rWP,rWP,64;	/* increment per block		*/
+#else
+#define LOAD_DATA(reg, off) \
+	lwbrx		reg,0,rWP; 	/* load data			*/ \
+	addi		rWP,rWP,4;	/* increment per word		*/
+#define NEXT_BLOCK			/* nothing to do		*/
+#endif
+
+#define R_LOAD_W(a, b, c, d, e, f, g, h, w, off) \
+	LOAD_DATA(w, off)		/* 1: W				*/ \
+	rotrwi		rT0,e,6;	/* 1: S1 = e rotr 6		*/ \
+	rotrwi		rT1,e,11;	/* 1: S1' = e rotr 11		*/ \
+	rotrwi		rT2,e,25;	/* 1: S1" = e rotr 25		*/ \
+	xor		rT0,rT0,rT1;	/* 1: S1 = S1 xor S1'		*/ \
+	and		rT3,e,f;	/* 1: ch = e and f		*/ \
+	xor		rT0,rT0,rT2;	/* 1: S1 = S1 xor S1"		*/ \
+	andc		rT1,g,e;	/* 1: ch' = ~e and g		*/ \
+	lwz		rT2,off(rKP);	/* 1: K				*/ \
+	xor		rT3,rT3,rT1;	/* 1: ch = ch xor ch'		*/ \
+	add		h,h,rT0;	/* 1: temp1 = h + S1		*/ \
+	add		rT3,rT3,w;	/* 1: temp1' = ch + w		*/ \
+	rotrwi		rT0,a,2;	/* 1: S0 = a rotr 2		*/ \
+	add		h,h,rT3;	/* 1: temp1 = temp1 + temp1'	*/ \
+	rotrwi		rT1,a,13;	/* 1: S0' = a rotr 13		*/ \
+	add		h,h,rT2;	/* 1: temp1 = temp1 + K		*/ \
+	rotrwi		rT3,a,22;	/* 1: S0" = a rotr 22		*/ \
+	xor		rT0,rT0,rT1;	/* 1: S0 = S0 xor S0'		*/ \
+	add		d,d,h;		/* 1: d = d + temp1		*/ \
+	xor		rT3,rT0,rT3;	/* 1: S0 = S0 xor S0"		*/ \
+	evmergelo	w,w,w;		/*    shift W			*/ \
+	or		rT2,a,b;	/* 1: maj = a or b		*/ \
+	and		rT1,a,b;	/* 1: maj' = a and b		*/ \
+	and		rT2,rT2,c;	/* 1: maj = maj and c		*/ \
+	LOAD_DATA(w, off+4)		/* 2: W				*/ \
+	or		rT2,rT1,rT2;	/* 1: maj = maj or maj'		*/ \
+	rotrwi		rT0,d,6;	/* 2: S1 = e rotr 6		*/ \
+	add		rT3,rT3,rT2;	/* 1: temp2 = S0 + maj		*/ \
+	rotrwi		rT1,d,11;	/* 2: S1' = e rotr 11		*/ \
+	add		h,h,rT3;	/* 1: h = temp1 + temp2		*/ \
+	rotrwi		rT2,d,25;	/* 2: S1" = e rotr 25		*/ \
+	xor		rT0,rT0,rT1;	/* 2: S1 = S1 xor S1'		*/ \
+	and		rT3,d,e;	/* 2: ch = e and f		*/ \
+	xor		rT0,rT0,rT2;	/* 2: S1 = S1 xor S1"		*/ \
+	andc		rT1,f,d;	/* 2: ch' = ~e and g		*/ \
+	lwz		rT2,off+4(rKP);	/* 2: K				*/ \
+	xor		rT3,rT3,rT1;	/* 2: ch = ch xor ch'		*/ \
+	add		g,g,rT0;	/* 2: temp1 = h + S1		*/ \
+	add		rT3,rT3,w;	/* 2: temp1' = ch + w		*/ \
+	rotrwi		rT0,h,2;	/* 2: S0 = a rotr 2		*/ \
+	add		g,g,rT3;	/* 2: temp1 = temp1 + temp1'	*/ \
+	rotrwi		rT1,h,13;	/* 2: S0' = a rotr 13		*/ \
+	add		g,g,rT2;	/* 2: temp1 = temp1 + K		*/ \
+	rotrwi		rT3,h,22;	/* 2: S0" = a rotr 22		*/ \
+	xor		rT0,rT0,rT1;	/* 2: S0 = S0 xor S0'		*/ \
+	or		rT2,h,a;	/* 2: maj = a or b		*/ \
+	xor		rT3,rT0,rT3;	/* 2: S0 = S0 xor S0"		*/ \
+	and		rT1,h,a;	/* 2: maj' = a and b		*/ \
+	and		rT2,rT2,b;	/* 2: maj = maj and c		*/ \
+	add		c,c,g;		/* 2: d = d + temp1		*/ \
+	or		rT2,rT1,rT2;	/* 2: maj = maj or maj'		*/ \
+	add		rT3,rT3,rT2;	/* 2: temp2 = S0 + maj		*/ \
+	add		g,g,rT3		/* 2: h = temp1 + temp2		*/
+
+#define R_CALC_W(a, b, c, d, e, f, g, h, w0, w1, w4, w5, w7, k, off) \
+	rotrwi		rT2,e,6;	/* 1: S1 = e rotr 6		*/ \
+	evmergelohi	rT0,w0,w1;	/*    w[-15]			*/ \
+	rotrwi		rT3,e,11;	/* 1: S1' = e rotr 11		*/ \
+	evsrwiu		rT1,rT0,3;	/*    s0 = w[-15] >> 3		*/ \
+	xor		rT2,rT2,rT3;	/* 1: S1 = S1 xor S1'		*/ \
+	evrlwi		rT0,rT0,25;	/*    s0' = w[-15] rotr	7	*/ \
+	rotrwi		rT3,e,25;	/* 1: S1' = e rotr 25		*/ \
+	evxor		rT1,rT1,rT0;	/*    s0 = s0 xor s0'		*/ \
+	xor		rT2,rT2,rT3;	/* 1: S1 = S1 xor S1'		*/ \
+	evrlwi		rT0,rT0,21;	/*    s0' = w[-15] rotr 18	*/ \
+	add		h,h,rT2;	/* 1: temp1 = h + S1		*/ \
+	evxor		rT0,rT0,rT1;	/*    s0 = s0 xor s0'		*/ \
+	and		rT2,e,f;	/* 1: ch = e and f		*/ \
+	evaddw		w0,w0,rT0;	/*    w = w[-16] + s0		*/ \
+	andc		rT3,g,e;	/* 1: ch' = ~e and g		*/ \
+	evsrwiu		rT0,w7,10;	/*    s1 = w[-2] >> 10		*/ \
+	xor		rT2,rT2,rT3;	/* 1: ch = ch xor ch'		*/ \
+	evrlwi		rT1,w7,15;	/*    s1' = w[-2] rotr 17	*/ \
+	add		h,h,rT2;	/* 1: temp1 = temp1 + ch	*/ \
+	evxor		rT0,rT0,rT1;	/*    s1 = s1 xor s1'		*/ \
+	rotrwi		rT2,a,2;	/* 1: S0 = a rotr 2		*/ \
+	evrlwi		rT1,w7,13;	/*    s1' = w[-2] rotr 19	*/ \
+	rotrwi		rT3,a,13;	/* 1: S0' = a rotr 13		*/ \
+	evxor		rT0,rT0,rT1;	/*    s1 = s1 xor s1'		*/ \
+	xor		rT2,rT2,rT3;	/* 1: S0 = S0 xor S0'		*/ \
+	evldw		rT1,off(rKP);	/*    k				*/ \
+	rotrwi		rT3,a,22;	/* 1: S0' = a rotr 22		*/ \
+	evaddw		w0,w0,rT0;	/*    w = w + s1		*/ \
+	xor		rT2,rT2,rT3;	/* 1: S0 = S0 xor S0'		*/ \
+	evmergelohi	rT0,w4,w5;	/*    w[-7]			*/ \
+	and		rT3,a,b;	/* 1: maj = a and b		*/ \
+	evaddw		w0,w0,rT0;	/*    w = w + w[-7]		*/ \
+	CMP_K##k##_LOOP							   \
+	add		rT2,rT2,rT3;	/* 1: temp2 = S0 + maj		*/ \
+	evaddw		rT1,rT1,w0;	/*    wk = w + k		*/ \
+	xor		rT3,a,b;	/* 1: maj = a xor b		*/ \
+	evmergehi	rT0,rT1,rT1;	/*    wk1/wk2			*/ \
+	and		rT3,rT3,c;	/* 1: maj = maj and c		*/ \
+	add		h,h,rT0;	/* 1: temp1 = temp1 + wk	*/ \
+	add		rT2,rT2,rT3;	/* 1: temp2 = temp2 + maj	*/ \
+	add		g,g,rT1;	/* 2: temp1 = temp1 + wk	*/ \
+	add		d,d,h;		/* 1: d = d + temp1		*/ \
+	rotrwi		rT0,d,6;	/* 2: S1 = e rotr 6		*/ \
+	add		h,h,rT2;	/* 1: h = temp1 + temp2		*/ \
+	rotrwi		rT1,d,11;	/* 2: S1' = e rotr 11		*/ \
+	rotrwi		rT2,d,25;	/* 2: S" = e rotr 25		*/ \
+	xor		rT0,rT0,rT1;	/* 2: S1 = S1 xor S1'		*/ \
+	and		rT3,d,e;	/* 2: ch = e and f		*/ \
+	xor		rT0,rT0,rT2;	/* 2: S1 = S1 xor S1"		*/ \
+	andc		rT1,f,d;	/* 2: ch' = ~e and g		*/ \
+	add		g,g,rT0;	/* 2: temp1 = h + S1		*/ \
+	xor		rT3,rT3,rT1;	/* 2: ch = ch xor ch'		*/ \
+	rotrwi		rT0,h,2;	/* 2: S0 = a rotr 2		*/ \
+	add		g,g,rT3;	/* 2: temp1 = temp1 + ch	*/ \
+	rotrwi		rT1,h,13;	/* 2: S0' = a rotr 13		*/ \
+	rotrwi		rT3,h,22;	/* 2: S0" = a rotr 22		*/ \
+	xor		rT0,rT0,rT1;	/* 2: S0 = S0 xor S0'		*/ \
+	or		rT2,h,a;	/* 2: maj = a or b		*/ \
+	and		rT1,h,a;	/* 2: maj' = a and b		*/ \
+	and		rT2,rT2,b;	/* 2: maj = maj and c		*/ \
+	xor		rT3,rT0,rT3;	/* 2: S0 = S0 xor S0"		*/ \
+	or		rT2,rT1,rT2;	/* 2: maj = maj or maj'		*/ \
+	add		c,c,g;		/* 2: d = d + temp1		*/ \
+	add		rT3,rT3,rT2;	/* 2: temp2 = S0 + maj		*/ \
+	add		g,g,rT3		/* 2: h = temp1 + temp2		*/
+
+_GLOBAL(ppc_spe_sha256_transform)
+	INITIALIZE
+
+	mtctr		r5
+	lwz		rH0,0(rHP)
+	lwz		rH1,4(rHP)
+	lwz		rH2,8(rHP)
+	lwz		rH3,12(rHP)
+	lwz		rH4,16(rHP)
+	lwz		rH5,20(rHP)
+	lwz		rH6,24(rHP)
+	lwz		rH7,28(rHP)
+
+ppc_spe_sha256_main:
+	lis		rKP,PPC_SPE_SHA256_K@ha
+	addi		rKP,rKP,PPC_SPE_SHA256_K@l
+
+	R_LOAD_W(rH0, rH1, rH2, rH3, rH4, rH5, rH6, rH7, rW0, 0)
+	R_LOAD_W(rH6, rH7, rH0, rH1, rH2, rH3, rH4, rH5, rW1, 8)
+	R_LOAD_W(rH4, rH5, rH6, rH7, rH0, rH1, rH2, rH3, rW2, 16)
+	R_LOAD_W(rH2, rH3, rH4, rH5, rH6, rH7, rH0, rH1, rW3, 24)
+	R_LOAD_W(rH0, rH1, rH2, rH3, rH4, rH5, rH6, rH7, rW4, 32)
+	R_LOAD_W(rH6, rH7, rH0, rH1, rH2, rH3, rH4, rH5, rW5, 40)
+	R_LOAD_W(rH4, rH5, rH6, rH7, rH0, rH1, rH2, rH3, rW6, 48)
+	R_LOAD_W(rH2, rH3, rH4, rH5, rH6, rH7, rH0, rH1, rW7, 56)
+ppc_spe_sha256_16_rounds:
+	addi		rKP,rKP,64
+	R_CALC_W(rH0, rH1, rH2, rH3, rH4, rH5, rH6, rH7,
+		 rW0, rW1, rW4, rW5, rW7, N, 0)
+	R_CALC_W(rH6, rH7, rH0, rH1, rH2, rH3, rH4, rH5,
+		 rW1, rW2, rW5, rW6, rW0, N, 8)
+	R_CALC_W(rH4, rH5, rH6, rH7, rH0, rH1, rH2, rH3,
+		 rW2, rW3, rW6, rW7, rW1, N, 16)
+	R_CALC_W(rH2, rH3, rH4, rH5, rH6, rH7, rH0, rH1,
+		 rW3, rW4, rW7, rW0, rW2, N, 24)
+	R_CALC_W(rH0, rH1, rH2, rH3, rH4, rH5, rH6, rH7,
+		 rW4, rW5, rW0, rW1, rW3, N, 32)
+	R_CALC_W(rH6, rH7, rH0, rH1, rH2, rH3, rH4, rH5,
+		 rW5, rW6, rW1, rW2, rW4, N, 40)
+	R_CALC_W(rH4, rH5, rH6, rH7, rH0, rH1, rH2, rH3,
+		 rW6, rW7, rW2, rW3, rW5, N, 48)
+	R_CALC_W(rH2, rH3, rH4, rH5, rH6, rH7, rH0, rH1,
+		 rW7, rW0, rW3, rW4, rW6, C, 56)
+	bt		gt,ppc_spe_sha256_16_rounds
+
+	lwz		rW0,0(rHP)
+	NEXT_BLOCK
+	lwz		rW1,4(rHP)
+	lwz		rW2,8(rHP)
+	lwz		rW3,12(rHP)
+	lwz		rW4,16(rHP)
+	lwz		rW5,20(rHP)
+	lwz		rW6,24(rHP)
+	lwz		rW7,28(rHP)
+
+	add		rH0,rH0,rW0
+	stw		rH0,0(rHP)
+	add		rH1,rH1,rW1
+	stw		rH1,4(rHP)
+	add		rH2,rH2,rW2
+	stw		rH2,8(rHP)
+	add		rH3,rH3,rW3
+	stw		rH3,12(rHP)
+	add		rH4,rH4,rW4
+	stw		rH4,16(rHP)
+	add		rH5,rH5,rW5
+	stw		rH5,20(rHP)
+	add		rH6,rH6,rW6
+	stw		rH6,24(rHP)
+	add		rH7,rH7,rW7
+	stw		rH7,28(rHP)
+
+	bdnz		ppc_spe_sha256_main
+
+	FINALIZE
+	blr
+
+.data
+.align 5
+PPC_SPE_SHA256_K:
+	.long 0x428a2f98,0x71374491,0xb5c0fbcf,0xe9b5dba5
+	.long 0x3956c25b,0x59f111f1,0x923f82a4,0xab1c5ed5
+	.long 0xd807aa98,0x12835b01,0x243185be,0x550c7dc3
+	.long 0x72be5d74,0x80deb1fe,0x9bdc06a7,0xc19bf174
+	.long 0xe49b69c1,0xefbe4786,0x0fc19dc6,0x240ca1cc
+	.long 0x2de92c6f,0x4a7484aa,0x5cb0a9dc,0x76f988da
+	.long 0x983e5152,0xa831c66d,0xb00327c8,0xbf597fc7
+	.long 0xc6e00bf3,0xd5a79147,0x06ca6351,0x14292967
+	.long 0x27b70a85,0x2e1b2138,0x4d2c6dfc,0x53380d13
+	.long 0x650a7354,0x766a0abb,0x81c2c92e,0x92722c85
+	.long 0xa2bfe8a1,0xa81a664b,0xc24b8b70,0xc76c51a3
+	.long 0xd192e819,0xd6990624,0xf40e3585,0x106aa070
+	.long 0x19a4c116,0x1e376c08,0x2748774c,0x34b0bcb5
+	.long 0x391c0cb3,0x4ed8aa4a,0x5b9cca4f,0x682e6ff3
+	.long 0x748f82ee,0x78a5636f,0x84c87814,0x8cc70208
+	.long 0x90befffa,0xa4506ceb,0xbef9a3f7,0xc67178f2
diff --git a/lib/crypto/powerpc/sha256.c b/lib/crypto/powerpc/sha256.c
new file mode 100644
index 000000000000..6b0f079587eb
--- /dev/null
+++ b/lib/crypto/powerpc/sha256.c
@@ -0,0 +1,70 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * SHA-256 Secure Hash Algorithm, SPE optimized
+ *
+ * Based on generic implementation. The assembler module takes care
+ * about the SPE registers so it can run from interrupt context.
+ *
+ * Copyright (c) 2015 Markus Stockhausen <stockhausen@collogia.de>
+ */
+
+#include <asm/switch_to.h>
+#include <crypto/internal/sha2.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/preempt.h>
+
+/*
+ * MAX_BYTES defines the number of bytes that are allowed to be processed
+ * between preempt_disable() and preempt_enable(). SHA256 takes ~2,000
+ * operations per 64 bytes. e500 cores can issue two arithmetic instructions
+ * per clock cycle using one 32/64 bit unit (SU1) and one 32 bit unit (SU2).
+ * Thus 1KB of input data will need an estimated maximum of 18,000 cycles.
+ * Headroom for cache misses included. Even with the low end model clocked
+ * at 667 MHz this equals to a critical time window of less than 27us.
+ *
+ */
+#define MAX_BYTES 1024
+
+extern void ppc_spe_sha256_transform(u32 *state, const u8 *src, u32 blocks);
+
+static void spe_begin(void)
+{
+	/* We just start SPE operations and will save SPE registers later. */
+	preempt_disable();
+	enable_kernel_spe();
+}
+
+static void spe_end(void)
+{
+	disable_kernel_spe();
+	/* reenable preemption */
+	preempt_enable();
+}
+
+void sha256_blocks_arch(u32 state[SHA256_STATE_WORDS],
+			const u8 *data, size_t nblocks)
+{
+	do {
+		/* cut input data into smaller blocks */
+		u32 unit = min_t(size_t, nblocks,
+				 MAX_BYTES / SHA256_BLOCK_SIZE);
+
+		spe_begin();
+		ppc_spe_sha256_transform(state, data, unit);
+		spe_end();
+
+		data += unit * SHA256_BLOCK_SIZE;
+		nblocks -= unit;
+	} while (nblocks);
+}
+EXPORT_SYMBOL_GPL(sha256_blocks_arch);
+
+bool sha256_is_arch_optimized(void)
+{
+	return true;
+}
+EXPORT_SYMBOL_GPL(sha256_is_arch_optimized);
+
+MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("SHA-256 Secure Hash Algorithm, SPE optimized");