powerpc: move the XOR code to lib/raid/

Move the optimized XOR into lib/raid and include it it in xor.ko instead
of always building it into the main kernel image.

Link: https://lkml.kernel.org/r/20260327061704.3707577-16-hch@lst.de
Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Eric Biggers <ebiggers@kernel.org>
Tested-by: Eric Biggers <ebiggers@kernel.org>
Cc: Albert Ou <aou@eecs.berkeley.edu>
Cc: Alexander Gordeev <agordeev@linux.ibm.com>
Cc: Alexandre Ghiti <alex@ghiti.fr>
Cc: Andreas Larsson <andreas@gaisler.com>
Cc: Anton Ivanov <anton.ivanov@cambridgegreys.com>
Cc: Ard Biesheuvel <ardb@kernel.org>
Cc: Arnd Bergmann <arnd@arndb.de>
Cc: "Borislav Petkov (AMD)" <bp@alien8.de>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Chris Mason <clm@fb.com>
Cc: Christian Borntraeger <borntraeger@linux.ibm.com>
Cc: Dan Williams <dan.j.williams@intel.com>
Cc: David S. Miller <davem@davemloft.net>
Cc: David Sterba <dsterba@suse.com>
Cc: Heiko Carstens <hca@linux.ibm.com>
Cc: Herbert Xu <herbert@gondor.apana.org.au>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Cc: Huacai Chen <chenhuacai@kernel.org>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Jason A. Donenfeld <jason@zx2c4.com>
Cc: Johannes Berg <johannes@sipsolutions.net>
Cc: Li Nan <linan122@huawei.com>
Cc: Madhavan Srinivasan <maddy@linux.ibm.com>
Cc: Magnus Lindholm <linmag7@gmail.com>
Cc: Matt Turner <mattst88@gmail.com>
Cc: Michael Ellerman <mpe@ellerman.id.au>
Cc: Nicholas Piggin <npiggin@gmail.com>
Cc: Palmer Dabbelt <palmer@dabbelt.com>
Cc: Richard Henderson <richard.henderson@linaro.org>
Cc: Richard Weinberger <richard@nod.at>
Cc: Russell King <linux@armlinux.org.uk>
Cc: Song Liu <song@kernel.org>
Cc: Sven Schnelle <svens@linux.ibm.com>
Cc: Ted Ts'o <tytso@mit.edu>
Cc: Vasily Gorbik <gor@linux.ibm.com>
Cc: WANG Xuerui <kernel@xen0n.name>
Cc: Will Deacon <will@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>

4 files changed, 250 insertions, 0 deletions

diff --git a/lib/raid/xor/Makefile b/lib/raid/xor/Makefile
index e8868f5fc396..006b44ce46bf 100644
--- a/lib/raid/xor/Makefile
+++ b/lib/raid/xor/Makefile
@@ -16,6 +16,7 @@ endif
 xor-$(CONFIG_ARM64)		+= arm64/xor-neon.o arm64/xor-neon-glue.o
 xor-$(CONFIG_CPU_HAS_LSX)	+= loongarch/xor_simd.o
 xor-$(CONFIG_CPU_HAS_LSX)	+= loongarch/xor_simd_glue.o
+xor-$(CONFIG_ALTIVEC)		+= powerpc/xor_vmx.o powerpc/xor_vmx_glue.o
 
 
 CFLAGS_arm/xor-neon.o		+= $(CC_FLAGS_FPU)
@@ -23,3 +24,7 @@ CFLAGS_REMOVE_arm/xor-neon.o	+= $(CC_FLAGS_NO_FPU)
 
 CFLAGS_arm64/xor-neon.o		+= $(CC_FLAGS_FPU)
 CFLAGS_REMOVE_arm64/xor-neon.o	+= $(CC_FLAGS_NO_FPU)
+
+CFLAGS_powerpc/xor_vmx.o	+= -mhard-float -maltivec \
+				   $(call cc-option,-mabi=altivec) \
+				   -isystem $(shell $(CC) -print-file-name=include)
diff --git a/lib/raid/xor/powerpc/xor_vmx.c b/lib/raid/xor/powerpc/xor_vmx.c
new file mode 100644
index 000000000000..aab49d056d18
--- /dev/null
+++ b/lib/raid/xor/powerpc/xor_vmx.c
@@ -0,0 +1,156 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ *
+ * Copyright (C) IBM Corporation, 2012
+ *
+ * Author: Anton Blanchard <anton@au.ibm.com>
+ */
+
+/*
+ * Sparse (as at v0.5.0) gets very, very confused by this file.
+ * Make it a bit simpler for it.
+ */
+#if !defined(__CHECKER__)
+#include <altivec.h>
+#else
+#define vec_xor(a, b) a ^ b
+#define vector __attribute__((vector_size(16)))
+#endif
+
+#include "xor_vmx.h"
+
+typedef vector signed char unative_t;
+
+#define DEFINE(V)				\
+	unative_t *V = (unative_t *)V##_in;	\
+	unative_t V##_0, V##_1, V##_2, V##_3
+
+#define LOAD(V)			\
+	do {			\
+		V##_0 = V[0];	\
+		V##_1 = V[1];	\
+		V##_2 = V[2];	\
+		V##_3 = V[3];	\
+	} while (0)
+
+#define STORE(V)		\
+	do {			\
+		V[0] = V##_0;	\
+		V[1] = V##_1;	\
+		V[2] = V##_2;	\
+		V[3] = V##_3;	\
+	} while (0)
+
+#define XOR(V1, V2)					\
+	do {						\
+		V1##_0 = vec_xor(V1##_0, V2##_0);	\
+		V1##_1 = vec_xor(V1##_1, V2##_1);	\
+		V1##_2 = vec_xor(V1##_2, V2##_2);	\
+		V1##_3 = vec_xor(V1##_3, V2##_3);	\
+	} while (0)
+
+void __xor_altivec_2(unsigned long bytes,
+		     unsigned long * __restrict v1_in,
+		     const unsigned long * __restrict v2_in)
+{
+	DEFINE(v1);
+	DEFINE(v2);
+	unsigned long lines = bytes / (sizeof(unative_t)) / 4;
+
+	do {
+		LOAD(v1);
+		LOAD(v2);
+		XOR(v1, v2);
+		STORE(v1);
+
+		v1 += 4;
+		v2 += 4;
+	} while (--lines > 0);
+}
+
+void __xor_altivec_3(unsigned long bytes,
+		     unsigned long * __restrict v1_in,
+		     const unsigned long * __restrict v2_in,
+		     const unsigned long * __restrict v3_in)
+{
+	DEFINE(v1);
+	DEFINE(v2);
+	DEFINE(v3);
+	unsigned long lines = bytes / (sizeof(unative_t)) / 4;
+
+	do {
+		LOAD(v1);
+		LOAD(v2);
+		LOAD(v3);
+		XOR(v1, v2);
+		XOR(v1, v3);
+		STORE(v1);
+
+		v1 += 4;
+		v2 += 4;
+		v3 += 4;
+	} while (--lines > 0);
+}
+
+void __xor_altivec_4(unsigned long bytes,
+		     unsigned long * __restrict v1_in,
+		     const unsigned long * __restrict v2_in,
+		     const unsigned long * __restrict v3_in,
+		     const unsigned long * __restrict v4_in)
+{
+	DEFINE(v1);
+	DEFINE(v2);
+	DEFINE(v3);
+	DEFINE(v4);
+	unsigned long lines = bytes / (sizeof(unative_t)) / 4;
+
+	do {
+		LOAD(v1);
+		LOAD(v2);
+		LOAD(v3);
+		LOAD(v4);
+		XOR(v1, v2);
+		XOR(v3, v4);
+		XOR(v1, v3);
+		STORE(v1);
+
+		v1 += 4;
+		v2 += 4;
+		v3 += 4;
+		v4 += 4;
+	} while (--lines > 0);
+}
+
+void __xor_altivec_5(unsigned long bytes,
+		     unsigned long * __restrict v1_in,
+		     const unsigned long * __restrict v2_in,
+		     const unsigned long * __restrict v3_in,
+		     const unsigned long * __restrict v4_in,
+		     const unsigned long * __restrict v5_in)
+{
+	DEFINE(v1);
+	DEFINE(v2);
+	DEFINE(v3);
+	DEFINE(v4);
+	DEFINE(v5);
+	unsigned long lines = bytes / (sizeof(unative_t)) / 4;
+
+	do {
+		LOAD(v1);
+		LOAD(v2);
+		LOAD(v3);
+		LOAD(v4);
+		LOAD(v5);
+		XOR(v1, v2);
+		XOR(v3, v4);
+		XOR(v1, v5);
+		XOR(v1, v3);
+		STORE(v1);
+
+		v1 += 4;
+		v2 += 4;
+		v3 += 4;
+		v4 += 4;
+		v5 += 4;
+	} while (--lines > 0);
+}
diff --git a/lib/raid/xor/powerpc/xor_vmx.h b/lib/raid/xor/powerpc/xor_vmx.h
new file mode 100644
index 000000000000..573c41d90dac
--- /dev/null
+++ b/lib/raid/xor/powerpc/xor_vmx.h
@@ -0,0 +1,22 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Simple interface to link xor_vmx.c and xor_vmx_glue.c
+ *
+ * Separating these file ensures that no altivec instructions are run
+ * outside of the enable/disable altivec block.
+ */
+
+void __xor_altivec_2(unsigned long bytes, unsigned long * __restrict p1,
+		     const unsigned long * __restrict p2);
+void __xor_altivec_3(unsigned long bytes, unsigned long * __restrict p1,
+		     const unsigned long * __restrict p2,
+		     const unsigned long * __restrict p3);
+void __xor_altivec_4(unsigned long bytes, unsigned long * __restrict p1,
+		     const unsigned long * __restrict p2,
+		     const unsigned long * __restrict p3,
+		     const unsigned long * __restrict p4);
+void __xor_altivec_5(unsigned long bytes, unsigned long * __restrict p1,
+		     const unsigned long * __restrict p2,
+		     const unsigned long * __restrict p3,
+		     const unsigned long * __restrict p4,
+		     const unsigned long * __restrict p5);
diff --git a/lib/raid/xor/powerpc/xor_vmx_glue.c b/lib/raid/xor/powerpc/xor_vmx_glue.c
new file mode 100644
index 000000000000..c41e38340700
--- /dev/null
+++ b/lib/raid/xor/powerpc/xor_vmx_glue.c
@@ -0,0 +1,67 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Altivec XOR operations
+ *
+ * Copyright 2017 IBM Corp.
+ */
+
+#include <linux/preempt.h>
+#include <linux/sched.h>
+#include <linux/raid/xor_impl.h>
+#include <asm/switch_to.h>
+#include <asm/xor.h>
+#include "xor_vmx.h"
+
+static void xor_altivec_2(unsigned long bytes, unsigned long * __restrict p1,
+		const unsigned long * __restrict p2)
+{
+	preempt_disable();
+	enable_kernel_altivec();
+	__xor_altivec_2(bytes, p1, p2);
+	disable_kernel_altivec();
+	preempt_enable();
+}
+
+static void xor_altivec_3(unsigned long bytes, unsigned long * __restrict p1,
+		const unsigned long * __restrict p2,
+		const unsigned long * __restrict p3)
+{
+	preempt_disable();
+	enable_kernel_altivec();
+	__xor_altivec_3(bytes, p1, p2, p3);
+	disable_kernel_altivec();
+	preempt_enable();
+}
+
+static void xor_altivec_4(unsigned long bytes, unsigned long * __restrict p1,
+		const unsigned long * __restrict p2,
+		const unsigned long * __restrict p3,
+		const unsigned long * __restrict p4)
+{
+	preempt_disable();
+	enable_kernel_altivec();
+	__xor_altivec_4(bytes, p1, p2, p3, p4);
+	disable_kernel_altivec();
+	preempt_enable();
+}
+
+static void xor_altivec_5(unsigned long bytes, unsigned long * __restrict p1,
+		const unsigned long * __restrict p2,
+		const unsigned long * __restrict p3,
+		const unsigned long * __restrict p4,
+		const unsigned long * __restrict p5)
+{
+	preempt_disable();
+	enable_kernel_altivec();
+	__xor_altivec_5(bytes, p1, p2, p3, p4, p5);
+	disable_kernel_altivec();
+	preempt_enable();
+}
+
+struct xor_block_template xor_block_altivec = {
+	.name = "altivec",
+	.do_2 = xor_altivec_2,
+	.do_3 = xor_altivec_3,
+	.do_4 = xor_altivec_4,
+	.do_5 = xor_altivec_5,
+};