Resguardo inicial

linux-7.2.3/lib/raid/xor/x86/xor-avx.c

@@ -0,0 +1,156 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Optimized XOR parity functions for AVX
+ *
+ * Copyright (C) 2012 Intel Corporation
+ * Author: Jim Kukunas <james.t.kukunas@linux.intel.com>
+ *
+ * Based on Ingo Molnar and Zach Brown's respective MMX and SSE routines
+ */
+#include <linux/compiler.h>
+#include <asm/fpu/api.h>
+#include "xor_impl.h"
+#include "xor_arch.h"
+
+#define BLOCK4(i) \
+		BLOCK(32 * i, 0) \
+		BLOCK(32 * (i + 1), 1) \
+		BLOCK(32 * (i + 2), 2) \
+		BLOCK(32 * (i + 3), 3)
+
+#define BLOCK16() \
+		BLOCK4(0) \
+		BLOCK4(4) \
+		BLOCK4(8) \
+		BLOCK4(12)
+
+static void xor_avx_2(unsigned long bytes, unsigned long * __restrict p0,
+		      const unsigned long * __restrict p1)
+{
+	unsigned long lines = bytes >> 9;
+
+	while (lines--) {
+#undef BLOCK
+#define BLOCK(i, reg) \
+do { \
+	asm volatile("vmovdqa %0, %%ymm" #reg : : "m" (p1[i / sizeof(*p1)])); \
+	asm volatile("vxorps %0, %%ymm" #reg ", %%ymm"  #reg : : \
+		"m" (p0[i / sizeof(*p0)])); \
+	asm volatile("vmovdqa %%ymm" #reg ", %0" : \
+		"=m" (p0[i / sizeof(*p0)])); \
+} while (0);
+
+		BLOCK16()
+
+		p0 = (unsigned long *)((uintptr_t)p0 + 512);
+		p1 = (unsigned long *)((uintptr_t)p1 + 512);
+	}
+}
+
+static void xor_avx_3(unsigned long bytes, unsigned long * __restrict p0,
+		      const unsigned long * __restrict p1,
+		      const unsigned long * __restrict p2)
+{
+	unsigned long lines = bytes >> 9;
+
+	while (lines--) {
+#undef BLOCK
+#define BLOCK(i, reg) \
+do { \
+	asm volatile("vmovdqa %0, %%ymm" #reg : : "m" (p2[i / sizeof(*p2)])); \
+	asm volatile("vxorps %0, %%ymm" #reg ", %%ymm" #reg : : \
+		"m" (p1[i / sizeof(*p1)])); \
+	asm volatile("vxorps %0, %%ymm" #reg ", %%ymm" #reg : : \
+		"m" (p0[i / sizeof(*p0)])); \
+	asm volatile("vmovdqa %%ymm" #reg ", %0" : \
+		"=m" (p0[i / sizeof(*p0)])); \
+} while (0);
+
+		BLOCK16()
+
+		p0 = (unsigned long *)((uintptr_t)p0 + 512);
+		p1 = (unsigned long *)((uintptr_t)p1 + 512);
+		p2 = (unsigned long *)((uintptr_t)p2 + 512);
+	}
+}
+
+static void xor_avx_4(unsigned long bytes, unsigned long * __restrict p0,
+		      const unsigned long * __restrict p1,
+		      const unsigned long * __restrict p2,
+		      const unsigned long * __restrict p3)
+{
+	unsigned long lines = bytes >> 9;
+
+	while (lines--) {
+#undef BLOCK
+#define BLOCK(i, reg) \
+do { \
+	asm volatile("vmovdqa %0, %%ymm" #reg : : "m" (p3[i / sizeof(*p3)])); \
+	asm volatile("vxorps %0, %%ymm" #reg ", %%ymm" #reg : : \
+		"m" (p2[i / sizeof(*p2)])); \
+	asm volatile("vxorps %0, %%ymm" #reg ", %%ymm" #reg : : \
+		"m" (p1[i / sizeof(*p1)])); \
+	asm volatile("vxorps %0, %%ymm" #reg ", %%ymm" #reg : : \
+		"m" (p0[i / sizeof(*p0)])); \
+	asm volatile("vmovdqa %%ymm" #reg ", %0" : \
+		"=m" (p0[i / sizeof(*p0)])); \
+} while (0);
+
+		BLOCK16();
+
+		p0 = (unsigned long *)((uintptr_t)p0 + 512);
+		p1 = (unsigned long *)((uintptr_t)p1 + 512);
+		p2 = (unsigned long *)((uintptr_t)p2 + 512);
+		p3 = (unsigned long *)((uintptr_t)p3 + 512);
+	}
+}
+
+static void xor_avx_5(unsigned long bytes, unsigned long * __restrict p0,
+	     const unsigned long * __restrict p1,
+	     const unsigned long * __restrict p2,
+	     const unsigned long * __restrict p3,
+	     const unsigned long * __restrict p4)
+{
+	unsigned long lines = bytes >> 9;
+
+	while (lines--) {
+#undef BLOCK
+#define BLOCK(i, reg) \
+do { \
+	asm volatile("vmovdqa %0, %%ymm" #reg : : "m" (p4[i / sizeof(*p4)])); \
+	asm volatile("vxorps %0, %%ymm" #reg ", %%ymm" #reg : : \
+		"m" (p3[i / sizeof(*p3)])); \
+	asm volatile("vxorps %0, %%ymm" #reg ", %%ymm" #reg : : \
+		"m" (p2[i / sizeof(*p2)])); \
+	asm volatile("vxorps %0, %%ymm" #reg ", %%ymm" #reg : : \
+		"m" (p1[i / sizeof(*p1)])); \
+	asm volatile("vxorps %0, %%ymm" #reg ", %%ymm" #reg : : \
+		"m" (p0[i / sizeof(*p0)])); \
+	asm volatile("vmovdqa %%ymm" #reg ", %0" : \
+		"=m" (p0[i / sizeof(*p0)])); \
+} while (0);
+
+		BLOCK16()
+
+		p0 = (unsigned long *)((uintptr_t)p0 + 512);
+		p1 = (unsigned long *)((uintptr_t)p1 + 512);
+		p2 = (unsigned long *)((uintptr_t)p2 + 512);
+		p3 = (unsigned long *)((uintptr_t)p3 + 512);
+		p4 = (unsigned long *)((uintptr_t)p4 + 512);
+	}
+}
+
+DO_XOR_BLOCKS(avx_inner, xor_avx_2, xor_avx_3, xor_avx_4, xor_avx_5);
+
+static void xor_gen_avx(void *dest, void **srcs, unsigned int src_cnt,
+			unsigned int bytes)
+{
+	kernel_fpu_begin();
+	xor_gen_avx_inner(dest, srcs, src_cnt, bytes);
+	kernel_fpu_end();
+}
+
+struct xor_block_template xor_block_avx = {
+	.name		= "avx",
+	.xor_gen	= xor_gen_avx,
+};

linux-7.2.3/lib/raid/xor/x86/xor-mmx.c

@@ -0,0 +1,515 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Optimized XOR parity functions for MMX.
+ *
+ * Copyright (C) 1998 Ingo Molnar.
+ */
+#include <asm/fpu/api.h>
+#include "xor_impl.h"
+#include "xor_arch.h"
+
+#define LD(x, y)	"       movq   8*("#x")(%1), %%mm"#y"   ;\n"
+#define ST(x, y)	"       movq %%mm"#y",   8*("#x")(%1)   ;\n"
+#define XO1(x, y)	"       pxor   8*("#x")(%2), %%mm"#y"   ;\n"
+#define XO2(x, y)	"       pxor   8*("#x")(%3), %%mm"#y"   ;\n"
+#define XO3(x, y)	"       pxor   8*("#x")(%4), %%mm"#y"   ;\n"
+#define XO4(x, y)	"       pxor   8*("#x")(%5), %%mm"#y"   ;\n"
+
+static void
+xor_pII_mmx_2(unsigned long bytes, unsigned long * __restrict p1,
+	      const unsigned long * __restrict p2)
+{
+	unsigned long lines = bytes >> 7;
+
+	asm volatile(
+#undef BLOCK
+#define BLOCK(i)				\
+	LD(i, 0)				\
+		LD(i + 1, 1)			\
+			LD(i + 2, 2)		\
+				LD(i + 3, 3)	\
+	XO1(i, 0)				\
+	ST(i, 0)				\
+		XO1(i+1, 1)			\
+		ST(i+1, 1)			\
+			XO1(i + 2, 2)		\
+			ST(i + 2, 2)		\
+				XO1(i + 3, 3)	\
+				ST(i + 3, 3)
+
+	" .align 32			;\n"
+	" 1:                            ;\n"
+
+	BLOCK(0)
+	BLOCK(4)
+	BLOCK(8)
+	BLOCK(12)
+
+	"       addl $128, %1         ;\n"
+	"       addl $128, %2         ;\n"
+	"       decl %0               ;\n"
+	"       jnz 1b                ;\n"
+	: "+r" (lines),
+	  "+r" (p1), "+r" (p2)
+	:
+	: "memory");
+}
+
+static void
+xor_pII_mmx_3(unsigned long bytes, unsigned long * __restrict p1,
+	      const unsigned long * __restrict p2,
+	      const unsigned long * __restrict p3)
+{
+	unsigned long lines = bytes >> 7;
+
+	asm volatile(
+#undef BLOCK
+#define BLOCK(i)				\
+	LD(i, 0)				\
+		LD(i + 1, 1)			\
+			LD(i + 2, 2)		\
+				LD(i + 3, 3)	\
+	XO1(i, 0)				\
+		XO1(i + 1, 1)			\
+			XO1(i + 2, 2)		\
+				XO1(i + 3, 3)	\
+	XO2(i, 0)				\
+	ST(i, 0)				\
+		XO2(i + 1, 1)			\
+		ST(i + 1, 1)			\
+			XO2(i + 2, 2)		\
+			ST(i + 2, 2)		\
+				XO2(i + 3, 3)	\
+				ST(i + 3, 3)
+
+	" .align 32			;\n"
+	" 1:                            ;\n"
+
+	BLOCK(0)
+	BLOCK(4)
+	BLOCK(8)
+	BLOCK(12)
+
+	"       addl $128, %1         ;\n"
+	"       addl $128, %2         ;\n"
+	"       addl $128, %3         ;\n"
+	"       decl %0               ;\n"
+	"       jnz 1b                ;\n"
+	: "+r" (lines),
+	  "+r" (p1), "+r" (p2), "+r" (p3)
+	:
+	: "memory");
+}
+
+static void
+xor_pII_mmx_4(unsigned long bytes, unsigned long * __restrict p1,
+	      const unsigned long * __restrict p2,
+	      const unsigned long * __restrict p3,
+	      const unsigned long * __restrict p4)
+{
+	unsigned long lines = bytes >> 7;
+
+	asm volatile(
+#undef BLOCK
+#define BLOCK(i)				\
+	LD(i, 0)				\
+		LD(i + 1, 1)			\
+			LD(i + 2, 2)		\
+				LD(i + 3, 3)	\
+	XO1(i, 0)				\
+		XO1(i + 1, 1)			\
+			XO1(i + 2, 2)		\
+				XO1(i + 3, 3)	\
+	XO2(i, 0)				\
+		XO2(i + 1, 1)			\
+			XO2(i + 2, 2)		\
+				XO2(i + 3, 3)	\
+	XO3(i, 0)				\
+	ST(i, 0)				\
+		XO3(i + 1, 1)			\
+		ST(i + 1, 1)			\
+			XO3(i + 2, 2)		\
+			ST(i + 2, 2)		\
+				XO3(i + 3, 3)	\
+				ST(i + 3, 3)
+
+	" .align 32			;\n"
+	" 1:                            ;\n"
+
+	BLOCK(0)
+	BLOCK(4)
+	BLOCK(8)
+	BLOCK(12)
+
+	"       addl $128, %1         ;\n"
+	"       addl $128, %2         ;\n"
+	"       addl $128, %3         ;\n"
+	"       addl $128, %4         ;\n"
+	"       decl %0               ;\n"
+	"       jnz 1b                ;\n"
+	: "+r" (lines),
+	  "+r" (p1), "+r" (p2), "+r" (p3), "+r" (p4)
+	:
+	: "memory");
+}
+
+
+static void
+xor_pII_mmx_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)
+{
+	unsigned long lines = bytes >> 7;
+
+	/* Make sure GCC forgets anything it knows about p4 or p5,
+	   such that it won't pass to the asm volatile below a
+	   register that is shared with any other variable.  That's
+	   because we modify p4 and p5 there, but we can't mark them
+	   as read/write, otherwise we'd overflow the 10-asm-operands
+	   limit of GCC < 3.1.  */
+	asm("" : "+r" (p4), "+r" (p5));
+
+	asm volatile(
+#undef BLOCK
+#define BLOCK(i)				\
+	LD(i, 0)				\
+		LD(i + 1, 1)			\
+			LD(i + 2, 2)		\
+				LD(i + 3, 3)	\
+	XO1(i, 0)				\
+		XO1(i + 1, 1)			\
+			XO1(i + 2, 2)		\
+				XO1(i + 3, 3)	\
+	XO2(i, 0)				\
+		XO2(i + 1, 1)			\
+			XO2(i + 2, 2)		\
+				XO2(i + 3, 3)	\
+	XO3(i, 0)				\
+		XO3(i + 1, 1)			\
+			XO3(i + 2, 2)		\
+				XO3(i + 3, 3)	\
+	XO4(i, 0)				\
+	ST(i, 0)				\
+		XO4(i + 1, 1)			\
+		ST(i + 1, 1)			\
+			XO4(i + 2, 2)		\
+			ST(i + 2, 2)		\
+				XO4(i + 3, 3)	\
+				ST(i + 3, 3)
+
+	" .align 32			;\n"
+	" 1:                            ;\n"
+
+	BLOCK(0)
+	BLOCK(4)
+	BLOCK(8)
+	BLOCK(12)
+
+	"       addl $128, %1         ;\n"
+	"       addl $128, %2         ;\n"
+	"       addl $128, %3         ;\n"
+	"       addl $128, %4         ;\n"
+	"       addl $128, %5         ;\n"
+	"       decl %0               ;\n"
+	"       jnz 1b                ;\n"
+	: "+r" (lines),
+	  "+r" (p1), "+r" (p2), "+r" (p3)
+	: "r" (p4), "r" (p5)
+	: "memory");
+
+	/* p4 and p5 were modified, and now the variables are dead.
+	   Clobber them just to be sure nobody does something stupid
+	   like assuming they have some legal value.  */
+	asm("" : "=r" (p4), "=r" (p5));
+}
+
+#undef LD
+#undef XO1
+#undef XO2
+#undef XO3
+#undef XO4
+#undef ST
+#undef BLOCK
+
+static void
+xor_p5_mmx_2(unsigned long bytes, unsigned long * __restrict p1,
+	     const unsigned long * __restrict p2)
+{
+	unsigned long lines = bytes >> 6;
+
+	asm volatile(
+	" .align 32	             ;\n"
+	" 1:                         ;\n"
+	"       movq   (%1), %%mm0   ;\n"
+	"       movq  8(%1), %%mm1   ;\n"
+	"       pxor   (%2), %%mm0   ;\n"
+	"       movq 16(%1), %%mm2   ;\n"
+	"       movq %%mm0,   (%1)   ;\n"
+	"       pxor  8(%2), %%mm1   ;\n"
+	"       movq 24(%1), %%mm3   ;\n"
+	"       movq %%mm1,  8(%1)   ;\n"
+	"       pxor 16(%2), %%mm2   ;\n"
+	"       movq 32(%1), %%mm4   ;\n"
+	"       movq %%mm2, 16(%1)   ;\n"
+	"       pxor 24(%2), %%mm3   ;\n"
+	"       movq 40(%1), %%mm5   ;\n"
+	"       movq %%mm3, 24(%1)   ;\n"
+	"       pxor 32(%2), %%mm4   ;\n"
+	"       movq 48(%1), %%mm6   ;\n"
+	"       movq %%mm4, 32(%1)   ;\n"
+	"       pxor 40(%2), %%mm5   ;\n"
+	"       movq 56(%1), %%mm7   ;\n"
+	"       movq %%mm5, 40(%1)   ;\n"
+	"       pxor 48(%2), %%mm6   ;\n"
+	"       pxor 56(%2), %%mm7   ;\n"
+	"       movq %%mm6, 48(%1)   ;\n"
+	"       movq %%mm7, 56(%1)   ;\n"
+
+	"       addl $64, %1         ;\n"
+	"       addl $64, %2         ;\n"
+	"       decl %0              ;\n"
+	"       jnz 1b               ;\n"
+	: "+r" (lines),
+	  "+r" (p1), "+r" (p2)
+	:
+	: "memory");
+}
+
+static void
+xor_p5_mmx_3(unsigned long bytes, unsigned long * __restrict p1,
+	     const unsigned long * __restrict p2,
+	     const unsigned long * __restrict p3)
+{
+	unsigned long lines = bytes >> 6;
+
+	asm volatile(
+	" .align 32,0x90             ;\n"
+	" 1:                         ;\n"
+	"       movq   (%1), %%mm0   ;\n"
+	"       movq  8(%1), %%mm1   ;\n"
+	"       pxor   (%2), %%mm0   ;\n"
+	"       movq 16(%1), %%mm2   ;\n"
+	"       pxor  8(%2), %%mm1   ;\n"
+	"       pxor   (%3), %%mm0   ;\n"
+	"       pxor 16(%2), %%mm2   ;\n"
+	"       movq %%mm0,   (%1)   ;\n"
+	"       pxor  8(%3), %%mm1   ;\n"
+	"       pxor 16(%3), %%mm2   ;\n"
+	"       movq 24(%1), %%mm3   ;\n"
+	"       movq %%mm1,  8(%1)   ;\n"
+	"       movq 32(%1), %%mm4   ;\n"
+	"       movq 40(%1), %%mm5   ;\n"
+	"       pxor 24(%2), %%mm3   ;\n"
+	"       movq %%mm2, 16(%1)   ;\n"
+	"       pxor 32(%2), %%mm4   ;\n"
+	"       pxor 24(%3), %%mm3   ;\n"
+	"       pxor 40(%2), %%mm5   ;\n"
+	"       movq %%mm3, 24(%1)   ;\n"
+	"       pxor 32(%3), %%mm4   ;\n"
+	"       pxor 40(%3), %%mm5   ;\n"
+	"       movq 48(%1), %%mm6   ;\n"
+	"       movq %%mm4, 32(%1)   ;\n"
+	"       movq 56(%1), %%mm7   ;\n"
+	"       pxor 48(%2), %%mm6   ;\n"
+	"       movq %%mm5, 40(%1)   ;\n"
+	"       pxor 56(%2), %%mm7   ;\n"
+	"       pxor 48(%3), %%mm6   ;\n"
+	"       pxor 56(%3), %%mm7   ;\n"
+	"       movq %%mm6, 48(%1)   ;\n"
+	"       movq %%mm7, 56(%1)   ;\n"
+
+	"       addl $64, %1         ;\n"
+	"       addl $64, %2         ;\n"
+	"       addl $64, %3         ;\n"
+	"       decl %0              ;\n"
+	"       jnz 1b               ;\n"
+	: "+r" (lines),
+	  "+r" (p1), "+r" (p2), "+r" (p3)
+	:
+	: "memory" );
+}
+
+static void
+xor_p5_mmx_4(unsigned long bytes, unsigned long * __restrict p1,
+	     const unsigned long * __restrict p2,
+	     const unsigned long * __restrict p3,
+	     const unsigned long * __restrict p4)
+{
+	unsigned long lines = bytes >> 6;
+
+	asm volatile(
+	" .align 32,0x90             ;\n"
+	" 1:                         ;\n"
+	"       movq   (%1), %%mm0   ;\n"
+	"       movq  8(%1), %%mm1   ;\n"
+	"       pxor   (%2), %%mm0   ;\n"
+	"       movq 16(%1), %%mm2   ;\n"
+	"       pxor  8(%2), %%mm1   ;\n"
+	"       pxor   (%3), %%mm0   ;\n"
+	"       pxor 16(%2), %%mm2   ;\n"
+	"       pxor  8(%3), %%mm1   ;\n"
+	"       pxor   (%4), %%mm0   ;\n"
+	"       movq 24(%1), %%mm3   ;\n"
+	"       pxor 16(%3), %%mm2   ;\n"
+	"       pxor  8(%4), %%mm1   ;\n"
+	"       movq %%mm0,   (%1)   ;\n"
+	"       movq 32(%1), %%mm4   ;\n"
+	"       pxor 24(%2), %%mm3   ;\n"
+	"       pxor 16(%4), %%mm2   ;\n"
+	"       movq %%mm1,  8(%1)   ;\n"
+	"       movq 40(%1), %%mm5   ;\n"
+	"       pxor 32(%2), %%mm4   ;\n"
+	"       pxor 24(%3), %%mm3   ;\n"
+	"       movq %%mm2, 16(%1)   ;\n"
+	"       pxor 40(%2), %%mm5   ;\n"
+	"       pxor 32(%3), %%mm4   ;\n"
+	"       pxor 24(%4), %%mm3   ;\n"
+	"       movq %%mm3, 24(%1)   ;\n"
+	"       movq 56(%1), %%mm7   ;\n"
+	"       movq 48(%1), %%mm6   ;\n"
+	"       pxor 40(%3), %%mm5   ;\n"
+	"       pxor 32(%4), %%mm4   ;\n"
+	"       pxor 48(%2), %%mm6   ;\n"
+	"       movq %%mm4, 32(%1)   ;\n"
+	"       pxor 56(%2), %%mm7   ;\n"
+	"       pxor 40(%4), %%mm5   ;\n"
+	"       pxor 48(%3), %%mm6   ;\n"
+	"       pxor 56(%3), %%mm7   ;\n"
+	"       movq %%mm5, 40(%1)   ;\n"
+	"       pxor 48(%4), %%mm6   ;\n"
+	"       pxor 56(%4), %%mm7   ;\n"
+	"       movq %%mm6, 48(%1)   ;\n"
+	"       movq %%mm7, 56(%1)   ;\n"
+
+	"       addl $64, %1         ;\n"
+	"       addl $64, %2         ;\n"
+	"       addl $64, %3         ;\n"
+	"       addl $64, %4         ;\n"
+	"       decl %0              ;\n"
+	"       jnz 1b               ;\n"
+	: "+r" (lines),
+	  "+r" (p1), "+r" (p2), "+r" (p3), "+r" (p4)
+	:
+	: "memory");
+}
+
+static void
+xor_p5_mmx_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)
+{
+	unsigned long lines = bytes >> 6;
+
+	/* Make sure GCC forgets anything it knows about p4 or p5,
+	   such that it won't pass to the asm volatile below a
+	   register that is shared with any other variable.  That's
+	   because we modify p4 and p5 there, but we can't mark them
+	   as read/write, otherwise we'd overflow the 10-asm-operands
+	   limit of GCC < 3.1.  */
+	asm("" : "+r" (p4), "+r" (p5));
+
+	asm volatile(
+	" .align 32,0x90             ;\n"
+	" 1:                         ;\n"
+	"       movq   (%1), %%mm0   ;\n"
+	"       movq  8(%1), %%mm1   ;\n"
+	"       pxor   (%2), %%mm0   ;\n"
+	"       pxor  8(%2), %%mm1   ;\n"
+	"       movq 16(%1), %%mm2   ;\n"
+	"       pxor   (%3), %%mm0   ;\n"
+	"       pxor  8(%3), %%mm1   ;\n"
+	"       pxor 16(%2), %%mm2   ;\n"
+	"       pxor   (%4), %%mm0   ;\n"
+	"       pxor  8(%4), %%mm1   ;\n"
+	"       pxor 16(%3), %%mm2   ;\n"
+	"       movq 24(%1), %%mm3   ;\n"
+	"       pxor   (%5), %%mm0   ;\n"
+	"       pxor  8(%5), %%mm1   ;\n"
+	"       movq %%mm0,   (%1)   ;\n"
+	"       pxor 16(%4), %%mm2   ;\n"
+	"       pxor 24(%2), %%mm3   ;\n"
+	"       movq %%mm1,  8(%1)   ;\n"
+	"       pxor 16(%5), %%mm2   ;\n"
+	"       pxor 24(%3), %%mm3   ;\n"
+	"       movq 32(%1), %%mm4   ;\n"
+	"       movq %%mm2, 16(%1)   ;\n"
+	"       pxor 24(%4), %%mm3   ;\n"
+	"       pxor 32(%2), %%mm4   ;\n"
+	"       movq 40(%1), %%mm5   ;\n"
+	"       pxor 24(%5), %%mm3   ;\n"
+	"       pxor 32(%3), %%mm4   ;\n"
+	"       pxor 40(%2), %%mm5   ;\n"
+	"       movq %%mm3, 24(%1)   ;\n"
+	"       pxor 32(%4), %%mm4   ;\n"
+	"       pxor 40(%3), %%mm5   ;\n"
+	"       movq 48(%1), %%mm6   ;\n"
+	"       movq 56(%1), %%mm7   ;\n"
+	"       pxor 32(%5), %%mm4   ;\n"
+	"       pxor 40(%4), %%mm5   ;\n"
+	"       pxor 48(%2), %%mm6   ;\n"
+	"       pxor 56(%2), %%mm7   ;\n"
+	"       movq %%mm4, 32(%1)   ;\n"
+	"       pxor 48(%3), %%mm6   ;\n"
+	"       pxor 56(%3), %%mm7   ;\n"
+	"       pxor 40(%5), %%mm5   ;\n"
+	"       pxor 48(%4), %%mm6   ;\n"
+	"       pxor 56(%4), %%mm7   ;\n"
+	"       movq %%mm5, 40(%1)   ;\n"
+	"       pxor 48(%5), %%mm6   ;\n"
+	"       pxor 56(%5), %%mm7   ;\n"
+	"       movq %%mm6, 48(%1)   ;\n"
+	"       movq %%mm7, 56(%1)   ;\n"
+
+	"       addl $64, %1         ;\n"
+	"       addl $64, %2         ;\n"
+	"       addl $64, %3         ;\n"
+	"       addl $64, %4         ;\n"
+	"       addl $64, %5         ;\n"
+	"       decl %0              ;\n"
+	"       jnz 1b               ;\n"
+	: "+r" (lines),
+	  "+r" (p1), "+r" (p2), "+r" (p3)
+	: "r" (p4), "r" (p5)
+	: "memory");
+
+	/* p4 and p5 were modified, and now the variables are dead.
+	   Clobber them just to be sure nobody does something stupid
+	   like assuming they have some legal value.  */
+	asm("" : "=r" (p4), "=r" (p5));
+}
+
+DO_XOR_BLOCKS(pII_mmx_inner, xor_pII_mmx_2, xor_pII_mmx_3, xor_pII_mmx_4,
+		xor_pII_mmx_5);
+
+static void xor_gen_pII_mmx(void *dest, void **srcs, unsigned int src_cnt,
+		unsigned int bytes)
+{
+	kernel_fpu_begin();
+	xor_gen_pII_mmx_inner(dest, srcs, src_cnt, bytes);
+	kernel_fpu_end();
+}
+
+struct xor_block_template xor_block_pII_mmx = {
+	.name		= "pII_mmx",
+	.xor_gen	= xor_gen_pII_mmx,
+};
+
+DO_XOR_BLOCKS(p5_mmx_inner, xor_p5_mmx_2, xor_p5_mmx_3, xor_p5_mmx_4,
+		xor_p5_mmx_5);
+
+static void xor_gen_p5_mmx(void *dest, void **srcs, unsigned int src_cnt,
+		unsigned int bytes)
+{
+	kernel_fpu_begin();
+	xor_gen_p5_mmx_inner(dest, srcs, src_cnt, bytes);
+	kernel_fpu_end();
+}
+
+struct xor_block_template xor_block_p5_mmx = {
+	.name		= "p5_mmx",
+	.xor_gen	= xor_gen_p5_mmx,
+};

linux-7.2.3/lib/raid/xor/x86/xor-sse.c

@@ -0,0 +1,459 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Optimized XOR parity functions for SSE.
+ *
+ * Cache avoiding checksumming functions utilizing KNI instructions
+ * Copyright (C) 1999 Zach Brown (with obvious credit due Ingo)
+ *
+ * Based on
+ * High-speed RAID5 checksumming functions utilizing SSE instructions.
+ * Copyright (C) 1998 Ingo Molnar.
+ *
+ * x86-64 changes / gcc fixes from Andi Kleen.
+ * Copyright 2002 Andi Kleen, SuSE Labs.
+ */
+#include <asm/fpu/api.h>
+#include "xor_impl.h"
+#include "xor_arch.h"
+
+#ifdef CONFIG_X86_32
+/* reduce register pressure */
+# define XOR_CONSTANT_CONSTRAINT "i"
+#else
+# define XOR_CONSTANT_CONSTRAINT "re"
+#endif
+
+#define OFFS(x)		"16*("#x")"
+#define PF_OFFS(x)	"256+16*("#x")"
+#define PF0(x)		"	prefetchnta "PF_OFFS(x)"(%[p1])		;\n"
+#define LD(x, y)	"	movaps "OFFS(x)"(%[p1]), %%xmm"#y"	;\n"
+#define ST(x, y)	"	movaps %%xmm"#y", "OFFS(x)"(%[p1])	;\n"
+#define PF1(x)		"	prefetchnta "PF_OFFS(x)"(%[p2])		;\n"
+#define PF2(x)		"	prefetchnta "PF_OFFS(x)"(%[p3])		;\n"
+#define PF3(x)		"	prefetchnta "PF_OFFS(x)"(%[p4])		;\n"
+#define PF4(x)		"	prefetchnta "PF_OFFS(x)"(%[p5])		;\n"
+#define XO1(x, y)	"	xorps "OFFS(x)"(%[p2]), %%xmm"#y"	;\n"
+#define XO2(x, y)	"	xorps "OFFS(x)"(%[p3]), %%xmm"#y"	;\n"
+#define XO3(x, y)	"	xorps "OFFS(x)"(%[p4]), %%xmm"#y"	;\n"
+#define XO4(x, y)	"	xorps "OFFS(x)"(%[p5]), %%xmm"#y"	;\n"
+#define NOP(x)
+
+#define BLK64(pf, op, i)				\
+		pf(i)					\
+		op(i, 0)				\
+			op(i + 1, 1)			\
+				op(i + 2, 2)		\
+					op(i + 3, 3)
+
+static void
+xor_sse_2(unsigned long bytes, unsigned long * __restrict p1,
+	  const unsigned long * __restrict p2)
+{
+	unsigned long lines = bytes >> 8;
+
+	asm volatile(
+#undef BLOCK
+#define BLOCK(i)					\
+		LD(i, 0)				\
+			LD(i + 1, 1)			\
+		PF1(i)					\
+				PF1(i + 2)		\
+				LD(i + 2, 2)		\
+					LD(i + 3, 3)	\
+		PF0(i + 4)				\
+				PF0(i + 6)		\
+		XO1(i, 0)				\
+			XO1(i + 1, 1)			\
+				XO1(i + 2, 2)		\
+					XO1(i + 3, 3)	\
+		ST(i, 0)				\
+			ST(i + 1, 1)			\
+				ST(i + 2, 2)		\
+					ST(i + 3, 3)	\
+
+
+		PF0(0)
+				PF0(2)
+
+	" .align 32			;\n"
+	" 1:                            ;\n"
+
+		BLOCK(0)
+		BLOCK(4)
+		BLOCK(8)
+		BLOCK(12)
+
+	"       add %[inc], %[p1]       ;\n"
+	"       add %[inc], %[p2]       ;\n"
+	"       dec %[cnt]              ;\n"
+	"       jnz 1b                  ;\n"
+	: [cnt] "+r" (lines),
+	  [p1] "+r" (p1), [p2] "+r" (p2)
+	: [inc] XOR_CONSTANT_CONSTRAINT (256UL)
+	: "memory");
+}
+
+static void
+xor_sse_2_pf64(unsigned long bytes, unsigned long * __restrict p1,
+	       const unsigned long * __restrict p2)
+{
+	unsigned long lines = bytes >> 8;
+
+	asm volatile(
+#undef BLOCK
+#define BLOCK(i)			\
+		BLK64(PF0, LD, i)	\
+		BLK64(PF1, XO1, i)	\
+		BLK64(NOP, ST, i)	\
+
+	" .align 32			;\n"
+	" 1:                            ;\n"
+
+		BLOCK(0)
+		BLOCK(4)
+		BLOCK(8)
+		BLOCK(12)
+
+	"       add %[inc], %[p1]       ;\n"
+	"       add %[inc], %[p2]       ;\n"
+	"       dec %[cnt]              ;\n"
+	"       jnz 1b                  ;\n"
+	: [cnt] "+r" (lines),
+	  [p1] "+r" (p1), [p2] "+r" (p2)
+	: [inc] XOR_CONSTANT_CONSTRAINT (256UL)
+	: "memory");
+}
+
+static void
+xor_sse_3(unsigned long bytes, unsigned long * __restrict p1,
+	  const unsigned long * __restrict p2,
+	  const unsigned long * __restrict p3)
+{
+	unsigned long lines = bytes >> 8;
+
+	asm volatile(
+#undef BLOCK
+#define BLOCK(i) \
+		PF1(i)					\
+				PF1(i + 2)		\
+		LD(i, 0)				\
+			LD(i + 1, 1)			\
+				LD(i + 2, 2)		\
+					LD(i + 3, 3)	\
+		PF2(i)					\
+				PF2(i + 2)		\
+		PF0(i + 4)				\
+				PF0(i + 6)		\
+		XO1(i, 0)				\
+			XO1(i + 1, 1)			\
+				XO1(i + 2, 2)		\
+					XO1(i + 3, 3)	\
+		XO2(i, 0)				\
+			XO2(i + 1, 1)			\
+				XO2(i + 2, 2)		\
+					XO2(i + 3, 3)	\
+		ST(i, 0)				\
+			ST(i + 1, 1)			\
+				ST(i + 2, 2)		\
+					ST(i + 3, 3)	\
+
+
+		PF0(0)
+				PF0(2)
+
+	" .align 32			;\n"
+	" 1:                            ;\n"
+
+		BLOCK(0)
+		BLOCK(4)
+		BLOCK(8)
+		BLOCK(12)
+
+	"       add %[inc], %[p1]       ;\n"
+	"       add %[inc], %[p2]       ;\n"
+	"       add %[inc], %[p3]       ;\n"
+	"       dec %[cnt]              ;\n"
+	"       jnz 1b                  ;\n"
+	: [cnt] "+r" (lines),
+	  [p1] "+r" (p1), [p2] "+r" (p2), [p3] "+r" (p3)
+	: [inc] XOR_CONSTANT_CONSTRAINT (256UL)
+	: "memory");
+}
+
+static void
+xor_sse_3_pf64(unsigned long bytes, unsigned long * __restrict p1,
+	       const unsigned long * __restrict p2,
+	       const unsigned long * __restrict p3)
+{
+	unsigned long lines = bytes >> 8;
+
+	asm volatile(
+#undef BLOCK
+#define BLOCK(i)			\
+		BLK64(PF0, LD, i)	\
+		BLK64(PF1, XO1, i)	\
+		BLK64(PF2, XO2, i)	\
+		BLK64(NOP, ST, i)	\
+
+	" .align 32			;\n"
+	" 1:                            ;\n"
+
+		BLOCK(0)
+		BLOCK(4)
+		BLOCK(8)
+		BLOCK(12)
+
+	"       add %[inc], %[p1]       ;\n"
+	"       add %[inc], %[p2]       ;\n"
+	"       add %[inc], %[p3]       ;\n"
+	"       dec %[cnt]              ;\n"
+	"       jnz 1b                  ;\n"
+	: [cnt] "+r" (lines),
+	  [p1] "+r" (p1), [p2] "+r" (p2), [p3] "+r" (p3)
+	: [inc] XOR_CONSTANT_CONSTRAINT (256UL)
+	: "memory");
+}
+
+static void
+xor_sse_4(unsigned long bytes, unsigned long * __restrict p1,
+	  const unsigned long * __restrict p2,
+	  const unsigned long * __restrict p3,
+	  const unsigned long * __restrict p4)
+{
+	unsigned long lines = bytes >> 8;
+
+	asm volatile(
+#undef BLOCK
+#define BLOCK(i) \
+		PF1(i)					\
+				PF1(i + 2)		\
+		LD(i, 0)				\
+			LD(i + 1, 1)			\
+				LD(i + 2, 2)		\
+					LD(i + 3, 3)	\
+		PF2(i)					\
+				PF2(i + 2)		\
+		XO1(i, 0)				\
+			XO1(i + 1, 1)			\
+				XO1(i + 2, 2)		\
+					XO1(i + 3, 3)	\
+		PF3(i)					\
+				PF3(i + 2)		\
+		PF0(i + 4)				\
+				PF0(i + 6)		\
+		XO2(i, 0)				\
+			XO2(i + 1, 1)			\
+				XO2(i + 2, 2)		\
+					XO2(i + 3, 3)	\
+		XO3(i, 0)				\
+			XO3(i + 1, 1)			\
+				XO3(i + 2, 2)		\
+					XO3(i + 3, 3)	\
+		ST(i, 0)				\
+			ST(i + 1, 1)			\
+				ST(i + 2, 2)		\
+					ST(i + 3, 3)	\
+
+
+		PF0(0)
+				PF0(2)
+
+	" .align 32			;\n"
+	" 1:                            ;\n"
+
+		BLOCK(0)
+		BLOCK(4)
+		BLOCK(8)
+		BLOCK(12)
+
+	"       add %[inc], %[p1]       ;\n"
+	"       add %[inc], %[p2]       ;\n"
+	"       add %[inc], %[p3]       ;\n"
+	"       add %[inc], %[p4]       ;\n"
+	"       dec %[cnt]              ;\n"
+	"       jnz 1b                  ;\n"
+	: [cnt] "+r" (lines), [p1] "+r" (p1),
+	  [p2] "+r" (p2), [p3] "+r" (p3), [p4] "+r" (p4)
+	: [inc] XOR_CONSTANT_CONSTRAINT (256UL)
+	: "memory");
+}
+
+static void
+xor_sse_4_pf64(unsigned long bytes, unsigned long * __restrict p1,
+	       const unsigned long * __restrict p2,
+	       const unsigned long * __restrict p3,
+	       const unsigned long * __restrict p4)
+{
+	unsigned long lines = bytes >> 8;
+
+	asm volatile(
+#undef BLOCK
+#define BLOCK(i)			\
+		BLK64(PF0, LD, i)	\
+		BLK64(PF1, XO1, i)	\
+		BLK64(PF2, XO2, i)	\
+		BLK64(PF3, XO3, i)	\
+		BLK64(NOP, ST, i)	\
+
+	" .align 32			;\n"
+	" 1:                            ;\n"
+
+		BLOCK(0)
+		BLOCK(4)
+		BLOCK(8)
+		BLOCK(12)
+
+	"       add %[inc], %[p1]       ;\n"
+	"       add %[inc], %[p2]       ;\n"
+	"       add %[inc], %[p3]       ;\n"
+	"       add %[inc], %[p4]       ;\n"
+	"       dec %[cnt]              ;\n"
+	"       jnz 1b                  ;\n"
+	: [cnt] "+r" (lines), [p1] "+r" (p1),
+	  [p2] "+r" (p2), [p3] "+r" (p3), [p4] "+r" (p4)
+	: [inc] XOR_CONSTANT_CONSTRAINT (256UL)
+	: "memory");
+}
+
+static void
+xor_sse_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)
+{
+	unsigned long lines = bytes >> 8;
+
+	asm volatile(
+#undef BLOCK
+#define BLOCK(i) \
+		PF1(i)					\
+				PF1(i + 2)		\
+		LD(i, 0)				\
+			LD(i + 1, 1)			\
+				LD(i + 2, 2)		\
+					LD(i + 3, 3)	\
+		PF2(i)					\
+				PF2(i + 2)		\
+		XO1(i, 0)				\
+			XO1(i + 1, 1)			\
+				XO1(i + 2, 2)		\
+					XO1(i + 3, 3)	\
+		PF3(i)					\
+				PF3(i + 2)		\
+		XO2(i, 0)				\
+			XO2(i + 1, 1)			\
+				XO2(i + 2, 2)		\
+					XO2(i + 3, 3)	\
+		PF4(i)					\
+				PF4(i + 2)		\
+		PF0(i + 4)				\
+				PF0(i + 6)		\
+		XO3(i, 0)				\
+			XO3(i + 1, 1)			\
+				XO3(i + 2, 2)		\
+					XO3(i + 3, 3)	\
+		XO4(i, 0)				\
+			XO4(i + 1, 1)			\
+				XO4(i + 2, 2)		\
+					XO4(i + 3, 3)	\
+		ST(i, 0)				\
+			ST(i + 1, 1)			\
+				ST(i + 2, 2)		\
+					ST(i + 3, 3)	\
+
+
+		PF0(0)
+				PF0(2)
+
+	" .align 32			;\n"
+	" 1:                            ;\n"
+
+		BLOCK(0)
+		BLOCK(4)
+		BLOCK(8)
+		BLOCK(12)
+
+	"       add %[inc], %[p1]       ;\n"
+	"       add %[inc], %[p2]       ;\n"
+	"       add %[inc], %[p3]       ;\n"
+	"       add %[inc], %[p4]       ;\n"
+	"       add %[inc], %[p5]       ;\n"
+	"       dec %[cnt]              ;\n"
+	"       jnz 1b                  ;\n"
+	: [cnt] "+r" (lines), [p1] "+r" (p1), [p2] "+r" (p2),
+	  [p3] "+r" (p3), [p4] "+r" (p4), [p5] "+r" (p5)
+	: [inc] XOR_CONSTANT_CONSTRAINT (256UL)
+	: "memory");
+}
+
+static void
+xor_sse_5_pf64(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)
+{
+	unsigned long lines = bytes >> 8;
+
+	asm volatile(
+#undef BLOCK
+#define BLOCK(i)			\
+		BLK64(PF0, LD, i)	\
+		BLK64(PF1, XO1, i)	\
+		BLK64(PF2, XO2, i)	\
+		BLK64(PF3, XO3, i)	\
+		BLK64(PF4, XO4, i)	\
+		BLK64(NOP, ST, i)	\
+
+	" .align 32			;\n"
+	" 1:                            ;\n"
+
+		BLOCK(0)
+		BLOCK(4)
+		BLOCK(8)
+		BLOCK(12)
+
+	"       add %[inc], %[p1]       ;\n"
+	"       add %[inc], %[p2]       ;\n"
+	"       add %[inc], %[p3]       ;\n"
+	"       add %[inc], %[p4]       ;\n"
+	"       add %[inc], %[p5]       ;\n"
+	"       dec %[cnt]              ;\n"
+	"       jnz 1b                  ;\n"
+	: [cnt] "+r" (lines), [p1] "+r" (p1), [p2] "+r" (p2),
+	  [p3] "+r" (p3), [p4] "+r" (p4), [p5] "+r" (p5)
+	: [inc] XOR_CONSTANT_CONSTRAINT (256UL)
+	: "memory");
+}
+
+DO_XOR_BLOCKS(sse_inner, xor_sse_2, xor_sse_3, xor_sse_4, xor_sse_5);
+
+static void xor_gen_sse(void *dest, void **srcs, unsigned int src_cnt,
+			unsigned int bytes)
+{
+	kernel_fpu_begin();
+	xor_gen_sse_inner(dest, srcs, src_cnt, bytes);
+	kernel_fpu_end();
+}
+
+struct xor_block_template xor_block_sse = {
+	.name		= "sse",
+	.xor_gen	= xor_gen_sse,
+};
+
+DO_XOR_BLOCKS(sse_pf64_inner, xor_sse_2_pf64, xor_sse_3_pf64, xor_sse_4_pf64,
+		xor_sse_5_pf64);
+
+static void xor_gen_sse_pf64(void *dest, void **srcs, unsigned int src_cnt,
+			unsigned int bytes)
+{
+	kernel_fpu_begin();
+	xor_gen_sse_pf64_inner(dest, srcs, src_cnt, bytes);
+	kernel_fpu_end();
+}
+
+struct xor_block_template xor_block_sse_pf64 = {
+	.name		= "prefetch64-sse",
+	.xor_gen	= xor_gen_sse_pf64,
+};

linux-7.2.3/lib/raid/xor/x86/xor_arch.h

@@ -0,0 +1,36 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+#include <asm/cpufeature.h>
+
+extern struct xor_block_template xor_block_pII_mmx;
+extern struct xor_block_template xor_block_p5_mmx;
+extern struct xor_block_template xor_block_sse;
+extern struct xor_block_template xor_block_sse_pf64;
+extern struct xor_block_template xor_block_avx;
+
+/*
+ * When SSE is available, use it as it can write around L2.  We may also be able
+ * to load into the L1 only depending on how the cpu deals with a load to a line
+ * that is being prefetched.
+ *
+ * When AVX2 is available, force using it as it is better by all measures.
+ *
+ * 32-bit without MMX can fall back to the generic routines.
+ */
+static __always_inline void __init arch_xor_init(void)
+{
+	if (boot_cpu_has(X86_FEATURE_AVX) &&
+	    boot_cpu_has(X86_FEATURE_OSXSAVE)) {
+		xor_force(&xor_block_avx);
+	} else if (IS_ENABLED(CONFIG_X86_64) || boot_cpu_has(X86_FEATURE_XMM)) {
+		xor_register(&xor_block_sse);
+		xor_register(&xor_block_sse_pf64);
+	} else if (boot_cpu_has(X86_FEATURE_MMX)) {
+		xor_register(&xor_block_pII_mmx);
+		xor_register(&xor_block_p5_mmx);
+	} else {
+		xor_register(&xor_block_8regs);
+		xor_register(&xor_block_8regs_p);
+		xor_register(&xor_block_32regs);
+		xor_register(&xor_block_32regs_p);
+	}
+}