riscv: lib: vectorize copy_to_user/copy_from_user

This patch utilizes Vector to perform copy_to_user/copy_from_user. If
Vector is available and the size of copy is large enough for Vector to
perform better than scalar, then direct the kernel to do Vector copies
for userspace. Though the best programming practice for users is to
reduce the copy, this provides a faster variant when copies are
inevitable.

The optimal size for using Vector, copy_to_user_thres, is only a
heuristic for now. We can add DT parsing if people feel the need of
customizing it.

The exception fixup code of the __asm_vector_usercopy must fallback to
the scalar one because accessing user pages might fault, and must be
sleepable. Current kernel-mode Vector does not allow tasks to be
preemptible, so we must disactivate Vector and perform a scalar fallback
in such case.

The original implementation of Vector operations comes from
https://github.com/sifive/sifive-libc, which we agree to contribute to
Linux kernel.

Co-developed-by: Jerry Shih <[email protected]>
Signed-off-by: Jerry Shih <[email protected]>
Co-developed-by: Nick Knight <[email protected]>
Signed-off-by: Nick Knight <[email protected]>
Suggested-by: Guo Ren <[email protected]>
Signed-off-by: Andy Chiu <[email protected]>
Tested-by: Björn Töpel <[email protected]>
Tested-by: Lad Prabhakar <[email protected]>
Link: https://lore.kernel.org/r/[email protected]
Signed-off-by: Palmer Dabbelt <[email protected]>

Author: AndybnACT

arch/riscv/Kconfig

@@ -525,6 +525,14 @@ config RISCV_ISA_V_DEFAULT_ENABLE
 
 	  If you don't know what to do here, say Y.
 
+config RISCV_ISA_V_UCOPY_THRESHOLD
+	int "Threshold size for vectorized user copies"
+	depends on RISCV_ISA_V
+	default 768
+	help
+	  Prefer using vectorized copy_to_user()/copy_from_user() when the
+	  workload size exceeds this value.
+
 config TOOLCHAIN_HAS_ZBB
 	bool
 	default y

arch/riscv/include/asm/asm-prototypes.h

@@ -11,6 +11,10 @@ long long __ashlti3(long long a, int b);
 
 #ifdef CONFIG_RISCV_ISA_V
 
+#ifdef CONFIG_MMU
+asmlinkage int enter_vector_usercopy(void *dst, void *src, size_t n);
+#endif /* CONFIG_MMU  */
+
 void xor_regs_2_(unsigned long bytes, unsigned long *__restrict p1,
 		 const unsigned long *__restrict p2);
 void xor_regs_3_(unsigned long bytes, unsigned long *__restrict p1,

arch/riscv/lib/Makefile

@@ -6,9 +6,13 @@ lib-y			+= memmove.o
 lib-y			+= strcmp.o
 lib-y			+= strlen.o
 lib-y			+= strncmp.o
-lib-$(CONFIG_MMU)	+= uaccess.o
+ifeq ($(CONFIG_MMU), y)
+lib-y				+= uaccess.o
+lib-$(CONFIG_RISCV_ISA_V)	+= uaccess_vector.o
+endif
 lib-$(CONFIG_64BIT)	+= tishift.o
 lib-$(CONFIG_RISCV_ISA_ZICBOZ)	+= clear_page.o
 
 obj-$(CONFIG_FUNCTION_ERROR_INJECTION) += error-inject.o
 lib-$(CONFIG_RISCV_ISA_V)	+= xor.o
+lib-$(CONFIG_RISCV_ISA_V)	+= riscv_v_helpers.o

arch/riscv/lib/riscv_v_helpers.c

@@ -0,0 +1,45 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Copyright (C) 2023 SiFive
+ * Author: Andy Chiu <[email protected]>
+ */
+#include <linux/linkage.h>
+#include <asm/asm.h>
+
+#include <asm/vector.h>
+#include <asm/simd.h>
+
+#ifdef CONFIG_MMU
+#include <asm/asm-prototypes.h>
+#endif
+
+#ifdef CONFIG_MMU
+size_t riscv_v_usercopy_threshold = CONFIG_RISCV_ISA_V_UCOPY_THRESHOLD;
+int __asm_vector_usercopy(void *dst, void *src, size_t n);
+int fallback_scalar_usercopy(void *dst, void *src, size_t n);
+asmlinkage int enter_vector_usercopy(void *dst, void *src, size_t n)
+{
+	size_t remain, copied;
+
+	/* skip has_vector() check because it has been done by the asm  */
+	if (!may_use_simd())
+		goto fallback;
+
+	kernel_vector_begin();
+	remain = __asm_vector_usercopy(dst, src, n);
+	kernel_vector_end();
+
+	if (remain) {
+		copied = n - remain;
+		dst += copied;
+		src += copied;
+		n = remain;
+		goto fallback;
+	}
+
+	return remain;
+
+fallback:
+	return fallback_scalar_usercopy(dst, src, n);
+}
+#endif

arch/riscv/lib/uaccess.S

@@ -3,6 +3,8 @@
 #include <asm/asm.h>
 #include <asm/asm-extable.h>
 #include <asm/csr.h>
+#include <asm/hwcap.h>
+#include <asm/alternative-macros.h>
 
 	.macro fixup op reg addr lbl
 100:
@@ -11,6 +13,13 @@
 	.endm
 
 SYM_FUNC_START(__asm_copy_to_user)
+#ifdef CONFIG_RISCV_ISA_V
+	ALTERNATIVE("j fallback_scalar_usercopy", "nop", 0, RISCV_ISA_EXT_v, CONFIG_RISCV_ISA_V)
+	REG_L	t0, riscv_v_usercopy_threshold
+	bltu	a2, t0, fallback_scalar_usercopy
+	tail enter_vector_usercopy
+#endif
+SYM_FUNC_START(fallback_scalar_usercopy)
 
 	/* Enable access to user memory */
 	li t6, SR_SUM
@@ -181,6 +190,7 @@ SYM_FUNC_START(__asm_copy_to_user)
 	sub a0, t5, a0
 	ret
 SYM_FUNC_END(__asm_copy_to_user)
+SYM_FUNC_END(fallback_scalar_usercopy)
 EXPORT_SYMBOL(__asm_copy_to_user)
 SYM_FUNC_ALIAS(__asm_copy_from_user, __asm_copy_to_user)
 EXPORT_SYMBOL(__asm_copy_from_user)

arch/riscv/lib/uaccess_vector.S

@@ -0,0 +1,53 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+
+#include <linux/linkage.h>
+#include <asm-generic/export.h>
+#include <asm/asm.h>
+#include <asm/asm-extable.h>
+#include <asm/csr.h>
+
+#define pDst a0
+#define pSrc a1
+#define iNum a2
+
+#define iVL a3
+
+#define ELEM_LMUL_SETTING m8
+#define vData v0
+
+	.macro fixup op reg addr lbl
+100:
+	\op \reg, \addr
+	_asm_extable	100b, \lbl
+	.endm
+
+SYM_FUNC_START(__asm_vector_usercopy)
+	/* Enable access to user memory */
+	li	t6, SR_SUM
+	csrs	CSR_STATUS, t6
+
+loop:
+	vsetvli iVL, iNum, e8, ELEM_LMUL_SETTING, ta, ma
+	fixup vle8.v vData, (pSrc), 10f
+	sub iNum, iNum, iVL
+	add pSrc, pSrc, iVL
+	fixup vse8.v vData, (pDst), 11f
+	add pDst, pDst, iVL
+	bnez iNum, loop
+
+	/* Exception fixup for vector load is shared with normal exit */
+10:
+	/* Disable access to user memory */
+	csrc	CSR_STATUS, t6
+	mv	a0, iNum
+	ret
+
+	/* Exception fixup code for vector store. */
+11:
+	/* Undo the subtraction after vle8.v */
+	add	iNum, iNum, iVL
+	/* Make sure the scalar fallback skip already processed bytes */
+	csrr	t2, CSR_VSTART
+	sub	iNum, iNum, t2
+	j	10b
+SYM_FUNC_END(__asm_vector_usercopy)