VisionFive2 Linux kernel

StarFive Tech Linux Kernel for VisionFive (JH7110) boards (mirror)

More than 9999 Commits   34 Branches   58 Tags
author: andy.hu <andy.hu@starfivetech.com> 2023-04-07 11:32:34 +0000 committer: andy.hu <andy.hu@starfivetech.com> 2023-04-07 11:32:34 +0000 commit: 8a86cc03a3ca69b130694300915de64e9b7a4569 parent: f97cc70c5356b5eed549aff2ab6a62bdb917475c
Commit Summary:
Merge branch 'CR_4563_memcpy_510_samin.guo' into 'jh7110-5.10.y-devel'
Diffstat:
5 files changed, 81 insertions, 104 deletions
diff --git a/arch/riscv/include/asm/string.h b/arch/riscv/include/asm/string.h
index 924af13f8555..f00a57889eec 100644
--- a/arch/riscv/include/asm/string.h
+++ b/arch/riscv/include/asm/string.h
@@ -14,8 +14,8 @@ extern asmlinkage void *memset(void *, int, size_t);
 extern asmlinkage void *__memset(void *, int, size_t);
 
 #define __HAVE_ARCH_MEMCPY
-extern asmlinkage void *memcpy(void *, const void *, size_t);
-extern asmlinkage void *__memcpy(void *, const void *, size_t);
+extern void *memcpy(void *dest, const void *src, size_t count);
+extern void *__memcpy(void *dest, const void *src, size_t count);
 
 /* For those files which don't want to check by kasan. */
 #if defined(CONFIG_KASAN) && !defined(__SANITIZE_ADDRESS__)
diff --git a/arch/riscv/kernel/riscv_ksyms.c b/arch/riscv/kernel/riscv_ksyms.c
index 450492e1cb4e..361565c4db7e 100644
--- a/arch/riscv/kernel/riscv_ksyms.c
+++ b/arch/riscv/kernel/riscv_ksyms.c
@@ -10,6 +10,4 @@
  * Assembly functions that may be used (directly or indirectly) by modules
  */
 EXPORT_SYMBOL(memset);
-EXPORT_SYMBOL(memcpy);
 EXPORT_SYMBOL(__memset);
-EXPORT_SYMBOL(__memcpy);
diff --git a/arch/riscv/lib/Makefile b/arch/riscv/lib/Makefile
index 47e7a8204460..719201006075 100644
--- a/arch/riscv/lib/Makefile
+++ b/arch/riscv/lib/Makefile
@@ -1,6 +1,11 @@
 # SPDX-License-Identifier: GPL-2.0-only
 lib-y			+= delay.o
-lib-y			+= memcpy.o
 lib-y			+= memset.o
 lib-$(CONFIG_MMU)	+= uaccess.o
 lib-$(CONFIG_64BIT)	+= tishift.o
+lib-y			+= string.o
+
+# string.o implements standard library functions like memset/memcpy etc.
+# # Use -ffreestanding to ensure that the compiler does not try to "optimize"
+# # them into calls to themselves.
+# CFLAGS_string.o := -ffreestanding
diff --git a/arch/riscv/lib/memcpy.S b/arch/riscv/lib/memcpy.S
deleted file mode 100644
index 51ab716253fa..000000000000
--- a/arch/riscv/lib/memcpy.S
+++ /dev/null
@@ -1,108 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-only */
-/*
- * Copyright (C) 2013 Regents of the University of California
- */
-
-#include <linux/linkage.h>
-#include <asm/asm.h>
-
-/* void *memcpy(void *, const void *, size_t) */
-ENTRY(__memcpy)
-WEAK(memcpy)
-	move t6, a0  /* Preserve return value */
-
-	/* Defer to byte-oriented copy for small sizes */
-	sltiu a3, a2, 128
-	bnez a3, 4f
-	/* Use word-oriented copy only if low-order bits match */
-	andi a3, t6, SZREG-1
-	andi a4, a1, SZREG-1
-	bne a3, a4, 4f
-
-	beqz a3, 2f  /* Skip if already aligned */
-	/*
-	 * Round to nearest double word-aligned address
-	 * greater than or equal to start address
-	 */
-	andi a3, a1, ~(SZREG-1)
-	addi a3, a3, SZREG
-	/* Handle initial misalignment */
-	sub a4, a3, a1
-1:
-	lb a5, 0(a1)
-	addi a1, a1, 1
-	sb a5, 0(t6)
-	addi t6, t6, 1
-	bltu a1, a3, 1b
-	sub a2, a2, a4  /* Update count */
-
-2:
-	andi a4, a2, ~((16*SZREG)-1)
-	beqz a4, 4f
-	add a3, a1, a4
-3:
-	REG_L a4,       0(a1)
-	REG_L a5,   SZREG(a1)
-	REG_L a6, 2*SZREG(a1)
-	REG_L a7, 3*SZREG(a1)
-	REG_L t0, 4*SZREG(a1)
-	REG_L t1, 5*SZREG(a1)
-	REG_L t2, 6*SZREG(a1)
-	REG_L t3, 7*SZREG(a1)
-	REG_L t4, 8*SZREG(a1)
-	REG_L t5, 9*SZREG(a1)
-	REG_S a4,       0(t6)
-	REG_S a5,   SZREG(t6)
-	REG_S a6, 2*SZREG(t6)
-	REG_S a7, 3*SZREG(t6)
-	REG_S t0, 4*SZREG(t6)
-	REG_S t1, 5*SZREG(t6)
-	REG_S t2, 6*SZREG(t6)
-	REG_S t3, 7*SZREG(t6)
-	REG_S t4, 8*SZREG(t6)
-	REG_S t5, 9*SZREG(t6)
-	REG_L a4, 10*SZREG(a1)
-	REG_L a5, 11*SZREG(a1)
-	REG_L a6, 12*SZREG(a1)
-	REG_L a7, 13*SZREG(a1)
-	REG_L t0, 14*SZREG(a1)
-	REG_L t1, 15*SZREG(a1)
-	addi a1, a1, 16*SZREG
-	REG_S a4, 10*SZREG(t6)
-	REG_S a5, 11*SZREG(t6)
-	REG_S a6, 12*SZREG(t6)
-	REG_S a7, 13*SZREG(t6)
-	REG_S t0, 14*SZREG(t6)
-	REG_S t1, 15*SZREG(t6)
-	addi t6, t6, 16*SZREG
-	bltu a1, a3, 3b
-	andi a2, a2, (16*SZREG)-1  /* Update count */
-
-4:
-	/* Handle trailing misalignment */
-	beqz a2, 6f
-	add a3, a1, a2
-
-	/* Use word-oriented copy if co-aligned to word boundary */
-	or a5, a1, t6
-	or a5, a5, a3
-	andi a5, a5, 3
-	bnez a5, 5f
-7:
-	lw a4, 0(a1)
-	addi a1, a1, 4
-	sw a4, 0(t6)
-	addi t6, t6, 4
-	bltu a1, a3, 7b
-
-	ret
-
-5:
-	lb a4, 0(a1)
-	addi a1, a1, 1
-	sb a4, 0(t6)
-	addi t6, t6, 1
-	bltu a1, a3, 5b
-6:
-	ret
-END(__memcpy)
diff --git a/arch/riscv/lib/string.c b/arch/riscv/lib/string.c
new file mode 100644
index 000000000000..32509ab0232e
--- /dev/null
+++ b/arch/riscv/lib/string.c
@@ -0,0 +1,91 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * String functions optimized for hardware which doesn't
+ * handle unaligned memory accesses efficiently.
+ *
+ * Copyright (C) 2021 Matteo Croce
+ */
+
+#define __NO_FORTIFY
+#include <linux/types.h>
+#include <linux/module.h>
+
+/* Minimum size for a word copy to be convenient */
+#define BYTES_LONG	sizeof(long)
+#define WORD_MASK	(BYTES_LONG - 1)
+#define MIN_THRESHOLD	(BYTES_LONG * 2)
+
+/* convenience union to avoid cast between different pointer types */
+union types {
+	u8 *as_u8;
+	unsigned long *as_ulong;
+	uintptr_t as_uptr;
+};
+
+union const_types {
+	const u8 *as_u8;
+	unsigned long *as_ulong;
+	uintptr_t as_uptr;
+};
+
+void *__memcpy(void *dest, const void *src, size_t count)
+{
+	union const_types s = { .as_u8 = src };
+	union types d = { .as_u8 = dest };
+	int distance = 0;
+
+	if (!IS_ENABLED(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS)) {
+		if (count < MIN_THRESHOLD)
+			goto copy_remainder;
+
+		/* Copy a byte at time until destination is aligned. */
+		for (; d.as_uptr & WORD_MASK; count--)
+			*d.as_u8++ = *s.as_u8++;
+
+		distance = s.as_uptr & WORD_MASK;
+	}
+
+	if (distance) {
+		unsigned long last, next;
+
+		/*
+		 * s is distance bytes ahead of d, and d just reached
+		 * the alignment boundary. Move s backward to word align it
+		 * and shift data to compensate for distance, in order to do
+		 * word-by-word copy.
+		 */
+		s.as_u8 -= distance;
+
+		next = s.as_ulong[0];
+		for (; count >= BYTES_LONG; count -= BYTES_LONG) {
+			last = next;
+			next = s.as_ulong[1];
+
+			d.as_ulong[0] = last >> (distance * 8) |
+					next << ((BYTES_LONG - distance) * 8);
+
+			d.as_ulong++;
+			s.as_ulong++;
+		}
+
+		/* Restore s with the original offset. */
+		s.as_u8 += distance;
+	} else {
+		/*
+		 * If the source and dest lower bits are the same, do a simple
+		 * 32/64 bit wide copy.
+		 */
+		for (; count >= BYTES_LONG; count -= BYTES_LONG)
+			*d.as_ulong++ = *s.as_ulong++;
+	}
+
+copy_remainder:
+	while (count--)
+		*d.as_u8++ = *s.as_u8++;
+
+	return dest;
+}
+EXPORT_SYMBOL(__memcpy);
+
+void *memcpy(void *dest, const void *src, size_t count) __weak __alias(__memcpy);
+EXPORT_SYMBOL(memcpy);