diff mbox series

[v5,3/3] riscv: optimized memset

Message ID 20210929172234.31620-4-mcroce@linux.microsoft.com (mailing list archive)
State New, archived
Headers show
Series riscv: optimized mem* functions | expand

Commit Message

Matteo Croce Sept. 29, 2021, 5:22 p.m. UTC 
From: Matteo Croce <mcroce@microsoft.com>

The generic memset is defined as a byte at time write. This is always
safe, but it's slower than a 4 byte or even 8 byte write.

Write a generic memset which fills the data one byte at time until the
destination is aligned, then fills using the largest size allowed,
and finally fills the remaining data one byte at time.

Signed-off-by: Matteo Croce <mcroce@microsoft.com>
---
 arch/riscv/include/asm/string.h |  10 +--
 arch/riscv/kernel/Makefile      |   1 -
 arch/riscv/kernel/riscv_ksyms.c |  13 ----
 arch/riscv/lib/Makefile         |   1 -
 arch/riscv/lib/memset.S         | 113 --------------------------------
 arch/riscv/lib/string.c         |  41 ++++++++++++
 6 files changed, 44 insertions(+), 135 deletions(-)
 delete mode 100644 arch/riscv/kernel/riscv_ksyms.c
 delete mode 100644 arch/riscv/lib/memset.S

Comments

Ley Foon Tan Nov. 25, 2021, 10:56 a.m. UTC | #1 
On Thu, Sep 30, 2021 at 1:56 AM Matteo Croce <mcroce@linux.microsoft.com> wrote:
>
> From: Matteo Croce <mcroce@microsoft.com>
>
> The generic memset is defined as a byte at time write. This is always
> safe, but it's slower than a 4 byte or even 8 byte write.
>
> Write a generic memset which fills the data one byte at time until the
> destination is aligned, then fills using the largest size allowed,
> and finally fills the remaining data one byte at time.
>
> Signed-off-by: Matteo Croce <mcroce@microsoft.com>
> ---
>  arch/riscv/include/asm/string.h |  10 +--
>  arch/riscv/kernel/Makefile      |   1 -
>  arch/riscv/kernel/riscv_ksyms.c |  13 ----
>  arch/riscv/lib/Makefile         |   1 -
>  arch/riscv/lib/memset.S         | 113 --------------------------------
>  arch/riscv/lib/string.c         |  41 ++++++++++++
>  6 files changed, 44 insertions(+), 135 deletions(-)
>  delete mode 100644 arch/riscv/kernel/riscv_ksyms.c
>  delete mode 100644 arch/riscv/lib/memset.S

This patch causes the Linux kernel to hang if compile with LLVM/Clang.
Tested on Qemu.

Steps to compile with Clang:
make CC=clang  defconfig
make CC=clang -j

Boot log:

[    0.000000] Linux version 5.15.4-01003-g23eeaac40da8 (xxxxx@ubuntu)
(clang version 14.0.0 (https://github.com/llvm/llvm-project
6b715e9c4d9cc00f59906d48cd57f4c767229093), GNU ld (GNU Binutils)
2.36.1) #151 SMP Thu Nov 25 18:41:47 +08 2021
[    0.000000] OF: fdt: Ignoring memory range 0x80000000 - 0x80200000
[    0.000000] Machine model: riscv-virtio,qemu
[    0.000000] earlycon: sbi0 at I/O port 0x0 (options '')
[    0.000000] printk: bootconsole [sbi0] enabled
[    0.000000] efi: UEFI not found.

Regards
Ley Foon
Emil Renner Berthing Dec. 6, 2021, 8:37 p.m. UTC | #2 
Hi Ley Foon,

You're right it doesn't boot for me either when building with

  make ARCH=riscv LLVM=1

The following patch fixes it for me though. In hindsigt it's perhaps a
bit surprising it works without -ffreestanding in GCC.

/Emil

---
 arch/riscv/lib/Makefile | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/arch/riscv/lib/Makefile b/arch/riscv/lib/Makefile
index e33263cc622a..6dfa919d4cd6 100644
--- a/arch/riscv/lib/Makefile
+++ b/arch/riscv/lib/Makefile
@@ -4,4 +4,9 @@ lib-$(CONFIG_MMU)	+= uaccess.o
 lib-$(CONFIG_64BIT)	+= tishift.o
 lib-$(CONFIG_CC_OPTIMIZE_FOR_PERFORMANCE) += 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
+
 obj-$(CONFIG_FUNCTION_ERROR_INJECTION) += error-inject.o
diff mbox series

Patch

diff --git a/arch/riscv/include/asm/string.h b/arch/riscv/include/asm/string.h
index 25d9b9078569..90500635035a 100644
--- a/arch/riscv/include/asm/string.h
+++ b/arch/riscv/include/asm/string.h
@@ -6,14 +6,10 @@ 
 #ifndef _ASM_RISCV_STRING_H
 #define _ASM_RISCV_STRING_H
 
-#include <linux/types.h>
-#include <linux/linkage.h>
-
-#define __HAVE_ARCH_MEMSET
-extern asmlinkage void *memset(void *, int, size_t);
-extern asmlinkage void *__memset(void *, int, size_t);
-
 #ifdef CONFIG_CC_OPTIMIZE_FOR_PERFORMANCE
+#define __HAVE_ARCH_MEMSET
+extern void *memset(void *s, int c, size_t count);
+extern void *__memset(void *s, int c, size_t count);
 #define __HAVE_ARCH_MEMCPY
 extern void *memcpy(void *dest, const void *src, size_t count);
 extern void *__memcpy(void *dest, const void *src, size_t count);
diff --git a/arch/riscv/kernel/Makefile b/arch/riscv/kernel/Makefile
index 3397ddac1a30..fecf03822435 100644
--- a/arch/riscv/kernel/Makefile
+++ b/arch/riscv/kernel/Makefile
@@ -31,7 +31,6 @@  obj-y	+= syscall_table.o
 obj-y	+= sys_riscv.o
 obj-y	+= time.o
 obj-y	+= traps.o
-obj-y	+= riscv_ksyms.o
 obj-y	+= stacktrace.o
 obj-y	+= cacheinfo.o
 obj-y	+= patch.o
diff --git a/arch/riscv/kernel/riscv_ksyms.c b/arch/riscv/kernel/riscv_ksyms.c
deleted file mode 100644
index 361565c4db7e..000000000000
--- a/arch/riscv/kernel/riscv_ksyms.c
+++ /dev/null
@@ -1,13 +0,0 @@ 
-// SPDX-License-Identifier: GPL-2.0-only
-/*
- * Copyright (C) 2017 Zihao Yu
- */
-
-#include <linux/export.h>
-#include <linux/uaccess.h>
-
-/*
- * Assembly functions that may be used (directly or indirectly) by modules
- */
-EXPORT_SYMBOL(memset);
-EXPORT_SYMBOL(__memset);
diff --git a/arch/riscv/lib/Makefile b/arch/riscv/lib/Makefile
index 484f5ff7b508..e33263cc622a 100644
--- a/arch/riscv/lib/Makefile
+++ b/arch/riscv/lib/Makefile
@@ -1,6 +1,5 @@ 
 # SPDX-License-Identifier: GPL-2.0-only
 lib-y			+= delay.o
-lib-y			+= memset.o
 lib-$(CONFIG_MMU)	+= uaccess.o
 lib-$(CONFIG_64BIT)	+= tishift.o
 lib-$(CONFIG_CC_OPTIMIZE_FOR_PERFORMANCE) += string.o
diff --git a/arch/riscv/lib/memset.S b/arch/riscv/lib/memset.S
deleted file mode 100644
index 34c5360c6705..000000000000
--- a/arch/riscv/lib/memset.S
+++ /dev/null
@@ -1,113 +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 *memset(void *, int, size_t) */
-ENTRY(__memset)
-WEAK(memset)
-	move t0, a0  /* Preserve return value */
-
-	/* Defer to byte-oriented fill for small sizes */
-	sltiu a3, a2, 16
-	bnez a3, 4f
-
-	/*
-	 * Round to nearest XLEN-aligned address
-	 * greater than or equal to start address
-	 */
-	addi a3, t0, SZREG-1
-	andi a3, a3, ~(SZREG-1)
-	beq a3, t0, 2f  /* Skip if already aligned */
-	/* Handle initial misalignment */
-	sub a4, a3, t0
-1:
-	sb a1, 0(t0)
-	addi t0, t0, 1
-	bltu t0, a3, 1b
-	sub a2, a2, a4  /* Update count */
-
-2: /* Duff's device with 32 XLEN stores per iteration */
-	/* Broadcast value into all bytes */
-	andi a1, a1, 0xff
-	slli a3, a1, 8
-	or a1, a3, a1
-	slli a3, a1, 16
-	or a1, a3, a1
-#ifdef CONFIG_64BIT
-	slli a3, a1, 32
-	or a1, a3, a1
-#endif
-
-	/* Calculate end address */
-	andi a4, a2, ~(SZREG-1)
-	add a3, t0, a4
-
-	andi a4, a4, 31*SZREG  /* Calculate remainder */
-	beqz a4, 3f            /* Shortcut if no remainder */
-	neg a4, a4
-	addi a4, a4, 32*SZREG  /* Calculate initial offset */
-
-	/* Adjust start address with offset */
-	sub t0, t0, a4
-
-	/* Jump into loop body */
-	/* Assumes 32-bit instruction lengths */
-	la a5, 3f
-#ifdef CONFIG_64BIT
-	srli a4, a4, 1
-#endif
-	add a5, a5, a4
-	jr a5
-3:
-	REG_S a1,        0(t0)
-	REG_S a1,    SZREG(t0)
-	REG_S a1,  2*SZREG(t0)
-	REG_S a1,  3*SZREG(t0)
-	REG_S a1,  4*SZREG(t0)
-	REG_S a1,  5*SZREG(t0)
-	REG_S a1,  6*SZREG(t0)
-	REG_S a1,  7*SZREG(t0)
-	REG_S a1,  8*SZREG(t0)
-	REG_S a1,  9*SZREG(t0)
-	REG_S a1, 10*SZREG(t0)
-	REG_S a1, 11*SZREG(t0)
-	REG_S a1, 12*SZREG(t0)
-	REG_S a1, 13*SZREG(t0)
-	REG_S a1, 14*SZREG(t0)
-	REG_S a1, 15*SZREG(t0)
-	REG_S a1, 16*SZREG(t0)
-	REG_S a1, 17*SZREG(t0)
-	REG_S a1, 18*SZREG(t0)
-	REG_S a1, 19*SZREG(t0)
-	REG_S a1, 20*SZREG(t0)
-	REG_S a1, 21*SZREG(t0)
-	REG_S a1, 22*SZREG(t0)
-	REG_S a1, 23*SZREG(t0)
-	REG_S a1, 24*SZREG(t0)
-	REG_S a1, 25*SZREG(t0)
-	REG_S a1, 26*SZREG(t0)
-	REG_S a1, 27*SZREG(t0)
-	REG_S a1, 28*SZREG(t0)
-	REG_S a1, 29*SZREG(t0)
-	REG_S a1, 30*SZREG(t0)
-	REG_S a1, 31*SZREG(t0)
-	addi t0, t0, 32*SZREG
-	bltu t0, a3, 3b
-	andi a2, a2, SZREG-1  /* Update count */
-
-4:
-	/* Handle trailing misalignment */
-	beqz a2, 6f
-	add a3, t0, a2
-5:
-	sb a1, 0(t0)
-	addi t0, t0, 1
-	bltu t0, a3, 5b
-6:
-	ret
-END(__memset)
diff --git a/arch/riscv/lib/string.c b/arch/riscv/lib/string.c
index 4442ca5ef13c..871ffbfac0ab 100644
--- a/arch/riscv/lib/string.c
+++ b/arch/riscv/lib/string.c
@@ -111,3 +111,44 @@  EXPORT_SYMBOL(__memmove);
 
 void *memmove(void *dest, const void *src, size_t count) __weak __alias(__memmove);
 EXPORT_SYMBOL(memmove);
+
+void *__memset(void *s, int c, size_t count)
+{
+	union types dest = { .as_u8 = s };
+
+	if (count >= MIN_THRESHOLD) {
+		unsigned long cu = (unsigned long)c;
+
+		/* Compose an ulong with 'c' repeated 4/8 times */
+#ifdef CONFIG_ARCH_HAS_FAST_MULTIPLIER
+		cu *= 0x0101010101010101UL;
+#else
+		cu |= cu << 8;
+		cu |= cu << 16;
+		/* Suppress warning on 32 bit machines */
+		cu |= (cu << 16) << 16;
+#endif
+		if (!IS_ENABLED(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS)) {
+			/*
+			 * Fill the buffer one byte at time until
+			 * the destination is word aligned.
+			 */
+			for (; count && dest.as_uptr & WORD_MASK; count--)
+				*dest.as_u8++ = c;
+		}
+
+		/* Copy using the largest size allowed */
+		for (; count >= BYTES_LONG; count -= BYTES_LONG)
+			*dest.as_ulong++ = cu;
+	}
+
+	/* copy the remainder */
+	while (count--)
+		*dest.as_u8++ = c;
+
+	return s;
+}
+EXPORT_SYMBOL(__memset);
+
+void *memset(void *s, int c, size_t count) __weak __alias(__memset);
+EXPORT_SYMBOL(memset);