From: Matteo Croce <mcroce@linux.microsoft.com> To: linux-riscv@lists.infradead.org Cc: linux-kernel@vger.kernel.org, linux-arch@vger.kernel.org, Paul Walmsley <paul.walmsley@sifive.com>, Palmer Dabbelt <palmer@dabbelt.com>, Albert Ou <aou@eecs.berkeley.edu>, Atish Patra <atish.patra@wdc.com>, Emil Renner Berthing <kernel@esmil.dk>, Akira Tsukamoto <akira.tsukamoto@gmail.com>, Drew Fustini <drew@beagleboard.org>, Bin Meng <bmeng.cn@gmail.com>, David Laight <David.Laight@aculab.com>, Guo Ren <guoren@kernel.org>, Christoph Hellwig <hch@lst.de> Subject: [PATCH v5 3/3] riscv: optimized memset Date: Wed, 29 Sep 2021 19:22:34 +0200 [thread overview] Message-ID: <20210929172234.31620-4-mcroce@linux.microsoft.com> (raw) In-Reply-To: <20210929172234.31620-1-mcroce@linux.microsoft.com> 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 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); -- 2.31.1
WARNING: multiple messages have this Message-ID (diff)
From: Matteo Croce <mcroce@linux.microsoft.com> To: linux-riscv@lists.infradead.org Cc: linux-kernel@vger.kernel.org, linux-arch@vger.kernel.org, Paul Walmsley <paul.walmsley@sifive.com>, Palmer Dabbelt <palmer@dabbelt.com>, Albert Ou <aou@eecs.berkeley.edu>, Atish Patra <atish.patra@wdc.com>, Emil Renner Berthing <kernel@esmil.dk>, Akira Tsukamoto <akira.tsukamoto@gmail.com>, Drew Fustini <drew@beagleboard.org>, Bin Meng <bmeng.cn@gmail.com>, David Laight <David.Laight@aculab.com>, Guo Ren <guoren@kernel.org>, Christoph Hellwig <hch@lst.de> Subject: [PATCH v5 3/3] riscv: optimized memset Date: Wed, 29 Sep 2021 19:22:34 +0200 [thread overview] Message-ID: <20210929172234.31620-4-mcroce@linux.microsoft.com> (raw) In-Reply-To: <20210929172234.31620-1-mcroce@linux.microsoft.com> 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 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); -- 2.31.1 _______________________________________________ linux-riscv mailing list linux-riscv@lists.infradead.org http://lists.infradead.org/mailman/listinfo/linux-riscv
next prev parent reply other threads:[~2021-09-29 17:22 UTC|newest] Thread overview: 24+ messages / expand[flat|nested] mbox.gz Atom feed top 2021-09-29 17:22 [PATCH v5 0/3] riscv: optimized mem* functions Matteo Croce 2021-09-29 17:22 ` Matteo Croce 2021-09-29 17:22 ` [PATCH v5 1/3] riscv: optimized memcpy Matteo Croce 2021-09-29 17:22 ` Matteo Croce 2021-09-30 1:24 ` Guo Ren 2021-09-30 1:24 ` Guo Ren 2021-09-30 1:36 ` Matteo Croce 2021-09-30 1:36 ` Matteo Croce 2021-09-30 19:43 ` Vineet Gupta 2021-09-30 19:43 ` Vineet Gupta 2021-10-01 8:06 ` David Laight 2021-10-01 8:06 ` David Laight 2021-10-01 11:23 ` Pavel Machek 2021-10-01 11:23 ` Pavel Machek 2021-10-02 17:20 ` Matteo Croce 2021-10-02 17:20 ` Matteo Croce 2021-09-29 17:22 ` [PATCH v5 2/3] riscv: optimized memmove Matteo Croce 2021-09-29 17:22 ` Matteo Croce 2021-09-29 17:22 ` Matteo Croce [this message] 2021-09-29 17:22 ` [PATCH v5 3/3] riscv: optimized memset Matteo Croce 2021-11-25 10:56 ` Ley Foon Tan 2021-11-25 10:56 ` Ley Foon Tan 2021-12-06 20:37 ` Emil Renner Berthing 2021-12-06 20:37 ` Emil Renner Berthing
Reply instructions: You may reply publicly to this message via plain-text email using any one of the following methods: * Save the following mbox file, import it into your mail client, and reply-to-all from there: mbox Avoid top-posting and favor interleaved quoting: https://en.wikipedia.org/wiki/Posting_style#Interleaved_style * Reply using the --to, --cc, and --in-reply-to switches of git-send-email(1): git send-email \ --in-reply-to=20210929172234.31620-4-mcroce@linux.microsoft.com \ --to=mcroce@linux.microsoft.com \ --cc=David.Laight@aculab.com \ --cc=akira.tsukamoto@gmail.com \ --cc=aou@eecs.berkeley.edu \ --cc=atish.patra@wdc.com \ --cc=bmeng.cn@gmail.com \ --cc=drew@beagleboard.org \ --cc=guoren@kernel.org \ --cc=hch@lst.de \ --cc=kernel@esmil.dk \ --cc=linux-arch@vger.kernel.org \ --cc=linux-kernel@vger.kernel.org \ --cc=linux-riscv@lists.infradead.org \ --cc=palmer@dabbelt.com \ --cc=paul.walmsley@sifive.com \ /path/to/YOUR_REPLY https://kernel.org/pub/software/scm/git/docs/git-send-email.html * If your mail client supports setting the In-Reply-To header via mailto: links, try the mailto: linkBe sure your reply has a Subject: header at the top and a blank line before the message body.
This is an external index of several public inboxes, see mirroring instructions on how to clone and mirror all data and code used by this external index.