From: Peter Zijlstra <peterz@infradead.org>
To: Huacai Chen <chenhuacai@loongson.cn>
Cc: Arnd Bergmann <arnd@arndb.de>, Andy Lutomirski <luto@kernel.org>,
Thomas Gleixner <tglx@linutronix.de>,
Andrew Morton <akpm@linux-foundation.org>,
David Airlie <airlied@linux.ie>, Jonathan Corbet <corbet@lwn.net>,
Linus Torvalds <torvalds@linux-foundation.org>,
linux-arch@vger.kernel.org, linux-doc@vger.kernel.org,
linux-kernel@vger.kernel.org, Xuefeng Li <lixuefeng@loongson.cn>,
Yanteng Si <siyanteng@loongson.cn>,
Huacai Chen <chenhuacai@gmail.com>,
Jiaxun Yang <jiaxun.yang@flygoat.com>
Subject: Re: [PATCH V4 16/22] LoongArch: Add misc common routines
Date: Fri, 1 Oct 2021 13:03:26 +0200 [thread overview]
Message-ID: <YVbq/kAZQimL3Vpc@hirez.programming.kicks-ass.net> (raw)
In-Reply-To: <20210927064300.624279-17-chenhuacai@loongson.cn>
On Mon, Sep 27, 2021 at 02:42:53PM +0800, Huacai Chen wrote:
> arch/loongarch/include/asm/cmpxchg.h | 137 ++++++++++++
> arch/loongarch/kernel/cmpxchg.c | 107 ++++++++++
This really should have gone into the atomics/locking patch.
> diff --git a/arch/loongarch/include/asm/cmpxchg.h b/arch/loongarch/include/asm/cmpxchg.h
> new file mode 100644
> index 000000000000..13ee1b62dc12
> --- /dev/null
> +++ b/arch/loongarch/include/asm/cmpxchg.h
> @@ -0,0 +1,137 @@
> +/* SPDX-License-Identifier: GPL-2.0 */
> +/*
> + * Copyright (C) 2020-2021 Loongson Technology Corporation Limited
> + */
> +#ifndef __ASM_CMPXCHG_H
> +#define __ASM_CMPXCHG_H
> +
> +#include <linux/bug.h>
> +#include <asm/barrier.h>
> +#include <asm/compiler.h>
> +
> +#define __xchg_asm(amswap_db, m, val) \
> +({ \
> + __typeof(val) __ret; \
> + \
> + __asm__ __volatile__ ( \
> + " "amswap_db" %1, %z2, %0 \n" \
> + : "+ZB" (*m), "=&r" (__ret) \
> + : "Jr" (val) \
> + : "memory"); \
> + \
> + __ret; \
> +})
> +
> +extern unsigned long __xchg_small(volatile void *ptr, unsigned long x,
> + unsigned int size);
> +
> +static inline unsigned long __xchg(volatile void *ptr, unsigned long x,
> + int size)
> +{
> + switch (size) {
> + case 1:
> + case 2:
> + return __xchg_small(ptr, x, size);
> +
> + case 4:
> + return __xchg_asm("amswap_db.w", (volatile u32 *)ptr, (u32)x);
> +
> + case 8:
> + return __xchg_asm("amswap_db.d", (volatile u64 *)ptr, (u64)x);
> +
> + default:
> + BUILD_BUG();
> + }
> +
> + return 0;
> +}
> +
> +#define arch_xchg(ptr, x) \
> +({ \
> + __typeof__(*(ptr)) __res; \
> + \
> + __res = (__typeof__(*(ptr))) \
> + __xchg((ptr), (unsigned long)(x), sizeof(*(ptr))); \
> + \
> + __res; \
> +})
> +
> +#define __cmpxchg_asm(ld, st, m, old, new) \
> +({ \
> + __typeof(old) __ret; \
> + \
> + __asm__ __volatile__( \
> + "1: " ld " %0, %2 # __cmpxchg_asm \n" \
> + " bne %0, %z3, 2f \n" \
> + " or $t0, %z4, $zero \n" \
> + " " st " $t0, %1 \n" \
> + " beq $zero, $t0, 1b \n" \
> + "2: \n" \
> + : "=&r" (__ret), "=ZB"(*m) \
> + : "ZB"(*m), "Jr" (old), "Jr" (new) \
> + : "t0", "memory"); \
> + \
> + __ret; \
> +})
> +
> +extern unsigned long __cmpxchg_small(volatile void *ptr, unsigned long old,
> + unsigned long new, unsigned int size);
> +
> +static inline unsigned long __cmpxchg(volatile void *ptr, unsigned long old,
> + unsigned long new, unsigned int size)
> +{
> + switch (size) {
> + case 1:
> + case 2:
> + return __cmpxchg_small(ptr, old, new, size);
> +
> + case 4:
> + return __cmpxchg_asm("ll.w", "sc.w", (volatile u32 *)ptr,
> + (u32)old, new);
> +
> + case 8:
> + return __cmpxchg_asm("ll.d", "sc.d", (volatile u64 *)ptr,
> + (u64)old, new);
> +
> + default:
> + BUILD_BUG();
> + }
> +
> + return 0;
> +}
> +
> +#define arch_cmpxchg_local(ptr, old, new) \
> + ((__typeof__(*(ptr))) \
> + __cmpxchg((ptr), \
> + (unsigned long)(__typeof__(*(ptr)))(old), \
> + (unsigned long)(__typeof__(*(ptr)))(new), \
> + sizeof(*(ptr))))
> +
> +#define arch_cmpxchg(ptr, old, new) \
> +({ \
> + __typeof__(*(ptr)) __res; \
> + \
> + __res = arch_cmpxchg_local((ptr), (old), (new)); \
> + \
> + __res; \
> +})
> +
> +#ifdef CONFIG_64BIT
> +#define arch_cmpxchg64_local(ptr, o, n) \
> + ({ \
> + BUILD_BUG_ON(sizeof(*(ptr)) != 8); \
> + arch_cmpxchg_local((ptr), (o), (n)); \
> + })
> +
> +#define arch_cmpxchg64(ptr, o, n) \
> + ({ \
> + BUILD_BUG_ON(sizeof(*(ptr)) != 8); \
> + arch_cmpxchg((ptr), (o), (n)); \
> + })
> +#else
> +#include <asm-generic/cmpxchg-local.h>
> +#define arch_cmpxchg64_local(ptr, o, n) __generic_cmpxchg64_local((ptr), (o), (n))
> +#define arch_cmpxchg64(ptr, o, n) arch_cmpxchg64_local((ptr), (o), (n))
> +#endif
> +
> +#endif /* __ASM_CMPXCHG_H */
> diff --git a/arch/loongarch/kernel/cmpxchg.c b/arch/loongarch/kernel/cmpxchg.c
> new file mode 100644
> index 000000000000..81bb9d01a3b5
> --- /dev/null
> +++ b/arch/loongarch/kernel/cmpxchg.c
> @@ -0,0 +1,107 @@
> +// SPDX-License-Identifier: GPL-2.0
> +/*
> + * Author: Huacai Chen <chenhuacai@loongson.cn>
> + * Copyright (C) 2020-2021 Loongson Technology Corporation Limited
> + *
> + * Derived from MIPS:
> + * Copyright (C) 2017 Imagination Technologies
> + * Author: Paul Burton <paul.burton@mips.com>
> + */
> +
> +#include <linux/bitops.h>
> +#include <asm/cmpxchg.h>
> +
> +unsigned long __xchg_small(volatile void *ptr, unsigned long val, unsigned int size)
> +{
> + u32 old32, mask, temp;
> + volatile u32 *ptr32;
> + unsigned int shift;
> +
> + /* Check that ptr is naturally aligned */
> + WARN_ON((unsigned long)ptr & (size - 1));
> +
> + /* Mask value to the correct size. */
> + mask = GENMASK((size * BITS_PER_BYTE) - 1, 0);
> + val &= mask;
> +
> + /*
> + * Calculate a shift & mask that correspond to the value we wish to
> + * exchange within the naturally aligned 4 byte integerthat includes
> + * it.
> + */
> + shift = (unsigned long)ptr & 0x3;
> + shift *= BITS_PER_BYTE;
> + mask <<= shift;
> +
> + /*
> + * Calculate a pointer to the naturally aligned 4 byte integer that
> + * includes our byte of interest, and load its value.
> + */
> + ptr32 = (volatile u32 *)((unsigned long)ptr & ~0x3);
> +
> + asm volatile (
> + "1: ll.w %0, %3 \n"
> + " and %1, %0, %4 \n"
> + " or %1, %1, %5 \n"
> + " sc.w %1, %2 \n"
> + " beqz %1, 1b \n"
> + : "=&r" (old32), "=&r" (temp), "=" GCC_OFF_SMALL_ASM() (*ptr32)
> + : GCC_OFF_SMALL_ASM() (*ptr32), "Jr" (~mask), "Jr" (val << shift)
> + : "memory");
> +
> + return (old32 & mask) >> shift;
> +}
> +
> +unsigned long __cmpxchg_small(volatile void *ptr, unsigned long old,
> + unsigned long new, unsigned int size)
> +{
> + u32 mask, old32, new32, load32, load;
> + volatile u32 *ptr32;
> + unsigned int shift;
> +
> + /* Check that ptr is naturally aligned */
> + WARN_ON((unsigned long)ptr & (size - 1));
> +
> + /* Mask inputs to the correct size. */
> + mask = GENMASK((size * BITS_PER_BYTE) - 1, 0);
> + old &= mask;
> + new &= mask;
> +
> + /*
> + * Calculate a shift & mask that correspond to the value we wish to
> + * compare & exchange within the naturally aligned 4 byte integer
> + * that includes it.
> + */
> + shift = (unsigned long)ptr & 0x3;
> + shift *= BITS_PER_BYTE;
> + mask <<= shift;
> +
> + /*
> + * Calculate a pointer to the naturally aligned 4 byte integer that
> + * includes our byte of interest, and load its value.
> + */
> + ptr32 = (volatile u32 *)((unsigned long)ptr & ~0x3);
> + load32 = *ptr32;
> +
> + while (true) {
> + /*
> + * Ensure the byte we want to exchange matches the expected
> + * old value, and if not then bail.
> + */
> + load = (load32 & mask) >> shift;
> + if (load != old)
> + return load;
> +
> + /*
> + * Calculate the old & new values of the naturally aligned
> + * 4 byte integer that include the byte we want to exchange.
> + * Attempt to exchange the old value for the new value, and
> + * return if we succeed.
> + */
> + old32 = (load32 & ~mask) | (old << shift);
> + new32 = (load32 & ~mask) | (new << shift);
> + load32 = arch_cmpxchg(ptr32, old32, new32);
> + if (load32 == old32)
> + return old;
> + }
This is absolutely terrible, that really wants to be a single ll/sc
loop.
> +}
next prev parent reply other threads:[~2021-10-01 11:05 UTC|newest]
Thread overview: 41+ messages / expand[flat|nested] mbox.gz Atom feed top
2021-09-27 6:42 [PATCH V4 00/22] arch: Add basic LoongArch support Huacai Chen
2021-09-27 6:42 ` [PATCH V4 01/22] Documentation: LoongArch: Add basic documentations Huacai Chen
2021-09-27 6:42 ` [PATCH V4 02/22] Documentation/zh_CN: Add basic LoongArch documentations Huacai Chen
2021-09-27 6:42 ` [PATCH V4 03/22] LoongArch: Add elf-related definitions Huacai Chen
2021-09-27 6:42 ` [PATCH V4 04/22] LoongArch: Add writecombine support for drm Huacai Chen
2021-09-27 6:42 ` [PATCH V4 05/22] LoongArch: Add build infrastructure Huacai Chen
2021-09-27 6:42 ` [PATCH V4 06/22] LoongArch: Add CPU definition headers Huacai Chen
2021-09-30 15:30 ` Xi Ruoyao
2021-10-02 10:49 ` Huacai Chen
2021-09-27 6:42 ` [PATCH V4 07/22] LoongArch: Add atomic/locking headers Huacai Chen
2021-10-01 10:52 ` Peter Zijlstra
2021-10-02 11:47 ` Huacai Chen
2021-10-01 11:04 ` Peter Zijlstra
2021-10-02 11:05 ` Huacai Chen
2021-09-27 6:42 ` [PATCH V4 08/22] LoongArch: Add other common headers Huacai Chen
2021-09-27 6:42 ` [PATCH V4 09/22] LoongArch: Add boot and setup routines Huacai Chen
2021-09-27 6:52 ` Ard Biesheuvel
2021-09-29 3:24 ` Huacai Chen
2021-09-27 6:42 ` [PATCH V4 10/22] LoongArch: Add exception/interrupt handling Huacai Chen
2021-09-27 6:42 ` [PATCH V4 11/22] LoongArch: Add process management Huacai Chen
2021-10-03 2:48 ` Al Viro
2021-10-03 9:10 ` Huacai Chen
2021-09-27 6:42 ` [PATCH V4 12/22] LoongArch: Add memory management Huacai Chen
2021-09-27 6:42 ` [PATCH V4 13/22] LoongArch: Add system call support Huacai Chen
2021-09-27 6:42 ` [PATCH V4 14/22] LoongArch: Add signal handling support Huacai Chen
2021-10-03 2:29 ` Al Viro
2021-10-03 9:09 ` Huacai Chen
2021-09-27 6:42 ` [PATCH V4 15/22] LoongArch: Add elf and module support Huacai Chen
2021-09-27 6:42 ` [PATCH V4 16/22] LoongArch: Add misc common routines Huacai Chen
2021-10-01 11:03 ` Peter Zijlstra [this message]
2021-10-02 10:56 ` Huacai Chen
2021-09-27 6:42 ` [PATCH V4 17/22] LoongArch: Add some library functions Huacai Chen
2021-09-27 6:42 ` [PATCH V4 18/22] LoongArch: Add PCI controller support Huacai Chen
2021-09-27 6:42 ` [PATCH V4 19/22] LoongArch: Add VDSO and VSYSCALL support Huacai Chen
2021-09-30 15:43 ` Xi Ruoyao
2021-10-02 10:53 ` Huacai Chen
2021-10-02 12:13 ` Xi Ruoyao
2021-10-02 12:44 ` Huacai Chen
2021-09-27 6:42 ` [PATCH V4 20/22] LoongArch: Add multi-processor (SMP) support Huacai Chen
2021-09-27 6:42 ` [PATCH V4 21/22] LoongArch: Add Non-Uniform Memory Access (NUMA) support Huacai Chen
2021-09-27 6:42 ` [PATCH V4 22/22] LoongArch: Add Loongson-3 default config file Huacai Chen
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=YVbq/kAZQimL3Vpc@hirez.programming.kicks-ass.net \
--to=peterz@infradead.org \
--cc=airlied@linux.ie \
--cc=akpm@linux-foundation.org \
--cc=arnd@arndb.de \
--cc=chenhuacai@gmail.com \
--cc=chenhuacai@loongson.cn \
--cc=corbet@lwn.net \
--cc=jiaxun.yang@flygoat.com \
--cc=linux-arch@vger.kernel.org \
--cc=linux-doc@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=lixuefeng@loongson.cn \
--cc=luto@kernel.org \
--cc=siyanteng@loongson.cn \
--cc=tglx@linutronix.de \
--cc=torvalds@linux-foundation.org \
/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: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).