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>,
Linus Torvalds <torvalds@linux-foundation.org>,
linux-arch@vger.kernel.org, Xuefeng Li <lixuefeng@loongson.cn>,
Huacai Chen <chenhuacai@gmail.com>,
Jiaxun Yang <jiaxun.yang@flygoat.com>
Subject: Re: [PATCH 17/19] LoongArch: Add multi-processor (SMP) support
Date: Tue, 6 Jul 2021 13:56:42 +0200 [thread overview]
Message-ID: <YORE+uqJzu3sL3Tf@hirez.programming.kicks-ass.net> (raw)
In-Reply-To: <20210706041820.1536502-18-chenhuacai@loongson.cn>
On Tue, Jul 06, 2021 at 12:18:18PM +0800, Huacai Chen wrote:
> diff --git a/arch/loongarch/include/asm/percpu.h b/arch/loongarch/include/asm/percpu.h
> index ea5979872485..ea3c3e7808dc 100644
> --- a/arch/loongarch/include/asm/percpu.h
> +++ b/arch/loongarch/include/asm/percpu.h
> @@ -5,6 +5,8 @@
> #ifndef __ASM_PERCPU_H
> #define __ASM_PERCPU_H
>
> +#include <asm/cmpxchg.h>
> +
> /* Use r21 for fast access */
> register unsigned long __my_cpu_offset __asm__("$r21");
>
> @@ -15,6 +17,181 @@ static inline void set_my_cpu_offset(unsigned long off)
> }
> #define __my_cpu_offset __my_cpu_offset
>
> +#define PERCPU_OP(op, asm_op, c_op) \
> +static inline unsigned long __percpu_##op(void *ptr, \
> + unsigned long val, int size) \
> +{ \
> + unsigned long ret; \
> + \
> + switch (size) { \
> + case 4: \
> + __asm__ __volatile__( \
> + "am"#asm_op".w" " %[ret], %[val], %[ptr] \n" \
> + : [ret] "=&r" (ret), [ptr] "+ZB"(*(u32 *)ptr) \
> + : [val] "r" (val)); \
> + break; \
> + case 8: \
> + __asm__ __volatile__( \
> + "am"#asm_op".d" " %[ret], %[val], %[ptr] \n" \
> + : [ret] "=&r" (ret), [ptr] "+ZB"(*(u64 *)ptr) \
> + : [val] "r" (val)); \
> + break; \
> + default: \
> + ret = 0; \
> + BUILD_BUG(); \
> + } \
> + \
> + return ret c_op val; \
> +}
> +
> +PERCPU_OP(add, add, +)
> +PERCPU_OP(and, and, &)
> +PERCPU_OP(or, or, |)
> +#undef PERCPU_OP
> +
> +static inline unsigned long __percpu_read(void *ptr, int size)
> +{
> + unsigned long ret;
> +
> + switch (size) {
> + case 1:
> + ret = READ_ONCE(*(u8 *)ptr);
> + break;
> + case 2:
> + ret = READ_ONCE(*(u16 *)ptr);
> + break;
> + case 4:
> + ret = READ_ONCE(*(u32 *)ptr);
> + break;
> + case 8:
> + ret = READ_ONCE(*(u64 *)ptr);
> + break;
> + default:
> + ret = 0;
> + BUILD_BUG();
> + }
> +
> + return ret;
> +}
> +
> +static inline void __percpu_write(void *ptr, unsigned long val, int size)
> +{
> + switch (size) {
> + case 1:
> + WRITE_ONCE(*(u8 *)ptr, (u8)val);
> + break;
> + case 2:
> + WRITE_ONCE(*(u16 *)ptr, (u16)val);
> + break;
> + case 4:
> + WRITE_ONCE(*(u32 *)ptr, (u32)val);
> + break;
> + case 8:
> + WRITE_ONCE(*(u64 *)ptr, (u64)val);
> + break;
> + default:
> + BUILD_BUG();
> + }
> +}
> +
> +static inline unsigned long __percpu_xchg(void *ptr, unsigned long val,
> + int size)
> +{
> + switch (size) {
> + case 1:
> + case 2:
> + return __xchg_small((volatile void *)ptr, val, size);
> +
> + case 4:
> + return __xchg_asm("amswap.w", (volatile u32 *)ptr, (u32)val);
> +
> + case 8:
> + if (!IS_ENABLED(CONFIG_64BIT))
> + return __xchg_called_with_bad_pointer();
> +
> + return __xchg_asm("amswap.d", (volatile u64 *)ptr, (u64)val);
> +
> + default:
> + return __xchg_called_with_bad_pointer();
> + }
> +}
> +
> +/* this_cpu_cmpxchg */
> +#define _protect_cmpxchg_local(pcp, o, n) \
> +({ \
> + typeof(*raw_cpu_ptr(&(pcp))) __ret; \
> + __ret = cmpxchg_local(raw_cpu_ptr(&(pcp)), o, n); \
> + __ret; \
> +})
> +
> +#define this_cpu_cmpxchg_1(ptr, o, n) _protect_cmpxchg_local(ptr, o, n)
> +#define this_cpu_cmpxchg_2(ptr, o, n) _protect_cmpxchg_local(ptr, o, n)
> +#define this_cpu_cmpxchg_4(ptr, o, n) _protect_cmpxchg_local(ptr, o, n)
> +#define this_cpu_cmpxchg_8(ptr, o, n) _protect_cmpxchg_local(ptr, o, n)
> +
> +#define _percpu_read(pcp) \
> +({ \
> + typeof(pcp) __retval; \
> + __retval = (typeof(pcp))__percpu_read(raw_cpu_ptr(&(pcp)), \
> + sizeof(pcp)); \
> + __retval; \
> +})
> +
> +#define _percpu_write(pcp, val) \
> +do { \
> + __percpu_write(raw_cpu_ptr(&(pcp)), (unsigned long)(val), \
> + sizeof(pcp)); \
> +} while (0) \
> +
> +#define _pcp_protect(operation, pcp, val) \
> +({ \
> + typeof(pcp) __retval; \
> + __retval = (typeof(pcp))operation(raw_cpu_ptr(&(pcp)), \
> + (val), sizeof(pcp)); \
> + __retval; \
> +})
> +
> +#define _percpu_add(pcp, val) \
> + _pcp_protect(__percpu_add, pcp, val)
> +
> +#define _percpu_add_return(pcp, val) _percpu_add(pcp, val)
> +
> +#define _percpu_and(pcp, val) \
> + _pcp_protect(__percpu_and, pcp, val)
> +
> +#define _percpu_or(pcp, val) \
> + _pcp_protect(__percpu_or, pcp, val)
> +
> +#define _percpu_xchg(pcp, val) ((typeof(pcp)) \
> + _pcp_protect(__percpu_xchg, pcp, (unsigned long)(val)))
> +
> +#define this_cpu_add_4(pcp, val) _percpu_add(pcp, val)
> +#define this_cpu_add_8(pcp, val) _percpu_add(pcp, val)
> +
> +#define this_cpu_add_return_4(pcp, val) _percpu_add_return(pcp, val)
> +#define this_cpu_add_return_8(pcp, val) _percpu_add_return(pcp, val)
> +
> +#define this_cpu_and_4(pcp, val) _percpu_and(pcp, val)
> +#define this_cpu_and_8(pcp, val) _percpu_and(pcp, val)
> +
> +#define this_cpu_or_4(pcp, val) _percpu_or(pcp, val)
> +#define this_cpu_or_8(pcp, val) _percpu_or(pcp, val)
> +
> +#define this_cpu_read_1(pcp) _percpu_read(pcp)
> +#define this_cpu_read_2(pcp) _percpu_read(pcp)
> +#define this_cpu_read_4(pcp) _percpu_read(pcp)
> +#define this_cpu_read_8(pcp) _percpu_read(pcp)
> +
> +#define this_cpu_write_1(pcp, val) _percpu_write(pcp, val)
> +#define this_cpu_write_2(pcp, val) _percpu_write(pcp, val)
> +#define this_cpu_write_4(pcp, val) _percpu_write(pcp, val)
> +#define this_cpu_write_8(pcp, val) _percpu_write(pcp, val)
> +
> +#define this_cpu_xchg_1(pcp, val) _percpu_xchg(pcp, val)
> +#define this_cpu_xchg_2(pcp, val) _percpu_xchg(pcp, val)
> +#define this_cpu_xchg_4(pcp, val) _percpu_xchg(pcp, val)
> +#define this_cpu_xchg_8(pcp, val) _percpu_xchg(pcp, val)
> +
> #include <asm-generic/percpu.h>
>
> #endif /* __ASM_PERCPU_H */
Sadness :-( You could've extended your LL/SC instructions to have an
extra address register like PowerPC does. Then per-cpu can be done like:
1: ll.w %1, %2, r21
...
sc.w %1, %2, r21
bne $zero, %1, 1b
Also AFAICT there is no NMI on this thing (even though you select
HAVE_NMI, I've not found any actual NMI code). So what is the
performance of CSR_CRMD_IE toggles vs using AMOs ?
next prev parent reply other threads:[~2021-07-06 12:34 UTC|newest]
Thread overview: 131+ messages / expand[flat|nested] mbox.gz Atom feed top
2021-07-06 4:18 [PATCH 00/19] arch: Add basic LoongArch support Huacai Chen
2021-07-06 4:18 ` [PATCH 01/19] LoongArch: Add elf-related definitions Huacai Chen
2021-07-06 4:18 ` [PATCH 02/19] LoongArch: Add writecombine support for drm Huacai Chen
2021-07-06 4:18 ` [PATCH 03/19] LoongArch: Add build infrastructure Huacai Chen
2021-07-06 10:12 ` Arnd Bergmann
2021-07-19 1:26 ` Huacai Chen
2021-07-19 7:43 ` Arnd Bergmann
2021-07-19 13:02 ` Huacai Chen
2021-07-06 10:35 ` Arnd Bergmann
2021-07-07 0:00 ` Randy Dunlap
2021-07-19 1:28 ` Huacai Chen
2021-07-06 4:18 ` [PATCH 05/19] LoongArch: Add boot and setup routines Huacai Chen
2021-07-06 10:16 ` Arnd Bergmann
2021-07-27 11:53 ` Huacai Chen
2021-07-27 12:40 ` Arnd Bergmann
2021-07-27 12:51 ` Ard Biesheuvel
2021-07-27 13:14 ` Arnd Bergmann
2021-07-27 16:22 ` Ard Biesheuvel
2021-07-27 17:53 ` Arnd Bergmann
2021-07-28 10:24 ` Huacai Chen
2021-07-06 10:55 ` Arnd Bergmann
2021-07-06 4:18 ` [PATCH 06/19] LoongArch: Add exception/interrupt handling Huacai Chen
2021-07-06 10:16 ` Arnd Bergmann
2021-07-06 10:56 ` Arnd Bergmann
2021-07-06 11:06 ` Peter Zijlstra
2021-07-07 13:56 ` Nicholas Piggin
2021-07-27 14:10 ` Peter Zijlstra
2021-07-27 15:08 ` Arnd Bergmann
2021-07-28 10:16 ` Huacai Chen
2021-07-28 12:23 ` Arnd Bergmann
2021-07-06 4:18 ` [PATCH 07/19] LoongArch: Add process management Huacai Chen
2021-07-06 10:16 ` Arnd Bergmann
2021-07-06 10:57 ` Arnd Bergmann
2021-07-06 11:09 ` Peter Zijlstra
2021-08-12 11:17 ` Huacai Chen
2021-08-12 12:29 ` Arnd Bergmann
2021-08-12 12:51 ` Huacai Chen
2021-07-06 4:18 ` [PATCH 08/19] LoongArch: Add memory management Huacai Chen
2021-07-06 10:16 ` Arnd Bergmann
2021-07-06 10:57 ` Arnd Bergmann
2021-08-12 11:20 ` Huacai Chen
2021-08-16 1:57 ` Guo Ren
2021-08-16 3:31 ` Huacai Chen
2021-07-06 4:18 ` [PATCH 09/19] LoongArch: Add system call support Huacai Chen
2021-07-06 10:17 ` Arnd Bergmann
2021-07-06 10:58 ` Arnd Bergmann
2021-07-07 4:24 ` Huacai Chen
2021-07-07 6:44 ` Arnd Bergmann
2021-07-07 7:00 ` Huacai Chen
2021-07-09 8:44 ` Huacai Chen
2021-07-06 13:51 ` Thomas Gleixner
2021-07-07 4:27 ` Huacai Chen
2021-08-12 12:40 ` Huacai Chen
2021-07-06 4:18 ` [PATCH 10/19] LoongArch: Add signal handling support Huacai Chen
2021-07-06 10:17 ` Arnd Bergmann
2021-07-06 10:59 ` Arnd Bergmann
2021-07-08 13:04 ` Huacai Chen
2021-07-08 13:23 ` Arnd Bergmann
2021-07-09 9:24 ` Huacai Chen
2021-07-09 10:22 ` Arnd Bergmann
2021-07-09 14:49 ` Eric W. Biederman
2021-07-09 15:59 ` Arnd Bergmann
2021-08-26 16:43 ` Xi Ruoyao
2021-08-27 4:23 ` Huacai Chen
2021-08-27 4:27 ` Xi Ruoyao
2021-07-06 4:18 ` [PATCH 11/19] LoongArch: Add elf and module support Huacai Chen
2021-07-06 4:18 ` [PATCH 12/19] LoongArch: Add misc common routines Huacai Chen
2021-07-06 10:17 ` Arnd Bergmann
2021-07-06 11:00 ` Arnd Bergmann
2021-07-23 10:41 ` Huacai Chen
2021-07-23 11:43 ` Arnd Bergmann
2021-07-24 12:53 ` Huacai Chen
2021-07-06 4:18 ` [PATCH 13/19] LoongArch: Add some library functions Huacai Chen
2021-07-06 10:17 ` Arnd Bergmann
2021-07-06 11:00 ` Arnd Bergmann
2021-08-12 11:22 ` Huacai Chen
2021-07-06 4:18 ` [PATCH 14/19] LoongArch: Add 64-bit Loongson platform Huacai Chen
2021-07-06 4:18 ` [PATCH 15/19] LoongArch: Add PCI controller support Huacai Chen
2021-07-06 10:17 ` Arnd Bergmann
2021-07-06 11:01 ` Arnd Bergmann
2021-08-12 11:29 ` Huacai Chen
2021-07-06 4:18 ` [PATCH 16/19] LoongArch: Add VDSO and VSYSCALL support Huacai Chen
2021-07-06 10:17 ` Arnd Bergmann
2021-07-06 11:02 ` Arnd Bergmann
2021-08-12 11:31 ` Huacai Chen
2021-07-06 4:18 ` [PATCH 17/19] LoongArch: Add multi-processor (SMP) support Huacai Chen
2021-07-06 10:17 ` Arnd Bergmann
2021-07-06 11:03 ` Arnd Bergmann
2021-07-06 11:32 ` Peter Zijlstra
2021-08-12 11:39 ` Huacai Chen
2021-07-06 11:56 ` Peter Zijlstra [this message]
2021-07-06 13:48 ` Peter Zijlstra
2021-08-12 11:41 ` Huacai Chen
2021-07-06 13:52 ` Peter Zijlstra
2021-07-06 4:18 ` [PATCH 18/19] LoongArch: Add Non-Uniform Memory Access (NUMA) support Huacai Chen
2021-07-06 10:18 ` Arnd Bergmann
2021-07-06 11:03 ` Arnd Bergmann
2021-08-12 11:46 ` Huacai Chen
2021-08-12 12:48 ` Arnd Bergmann
2021-07-06 4:18 ` [PATCH 19/19] LoongArch: Add Loongson-3 default config file Huacai Chen
2021-07-06 10:18 ` Arnd Bergmann
2021-07-06 11:04 ` Arnd Bergmann
2021-08-12 11:58 ` Huacai Chen
2021-08-12 12:50 ` Arnd Bergmann
2021-07-06 10:11 ` [PATCH 00/19] arch: Add basic LoongArch support Arnd Bergmann
2021-07-07 3:04 ` Huacai Chen
2021-07-07 7:28 ` Arnd Bergmann
2021-07-29 16:48 ` Huacai Chen
2021-07-30 20:50 ` Arnd Bergmann
2021-07-06 10:33 ` Arnd Bergmann
[not found] ` <20210706041820.1536502-5-chenhuacai@loongson.cn>
2021-07-06 10:16 ` [PATCH 04/19] LoongArch: Add common headers Arnd Bergmann
2021-08-12 11:05 ` Huacai Chen
2021-08-12 12:45 ` Arnd Bergmann
2021-08-13 3:30 ` Huacai Chen
2021-08-13 7:05 ` Arnd Bergmann
2021-08-13 8:14 ` Huacai Chen
2021-08-13 9:08 ` Arnd Bergmann
2021-08-14 2:50 ` Huacai Chen
2021-08-15 8:56 ` Arnd Bergmann
2021-08-16 4:10 ` Huacai Chen
2021-08-18 9:38 ` Arnd Bergmann
2021-08-20 4:00 ` Huacai Chen
2021-08-20 7:55 ` Arnd Bergmann
2021-08-21 8:16 ` Huacai Chen
2021-07-06 10:54 ` Arnd Bergmann
2021-07-06 10:57 ` Peter Zijlstra
2021-07-06 11:23 ` Peter Zijlstra
2021-07-06 12:59 ` Arnd Bergmann
2021-07-06 13:20 ` Peter Zijlstra
2021-07-06 13:37 ` Peter Zijlstra
2021-07-06 11:59 ` Peter Zijlstra
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=YORE+uqJzu3sL3Tf@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=jiaxun.yang@flygoat.com \
--cc=linux-arch@vger.kernel.org \
--cc=lixuefeng@loongson.cn \
--cc=luto@kernel.org \
--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).