From: Nick Desaulniers <ndesaulniers@google.com>
To: Brian Gerst <brgerst@gmail.com>
Cc: LKML <linux-kernel@vger.kernel.org>,
"maintainer:X86 ARCHITECTURE (32-BIT AND 64-BIT)"
<x86@kernel.org>, Thomas Gleixner <tglx@linutronix.de>,
Ingo Molnar <mingo@kernel.org>, Borislav Petkov <bp@alien8.de>,
"H . Peter Anvin" <hpa@zytor.com>,
Andy Lutomirski <luto@kernel.org>,
Peter Zijlstra <peterz@infradead.org>
Subject: Re: [PATCH v2 04/10] x86/percpu: Clean up percpu_add_op()
Date: Mon, 1 Jun 2020 13:18:50 -0700 [thread overview]
Message-ID: <CAKwvOdkWGjqLHkZ7TTvROuG=-v9O46ij942DWLCqksjwtTLFfQ@mail.gmail.com> (raw)
In-Reply-To: <20200530221127.459704-5-brgerst@gmail.com>
On Sat, May 30, 2020 at 3:11 PM Brian Gerst <brgerst@gmail.com> wrote:
>
> The core percpu macros already have a switch on the data size, so the switch
> in the x86 code is redundant and produces more dead code.
>
> Also use appropriate types for the width of the instructions. This avoids
> errors when compiling with Clang.
>
> Signed-off-by: Brian Gerst <brgerst@gmail.com>
Reviewed-by: Nick Desaulniers <ndesaulniers@google.com>
> ---
> arch/x86/include/asm/percpu.h | 99 ++++++++---------------------------
> 1 file changed, 22 insertions(+), 77 deletions(-)
>
> diff --git a/arch/x86/include/asm/percpu.h b/arch/x86/include/asm/percpu.h
> index a40d2e055f58..2a24f3c795eb 100644
> --- a/arch/x86/include/asm/percpu.h
> +++ b/arch/x86/include/asm/percpu.h
> @@ -130,64 +130,32 @@ do { \
> : [val] __pcpu_reg_imm_##size(pto_val__)); \
> } while (0)
>
> +#define percpu_unary_op(size, qual, op, _var) \
> +({ \
> + asm qual (__pcpu_op1_##size(op, __percpu_arg([var])) \
> + : [var] "+m" (_var)); \
> +})
> +
> /*
> * Generate a percpu add to memory instruction and optimize code
> * if one is added or subtracted.
> */
> -#define percpu_add_op(qual, var, val) \
> +#define percpu_add_op(size, qual, var, val) \
> do { \
> - typedef typeof(var) pao_T__; \
> const int pao_ID__ = (__builtin_constant_p(val) && \
> ((val) == 1 || (val) == -1)) ? \
> (int)(val) : 0; \
> if (0) { \
> - pao_T__ pao_tmp__; \
> + typeof(var) pao_tmp__; \
> pao_tmp__ = (val); \
> (void)pao_tmp__; \
> } \
> - switch (sizeof(var)) { \
> - case 1: \
> - if (pao_ID__ == 1) \
> - asm qual ("incb "__percpu_arg(0) : "+m" (var)); \
> - else if (pao_ID__ == -1) \
> - asm qual ("decb "__percpu_arg(0) : "+m" (var)); \
> - else \
> - asm qual ("addb %1, "__percpu_arg(0) \
> - : "+m" (var) \
> - : "qi" ((pao_T__)(val))); \
> - break; \
> - case 2: \
> - if (pao_ID__ == 1) \
> - asm qual ("incw "__percpu_arg(0) : "+m" (var)); \
> - else if (pao_ID__ == -1) \
> - asm qual ("decw "__percpu_arg(0) : "+m" (var)); \
> - else \
> - asm qual ("addw %1, "__percpu_arg(0) \
> - : "+m" (var) \
> - : "ri" ((pao_T__)(val))); \
> - break; \
> - case 4: \
> - if (pao_ID__ == 1) \
> - asm qual ("incl "__percpu_arg(0) : "+m" (var)); \
> - else if (pao_ID__ == -1) \
> - asm qual ("decl "__percpu_arg(0) : "+m" (var)); \
> - else \
> - asm qual ("addl %1, "__percpu_arg(0) \
> - : "+m" (var) \
> - : "ri" ((pao_T__)(val))); \
> - break; \
> - case 8: \
> - if (pao_ID__ == 1) \
> - asm qual ("incq "__percpu_arg(0) : "+m" (var)); \
> - else if (pao_ID__ == -1) \
> - asm qual ("decq "__percpu_arg(0) : "+m" (var)); \
> - else \
> - asm qual ("addq %1, "__percpu_arg(0) \
> - : "+m" (var) \
> - : "re" ((pao_T__)(val))); \
> - break; \
> - default: __bad_percpu_size(); \
> - } \
> + if (pao_ID__ == 1) \
> + percpu_unary_op(size, qual, "inc", var); \
> + else if (pao_ID__ == -1) \
> + percpu_unary_op(size, qual, "dec", var); \
> + else \
> + percpu_to_op(size, qual, "add", var, val); \
> } while (0)
>
> #define percpu_from_op(size, qual, op, _var) \
> @@ -228,29 +196,6 @@ do { \
> pfo_ret__; \
> })
>
> -#define percpu_unary_op(qual, op, var) \
> -({ \
> - switch (sizeof(var)) { \
> - case 1: \
> - asm qual (op "b "__percpu_arg(0) \
> - : "+m" (var)); \
> - break; \
> - case 2: \
> - asm qual (op "w "__percpu_arg(0) \
> - : "+m" (var)); \
> - break; \
> - case 4: \
> - asm qual (op "l "__percpu_arg(0) \
> - : "+m" (var)); \
> - break; \
> - case 8: \
> - asm qual (op "q "__percpu_arg(0) \
> - : "+m" (var)); \
> - break; \
> - default: __bad_percpu_size(); \
> - } \
> -})
> -
> /*
> * Add return operation
> */
> @@ -388,9 +333,9 @@ do { \
> #define raw_cpu_write_1(pcp, val) percpu_to_op(1, , "mov", (pcp), val)
> #define raw_cpu_write_2(pcp, val) percpu_to_op(2, , "mov", (pcp), val)
> #define raw_cpu_write_4(pcp, val) percpu_to_op(4, , "mov", (pcp), val)
> -#define raw_cpu_add_1(pcp, val) percpu_add_op(, (pcp), val)
> -#define raw_cpu_add_2(pcp, val) percpu_add_op(, (pcp), val)
> -#define raw_cpu_add_4(pcp, val) percpu_add_op(, (pcp), val)
> +#define raw_cpu_add_1(pcp, val) percpu_add_op(1, , (pcp), val)
> +#define raw_cpu_add_2(pcp, val) percpu_add_op(2, , (pcp), val)
> +#define raw_cpu_add_4(pcp, val) percpu_add_op(4, , (pcp), val)
> #define raw_cpu_and_1(pcp, val) percpu_to_op(1, , "and", (pcp), val)
> #define raw_cpu_and_2(pcp, val) percpu_to_op(2, , "and", (pcp), val)
> #define raw_cpu_and_4(pcp, val) percpu_to_op(4, , "and", (pcp), val)
> @@ -419,9 +364,9 @@ do { \
> #define this_cpu_write_1(pcp, val) percpu_to_op(1, volatile, "mov", (pcp), val)
> #define this_cpu_write_2(pcp, val) percpu_to_op(2, volatile, "mov", (pcp), val)
> #define this_cpu_write_4(pcp, val) percpu_to_op(4, volatile, "mov", (pcp), val)
> -#define this_cpu_add_1(pcp, val) percpu_add_op(volatile, (pcp), val)
> -#define this_cpu_add_2(pcp, val) percpu_add_op(volatile, (pcp), val)
> -#define this_cpu_add_4(pcp, val) percpu_add_op(volatile, (pcp), val)
> +#define this_cpu_add_1(pcp, val) percpu_add_op(1, volatile, (pcp), val)
> +#define this_cpu_add_2(pcp, val) percpu_add_op(2, volatile, (pcp), val)
> +#define this_cpu_add_4(pcp, val) percpu_add_op(4, volatile, (pcp), val)
> #define this_cpu_and_1(pcp, val) percpu_to_op(1, volatile, "and", (pcp), val)
> #define this_cpu_and_2(pcp, val) percpu_to_op(2, volatile, "and", (pcp), val)
> #define this_cpu_and_4(pcp, val) percpu_to_op(4, volatile, "and", (pcp), val)
> @@ -470,7 +415,7 @@ do { \
> #ifdef CONFIG_X86_64
> #define raw_cpu_read_8(pcp) percpu_from_op(8, , "mov", pcp)
> #define raw_cpu_write_8(pcp, val) percpu_to_op(8, , "mov", (pcp), val)
> -#define raw_cpu_add_8(pcp, val) percpu_add_op(, (pcp), val)
> +#define raw_cpu_add_8(pcp, val) percpu_add_op(8, , (pcp), val)
> #define raw_cpu_and_8(pcp, val) percpu_to_op(8, , "and", (pcp), val)
> #define raw_cpu_or_8(pcp, val) percpu_to_op(8, , "or", (pcp), val)
> #define raw_cpu_add_return_8(pcp, val) percpu_add_return_op(, pcp, val)
> @@ -479,7 +424,7 @@ do { \
>
> #define this_cpu_read_8(pcp) percpu_from_op(8, volatile, "mov", pcp)
> #define this_cpu_write_8(pcp, val) percpu_to_op(8, volatile, "mov", (pcp), val)
> -#define this_cpu_add_8(pcp, val) percpu_add_op(volatile, (pcp), val)
> +#define this_cpu_add_8(pcp, val) percpu_add_op(8, volatile, (pcp), val)
> #define this_cpu_and_8(pcp, val) percpu_to_op(8, volatile, "and", (pcp), val)
> #define this_cpu_or_8(pcp, val) percpu_to_op(8, volatile, "or", (pcp), val)
> #define this_cpu_add_return_8(pcp, val) percpu_add_return_op(volatile, pcp, val)
> --
> 2.25.4
>
--
Thanks,
~Nick Desaulniers
next prev parent reply other threads:[~2020-06-01 20:19 UTC|newest]
Thread overview: 32+ messages / expand[flat|nested] mbox.gz Atom feed top
2020-05-30 22:11 [PATCH v2 00/10] x86: Clean up percpu operations Brian Gerst
2020-05-30 22:11 ` [PATCH v2 01/10] x86/percpu: Introduce size abstraction macros Brian Gerst
2020-06-01 20:48 ` Nick Desaulniers
2020-05-30 22:11 ` [PATCH v2 02/10] x86/percpu: Clean up percpu_to_op() Brian Gerst
2020-07-09 10:30 ` Peter Zijlstra
2020-07-10 4:38 ` Brian Gerst
2020-07-10 8:53 ` Peter Zijlstra
2020-07-10 16:56 ` Nick Desaulniers
2020-05-30 22:11 ` [PATCH v2 03/10] x86/percpu: Clean up percpu_from_op() Brian Gerst
2020-05-30 22:11 ` [PATCH v2 04/10] x86/percpu: Clean up percpu_add_op() Brian Gerst
2020-06-01 20:18 ` Nick Desaulniers [this message]
2020-05-30 22:11 ` [PATCH v2 05/10] x86/percpu: Remove "e" constraint from XADD Brian Gerst
2020-06-01 18:50 ` Nick Desaulniers
2020-05-30 22:11 ` [PATCH v2 06/10] x86/percpu: Clean up percpu_add_return_op() Brian Gerst
2020-06-01 19:47 ` Nick Desaulniers
2020-05-30 22:11 ` [PATCH v2 07/10] x86/percpu: Clean up percpu_xchg_op() Brian Gerst
2020-05-30 22:11 ` [PATCH v2 08/10] x86/percpu: Clean up percpu_cmpxchg_op() Brian Gerst
2020-05-30 22:11 ` [PATCH v2 09/10] x86/percpu: Clean up percpu_stable_op() Brian Gerst
2020-06-01 20:43 ` Nick Desaulniers
2020-06-02 14:19 ` Brian Gerst
2020-07-09 10:25 ` Peter Zijlstra
2020-05-30 22:11 ` [PATCH v2 10/10] x86/percpu: Remove unused PER_CPU() macro Brian Gerst
2020-06-01 20:26 ` Nick Desaulniers
2020-06-01 21:00 ` [PATCH v2 00/10] x86: Clean up percpu operations Nick Desaulniers
2020-07-08 19:36 ` Nick Desaulniers
2020-07-09 20:02 ` Nick Desaulniers
2020-07-13 22:24 ` Nick Desaulniers
2020-07-13 22:40 ` Linus Torvalds
2020-07-13 22:58 ` Nick Desaulniers
2020-07-14 0:31 ` Nick Desaulniers
2020-07-14 1:29 ` Linus Torvalds
2020-07-09 10:30 ` 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='CAKwvOdkWGjqLHkZ7TTvROuG=-v9O46ij942DWLCqksjwtTLFfQ@mail.gmail.com' \
--to=ndesaulniers@google.com \
--cc=bp@alien8.de \
--cc=brgerst@gmail.com \
--cc=hpa@zytor.com \
--cc=linux-kernel@vger.kernel.org \
--cc=luto@kernel.org \
--cc=mingo@kernel.org \
--cc=peterz@infradead.org \
--cc=tglx@linutronix.de \
--cc=x86@kernel.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 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.