Re: [PATCH v2 09/10] x86/percpu: Clean up percpu_stable_op()

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 09/10] x86/percpu: Clean up percpu_stable_op()
Date: Mon, 1 Jun 2020 13:43:18 -0700	[thread overview]
Message-ID: <CAKwvOdmgN7xra26_xBYCJo45OdOUHLNmw16ioLOE171f_HE0eA@mail.gmail.com> (raw)
In-Reply-To: <20200530221127.459704-10-brgerst@gmail.com>

On Sat, May 30, 2020 at 3:11 PM Brian Gerst <brgerst@gmail.com> wrote:
>
> Use __pcpu_size_call_return() to simplify this_cpu_read_stable().

Clever! As in this_cpu_read() in include/linux/percpu-defs.h.  Could
be its own patch before this, but it's fine.
Reviewed-by: Nick Desaulniers <ndesaulniers@google.com>

> Also remove __bad_percpu_size() which is now unused.
>
> Signed-off-by: Brian Gerst <brgerst@gmail.com>
> ---
>  arch/x86/include/asm/percpu.h | 41 ++++++++++-------------------------
>  1 file changed, 12 insertions(+), 29 deletions(-)
>
> diff --git a/arch/x86/include/asm/percpu.h b/arch/x86/include/asm/percpu.h
> index 7efc0b5c4ff0..cf2b9c2a241e 100644
> --- a/arch/x86/include/asm/percpu.h
> +++ b/arch/x86/include/asm/percpu.h
> @@ -85,7 +85,6 @@
>
>  /* For arch-specific code, we can use direct single-insn ops (they
>   * don't give an lvalue though). */
> -extern void __bad_percpu_size(void);
>
>  #define __pcpu_type_1 u8
>  #define __pcpu_type_2 u16
> @@ -167,33 +166,13 @@ do {                                                                      \
>         (typeof(_var))(unsigned long) pfo_val__;                        \
>  })
>
> -#define percpu_stable_op(op, var)                      \
> -({                                                     \
> -       typeof(var) pfo_ret__;                          \
> -       switch (sizeof(var)) {                          \
> -       case 1:                                         \
> -               asm(op "b "__percpu_arg(P1)",%0"        \

What does the `P` do here?
https://gcc.gnu.org/onlinedocs/gcc/Simple-Constraints.html#Simple-Constraints
says can be machine dependent integral literal in a certain range.
https://gcc.gnu.org/onlinedocs/gcc/Machine-Constraints.html#Machine-Constraints
doesn't document `P` for x86 though...

> -                   : "=q" (pfo_ret__)                  \
> -                   : "p" (&(var)));                    \
> -               break;                                  \
> -       case 2:                                         \
> -               asm(op "w "__percpu_arg(P1)",%0"        \
> -                   : "=r" (pfo_ret__)                  \
> -                   : "p" (&(var)));                    \
> -               break;                                  \
> -       case 4:                                         \
> -               asm(op "l "__percpu_arg(P1)",%0"        \
> -                   : "=r" (pfo_ret__)                  \
> -                   : "p" (&(var)));                    \
> -               break;                                  \
> -       case 8:                                         \
> -               asm(op "q "__percpu_arg(P1)",%0"        \
> -                   : "=r" (pfo_ret__)                  \
> -                   : "p" (&(var)));                    \
> -               break;                                  \
> -       default: __bad_percpu_size();                   \
> -       }                                               \
> -       pfo_ret__;                                      \
> +#define percpu_stable_op(size, op, _var)                               \
> +({                                                                     \
> +       __pcpu_type_##size pfo_val__;                                   \
> +       asm(__pcpu_op2_##size(op, __percpu_arg(P[var]), "%[val]")       \
> +           : [val] __pcpu_reg_##size("=", pfo_val__)                   \
> +           : [var] "p" (&(_var)));                                     \
> +       (typeof(_var))(unsigned long) pfo_val__;                        \
>  })
>
>  /*
> @@ -258,7 +237,11 @@ do {                                                                       \
>   * per-thread variables implemented as per-cpu variables and thus
>   * stable for the duration of the respective task.
>   */
> -#define this_cpu_read_stable(var)      percpu_stable_op("mov", var)
> +#define this_cpu_read_stable_1(pcp)    percpu_stable_op(1, "mov", pcp)
> +#define this_cpu_read_stable_2(pcp)    percpu_stable_op(2, "mov", pcp)
> +#define this_cpu_read_stable_4(pcp)    percpu_stable_op(4, "mov", pcp)
> +#define this_cpu_read_stable_8(pcp)    percpu_stable_op(8, "mov", pcp)
> +#define this_cpu_read_stable(pcp)      __pcpu_size_call_return(this_cpu_read_stable_, pcp)
>
>  #define raw_cpu_read_1(pcp)            percpu_from_op(1, , "mov", pcp)
>  #define raw_cpu_read_2(pcp)            percpu_from_op(2, , "mov", pcp)
> --
> 2.25.4
>

-- 
Thanks,
~Nick Desaulniers