[<prev] [next>] [<thread-prev] [day] [month] [year] [list]
Message-ID: <31da0378-59be-42fc-a813-be3946d2b504@gmail.com>
Date: Sun, 18 Jan 2026 18:25:46 +0100
From: Uros Bizjak <ubizjak@...il.com>
To: Thomas Gleixner <tglx@...nel.org>, LKML <linux-kernel@...r.kernel.org>
Cc: x86@...nel.org
Subject: Re: [PATCH] x86/percpu: Make CONFIG_USE_X86_SEG_SUPPORT work with
sparse
On 1/18/26 15:45, Thomas Gleixner wrote:
> Now that sparse builds enforce the usage of typeof_unqual() the casts in
> __raw_cpu_read/write() cause sparse to emit tons of false postive
> warnings:
>
> warning: cast removes address space '__percpu' of expression
>
> Address this by annotating the casts with __force.
>
> Reported-by: kernel test robot <lkp@...el.com>
> Signed-off-by: Thomas Gleixner <tglx@...nel.org>
> Closes: https://lore.kernel.org/oe-kbuild-all/202601181733.YZOf9XU3-lkp@intel.com/
> ---
> arch/x86/include/asm/percpu.h | 8 ++++----
> 1 file changed, 4 insertions(+), 4 deletions(-)
>
> --- a/arch/x86/include/asm/percpu.h
> +++ b/arch/x86/include/asm/percpu.h
> @@ -137,12 +137,12 @@
>
> #define __raw_cpu_read(size, qual, pcp) \
> ({ \
> - *(qual __my_cpu_type(pcp) *)__my_cpu_ptr(&(pcp)); \
> + *(qual __my_cpu_type(pcp) * __force)__my_cpu_ptr(&(pcp)); \
> })
>
> -#define __raw_cpu_write(size, qual, pcp, val) \
> -do { \
> - *(qual __my_cpu_type(pcp) *)__my_cpu_ptr(&(pcp)) = (val); \
> +#define __raw_cpu_write(size, qual, pcp, val) \
> +do { \
> + *(qual __my_cpu_type(pcp) * __force)__my_cpu_ptr(&(pcp)) = (val); \
> } while (0)
>
> #define __raw_cpu_read_const(pcp) __raw_cpu_read(, , pcp)
Perhaps these defines can be simplified a bit as:
#define __raw_cpu_read(size, qual, pcp) \
(*(qual __my_cpu_type(pcp) * __force)__my_cpu_ptr(&(pcp)))
#define __raw_cpu_write(size, qual, pcp, val) \
(*(qual __my_cpu_type(pcp) * __force)__my_cpu_ptr(&(pcp)) = (val))
Uros.
Powered by blists - more mailing lists