Re: [Xen-devel] [PATCH v2 1/2] xen/link: Introduce .bss.percpu.page_aligned

[Julien Grall <julien.grall@xxxxxxx>]

Hi Andrew,

On 7/26/19 9:32 PM, Andrew Cooper wrote:
> Future changes are going to need to page align some percpu data.
>
> This means that the percpu area needs suitably aligning in the BSS so CPU0 has
> correctly aligned data.  Shuffle the exact link order of items within the BSS
> to give .bss.percpu.page_aligned appropriate alignment.
>
> In addition, we need to be able to specify an alignment attribute to
> __DEFINE_PER_CPU().  Rework it so the caller passes in all attributes, and
> adjust DEFINE_PER_CPU{,_READ_MOSTLY}() to match.  This has the added bonus
> that it is now possible to grep for .bss.percpu and find all the users.
>
> Finally, introduce DEFINE_PER_CPU_PAGE_ALIGNED() which uses both section and
> alignment attributes.
>
> Signed-off-by: Andrew Cooper <andrew.cooper3@xxxxxxxxxx>
Acked-by: Julien Grall <julien.grall@xxxxxxx>

Cheers,

> ---
> CC: Jan Beulich <JBeulich@xxxxxxxx>
> CC: Wei Liu <wl@xxxxxxx>
> CC: Roger Pau Monné <roger.pau@xxxxxxxxxx>
> CC: Stefano Stabellini <sstabellini@xxxxxxxxxx>
> CC: Julien Grall <julien.grall@xxxxxxx>
> CC: Volodymyr Babchuk <Volodymyr_Babchuk@xxxxxxxx>
>
> v2:
>   * Rework __DEFINE_PER_CPU() to allow for further attributes to be passed.
>   * Specify __aligned(PAGE_SIZE) as part of DEFINE_PER_CPU_PAGE_ALIGNED().
> ---
>   xen/arch/arm/xen.lds.S       |  5 +++--
>   xen/arch/x86/xen.lds.S       |  5 +++--
>   xen/include/asm-arm/percpu.h |  6 ++----
>   xen/include/asm-x86/percpu.h |  6 ++----
>   xen/include/xen/percpu.h     | 10 ++++++++--
>   5 files changed, 18 insertions(+), 14 deletions(-)
>
> diff --git a/xen/arch/arm/xen.lds.S b/xen/arch/arm/xen.lds.S
> index 12c107f45d..07cbdf2543 100644
> --- a/xen/arch/arm/xen.lds.S
> +++ b/xen/arch/arm/xen.lds.S
> @@ -201,14 +201,15 @@ SECTIONS
>          *(.bss.stack_aligned)
>          . = ALIGN(PAGE_SIZE);
>          *(.bss.page_aligned)
> -       *(.bss)
> -       . = ALIGN(SMP_CACHE_BYTES);
>          __per_cpu_start = .;
> +       *(.bss.percpu.page_aligned)
>          *(.bss.percpu)
>          . = ALIGN(SMP_CACHE_BYTES);
>          *(.bss.percpu.read_mostly)
>          . = ALIGN(SMP_CACHE_BYTES);
>          __per_cpu_data_end = .;
> +       *(.bss)
> +       . = ALIGN(SMP_CACHE_BYTES);
>          __bss_end = .;
>     } :text
>     _end = . ;
> diff --git a/xen/arch/x86/xen.lds.S b/xen/arch/x86/xen.lds.S
> index a73139cd29..b8a2ea4259 100644
> --- a/xen/arch/x86/xen.lds.S
> +++ b/xen/arch/x86/xen.lds.S
> @@ -293,14 +293,15 @@ SECTIONS
>          __bss_start = .;
>          *(.bss.stack_aligned)
>          *(.bss.page_aligned*)
> -       *(.bss)
> -       . = ALIGN(SMP_CACHE_BYTES);
>          __per_cpu_start = .;
> +       *(.bss.percpu.page_aligned)
>          *(.bss.percpu)
>          . = ALIGN(SMP_CACHE_BYTES);
>          *(.bss.percpu.read_mostly)
>          . = ALIGN(SMP_CACHE_BYTES);
>          __per_cpu_data_end = .;
> +       *(.bss)
> +       . = ALIGN(SMP_CACHE_BYTES);
>          __bss_end = .;
>     } :text
>     _end = . ;
> diff --git a/xen/include/asm-arm/percpu.h b/xen/include/asm-arm/percpu.h
> index 9584b830d4..264120b192 100644
> --- a/xen/include/asm-arm/percpu.h
> +++ b/xen/include/asm-arm/percpu.h
> @@ -10,10 +10,8 @@ extern char __per_cpu_start[], __per_cpu_data_end[];
>   extern unsigned long __per_cpu_offset[NR_CPUS];
>   void percpu_init_areas(void);
>   
> -/* Separate out the type, so (int[3], foo) works. */
> -#define __DEFINE_PER_CPU(type, name, suffix)                    \
> -    __section(".bss.percpu" #suffix)                            \
> -    __typeof__(type) per_cpu_##name
> +#define __DEFINE_PER_CPU(attr, type, name) \
> +    attr __typeof__(type) per_cpu_ ## name
>   
>   #define per_cpu(var, cpu)  \
>       (*RELOC_HIDE(&per_cpu__##var, __per_cpu_offset[cpu]))
> diff --git a/xen/include/asm-x86/percpu.h b/xen/include/asm-x86/percpu.h
> index ff34dc7897..5b6cef04c4 100644
> --- a/xen/include/asm-x86/percpu.h
> +++ b/xen/include/asm-x86/percpu.h
> @@ -7,10 +7,8 @@ extern unsigned long __per_cpu_offset[NR_CPUS];
>   void percpu_init_areas(void);
>   #endif
>   
> -/* Separate out the type, so (int[3], foo) works. */
> -#define __DEFINE_PER_CPU(type, name, suffix)                    \
> -    __section(".bss.percpu" #suffix)                            \
> -    __typeof__(type) per_cpu_##name
> +#define __DEFINE_PER_CPU(attr, type, name) \
> +    attr __typeof__(type) per_cpu_ ## name
>   
>   /* var is in discarded region: offset to particular copy we want */
>   #define per_cpu(var, cpu)  \
> diff --git a/xen/include/xen/percpu.h b/xen/include/xen/percpu.h
> index aeec5c19d6..71a31cc361 100644
> --- a/xen/include/xen/percpu.h
> +++ b/xen/include/xen/percpu.h
> @@ -9,9 +9,15 @@
>    * The _##name concatenation is being used here to prevent 'name' from getting
>    * macro expanded, while still allowing a per-architecture symbol name prefix.
>    */
> -#define DEFINE_PER_CPU(type, name) __DEFINE_PER_CPU(type, _##name, )
> +#define DEFINE_PER_CPU(type, name) \
> +    __DEFINE_PER_CPU(__section(".bss.percpu"), type, _ ## name)
> +
> +#define DEFINE_PER_CPU_PAGE_ALIGNED(type, name) \
> +    __DEFINE_PER_CPU(__section(".bss.percpu.page_aligned") \
> +                     __aligned(PAGE_SIZE), type, _ ## name)
> +
>   #define DEFINE_PER_CPU_READ_MOSTLY(type, name) \
> -       __DEFINE_PER_CPU(type, _##name, .read_mostly)
> +    __DEFINE_PER_CPU(__section(".bss.percpu.read_mostly"), type, _ ## name)
>   
>   #define get_per_cpu_var(var)  (per_cpu__##var)
>   
--
Julien Grall

_______________________________________________
Xen-devel mailing list
Xen-devel@xxxxxxxxxxxxxxxxxxxx
https://lists.xenproject.org/mailman/listinfo/xen-devel