linux-kernel - Re: [PATCH v5 1/1] mm/percpu: Conditionally define _shared_alloc_tag via CONFIG_ARCH_MODULE_NEEDS_WEAK_PER

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives
Hash Suite: Windows password security audit tool. GUI, reports in PDF.
[<prev] [next>] [<thread-prev] [day] [month] [year] [list]
Message-ID: <CAJuCfpHp-TdXhqLN1rNvN+kYkGsvMeKDN6kpWxVwUM_fOKgfvg@mail.gmail.com>
Date: Tue, 17 Jun 2025 07:12:26 -0700
From: Suren Baghdasaryan <surenb@...gle.com>
To: Hao Ge <hao.ge@...ux.dev>
Cc: Andrew Morton <akpm@...ux-foundation.org>, David Hildenbrand <david@...hat.com>, 
	Lorenzo Stoakes <lorenzo.stoakes@...cle.com>, "Liam R. Howlett" <Liam.Howlett@...cle.com>, 
	Vlastimil Babka <vbabka@...e.cz>, Mike Rapoport <rppt@...nel.org>, 
	Richard Henderson <richard.henderson@...aro.org>, Matt Turner <mattst88@...il.com>, 
	Dennis Zhou <dennis@...nel.org>, Tejun Heo <tj@...nel.org>, Christoph Lameter <cl@...ux.com>, 
	Heiko Carstens <hca@...ux.ibm.com>, Vasily Gorbik <gor@...ux.ibm.com>, 
	Alexander Gordeev <agordeev@...ux.ibm.com>, Christian Borntraeger <borntraeger@...ux.ibm.com>, 
	Sven Schnelle <svens@...ux.ibm.com>, Kent Overstreet <kent.overstreet@...ux.dev>, linux-mm@...ck.org, 
	linux-kernel@...r.kernel.org, linux-alpha@...r.kernel.org, 
	linux-s390@...r.kernel.org, Hao Ge <gehao@...inos.cn>
Subject: Re: [PATCH v5 1/1] mm/percpu: Conditionally define _shared_alloc_tag
 via CONFIG_ARCH_MODULE_NEEDS_WEAK_PER_CPU

On Tue, Jun 17, 2025 at 12:12 AM Hao Ge <hao.ge@...ux.dev> wrote:
>
> From: Hao Ge <gehao@...inos.cn>
>
> Recently discovered this entry while checking kallsyms on ARM64:
> ffff800083e509c0 D _shared_alloc_tag
>
> If ARCH_NEEDS_WEAK_PER_CPU is not defined(it is only defined for
> s390 and alpha architectures), there's no need to statically define
> the percpu variable _shared_alloc_tag.
>
> Therefore, we need to implement isolation for this purpose.
>
> When building the core kernel code for s390 or alpha architectures,
> ARCH_NEEDS_WEAK_PER_CPU remains undefined (as it is gated
> by #if defined(MODULE)). However, when building modules for these
> architectures, the macro is explicitly defined.
>
> Therefore, we remove all instances of ARCH_NEEDS_WEAK_PER_CPU from
> the code and introduced CONFIG_ARCH_MODULE_NEEDS_WEAK_PER_CPU to
> replace the relevant logic. We can now conditionally define the perpcu
> variable _shared_alloc_tag based on CONFIG_ARCH_MODULE_NEEDS_WEAK_PER_CPU.
> This allows architectures (such as s390/alpha) that require weak
> definitions for percpu variables in modules to include the definition,
> while others can omit it via compile-time exclusion.
>
> Suggested-by: Suren Baghdasaryan <surenb@...gle.com>
> Signed-off-by: Hao Ge <gehao@...inos.cn>
> ---
>  arch/alpha/Kconfig              | 1 +
>  arch/alpha/include/asm/percpu.h | 5 ++---
>  arch/s390/Kconfig               | 1 +
>  arch/s390/include/asm/percpu.h  | 5 ++---
>  include/linux/alloc_tag.h       | 6 +++---
>  include/linux/percpu-defs.h     | 7 ++++---
>  lib/alloc_tag.c                 | 2 ++
>  mm/Kconfig                      | 7 +++++++
>  8 files changed, 22 insertions(+), 12 deletions(-)
>
> diff --git a/arch/alpha/Kconfig b/arch/alpha/Kconfig
> index 109a4cddcd13..80367f2cf821 100644
> --- a/arch/alpha/Kconfig
> +++ b/arch/alpha/Kconfig
> @@ -7,6 +7,7 @@ config ALPHA
>         select ARCH_HAS_DMA_OPS if PCI
>         select ARCH_MIGHT_HAVE_PC_PARPORT
>         select ARCH_MIGHT_HAVE_PC_SERIO
> +       select ARCH_MODULE_NEEDS_WEAK_PER_CPU if SMP
>         select ARCH_NO_PREEMPT
>         select ARCH_NO_SG_CHAIN
>         select ARCH_USE_CMPXCHG_LOCKREF
> diff --git a/arch/alpha/include/asm/percpu.h b/arch/alpha/include/asm/percpu.h
> index 6923249f2d49..4383d66341dc 100644
> --- a/arch/alpha/include/asm/percpu.h
> +++ b/arch/alpha/include/asm/percpu.h
> @@ -9,10 +9,9 @@
>   * way above 4G.
>   *
>   * Always use weak definitions for percpu variables in modules.
> + * Therefore, we have enabled CONFIG_ARCH_MODULE_NEEDS_WEAK_PER_CPU
> + * in the Kconfig.
>   */
> -#if defined(MODULE) && defined(CONFIG_SMP)
> -#define ARCH_NEEDS_WEAK_PER_CPU
> -#endif
>
>  #include <asm-generic/percpu.h>
>
> diff --git a/arch/s390/Kconfig b/arch/s390/Kconfig
> index 0c16dc443e2f..b652cb952f31 100644
> --- a/arch/s390/Kconfig
> +++ b/arch/s390/Kconfig
> @@ -132,6 +132,7 @@ config S390
>         select ARCH_INLINE_WRITE_UNLOCK_IRQ
>         select ARCH_INLINE_WRITE_UNLOCK_IRQRESTORE
>         select ARCH_MHP_MEMMAP_ON_MEMORY_ENABLE
> +       select ARCH_MODULE_NEEDS_WEAK_PER_CPU
>         select ARCH_STACKWALK
>         select ARCH_SUPPORTS_ATOMIC_RMW
>         select ARCH_SUPPORTS_DEBUG_PAGEALLOC
> diff --git a/arch/s390/include/asm/percpu.h b/arch/s390/include/asm/percpu.h
> index 84f6b8357b45..96af7d964014 100644
> --- a/arch/s390/include/asm/percpu.h
> +++ b/arch/s390/include/asm/percpu.h
> @@ -16,10 +16,9 @@
>   * For 64 bit module code, the module may be more than 4G above the
>   * per cpu area, use weak definitions to force the compiler to
>   * generate external references.
> + * Therefore, we have enabled CONFIG_ARCH_MODULE_NEEDS_WEAK_PER_CPU
> + * in the Kconfig.
>   */
> -#if defined(MODULE)
> -#define ARCH_NEEDS_WEAK_PER_CPU
> -#endif
>
>  /*
>   * We use a compare-and-swap loop since that uses less cpu cycles than
> diff --git a/include/linux/alloc_tag.h b/include/linux/alloc_tag.h
> index 8f7931eb7d16..9ef2633e2c08 100644
> --- a/include/linux/alloc_tag.h
> +++ b/include/linux/alloc_tag.h
> @@ -88,7 +88,7 @@ static inline struct alloc_tag *ct_to_alloc_tag(struct codetag *ct)
>         return container_of(ct, struct alloc_tag, ct);
>  }
>
> -#ifdef ARCH_NEEDS_WEAK_PER_CPU
> +#if defined(CONFIG_ARCH_MODULE_NEEDS_WEAK_PER_CPU) && defined(MODULE)
>  /*
>   * When percpu variables are required to be defined as weak, static percpu
>   * variables can't be used inside a function (see comments for DECLARE_PER_CPU_SECTION).
> @@ -102,7 +102,7 @@ DECLARE_PER_CPU(struct alloc_tag_counters, _shared_alloc_tag);
>                 .ct = CODE_TAG_INIT,                                            \
>                 .counters = &_shared_alloc_tag };
>
> -#else /* ARCH_NEEDS_WEAK_PER_CPU */
> +#else /* CONFIG_ARCH_MODULE_NEEDS_WEAK_PER_CPU && MODULE */
>
>  #ifdef MODULE
>
> @@ -123,7 +123,7 @@ DECLARE_PER_CPU(struct alloc_tag_counters, _shared_alloc_tag);
>
>  #endif /* MODULE */
>
> -#endif /* ARCH_NEEDS_WEAK_PER_CPU */
> +#endif /* CONFIG_ARCH_MODULE_NEEDS_WEAK_PER_CPU && MODULE */
>
>  DECLARE_STATIC_KEY_MAYBE(CONFIG_MEM_ALLOC_PROFILING_ENABLED_BY_DEFAULT,
>                         mem_alloc_profiling_key);
> diff --git a/include/linux/percpu-defs.h b/include/linux/percpu-defs.h
> index 0aeb0e276a3e..5931fcad9a91 100644
> --- a/include/linux/percpu-defs.h
> +++ b/include/linux/percpu-defs.h
> @@ -63,14 +63,15 @@
>   * 1. The symbol must be globally unique, even the static ones.
>   * 2. Static percpu variables cannot be defined inside a function.
>   *
> - * Archs which need weak percpu definitions should define
> - * ARCH_NEEDS_WEAK_PER_CPU in asm/percpu.h when necessary.
> + * Archs which need weak percpu definitions should set
> + * CONFIG_ARCH_MODULE_NEEDS_WEAK_PER_CPU when necessary.
>   *
>   * To ensure that the generic code observes the above two
>   * restrictions, if CONFIG_DEBUG_FORCE_WEAK_PER_CPU is set weak
>   * definition is used for all cases.
>   */
> -#if defined(ARCH_NEEDS_WEAK_PER_CPU) || defined(CONFIG_DEBUG_FORCE_WEAK_PER_CPU)
> +#if defined(CONFIG_ARCH_MODULE_NEEDS_WEAK_PER_CPU) && defined(MODULE) || \
> +       defined(CONFIG_DEBUG_FORCE_WEAK_PER_CPU)

Please enclose defined(CONFIG_ARCH_MODULE_NEEDS_WEAK_PER_CPU) &&
defined(MODULE) part of the condition in parentheses.

>  /*
>   * __pcpu_scope_* dummy variable is used to enforce scope.  It
>   * receives the static modifier when it's used in front of
> diff --git a/lib/alloc_tag.c b/lib/alloc_tag.c
> index c7f602fa7b23..ab0936ebf38e 100644
> --- a/lib/alloc_tag.c
> +++ b/lib/alloc_tag.c
> @@ -24,8 +24,10 @@ static bool mem_profiling_support;
>
>  static struct codetag_type *alloc_tag_cttype;
>
> +#ifdef CONFIG_ARCH_MODULE_NEEDS_WEAK_PER_CPU
>  DEFINE_PER_CPU(struct alloc_tag_counters, _shared_alloc_tag);
>  EXPORT_SYMBOL(_shared_alloc_tag);
> +#endif
>
>  DEFINE_STATIC_KEY_MAYBE(CONFIG_MEM_ALLOC_PROFILING_ENABLED_BY_DEFAULT,
>                         mem_alloc_profiling_key);
> diff --git a/mm/Kconfig b/mm/Kconfig
> index e113f713b493..00514df3eae4 100644
> --- a/mm/Kconfig
> +++ b/mm/Kconfig
> @@ -929,6 +929,13 @@ config ARCH_SUPPORTS_PUD_PFNMAP
>         def_bool y
>         depends on ARCH_SUPPORTS_HUGE_PFNMAP && HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD
>
> +#
> +# Architectures that always use weak definitions for percpu
> +# variables in modules should set this.
> +#
> +config ARCH_MODULE_NEEDS_WEAK_PER_CPU
> +       bool
> +
>  #
>  # UP and nommu archs use km based percpu allocator
>  #
> --
> 2.25.1
>