mm/percpu: conditionally define _shared_alloc_tag via CONFIG_ARCH_MODULE_NEEDS_WEAK_PER_CPU

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.

Link: https://lkml.kernel.org/r/20250618015809.1235761-1-hao.ge@linux.dev
Signed-off-by: Hao Ge <gehao@kylinos.cn>
Suggested-by: Suren Baghdasaryan <surenb@google.com>
Acked-by: Alexander Gordeev <agordeev@linux.ibm.com>	[s390]
Acked-by: Mike Rapoport (Microsoft) <rppt@kernel.org>
Cc: Chistoph Lameter <cl@linux.com>
Cc: Christian Borntraeger <borntraeger@linux.ibm.com>
Cc: David Hildenbrand <david@redhat.com>
Cc: Dennis Zhou <dennis@kernel.org>
Cc: Heiko Carstens <hca@linux.ibm.com>
Cc: Kent Overstreet <kent.overstreet@linux.dev>
Cc: Liam Howlett <liam.howlett@oracle.com>
Cc: Lorenzo Stoakes <lorenzo.stoakes@oracle.com>
Cc: Matt Turner <mattst88@gmail.com>
Cc: Richard Henderson <richard.henderson@linaro.org>
Cc: Sven Schnelle <svens@linux.ibm.com>
Cc: Tejun Heo <tj@kernel.org>
Cc: Vasily Gorbik <gor@linux.ibm.com>
Cc: Vlastimil Babka <vbabka@suse.cz>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>

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

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>
 

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

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

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);

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
+ * Archs which need weak percpu definitions should set
- * ARCH_NEEDS_WEAK_PER_CPU in asm/percpu.h when necessary.
+ * 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)
 /*
  * __pcpu_scope_* dummy variable is used to enforce scope.  It
  * receives the static modifier when it's used in front of

lib/alloc_tag.c

@@ -25,8 +25,10 @@ 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);

mm/Kconfig

@@ -933,6 +933,13 @@ 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
 #