mm: percpu: enable per-cpu allocation tagging

Redefine __alloc_percpu, __alloc_percpu_gfp and __alloc_reserved_percpu
to record allocations and deallocations done by these functions.

[surenb@google.com: undo _noprof additions in the documentation]
  Link: https://lkml.kernel.org/r/20240326231453.1206227-6-surenb@google.com
Link: https://lkml.kernel.org/r/20240321163705.3067592-30-surenb@google.comSigned-off-by: Kent Overstreet <kent.overstreet@linux.dev>
Signed-off-by: Suren Baghdasaryan <surenb@google.com>
Tested-by: Kees Cook <keescook@chromium.org>
Cc: Alexander Viro <viro@zeniv.linux.org.uk>
Cc: Alex Gaynor <alex.gaynor@gmail.com>
Cc: Alice Ryhl <aliceryhl@google.com>
Cc: Andreas Hindborg <a.hindborg@samsung.com>
Cc: Benno Lossin <benno.lossin@proton.me>
Cc: "Björn Roy Baron" <bjorn3_gh@protonmail.com>
Cc: Boqun Feng <boqun.feng@gmail.com>
Cc: Christoph Lameter <cl@linux.com>
Cc: Dennis Zhou <dennis@kernel.org>
Cc: Gary Guo <gary@garyguo.net>
Cc: Miguel Ojeda <ojeda@kernel.org>
Cc: Pasha Tatashin <pasha.tatashin@soleen.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Tejun Heo <tj@kernel.org>
Cc: Vlastimil Babka <vbabka@suse.cz>
Cc: Wedson Almeida Filho <wedsonaf@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>

include/linux/percpu.h

@@ -2,6 +2,7 @@
 #ifndef __LINUX_PERCPU_H
 #define __LINUX_PERCPU_H
 
+#include <linux/alloc_tag.h>
 #include <linux/mmdebug.h>
 #include <linux/preempt.h>
 #include <linux/smp.h>
@@ -9,6 +10,7 @@
 #include <linux/pfn.h>
 #include <linux/init.h>
 #include <linux/cleanup.h>
+#include <linux/sched.h>
 
 #include <asm/percpu.h>
 
@@ -125,7 +127,6 @@ extern int __init pcpu_page_first_chunk(size_t reserved_size,
 				pcpu_fc_cpu_to_node_fn_t cpu_to_nd_fn);
 #endif
 
-extern void __percpu *__alloc_reserved_percpu(size_t size, size_t align) __alloc_size(1);
 extern bool __is_kernel_percpu_address(unsigned long addr, unsigned long *can_addr);
 extern bool is_kernel_percpu_address(unsigned long addr);
 
@@ -133,14 +134,16 @@ extern bool is_kernel_percpu_address(unsigned long addr);
 extern void __init setup_per_cpu_areas(void);
 #endif
 
-extern void __percpu *__alloc_percpu_gfp(size_t size, size_t align, gfp_t gfp) __alloc_size(1);
-extern void __percpu *__alloc_percpu(size_t size, size_t align) __alloc_size(1);
-extern void free_percpu(void __percpu *__pdata);
+extern void __percpu *pcpu_alloc_noprof(size_t size, size_t align, bool reserved,
+				   gfp_t gfp) __alloc_size(1);
 extern size_t pcpu_alloc_size(void __percpu *__pdata);
 
-DEFINE_FREE(free_percpu, void __percpu *, free_percpu(_T))
-
-extern phys_addr_t per_cpu_ptr_to_phys(void *addr);
+#define __alloc_percpu_gfp(_size, _align, _gfp)				\
+	alloc_hooks(pcpu_alloc_noprof(_size, _align, false, _gfp))
+#define __alloc_percpu(_size, _align)					\
+	alloc_hooks(pcpu_alloc_noprof(_size, _align, false, GFP_KERNEL))
+#define __alloc_reserved_percpu(_size, _align)				\
+	alloc_hooks(pcpu_alloc_noprof(_size, _align, true, GFP_KERNEL))
 
 #define alloc_percpu_gfp(type, gfp)					\
 	(typeof(type) __percpu *)__alloc_percpu_gfp(sizeof(type),	\
@@ -149,6 +152,12 @@ extern phys_addr_t per_cpu_ptr_to_phys(void *addr);
 	(typeof(type) __percpu *)__alloc_percpu(sizeof(type),		\
 						__alignof__(type))
 
+extern void free_percpu(void __percpu *__pdata);
+
+DEFINE_FREE(free_percpu, void __percpu *, free_percpu(_T))
+
+extern phys_addr_t per_cpu_ptr_to_phys(void *addr);
+
 extern unsigned long pcpu_nr_pages(void);
 
 #endif /* __LINUX_PERCPU_H */

mm/percpu.c

@@ -1740,7 +1740,7 @@ static void pcpu_alloc_tag_free_hook(struct pcpu_chunk *chunk, int off, size_t s
  * RETURNS:
  * Percpu pointer to the allocated area on success, NULL on failure.
  */
-static void __percpu *pcpu_alloc(size_t size, size_t align, bool reserved,
+void __percpu *pcpu_alloc_noprof(size_t size, size_t align, bool reserved,
 				 gfp_t gfp)
 {
 	gfp_t pcpu_gfp;
@@ -1907,6 +1907,8 @@ static void __percpu *pcpu_alloc(size_t size, size_t align, bool reserved,
 
 	pcpu_memcg_post_alloc_hook(objcg, chunk, off, size);
 
+	pcpu_alloc_tag_alloc_hook(chunk, off, size);
+
 	return ptr;
 
 fail_unlock:
@@ -1935,61 +1937,7 @@ static void __percpu *pcpu_alloc(size_t size, size_t align, bool reserved,
 
 	return NULL;
 }
-
-/**
- * __alloc_percpu_gfp - allocate dynamic percpu area
- * @size: size of area to allocate in bytes
- * @align: alignment of area (max PAGE_SIZE)
- * @gfp: allocation flags
- *
- * Allocate zero-filled percpu area of @size bytes aligned at @align.  If
- * @gfp doesn't contain %GFP_KERNEL, the allocation doesn't block and can
- * be called from any context but is a lot more likely to fail. If @gfp
- * has __GFP_NOWARN then no warning will be triggered on invalid or failed
- * allocation requests.
- *
- * RETURNS:
- * Percpu pointer to the allocated area on success, NULL on failure.
- */
-void __percpu *__alloc_percpu_gfp(size_t size, size_t align, gfp_t gfp)
-{
-	return pcpu_alloc(size, align, false, gfp);
-}
-EXPORT_SYMBOL_GPL(__alloc_percpu_gfp);
-
-/**
- * __alloc_percpu - allocate dynamic percpu area
- * @size: size of area to allocate in bytes
- * @align: alignment of area (max PAGE_SIZE)
- *
- * Equivalent to __alloc_percpu_gfp(size, align, %GFP_KERNEL).
- */
-void __percpu *__alloc_percpu(size_t size, size_t align)
-{
-	return pcpu_alloc(size, align, false, GFP_KERNEL);
-}
-EXPORT_SYMBOL_GPL(__alloc_percpu);
-
-/**
- * __alloc_reserved_percpu - allocate reserved percpu area
- * @size: size of area to allocate in bytes
- * @align: alignment of area (max PAGE_SIZE)
- *
- * Allocate zero-filled percpu area of @size bytes aligned at @align
- * from reserved percpu area if arch has set it up; otherwise,
- * allocation is served from the same dynamic area.  Might sleep.
- * Might trigger writeouts.
- *
- * CONTEXT:
- * Does GFP_KERNEL allocation.
- *
- * RETURNS:
- * Percpu pointer to the allocated area on success, NULL on failure.
- */
-void __percpu *__alloc_reserved_percpu(size_t size, size_t align)
-{
-	return pcpu_alloc(size, align, true, GFP_KERNEL);
-}
+EXPORT_SYMBOL_GPL(pcpu_alloc_noprof);
 
 /**
  * pcpu_balance_free - manage the amount of free chunks
@@ -2328,6 +2276,8 @@ void free_percpu(void __percpu *ptr)
 	spin_lock_irqsave(&pcpu_lock, flags);
 	size = pcpu_free_area(chunk, off);
 
+	pcpu_alloc_tag_free_hook(chunk, off, size);
+
 	pcpu_memcg_free_hook(chunk, off, size);
 
 	/*