Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 23.128.96.34 as permitted sender) client-ip=23.128.96.34;
Date:   Tue, 24 Oct 2023 06:46:28 -0700
In-Reply-To: <20231024134637.3120277-1-surenb@google.com>
Mime-Version: 1.0
References: <20231024134637.3120277-1-surenb@google.com>
Message-ID: <20231024134637.3120277-32-surenb@google.com>
Subject: [PATCH v2 31/39] mm: percpu: enable per-cpu allocation tagging
From:   Suren Baghdasaryan <surenb@google.com>
To:     akpm@linux-foundation.org
Cc:     kent.overstreet@linux.dev, mhocko@suse.com, vbabka@suse.cz,
        hannes@cmpxchg.org, roman.gushchin@linux.dev, mgorman@suse.de,
        dave@stgolabs.net, willy@infradead.org, liam.howlett@oracle.com,
        corbet@lwn.net, void@manifault.com, peterz@infradead.org,
        juri.lelli@redhat.com, ldufour@linux.ibm.com,
        catalin.marinas@arm.com, will@kernel.org, arnd@arndb.de,
        tglx@linutronix.de, mingo@redhat.com, dave.hansen@linux.intel.com,
        x86@kernel.org, peterx@redhat.com, david@redhat.com,
        axboe@kernel.dk, mcgrof@kernel.org, masahiroy@kernel.org,
        nathan@kernel.org, dennis@kernel.org, tj@kernel.org,
        muchun.song@linux.dev, rppt@kernel.org, paulmck@kernel.org,
        pasha.tatashin@soleen.com, yosryahmed@google.com,
        yuzhao@google.com, dhowells@redhat.com, hughd@google.com,
        andreyknvl@gmail.com, keescook@chromium.org,
        ndesaulniers@google.com, vvvvvv@google.com,
        gregkh@linuxfoundation.org, ebiggers@google.com, ytcoode@gmail.com,
        vincent.guittot@linaro.org, dietmar.eggemann@arm.com,
        rostedt@goodmis.org, bsegall@google.com, bristot@redhat.com,
        vschneid@redhat.com, cl@linux.com, penberg@kernel.org,
        iamjoonsoo.kim@lge.com, 42.hyeyoo@gmail.com, glider@google.com,
        elver@google.com, dvyukov@google.com, shakeelb@google.com,
        songmuchun@bytedance.com, jbaron@akamai.com, rientjes@google.com,
        minchan@google.com, kaleshsingh@google.com, surenb@google.com,
        kernel-team@android.com, linux-doc@vger.kernel.org,
        linux-kernel@vger.kernel.org, iommu@lists.linux.dev,
        linux-arch@vger.kernel.org, linux-fsdevel@vger.kernel.org,
        linux-mm@kvack.org, linux-modules@vger.kernel.org,
        kasan-dev@googlegroups.com, cgroups@vger.kernel.org
Content-Type: text/plain; charset="UTF-8"
Precedence: bulk

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

Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
Signed-off-by: Suren Baghdasaryan <surenb@google.com>
---
 include/linux/alloc_tag.h | 15 +++++++++
 include/linux/percpu.h    | 23 +++++++++-----
 mm/percpu.c               | 64 +++++----------------------------------
 3 files changed, 38 insertions(+), 64 deletions(-)

diff --git a/include/linux/alloc_tag.h b/include/linux/alloc_tag.h
index 6fa8a94d8bc1..3fe51e67e231 100644
--- a/include/linux/alloc_tag.h
+++ b/include/linux/alloc_tag.h
@@ -140,4 +140,19 @@ static inline void alloc_tag_add(union codetag_ref *ref, struct alloc_tag *tag,
 	_res;								\
 })
 
+/*
+ * workaround for a sparse bug: it complains about res_type_to_err() when
+ * typeof(_do_alloc) is a __percpu pointer, but gcc won't let us add a separate
+ * __percpu case to res_type_to_err():
+ */
+#define alloc_hooks_pcpu(_do_alloc)					\
+({									\
+	typeof(_do_alloc) _res;						\
+	DEFINE_ALLOC_TAG(_alloc_tag, _old);				\
+									\
+	_res = _do_alloc;						\
+	alloc_tag_restore(&_alloc_tag, _old);				\
+	_res;								\
+})
+
 #endif /* _LINUX_ALLOC_TAG_H */
diff --git a/include/linux/percpu.h b/include/linux/percpu.h
index 68fac2e7cbe6..338c1ef9c93d 100644
--- a/include/linux/percpu.h
+++ b/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>
 
@@ -121,7 +123,6 @@ 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);
 
@@ -129,13 +130,15 @@ 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);
 
-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(pcpu_alloc_noprof(_size, _align, false, _gfp))
+#define __alloc_percpu(_size, _align)					\
+	alloc_hooks_pcpu(pcpu_alloc_noprof(_size, _align, false, GFP_KERNEL))
+#define __alloc_reserved_percpu(_size, _align)				\
+	alloc_hooks_pcpu(pcpu_alloc_noprof(_size, _align, true, GFP_KERNEL))
 
 #define alloc_percpu_gfp(type, gfp)					\
 	(typeof(type) __percpu *)__alloc_percpu_gfp(sizeof(type),	\
@@ -144,6 +147,12 @@ 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 */
diff --git a/mm/percpu.c b/mm/percpu.c
index 002ee5d38fd5..328a5b3c943b 100644
--- a/mm/percpu.c
+++ b/mm/percpu.c
@@ -1728,7 +1728,7 @@ static void pcpu_alloc_tag_free_hook(struct pcpu_chunk *chunk, int off, size_t s
 #endif
 
 /**
- * pcpu_alloc - the percpu allocator
+ * pcpu_alloc_noprof - the percpu allocator
  * @size: size of area to allocate in bytes
  * @align: alignment of area (max PAGE_SIZE)
  * @reserved: allocate from the reserved chunk if available
@@ -1742,7 +1742,7 @@ 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;
@@ -1909,6 +1909,8 @@ 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:
@@ -1937,61 +1939,7 @@ 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
@@ -2301,6 +2249,8 @@ void free_percpu(void __percpu *ptr)
 
 	size = pcpu_free_area(chunk, off);
 
+	pcpu_alloc_tag_free_hook(chunk, off, size);
+
 	pcpu_memcg_free_hook(chunk, off, size);
 
 	/*
-- 
2.42.0.758.gaed0368e0e-goog