All of lore.kernel.org
 help / color / mirror / Atom feed
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
Subject: [PATCH v2 31/39] mm: percpu: enable per-cpu allocation tagging
Date: Tue, 24 Oct 2023 06:46:28 -0700	[thread overview]
Message-ID: <20231024134637.3120277-32-surenb@google.com> (raw)
In-Reply-To: <20231024134637.3120277-1-surenb@google.com>

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


  parent reply	other threads:[~2023-10-24 13:48 UTC|newest]

Thread overview: 64+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2023-10-24 13:45 [PATCH v2 00/39] Memory allocation profiling Suren Baghdasaryan
2023-10-24 13:45 ` [PATCH v2 01/39] lib/string_helpers: Add flags param to string_get_size() Suren Baghdasaryan
2023-10-24 14:26   ` Andy Shevchenko
2023-10-24 17:08     ` Suren Baghdasaryan
2023-10-24 19:46     ` Kent Overstreet
2023-10-26 13:12       ` Andy Shevchenko
2023-10-26 18:44         ` Kent Overstreet
2023-10-30 20:07           ` Andy Shevchenko
2023-10-30 22:35             ` Kent Overstreet
2023-10-24 13:45 ` [PATCH v2 02/39] scripts/kallysms: Always include __start and __stop symbols Suren Baghdasaryan
2023-10-24 13:46 ` [PATCH v2 03/39] fs: Convert alloc_inode_sb() to a macro Suren Baghdasaryan
2023-10-24 13:46 ` [PATCH v2 04/39] nodemask: Split out include/linux/nodemask_types.h Suren Baghdasaryan
2023-10-24 13:46 ` [PATCH v2 05/39] prandom: Remove unused include Suren Baghdasaryan
2023-10-24 13:46 ` [PATCH v2 06/39] mm: enumerate all gfp flags Suren Baghdasaryan
2023-10-25  5:46   ` Petr Tesařík
2023-10-25 15:28     ` Suren Baghdasaryan
2023-10-28 17:21       ` Petr Tesařík
2023-10-24 13:46 ` [PATCH v2 07/39] mm: introduce slabobj_ext to support slab object extensions Suren Baghdasaryan
2023-10-24 21:35   ` kernel test robot
2023-10-25  4:54   ` kernel test robot
2023-10-24 13:46 ` [PATCH v2 08/39] mm: introduce __GFP_NO_OBJ_EXT flag to selectively prevent slabobj_ext creation Suren Baghdasaryan
2023-10-24 13:46 ` [PATCH v2 09/39] mm/slab: introduce SLAB_NO_OBJ_EXT to avoid obj_ext creation Suren Baghdasaryan
2023-10-24 13:46 ` [PATCH v2 10/39] mm: prevent slabobj_ext allocations for slabobj_ext and kmem_cache objects Suren Baghdasaryan
2023-10-24 13:46 ` [PATCH v2 11/39] slab: objext: introduce objext_flags as extension to page_memcg_data_flags Suren Baghdasaryan
2023-10-24 13:46 ` [PATCH v2 12/39] lib: code tagging framework Suren Baghdasaryan
2023-10-24 13:46 ` [PATCH v2 13/39] lib: code tagging module support Suren Baghdasaryan
2023-10-24 13:46 ` [PATCH v2 14/39] lib: prevent module unloading if memory is not freed Suren Baghdasaryan
2023-10-24 13:46 ` [PATCH v2 15/39] lib: add allocation tagging support for memory allocation profiling Suren Baghdasaryan
2023-10-24 13:46 ` [PATCH v2 16/39] lib: introduce support for page allocation tagging Suren Baghdasaryan
2023-10-24 13:46 ` [PATCH v2 17/39] change alloc_pages name in dma_map_ops to avoid name conflicts Suren Baghdasaryan
2023-10-24 13:46 ` [PATCH v2 18/39] change alloc_pages name in ivpu_bo_ops to avoid conflicts Suren Baghdasaryan
2023-10-24 13:46 ` [PATCH v2 19/39] mm: enable page allocation tagging Suren Baghdasaryan
2023-10-24 13:46 ` [PATCH v2 20/39] mm: create new codetag references during page splitting Suren Baghdasaryan
2023-10-24 13:46 ` [PATCH v2 21/39] mm/page_ext: enable early_page_ext when CONFIG_MEM_ALLOC_PROFILING_DEBUG=y Suren Baghdasaryan
2023-10-24 13:46 ` [PATCH v2 22/39] lib: add codetag reference into slabobj_ext Suren Baghdasaryan
2023-10-24 13:46 ` [PATCH v2 23/39] mm/slab: add allocation accounting into slab allocation and free paths Suren Baghdasaryan
2023-10-24 13:46 ` [PATCH v2 24/39] mm/slab: enable slab allocation tagging for kmalloc and friends Suren Baghdasaryan
2023-10-24 22:40   ` kernel test robot
2023-10-24 13:46 ` [PATCH v2 25/39] mm/slub: Mark slab_free_freelist_hook() __always_inline Suren Baghdasaryan
2023-10-24 13:46 ` [PATCH v2 26/39] mempool: Hook up to memory allocation profiling Suren Baghdasaryan
2023-10-24 23:43   ` kernel test robot
2023-10-24 13:46 ` [PATCH v2 27/39] xfs: Memory allocation profiling fixups Suren Baghdasaryan
2023-10-24 13:46 ` [PATCH v2 28/39] timekeeping: Fix a circular include dependency Suren Baghdasaryan
2023-10-25 17:33   ` Thomas Gleixner
2023-10-26 18:33     ` Suren Baghdasaryan
2023-10-26 23:05       ` Thomas Gleixner
2023-10-26 23:54         ` Kent Overstreet
2023-10-27  6:35           ` Arnd Bergmann
2023-10-27 15:28             ` Nick Desaulniers
2023-10-24 13:46 ` [PATCH v2 29/39] mm: percpu: Introduce pcpuobj_ext Suren Baghdasaryan
2023-10-24 13:46 ` [PATCH v2 30/39] mm: percpu: Add codetag reference into pcpuobj_ext Suren Baghdasaryan
2023-10-24 13:46 ` Suren Baghdasaryan [this message]
2023-10-24 13:46 ` [PATCH v2 32/39] arm64: Fix circular header dependency Suren Baghdasaryan
2023-10-24 13:46 ` [PATCH v2 33/39] mm: vmalloc: Enable memory allocation profiling Suren Baghdasaryan
2023-10-24 17:08   ` kernel test robot
2023-10-25  0:58   ` kernel test robot
2023-10-24 13:46 ` [PATCH v2 34/39] rhashtable: Plumb through alloc tag Suren Baghdasaryan
2023-10-24 13:46 ` [PATCH v2 35/39] lib: add memory allocations report in show_mem() Suren Baghdasaryan
2023-10-24 13:46 ` [PATCH v2 36/39] codetag: debug: skip objext checking when it's for objext itself Suren Baghdasaryan
2023-10-24 13:46 ` [PATCH v2 37/39] codetag: debug: mark codetags for reserved pages as empty Suren Baghdasaryan
2023-10-24 13:46 ` [PATCH v2 38/39] codetag: debug: introduce OBJEXTS_ALLOC_FAIL to mark failed slab_ext allocations Suren Baghdasaryan
2023-10-24 13:46 ` [PATCH v2 39/39] MAINTAINERS: Add entries for code tagging and memory allocation profiling Suren Baghdasaryan
2023-10-24 18:29 ` [PATCH v2 00/39] Memory " Roman Gushchin
2023-10-24 18:38   ` Suren Baghdasaryan

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20231024134637.3120277-32-surenb@google.com \
    --to=surenb@google.com \
    --cc=42.hyeyoo@gmail.com \
    --cc=akpm@linux-foundation.org \
    --cc=andreyknvl@gmail.com \
    --cc=arnd@arndb.de \
    --cc=axboe@kernel.dk \
    --cc=bristot@redhat.com \
    --cc=bsegall@google.com \
    --cc=catalin.marinas@arm.com \
    --cc=cgroups@vger.kernel.org \
    --cc=cl@linux.com \
    --cc=corbet@lwn.net \
    --cc=dave.hansen@linux.intel.com \
    --cc=dave@stgolabs.net \
    --cc=david@redhat.com \
    --cc=dennis@kernel.org \
    --cc=dhowells@redhat.com \
    --cc=dietmar.eggemann@arm.com \
    --cc=dvyukov@google.com \
    --cc=ebiggers@google.com \
    --cc=elver@google.com \
    --cc=glider@google.com \
    --cc=gregkh@linuxfoundation.org \
    --cc=hannes@cmpxchg.org \
    --cc=hughd@google.com \
    --cc=iamjoonsoo.kim@lge.com \
    --cc=iommu@lists.linux.dev \
    --cc=jbaron@akamai.com \
    --cc=juri.lelli@redhat.com \
    --cc=kaleshsingh@google.com \
    --cc=kasan-dev@googlegroups.com \
    --cc=keescook@chromium.org \
    --cc=kent.overstreet@linux.dev \
    --cc=kernel-team@android.com \
    --cc=ldufour@linux.ibm.com \
    --cc=liam.howlett@oracle.com \
    --cc=linux-arch@vger.kernel.org \
    --cc=linux-doc@vger.kernel.org \
    --cc=linux-fsdevel@vger.kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-mm@kvack.org \
    --cc=linux-modules@vger.kernel.org \
    --cc=masahiroy@kernel.org \
    --cc=mcgrof@kernel.org \
    --cc=mgorman@suse.de \
    --cc=mhocko@suse.com \
    --cc=minchan@google.com \
    --cc=mingo@redhat.com \
    --cc=muchun.song@linux.dev \
    --cc=nathan@kernel.org \
    --cc=ndesaulniers@google.com \
    --cc=pasha.tatashin@soleen.com \
    --cc=paulmck@kernel.org \
    --cc=penberg@kernel.org \
    --cc=peterx@redhat.com \
    --cc=peterz@infradead.org \
    --cc=rientjes@google.com \
    --cc=roman.gushchin@linux.dev \
    --cc=rostedt@goodmis.org \
    --cc=rppt@kernel.org \
    --cc=shakeelb@google.com \
    --cc=songmuchun@bytedance.com \
    --cc=tglx@linutronix.de \
    --cc=tj@kernel.org \
    --cc=vbabka@suse.cz \
    --cc=vincent.guittot@linaro.org \
    --cc=void@manifault.com \
    --cc=vschneid@redhat.com \
    --cc=vvvvvv@google.com \
    --cc=will@kernel.org \
    --cc=willy@infradead.org \
    --cc=x86@kernel.org \
    --cc=yosryahmed@google.com \
    --cc=ytcoode@gmail.com \
    --cc=yuzhao@google.com \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.