linux-kernel - Re: [PATCH 1/1] alloc_tag: mark inaccurate allocation counters in /proc/allocinfo output

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] [thread-next>] [day] [month] [year] [list]
Message-ID: <e073e41d-3317-49a9-a2ee-c0e8def66dcd@gmail.com>
Date: Wed, 10 Sep 2025 17:02:37 -0400
From: Usama Arif <usamaarif642@...il.com>
To: Suren Baghdasaryan <surenb@...gle.com>, Vlastimil Babka <vbabka@...e.cz>
Cc: akpm@...ux-foundation.org, kent.overstreet@...ux.dev, hannes@...xchg.org,
 rientjes@...gle.com, roman.gushchin@...ux.dev, harry.yoo@...cle.com,
 shakeel.butt@...ux.dev, 00107082@....com, pasha.tatashin@...een.com,
 souravpanda@...gle.com, linux-mm@...ck.org, linux-kernel@...r.kernel.org
Subject: Re: [PATCH 1/1] alloc_tag: mark inaccurate allocation counters in
 /proc/allocinfo output



On 10/09/2025 15:50, Suren Baghdasaryan wrote:
> On Tue, Sep 9, 2025 at 11:25 PM Vlastimil Babka <vbabka@...e.cz> wrote:
>>
>> On 9/10/25 01:49, Suren Baghdasaryan wrote:
>>> While rare, memory allocation profiling can contain inaccurate counters
>>> if slab object extension vector allocation fails. That allocation might
>>> succeed later but prior to that, slab allocations that would have used
>>> that object extension vector will not be accounted for. To indicate
>>> incorrect counters, mark them with an asterisk in the /proc/allocinfo
>>> output.
>>> Bump up /proc/allocinfo version to reflect change in the file format.
>>
>> Since it's rare, is it worth the trouble?
> 
> Apparently they are seen in Meta's fleet which instigated this thread:
> https://lore.kernel.org/all/17fab2d6-5a74-4573-bcc3-b75951508f0a@gmail.com/
> 

Yes it happens on memory bound services!

>>
>>> Example output with invalid counters:
>>> allocinfo - version: 2.0
>>>            0        0 arch/x86/kernel/kdebugfs.c:105 func:create_setup_data_nodes
>>>            0        0 arch/x86/kernel/alternative.c:2090 func:alternatives_smp_module_add
>>>           0*       0* arch/x86/kernel/alternative.c:127 func:__its_alloc
>>>            0        0 arch/x86/kernel/fpu/regset.c:160 func:xstateregs_set
>>>            0        0 arch/x86/kernel/fpu/xstate.c:1590 func:fpstate_realloc
>>>            0        0 arch/x86/kernel/cpu/aperfmperf.c:379 func:arch_enable_hybrid_capacity_scale
>>>            0        0 arch/x86/kernel/cpu/amd_cache_disable.c:258 func:init_amd_l3_attrs
>>>       49152*      48* arch/x86/kernel/cpu/mce/core.c:2709 func:mce_device_create
>>>        32768        1 arch/x86/kernel/cpu/mce/genpool.c:132 func:mce_gen_pool_create
>>>            0        0 arch/x86/kernel/cpu/mce/amd.c:1341 func:mce_threshold_create_device
>>>
>>> Suggested-by: Johannes Weiner <hannes@...xchg.org>
>>
>> Here a link might have been helpful :)
> 
> Right, here it is and suggestion is in the last paragraph:
> https://lore.kernel.org/all/20250519160846.GA773385@cmpxchg.org/
> 
>>
>>> Signed-off-by: Suren Baghdasaryan <surenb@...gle.com>
>>> ---

Acked-by: Usama Arif <usamaarif642@...il.com>

>>> Patch is based on mm-new.
>>>
>>>  include/linux/alloc_tag.h | 12 ++++++++++++
>>>  include/linux/codetag.h   |  5 ++++-
>>>  lib/alloc_tag.c           |  7 +++++--
>>>  mm/slub.c                 |  2 ++
>>>  4 files changed, 23 insertions(+), 3 deletions(-)
>>>
>>> diff --git a/include/linux/alloc_tag.h b/include/linux/alloc_tag.h
>>> index 9ef2633e2c08..d40ac39bfbe8 100644
>>> --- a/include/linux/alloc_tag.h
>>> +++ b/include/linux/alloc_tag.h
>>> @@ -221,6 +221,16 @@ static inline void alloc_tag_sub(union codetag_ref *ref, size_t bytes)
>>>       ref->ct = NULL;
>>>  }
>>>
>>> +static inline void alloc_tag_set_inaccurate(struct alloc_tag *tag)
>>> +{
>>> +     tag->ct.flags |= CODETAG_FLAG_INACCURATE;
>>> +}
>>> +
>>> +static inline bool alloc_tag_is_inaccurate(struct alloc_tag *tag)
>>> +{
>>> +     return !!(tag->ct.flags & CODETAG_FLAG_INACCURATE);
>>> +}
>>> +
>>>  #define alloc_tag_record(p)  ((p) = current->alloc_tag)
>>>
>>>  #else /* CONFIG_MEM_ALLOC_PROFILING */
>>> @@ -230,6 +240,8 @@ static inline bool mem_alloc_profiling_enabled(void) { return false; }
>>>  static inline void alloc_tag_add(union codetag_ref *ref, struct alloc_tag *tag,
>>>                                size_t bytes) {}
>>>  static inline void alloc_tag_sub(union codetag_ref *ref, size_t bytes) {}
>>> +static inline void alloc_tag_set_inaccurate(struct alloc_tag *tag) {}
>>> +static inline bool alloc_tag_is_inaccurate(struct alloc_tag *tag) { return false; }
>>>  #define alloc_tag_record(p)  do {} while (0)
>>>
>>>  #endif /* CONFIG_MEM_ALLOC_PROFILING */
>>> diff --git a/include/linux/codetag.h b/include/linux/codetag.h
>>> index 457ed8fd3214..8ea2a5f7c98a 100644
>>> --- a/include/linux/codetag.h
>>> +++ b/include/linux/codetag.h
>>> @@ -16,13 +16,16 @@ struct module;
>>>  #define CODETAG_SECTION_START_PREFIX "__start_"
>>>  #define CODETAG_SECTION_STOP_PREFIX  "__stop_"
>>>
>>> +/* codetag flags */
>>> +#define CODETAG_FLAG_INACCURATE      (1 << 0)
>>> +
>>>  /*
>>>   * An instance of this structure is created in a special ELF section at every
>>>   * code location being tagged.  At runtime, the special section is treated as
>>>   * an array of these.
>>>   */
>>>  struct codetag {
>>> -     unsigned int flags; /* used in later patches */
>>> +     unsigned int flags;
>>>       unsigned int lineno;
>>>       const char *modname;
>>>       const char *function;
>>> diff --git a/lib/alloc_tag.c b/lib/alloc_tag.c
>>> index e9b33848700a..a7f15117c759 100644
>>> --- a/lib/alloc_tag.c
>>> +++ b/lib/alloc_tag.c
>>> @@ -80,7 +80,7 @@ static void allocinfo_stop(struct seq_file *m, void *arg)
>>>  static void print_allocinfo_header(struct seq_buf *buf)
>>>  {
>>>       /* Output format version, so we can change it. */
>>> -     seq_buf_printf(buf, "allocinfo - version: 1.0\n");
>>> +     seq_buf_printf(buf, "allocinfo - version: 2.0\n");
>>>       seq_buf_printf(buf, "#     <size>  <calls> <tag info>\n");
>>>  }
>>>
>>> @@ -90,7 +90,10 @@ static void alloc_tag_to_text(struct seq_buf *out, struct codetag *ct)
>>>       struct alloc_tag_counters counter = alloc_tag_read(tag);
>>>       s64 bytes = counter.bytes;
>>>
>>> -     seq_buf_printf(out, "%12lli %8llu ", bytes, counter.calls);
>>> +     if (unlikely(alloc_tag_is_inaccurate(tag)))
>>> +             seq_buf_printf(out, "%11lli* %7llu* ", bytes, counter.calls);
>>> +     else
>>> +             seq_buf_printf(out, "%12lli %8llu ", bytes, counter.calls);
>>>       codetag_to_text(out, ct);
>>>       seq_buf_putc(out, ' ');
>>>       seq_buf_putc(out, '\n');
>>> diff --git a/mm/slub.c b/mm/slub.c
>>> index af343ca570b5..9c04f29ee8de 100644
>>> --- a/mm/slub.c
>>> +++ b/mm/slub.c
>>> @@ -2143,6 +2143,8 @@ __alloc_tagging_slab_alloc_hook(struct kmem_cache *s, void *object, gfp_t flags)
>>>        */
>>>       if (likely(obj_exts))
>>>               alloc_tag_add(&obj_exts->ref, current->alloc_tag, s->size);
>>> +     else
>>> +             alloc_tag_set_inaccurate(current->alloc_tag);
>>>  }
>>>
>>>  static inline void
>>>
>>> base-commit: f4e8f46973fe0c0f579944a37e96ba9efbe00cca
>>