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: <CAADnVQJ=bNg9nWQPXGjJ11pZnmjntt=zLBqtJng3328T1L-u0g@mail.gmail.com>
Date: Fri, 31 May 2024 09:43:53 -0700
From: Alexei Starovoitov <alexei.starovoitov@...il.com>
To: Vlastimil Babka <vbabka@...e.cz>
Cc: Akinobu Mita <akinobu.mita@...il.com>, Christoph Lameter <cl@...ux.com>, 
	David Rientjes <rientjes@...gle.com>, Alexei Starovoitov <ast@...nel.org>, 
	Daniel Borkmann <daniel@...earbox.net>, Andrii Nakryiko <andrii@...nel.org>, 
	"Naveen N. Rao" <naveen.n.rao@...ux.ibm.com>, 
	Anil S Keshavamurthy <anil.s.keshavamurthy@...el.com>, "David S. Miller" <davem@...emloft.net>, 
	Masami Hiramatsu <mhiramat@...nel.org>, Steven Rostedt <rostedt@...dmis.org>, 
	Mark Rutland <mark.rutland@....com>, Jiri Olsa <jolsa@...nel.org>, 
	Roman Gushchin <roman.gushchin@...ux.dev>, Hyeonggon Yoo <42.hyeyoo@...il.com>, 
	LKML <linux-kernel@...r.kernel.org>, linux-mm <linux-mm@...ck.org>, 
	bpf <bpf@...r.kernel.org>, 
	linux-trace-kernel <linux-trace-kernel@...r.kernel.org>
Subject: Re: [PATCH RFC 3/4] mm, slab: add static key for should_failslab()

On Fri, May 31, 2024 at 2:33 AM Vlastimil Babka <vbabka@...e.cz> wrote:
>
> Since commit 4f6923fbb352 ("mm: make should_failslab always available for
> fault injection") should_failslab() is unconditionally a noinline
> function. This adds visible overhead to the slab allocation hotpath,
> even if the function is empty. With CONFIG_FAILSLAB=y there's additional
> overhead when the functionality is not enabled by a boot parameter or
> debugfs.
>
> The overhead can be eliminated with a static key around the callsite.
> Fault injection and error injection frameworks can now be told that the
> this function has a static key associated, and are able to enable and
> disable it accordingly.
>
> Signed-off-by: Vlastimil Babka <vbabka@...e.cz>
> ---
>  mm/failslab.c |  2 +-
>  mm/slab.h     |  3 +++
>  mm/slub.c     | 10 +++++++---
>  3 files changed, 11 insertions(+), 4 deletions(-)
>
> diff --git a/mm/failslab.c b/mm/failslab.c
> index ffc420c0e767..878fd08e5dac 100644
> --- a/mm/failslab.c
> +++ b/mm/failslab.c
> @@ -9,7 +9,7 @@ static struct {
>         bool ignore_gfp_reclaim;
>         bool cache_filter;
>  } failslab = {
> -       .attr = FAULT_ATTR_INITIALIZER,
> +       .attr = FAULT_ATTR_INITIALIZER_KEY(&should_failslab_active.key),
>         .ignore_gfp_reclaim = true,
>         .cache_filter = false,
>  };
> diff --git a/mm/slab.h b/mm/slab.h
> index 5f8f47c5bee0..792e19cb37b8 100644
> --- a/mm/slab.h
> +++ b/mm/slab.h
> @@ -11,6 +11,7 @@
>  #include <linux/memcontrol.h>
>  #include <linux/kfence.h>
>  #include <linux/kasan.h>
> +#include <linux/jump_label.h>
>
>  /*
>   * Internal slab definitions
> @@ -160,6 +161,8 @@ static_assert(IS_ALIGNED(offsetof(struct slab, freelist), sizeof(freelist_aba_t)
>   */
>  #define slab_page(s) folio_page(slab_folio(s), 0)
>
> +DECLARE_STATIC_KEY_FALSE(should_failslab_active);
> +
>  /*
>   * If network-based swap is enabled, sl*b must keep track of whether pages
>   * were allocated from pfmemalloc reserves.
> diff --git a/mm/slub.c b/mm/slub.c
> index 0809760cf789..3bb579760a37 100644
> --- a/mm/slub.c
> +++ b/mm/slub.c
> @@ -3874,13 +3874,15 @@ static __always_inline void maybe_wipe_obj_freeptr(struct kmem_cache *s,
>                         0, sizeof(void *));
>  }
>
> +DEFINE_STATIC_KEY_FALSE(should_failslab_active);
> +
>  noinline int should_failslab(struct kmem_cache *s, gfp_t gfpflags)
>  {
>         if (__should_failslab(s, gfpflags))
>                 return -ENOMEM;
>         return 0;
>  }
> -ALLOW_ERROR_INJECTION(should_failslab, ERRNO);
> +ALLOW_ERROR_INJECTION_KEY(should_failslab, ERRNO, &should_failslab_active);
>
>  static __fastpath_inline
>  struct kmem_cache *slab_pre_alloc_hook(struct kmem_cache *s, gfp_t flags)
> @@ -3889,8 +3891,10 @@ struct kmem_cache *slab_pre_alloc_hook(struct kmem_cache *s, gfp_t flags)
>
>         might_alloc(flags);
>
> -       if (unlikely(should_failslab(s, flags)))
> -               return NULL;
> +       if (static_branch_unlikely(&should_failslab_active)) {
> +               if (should_failslab(s, flags))
> +                       return NULL;
> +       }

makes sense.
Acked-by: Alexei Starovoitov <ast@...nel.org>

Do you have any microbenchmark numbers before/after this optimization?

Powered by blists - more mailing lists

Powered by Openwall GNU/*/Linux Powered by OpenVZ