Re: [PATCH] mm/slub: disable slab merging in the default configuration

[David Rientjes <rientjes@google.com>]

[-- Attachment #1: Type: text/plain, Size: 5703 bytes --]

On Tue, 27 Jun 2023, Julian Pidancet wrote:

> Make CONFIG_SLAB_MERGE_DEFAULT default to n unless CONFIG_SLUB_TINY is
> enabled. Benefits of slab merging is limited on systems that are not
> memory constrained: the overhead is negligible and evidence of its
> effect on cache hotness is hard to come by.
> 

I don't have an objection to this, I think it makes sense.

When you say overhead here, I assume you're referring to memory footprint?  
Did you happen to have some system-wide numbers for what that looks like 
when running some benchmarks, or even what the slab usage looks like after 
a fresh boot?

> On the other hand, distinguishing allocations into different slabs will
> make attacks that rely on "heap spraying" more difficult to carry out
> with success.
> 
> Take sides with security in the default kernel configuration over
> questionnable performance benefits/memory efficiency.
> 
> Signed-off-by: Julian Pidancet <julian.pidancet@oracle.com>
> ---
> In an attempt to assess the performance impact of disabling slab
> merging, a timed linux kernel compilation test has been conducted first
> using slab_merge, then using slab_nomerge. Both tests started in an
> identical state.  Commodity hardware was used: a laptop with an AMD Ryzen
> 5 3500U CPU, and 16GiB of RAM. The kernel source files were placed on
> an XFS partition because of the extensive use of slab caches in XFS.
> 
> The results are as follows:
> 
>       | slab_merge       | slab_nomerge     |
> ------+------------------+------------------|
> Time  | 489.074 ± 10.334 | 489.975 ± 10.350 |
> Min   |          459.688 |          460.554 |
> Max   |          493.126 |          494.282 |
> 
> The benchmark favors the configuration where merging is disabled, but the
> difference is only ~0.18%, well under statistical significance.
> 

I think this data should be in the changelog itself, as well as any 
numbers to share on the memory footprint differences.

>  .../admin-guide/kernel-parameters.txt         | 29 ++++++++++---------
>  Documentation/mm/slub.rst                     |  5 ++--
>  mm/Kconfig                                    |  6 ++--
>  3 files changed, 21 insertions(+), 19 deletions(-)
> 
> diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt
> index 9e5bab29685f..5fbf6ed3c62e 100644
> --- a/Documentation/admin-guide/kernel-parameters.txt
> +++ b/Documentation/admin-guide/kernel-parameters.txt
> @@ -5652,21 +5652,22 @@
>  
>  	slram=		[HW,MTD]
>  
> -	slab_merge	[MM]
> -			Enable merging of slabs with similar size when the
> -			kernel is built without CONFIG_SLAB_MERGE_DEFAULT.
> -
>  	slab_nomerge	[MM]
> -			Disable merging of slabs with similar size. May be
> -			necessary if there is some reason to distinguish
> -			allocs to different slabs, especially in hardened
> -			environments where the risk of heap overflows and
> -			layout control by attackers can usually be
> -			frustrated by disabling merging. This will reduce
> -			most of the exposure of a heap attack to a single
> -			cache (risks via metadata attacks are mostly
> -			unchanged). Debug options disable merging on their
> -			own.
> +			Disable merging of slabs with similar size when
> +			the kernel is built with CONFIG_SLAB_MERGE_DEFAULT.
> +			Allocations of the same size made in distinct
> +			caches will be placed in separate slabs. In
> +			hardened environment, the risk of heap overflows
> +			and layout control by attackers can usually be
> +			frustrated by disabling merging.
> +
> +	slab_merge	[MM]
> +			Enable merging of slabs with similar size. May be
> +			necessary to reduce overhead or increase cache
> +			hotness of objects, at the cost of increased
> +			exposure in case of a heap attack to a single
> +			cache. (risks via metadata attacks are mostly
> +			unchanged).
>  			For more information see Documentation/mm/slub.rst.
>  
>  	slab_max_order=	[MM, SLAB]
> diff --git a/Documentation/mm/slub.rst b/Documentation/mm/slub.rst
> index be75971532f5..e2549f4a98dd 100644
> --- a/Documentation/mm/slub.rst
> +++ b/Documentation/mm/slub.rst
> @@ -122,8 +122,9 @@ used on the wrong slab.
>  Slab merging
>  ============
>  
> -If no debug options are specified then SLUB may merge similar slabs together
> -in order to reduce overhead and increase cache hotness of objects.
> +If the kernel is built with ``CONFIG_SLAB_MEGE_DEFAULT`` or if ``slab_merge``

s/MEGE/MERGE/

> +is specified on the kernel command line, then SLUB may merge similar slabs
> +together in order to reduce overhead and increase cache hotness of objects.

Specify that this is memory overhead?

>  ``slabinfo -a`` displays which slabs were merged together.
>  
>  Slab validation
> diff --git a/mm/Kconfig b/mm/Kconfig
> index 7672a22647b4..05b0304302d4 100644
> --- a/mm/Kconfig
> +++ b/mm/Kconfig
> @@ -255,7 +255,7 @@ config SLUB_TINY
>  
>  config SLAB_MERGE_DEFAULT
>  	bool "Allow slab caches to be merged"
> -	default y
> +	default n
>  	depends on SLAB || SLUB
>  	help
>  	  For reduced kernel memory fragmentation, slab caches can be
> @@ -264,8 +264,8 @@ config SLAB_MERGE_DEFAULT
>  	  overwrite objects from merged caches (and more easily control
>  	  cache layout), which makes such heap attacks easier to exploit
>  	  by attackers. By keeping caches unmerged, these kinds of exploits
> -	  can usually only damage objects in the same cache. To disable
> -	  merging at runtime, "slab_nomerge" can be passed on the kernel
> +	  can usually only damage objects in the same cache. To enable
> +	  merging at runtime, "slab_merge" can be passed on the kernel
>  	  command line.
>  
>  config SLAB_FREELIST_RANDOM
> -- 
> 2.40.1
> 
>