Re: [PATCH 5/5] slab: Allocate and use per-call-site caches

[Xiu Jianfeng]

Hi Kees,

On 2024/8/9 15:33, Kees Cook wrote:
> Use separate per-call-site kmem_cache or kmem_buckets. These are
> allocated on demand to avoid wasting memory for unused caches.
> 
> A few caches need to be allocated very early to support allocating the
> caches themselves: kstrdup(), kvasprintf(), and pcpu_mem_zalloc(). Any
> GFP_ATOMIC allocations are currently left to be allocated from
> KMALLOC_NORMAL.
> 
> With a distro config, /proc/slabinfo grows from ~400 entries to ~2200.
> 
> Since this feature (CONFIG_SLAB_PER_SITE) is redundant to
> CONFIG_RANDOM_KMALLOC_CACHES, mark it a incompatible. Add Kconfig help
> text that compares the features.
> 
> Improvements needed:
> - Retain call site gfp flags in alloc_tag meta field to:
>   - pre-allocate all GFP_ATOMIC caches (since their caches cannot
>     be allocated on demand unless we want them to be GFP_ATOMIC
>     themselves...)
>   - Separate MEMCG allocations as well
> - Allocate individual caches within kmem_buckets on demand to
>   further reduce memory usage overhead.
> 
> Signed-off-by: Kees Cook <kees@xxxxxxxxxx>
> ---
> Cc: Suren Baghdasaryan <surenb@xxxxxxxxxx>
> Cc: Kent Overstreet <kent.overstreet@xxxxxxxxx>
> Cc: Vlastimil Babka <vbabka@xxxxxxx>
> Cc: Christoph Lameter <cl@xxxxxxxxx>
> Cc: Pekka Enberg <penberg@xxxxxxxxxx>
> Cc: David Rientjes <rientjes@xxxxxxxxxx>
> Cc: Joonsoo Kim <iamjoonsoo.kim@xxxxxxx>
> Cc: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
> Cc: Roman Gushchin <roman.gushchin@xxxxxxxxx>
> Cc: Hyeonggon Yoo <42.hyeyoo@xxxxxxxxx>
> Cc: linux-mm@xxxxxxxxx
> ---
>  include/linux/alloc_tag.h |   8 +++
>  lib/alloc_tag.c           | 121 +++++++++++++++++++++++++++++++++++---
>  mm/Kconfig                |  19 +++++-
>  mm/slab_common.c          |   1 +
>  mm/slub.c                 |  31 +++++++++-
>  5 files changed, 170 insertions(+), 10 deletions(-)
> 

[...]

> diff --git a/mm/slub.c b/mm/slub.c
> index 3520acaf9afa..d14102c4b4d7 100644
> --- a/mm/slub.c
> +++ b/mm/slub.c
> @@ -4135,6 +4135,35 @@ void *__kmalloc_large_node_noprof(size_t size, gfp_t flags, int node)
>  }
>  EXPORT_SYMBOL(__kmalloc_large_node_noprof);
>  
> +static __always_inline
> +struct kmem_cache *choose_slab(size_t size, kmem_buckets *b, gfp_t flags,
> +			       unsigned long caller)
> +{
> +#ifdef CONFIG_SLAB_PER_SITE
> +	struct alloc_tag *tag = current->alloc_tag;

There is a compile error here if CONFIG_MEM_ALLOC_PROFILING is disabled
when I test this patchset.

mm/slub.c: In function ‘choose_slab’:
mm/slub.c:4187:40: error: ‘struct task_struct’ has no member named
‘alloc_tag’
 4187 |         struct alloc_tag *tag = current->alloc_tag;
      |                                        ^~
  CC      mm/page_reporting.o

maybe CONFIG_SLAB_PER_SITE should depend on CONFIG_MEM_ALLOC_PROFILING


> +
> +	if (!b && tag && tag->meta.sized &&
> +	    kmalloc_type(flags, caller) == KMALLOC_NORMAL &&
> +	    (flags & GFP_ATOMIC) != GFP_ATOMIC) {
> +		void *p = READ_ONCE(tag->meta.cache);
> +
> +		if (!p && slab_state >= UP) {
> +			alloc_tag_site_init(&tag->ct, true);
> +			p = READ_ONCE(tag->meta.cache);
> +		}
> +
> +		if (tag->meta.sized < SIZE_MAX) {
> +			if (p)
> +				return p;
> +			/* Otherwise continue with default buckets. */
> +		} else {
> +			b = p;
> +		}
> +	}
> +#endif
> +	return kmalloc_slab(size, b, flags, caller);
> +}
> +
>  static __always_inline
>  void *__do_kmalloc_node(size_t size, kmem_buckets *b, gfp_t flags, int node,
>  			unsigned long caller)
> @@ -4152,7 +4181,7 @@ void *__do_kmalloc_node(size_t size, kmem_buckets *b, gfp_t flags, int node,
>  	if (unlikely(!size))
>  		return ZERO_SIZE_PTR;
>  
> -	s = kmalloc_slab(size, b, flags, caller);
> +	s = choose_slab(size, b, flags, caller);
>  
>  	ret = slab_alloc_node(s, NULL, flags, node, caller, size);
>  	ret = kasan_kmalloc(s, ret, size, flags);