Re: [PATCH 08/10] mm/slab: Allow dynamic kmalloc() minimum alignment

[Hyeonggon Yoo]

On Tue, Apr 05, 2022 at 02:57:56PM +0100, Catalin Marinas wrote:
> ARCH_KMALLOC_MINALIGN represents the minimum guaranteed kmalloc()
> alignment but an architecture may require a larger run-time alignment.
> Do not create kmalloc caches smaller than arch_kmalloc_minalign().
> 
> Signed-off-by: Catalin Marinas <catalin.marinas@xxxxxxx>
> Cc: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
> ---
>  include/linux/slab.h |  2 ++
>  mm/slab.c            |  6 +-----
>  mm/slab.h            |  2 ++
>  mm/slab_common.c     | 33 +++++++++++++++++++++++----------
>  4 files changed, 28 insertions(+), 15 deletions(-)
> 
> diff --git a/include/linux/slab.h b/include/linux/slab.h
> index d58211bdeceb..2137dba85691 100644
> --- a/include/linux/slab.h
> +++ b/include/linux/slab.h
> @@ -332,6 +332,8 @@ enum kmalloc_cache_type {
>  extern struct kmem_cache *
>  kmalloc_caches[NR_KMALLOC_TYPES][KMALLOC_SHIFT_HIGH + 1];
>  
> +unsigned int arch_kmalloc_minalign(void);
> +
>  /*
>   * Define gfp bits that should not be set for KMALLOC_NORMAL.
>   */
> diff --git a/mm/slab.c b/mm/slab.c
> index b04e40078bdf..4aaeeb9c994d 100644
> --- a/mm/slab.c
> +++ b/mm/slab.c
> @@ -1256,11 +1256,7 @@ void __init kmem_cache_init(void)
>  	 * Initialize the caches that provide memory for the  kmem_cache_node
>  	 * structures first.  Without this, further allocations will bug.
>  	 */
> -	kmalloc_caches[KMALLOC_NORMAL][INDEX_NODE] = create_kmalloc_cache(
> -				kmalloc_info[INDEX_NODE].name[KMALLOC_NORMAL],
> -				kmalloc_info[INDEX_NODE].size,
> -				ARCH_KMALLOC_FLAGS, 0,
> -				kmalloc_info[INDEX_NODE].size);
> +	new_kmalloc_cache(INDEX_NODE, KMALLOC_NORMAL, ARCH_KMALLOC_FLAGS);
>  	slab_state = PARTIAL_NODE;
>  	setup_kmalloc_cache_index_table();
>  
> diff --git a/mm/slab.h b/mm/slab.h
> index fd7ae2024897..e9238406602a 100644
> --- a/mm/slab.h
> +++ b/mm/slab.h
> @@ -283,6 +283,8 @@ int __kmem_cache_create(struct kmem_cache *, slab_flags_t flags);
>  struct kmem_cache *create_kmalloc_cache(const char *name, unsigned int size,
>  			slab_flags_t flags, unsigned int useroffset,
>  			unsigned int usersize);
> +void __init new_kmalloc_cache(int idx, enum kmalloc_cache_type type,
> +			      slab_flags_t flags);
>  extern void create_boot_cache(struct kmem_cache *, const char *name,
>  			unsigned int size, slab_flags_t flags,
>  			unsigned int useroffset, unsigned int usersize);
> diff --git a/mm/slab_common.c b/mm/slab_common.c
> index 6ee64d6208b3..594d8a8a68d0 100644
> --- a/mm/slab_common.c
> +++ b/mm/slab_common.c
> @@ -838,9 +838,18 @@ void __init setup_kmalloc_cache_index_table(void)
>  	}
>  }
>  
> -static void __init
> +unsigned int __weak arch_kmalloc_minalign(void)
> +{
> +	return ARCH_KMALLOC_MINALIGN;
> +}
> +

As ARCH_KMALLOC_ALIGN and arch_kmalloc_minalign() may not be same after
patch 10, I think s/ARCH_KMALLOC_ALIGN/arch_kmalloc_minalign/g
for every user of it would be more correct?

> +void __init
>  new_kmalloc_cache(int idx, enum kmalloc_cache_type type, slab_flags_t flags)
>  {
> +	unsigned int minalign = arch_kmalloc_minalign();
> +	unsigned int aligned_size = kmalloc_info[idx].size;
> +	int aligned_idx = idx;
> +
>  	if (type == KMALLOC_RECLAIM) {
>  		flags |= SLAB_RECLAIM_ACCOUNT;
>  	} else if (IS_ENABLED(CONFIG_MEMCG_KMEM) && (type == KMALLOC_CGROUP)) {
> @@ -851,10 +860,17 @@ new_kmalloc_cache(int idx, enum kmalloc_cache_type type, slab_flags_t flags)
>  		flags |= SLAB_ACCOUNT;
>  	}
>  
> -	kmalloc_caches[type][idx] = create_kmalloc_cache(
> -					kmalloc_info[idx].name[type],
> -					kmalloc_info[idx].size, flags, 0,
> -					kmalloc_info[idx].size);
> +	if (minalign > ARCH_KMALLOC_MINALIGN) {
> +		aligned_size = ALIGN(aligned_size, minalign);
> +		aligned_idx = __kmalloc_index(aligned_size, false);
> +	}
> +
> +	if (!kmalloc_caches[type][aligned_idx])
> +		kmalloc_caches[type][aligned_idx] = create_kmalloc_cache(
> +					kmalloc_info[aligned_idx].name[type],
> +					aligned_size, flags, 0, aligned_size);
> +	if (idx != aligned_idx)
> +		kmalloc_caches[type][idx] = kmalloc_caches[type][aligned_idx];

I would prefer detecting minimum kmalloc size in create_kmalloc_caches()
in runtime instead of changing behavior of new_kmalloc_cache().

>  	/*
>  	 * If CONFIG_MEMCG_KMEM is enabled, disable cache merging for
> @@ -904,11 +920,8 @@ void __init create_kmalloc_caches(slab_flags_t flags)
>  		struct kmem_cache *s = kmalloc_caches[KMALLOC_NORMAL][i];
>  
>  		if (s) {
> -			kmalloc_caches[KMALLOC_DMA][i] = create_kmalloc_cache(
> -				kmalloc_info[i].name[KMALLOC_DMA],
> -				kmalloc_info[i].size,
> -				SLAB_CACHE_DMA | flags, 0,
> -				kmalloc_info[i].size);
> +			new_kmalloc_cache(i, KMALLOC_DMA,
> +					  SLAB_CACHE_DMA | flags);
>  		}
>  	}
>  #endif

-- 
Thank you, You are awesome!
Hyeonggon :-)