linux-kernel - Re: [PATCH v7] hugetlbfs: Extend the definition of hugepages parameter to support node allocation

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: <YVNHIzpmxSotbbBX@kernel.org>
Date:   Tue, 28 Sep 2021 09:47:31 -0700
From:   Mike Rapoport <rppt@...nel.org>
To:     Zhenguo Yao <yaozhenguo1@...il.com>
Cc:     mike.kravetz@...cle.com, mpe@...erman.id.au,
        benh@...nel.crashing.org, paulus@...ba.org, corbet@....net,
        akpm@...ux-foundation.org, yaozhenguo@...com, willy@...radead.org,
        linux-kernel@...r.kernel.org, linux-doc@...r.kernel.org,
        linux-mm@...ck.org
Subject: Re: [PATCH v7] hugetlbfs: Extend the definition of hugepages
 parameter to support node allocation

Hi,

On Mon, Sep 27, 2021 at 06:41:49PM +0800, Zhenguo Yao wrote:
> We can specify the number of hugepages to allocate at boot. But the
> hugepages is balanced in all nodes at present. In some scenarios,
> we only need hugepages in one node. For example: DPDK needs hugepages
> which are in the same node as NIC. if DPDK needs four hugepages of 1G
> size in node1 and system has 16 numa nodes. We must reserve 64 hugepages
> in kernel cmdline. But, only four hugepages are used. The others should
> be free after boot. If the system memory is low(for example: 64G), it will
> be an impossible task. So, Extending hugepages parameter to support
> specifying hugepages at a specific node.
> For example add following parameter:
> 
> hugepagesz=1G hugepages=0:1,1:3
> 
> It will allocate 1 hugepage in node0 and 3 hugepages in node1.
> 
> Signed-off-by: Zhenguo Yao <yaozhenguo1@...il.com>
> ---

...

> diff --git a/arch/powerpc/mm/hugetlbpage.c b/arch/powerpc/mm/hugetlbpage.c
> index 9a75ba078e1b..dd40ce6e7565 100644
> --- a/arch/powerpc/mm/hugetlbpage.c
> +++ b/arch/powerpc/mm/hugetlbpage.c
> @@ -229,17 +229,22 @@ static int __init pseries_alloc_bootmem_huge_page(struct hstate *hstate)
>  	m->hstate = hstate;
>  	return 1;
>  }
> +
> +bool __init node_specific_alloc_support(void)

I'd suggest to namespace this to hugetlb, e.g.

hugetlb_node_alloc_supported()

> +{
> +	return false;
> +}
>  #endif
>  
>  
> -int __init alloc_bootmem_huge_page(struct hstate *h)
> +int __init alloc_bootmem_huge_page(struct hstate *h, int nid)
>  {
>  
>  #ifdef CONFIG_PPC_BOOK3S_64
>  	if (firmware_has_feature(FW_FEATURE_LPAR) && !radix_enabled())
>  		return pseries_alloc_bootmem_huge_page(h);
>  #endif
> -	return __alloc_bootmem_huge_page(h);
> +	return __alloc_bootmem_huge_page(h, nid);
>  }
>  
>  #ifndef CONFIG_PPC_BOOK3S_64

...

> @@ -2868,33 +2869,41 @@ struct page *alloc_huge_page(struct vm_area_struct *vma,
>  	return ERR_PTR(-ENOSPC);
>  }
>  
> -int alloc_bootmem_huge_page(struct hstate *h)
> +int alloc_bootmem_huge_page(struct hstate *h, int nid)
>  	__attribute__ ((weak, alias("__alloc_bootmem_huge_page")));
> -int __alloc_bootmem_huge_page(struct hstate *h)
> +int __alloc_bootmem_huge_page(struct hstate *h, int nid)
>  {
>  	struct huge_bootmem_page *m;
>  	int nr_nodes, node;
>  
> +	if (nid >= nr_online_nodes)
> +		return 0;
> +	/* do node specific alloc */
> +	if (nid != NUMA_NO_NODE) {
> +		m = memblock_alloc_try_nid_raw(huge_page_size(h), huge_page_size(h),
> +				0, MEMBLOCK_ALLOC_ACCESSIBLE, nid);
> +		if (m)
> +			goto found;
> +		else
> +			return 0;

Nit: you could make it a bit simpler with

		if (!m)
			return 0;
		goto found;

> +	}
> +	/* do all node balanced alloc */
>  	for_each_node_mask_to_alloc(h, nr_nodes, node, &node_states[N_MEMORY]) {
> -		void *addr;
> -
> -		addr = memblock_alloc_try_nid_raw(
> +		m = memblock_alloc_try_nid_raw(
>  				huge_page_size(h), huge_page_size(h),
>  				0, MEMBLOCK_ALLOC_ACCESSIBLE, node);
> -		if (addr) {
> -			/*
> -			 * Use the beginning of the huge page to store the
> -			 * huge_bootmem_page struct (until gather_bootmem
> -			 * puts them into the mem_map).
> -			 */
> -			m = addr;
> +		/*
> +		 * Use the beginning of the huge page to store the
> +		 * huge_bootmem_page struct (until gather_bootmem
> +		 * puts them into the mem_map).
> +		 */
> +		if (m)
>  			goto found;
> -		}
> +		else
> +			return 0;

ditto

>  	}
> -	return 0;
>  
>  found:
> -	BUG_ON(!IS_ALIGNED(virt_to_phys(m), huge_page_size(h)));
>  	/* Put them into a private list first because mem_map is not up yet */
>  	INIT_LIST_HEAD(&m->list);
>  	list_add(&m->list, &huge_boot_pages);

-- 
Sincerely yours,
Mike.