netdev - Re: [PATCH net-next v3] xsk: support use vaddr as ring

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]

Date:   Tue, 14 Feb 2023 15:45:12 +0100
From:   Alexander Lobakin <alexandr.lobakin@...el.com>
To:     Xuan Zhuo <xuanzhuo@...ux.alibaba.com>
CC:     Björn Töpel <bjorn@...nel.org>,
        Magnus Karlsson <magnus.karlsson@...el.com>,
        Maciej Fijalkowski <maciej.fijalkowski@...el.com>,
        Jonathan Lemon <jonathan.lemon@...il.com>,
        "David S. Miller" <davem@...emloft.net>,
        Eric Dumazet <edumazet@...gle.com>,
        Jakub Kicinski <kuba@...nel.org>,
        Paolo Abeni <pabeni@...hat.com>,
        "Alexei Starovoitov" <ast@...nel.org>,
        Daniel Borkmann <daniel@...earbox.net>,
        "Jesper Dangaard Brouer" <hawk@...nel.org>,
        John Fastabend <john.fastabend@...il.com>,
        <bpf@...r.kernel.org>, <netdev@...r.kernel.org>
Subject: Re: [PATCH net-next v3] xsk: support use vaddr as ring

From: Xuan Zhuo <xuanzhuo@...ux.alibaba.com>
Date: Tue, 14 Feb 2023 09:51:12 +0800

> When we try to start AF_XDP on some machines with long running time, due
> to the machine's memory fragmentation problem, there is no sufficient
> contiguous physical memory that will cause the start failure.

[...]

> @@ -1319,13 +1317,10 @@ static int xsk_mmap(struct file *file, struct socket *sock,
>  
>  	/* Matches the smp_wmb() in xsk_init_queue */
>  	smp_rmb();
> -	qpg = virt_to_head_page(q->ring);
> -	if (size > page_size(qpg))
> +	if (size > PAGE_ALIGN(q->ring_size))

You can set q->ring_size as PAGE_ALIGN(size) already at the allocation
to simplify this. I don't see any other places where you use it.

>  		return -EINVAL;
>  
> -	pfn = virt_to_phys(q->ring) >> PAGE_SHIFT;
> -	return remap_pfn_range(vma, vma->vm_start, pfn,
> -			       size, vma->vm_page_prot);
> +	return remap_vmalloc_range(vma, q->ring, 0);
>  }
>  
>  static int xsk_notifier(struct notifier_block *this,
> diff --git a/net/xdp/xsk_queue.c b/net/xdp/xsk_queue.c
> index 6cf9586e5027..247316bdfcbe 100644
> --- a/net/xdp/xsk_queue.c
> +++ b/net/xdp/xsk_queue.c
> @@ -7,6 +7,7 @@
>  #include <linux/slab.h>
>  #include <linux/overflow.h>
>  #include <net/xdp_sock_drv.h>
> +#include <linux/vmalloc.h>

Alphabetic order maybe?

>  
>  #include "xsk_queue.h"
>  
> @@ -23,7 +24,6 @@ static size_t xskq_get_ring_size(struct xsk_queue *q, bool umem_queue)
>  struct xsk_queue *xskq_create(u32 nentries, bool umem_queue)
>  {
>  	struct xsk_queue *q;
> -	gfp_t gfp_flags;
>  	size_t size;
>  
>  	q = kzalloc(sizeof(*q), GFP_KERNEL);
> @@ -33,12 +33,10 @@ struct xsk_queue *xskq_create(u32 nentries, bool umem_queue)
>  	q->nentries = nentries;
>  	q->ring_mask = nentries - 1;
>  
> -	gfp_flags = GFP_KERNEL | __GFP_ZERO | __GFP_NOWARN |
> -		    __GFP_COMP  | __GFP_NORETRY;
>  	size = xskq_get_ring_size(q, umem_queue);
>  
> -	q->ring = (struct xdp_ring *)__get_free_pages(gfp_flags,
> -						      get_order(size));
> +	q->ring_size = size;

Maybe assign size only after successful allocation?

> +	q->ring = (struct xdp_ring *)vmalloc_user(size);

The cast from `void *` is redundant. It was needed for
__get_free_pages() since it returns pointer as long.

>  	if (!q->ring) {
>  		kfree(q);
>  		return NULL;
> @@ -52,6 +50,6 @@ void xskq_destroy(struct xsk_queue *q)
>  	if (!q)
>  		return;
>  
> -	page_frag_free(q->ring);
> +	vfree(q->ring);
>  	kfree(q);
>  }
> diff --git a/net/xdp/xsk_queue.h b/net/xdp/xsk_queue.h
> index c6fb6b763658..35922b8b92a8 100644
> --- a/net/xdp/xsk_queue.h
> +++ b/net/xdp/xsk_queue.h
> @@ -45,6 +45,7 @@ struct xsk_queue {
>  	struct xdp_ring *ring;
>  	u64 invalid_descs;
>  	u64 queue_empty_descs;
> +	size_t ring_size;
>  };
>  
>  /* The structure of the shared state of the rings are a simple
Thanks,
Olek