netdev - Re: [PATCH 1/1] mm: Fix struct page layout on 32-bit systems

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: <20210416190823.3b3aace0@carbon>
Date:   Fri, 16 Apr 2021 19:08:23 +0200
From:   Jesper Dangaard Brouer <brouer@...hat.com>
To:     Matthew Wilcox <willy@...radead.org>
Cc:     David Laight <David.Laight@...lab.com>,
        "linux-kernel@...r.kernel.org" <linux-kernel@...r.kernel.org>,
        "linux-mm@...ck.org" <linux-mm@...ck.org>,
        "netdev@...r.kernel.org" <netdev@...r.kernel.org>,
        "linuxppc-dev@...ts.ozlabs.org" <linuxppc-dev@...ts.ozlabs.org>,
        "linux-arm-kernel@...ts.infradead.org" 
        <linux-arm-kernel@...ts.infradead.org>,
        "linux-mips@...r.kernel.org" <linux-mips@...r.kernel.org>,
        Ilias Apalodimas <ilias.apalodimas@...aro.org>,
        Matteo Croce <mcroce@...ux.microsoft.com>,
        Grygorii Strashko <grygorii.strashko@...com>,
        Arnd Bergmann <arnd@...nel.org>,
        Christoph Hellwig <hch@....de>, brouer@...hat.com
Subject: Re: [PATCH 1/1] mm: Fix struct page layout on 32-bit systems

On Fri, 16 Apr 2021 16:27:55 +0100
Matthew Wilcox <willy@...radead.org> wrote:

> On Thu, Apr 15, 2021 at 08:08:32PM +0200, Jesper Dangaard Brouer wrote:
> > See below patch.  Where I swap32 the dma address to satisfy
> > page->compound having bit zero cleared. (It is the simplest fix I could
> > come up with).  
> 
> I think this is slightly simpler, and as a bonus code that assumes the
> old layout won't compile.

This is clever, I like it!  When reading the code one just have to
remember 'unsigned long' size difference between 64-bit vs 32-bit.
And I assume compiler can optimize the sizeof check out then doable.

> diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h
> index 6613b26a8894..5aacc1c10a45 100644
> --- a/include/linux/mm_types.h
> +++ b/include/linux/mm_types.h
> @@ -97,10 +97,10 @@ struct page {
>  		};
>  		struct {	/* page_pool used by netstack */
>  			/**
> -			 * @dma_addr: might require a 64-bit value even on
> +			 * @dma_addr: might require a 64-bit value on
>  			 * 32-bit architectures.
>  			 */
> -			dma_addr_t dma_addr;
> +			unsigned long dma_addr[2];
>  		};
>  		struct {	/* slab, slob and slub */
>  			union {
> diff --git a/include/net/page_pool.h b/include/net/page_pool.h
> index b5b195305346..db7c7020746a 100644
> --- a/include/net/page_pool.h
> +++ b/include/net/page_pool.h
> @@ -198,7 +198,17 @@ static inline void page_pool_recycle_direct(struct page_pool *pool,
>  
>  static inline dma_addr_t page_pool_get_dma_addr(struct page *page)
>  {
> -	return page->dma_addr;
> +	dma_addr_t ret = page->dma_addr[0];
> +	if (sizeof(dma_addr_t) > sizeof(unsigned long))
> +		ret |= (dma_addr_t)page->dma_addr[1] << 32;
> +	return ret;
> +}
> +
> +static inline void page_pool_set_dma_addr(struct page *page, dma_addr_t addr)
> +{
> +	page->dma_addr[0] = addr;
> +	if (sizeof(dma_addr_t) > sizeof(unsigned long))
> +		page->dma_addr[1] = addr >> 32;
>  }
>  
>  static inline bool is_page_pool_compiled_in(void)
> diff --git a/net/core/page_pool.c b/net/core/page_pool.c
> index ad8b0707af04..f014fd8c19a6 100644
> --- a/net/core/page_pool.c
> +++ b/net/core/page_pool.c
> @@ -174,8 +174,10 @@ static void page_pool_dma_sync_for_device(struct page_pool *pool,
>  					  struct page *page,
>  					  unsigned int dma_sync_size)
>  {
> +	dma_addr_t dma_addr = page_pool_get_dma_addr(page);
> +
>  	dma_sync_size = min(dma_sync_size, pool->p.max_len);
> -	dma_sync_single_range_for_device(pool->p.dev, page->dma_addr,
> +	dma_sync_single_range_for_device(pool->p.dev, dma_addr,
>  					 pool->p.offset, dma_sync_size,
>  					 pool->p.dma_dir);
>  }
> @@ -226,7 +228,7 @@ static struct page *__page_pool_alloc_pages_slow(struct page_pool *pool,
>  		put_page(page);
>  		return NULL;
>  	}
> -	page->dma_addr = dma;
> +	page_pool_set_dma_addr(page, dma);
>  
>  	if (pool->p.flags & PP_FLAG_DMA_SYNC_DEV)
>  		page_pool_dma_sync_for_device(pool, page, pool->p.max_len);
> @@ -294,13 +296,13 @@ void page_pool_release_page(struct page_pool *pool, struct page *page)
>  		 */
>  		goto skip_dma_unmap;
>  
> -	dma = page->dma_addr;
> +	dma = page_pool_get_dma_addr(page);
>  
> -	/* When page is unmapped, it cannot be returned our pool */
> +	/* When page is unmapped, it cannot be returned to our pool */
>  	dma_unmap_page_attrs(pool->p.dev, dma,
>  			     PAGE_SIZE << pool->p.order, pool->p.dma_dir,
>  			     DMA_ATTR_SKIP_CPU_SYNC);
> -	page->dma_addr = 0;
> +	page_pool_set_dma_addr(page, 0);
>  skip_dma_unmap:
>  	/* This may be the last page returned, releasing the pool, so
>  	 * it is not safe to reference pool afterwards.
> 



-- 
Best regards,
  Jesper Dangaard Brouer
  MSc.CS, Principal Kernel Engineer at Red Hat
  LinkedIn: http://www.linkedin.com/in/brouer