netdev - Re: [PATCH] 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>] [day] [month] [year] [list]
Message-ID: <20210510183804.05bc134f@linux.microsoft.com>
Date:   Mon, 10 May 2021 18:38:04 +0200
From:   Matteo Croce <mcroce@...ux.microsoft.com>
To:     "Matthew Wilcox (Oracle)" <willy@...radead.org>
Cc:     linux-mm@...ck.org, stable@...r.kernel.org,
        Ilias Apalodimas <ilias.apalodimas@...aro.org>,
        Jesper Dangaard Brouer <brouer@...hat.com>,
        Vlastimil Babka <vbabka@...e.cz>, netdev@...r.kernel.org
Subject: Re: [PATCH] mm: Fix struct page layout on 32-bit systems

On Mon, 10 May 2021 16:32:11 +0100
"Matthew Wilcox (Oracle)" <willy@...radead.org> wrote:

> 32-bit architectures which expect 8-byte alignment for 8-byte integers
> and need 64-bit DMA addresses (arm, mips, ppc) had their struct page
> inadvertently expanded in 2019.  When the dma_addr_t was added, it
> forced the alignment of the union to 8 bytes, which inserted a 4 byte
> gap between 'flags' and the union.
> 
> Fix this by storing the dma_addr_t in one or two adjacent unsigned
> longs. This restores the alignment to that of an unsigned long.  We
> always store the low bits in the first word to prevent the PageTail
> bit from being inadvertently set on a big endian platform.  If that
> happened, get_user_pages_fast() racing against a page which was freed
> and reallocated to the page_pool could dereference a bogus
> compound_head(), which would be hard to trace back to this cause.
> 
> Fixes: c25fff7171be ("mm: add dma_addr_t to struct page")
> Cc: stable@...r.kernel.org
> Signed-off-by: Matthew Wilcox (Oracle) <willy@...radead.org>
> Acked-by: Ilias Apalodimas <ilias.apalodimas@...aro.org>
> Acked-by: Jesper Dangaard Brouer <brouer@...hat.com>
> Acked-by: Vlastimil Babka <vbabka@...e.cz>
> ---
>  include/linux/mm_types.h |  4 ++--
>  include/net/page_pool.h  | 12 +++++++++++-
>  net/core/page_pool.c     | 12 +++++++-----
>  3 files changed, 20 insertions(+), 8 deletions(-)
> 
> 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 6d517a37c18b..b4b6de909c93 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] << 16 << 16;
> +	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] = upper_32_bits(addr);
>  }
>  
>  static inline bool is_page_pool_compiled_in(void)
> diff --git a/net/core/page_pool.c b/net/core/page_pool.c
> index 9ec1aa9640ad..3c4c4c7a0402 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);
>  }
> @@ -195,7 +197,7 @@ static bool page_pool_dma_map(struct page_pool
> *pool, struct page *page) if (dma_mapping_error(pool->p.dev, dma))
>  		return false;
>  
> -	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); @@ -331,13 +333,13 @@ 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.

I rebased the skb recycling series against this change. I have it
running since a few days on a machine (MacchiatoBIN Double shot) which
uses the mvpp2 driver.
No issues so far.

Regards,
-- 
per aspera ad upstream