Netdev Archive on lore.kernel.org
help / color / mirror / Atom feed
From: Jesper Dangaard Brouer <jbrouer@redhat.com>
To: Yunsheng Lin <linyunsheng@huawei.com>,
	davem@davemloft.net, kuba@kernel.org
Cc: brouer@redhat.com, alexander.duyck@gmail.com,
	linux@armlinux.org.uk, mw@semihalf.com, linuxarm@openeuler.org,
	yisen.zhuang@huawei.com, salil.mehta@huawei.com,
	thomas.petazzoni@bootlin.com, hawk@kernel.org,
	ilias.apalodimas@linaro.org, ast@kernel.org,
	daniel@iogearbox.net, john.fastabend@gmail.com,
	akpm@linux-foundation.org, peterz@infradead.org, will@kernel.org,
	willy@infradead.org, vbabka@suse.cz, fenghua.yu@intel.com,
	guro@fb.com, peterx@redhat.com, feng.tang@intel.com,
	jgg@ziepe.ca, mcroce@microsoft.com, hughd@google.com,
	jonathan.lemon@gmail.com, alobakin@pm.me, willemb@google.com,
	wenxu@ucloud.cn, cong.wang@bytedance.com, haokexin@gmail.com,
	nogikh@google.com, elver@google.com, yhs@fb.com,
	kpsingh@kernel.org, andrii@kernel.org, kafai@fb.com,
	songliubraving@fb.com, netdev@vger.kernel.org,
	linux-kernel@vger.kernel.org, bpf@vger.kernel.org
Subject: Re: [PATCH rfc v5 2/4] page_pool: add interface to manipulate frag count in page pool
Date: Wed, 14 Jul 2021 12:18:44 +0200	[thread overview]
Message-ID: <79d9e41c-6433-efe1-773a-4f5e91e8de0f@redhat.com> (raw)
In-Reply-To: <1626255285-5079-3-git-send-email-linyunsheng@huawei.com>



On 14/07/2021 11.34, Yunsheng Lin wrote:
> As suggested by Alexander, "A DMA mapping should be page
> aligned anyway so the lower 12 bits would be reserved 0",
> so it might make more sense to repurpose the lower 12 bits
> of the dma address to store the frag count for frag page
> support in page pool for 32 bit systems with 64 bit dma,
> which should be rare those days.

Do we have any real driver users with 32-bit arch and 64-bit DMA, that 
want to use this new frag-count system you are adding to page_pool?

This "lower 12-bit use" complicates the code we need to maintain 
forever. My guess is that it is never used, but we need to update and 
maintain it, and it will never be tested.

Why don't you simply reject using page_pool flag PP_FLAG_PAGE_FRAG 
during setup of the page_pool for this case?

  if ((pool->p.flags & PP_FLAG_PAGE_FRAG) &&
      (sizeof(dma_addr_t) > sizeof(unsigned long)))
    goto reject-setup;


> For normal system, the dma_addr[1] in 'struct page' is not
> used, so we can reuse one of the dma_addr for storing frag
> count, which means how many frags this page might be splited
> to.
> 
> The PAGE_POOL_DMA_USE_PP_FRAG_COUNT macro is added to decide
> where to store the frag count, as the "sizeof(dma_addr_t) >
> sizeof(unsigned long)" is false for most systems those days,
> so hopefully the compiler will optimize out the unused code
> for those systems.
> 
> The newly added page_pool_set_frag_count() should be called
> before the page is passed to any user. Otherwise, call the
> newly added page_pool_atomic_sub_frag_count_return().
> 
> Signed-off-by: Yunsheng Lin <linyunsheng@huawei.com>
> ---
>   include/linux/mm_types.h |  8 +++++--
>   include/net/page_pool.h  | 54 ++++++++++++++++++++++++++++++++++++++++++------
>   net/core/page_pool.c     | 10 +++++++++
>   3 files changed, 64 insertions(+), 8 deletions(-)
> 
> diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h
> index d33d97c..82bcbb0 100644
> --- a/include/linux/mm_types.h
> +++ b/include/linux/mm_types.h
> @@ -103,11 +103,15 @@ struct page {
>   			unsigned long pp_magic;
>   			struct page_pool *pp;
>   			unsigned long _pp_mapping_pad;
> +			atomic_long_t pp_frag_count;
>   			/**
>   			 * @dma_addr: might require a 64-bit value on
> -			 * 32-bit architectures.
> +			 * 32-bit architectures, if so, store the lower 32
> +			 * bits in pp_frag_count, and a DMA mapping should
> +			 * be page aligned, so the frag count can be stored
> +			 * in lower 12 bits for 4K page size.
>   			 */
> -			unsigned long dma_addr[2];
> +			unsigned long dma_addr;
>   		};
>   		struct {	/* slab, slob and slub */
>   			union {
> diff --git a/include/net/page_pool.h b/include/net/page_pool.h
> index 8d7744d..ef449c2 100644
> --- a/include/net/page_pool.h
> +++ b/include/net/page_pool.h
> @@ -198,19 +198,61 @@ static inline void page_pool_recycle_direct(struct page_pool *pool,
>   	page_pool_put_full_page(pool, page, true);
>   }
>   
> +#define PAGE_POOL_DMA_USE_PP_FRAG_COUNT	\
> +			(sizeof(dma_addr_t) > sizeof(unsigned long))
> +
>   static inline dma_addr_t page_pool_get_dma_addr(struct page *page)
>   {
> -	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;
> +	dma_addr_t ret = page->dma_addr;
> +
> +	if (PAGE_POOL_DMA_USE_PP_FRAG_COUNT) {
> +		ret <<= 32;
> +		ret |= atomic_long_read(&page->pp_frag_count) & PAGE_MASK;
> +	}
> +
>   	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);
> +	if (PAGE_POOL_DMA_USE_PP_FRAG_COUNT) {
> +		atomic_long_set(&page->pp_frag_count, addr & PAGE_MASK);
> +		addr >>= 32;
> +	}
> +
> +	page->dma_addr = addr;
> +}
> +
> +static inline long page_pool_atomic_sub_frag_count_return(struct page *page,
> +							  long nr)
> +{
> +	long frag_count = atomic_long_read(&page->pp_frag_count);
> +	long ret;
> +
> +	if (PAGE_POOL_DMA_USE_PP_FRAG_COUNT) {
> +		if ((frag_count & ~PAGE_MASK) == nr)
> +			return 0;
> +
> +		ret = atomic_long_sub_return(nr, &page->pp_frag_count);
> +		WARN_ON((ret & PAGE_MASK) != (frag_count & PAGE_MASK));
> +		ret &= ~PAGE_MASK;
> +	} else {
> +		if (frag_count == nr)
> +			return 0;
> +
> +		ret = atomic_long_sub_return(nr, &page->pp_frag_count);
> +		WARN_ON(ret < 0);
> +	}
> +
> +	return ret;
> +}
> +
> +static inline void page_pool_set_frag_count(struct page *page, long nr)
> +{
> +	if (PAGE_POOL_DMA_USE_PP_FRAG_COUNT)
> +		nr |= atomic_long_read(&page->pp_frag_count) & PAGE_MASK;
> +
> +	atomic_long_set(&page->pp_frag_count, nr);
>   }
>   
>   static inline bool is_page_pool_compiled_in(void)
> diff --git a/net/core/page_pool.c b/net/core/page_pool.c
> index 78838c6..0082f33 100644
> --- a/net/core/page_pool.c
> +++ b/net/core/page_pool.c
> @@ -198,6 +198,16 @@ static bool page_pool_dma_map(struct page_pool *pool, struct page *page)
>   	if (dma_mapping_error(pool->p.dev, dma))
>   		return false;
>   
> +	if (PAGE_POOL_DMA_USE_PP_FRAG_COUNT &&
> +	    WARN_ON(pool->p.flags & PP_FLAG_PAGE_FRAG &&
> +		    dma & ~PAGE_MASK)) {
> +		dma_unmap_page_attrs(pool->p.dev, dma,
> +				     PAGE_SIZE << pool->p.order,
> +				     pool->p.dma_dir,
> +				     DMA_ATTR_SKIP_CPU_SYNC);
> +		return false;
> +	}
> +
>   	page_pool_set_dma_addr(page, dma);
>   
>   	if (pool->p.flags & PP_FLAG_DMA_SYNC_DEV)
> 


  reply	other threads:[~2021-07-14 10:18 UTC|newest]

Thread overview: 9+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2021-07-14  9:34 [PATCH rfc v5 0/4] add frag page support " Yunsheng Lin
2021-07-14  9:34 ` [PATCH rfc v5 1/4] page_pool: keep pp info as long as page pool owns the page Yunsheng Lin
2021-07-14  9:34 ` [PATCH rfc v5 2/4] page_pool: add interface to manipulate frag count in page pool Yunsheng Lin
2021-07-14 10:18   ` Jesper Dangaard Brouer [this message]
2021-07-14 10:28     ` Ilias Apalodimas
2021-07-14 14:46     ` Alexander Duyck
2021-07-15  3:49       ` Yunsheng Lin
2021-07-14  9:34 ` [PATCH rfc v5 3/4] page_pool: add frag page recycling support " Yunsheng Lin
2021-07-14  9:34 ` [PATCH rfc v5 4/4] net: hns3: support skb's frag page recycling based on " Yunsheng Lin

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=79d9e41c-6433-efe1-773a-4f5e91e8de0f@redhat.com \
    --to=jbrouer@redhat.com \
    --cc=akpm@linux-foundation.org \
    --cc=alexander.duyck@gmail.com \
    --cc=alobakin@pm.me \
    --cc=andrii@kernel.org \
    --cc=ast@kernel.org \
    --cc=bpf@vger.kernel.org \
    --cc=brouer@redhat.com \
    --cc=cong.wang@bytedance.com \
    --cc=daniel@iogearbox.net \
    --cc=davem@davemloft.net \
    --cc=elver@google.com \
    --cc=feng.tang@intel.com \
    --cc=fenghua.yu@intel.com \
    --cc=guro@fb.com \
    --cc=haokexin@gmail.com \
    --cc=hawk@kernel.org \
    --cc=hughd@google.com \
    --cc=ilias.apalodimas@linaro.org \
    --cc=jgg@ziepe.ca \
    --cc=john.fastabend@gmail.com \
    --cc=jonathan.lemon@gmail.com \
    --cc=kafai@fb.com \
    --cc=kpsingh@kernel.org \
    --cc=kuba@kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux@armlinux.org.uk \
    --cc=linuxarm@openeuler.org \
    --cc=linyunsheng@huawei.com \
    --cc=mcroce@microsoft.com \
    --cc=mw@semihalf.com \
    --cc=netdev@vger.kernel.org \
    --cc=nogikh@google.com \
    --cc=peterx@redhat.com \
    --cc=peterz@infradead.org \
    --cc=salil.mehta@huawei.com \
    --cc=songliubraving@fb.com \
    --cc=thomas.petazzoni@bootlin.com \
    --cc=vbabka@suse.cz \
    --cc=wenxu@ucloud.cn \
    --cc=will@kernel.org \
    --cc=willemb@google.com \
    --cc=willy@infradead.org \
    --cc=yhs@fb.com \
    --cc=yisen.zhuang@huawei.com \
    --subject='Re: [PATCH rfc v5 2/4] page_pool: add interface to manipulate frag count in page pool' \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link

This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).