LKML 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,
	chenhao288@hisilicon.com, Linux-MM <linux-mm@kvack.org>
Subject: Re: [PATCH net-next v2 2/4] page_pool: add interface to manipulate frag count in page pool
Date: Tue, 10 Aug 2021 16:58:05 +0200	[thread overview]
Message-ID: <a3999ff2-2385-41a6-c3f5-ccd6cf67badf@redhat.com> (raw)
In-Reply-To: <1628217982-53533-3-git-send-email-linyunsheng@huawei.com>



On 06/08/2021 04.46, Yunsheng Lin wrote:
> For 32 bit systems with 64 bit dma, dma_addr[1] is used to
> store the upper 32 bit dma addr, those system should be rare
> those days.
> 
> For normal system, the dma_addr[1] in 'struct page' is not
> used, so we can reuse dma_addr[1] for storing frag count,
> which means how many frags this page might be splited to.
> 
> In order to simplify the page frag support in the page pool,
> the PAGE_POOL_DMA_USE_PP_FRAG_COUNT macro is added to indicate
> the 32 bit systems with 64 bit dma, and the page frag support
> in page pool is disabled for such system.
> 
> The newly added page_pool_set_frag_count() is called to reserve
> the maximum frag count before any page frag is passed to the
> user. The page_pool_atomic_sub_frag_count_return() is called
> when user is done with the page frag.
> 
> Signed-off-by: Yunsheng Lin <linyunsheng@huawei.com>
> ---
>   include/linux/mm_types.h | 18 +++++++++++++-----
>   include/net/page_pool.h  | 46 +++++++++++++++++++++++++++++++++++++++-------
>   net/core/page_pool.c     |  4 ++++
>   3 files changed, 56 insertions(+), 12 deletions(-)
> 
> diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h
> index 52bbd2b..7f8ee09 100644
> --- a/include/linux/mm_types.h
> +++ b/include/linux/mm_types.h
> @@ -103,11 +103,19 @@ struct page {
>   			unsigned long pp_magic;
>   			struct page_pool *pp;
>   			unsigned long _pp_mapping_pad;
> -			/**
> -			 * @dma_addr: might require a 64-bit value on
> -			 * 32-bit architectures.
> -			 */
> -			unsigned long dma_addr[2];
> +			unsigned long dma_addr;
> +			union {
> +				/**
> +				 * dma_addr_upper: might require a 64-bit
> +				 * value on 32-bit architectures.
> +				 */
> +				unsigned long dma_addr_upper;
> +				/**
> +				 * For frag page support, not supported in
> +				 * 32-bit architectures with 64-bit DMA.
> +				 */
> +				atomic_long_t pp_frag_count;
> +			};
>   		};
>   		struct {	/* slab, slob and slub */
>   			union {
> diff --git a/include/net/page_pool.h b/include/net/page_pool.h
> index 8d7744d..42e6997 100644
> --- a/include/net/page_pool.h
> +++ b/include/net/page_pool.h
> @@ -45,7 +45,10 @@
>   					* Please note DMA-sync-for-CPU is still
>   					* device driver responsibility
>   					*/
> -#define PP_FLAG_ALL		(PP_FLAG_DMA_MAP | PP_FLAG_DMA_SYNC_DEV)
> +#define PP_FLAG_PAGE_FRAG	BIT(2) /* for page frag feature */
> +#define PP_FLAG_ALL		(PP_FLAG_DMA_MAP |\
> +				 PP_FLAG_DMA_SYNC_DEV |\
> +				 PP_FLAG_PAGE_FRAG)
>   
>   /*
>    * Fast allocation side cache array/stack
> @@ -198,19 +201,48 @@ 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 |= (dma_addr_t)page->dma_addr_upper << 16 << 16;

I find the macro name confusing.

I think it would be easier to read the code, if it was called:
  PAGE_POOL_DMA_CANNOT_USE_PP_FRAG_COUNT

> +
>   	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);
> +	page->dma_addr = addr;
> +	if (PAGE_POOL_DMA_USE_PP_FRAG_COUNT)
> +		page->dma_addr_upper = upper_32_bits(addr);
> +}
> +
> +static inline void page_pool_set_frag_count(struct page *page, long nr)
> +{
> +	atomic_long_set(&page->pp_frag_count, nr);
> +}
> +
> +static inline long page_pool_atomic_sub_frag_count_return(struct page *page,
> +							  long nr)
> +{
> +	long ret;
> +
> +	/* As suggested by Alexander, atomic_long_read() may cover up the
> +	 * reference count errors, so avoid calling atomic_long_read() in
> +	 * the cases of freeing or draining the page_frags, where we would
> +	 * not expect it to match or that are slowpath anyway.
> +	 */
> +	if (__builtin_constant_p(nr) &&
> +	    atomic_long_read(&page->pp_frag_count) == nr)
> +		return 0;
> +
> +	ret = atomic_long_sub_return(nr, &page->pp_frag_count);
> +	WARN_ON(ret < 0);
> +	return ret;
>   }
>   
>   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..68fab94 100644
> --- a/net/core/page_pool.c
> +++ b/net/core/page_pool.c
> @@ -67,6 +67,10 @@ static int page_pool_init(struct page_pool *pool,
>   		 */
>   	}
>   
> +	if (PAGE_POOL_DMA_USE_PP_FRAG_COUNT &&
> +	    pool->p.flags & PP_FLAG_PAGE_FRAG)
> +		return -EINVAL;

I read this as: if the page_pool use pp_frag_count and have flag set, 
then it is invalid/no-allowed, which seems wrong.

I find this code more intuitive to read:

  +	if (PAGE_POOL_DMA_CANNOT_USE_PP_FRAG_COUNT &&
  +	    pool->p.flags & PP_FLAG_PAGE_FRAG)
  +		return -EINVAL;

--Jesper


  reply	other threads:[~2021-08-10 14:58 UTC|newest]

Thread overview: 19+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2021-08-06  2:46 [PATCH net-next v2 0/4] add frag page support " Yunsheng Lin
2021-08-06  2:46 ` [PATCH net-next v2 1/4] page_pool: keep pp info as long as page pool owns the page Yunsheng Lin
2021-08-06  2:46 ` [PATCH net-next v2 2/4] page_pool: add interface to manipulate frag count in page pool Yunsheng Lin
2021-08-10 14:58   ` Jesper Dangaard Brouer [this message]
2021-08-11  0:48     ` Yunsheng Lin
2021-08-12 15:17   ` Jesper Dangaard Brouer
2021-08-06  2:46 ` [PATCH net-next v2 3/4] page_pool: add frag page recycling support " Yunsheng Lin
2021-08-06  2:46 ` [PATCH net-next v2 4/4] net: hns3: support skb's frag page recycling based on " Yunsheng Lin
2021-09-08  8:31   ` moyufeng
2021-09-08 15:08     ` Jakub Kicinski
2021-09-08 15:26       ` Ilias Apalodimas
2021-09-08 15:57         ` Jakub Kicinski
2021-09-08 16:47           ` Jesper Dangaard Brouer
2021-09-08 16:51           ` Ilias Apalodimas
2021-08-10 14:01 ` [PATCH net-next v2 0/4] add frag page support in " Jakub Kicinski
2021-08-10 14:23   ` Jesper Dangaard Brouer
2021-08-10 14:43     ` Jakub Kicinski
2021-08-10 15:09       ` Alexander Duyck
2021-08-11  1:06         ` [Linuxarm] " 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=a3999ff2-2385-41a6-c3f5-ccd6cf67badf@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=chenhao288@hisilicon.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-mm@kvack.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 net-next v2 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).