From: Saeed Mahameed <saeedm@mellanox.com>
To: "linyunsheng@huawei.com" <linyunsheng@huawei.com>,
Li Rongqing <lirongqing@baidu.com>,
"brouer@redhat.com" <brouer@redhat.com>
Cc: "jonathan.lemon@gmail.com" <jonathan.lemon@gmail.com>,
"ilias.apalodimas@linaro.org" <ilias.apalodimas@linaro.org>,
"netdev@vger.kernel.org" <netdev@vger.kernel.org>
Subject: Re: 答复: [PATCH][v2] page_pool: handle page recycle for NUMA_NO_NODE condition
Date: Tue, 10 Dec 2019 19:56:50 +0000 [thread overview]
Message-ID: <ad3736af529f60772176d23f3aad6edf5d0096de.camel@mellanox.com> (raw)
In-Reply-To: <bb3c3846334744d7bbe83b1a29eaa762@baidu.com>
On Tue, 2019-12-10 at 09:39 +0000, Li,Rongqing wrote:
> > static int mvneta_create_page_pool(struct mvneta_port *pp,
> > struct mvneta_rx_queue *rxq, int
> > size) {
> > struct bpf_prog *xdp_prog = READ_ONCE(pp->xdp_prog);
> > struct page_pool_params pp_params = {
> > .order = 0,
> > .flags = PP_FLAG_DMA_MAP | PP_FLAG_DMA_SYNC_DEV,
> > .pool_size = size,
> > .nid = cpu_to_node(0),
>
> This kind of device should only be installed to vendor's platform
> which did not support numa
>
> But as you say , Saeed advice maybe cause that recycle always fail,
> if nid is configured like upper, and different from running NAPI node
> id
>
I don't see an issue here, By definition recycling must fail in such
case :).
> And maybe we can catch this case by the below
>
> diff --git a/net/core/page_pool.c b/net/core/page_pool.c
> index 3c8b51ccd1c1..973235c09487 100644
> --- a/net/core/page_pool.c
> +++ b/net/core/page_pool.c
> @@ -328,6 +328,11 @@ static bool pool_page_reusable(struct page_pool
> *pool, struct page *page)
> void __page_pool_put_page(struct page_pool *pool, struct page *page,
> unsigned int dma_sync_size, bool
> allow_direct)
> {
> + allow_direct = allow_direct && in_serving_softirq();
> +
> + if (allow_direct)
> + WARN_ON_ONCE((pool->p.nid != NUMA_NO_NODE) &&
> + (pool->p.nid != numa_mem_id()));
> /* This allocator is optimized for the XDP mode that uses
> * one-frame-per-page, but have fallbacks that act like the
> * regular page allocator APIs.
> @@ -342,7 +347,7 @@ void __page_pool_put_page(struct page_pool *pool,
> struct page *page,
> page_pool_dma_sync_for_device(pool, page,
> dma_sync_size);
>
> - if (allow_direct && in_serving_softirq())
> + if (allow_direct)
> if (__page_pool_recycle_direct(page, pool))
> return;
>
>
too much data path complications for my taste, we need to establish
some assumptions.
1) user know what he is doing, MSIX/NAPI affinity should be as hinted
by driver, pool nid should correspond to the affinity hint.
2) if necessary mitigate NAPI numa migration via page_pool_update_nid()
next prev parent reply other threads:[~2019-12-10 19:56 UTC|newest]
Thread overview: 44+ messages / expand[flat|nested] mbox.gz Atom feed top
2019-12-06 9:32 [PATCH][v2] page_pool: handle page recycle for NUMA_NO_NODE condition Li RongQing
2019-12-07 3:52 ` Saeed Mahameed
2019-12-09 1:31 ` Yunsheng Lin
2019-12-09 3:47 ` 答复: " Li,Rongqing
2019-12-09 9:30 ` Ilias Apalodimas
2019-12-09 10:37 ` 答复: " Li,Rongqing
2019-12-09 12:14 ` Jesper Dangaard Brouer
2019-12-09 23:34 ` Saeed Mahameed
2019-12-10 1:31 ` Yunsheng Lin
2019-12-10 9:39 ` 答复: " Li,Rongqing
2019-12-10 14:52 ` Ilias Apalodimas
2019-12-10 19:56 ` Saeed Mahameed [this message]
2019-12-10 19:45 ` Saeed Mahameed
2019-12-11 3:01 ` Yunsheng Lin
2019-12-11 3:06 ` Yunsheng Lin
2019-12-11 20:57 ` Saeed Mahameed
2019-12-12 1:04 ` Yunsheng Lin
2019-12-10 15:02 ` Ilias Apalodimas
2019-12-10 20:02 ` Saeed Mahameed
2019-12-10 20:10 ` Ilias Apalodimas
2019-12-11 18:49 ` Jesper Dangaard Brouer
2019-12-11 21:24 ` Saeed Mahameed
2019-12-12 1:34 ` Yunsheng Lin
2019-12-12 10:18 ` Jesper Dangaard Brouer
2019-12-13 3:40 ` Yunsheng Lin
2019-12-13 6:27 ` 答复: " Li,Rongqing
2019-12-13 6:53 ` Yunsheng Lin
2019-12-13 8:48 ` Jesper Dangaard Brouer
2019-12-16 1:51 ` Yunsheng Lin
2019-12-16 4:02 ` 答复: " Li,Rongqing
2019-12-16 10:13 ` Ilias Apalodimas
2019-12-16 10:16 ` Ilias Apalodimas
2019-12-16 10:57 ` 答复: " Li,Rongqing
2019-12-17 19:38 ` Saeed Mahameed
2019-12-17 19:35 ` Saeed Mahameed
2019-12-17 19:27 ` Saeed Mahameed
2019-12-16 12:15 ` Michal Hocko
2019-12-16 12:34 ` Ilias Apalodimas
2019-12-16 13:08 ` Michal Hocko
2019-12-16 13:21 ` Ilias Apalodimas
2019-12-17 2:11 ` Yunsheng Lin
2019-12-17 9:11 ` Michal Hocko
2019-12-19 2:09 ` Yunsheng Lin
2019-12-19 11:53 ` Michal Hocko
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=ad3736af529f60772176d23f3aad6edf5d0096de.camel@mellanox.com \
--to=saeedm@mellanox.com \
--cc=brouer@redhat.com \
--cc=ilias.apalodimas@linaro.org \
--cc=jonathan.lemon@gmail.com \
--cc=linyunsheng@huawei.com \
--cc=lirongqing@baidu.com \
--cc=netdev@vger.kernel.org \
/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
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
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).