From: Simon Horman <horms@kernel.org>
To: Suman Ghosh <sumang@marvell.com>
Cc: sgoutham@marvell.com, gakula@marvell.com, sbhatta@marvell.com,
hkelam@marvell.com, davem@davemloft.net, edumazet@google.com,
kuba@kernel.org, pabeni@redhat.com, netdev@vger.kernel.org,
linux-kernel@vger.kernel.org, lcherian@marvell.com,
jerinj@marvell.com, john.fastabend@gmail.com,
bbhushan2@marvell.com, hawk@kernel.org, andrew+netdev@lunn.ch,
ast@kernel.org, daniel@iogearbox.net, bpf@vger.kernel.org,
larysa.zaremba@intel.com
Subject: Re: [net-next PATCH v5 1/6] octeontx2-pf: use xdp_return_frame() to free xdp buffers
Date: Mon, 10 Feb 2025 17:53:00 +0000 [thread overview]
Message-ID: <20250210175300.GH554665@kernel.org> (raw)
In-Reply-To: <20250210162543.GF554665@kernel.org>
On Mon, Feb 10, 2025 at 04:25:43PM +0000, Simon Horman wrote:
> On Thu, Feb 06, 2025 at 02:20:29PM +0530, Suman Ghosh wrote:
> > xdp_return_frames() will help to free the xdp frames and their
> > associated pages back to page pool.
> >
> > Signed-off-by: Geetha sowjanya <gakula@marvell.com>
> > Signed-off-by: Suman Ghosh <sumang@marvell.com>
>
> > diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_txrx.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_txrx.c
> > index 224cef938927..d46f05993d3f 100644
> > --- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_txrx.c
> > +++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_txrx.c
> > @@ -96,20 +96,22 @@ static unsigned int frag_num(unsigned int i)
> >
> > static void otx2_xdp_snd_pkt_handler(struct otx2_nic *pfvf,
> > struct otx2_snd_queue *sq,
> > - struct nix_cqe_tx_s *cqe)
> > + struct nix_cqe_tx_s *cqe)
> > {
> > struct nix_send_comp_s *snd_comp = &cqe->comp;
> > struct sg_list *sg;
> > struct page *page;
> > - u64 pa;
> > + u64 pa, iova;
> >
> > sg = &sq->sg[snd_comp->sqe_id];
> >
> > - pa = otx2_iova_to_phys(pfvf->iommu_domain, sg->dma_addr[0]);
> > - otx2_dma_unmap_page(pfvf, sg->dma_addr[0],
> > - sg->size[0], DMA_TO_DEVICE);
> > + iova = sg->dma_addr[0];
> > + pa = otx2_iova_to_phys(pfvf->iommu_domain, iova);
> > page = virt_to_page(phys_to_virt(pa));
> > - put_page(page);
>
> Hi Suman,
>
> With this patch applied page is assigned but otherwise unused in this
> function. So unless there are some side effects of the above, I think
> page and in turn pa and iova can be removed.
I now see that page and pa are removed in patch 6/6, although iova
is left behind. I think it would be best to move the cleanup forward
to this patch.
>
> > + if (sg->flags & XDP_REDIRECT)
> > + otx2_dma_unmap_page(pfvf, sg->dma_addr[0], sg->size[0], DMA_TO_DEVICE);
> > + xdp_return_frame((struct xdp_frame *)sg->skb);
> > + sg->skb = (u64)NULL;
> > }
> >
> > static void otx2_snd_pkt_handler(struct otx2_nic *pfvf,
>
> ...
>
next prev parent reply other threads:[~2025-02-10 17:53 UTC|newest]
Thread overview: 21+ messages / expand[flat|nested] mbox.gz Atom feed top
2025-02-06 8:50 [net-next PATCH v5 0/6] Add af_xdp support for cn10k Suman Ghosh
2025-02-06 8:50 ` [net-next PATCH v5 1/6] octeontx2-pf: use xdp_return_frame() to free xdp buffers Suman Ghosh
2025-02-10 16:25 ` Simon Horman
2025-02-10 17:53 ` Simon Horman [this message]
2025-02-12 6:45 ` [EXTERNAL] " Suman Ghosh
2025-02-12 6:44 ` Suman Ghosh
2025-02-10 17:54 ` Simon Horman
2025-02-12 6:52 ` [EXTERNAL] " Suman Ghosh
2025-02-06 8:50 ` [net-next PATCH v5 2/6] octeontx2-pf: Add AF_XDP non-zero copy support Suman Ghosh
2025-02-10 16:41 ` Simon Horman
2025-02-11 7:07 ` [EXTERNAL] " Suman Ghosh
2025-02-11 10:09 ` Simon Horman
2025-02-06 8:50 ` [net-next PATCH v5 3/6] octeontx2-pf: AF_XDP zero copy receive support Suman Ghosh
2025-02-10 17:56 ` Simon Horman
2025-02-12 7:32 ` [EXTERNAL] " Suman Ghosh
2025-02-06 8:50 ` [net-next PATCH v5 4/6] octeontx2-pf: Reconfigure RSS table after enabling AF_XDP zerocopy on rx queue Suman Ghosh
2025-02-06 8:50 ` [net-next PATCH v5 5/6] octeontx2-pf: Prepare for AF_XDP Suman Ghosh
2025-02-10 17:57 ` Simon Horman
2025-02-12 8:51 ` [EXTERNAL] " Suman Ghosh
2025-02-06 8:50 ` [net-next PATCH v5 6/6] octeontx2-pf: AF_XDP zero copy transmit support Suman Ghosh
2025-02-07 11:40 ` kernel test robot
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=20250210175300.GH554665@kernel.org \
--to=horms@kernel.org \
--cc=andrew+netdev@lunn.ch \
--cc=ast@kernel.org \
--cc=bbhushan2@marvell.com \
--cc=bpf@vger.kernel.org \
--cc=daniel@iogearbox.net \
--cc=davem@davemloft.net \
--cc=edumazet@google.com \
--cc=gakula@marvell.com \
--cc=hawk@kernel.org \
--cc=hkelam@marvell.com \
--cc=jerinj@marvell.com \
--cc=john.fastabend@gmail.com \
--cc=kuba@kernel.org \
--cc=larysa.zaremba@intel.com \
--cc=lcherian@marvell.com \
--cc=linux-kernel@vger.kernel.org \
--cc=netdev@vger.kernel.org \
--cc=pabeni@redhat.com \
--cc=sbhatta@marvell.com \
--cc=sgoutham@marvell.com \
--cc=sumang@marvell.com \
/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).