From: Joe Damato <joe@dama.to>
To: Koichiro Den <den@valinux.co.jp>
Cc: Jon Mason <jdmason@kudzu.us>, Dave Jiang <dave.jiang@intel.com>,
Allen Hubbe <allenbh@gmail.com>,
Andrew Lunn <andrew+netdev@lunn.ch>,
"David S. Miller" <davem@davemloft.net>,
Eric Dumazet <edumazet@google.com>,
Jakub Kicinski <kuba@kernel.org>, Paolo Abeni <pabeni@redhat.com>,
ntb@lists.linux.dev, netdev@vger.kernel.org,
linux-kernel@vger.kernel.org
Subject: Re: [PATCH net-next v4 01/10] NTB: ntb_transport: Order RX descriptor reads after completion
Date: Fri, 18 Sep 2026 17:36:43 -0700 [thread overview]
Message-ID: <aq3ZG222WqEDp1Je@devvm20253.cco0.facebook.com> (raw)
In-Reply-To: <20260914084838.2158249-2-den@valinux.co.jp>
On Mon, Sep 14, 2026 at 05:48:29PM +0900, Koichiro Den wrote:
> The peer writes payloads and descriptors into a DMA-coherent memory
> window. ntb_process_rxc() checks DESC_DONE_FLAG before consuming the
> descriptor and payload, but coherent memory alone does not order those
> reads on weakly ordered CPUs.
>
> Read the completion word once and issue dma_rmb() after DONE is observed.
> Use the saved word for subsequent transport flag checks.
>
> Fixes: fce8a7bb5b4b ("PCI-Express Non-Transparent Bridge Support")
> Reported-by: Sashiko <sashiko-bot@kernel.org>
> Link: https://lore.kernel.org/r/20260815032932.151F11F000E9@smtp.kernel.org/
> Reviewed-by: Dave Jiang <dave.jiang@intel.com>
> Signed-off-by: Koichiro Den <den@valinux.co.jp>
> ---
> Changes in v4:
> - No changes.
>
> drivers/ntb/ntb_transport.c | 14 +++++++++-----
> 1 file changed, 9 insertions(+), 5 deletions(-)
>
> diff --git a/drivers/ntb/ntb_transport.c b/drivers/ntb/ntb_transport.c
> index f9caa1a653c5..74f4f8c1c7be 100644
> --- a/drivers/ntb/ntb_transport.c
> +++ b/drivers/ntb/ntb_transport.c
> @@ -1609,21 +1609,25 @@ static int ntb_process_rxc(struct ntb_transport_qp *qp)
> {
> struct ntb_payload_header *hdr;
> struct ntb_queue_entry *entry;
> + unsigned int flags;
> void *offset;
>
> offset = qp->rx_buff + qp->rx_max_frame * qp->rx_index;
> hdr = offset + qp->rx_max_frame - sizeof(struct ntb_payload_header);
>
> - dev_dbg(&qp->ndev->pdev->dev, "qp %d: RX ver %u len %d flags %x\n",
> - qp->qp_num, hdr->ver, hdr->len, hdr->flags);
> -
> - if (!(hdr->flags & DESC_DONE_FLAG)) {
> + flags = READ_ONCE(hdr->flags);
> + if (!(flags & DESC_DONE_FLAG)) {
> dev_dbg(&qp->ndev->pdev->dev, "done flag not set\n");
I get why the dev_dbg line above was moved down, but i feel like if this case
is hit, you lose some of the debugability that the debug line intended?
idk maybe this dev_dbg should be something like
dev_dbg(blah->dev, "qp %d: done flag not set, flags %x\n", qp->qp_num, flags)
so that some of the debuggability is still preserved when this case is hit ?
> qp->rx_ring_empty++;
> return -EAGAIN;
> }
>
> - if (hdr->flags & LINK_DOWN_FLAG) {
> + dma_rmb();
> +
> + dev_dbg(&qp->ndev->pdev->dev, "qp %d: RX ver %u len %d flags %x\n",
> + qp->qp_num, hdr->ver, hdr->len, flags);
I guess the above is a nit, so
Reviewed-by: Joe Damato <joe@dama.to>
next prev parent reply other threads:[~2026-09-19 0:36 UTC|newest]
Thread overview: 25+ messages / expand[flat|nested] mbox.gz Atom feed top
2026-09-14 8:48 [PATCH net-next v4 00/10] net: ntb_netdev: Preserve checksum offload across NTB Koichiro Den
2026-09-14 8:48 ` [PATCH net-next v4 01/10] NTB: ntb_transport: Order RX descriptor reads after completion Koichiro Den
2026-09-19 0:36 ` Joe Damato [this message]
2026-09-19 12:37 ` Koichiro Den
2026-09-14 8:48 ` [PATCH net-next v4 02/10] NTB: ntb_transport: Use little-endian shared fields Koichiro Den
2026-09-19 0:54 ` Joe Damato
2026-09-19 13:06 ` Koichiro Den
2026-09-14 8:48 ` [PATCH net-next v4 03/10] NTB: ntb_transport: Order RX entry completion Koichiro Den
2026-09-19 1:10 ` Joe Damato
2026-09-19 12:53 ` Koichiro Den
2026-09-14 8:48 ` [PATCH net-next v4 04/10] NTB: ntb_transport: Keep local QP link requests separate Koichiro Den
2026-09-17 20:49 ` netdev-bot+sashiko
2026-09-14 8:48 ` [PATCH net-next v4 05/10] NTB: ntb_transport: Exchange client capabilities at link-up Koichiro Den
2026-09-15 8:50 ` sashiko-bot
2026-09-19 12:51 ` Koichiro Den
2026-09-17 20:49 ` netdev-bot+sashiko
2026-09-14 8:48 ` [PATCH net-next v4 06/10] NTB: ntb_transport: Add per-payload client metadata Koichiro Den
2026-09-14 8:48 ` [PATCH net-next v4 07/10] net: ntb_netdev: Reject short RX frames Koichiro Den
2026-09-19 1:14 ` Joe Damato
2026-09-14 8:48 ` [PATCH net-next v4 08/10] net: ntb_netdev: Factor out RX statistics update Koichiro Den
2026-09-14 8:48 ` [PATCH net-next v4 09/10] net: ntb_netdev: Introduce an optional packet header, ntb_netdev_hdr Koichiro Den
2026-09-17 20:49 ` netdev-bot+sashiko
2026-09-14 8:48 ` [PATCH net-next v4 10/10] net: ntb_netdev: Preserve CHECKSUM_PARTIAL across NTB Koichiro Den
2026-09-17 20:49 ` netdev-bot+sashiko
2026-10-09 5:10 ` [PATCH net-next v4 00/10] net: ntb_netdev: Preserve checksum offload " Koichiro Den
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=aq3ZG222WqEDp1Je@devvm20253.cco0.facebook.com \
--to=joe@dama.to \
--cc=allenbh@gmail.com \
--cc=andrew+netdev@lunn.ch \
--cc=dave.jiang@intel.com \
--cc=davem@davemloft.net \
--cc=den@valinux.co.jp \
--cc=edumazet@google.com \
--cc=jdmason@kudzu.us \
--cc=kuba@kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=netdev@vger.kernel.org \
--cc=ntb@lists.linux.dev \
--cc=pabeni@redhat.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 an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.