From: Jason Wang <jasowang@redhat.com>
To: netdev@vger.kernel.org, linux-kernel@vger.kernel.org
Cc: mst@redhat.com, sergei.shtylyov@cogentembedded.com,
christoffer.dall@linaro.org, brouer@redhat.com,
Jason Wang <jasowang@redhat.com>
Subject: [PATCH V4 net 2/3] tuntap: disable preemption during XDP processing
Date: Sat, 24 Feb 2018 11:32:25 +0800 [thread overview]
Message-ID: <1519443146-9089-2-git-send-email-jasowang@redhat.com> (raw)
In-Reply-To: <1519443146-9089-1-git-send-email-jasowang@redhat.com>
Except for tuntap, all other drivers' XDP was implemented at NAPI
poll() routine in a bh. This guarantees all XDP operation were done at
the same CPU which is required by e.g BFP_MAP_TYPE_PERCPU_ARRAY. But
for tuntap, we do it in process context and we try to protect XDP
processing by RCU reader lock. This is insufficient since
CONFIG_PREEMPT_RCU can preempt the RCU reader critical section which
breaks the assumption that all XDP were processed in the same CPU.
Fixing this by simply disabling preemption during XDP processing.
Fixes: 761876c857cb ("tap: XDP support")
Signed-off-by: Jason Wang <jasowang@redhat.com>
---
drivers/net/tun.c | 6 ++++++
1 file changed, 6 insertions(+)
diff --git a/drivers/net/tun.c b/drivers/net/tun.c
index 2823a4a..63d39fe6 100644
--- a/drivers/net/tun.c
+++ b/drivers/net/tun.c
@@ -1642,6 +1642,7 @@ static struct sk_buff *tun_build_skb(struct tun_struct *tun,
else
*skb_xdp = 0;
+ preempt_disable();
rcu_read_lock();
xdp_prog = rcu_dereference(tun->xdp_prog);
if (xdp_prog && !*skb_xdp) {
@@ -1665,6 +1666,7 @@ static struct sk_buff *tun_build_skb(struct tun_struct *tun,
if (err)
goto err_redirect;
rcu_read_unlock();
+ preempt_enable();
return NULL;
case XDP_TX:
xdp_xmit = true;
@@ -1686,6 +1688,7 @@ static struct sk_buff *tun_build_skb(struct tun_struct *tun,
skb = build_skb(buf, buflen);
if (!skb) {
rcu_read_unlock();
+ preempt_enable();
return ERR_PTR(-ENOMEM);
}
@@ -1698,10 +1701,12 @@ static struct sk_buff *tun_build_skb(struct tun_struct *tun,
skb->dev = tun->dev;
generic_xdp_tx(skb, xdp_prog);
rcu_read_unlock();
+ preempt_enable();
return NULL;
}
rcu_read_unlock();
+ preempt_enable();
return skb;
@@ -1709,6 +1714,7 @@ static struct sk_buff *tun_build_skb(struct tun_struct *tun,
put_page(alloc_frag->page);
err_xdp:
rcu_read_unlock();
+ preempt_enable();
this_cpu_inc(tun->pcpu_stats->rx_dropped);
return NULL;
}
--
2.7.4
next prev parent reply other threads:[~2018-02-24 3:32 UTC|newest]
Thread overview: 8+ messages / expand[flat|nested] mbox.gz Atom feed top
2018-02-24 3:32 [PATCH V4 net 1/3] Revert "tuntap: add missing xdp flush" Jason Wang
2018-02-24 3:32 ` Jason Wang [this message]
2018-02-26 11:02 ` [PATCH V4 net 2/3] tuntap: disable preemption during XDP processing Jesper Dangaard Brouer
2018-02-26 13:43 ` Jason Wang
2018-02-26 18:50 ` David Miller
2018-02-24 3:32 ` [PATCH V4 net 3/3] tuntap: correctly add the missing XDP flush Jason Wang
2018-02-26 18:50 ` David Miller
2018-02-26 18:50 ` [PATCH V4 net 1/3] Revert "tuntap: add missing xdp flush" David Miller
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=1519443146-9089-2-git-send-email-jasowang@redhat.com \
--to=jasowang@redhat.com \
--cc=brouer@redhat.com \
--cc=christoffer.dall@linaro.org \
--cc=linux-kernel@vger.kernel.org \
--cc=mst@redhat.com \
--cc=netdev@vger.kernel.org \
--cc=sergei.shtylyov@cogentembedded.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).