public inbox for netdev@vger.kernel.org 
 help / color / mirror / Atom feed
From: Shan Wei <shanwei@cn•fujitsu.com>
To: "Michael S. Tsirkin" <mst@redhat•com>
Cc: "Michał Mirosław" <mirq-linux@rere•qmqm.pl>,
	"Herbert Xu" <herbert@gondor•hengli.com.au>,
	netdev@vger•kernel.org,
	"Ben Hutchings" <bhutchings@solarflare•com>
Subject: Re: tap/bridge: Dropping NETIF_F_GSO/NETIF_F_SG
Date: Thu, 05 May 2011 17:34:43 +0800	[thread overview]
Message-ID: <4DC26F33.8010700@cn.fujitsu.com> (raw)
In-Reply-To: <20110505084428.GB17647@redhat.com>

Michael S. Tsirkin wrote, at 05/05/2011 04:44 PM:
> On Thu, May 05, 2011 at 01:28:54AM +0200, Michał Mirosław wrote:
>> On Thu, May 05, 2011 at 08:34:15AM +1000, Herbert Xu wrote:
>>> On Wed, May 04, 2011 at 09:18:14PM +0300, Michael S. Tsirkin wrote:
>>>> BTW, I just noticed that net-next spits out
>>>> many of the following when I run any VMs:
>>>>
>>>> tap0: Dropping NETIF_F_SG since no checksum feature.
>>>> tap0: Dropping NETIF_F_GSO since no SG feature.
>>>> tap0: Features changed: 0x401b4849 -> 0x40004040
>>>> device msttap0 entered promiscuous mode
>>>> br0: Dropping NETIF_F_GSO since no SG feature.
>>>> br0: port 1(msttap0) entering forwarding state
>>>> br0: port 1(msttap0) entering forwarding state
>>>> tap0: Features changed: 0x40004040 -> 0x40024849
>>>> tap0: Dropping NETIF_F_SG since no checksum feature.
>>>> tap0: Dropping NETIF_F_GSO since no SG feature.
>>>> tap0: Features changed: 0x40024849 -> 0x40004040
>>>> br0: Dropping NETIF_F_GSO since no SG feature.
>>>> tap0: Dropping NETIF_F_SG since no checksum feature.
>>>> tap0: Dropping NETIF_F_GSO since no SG feature.
>>>> tap0: Dropping NETIF_F_SG since no checksum feature.
>>>> tap0: Dropping NETIF_F_GSO since no SG feature.
>>>> tap0: Dropping NETIF_F_SG since no checksum feature.
>>>> tap0: Dropping NETIF_F_GSO since no SG feature.
>>>> tap0: Dropping NETIF_F_SG since no checksum feature.
>>>> tap0: Dropping NETIF_F_GSO since no SG feature.
>>>> tap0: Features changed: 0x40004040 -> 0x401b4849
>>>> tap0: Dropping NETIF_F_SG since no checksum feature.
>>>> tap0: Dropping NETIF_F_GSO since no SG feature.
>>>> tap0: Features changed: 0x401b4849 -> 0x40004040
>>>> br0: Dropping NETIF_F_GSO since no SG feature.
>>>>
>>>> My problem is not primarily with warnings:
>>>>
>>>> will that linearize all packets and disable GSO
>>>> for tap and bridge? If yes it can't be good
>>>> for performance...
>>> I think so.  So the question is why is checksum off?
>>
>> Whatever application is creating the tap0 device is not calling
>> ioctl(TUNSETOFFLOAD) with TUN_F_CSUM set. This is userspace bug/feature
>> exposed by recent changes to netdev features handling.
>>
>> Best Regards,
>> Michał Mirosław
> 
> No, I think it's not a bug in userspace. Here is what it does:
> 
>     /* Check if our kernel supports TUNSETOFFLOAD */
>     if (ioctl(fd, TUNSETOFFLOAD, 0) != 0 && errno == EINVAL) {
>         return;
>     }
> 
>     if (csum) {
>         offload |= TUN_F_CSUM;
>         if (tso4)
>             offload |= TUN_F_TSO4;
>         if (tso6)
>             offload |= TUN_F_TSO6;
>         if ((tso4 || tso6) && ecn)
>             offload |= TUN_F_TSO_ECN;
>         if (ufo)
>             offload |= TUN_F_UFO;
>     }
> 
>     if (ioctl(fd, TUNSETOFFLOAD, offload) != 0) {
>         offload &= ~TUN_F_UFO;
>         if (ioctl(fd, TUNSETOFFLOAD, offload) != 0) {
>             fprintf(stderr, "TUNSETOFFLOAD ioctl() failed: %s\n",
>                     strerror(errno));
>         }
>     }
> 
> The first call is just to check that ioctl works.
> When checking for ioctl in this way, userspace clears checksum.
> This will clear SG and thus GSO; later userspace enables checksum.
> checksum is on but SG is by now disabled so GSO gets cleared again too.
> 
> 
> It's also likely a problem that
> userspace can trigger warnings in log for what used to be
> a legal way to check for ioctl and/or disable checksum offloading,
> but that is more minor.

Maybe it's a kernel bug. Can you try following changes?

TUN_F_TSO4, TUN_F_TSO6, TUN_F_TSO_ECN, TUN_F_UFO these features are 
depend on NETIF_F_SG. If NETIF_F_SG is not set, these features are not be
enabled and  warnings are printed in netdev_fix_features().


diff --git a/drivers/net/tun.c b/drivers/net/tun.c
index 0636f70..eea92e0 100644
--- a/drivers/net/tun.c
+++ b/drivers/net/tun.c
@@ -1178,7 +1178,7 @@ static int set_offload(struct tun_struct *tun, unsigned long arg)
        u32 features = 0;
 
        if (arg & TUN_F_CSUM) {
-               features |= NETIF_F_HW_CSUM;
+               features |= NETIF_F_HW_CSUM | NETIF_F_SG;
                arg &= ~TUN_F_CSUM;
 
                if (arg & (TUN_F_TSO4|TUN_F_TSO6)) {


-- 
Best Regards
-----
Shan Wei

  reply	other threads:[~2011-05-05  9:42 UTC|newest]

Thread overview: 40+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2011-05-04 18:18 tap/bridge: Dropping NETIF_F_GSO/NETIF_F_SG Michael S. Tsirkin
2011-05-04 22:34 ` Herbert Xu
2011-05-04 23:28   ` Michał Mirosław
2011-05-05  0:19     ` Herbert Xu
2011-05-05  8:44     ` Michael S. Tsirkin
2011-05-05  9:34       ` Shan Wei [this message]
2011-05-05 10:05         ` Herbert Xu
2011-05-16  7:32           ` Michael S. Tsirkin
2011-05-16  8:07             ` Herbert Xu
2011-05-16  8:18               ` Michael S. Tsirkin
2011-05-16  9:38                 ` Herbert Xu
2011-05-16  9:48                   ` Michael S. Tsirkin
2011-05-16 10:43                     ` Herbert Xu
2011-05-16 11:21                       ` Michael S. Tsirkin
2011-05-16 12:18                         ` Herbert Xu
2011-05-16 12:24                           ` Michał Mirosław
2011-05-16 22:46                             ` Herbert Xu
2011-05-16 23:06                               ` David Miller
2011-05-16 23:45                                 ` Herbert Xu
2011-05-17  5:18                                   ` Michael S. Tsirkin
2011-05-17  5:24                                     ` Herbert Xu
2011-05-17  5:48                                       ` Michael S. Tsirkin
2011-05-17  6:25                                         ` Herbert Xu
2011-05-17  8:08                               ` Michał Mirosław
2011-05-17  8:15                                 ` Michał Mirosław
2011-05-17  8:19                                 ` [PATCH] net: tuntap: Fix tun_net_fix_features() Michał Mirosław
2011-05-17 14:29                                   ` Michael S. Tsirkin
2011-05-17 14:46                                     ` Michał Mirosław
2011-05-17 14:54                                       ` Michael S. Tsirkin
2011-05-17 15:00                                         ` Michał Mirosław
2011-05-17 15:11                                           ` Michael S. Tsirkin
2011-06-01  9:25                                   ` Michael S. Tsirkin
2011-06-20 19:14                                   ` [RESENT PATCH] " Michał Mirosław
2011-06-20 19:25                                     ` Ben Hutchings
2011-06-20 19:44                                       ` Michał Mirosław
2011-05-16 10:53                     ` tap/bridge: Dropping NETIF_F_GSO/NETIF_F_SG Michał Mirosław
2011-05-16  8:28               ` Michael S. Tsirkin
2011-05-05 15:26 ` Michał Mirosław
2011-05-14  6:54   ` Shan Wei
2011-05-16  7:28   ` Michael S. Tsirkin

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=4DC26F33.8010700@cn.fujitsu.com \
    --to=shanwei@cn$(echo .)fujitsu.com \
    --cc=bhutchings@solarflare$(echo .)com \
    --cc=herbert@gondor$(echo .)hengli.com.au \
    --cc=mirq-linux@rere$(echo .)qmqm.pl \
    --cc=mst@redhat$(echo .)com \
    --cc=netdev@vger$(echo .)kernel.org \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html
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