[Qemu-devel] [PULL 0/2] Net patches

[Qemu-devel] [PULL 0/2] Net patches

[Stefan Hajnoczi]

The following changes since commit 64afc2b4d48fb21e085517c38a59a3f61a11283c:

  Merge remote-tracking branch 'luiz/queue/qmp' into staging (2013-05-23 14:16:35 -0500)

are available in the git repository at:


  git://github.com/stefanha/qemu.git net

for you to fetch changes up to 00b7ade807b5ce6779ddd86ce29c5521ec5c529a:

  rtl8139: flush queued packets when RxBufPtr is written (2013-05-24 16:34:13 +0200)

----------------------------------------------------------------
Alasdair McLeay (1):
      net: support for bridged networking on Mac OS X

Stefan Hajnoczi (1):
      rtl8139: flush queued packets when RxBufPtr is written

 hw/net/rtl8139.c | 3 +++
 net/tap-bsd.c    | 3 ++-
 2 files changed, 5 insertions(+), 1 deletion(-)

-- 
1.8.1.4

[Qemu-devel] [PATCH 1/2] net: support for bridged networking on Mac OS X

[Stefan Hajnoczi]

From: Alasdair McLeay <alasdair.mcleay@me.com>

tun tap can be implemented on Mac OS X using
http://tuntaposx.sourceforge.net

It behaves in the same way as FreeBSD/OpenBSD implementations, but Qemu
needs a patch to use the OpenBS/FreeBSD code.

As per the patch listed in this forum thread:
http://forum.gns3.net/post17679.html#p17679

And also as used in the MacPorts installation:
https://trac.macports.org/browser/trunk/dports/emulators/qemu/files/patch-net-tap-interface.diff

Signed-off-by: Alasdair McLeay <alasdair.mcleay@me.com>
Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
---
 net/tap-bsd.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/net/tap-bsd.c b/net/tap-bsd.c
index bcdb268..f61d580 100644
--- a/net/tap-bsd.c
+++ b/net/tap-bsd.c
@@ -44,7 +44,8 @@ int tap_open(char *ifname, int ifname_size, int *vnet_hdr,
     struct stat s;
 #endif
 
-#if defined(__FreeBSD__) || defined(__FreeBSD_kernel__) || defined(__OpenBSD__)
+#if defined(__FreeBSD__) || defined(__FreeBSD_kernel__) || \
+    defined(__OpenBSD__) || defined(__APPLE__)
     /* if no ifname is given, always start the search from tap0/tun0. */
     int i;
     char dname[100];
-- 
1.8.1.4

[Qemu-devel] [PATCH 2/2] rtl8139: flush queued packets when RxBufPtr is written

[Stefan Hajnoczi]

Net queues support efficient "receive disable".  For example, tap's file
descriptor will not be polled while its peer has receive disabled.  This
saves CPU cycles for needlessly copying and then dropping packets which
the peer cannot receive.

rtl8139 is missing the qemu_flush_queued_packets() call that wakes the
queue up when receive becomes possible again.

As a result, the Windows 7 guest driver reaches a state where the
rtl8139 cannot receive packets.  The driver has actually refilled the
receive buffer but we never resume reception.

The bug can be reproduced by running a large FTP 'get' inside a Windows
7 guest:

  $ qemu -netdev tap,id=tap0,...
         -device rtl8139,netdev=tap0

The Linux guest driver does not trigger the bug, probably due to a
different buffer management strategy.

Reported-by: Oliver Francke <oliver.francke@filoo.de>
Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
---
 hw/net/rtl8139.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/hw/net/rtl8139.c b/hw/net/rtl8139.c
index 9369507..7993f9f 100644
--- a/hw/net/rtl8139.c
+++ b/hw/net/rtl8139.c
@@ -2575,6 +2575,9 @@ static void rtl8139_RxBufPtr_write(RTL8139State *s, uint32_t val)
     /* this value is off by 16 */
     s->RxBufPtr = MOD2(val + 0x10, s->RxBufferSize);
 
+    /* more buffer space may be available so try to receive */
+    qemu_flush_queued_packets(qemu_get_queue(s->nic));
+
     DPRINTF(" CAPR write: rx buffer length %d head 0x%04x read 0x%04x\n",
         s->RxBufferSize, s->RxBufAddr, s->RxBufPtr);
 }
-- 
1.8.1.4

Re: [Qemu-devel] [PATCH 2/2] rtl8139: flush queued packets when RxBufPtr is written

[Paolo Bonzini]

Il 24/05/2013 16:38, Stefan Hajnoczi ha scritto:
> Net queues support efficient "receive disable".  For example, tap's file
> descriptor will not be polled while its peer has receive disabled.  This
> saves CPU cycles for needlessly copying and then dropping packets which
> the peer cannot receive.
> 
> rtl8139 is missing the qemu_flush_queued_packets() call that wakes the
> queue up when receive becomes possible again.
> 
> As a result, the Windows 7 guest driver reaches a state where the
> rtl8139 cannot receive packets.  The driver has actually refilled the
> receive buffer but we never resume reception.
> 
> The bug can be reproduced by running a large FTP 'get' inside a Windows
> 7 guest:
> 
>   $ qemu -netdev tap,id=tap0,...
>          -device rtl8139,netdev=tap0
> 
> The Linux guest driver does not trigger the bug, probably due to a
> different buffer management strategy.
> 
> Reported-by: Oliver Francke <oliver.francke@filoo.de>
> Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
> ---
>  hw/net/rtl8139.c | 3 +++
>  1 file changed, 3 insertions(+)
> 
> diff --git a/hw/net/rtl8139.c b/hw/net/rtl8139.c
> index 9369507..7993f9f 100644
> --- a/hw/net/rtl8139.c
> +++ b/hw/net/rtl8139.c
> @@ -2575,6 +2575,9 @@ static void rtl8139_RxBufPtr_write(RTL8139State *s, uint32_t val)
>      /* this value is off by 16 */
>      s->RxBufPtr = MOD2(val + 0x10, s->RxBufferSize);
>  
> +    /* more buffer space may be available so try to receive */
> +    qemu_flush_queued_packets(qemu_get_queue(s->nic));
> +
>      DPRINTF(" CAPR write: rx buffer length %d head 0x%04x read 0x%04x\n",
>          s->RxBufferSize, s->RxBufAddr, s->RxBufPtr);
>  }
> 

Do you have time to update the branch with a "Cc: qemu-stable@nongnu.org"?

Paolo

Re: [Qemu-devel] [PATCH 2/2] rtl8139: flush queued packets when RxBufPtr is written

[Stefan Hajnoczi]

On Fri, May 24, 2013 at 05:18:09PM +0200, Paolo Bonzini wrote:
> Il 24/05/2013 16:38, Stefan Hajnoczi ha scritto:
> > diff --git a/hw/net/rtl8139.c b/hw/net/rtl8139.c
> > index 9369507..7993f9f 100644
> > --- a/hw/net/rtl8139.c
> > +++ b/hw/net/rtl8139.c
> > @@ -2575,6 +2575,9 @@ static void rtl8139_RxBufPtr_write(RTL8139State *s, uint32_t val)
> >      /* this value is off by 16 */
> >      s->RxBufPtr = MOD2(val + 0x10, s->RxBufferSize);
> >  
> > +    /* more buffer space may be available so try to receive */
> > +    qemu_flush_queued_packets(qemu_get_queue(s->nic));
> > +
> >      DPRINTF(" CAPR write: rx buffer length %d head 0x%04x read 0x%04x\n",
> >          s->RxBufferSize, s->RxBufAddr, s->RxBufPtr);
> >  }
> > 
> 
> Do you have time to update the branch with a "Cc: qemu-stable@nongnu.org"?

It has been merged.  Will try to CC qemu-stable in the future.

Stefan

Re: [Qemu-devel] [PULL 0/2] Net patches

[Anthony Liguori]

Pulled.  Thanks.

Regards,

Anthony Liguori