similar to: [PATCH 2/4] virtio_net: return NETDEV_TX_BUSY instead of queueing an extra skb.

If we fail to transmit a packet, we assume the queue is full and put the skb into last_xmit_skb. However, if more space frees up before we xmit it, we loop, and the result can be transmitting the same skb twice. Fix is simple: set skb to NULL if we've used it in some way, and check before sending. Signed-off-by: Rusty Russell <rusty at rustcorp.com.au> --- drivers/net/virtio_net.c |

If we fail to transmit a packet, we assume the queue is full and put the skb into last_xmit_skb. However, if more space frees up before we xmit it, we loop, and the result can be transmitting the same skb twice. Fix is simple: set skb to NULL if we've used it in some way, and check before sending. Signed-off-by: Rusty Russell <rusty at rustcorp.com.au> --- drivers/net/virtio_net.c |

Herbert tells me that returning NETDEV_TX_BUSY from hard_start_xmit is seen as a poor thing to do; we should cache the packet and stop the queue. Signed-off-by: Rusty Russell <rusty at rustcorp.com.au> --- drivers/net/virtio_net.c | 58 ++++++++++++++++++++++++++++++++--------------- 1 file changed, 40 insertions(+), 18 deletions(-) diff -r 26ba2dd67f46 drivers/net/virtio_net.c ---

Herbert tells me that returning NETDEV_TX_BUSY from hard_start_xmit is seen as a poor thing to do; we should cache the packet and stop the queue. Signed-off-by: Rusty Russell <rusty at rustcorp.com.au> --- drivers/net/virtio_net.c | 58 ++++++++++++++++++++++++++++++++--------------- 1 file changed, 40 insertions(+), 18 deletions(-) diff -r 26ba2dd67f46 drivers/net/virtio_net.c ---

Herbert tells me that returning NETDEV_TX_BUSY from hard_start_xmit is seen as a poor thing to do; we should cache the packet and stop the queue. Signed-off-by: Rusty Russell <rusty at rustcorp.com.au> --- drivers/net/virtio_net.c | 57 +++++++++++++++++++++++++++++++---------------- 1 file changed, 38 insertions(+), 19 deletions(-) diff -r a936d320f6d5 drivers/net/virtio_net.c ---

Herbert tells me that returning NETDEV_TX_BUSY from hard_start_xmit is seen as a poor thing to do; we should cache the packet and stop the queue. Signed-off-by: Rusty Russell <rusty at rustcorp.com.au> --- drivers/net/virtio_net.c | 57 +++++++++++++++++++++++++++++++---------------- 1 file changed, 38 insertions(+), 19 deletions(-) diff -r a936d320f6d5 drivers/net/virtio_net.c ---

This API change means that virtio_net can tell how much capacity remains for buffers. It's necessarily fuzzy, since VIRTIO_RING_F_INDIRECT_DESC means we can fit any number of descriptors in one, *if* we can kmalloc. Signed-off-by: Rusty Russell <rusty at rustcorp.com.au> Cc: Dinesh Subhraveti <dineshs at us.ibm.com> --- drivers/block/virtio_blk.c | 2 +-

This API change means that virtio_net can tell how much capacity remains for buffers. It's necessarily fuzzy, since VIRTIO_RING_F_INDIRECT_DESC means we can fit any number of descriptors in one, *if* we can kmalloc. Signed-off-by: Rusty Russell <rusty at rustcorp.com.au> Cc: Dinesh Subhraveti <dineshs at us.ibm.com> --- drivers/block/virtio_blk.c | 2 +-

From: Mark McLoughlin <markmc at redhat.com> hdr->csum_start is the offset from the start of the ethernet header to the transport layer checksum field. skb->csum_start is the offset from skb->head. skb_partial_csum_set() assumes that skb->data points to the ethernet header - i.e. it computes skb->csum_start by adding the headroom to hdr->csum_start. Since

The virtio_net driver is complicated by the two methods of freeing old xmit buffers (in addition to freeing old ones at the start of the xmit path). The original code used a 1/10 second timer attached to xmit_free(), reset on every xmit. Before we orphaned skbs on xmit, the transmitting userspace could block with a full socket until the timer fired, the skb destructor was called, and they were

The virtio_net driver is complicated by the two methods of freeing old xmit buffers (in addition to freeing old ones at the start of the xmit path). The original code used a 1/10 second timer attached to xmit_free(), reset on every xmit. Before we orphaned skbs on xmit, the transmitting userspace could block with a full socket until the timer fired, the skb destructor was called, and they were

[PATCH] virtio_net: Delay dropping tx skbs Cc: Mark McLoughlin <markmc at redhat.com>, virtualization at lists.linux-foundation.org, netdev at vger.kernel.org MIME-Version: 1.0 Content-Transfer-Encoding: 7bit Content-Disposition: inline Message-Id: <200807151340.00446.rusty at rustcorp.com.au> From: Mark McLoughlin <markmc at redhat.com> On Mon, 2008-05-26 at 17:42 +1000,

[PATCH] virtio_net: Delay dropping tx skbs Cc: Mark McLoughlin <markmc at redhat.com>, virtualization at lists.linux-foundation.org, netdev at vger.kernel.org MIME-Version: 1.0 Content-Transfer-Encoding: 7bit Content-Disposition: inline Message-Id: <200807151340.00446.rusty at rustcorp.com.au> From: Mark McLoughlin <markmc at redhat.com> On Mon, 2008-05-26 at 17:42 +1000,

virtio net used to unlink skbs from send queues on error, but ever since 48925e372f04f5e35fec6269127c62b2c71ab794 we do not do this. This causes guest data corruption and crashes with vhost since net core can requeue the skb or free it without it being taken off the list. This patch fixes this by queueing the skb after successfull transmit. Signed-off-by: Michael S. Tsirkin <mst at

virtio net used to unlink skbs from send queues on error, but ever since 48925e372f04f5e35fec6269127c62b2c71ab794 we do not do this. This causes guest data corruption and crashes with vhost since net core can requeue the skb or free it without it being taken off the list. This patch fixes this by queueing the skb after successfull transmit. Signed-off-by: Michael S. Tsirkin <mst at

virtio net will never try to overflow the TX ring, so the only reason add_buf may fail is out of memory. Thus, we can not stop the device until some request completes - there's no guarantee anything at all is outstanding. Make the error message clearer as well: error here does not indicate queue full. Signed-off-by: Michael S. Tsirkin <mst at redhat.com> --- drivers/net/virtio_net.c |

virtio net will never try to overflow the TX ring, so the only reason add_buf may fail is out of memory. Thus, we can not stop the device until some request completes - there's no guarantee anything at all is outstanding. Make the error message clearer as well: error here does not indicate queue full. Signed-off-by: Michael S. Tsirkin <mst at redhat.com> --- drivers/net/virtio_net.c |

This paraphrases DaveM (and steals some of his words) explaining why a device shouldn't return NETDEV_TX_BUSY, even though it looks so inviting to driver authors. See http://www.spinics.net/lists/netdev/msg322350.html Inspired-by: David Miller <davem at davemloft.net> Signed-off-by: Rusty Russell <rusty at rustcorp.com.au> diff --git a/include/linux/netdevice.h

From c1e1126c39fe107f68adec196d4e558a14540939 Mon Sep 17 00:00:00 2001 From: Anthony Liguori <aliguori@us.ibm.com> Date: Mon, 12 Nov 2007 21:30:26 -0600 Subject: [PATCH] virtio: use an hrtimer for tx coalescing. Not sure why hrtimer's cb_mode only exists with CONFIG_HIGH_RES_TIMERS; that seems like a bug to me. Signed-off-by: Rusty Russell <rusty@rustcorp.com.au> ---

From c1e1126c39fe107f68adec196d4e558a14540939 Mon Sep 17 00:00:00 2001 From: Anthony Liguori <aliguori@us.ibm.com> Date: Mon, 12 Nov 2007 21:30:26 -0600 Subject: [PATCH] virtio: use an hrtimer for tx coalescing. Not sure why hrtimer's cb_mode only exists with CONFIG_HIGH_RES_TIMERS; that seems like a bug to me. Signed-off-by: Rusty Russell <rusty@rustcorp.com.au> ---