search for: ndo_start_xmit

On Tue, Oct 14, 2014 at 02:53:27PM -0400, David Miller wrote: > From: Jason Wang <jasowang at redhat.com> > Date: Sat, 11 Oct 2014 15:16:43 +0800 > > > We free old transmitted packets in ndo_start_xmit() currently, so any > > packet must be orphaned also there. This was used to reduce the overhead of > > tx interrupt to achieve better performance. But this may not work for some > > protocols such as TCP stream. TCP depends on the value of sk_wmem_alloc to > > implement var...

On Tue, Oct 14, 2014 at 02:53:27PM -0400, David Miller wrote: > From: Jason Wang <jasowang at redhat.com> > Date: Sat, 11 Oct 2014 15:16:43 +0800 > > > We free old transmitted packets in ndo_start_xmit() currently, so any > > packet must be orphaned also there. This was used to reduce the overhead of > > tx interrupt to achieve better performance. But this may not work for some > > protocols such as TCP stream. TCP depends on the value of sk_wmem_alloc to > > implement var...

We free transmitted packets in ndo_start_xmit() in the past to get better performance in the past. One side effect is that skb_orphan() needs to be called in ndo_start_xmit() which makes sk_wmem_alloc not accurate in fact. For TCP protocol, this means several optimization could not work well such as TCP small queue and auto corking. This can l...

We free transmitted packets in ndo_start_xmit() in the past to get better performance in the past. One side effect is that skb_orphan() needs to be called in ndo_start_xmit() which makes sk_wmem_alloc not accurate in fact. For TCP protocol, this means several optimization could not work well such as TCP small queue and auto corking. This can l...

On Tue, Oct 14, 2014 at 02:53:27PM -0400, David Miller wrote: > From: Jason Wang <jasowang at redhat.com> > Date: Sat, 11 Oct 2014 15:16:43 +0800 > > > We free old transmitted packets in ndo_start_xmit() currently, so any > > packet must be orphaned also there. This was used to reduce the overhead of > > tx interrupt to achieve better performance. But this may not work for some > > protocols such as TCP stream. TCP depends on the value of sk_wmem_alloc to > > implement var...

On Tue, Oct 14, 2014 at 02:53:27PM -0400, David Miller wrote: > From: Jason Wang <jasowang at redhat.com> > Date: Sat, 11 Oct 2014 15:16:43 +0800 > > > We free old transmitted packets in ndo_start_xmit() currently, so any > > packet must be orphaned also there. This was used to reduce the overhead of > > tx interrupt to achieve better performance. But this may not work for some > > protocols such as TCP stream. TCP depends on the value of sk_wmem_alloc to > > implement var...

From: Jason Wang <jasowang at redhat.com> Date: Sat, 11 Oct 2014 15:16:43 +0800 > We free old transmitted packets in ndo_start_xmit() currently, so any > packet must be orphaned also there. This was used to reduce the overhead of > tx interrupt to achieve better performance. But this may not work for some > protocols such as TCP stream. TCP depends on the value of sk_wmem_alloc to > implement various optimization fo...

On Sat, 2014-10-11 at 15:16 +0800, Jason Wang wrote: > We free transmitted packets in ndo_start_xmit() in the past to get better > performance in the past. One side effect is that skb_orphan() needs to be > called in ndo_start_xmit() which makes sk_wmem_alloc not accurate in > fact. For TCP protocol, this means several optimization could not work well > such as TCP small queue and auto...

Hello all: We free old transmitted packets in ndo_start_xmit() currently, so any packet must be orphaned also there. This was used to reduce the overhead of tx interrupt to achieve better performance. But this may not work for some protocols such as TCP stream. TCP depends on the value of sk_wmem_alloc to implement various optimization for small packets stre...

Hello all: We free old transmitted packets in ndo_start_xmit() currently, so any packet must be orphaned also there. This was used to reduce the overhead of tx interrupt to achieve better performance. But this may not work for some protocols such as TCP stream. TCP depends on the value of sk_wmem_alloc to implement various optimization for small packets stre...

...lower devs here? link down is often indication of a hardware problem. lower dev might stop responding down the road. > > > +static const struct net_device_ops failover_dev_ops = { > > > + .ndo_open = failover_open, > > > + .ndo_stop = failover_close, > > > + .ndo_start_xmit = failover_start_xmit, > > > + .ndo_select_queue = failover_select_queue, > > > + .ndo_get_stats64 = failover_get_stats, > > > + .ndo_change_mtu = failover_change_mtu, > > > + .ndo_set_rx_mode = failover_set_rx_mode, > > > + .ndo_validate_addr = eth_va...

...MLX5E_TX_SKB_CB(skb)->num_wqebbs = DIV_ROUND_UP(ds_cnt, > > And in the middle of this we have: > > skb_pull_inline(skb, ihs); > > This is looks illegal. > > You must not modify the data pointers of any SKB that you receive for > sending via ->ndo_start_xmit() unless you know that absolutely you are > the one and only reference that exists to that SKB. > > And exactly for the case you are trying to "fix" here, you do not. If > the SKB is cloned, or has an elevated users count, someone else can be > looking at it exactly at th...

...MLX5E_TX_SKB_CB(skb)->num_wqebbs = DIV_ROUND_UP(ds_cnt, > > And in the middle of this we have: > > skb_pull_inline(skb, ihs); > > This is looks illegal. > > You must not modify the data pointers of any SKB that you receive for > sending via ->ndo_start_xmit() unless you know that absolutely you are > the one and only reference that exists to that SKB. > > And exactly for the case you are trying to "fix" here, you do not. If > the SKB is cloned, or has an elevated users count, someone else can be > looking at it exactly at th...

On Sat, Oct 11, 2014 at 03:16:46PM +0800, Jason Wang wrote: > We free transmitted packets in ndo_start_xmit() in the past to get better > performance in the past. One side effect is that skb_orphan() needs to be > called in ndo_start_xmit() which makes sk_wmem_alloc not accurate in > fact. For TCP protocol, this means several optimization could not work well > such as TCP small queue and auto...

...mit >> skbs. >> >> Several notes: >> - Tx interrupt storm avoidance when queue is about to be full is >> kept. > But queue is typically *not* full. More important to avoid interrupt > storms in that case IMO. Yes. >> Since we may enable callbacks in both ndo_start_xmit() and tx >> napi, patch 1 adds a check to make sure used event never go >> back. This will let the napi not enable the callbacks wrongly after >> delayed callbacks was used. > So why not just use delayed callbacks? This means the tx interrupt are coalesced in a somewhat...

...mit >> skbs. >> >> Several notes: >> - Tx interrupt storm avoidance when queue is about to be full is >> kept. > But queue is typically *not* full. More important to avoid interrupt > storms in that case IMO. Yes. >> Since we may enable callbacks in both ndo_start_xmit() and tx >> napi, patch 1 adds a check to make sure used event never go >> back. This will let the napi not enable the callbacks wrongly after >> delayed callbacks was used. > So why not just use delayed callbacks? This means the tx interrupt are coalesced in a somewhat...

...issues + * with drivers which can hold transmitted skbs for long times */ + skb_orphan(skb); + if (likely(!skb->next)) { if (!list_empty(&ptype_all)) dev_queue_xmit_nit(skb, dev); @@ -1688,22 +1692,7 @@ int dev_hard_start_xmit(struct sk_buff * goto gso; } - rc = ops->ndo_start_xmit(skb, dev); - /* - * TODO: if skb_orphan() was called by - * dev->hard_start_xmit() (for example, the unmodified - * igb driver does that; bnx2 doesn't), then - * skb_tx_software_timestamp() will be unable to send - * back the time stamp. - * - * How can this be prevented? Alwa...

...issues + * with drivers which can hold transmitted skbs for long times */ + skb_orphan(skb); + if (likely(!skb->next)) { if (!list_empty(&ptype_all)) dev_queue_xmit_nit(skb, dev); @@ -1688,22 +1692,7 @@ int dev_hard_start_xmit(struct sk_buff * goto gso; } - rc = ops->ndo_start_xmit(skb, dev); - /* - * TODO: if skb_orphan() was called by - * dev->hard_start_xmit() (for example, the unmodified - * igb driver does that; bnx2 doesn't), then - * skb_tx_software_timestamp() will be unable to send - * back the time stamp. - * - * How can this be prevented? Alwa...

On 10/15/2014 06:18 PM, Michael S. Tsirkin wrote: > On Wed, Oct 15, 2014 at 03:25:29PM +0800, Jason Wang wrote: >> > Orphan skb in ndo_start_xmit() breaks socket accounting and packet >> > queuing. This in fact breaks lots of things such as pktgen and several >> > TCP optimizations. And also make BQL can't be implemented for >> > virtio-net. >> > >> > This patch tries to solve this issue by e...

On 10/15/2014 06:18 PM, Michael S. Tsirkin wrote: > On Wed, Oct 15, 2014 at 03:25:29PM +0800, Jason Wang wrote: >> > Orphan skb in ndo_start_xmit() breaks socket accounting and packet >> > queuing. This in fact breaks lots of things such as pktgen and several >> > TCP optimizations. And also make BQL can't be implemented for >> > virtio-net. >> > >> > This patch tries to solve this issue by e...