Message ID | 20110219112842.GE2782@psychotron.redhat.com |
---|---|
State | RFC, archived |
Delegated to: | David Miller |
Headers | show |
Le 19/02/2011 12:28, Jiri Pirko a écrit : > Sat, Feb 19, 2011 at 12:08:31PM CET, jpirko@redhat.com wrote: >> Sat, Feb 19, 2011 at 11:56:23AM CET, nicolas.2p.debian@gmail.com wrote: >>> Le 19/02/2011 09:05, Jiri Pirko a écrit : >>>> This patch converts bonding to use rx_handler. Results in cleaner >>>> __netif_receive_skb() with much less exceptions needed. Also >>>> bond-specific work is moved into bond code. >>>> >>>> Signed-off-by: Jiri Pirko<jpirko@redhat.com> >>>> >>>> v1->v2: >>>> using skb_iif instead of new input_dev to remember original >>>> device >>>> v2->v3: >>>> set orig_dev = skb->dev if skb_iif is set >>>> >>> >>> Why do we need to let the rx_handlers call netif_rx() or __netif_receive_skb()? >>> >>> Bonding used to be handled with very few overhead, simply replacing >>> skb->dev with skb->dev->master. Time has passed and we eventually >>> added many special processing for bonding into __netif_receive_skb(), >>> but the overhead remained very light. >>> >>> Calling netif_rx() (or __netif_receive_skb()) to allow nesting would probably lead to some overhead. >>> >>> Can't we, instead, loop inside __netif_receive_skb(), and deliver >>> whatever need to be delivered, to whoever need, inside the loop ? >>> >>> rx_handler = rcu_dereference(skb->dev->rx_handler); >>> while (rx_handler) { >>> /* ... */ >>> orig_dev = skb->dev; >>> skb = rx_handler(skb); >>> /* ... */ >>> rx_handler = (skb->dev != orig_dev) ? rcu_dereference(skb->dev->rx_handler) : NULL; >>> } >>> >>> This would reduce the overhead, while still allowing nesting: vlan on >>> top on bonding, bridge on top on bonding, ... >> >> I see your point. Makes sense to me. But the loop would have to include >> at least processing of ptype_all too. I'm going to cook a follow-up >> patch. >> > > DRAFT (doesn't modify rx_handlers): > > diff --git a/net/core/dev.c b/net/core/dev.c > index 4ebf7fe..e5dba47 100644 > --- a/net/core/dev.c > +++ b/net/core/dev.c > @@ -3115,6 +3115,7 @@ static int __netif_receive_skb(struct sk_buff *skb) > { > struct packet_type *ptype, *pt_prev; > rx_handler_func_t *rx_handler; > + struct net_device *dev; > struct net_device *orig_dev; > struct net_device *null_or_dev; > int ret = NET_RX_DROP; > @@ -3129,7 +3130,9 @@ static int __netif_receive_skb(struct sk_buff *skb) > if (netpoll_receive_skb(skb)) > return NET_RX_DROP; > > - __this_cpu_inc(softnet_data.processed); > + skb->skb_iif = skb->dev->ifindex; > + orig_dev = skb->dev; orig_dev should be set inside the loop, to reflect "previously crossed device", while following the path: eth0 -> bond0 -> br0. First step inside loop: orig_dev = eth0 skb->dev = bond0 (at the end of the loop). Second step inside loop: orig_dev = bond0 skb->dev = br0 (et the end of the loop). This would allow for exact match delivery to bond0 if someone bind there. > + > skb_reset_network_header(skb); > skb_reset_transport_header(skb); > skb->mac_len = skb->network_header - skb->mac_header; > @@ -3138,12 +3141,9 @@ static int __netif_receive_skb(struct sk_buff *skb) > > rcu_read_lock(); > > - if (!skb->skb_iif) { > - skb->skb_iif = skb->dev->ifindex; > - orig_dev = skb->dev; > - } else { > - orig_dev = dev_get_by_index_rcu(dev_net(skb->dev), skb->skb_iif); > - } I like the fact that it removes the above part. > +another_round: > + __this_cpu_inc(softnet_data.processed); > + dev = skb->dev; > > #ifdef CONFIG_NET_CLS_ACT > if (skb->tc_verd& TC_NCLS) { > @@ -3153,7 +3153,7 @@ static int __netif_receive_skb(struct sk_buff *skb) > #endif > > list_for_each_entry_rcu(ptype,&ptype_all, list) { > - if (!ptype->dev || ptype->dev == skb->dev) { > + if (!ptype->dev || ptype->dev == dev) { > if (pt_prev) > ret = deliver_skb(skb, pt_prev, orig_dev); > pt_prev = ptype; Inside the loop, we should only do exact match delivery, for &ptype_all and for &ptype_base[ntohs(type) & PTYPE_HASH_MASK]: list_for_each_entry_rcu(ptype, &ptype_all, list) { - if (!ptype->dev || ptype->dev == dev) { + if (ptype->dev == dev) { if (pt_prev) ret = deliver_skb(skb, pt_prev, orig_dev); pt_prev = ptype; } } list_for_each_entry_rcu(ptype, &ptype_base[ntohs(type) & PTYPE_HASH_MASK], list) { if (ptype->type == type && - (ptype->dev == null_or_dev || ptype->dev == skb->dev)) { + (ptype->dev == skb->dev)) { if (pt_prev) ret = deliver_skb(skb, pt_prev, orig_dev); pt_prev = ptype; } } After leaving the loop, we can do wilcard delivery, if skb is not NULL. list_for_each_entry_rcu(ptype, &ptype_all, list) { - if (!ptype->dev || ptype->dev == dev) { + if (!ptype->dev) { if (pt_prev) ret = deliver_skb(skb, pt_prev, orig_dev); pt_prev = ptype; } } list_for_each_entry_rcu(ptype, &ptype_base[ntohs(type) & PTYPE_HASH_MASK], list) { - if (ptype->type == type && - (ptype->dev == null_or_dev || ptype->dev == skb->dev)) { + if (ptype->type == type && !ptype->dev) { if (pt_prev) ret = deliver_skb(skb, pt_prev, orig_dev); pt_prev = ptype; } } This would reduce the number of tests inside the list_for_each_entry_rcu() loops. And because we match only ptype->dev == dev inside the loop and !ptype->dev outside the loop, this should avoid duplicate delivery. Also, for performance reason, exact match protocol handler lists might be moved from ptype_base or ptype_all to a per net_device list. That way, the list_for_each_entry_rcu() inside the loop could be empty if no protocol handler bind on the current dev. inside loop: list_for_each_entry_rcu(ptype, dev->ptype_all, list) { if (pt_prev) ret = deliver_skb(skb, pt_prev, orig_dev); pt_prev = ptype; } list_for_each_entry_rcu(ptype, dev->ptype_base[ntohs(type) & PTYPE_HASH_MASK], list) { if (ptype->type == type) { if (pt_prev) ret = deliver_skb(skb, pt_prev, orig_dev); pt_prev = ptype; } } Outside loop : list_for_each_entry_rcu(ptype, &ptype_all, list) { if (pt_prev) ret = deliver_skb(skb, pt_prev, orig_dev); pt_prev = ptype; } list_for_each_entry_rcu(ptype, &ptype_base[ntohs(type) & PTYPE_HASH_MASK], list) { if (ptype->type == type) { if (pt_prev) ret = deliver_skb(skb, pt_prev, orig_dev); pt_prev = ptype; } } This would require several changes into ptype_all and ptype_base handling, but should be faster. > @@ -3167,7 +3167,7 @@ static int __netif_receive_skb(struct sk_buff *skb) > ncls: > #endif > > - rx_handler = rcu_dereference(skb->dev->rx_handler); > + rx_handler = rcu_dereference(dev->rx_handler); > if (rx_handler) { > if (pt_prev) { > ret = deliver_skb(skb, pt_prev, orig_dev); > @@ -3176,6 +3176,8 @@ ncls: > skb = rx_handler(skb); > if (!skb) > goto out; > + if (dev != skb->dev) I would use "if (skb->dev != dev)" for clarity, because skb->dev is expected to have changed, not dev. > + goto another_round; > } > > if (vlan_tx_tag_present(skb)) { > Nicolas. -- To unsubscribe from this list: send the line "unsubscribe netdev" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html
Sat, Feb 19, 2011 at 02:18:00PM CET, nicolas.2p.debian@gmail.com wrote: >Le 19/02/2011 12:28, Jiri Pirko a écrit : >>Sat, Feb 19, 2011 at 12:08:31PM CET, jpirko@redhat.com wrote: >>>Sat, Feb 19, 2011 at 11:56:23AM CET, nicolas.2p.debian@gmail.com wrote: >>>>Le 19/02/2011 09:05, Jiri Pirko a écrit : >>>>>This patch converts bonding to use rx_handler. Results in cleaner >>>>>__netif_receive_skb() with much less exceptions needed. Also >>>>>bond-specific work is moved into bond code. >>>>> >>>>>Signed-off-by: Jiri Pirko<jpirko@redhat.com> >>>>> >>>>>v1->v2: >>>>> using skb_iif instead of new input_dev to remember original >>>>> device >>>>>v2->v3: >>>>> set orig_dev = skb->dev if skb_iif is set >>>>> >>>> >>>>Why do we need to let the rx_handlers call netif_rx() or __netif_receive_skb()? >>>> >>>>Bonding used to be handled with very few overhead, simply replacing >>>>skb->dev with skb->dev->master. Time has passed and we eventually >>>>added many special processing for bonding into __netif_receive_skb(), >>>>but the overhead remained very light. >>>> >>>>Calling netif_rx() (or __netif_receive_skb()) to allow nesting would probably lead to some overhead. >>>> >>>>Can't we, instead, loop inside __netif_receive_skb(), and deliver >>>>whatever need to be delivered, to whoever need, inside the loop ? >>>> >>>>rx_handler = rcu_dereference(skb->dev->rx_handler); >>>>while (rx_handler) { >>>> /* ... */ >>>> orig_dev = skb->dev; >>>> skb = rx_handler(skb); >>>> /* ... */ >>>> rx_handler = (skb->dev != orig_dev) ? rcu_dereference(skb->dev->rx_handler) : NULL; >>>>} >>>> >>>>This would reduce the overhead, while still allowing nesting: vlan on >>>>top on bonding, bridge on top on bonding, ... >>> >>>I see your point. Makes sense to me. But the loop would have to include >>>at least processing of ptype_all too. I'm going to cook a follow-up >>>patch. >>> >> >>DRAFT (doesn't modify rx_handlers): >> >>diff --git a/net/core/dev.c b/net/core/dev.c >>index 4ebf7fe..e5dba47 100644 >>--- a/net/core/dev.c >>+++ b/net/core/dev.c >>@@ -3115,6 +3115,7 @@ static int __netif_receive_skb(struct sk_buff *skb) >> { >> struct packet_type *ptype, *pt_prev; >> rx_handler_func_t *rx_handler; >>+ struct net_device *dev; >> struct net_device *orig_dev; >> struct net_device *null_or_dev; >> int ret = NET_RX_DROP; >>@@ -3129,7 +3130,9 @@ static int __netif_receive_skb(struct sk_buff *skb) >> if (netpoll_receive_skb(skb)) >> return NET_RX_DROP; >> >>- __this_cpu_inc(softnet_data.processed); >>+ skb->skb_iif = skb->dev->ifindex; >>+ orig_dev = skb->dev; > >orig_dev should be set inside the loop, to reflect "previously >crossed device", while following the path: > >eth0 -> bond0 -> br0. > >First step inside loop: > >orig_dev = eth0 >skb->dev = bond0 (at the end of the loop). > >Second step inside loop: > >orig_dev = bond0 >skb->dev = br0 (et the end of the loop). > >This would allow for exact match delivery to bond0 if someone bind there. > >>+ >> skb_reset_network_header(skb); >> skb_reset_transport_header(skb); >> skb->mac_len = skb->network_header - skb->mac_header; >>@@ -3138,12 +3141,9 @@ static int __netif_receive_skb(struct sk_buff *skb) >> >> rcu_read_lock(); >> >>- if (!skb->skb_iif) { >>- skb->skb_iif = skb->dev->ifindex; >>- orig_dev = skb->dev; >>- } else { >>- orig_dev = dev_get_by_index_rcu(dev_net(skb->dev), skb->skb_iif); >>- } > >I like the fact that it removes the above part. > >>+another_round: >>+ __this_cpu_inc(softnet_data.processed); >>+ dev = skb->dev; >> >> #ifdef CONFIG_NET_CLS_ACT >> if (skb->tc_verd& TC_NCLS) { >>@@ -3153,7 +3153,7 @@ static int __netif_receive_skb(struct sk_buff *skb) >> #endif >> >> list_for_each_entry_rcu(ptype,&ptype_all, list) { >>- if (!ptype->dev || ptype->dev == skb->dev) { >>+ if (!ptype->dev || ptype->dev == dev) { >> if (pt_prev) >> ret = deliver_skb(skb, pt_prev, orig_dev); >> pt_prev = ptype; > >Inside the loop, we should only do exact match delivery, for >&ptype_all and for &ptype_base[ntohs(type) & PTYPE_HASH_MASK]: > > list_for_each_entry_rcu(ptype, &ptype_all, list) { >- if (!ptype->dev || ptype->dev == dev) { >+ if (ptype->dev == dev) { > if (pt_prev) > ret = deliver_skb(skb, pt_prev, orig_dev); > pt_prev = ptype; > } > } > > > list_for_each_entry_rcu(ptype, > &ptype_base[ntohs(type) & PTYPE_HASH_MASK], list) { > if (ptype->type == type && >- (ptype->dev == null_or_dev || ptype->dev == skb->dev)) { >+ (ptype->dev == skb->dev)) { > if (pt_prev) > ret = deliver_skb(skb, pt_prev, orig_dev); > pt_prev = ptype; > } > } > >After leaving the loop, we can do wilcard delivery, if skb is not NULL. > > list_for_each_entry_rcu(ptype, &ptype_all, list) { >- if (!ptype->dev || ptype->dev == dev) { >+ if (!ptype->dev) { > if (pt_prev) > ret = deliver_skb(skb, pt_prev, orig_dev); > pt_prev = ptype; > } > } > > > list_for_each_entry_rcu(ptype, > &ptype_base[ntohs(type) & PTYPE_HASH_MASK], list) { >- if (ptype->type == type && >- (ptype->dev == null_or_dev || ptype->dev == skb->dev)) { >+ if (ptype->type == type && !ptype->dev) { > if (pt_prev) > ret = deliver_skb(skb, pt_prev, orig_dev); > pt_prev = ptype; > } > } > >This would reduce the number of tests inside the >list_for_each_entry_rcu() loops. And because we match only ptype->dev >== dev inside the loop and !ptype->dev outside the loop, this should >avoid duplicate delivery. Would you care to put this into patch so I can see the whole picture? Thanks. -- To unsubscribe from this list: send the line "unsubscribe netdev" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html
Le 19/02/2011 14:46, Jiri Pirko a écrit : > Sat, Feb 19, 2011 at 02:18:00PM CET, nicolas.2p.debian@gmail.com wrote: [snip] >> Inside the loop, we should only do exact match delivery, for >> &ptype_all and for&ptype_base[ntohs(type)& PTYPE_HASH_MASK]: >> >> list_for_each_entry_rcu(ptype,&ptype_all, list) { >> - if (!ptype->dev || ptype->dev == dev) { >> + if (ptype->dev == dev) { >> if (pt_prev) >> ret = deliver_skb(skb, pt_prev, orig_dev); >> pt_prev = ptype; >> } >> } >> >> >> list_for_each_entry_rcu(ptype, >> &ptype_base[ntohs(type)& PTYPE_HASH_MASK], list) { >> if (ptype->type == type&& >> - (ptype->dev == null_or_dev || ptype->dev == skb->dev)) { >> + (ptype->dev == skb->dev)) { >> if (pt_prev) >> ret = deliver_skb(skb, pt_prev, orig_dev); >> pt_prev = ptype; >> } >> } >> >> After leaving the loop, we can do wilcard delivery, if skb is not NULL. >> >> list_for_each_entry_rcu(ptype,&ptype_all, list) { >> - if (!ptype->dev || ptype->dev == dev) { >> + if (!ptype->dev) { >> if (pt_prev) >> ret = deliver_skb(skb, pt_prev, orig_dev); >> pt_prev = ptype; >> } >> } >> >> >> list_for_each_entry_rcu(ptype, >> &ptype_base[ntohs(type)& PTYPE_HASH_MASK], list) { >> - if (ptype->type == type&& >> - (ptype->dev == null_or_dev || ptype->dev == skb->dev)) { >> + if (ptype->type == type&& !ptype->dev) { >> if (pt_prev) >> ret = deliver_skb(skb, pt_prev, orig_dev); >> pt_prev = ptype; >> } >> } >> >> This would reduce the number of tests inside the >> list_for_each_entry_rcu() loops. And because we match only ptype->dev >> == dev inside the loop and !ptype->dev outside the loop, this should >> avoid duplicate delivery. > > Would you care to put this into patch so I can see the whole picture? > Thanks. I will try. Nicolas. -- To unsubscribe from this list: send the line "unsubscribe netdev" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html
diff --git a/net/core/dev.c b/net/core/dev.c index 4ebf7fe..e5dba47 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -3115,6 +3115,7 @@ static int __netif_receive_skb(struct sk_buff *skb) { struct packet_type *ptype, *pt_prev; rx_handler_func_t *rx_handler; + struct net_device *dev; struct net_device *orig_dev; struct net_device *null_or_dev; int ret = NET_RX_DROP; @@ -3129,7 +3130,9 @@ static int __netif_receive_skb(struct sk_buff *skb) if (netpoll_receive_skb(skb)) return NET_RX_DROP; - __this_cpu_inc(softnet_data.processed); + skb->skb_iif = skb->dev->ifindex; + orig_dev = skb->dev; + skb_reset_network_header(skb); skb_reset_transport_header(skb); skb->mac_len = skb->network_header - skb->mac_header; @@ -3138,12 +3141,9 @@ static int __netif_receive_skb(struct sk_buff *skb) rcu_read_lock(); - if (!skb->skb_iif) { - skb->skb_iif = skb->dev->ifindex; - orig_dev = skb->dev; - } else { - orig_dev = dev_get_by_index_rcu(dev_net(skb->dev), skb->skb_iif); - } +another_round: + __this_cpu_inc(softnet_data.processed); + dev = skb->dev; #ifdef CONFIG_NET_CLS_ACT if (skb->tc_verd & TC_NCLS) { @@ -3153,7 +3153,7 @@ static int __netif_receive_skb(struct sk_buff *skb) #endif list_for_each_entry_rcu(ptype, &ptype_all, list) { - if (!ptype->dev || ptype->dev == skb->dev) { + if (!ptype->dev || ptype->dev == dev) { if (pt_prev) ret = deliver_skb(skb, pt_prev, orig_dev); pt_prev = ptype; @@ -3167,7 +3167,7 @@ static int __netif_receive_skb(struct sk_buff *skb) ncls: #endif - rx_handler = rcu_dereference(skb->dev->rx_handler); + rx_handler = rcu_dereference(dev->rx_handler); if (rx_handler) { if (pt_prev) { ret = deliver_skb(skb, pt_prev, orig_dev); @@ -3176,6 +3176,8 @@ ncls: skb = rx_handler(skb); if (!skb) goto out; + if (dev != skb->dev) + goto another_round; } if (vlan_tx_tag_present(skb)) {