aboutsummaryrefslogtreecommitdiffstats
path: root/net (follow)
AgeCommit message (Collapse)AuthorFilesLines
2019-01-28netfilter: ipv4: remove useless export_symbolFlorian Westphal2-18/+19
Only one caller; place it where needed and get rid of the EXPORT_SYMBOL. Signed-off-by: Florian Westphal <fw@strlen.de> Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
2019-01-28netfilter: conntrack: fix error path in nf_conntrack_pernet_init()Cong Wang1-2/+2
When nf_ct_netns_get() fails, it should clean up itself, its caller doesn't need to call nf_conntrack_fini_net(). nf_conntrack_init_net() is called after registering sysctl and proc, so its cleanup function should be called before unregistering sysctl and proc. Fixes: ba3fbe663635 ("netfilter: nf_conntrack: provide modparam to always register conntrack hooks") Fixes: b884fa461776 ("netfilter: conntrack: unify sysctl handling") Reported-and-tested-by: syzbot+fcee88b2d87f0539dfe9@syzkaller.appspotmail.com Signed-off-by: Cong Wang <xiyou.wangcong@gmail.com> Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
2019-01-28netfilter: nft_counter: remove wrong __percpu of nft_counter_resest()'s argLuc Van Oostenryck1-1/+1
nft_counter_rest() has its first argument declared as struct nft_counter_percpu_priv __percpu *priv but this structure is not percpu (it only countains a member 'counter' which is, correctly, a pointer to a percpu struct nft_counter). So, remove the '__percpu' from the argument's declaration. Signed-off-by: Luc Van Oostenryck <luc.vanoostenryck@gmail.com> Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
2019-01-28ipvs: use indirect call wrappersMatteo Croce3-10/+45
Use the new indirect call wrappers in IPVS when calling the TCP or UDP protocol specific functions. This avoids an indirect calls in IPVS, and reduces the performance impact of the Spectre mitigation. Signed-off-by: Matteo Croce <mcroce@redhat.com> Acked-by: Julian Anastasov <ja@ssi.bg> Acked-by: Simon Horman <horms@verge.net.au> Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
2019-01-28ipvs: avoid indirect calls when calculating checksumsMatteo Croce4-15/+19
The function pointer ip_vs_protocol->csum_check is only used in protocol specific code, and never in the generic one. Remove the function pointer from struct ip_vs_protocol and call the checksum functions directly. This reduces the performance impact of the Spectre mitigation, and should give a small improvement even with RETPOLINES disabled. Signed-off-by: Matteo Croce <mcroce@redhat.com> Acked-by: Julian Anastasov <ja@ssi.bg> Acked-by: Simon Horman <horms@verge.net.au> Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
2019-01-22netfilter: conntrack: fix bogus port values for other l4 protocolsFlorian Westphal1-11/+35
We must only extract l4 proto information if we can track the layer 4 protocol. Before removal of pkt_to_tuple callback, the code to extract port information was only reached for TCP/UDP/LITE/DCCP/SCTP. The other protocols were handled by the indirect call, and the 'generic' tracker took care of other protocols that have no notion of 'ports'. After removal of the callback we must be more strict here and only init port numbers for those protocols that have ports. Fixes: df5e1629087a ("netfilter: conntrack: remove pkt_to_tuple callback") Signed-off-by: Florian Westphal <fw@strlen.de> Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
2019-01-22netfilter: conntrack: fix IPV6=n buildsFlorian Westphal2-0/+10
Stephen Rothwell reports: After merging the netfilter-next tree, today's linux-next build (powerpc ppc64_defconfig) failed like this: ERROR: "nf_conntrack_invert_icmpv6_tuple" [nf_conntrack.ko] undefined! ERROR: "nf_conntrack_icmpv6_packet" [nf_conntrack.ko] undefined! ERROR: "nf_conntrack_icmpv6_init_net" [nf_conntrack.ko] undefined! ERROR: "icmpv6_pkt_to_tuple" [nf_conntrack.ko] undefined! ERROR: "nf_ct_gre_keymap_destroy" [nf_conntrack.ko] undefined! icmpv6 related errors are due to lack of IS_ENABLED(CONFIG_IPV6) (no icmpv6 support is builtin if kernel has CONFIG_IPV6=n), the nf_ct_gre_keymap_destroy error is due to lack of PROTO_GRE check. Fixes: a47c54048162 ("netfilter: conntrack: handle builtin l4proto packet functions via direct calls") Fixes: e2e48b471634 ("netfilter: conntrack: handle icmp pkt_to_tuple helper via direct calls") Fixes: 197c4300aec0 ("netfilter: conntrack: remove invert_tuple callback") Fixes: 2a389de86e4a ("netfilter: conntrack: remove l4proto init and get_net callbacks") Fixes: e56894356f60 ("netfilter: conntrack: remove l4proto destroy hook") Reported-by: Stephen Rothwell <sfr@canb.auug.org.au> Signed-off-by: Florian Westphal <fw@strlen.de> Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
2019-01-18Revert "netfilter: nft_hash: add map lookups for hashing operations"Laura Garcia Liebana1-121/+0
A better way to implement this from userspace has been found without specific code in the kernel side, revert this. Fixes: b9ccc07e3f31 ("netfilter: nft_hash: add map lookups for hashing operations") Signed-off-by: Laura Garcia Liebana <nevola@gmail.com> Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
2019-01-18netfilter: nat: un-export nf_nat_used_tupleFlorian Westphal1-2/+1
Not used since 203f2e78200c27e ("netfilter: nat: remove l4proto->unique_tuple") Signed-off-by: Florian Westphal <fw@strlen.de> Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
2019-01-18netfilter: nft_meta: Add NFT_META_I/OIFKIND meta typewenxu1-0/+12
In the ip_rcv the skb goes through the PREROUTING hook first, then kicks in vrf device and go through the same hook again. When conntrack dnat works with vrf, there will be some conflict with rules because the packet goes through the hook twice with different nf status. ip link add user1 type vrf table 1 ip link add user2 type vrf table 2 ip l set dev tun1 master user1 ip l set dev tun2 master user2 nft add table firewall nft add chain firewall zones { type filter hook prerouting priority - 300 \; } nft add rule firewall zones counter ct zone set iif map { "tun1" : 1, "tun2" : 2 } nft add chain firewall rule-1000-ingress nft add rule firewall rule-1000-ingress ct zone 1 tcp dport 22 ct state new counter accept nft add rule firewall rule-1000-ingress counter drop nft add chain firewall rule-1000-egress nft add rule firewall rule-1000-egress tcp dport 22 ct state new counter drop nft add rule firewall rule-1000-egress counter accept nft add chain firewall rules-all { type filter hook prerouting priority - 150 \; } nft add rule firewall rules-all ip daddr vmap { "2.2.2.11" : jump rule-1000-ingress } nft add rule firewall rules-all ct zone vmap { 1 : jump rule-1000-egress } nft add rule firewall dnat-all ct zone vmap { 1 : jump dnat-1000 } nft add rule firewall dnat-1000 ip daddr 2.2.2.11 counter dnat to 10.0.0.7 For a package with ip daddr 2.2.2.11 and tcp dport 22, first time accept in the rule-1000-ingress and dnat to 10.0.0.7. Then second time the packet goto the wrong chain rule-1000-egress which leads the packet drop With this patch, userspace can add the 'don't re-do entire ruleset for vrf' policy itself via: nft add rule firewall rules-all meta iifkind "vrf" counter accept Signed-off-by: wenxu <wenxu@ucloud.cn> Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
2019-01-18netfilter: nf_conntrack: provide modparam to always register conntrack hooksPablo Neira Ayuso1-4/+24
The connection tracking hooks can be optionally registered per netns when conntrack is specifically invoked from the ruleset since 0c66dc1ea3f0 ("netfilter: conntrack: register hooks in netns when needed by ruleset"). Then, since 4d3a57f23dec ("netfilter: conntrack: do not enable connection tracking unless needed"), the default behaviour is changed to always register them on demand. This patch provides a toggle that allows users to always register them. Without this toggle, in order to use conntrack for statistics collection, you need a dummy rule that refers to conntrack, eg. iptables -I INPUT -m state --state NEW This patch allows users to restore the original behaviour via modparam, ie. always register connection tracking, eg. modprobe nf_conntrack enable_hooks=1 Hence, no dummy rule is required. Reported-by: Laura Garcia <nevola@gmail.com> Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
2019-01-18netfilter: conntrack: remove nf_ct_l4proto_find_getFlorian Westphal9-174/+43
Its now same as __nf_ct_l4proto_find(), so rename that to nf_ct_l4proto_find and use it everywhere. It never returns NULL and doesn't need locks or reference counts. Before this series: 302824 net/netfilter/nf_conntrack.ko 21504 net/netfilter/nf_conntrack_proto_gre.ko text data bss dec hex filename 6281 1732 4 8017 1f51 nf_conntrack_proto_gre.ko 108356 20613 236 129205 1f8b5 nf_conntrack.ko After: 294864 net/netfilter/nf_conntrack.ko text data bss dec hex filename 106979 19557 240 126776 1ef38 nf_conntrack.ko so, even with builtin gre, total size got reduced. Signed-off-by: Florian Westphal <fw@strlen.de> Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
2019-01-18netfilter: conntrack: remove l4proto destroy hookFlorian Westphal2-18/+11
Only one user (gre), add a direct call and remove this facility. Signed-off-by: Florian Westphal <fw@strlen.de> Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
2019-01-18netfilter: conntrack: remove l4proto init and get_net callbacksFlorian Westphal9-217/+56
Those were needed we still had modular trackers. As we don't have those anymore, prefer direct calls and remove all the (un)register infrastructure associated with this. Signed-off-by: Florian Westphal <fw@strlen.de> Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
2019-01-18netfilter: conntrack: remove sysctl registration helpersFlorian Westphal1-76/+1
After previous patch these are not used anymore. Signed-off-by: Florian Westphal <fw@strlen.de> Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
2019-01-18netfilter: conntrack: unify sysctl handlingFlorian Westphal9-460/+391
Due to historical reasons, all l4 trackers register their own sysctls. This leads to copy&pasted boilerplate code, that does exactly same thing, just with different data structure. Place all of this in a single file. This allows to remove the various ctl_table pointers from the ct_netns structure and reduces overall code size. Signed-off-by: Florian Westphal <fw@strlen.de> Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
2019-01-18netfilter: conntrack: avoid unneeded nf_conntrack_l4proto lookupsFlorian Westphal8-64/+21
after removal of the packet and invert function pointers, several places do not need to lookup the l4proto structure anymore. Remove those lookups. The function nf_ct_invert_tuplepr becomes redundant, replace it with nf_ct_invert_tuple everywhere. Signed-off-by: Florian Westphal <fw@strlen.de> Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
2019-01-18netfilter: conntrack: remove pernet l4 proto register interfaceFlorian Westphal1-16/+12
No used anymore. Signed-off-by: Florian Westphal <fw@strlen.de> Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
2019-01-18netfilter: conntrack: remove remaining l4proto indirect packet callsFlorian Westphal3-48/+24
Now that all l4trackers are builtin, no need to use a mix of direct and indirect calls. This removes the last two users: gre and the generic l4 protocol tracker. Signed-off-by: Florian Westphal <fw@strlen.de> Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
2019-01-18netfilter: conntrack: remove module owner fieldFlorian Westphal4-17/+0
No need to get/put module owner reference, none of these can be removed anymore. Signed-off-by: Florian Westphal <fw@strlen.de> Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
2019-01-18netfilter: conntrack: remove invert_tuple callbackFlorian Westphal3-8/+10
Only used by icmp(v6). Prefer a direct call and remove this function from the l4proto struct. Signed-off-by: Florian Westphal <fw@strlen.de> Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
2019-01-18netfilter: conntrack: remove pkt_to_tuple callbackFlorian Westphal3-16/+6
GRE is now builtin, so we can handle it via direct call and remove the callback. Signed-off-by: Florian Westphal <fw@strlen.de> Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
2019-01-18netfilter: conntrack: remove net_idFlorian Westphal1-6/+2
No users anymore. Signed-off-by: Florian Westphal <fw@strlen.de> Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
2019-01-18netfilter: conntrack: gre: switch module to be built-inFlorian Westphal5-85/+27
This makes the last of the modular l4 trackers 'bool'. After this, all infrastructure to handle dynamic l4 protocol registration becomes obsolete and can be removed in followup patches. Old: 302824 net/netfilter/nf_conntrack.ko 21504 net/netfilter/nf_conntrack_proto_gre.ko New: 313728 net/netfilter/nf_conntrack.ko Old: text data bss dec hex filename 6281 1732 4 8017 1f51 nf_conntrack_proto_gre.ko 108356 20613 236 129205 1f8b5 nf_conntrack.ko New: 112095 21381 240 133716 20a54 nf_conntrack.ko The size increase is only temporary. Signed-off-by: Florian Westphal <fw@strlen.de> Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
2019-01-18netfilter: conntrack: gre: convert rwlock to rcuFlorian Westphal1-22/+15
We can use gre. Lock is only needed when a new expectation is added. In case a single spinlock proves to be problematic we can either add one per netns or use an array of locks combined with net_hash_mix() or similar to pick the 'correct' one. But given this is only needed for an expectation rather than per packet a single one should be ok. Signed-off-by: Florian Westphal <fw@strlen.de> Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
2019-01-18netfilter: conntrack: handle icmp pkt_to_tuple helper via direct callsFlorian Westphal3-8/+12
rather than handling them via indirect call, use a direct one instead. This leaves GRE as the last user of this indirect call facility. Signed-off-by: Florian Westphal <fw@strlen.de> Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
2019-01-18netfilter: conntrack: handle builtin l4proto packet functions via direct callsFlorian Westphal7-44/+76
The l4 protocol trackers are invoked via indirect call: l4proto->packet(). With one exception (gre), all l4trackers are builtin, so we can make .packet optional and use a direct call for most protocols. Signed-off-by: Florian Westphal <fw@strlen.de> Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
2019-01-18netfilter: nf_tables: Support RULE_ID reference in new rulePhil Sutter1-0/+9
To allow for a batch to contain rules in arbitrary ordering, introduce NFTA_RULE_POSITION_ID attribute which works just like NFTA_RULE_POSITION but contains the ID of another rule within the same batch. This helps iptables-nft-restore handling dumps with mixed insert/append commands correctly. Note that NFTA_RULE_POSITION takes precedence over NFTA_RULE_POSITION_ID, so if the former is present, the latter is ignored. Signed-off-by: Phil Sutter <phil@nwl.cc> Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
2019-01-18netfilter: physdev: relax br_netfilter dependencyFlorian Westphal2-7/+7
Following command: iptables -D FORWARD -m physdev ... causes connectivity loss in some setups. Reason is that iptables userspace will probe kernel for the module revision of the physdev patch, and physdev has an artificial dependency on br_netfilter (xt_physdev use makes no sense unless a br_netfilter module is loaded). This causes the "phydev" module to be loaded, which in turn enables the "call-iptables" infrastructure. bridged packets might then get dropped by the iptables ruleset. The better fix would be to change the "call-iptables" defaults to 0 and enforce explicit setting to 1, but that breaks backwards compatibility. This does the next best thing: add a request_module call to checkentry. This was a stray '-D ... -m physdev' won't activate br_netfilter anymore. Signed-off-by: Florian Westphal <fw@strlen.de> Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
2019-01-18netfilter: conntrack: remove helper hook againFlorian Westphal1-106/+36
place them into the confirm one. Old: hook (300): ipv4/6_help() first call helper, then seqadj. hook (INT_MAX): confirm Now: hook (INT_MAX): confirm, first call helper, then seqadj, then confirm Not having the extra call is noticeable in bechmarks. Signed-off-by: Florian Westphal <fw@strlen.de> Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
2019-01-18netfilter: nf_tables: add direct calls for all builtin expressionsFlorian Westphal9-31/+39
With CONFIG_RETPOLINE its faster to add an if (ptr == &foo_func) check and and use direct calls for all the built-in expressions. ~15% improvement in pathological cases. checkpatch doesn't like the X macro due to the embedded return statement, but the macro has a very limited scope so I don't think its a problem. I would like to avoid bugs of the form If (e->ops->eval == (unsigned long)nft_foo_eval) nft_bar_eval(); and open-coded if ()/else if()/else cascade, thus the macro. Signed-off-by: Florian Westphal <fw@strlen.de> Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
2019-01-18netfilter: nf_tables: handle nft_object lookups via rhltableFlorian Westphal2-13/+93
Instead of linear search, use rhlist interface to look up the objects. This fixes rulesets with thousands of named objects (quota, counters and the like). We only use a single table for this and consider the address of the table we're doing the lookup in as a part of the key. This reduces restore time of a sample ruleset with ~20k named counters from 37 seconds to 0.8 seconds. Signed-off-by: Florian Westphal <fw@strlen.de> Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
2019-01-18netfilter: nf_tables: prepare nft_object for lookups via hashtableFlorian Westphal3-13/+18
Add a 'key' structure for object, so we can look them up by name + table combination (the name can be the same in each table). Signed-off-by: Florian Westphal <fw@strlen.de> Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
2019-01-17tcp: move rx_opt & syn_data_acked init to tcp_disconnect()Eric Dumazet2-6/+4
If we make sure all listeners have these fields cleared, then a clone will also inherit zero values. Signed-off-by: Eric Dumazet <edumazet@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-01-17tcp: move tp->rack init to tcp_disconnect()Eric Dumazet2-6/+6
If we make sure all listeners have proper tp->rack value, then a clone will also inherit proper initial value. Note that fresh sockets init tp->rack from tcp_init_sock() Signed-off-by: Eric Dumazet <edumazet@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-01-17tcp: move app_limited init to tcp_disconnect()Eric Dumazet2-3/+3
If we make sure all listeners have app_limited set to ~0U, then a clone will also inherit proper initial value. Signed-off-by: Eric Dumazet <edumazet@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-01-17tcp: move retrans_out, sacked_out, tlp_high_seq, last_oow_ack_time init to tcp_disconnect()Eric Dumazet2-4/+4
If we make sure all listeners have these fields cleared, then a clone will also inherit zero values. Signed-off-by: Eric Dumazet <edumazet@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-01-17tcp: do not clear urg_data in tcp_create_openreq_childEric Dumazet1-2/+0
All listeners have this field cleared already, since tcp_disconnect() clears it and newly created sockets have also a zero value here. So a clone will inherit a zero value here. Signed-off-by: Eric Dumazet <edumazet@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-01-17tcp: move snd_cwnd & snd_cwnd_cnt init to tcp_disconnect()Eric Dumazet2-9/+1
Passive connections can inherit proper value by cloning, if we make sure all listeners have the proper values there. tcp_disconnect() was setting snd_cwnd to 2, which seems quite obsolete since IW10 adoption. Also remove an obsolete comment. Signed-off-by: Eric Dumazet <edumazet@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-01-17tcp: move mdev_us init to tcp_disconnect()Eric Dumazet2-1/+1
If we make sure a listener always has its mdev_us field set to TCP_TIMEOUT_INIT, we do not need to rewrite this field after a new clone is created. tcp_disconnect() is very seldom used in real applications. Signed-off-by: Eric Dumazet <edumazet@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-01-17tcp: do not clear srtt_us in tcp_create_openreq_childEric Dumazet1-1/+0
All listeners have this field cleared already, since tcp_disconnect() clears it and newly created sockets have also a zero value here. So a clone will inherit a zero value here. Signed-off-by: Eric Dumazet <edumazet@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-01-17tcp: do not clear packets_out in tcp_create_openreq_child()Eric Dumazet1-1/+0
New sockets have this field cleared, and tcp_disconnect() calls tcp_write_queue_purge() which among other things also clear tp->packets_out So a listener is guaranteed to have this field cleared. Signed-off-by: Eric Dumazet <edumazet@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-01-17tcp: move icsk_rto init to tcp_disconnect()Eric Dumazet2-1/+1
If we make sure a listener always has its icsk_rto field set to TCP_TIMEOUT_INIT, we do not need to rewrite this field after a new clone is created. tcp_disconnect() is very seldom used in real applications. Signed-off-by: Eric Dumazet <edumazet@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-01-17tcp: do not set snd_ssthresh in tcp_create_openreq_child()Eric Dumazet1-1/+0
New sockets get the field set to TCP_INFINITE_SSTHRESH in tcp_init_sock() In case a socket had this field changed and transitions to TCP_LISTEN state, tcp_disconnect() also makes sure snd_ssthresh is set to TCP_INFINITE_SSTHRESH. So a listener has this field set to TCP_INFINITE_SSTHRESH already. Signed-off-by: Eric Dumazet <edumazet@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-01-17tipc: remove unneeded semicolon in trace.cYueHaibing1-2/+2
Remove unneeded semicolon Signed-off-by: YueHaibing <yuehaibing@huawei.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-01-17net: add a route cache full diagnostic messagePeter Oskolkov1-1/+5
In some testing scenarios, dst/route cache can fill up so quickly that even an explicit GC call occasionally fails to clean it up. This leads to sporadically failing calls to dst_alloc and "network unreachable" errors to the user, which is confusing. This patch adds a diagnostic message to make the cause of the failure easier to determine. Signed-off-by: Peter Oskolkov <posk@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-01-17switchdev: Add extack argument to call_switchdev_notifiers()Petr Machata3-4/+5
A follow-up patch will enable vetoing of FDB entries. Make it possible to communicate details of why an FDB entry is not acceptable back to the user. Signed-off-by: Petr Machata <petrm@mellanox.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-01-17net: Add extack argument to ndo_fdb_add()Petr Machata5-6/+11
Drivers may not be able to support certain FDB entries, and an error code is insufficient to give clear hints as to the reasons of rejection. In order to make it possible to communicate the rejection reason, extend ndo_fdb_add() with an extack argument. Adapt the existing implementations of ndo_fdb_add() to take the parameter (and ignore it). Pass the extack parameter when invoking ndo_fdb_add() from rtnl_fdb_add(). Signed-off-by: Petr Machata <petrm@mellanox.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-01-17tcp: less aggressive window probing on local congestionYuchung Cheng1-15/+7
Previously when the sender fails to send (original) data packet or window probes due to congestion in the local host (e.g. throttling in qdisc), it'll retry within an RTO or two up to 500ms. In low-RTT networks such as data-centers, RTO is often far below the default minimum 200ms. Then local host congestion could trigger a retry storm pouring gas to the fire. Worse yet, the probe counter (icsk_probes_out) is not properly updated so the aggressive retry may exceed the system limit (15 rounds) until the packet finally slips through. On such rare events, it's wise to retry more conservatively (500ms) and update the stats properly to reflect these incidents and follow the system limit. Note that this is consistent with the behaviors when a keep-alive probe or RTO retry is dropped due to local congestion. Signed-off-by: Yuchung Cheng <ycheng@google.com> Signed-off-by: Eric Dumazet <edumazet@google.com> Reviewed-by: Neal Cardwell <ncardwell@google.com> Reviewed-by: Soheil Hassas Yeganeh <soheil@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-01-17tcp: retry more conservatively on local congestionYuchung Cheng1-5/+3
Previously when the sender fails to retransmit a data packet on timeout due to congestion in the local host (e.g. throttling in qdisc), it'll retry within an RTO up to 500ms. In low-RTT networks such as data-centers, RTO is often far below the default minimum 200ms (and the cap 500ms). Then local host congestion could trigger a retry storm pouring gas to the fire. Worse yet, the retry counter (icsk_retransmits) is not properly updated so the aggressive retry may exceed the system limit (15 rounds) until the packet finally slips through. On such rare events, it's wise to retry more conservatively (500ms) and update the stats properly to reflect these incidents and follow the system limit. Note that this is consistent with the behavior when a keep-alive probe is dropped due to local congestion. Signed-off-by: Yuchung Cheng <ycheng@google.com> Signed-off-by: Eric Dumazet <edumazet@google.com> Reviewed-by: Neal Cardwell <ncardwell@google.com> Reviewed-by: Soheil Hassas Yeganeh <soheil@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
Copyright © 1996 – 2023 Jason A. Donenfeld. All Rights Reverse Engineered.