- 10 3月, 2018 1 次提交
-
-
由 Eric Dumazet 提交于
fallback tunnels (like tunl0, gre0, gretap0, erspan0, sit0, ip6tnl0, ip6gre0) are automatically created when the corresponding module is loaded. These tunnels are also automatically created when a new network namespace is created, at a great cost. In many cases, netns are used for isolation purposes, and these extra network devices are a waste of resources. We are using thousands of netns per host, and hit the netns creation/delete bottleneck a lot. (Many thanks to Kirill for recent work on this) Add a new sysctl so that we can opt-out from this automatic creation. Note that these tunnels are still created for the initial namespace, to be the least intrusive for typical setups. Tested: lpk43:~# cat add_del_unshare.sh for i in `seq 1 40` do (for j in `seq 1 100` ; do unshare -n /bin/true >/dev/null ; done) & done wait lpk43:~# echo 0 >/proc/sys/net/core/fb_tunnels_only_for_init_net lpk43:~# time ./add_del_unshare.sh real 0m37.521s user 0m0.886s sys 7m7.084s lpk43:~# echo 1 >/proc/sys/net/core/fb_tunnels_only_for_init_net lpk43:~# time ./add_del_unshare.sh real 0m4.761s user 0m0.851s sys 1m8.343s lpk43:~# Signed-off-by: NEric Dumazet <edumazet@google.com> Signed-off-by: NDavid S. Miller <davem@davemloft.net>
-
- 09 3月, 2018 2 次提交
-
-
由 Kirill Tkhai 提交于
These pernet_operations are similar to ipv4_net_ops. They are safe to be async. Signed-off-by: NKirill Tkhai <ktkhai@virtuozzo.com> Signed-off-by: NDavid S. Miller <davem@davemloft.net>
-
由 Kirill Tkhai 提交于
The pernet_operations: ip6table_filter_net_ops ip6table_mangle_net_ops ip6table_nat_net_ops ip6table_raw_net_ops ip6table_security_net_ops have exit methods, which call ip6t_unregister_table(). ip6table_filter_net_ops has init method registering filter table. Since there must not be in-flight ipv6 packets at the time of pernet_operations execution and since pernet_operations don't send ipv6 packets each other, these pernet_operations are safe to be async. Signed-off-by: NKirill Tkhai <ktkhai@virtuozzo.com> Signed-off-by: NDavid S. Miller <davem@davemloft.net>
-
- 08 3月, 2018 2 次提交
-
-
由 Eric Dumazet 提交于
Kirill found that recently added synchronize_rcu() call in ip6mr_sk_done() was slowing down netns dismantle and posted a patch to use it only if the socket was found. I instead suggested to get rid of this call, and use instead SOCK_RCU_FREE We might later change IPv4 side to use the same technique and unify both stacks. IPv4 does not use synchronize_rcu() but has a call_rcu() that could be replaced by SOCK_RCU_FREE. Tested: time for i in {1..1000}; do unshare -n /bin/false;done Before : real 7m18.911s After : real 10.187s Fixes: 8571ab47 ("ip6mr: Make mroute_sk rcu-based") Signed-off-by: NEric Dumazet <edumazet@google.com> Reported-by: NKirill Tkhai <ktkhai@virtuozzo.com> Cc: Yuval Mintz <yuvalm@mellanox.com> Reviewed-by: NKirill Tkhai <ktkhai@virtuozzo.com> Signed-off-by: NDavid S. Miller <davem@davemloft.net>
-
由 Gustavo A. R. Silva 提交于
Assign true or false to boolean variables instead of an integer value. This issue was detected with the help of Coccinelle. Signed-off-by: NGustavo A. R. Silva <garsilva@embeddedor.com> Signed-off-by: NDavid S. Miller <davem@davemloft.net>
-
- 05 3月, 2018 9 次提交
-
-
由 Kirill Tkhai 提交于
These pernet_operations call xt_proto_init() and xt_proto_fini(), which just register and unregister /proc entries. They are safe to be marked as async. Signed-off-by: NKirill Tkhai <ktkhai@virtuozzo.com> Signed-off-by: NDavid S. Miller <davem@davemloft.net>
-
由 Kirill Tkhai 提交于
These pernet_operations use nf_log_set() and nf_log_unset() in their methods: nf_log_bridge_net_ops nf_log_arp_net_ops nf_log_ipv4_net_ops nf_log_ipv6_net_ops nf_log_netdev_net_ops Nobody can send such a packet to a net before it's became registered, nobody can send a packet after all netdevices are unregistered. So, these pernet_operations are able to be marked as async. Signed-off-by: NKirill Tkhai <ktkhai@virtuozzo.com> Signed-off-by: NDavid S. Miller <davem@davemloft.net>
-
由 William Tu 提交于
Currently GRE sequence number can only be used in native tunnel mode. This patch adds sequence number support for gre collect metadata mode. RFC2890 defines GRE sequence number to be specific to the traffic flow identified by the key. However, this patch does not implement per-key seqno. The sequence number is shared in the same tunnel device. That is, different tunnel keys using the same collect_md tunnel share single sequence number. Signed-off-by: NWilliam Tu <u9012063@gmail.com> Acked-by: NDaniel Borkmann <daniel@iogearbox.net> Signed-off-by: NDavid S. Miller <davem@davemloft.net>
-
由 Daniel Axtens 提交于
Replace skb_gso_network_seglen() with skb_gso_validate_network_len(), as it considers the GSO_BY_FRAGS case. Signed-off-by: NDaniel Axtens <dja@axtens.net> Reviewed-by: NMarcelo Ricardo Leitner <marcelo.leitner@gmail.com> Signed-off-by: NDavid S. Miller <davem@davemloft.net>
-
由 Daniel Axtens 提交于
If you take a GSO skb, and split it into packets, will the network length (L3 headers + L4 headers + payload) of those packets be small enough to fit within a given MTU? skb_gso_validate_mtu gives you the answer to that question. However, we recently added to add a way to validate the MAC length of a split GSO skb (L2+L3+L4+payload), and the names get confusing, so rename skb_gso_validate_mtu to skb_gso_validate_network_len Signed-off-by: NDaniel Axtens <dja@axtens.net> Reviewed-by: NMarcelo Ricardo Leitner <marcelo.leitner@gmail.com> Signed-off-by: NDavid S. Miller <davem@davemloft.net>
-
由 David Ahern 提交于
Some operators prefer IPv6 path selection to use a standard 5-tuple hash rather than just an L3 hash with the flow the label. To that end add support to IPv6 for multipath hash policy similar to bf4e0a3d ("net: ipv4: add support for ECMP hash policy choice"). The default is still L3 which covers source and destination addresses along with flow label and IPv6 protocol. Signed-off-by: NDavid Ahern <dsahern@gmail.com> Reviewed-by: NIdo Schimmel <idosch@mellanox.com> Tested-by: NIdo Schimmel <idosch@mellanox.com> Reviewed-by: NNikolay Aleksandrov <nikolay@cumulusnetworks.com> Signed-off-by: NDavid S. Miller <davem@davemloft.net>
-
由 David Ahern 提交于
IPv6 does path selection for multipath routes deep in the lookup functions. The next patch adds L4 hash option and needs the skb for the forward path. To get the skb to the relevant FIB lookup functions it needs to go through the fib rules layer, so add a lookup_data argument to the fib_lookup_arg struct. Signed-off-by: NDavid Ahern <dsahern@gmail.com> Reviewed-by: NIdo Schimmel <idosch@mellanox.com> Reviewed-by: NNikolay Aleksandrov <nikolay@cumulusnetworks.com> Signed-off-by: NDavid S. Miller <davem@davemloft.net>
-
由 David Ahern 提交于
Make rt6_multipath_hash more of a direct parallel to fib_multipath_hash and reduce stack and overhead in the process: get_hash_from_flowi6 is just a wrapper around __get_hash_from_flowi6 with another stack allocation for flow_keys. Move setting the addresses, protocol and label into rt6_multipath_hash and allow it to make the call to flow_hash_from_keys. Signed-off-by: NDavid Ahern <dsahern@gmail.com> Reviewed-by: NIdo Schimmel <idosch@mellanox.com> Reviewed-by: NNikolay Aleksandrov <nikolay@cumulusnetworks.com> Signed-off-by: NDavid S. Miller <davem@davemloft.net>
-
由 David Ahern 提交于
Symmetry is good and allows easy comparison that ipv4 and ipv6 are doing the same thing. To that end, change ip_multipath_l3_keys to set addresses at the end after the icmp compares, and move the initialization of ipv6 flow keys to rt6_multipath_hash. Signed-off-by: NDavid Ahern <dsahern@gmail.com> Reviewed-by: NIdo Schimmel <idosch@mellanox.com> Reviewed-by: NNikolay Aleksandrov <nikolay@cumulusnetworks.com> Signed-off-by: NDavid S. Miller <davem@davemloft.net>
-
- 02 3月, 2018 12 次提交
-
-
由 Sabrina Dubroca 提交于
According to RFC 4429 (section 3.1), adding new IPv6 addresses as optimistic addresses is acceptable, as long as the implementation follows some rules: * Optimistic DAD SHOULD only be used when the implementation is aware that the address is based on a most likely unique interface identifier (such as in [RFC2464]), generated randomly [RFC3041], or by a well-distributed hash function [RFC3972] or assigned by Dynamic Host Configuration Protocol for IPv6 (DHCPv6) [RFC3315]. Optimistic DAD SHOULD NOT be used for manually entered addresses. Thus, it seems reasonable to allow userspace to set the optimistic flag when adding new addresses. We must not let userspace set NODAD + OPTIMISTIC, since if the kernel is not performing DAD we would never clear the optimistic flag. We must also ignore userspace's request to add OPTIMISTIC flag to addresses that have already completed DAD (addresses that don't have the TENTATIVE flag, or that have the DADFAILED flag). Then we also need to clear the OPTIMISTIC flag on permanent addresses when DAD fails. Otherwise, IFA_F_OPTIMISTIC addresses added by userspace can still be used after DAD has failed, because in ipv6_chk_addr_and_flags(), IFA_F_OPTIMISTIC overrides IFA_F_TENTATIVE. Setting IFA_F_OPTIMISTIC from userspace is conditional on CONFIG_IPV6_OPTIMISTIC_DAD and the optimistic_dad sysctl. Signed-off-by: NSabrina Dubroca <sd@queasysnail.net> Reviewed-by: NStefano Brivio <sbrivio@redhat.com> Signed-off-by: NDavid S. Miller <davem@davemloft.net>
-
由 Yuval Mintz 提交于
The various MFC entries are being held in the same kind of mr_tables for both ipmr and ip6mr, and their traversal logic is identical. Also, with the exception of the addresses [and other small tidbits] the major bulk of the nla setting is identical. Unite as much of the dumping as possible between the two. Notice this requires creating an mr_table iterator for each, as the for-each preprocessor macro can't be used by the common logic. Signed-off-by: NYuval Mintz <yuvalm@mellanox.com> Acked-by: NNikolay Aleksandrov <nikolay@cumulusnetworks.com> Signed-off-by: NDavid S. Miller <davem@davemloft.net>
-
由 Yuval Mintz 提交于
MFC_NOTIFY exists in ip6mr, probably as some legacy code [was already removed for ipmr in commit 06bd6c03 ("net: ipmr: remove unused MFC_NOTIFY flag and make the flags enum"). Remove it from ip6mr as well, and move the enum into a common file; Notice MFC_OFFLOAD is currently only used by ipmr. Signed-off-by: NYuval Mintz <yuvalm@mellanox.com> Acked-by: NNikolay Aleksandrov <nikolay@cumulusnetworks.com> Signed-off-by: NDavid S. Miller <davem@davemloft.net>
-
由 Yuval Mintz 提交于
Same as previously done with the mfc seq, the logic for the vif seq is refactored to be shared between ipmr and ip6mr. Signed-off-by: NYuval Mintz <yuvalm@mellanox.com> Acked-by: NNikolay Aleksandrov <nikolay@cumulusnetworks.com> Signed-off-by: NDavid S. Miller <davem@davemloft.net>
-
由 Yuval Mintz 提交于
With the exception of the final dump, ipmr and ip6mr have the exact same seq logic for traversing a given mr_table. Refactor that code and make it common. Signed-off-by: NYuval Mintz <yuvalm@mellanox.com> Acked-by: NNikolay Aleksandrov <nikolay@cumulusnetworks.com> Signed-off-by: NDavid S. Miller <davem@davemloft.net>
-
由 Yuval Mintz 提交于
ipmr and ip6mr utilize the exact same methods for searching the hashed resolved connections, difference being only in the construction of the hash comparison key. In order to unite the flow, introduce an mr_table operation set that would contain the protocol specific information required for common flows, in this case - the hash parameters and a comparison key representing a (*,*) route. Signed-off-by: NYuval Mintz <yuvalm@mellanox.com> Acked-by: NNikolay Aleksandrov <nikolay@cumulusnetworks.com> Signed-off-by: NDavid S. Miller <davem@davemloft.net>
-
由 Yuval Mintz 提交于
mfc_cache and mfc6_cache are almost identical - the main difference is in the origin/group addresses and comparison-key. Make a common structure encapsulating most of the multicast routing logic - mr_mfc and convert both ipmr and ip6mr into using it. For easy conversion [casting, in this case] mr_mfc has to be the first field inside every multicast routing abstraction utilizing it. Signed-off-by: NYuval Mintz <yuvalm@mellanox.com> Acked-by: NNikolay Aleksandrov <nikolay@cumulusnetworks.com> Signed-off-by: NDavid S. Miller <davem@davemloft.net>
-
由 Yuval Mintz 提交于
Now that both ipmr and ip6mr are using the same mr_table structure, we can have a common function to allocate & initialize a new instance. Signed-off-by: NYuval Mintz <yuvalm@mellanox.com> Acked-by: NNikolay Aleksandrov <nikolay@cumulusnetworks.com> Signed-off-by: NDavid S. Miller <davem@davemloft.net>
-
由 Yuval Mintz 提交于
Following previous changes to ip6mr, mr_table and mr6_table are basically the same [up to mr6_table having additional '6' suffixes to its variable names]. Move the common structure definition into a common header; This requires renaming all references in ip6mr to variables that had the distinct suffix. Signed-off-by: NYuval Mintz <yuvalm@mellanox.com> Acked-by: NNikolay Aleksandrov <nikolay@cumulusnetworks.com> Signed-off-by: NDavid S. Miller <davem@davemloft.net>
-
由 Yuval Mintz 提交于
Since commit 8fb472c0 ("ipmr: improve hash scalability") ipmr has been using rhashtable as a basis for its mfc routes, but ip6mr is currently still using the old private MFC hash implementation. Align ip6mr to the current ipmr implementation. Signed-off-by: NYuval Mintz <yuvalm@mellanox.com> Acked-by: NNikolay Aleksandrov <nikolay@cumulusnetworks.com> Signed-off-by: NDavid S. Miller <davem@davemloft.net>
-
由 Yuval Mintz 提交于
In ipmr the mr_table socket is handled under RCU. Introduce the same for ip6mr. Signed-off-by: NYuval Mintz <yuvalm@mellanox.com> Acked-by: NNikolay Aleksandrov <nikolay@cumulusnetworks.com> Signed-off-by: NDavid S. Miller <davem@davemloft.net>
-
由 Yuval Mintz 提交于
The two implementations have almost identical structures - vif_device and mif_device. As a step toward uniforming the mr_tables, eliminate the mif_device and relocate the vif_device definition into a new common header file. Also, introduce a common initializing function for setting most of the vif_device fields in a new common source file. This requires modifying the ipv{4,6] Kconfig and ipv4 makefile as we're introducing a new common config option - CONFIG_IP_MROUTE_COMMON. Signed-off-by: NYuval Mintz <yuvalm@mellanox.com> Acked-by: NNikolay Aleksandrov <nikolay@cumulusnetworks.com> Signed-off-by: NDavid S. Miller <davem@davemloft.net>
-
- 01 3月, 2018 3 次提交
-
-
由 Roopa Prabhu 提交于
Dissect flow in fwd path if fib rules require it. Controlled by a flag to avoid penatly for the common case. Flag is set when fib rules with sport, dport and proto match that require flow dissect are installed. Also passes the dissected hash keys to the multipath hash function when applicable to avoid dissecting the flow again. icmp packets will continue to use inner header for hash calculations. Signed-off-by: NRoopa Prabhu <roopa@cumulusnetworks.com> Acked-by: NPaolo Abeni <pabeni@redhat.com> Acked-by: NNikolay Aleksandrov <nikolay@cumulusnetworks.com> Signed-off-by: NDavid S. Miller <davem@davemloft.net>
-
由 Roopa Prabhu 提交于
support to match on src port, dst port and ip protocol. Signed-off-by: NRoopa Prabhu <roopa@cumulusnetworks.com> Acked-by: NNikolay Aleksandrov <nikolay@cumulusnetworks.com> Signed-off-by: NDavid S. Miller <davem@davemloft.net>
-
由 Stephen Hemminger 提交于
Ran simple script to find/remove trailing whitespace and blank lines at EOF because that kind of stuff git whines about and editors leave behind. Signed-off-by: NStephen Hemminger <stephen@networkplumber.org> Signed-off-by: NDavid S. Miller <davem@davemloft.net>
-
- 28 2月, 2018 10 次提交
-
-
由 Petr Machata 提交于
Determining whether a device is a GRE device is easily done by inspecting struct net_device.type. However, for the tap variants, the type is just ARPHRD_ETHER. Therefore introduce two predicate functions that use netdev_ops to tell the tap devices. Signed-off-by: NPetr Machata <petrm@mellanox.com> Reviewed-by: NIdo Schimmel <idosch@mellanox.com> Signed-off-by: NJiri Pirko <jiri@mellanox.com> Signed-off-by: NDavid S. Miller <davem@davemloft.net>
-
由 Xin Long 提交于
Commit 128bb975 ("ip6_gre: init dev->mtu and dev->hard_header_len correctly") fixed IFLA_MTU ignored on NEWLINK for ip6_gre. The same mtu fix is also needed for sit. Note that dev->hard_header_len setting for sit works fine, no need to fix it. sit is actually ipv4 tunnel, it can't call ip6_tnl_change_mtu to set mtu. Reported-by: NJianlin Shi <jishi@redhat.com> Signed-off-by: NXin Long <lucien.xin@gmail.com> Signed-off-by: NDavid S. Miller <davem@davemloft.net>
-
由 Xin Long 提交于
Commit 128bb975 ("ip6_gre: init dev->mtu and dev->hard_header_len correctly") fixed IFLA_MTU ignored on NEWLINK for ip6_gre. The same mtu fix is also needed for ip6_tunnel. Note that dev->hard_header_len setting for ip6_tunnel works fine, no need to fix it. Reported-by: NJianlin Shi <jishi@redhat.com> Signed-off-by: NXin Long <lucien.xin@gmail.com> Signed-off-by: NDavid S. Miller <davem@davemloft.net>
-
由 Kirill Tkhai 提交于
These pernet_operations only unregister nf hooks. So, they are able to be marked as async. Signed-off-by: NKirill Tkhai <ktkhai@virtuozzo.com> Signed-off-by: NDavid S. Miller <davem@davemloft.net>
-
由 Kirill Tkhai 提交于
These pernet_operations register and unregister nf hooks. Also they populate and depopulate ila_net_id-pointed hash table. The table is changed by hooks during skb processing and via netlink request. It looks impossible for another net pernet_operations to force the table reading or writing, so, they are able to be marked as async. Signed-off-by: NKirill Tkhai <ktkhai@virtuozzo.com> Signed-off-by: NDavid S. Miller <davem@davemloft.net>
-
由 Kirill Tkhai 提交于
These pernet_operations are similar to ip6_tnl_net_ops. Exit method unregisters all net sit devices, and it looks like another pernet_operations are not interested in foreign net sit list. Init method registers netdevice. So, it's possible to mark them async. Signed-off-by: NKirill Tkhai <ktkhai@virtuozzo.com> Signed-off-by: NDavid S. Miller <davem@davemloft.net>
-
由 Kirill Tkhai 提交于
These pernet_operations are similar to ip6_tnl_net_ops. Exit method unregisters all net vti6 tunnels, and it looks like another pernet_operations are not interested in foreign net vti6 list. Init method registers netdevice. So, it's possible to mark them async. Signed-off-by: NKirill Tkhai <ktkhai@virtuozzo.com> Signed-off-by: NDavid S. Miller <davem@davemloft.net>
-
由 Kirill Tkhai 提交于
These pernet_operations are similar to ip6gre_net_ops. Exit method unregisters all net ip6_tnl tunnels, and it looks like another pernet_operations are not interested in foreign net tunnels list. So, it's possible to mark them async. Signed-off-by: NKirill Tkhai <ktkhai@virtuozzo.com> Signed-off-by: NDavid S. Miller <davem@davemloft.net>
-
由 Kirill Tkhai 提交于
These pernet_operations are similar to bond_net_ops. Exit method unregisters all net ip6gre devices, and it looks like another pernet_operations are not interested in foreign net ip6gre list or net_generic()->tunnels_wc. Init method registers net device. So, it's possible to mark them async. Signed-off-by: NKirill Tkhai <ktkhai@virtuozzo.com> Signed-off-by: NDavid S. Miller <davem@davemloft.net>
-
由 Kirill Tkhai 提交于
These pernet_operations make pretty simple actions like variable initialization on init, debug checks on exit, and so on, and they obviously are able to be executed in parallel with any others: vrf_net_ops lockd_net_ops grace_net_ops xfrm6_tunnel_net_ops kcm_net_ops tcf_net_ops Signed-off-by: NKirill Tkhai <ktkhai@virtuozzo.com> Signed-off-by: NDavid S. Miller <davem@davemloft.net>
-
- 26 2月, 2018 1 次提交
-
-
由 Eric Dumazet 提交于
For some reason, Florian forgot to apply to ip6_route_me_harder the fix that went in commit 29e09229 ("netfilter: use skb_to_full_sk in ip_route_me_harder") Fixes: ca6fb065 ("tcp: attach SYNACK messages to request sockets instead of listener") Signed-off-by: NEric Dumazet <edumazet@google.com> Reported-by: Nsyzbot <syzkaller@googlegroups.com> Signed-off-by: NPablo Neira Ayuso <pablo@netfilter.org>
-