- 18 Feb, 2016 6 commits
-
-
Florian Westphal authored
This reverts commit bb9b18fb ("genl: Add genlmsg_new_unicast() for unicast message allocation")'. Nothing wrong with it; its no longer needed since this was only for mmapped netlink support. Signed-off-by:
Florian Westphal <fw@strlen.de> Signed-off-by:
David S. Miller <davem@davemloft.net>
-
Florian Westphal authored
revert commit 795449d8 ("openvswitch: Enable memory mapped Netlink i/o"). Following the mmaped netlink removal this code can be removed. Signed-off-by:
-
Florian Westphal authored
mmapped netlink has a number of unresolved issues: - TX zerocopy support had to be disabled more than a year ago via commit 4682a035 ("netlink: Always copy on mmap TX.") because the content of the mmapped area can change after netlink attribute validation but before message processing. - RX support was implemented mainly to speed up nfqueue dumping packet payload to userspace. However, since commit ae08ce00 ("netfilter: nfnetlink_queue: zero copy support") we avoid one copy with the socket-based interface too (via the skb_zerocopy helper). The other problem is that skbs attached to mmaped netlink socket behave different from normal skbs: - they don't have a shinfo area, so all functions that use skb_shinfo() (e.g. skb_clone) cannot be used. - reserving headroom prevents userspace from seeing the content as it expects message to start at skb->head. See for instance commit aa3a0220 ("netlink: not trim skb for mmaped socket when dump"). - skbs handed e.g. to netlink_ack must have non-NULL skb->sk, else we crash because it needs the sk to check if a tx ring is attached. Also not obvious, leads to non-intuitive bug fixes such as 7c7bdf35 ("netfilter: nfnetlink: use original skbuff when acking batches"). mmaped netlink also didn't play nicely with the skb_zerocopy helper used by nfqueue and openvswitch. Daniel Borkmann fixed this via commit 6bb0fef4 ("netlink, mmap: fix edge-case leakages in nf queue zero-copy")' but at the cost of also needing to provide remaining length to the allocation function. nfqueue also has problems when used with mmaped rx netlink: - mmaped netlink doesn't allow use of nfqueue batch verdict messages. Problem is that in the mmap case, the allocation time also determines the ordering in which the frame will be seen by userspace (A allocating before B means that A is located in earlier ring slot, but this also means that B might get a lower sequence number then A since seqno is decided later. To fix this we would need to extend the spinlocked region to also cover the allocation and message setup which isn't desirable. - nfqueue can now be configured to queue large (GSO) skbs to userspace. Queing GSO packets is faster than having to force a software segmentation in the kernel, so this is a desirable option. However, with a mmap based ring one has to use 64kb per ring slot element, else mmap has to fall back to the socket path (NL_MMAP_STATUS_COPY) for all large packets. To use the mmap interface, userspace not only has to probe for mmap netlink support, it also has to implement a recv/socket receive path in order to handle messages that exceed the size of an rx ring element. Cc: Daniel Borkmann <daniel@iogearbox.net> Cc: Ken-ichirou MATSUZAWA <chamaken@gmail.com> Cc: Pablo Neira Ayuso <pablo@netfilter.org> Cc: Patrick McHardy <kaber@trash.net> Cc: Thomas Graf <tgraf@suug.ch> Signed-off-by:
-
Jamal Hadi Salim authored
Signed-off-by:
Jamal Hadi Salim <jhs@mojatatu.com> Acked-by:
Daniel Borkmann <daniel@iogearbox.net> Signed-off-by:
-
Ido Schimmel authored
When VLANs are created / destroyed on a VLAN filtering bridge (MASTER flag set), the configuration is passed down to the hardware. However, when only the flags (e.g. PVID) are toggled, the configuration is done in the software bridge alone. While it is possible to pass these flags to hardware when invoked with the SELF flag set, this creates inconsistency with regards to the way the VLANs are initially configured. Pass the flags down to the hardware even when the VLAN already exists and only the flags are toggled. Signed-off-by:
Ido Schimmel <idosch@mellanox.com> Signed-off-by:
Jiri Pirko <jiri@mellanox.com> Signed-off-by:
-
Colin Ian King authored
Ever since commit 04ed3e74 ("net: change netdev->features to u32") the format string fmt_long_hex has not been used, so we may as well remove it. Signed-off-by:
Colin Ian King <colin.king@canonical.com> Signed-off-by:
-
- 17 Feb, 2016 11 commits
-
-
Zhang Shengju authored
Since function vlan_proc_rem_dev() will only return 0, it's better to return void instead of int. Signed-off-by:
Zhang Shengju <zhangshengju@cmss.chinamobile.com> Signed-off-by:
-
Ben Hutchings authored
There are no longer any in-tree drivers that use it. Signed-off-by:
Ben Hutchings <ben@decadent.org.uk> Signed-off-by:
-
One Thousand Gnomes authored
The timeout is a long, we return it truncated if it is huge. Basically harmless as the only caller does a boolean check, but tidy it up anyway. (64bit build tested this time. Thank you 0day) Signed-off-by:
Alan Cox <alan@linux.intel.com> Signed-off-by:
-
Xin Long authored
Since commit 8b570dc9 ("sctp: only drop the reference on the datamsg after sending a msg") used sctp_datamsg_put in sctp_sendmsg, instead of sctp_datamsg_free, this function has no use in sctp. So we will remove it. Signed-off-by:
Xin Long <lucien.xin@gmail.com> Signed-off-by:
-
Xin Long authored
sctp_seq_dump_remote_addrs is only called by sctp_assocs_seq_show() and it has been protected by rcu_read_lock that is from rhashtable_walk_start(). So we will remove this one. Signed-off-by:
-
Xin Long authored
__sctp_lookup_association() is only invoked by sctp_v4_err() and sctp_rcv(), both which run on the rx BH, and it has been protected by rcu_read_lock [see ip_local_deliver_finish() / ipv6_rcv()]. So we can move it to sctp_lookup_association, only let sctp_lookup_association use rcu_read_lock. Signed-off-by:
-
Rosen, Rami authored
commit 3ed80a62 (cgroup: drop module support) made including module.h redundant in the net cgroup controllers, netclassid_cgroup.c and netprio_cgroup.c. This patch removes them. Signed-off-by:
Rami Rosen <rami.rosen@intel.com> Acked-by:
Tejun Heo <tj@kernel.org> Signed-off-by:
-
John Fastabend authored
Its useful to turn off the qdisc offload feature at a per device level. This gives us a big hammer to enable/disable offloading. More fine grained control (i.e. per rule) may be supported later. Signed-off-by:
John Fastabend <john.r.fastabend@intel.com> Acked-by:
-
John Fastabend authored
This patch allows netdev drivers to consume cls_u32 offloads via the ndo_setup_tc ndo op. This works aligns with how network drivers have been doing qdisc offloads for mqprio. Signed-off-by:
-
John Fastabend authored
This patch updates setup_tc so we can pass additional parameters into the ndo op in a generic way. To do this we provide structured union and type flag. This lets each classifier and qdisc provide its own set of attributes without having to add new ndo ops or grow the signature of the callback. Signed-off-by:
-
John Fastabend authored
The ndo_setup_tc() op was added to support drivers offloading tx qdiscs however only support for mqprio was ever added. So we only ever added support for passing the number of traffic classes to the driver. This patch generalizes the ndo_setup_tc op so that a handle can be provided to indicate if the offload is for ingress or egress or potentially even child qdiscs. CC: Murali Karicheri <m-karicheri2@ti.com> CC: Shradha Shah <sshah@solarflare.com> CC: Or Gerlitz <ogerlitz@mellanox.com> CC: Ariel Elior <ariel.elior@qlogic.com> CC: Jeff Kirsher <jeffrey.t.kirsher@intel.com> CC: Bruce Allan <bruce.w.allan@intel.com> CC: Jesse Brandeburg <jesse.brandeburg@intel.com> CC: Don Skidmore <donald.c.skidmore@intel.com> Signed-off-by:
-
- 16 Feb, 2016 15 commits
-
-
Nikolay Borisov authored
Now that all the ip fragmentation related sysctls are namespaceified there is no reason to hide them anymore from "root" users inside containers. Signed-off-by:
Nikolay Borisov <kernel@kyup.com> Signed-off-by:
-
Nikolay Borisov authored
Signed-off-by:
-
Nikolay Borisov authored
Signed-off-by:
-
Nikolay Borisov authored
Signed-off-by:
-
Nikolay Borisov authored
When igmp related sysctl were namespacified their initializatin was erroneously put into the tcp socket namespace constructor. This patch moves the relevant code into the igmp namespace constructor to keep things consistent. Also sprinkle some #ifdefs to silence warnings Signed-off-by:
-
Nikolay Borisov authored
Signed-off-by:
-
Eric Dumazet authored
tcpi_min_rtt reports the minimal rtt observed by TCP stack for the flow, in usec unit. Might be ~0U if not yet known. tcpi_notsent_bytes reports the amount of bytes in the write queue that were not yet sent. This is done in a single patch to not add a temporary 32bit padding hole in tcp_info. Signed-off-by:
Eric Dumazet <edumazet@google.com> Signed-off-by:
-
Paolo Abeni authored
In case of UDP traffic with datagram length below MTU this gives about 4% performance increase Signed-off-by:
Paolo Abeni <pabeni@redhat.com> Suggested-and-Acked-by:
Hannes Frederic Sowa <hannes@stressinduktion.org> Signed-off-by:
-
Paolo Abeni authored
In case of UDP traffic with datagram length below MTU this give about 2% performance increase when tunneling over ipv4 and about 60% when tunneling over ipv6 Signed-off-by:
-
Paolo Abeni authored
The current ip_tunnel cache implementation is prone to a race that will cause the wrong dst to be cached on cuncurrent dst cache miss and ip tunnel update via netlink. Replacing with the generic implementation fix the issue. Signed-off-by:
-
Paolo Abeni authored
This also fix a potential race into the existing tunnel code, which could lead to the wrong dst to be permanenty cached: CPU1: CPU2: <xmit on ip6_tunnel> <cache lookup fails> dst = ip6_route_output(...) <tunnel params are changed via nl> dst_cache_reset() // no effect, // the cache is empty dst_cache_set() // the wrong dst // is permanenty stored // into the cache With the new dst implementation the above race is not possible since the first cache lookup after dst_cache_reset will fail due to the timestamp check Signed-off-by:
-
Paolo Abeni authored
This patch add a generic, lockless dst cache implementation. The need for lock is avoided updating the dst cache fields only in per cpu scope, and requiring that the cache manipulation functions are invoked with the local bh disabled. The refresh_ts and reset_ts fields are used to ensure the cache consistency in case of cuncurrent cache update (dst_cache_set*) and reset operation (dst_cache_reset). Consider the following scenario: CPU1: CPU2: <cache lookup with emtpy cache: it fails> <get dst via uncached route lookup> <related configuration changes> dst_cache_reset() dst_cache_set() The dst entry set passed to dst_cache_set() should not be used for later dst cache lookup, because it's obtained using old configuration values. Since the refresh_ts is updated only on dst_cache lookup, the cached value in the above scenario will be discarded on the next lookup. Signed-off-by: -
Richard Alpe authored
Refactor tipc_node_xmit() to fail fast and fail early. Fix several potential memory leaks in unexpected error paths. Reported-by:
Dmitry Vyukov <dvyukov@google.com> Reviewed-by:
Jon Maloy <jon.maloy@ericsson.com> Signed-off-by:
Richard Alpe <richard.alpe@ericsson.com> Signed-off-by:
-
Keller, Jacob E authored
Add a sanity check to ensure that all requested channel sizes are within bounds, which should reduce errors in driver implementation. Signed-off-by:
Jacob Keller <jacob.e.keller@intel.com> Signed-off-by:
-
Keller, Jacob E authored
Ethernet drivers implementing both {GS}RXFH and {GS}CHANNELS ethtool ops incorrectly allow SCHANNELS when it would conflict with the settings from SRXFH. This occurs because it is not possible for drivers to understand whether their Rx flow indirection table has been configured or is in the default state. In addition, drivers currently behave in various ways when increasing the number of Rx channels. Some drivers will always destroy the Rx flow indirection table when this occurs, whether it has been set by the user or not. Other drivers will attempt to preserve the table even if the user has never modified it from the default driver settings. Neither of these situation is desirable because it leads to unexpected behavior or loss of user configuration. The correct behavior is to simply return -EINVAL when SCHANNELS would conflict with the current Rx flow table settings. However, it should only do so if the current settings were modified by the user. If we required that the new settings never conflict with the current (default) Rx flow settings, we would force users to first reduce their Rx flow settings and then reduce the number of Rx channels. This patch proposes a solution implemented in net/core/ethtool.c which ensures that all drivers behave correctly. It checks whether the RXFH table has been configured to non-default settings, and stores this information in a private netdev flag. When the number of channels is requested to change, it first ensures that the current Rx flow table is not going to assign flows to now disabled channels. Signed-off-by:
-
- 12 Feb, 2016 7 commits
-
-
Edward Cree authored
All users now pass false, so we can remove it, and remove the code that was conditional upon it. Signed-off-by:
Edward Cree <ecree@solarflare.com> Signed-off-by:
-
Edward Cree authored
Signed-off-by:
-
Edward Cree authored
Signed-off-by:
-
Edward Cree authored
If the dst device doesn't support it, it'll get fixed up later anyway by validate_xmit_skb(). Also, this allows us to take advantage of LCO to avoid summing the payload multiple times. Signed-off-by:
-
Edward Cree authored
The arithmetic properties of the ones-complement checksum mean that a correctly checksummed inner packet, including its checksum, has a ones complement sum depending only on whatever value was used to initialise the checksum field before checksumming (in the case of TCP and UDP, this is the ones complement sum of the pseudo header, complemented). Consequently, if we are going to offload the inner checksum with CHECKSUM_PARTIAL, we can compute the outer checksum based only on the packed data not covered by the inner checksum, and the initial value of the inner checksum field. Signed-off-by:
-
Eric Dumazet authored
Implement strategy used in __inet_hash_connect() in opposite way : Try to find a candidate using odd ports, then fallback to even ports. We no longer disable BH for whole traversal, but one bucket at a time. We also use cond_resched() to yield cpu to other tasks if needed. I removed one indentation level and tried to mirror the loop we have in __inet_hash_connect() and variable names to ease code maintenance. Signed-off-by:
-
Eric Dumazet authored
In commit 07f4c900 ("tcp/dccp: try to not exhaust ip_local_port_range in connect()"), I added a very simple heuristic, so that we got better chances to use even ports, and allow bind() users to have more available slots. It gave nice results, but with more than 200,000 TCP sessions on a typical server, the ~30,000 ephemeral ports are still a rare resource. I chose to go a step further, by looking at all even ports, and if none was available, fallback to odd ports. The companion patch does the same in bind(), but in opposite way. I've seen exec times of up to 30ms on busy servers, so I no longer disable BH for the whole traversal, but only for each hash bucket. I also call cond_resched() to be gentle to other tasks. Signed-off-by:
-
- 11 Feb, 2016 1 commit
-
-
Jesper Dangaard Brouer authored
The network stack defers SKBs free, in-case free happens in IRQ or when IRQs are disabled. This happens in __dev_kfree_skb_irq() that writes SKBs that were free'ed during IRQ to the softirq completion queue (softnet_data.completion_queue). These SKBs are naturally delayed, and cleaned up during NET_TX_SOFTIRQ in function net_tx_action(). Take advantage of this a use the skb defer and flush API, as we are already in softirq context. For modern drivers this rarely happens. Although most drivers do call dev_kfree_skb_any(), which detects the situation and calls __dev_kfree_skb_irq() when needed. This due to netpoll can call from IRQ context. Signed-off-by:
Alexander Duyck <alexander.h.duyck@redhat.com> Signed-off-by:
Jesper Dangaard Brouer <brouer@redhat.com> Signed-off-by:
-
