- 28 Jan, 2008 40 commits
-
-
Pavel Emelyanov authored
Same as in the previous patch for ipv4, compact the API and hide hash table and rwlock inside the raw.c file. Plus fix some "bad" places from checkpatch.pl point of view (assignments inside if()). Signed-off-by:
Pavel Emelyanov <xemul@openvz.org> Signed-off-by:
David S. Miller <davem@davemloft.net>
-
Pavel Emelyanov authored
The raw sockets functions are explicitly used from inside the kernel in two places: 1. in ip_local_deliver_finish to intercept skb-s 2. in icmp_error For this purposes many functions and even data structures, that are naturally internal for raw protocol, are exported. Compact the API to two functions and hide all the other (including hash table and rwlock) inside the net/ipv4/raw.c Signed-off-by:
-
Denis V. Lunev authored
Signed-off-by:
Denis V. Lunev <den@openvz.org> Signed-off-by:
-
Denis V. Lunev authored
Because of the global nature of garbage collection, and because of the cost of per namespace hash tables unix_socket_table has been kept global. With a filter added on lookups so we don't see sockets from the wrong namespace. Currently I don't fold the namesapce into the hash so multiple namespaces using the same socket name will be guaranteed a hash collision. Changes from v1: - fixed unix_seq_open Signed-off-by:
Eric W. Biederman <ebiederm@xmission.com> Signed-off-by:
-
Denis V. Lunev authored
This is done by making packet_sklist_lock and packet_sklist per network namespace and adding an additional filter condition on received packets to ensure they came from the proper network namespace. Changes from v1: - prohibit to call inet_dgram_ops.ioctl in other than init_net Signed-off-by:
-
Eric W. Biederman authored
After the previous prep work this just consists of removing checks limiting the code to work in the initial network namespace, and updating rtmsg_ifinfo so we can generate events for devices in something other then the initial network namespace. Referring to network other network devices like the IFLA_LINK and IFLA_MASTER attributes do, gets interesting if those network devices happen to be in other network namespaces. Currently ifindex numbers are allocated globally so I have taken the path of least resistance and not still report the information even though the devices they are talking about are invisible. If applications start getting confused or when ifindex numbers become local to the network namespace we may need to do something different in the future. Signed-off-by:
Denis V. Lunev <den@openz.org> Signed-off-by:
-
Denis V. Lunev authored
After this patch none of the netlink callback support anything except the initial network namespace but the rtnetlink infrastructure now handles multiple network namespaces. Changes from v2: - IPv6 addrlabel processing Changes from v1: - no need for special rtnl_unlock handling - fixed IPv6 ndisc Signed-off-by:
-
Denis V. Lunev authored
Before I can enable rtnetlink to work in all network namespaces I need to be certain that something won't break. So this patch deliberately disables all of the rtnletlink methods in everything except the initial network namespace. After the methods have been audited this extra check can be disabled. Changes from v1: - added IPv6 addrlabel protection Signed-off-by:
Herbert Xu <herbert@gondor.apana.org.au>
-
Patrick McHardy authored
Signed-off-by:
Patrick McHardy <kaber@trash.net> Signed-off-by:
-
Patrick McHardy authored
Only devices that are UP are in the hash, so macvlan_broadcast() doesn't need to check for IFF_UP. Signed-off-by:
-
David S. Miller authored
Based upon a suggestion by Francois Romieu. Signed-off-by: -
Rumen G. Bogdanovski authored
With this patch the synced connections are created with their real state, which can be changed on the next synchronizations if necessary. This way on fail-over all the connections will be treated according to their actual state, causing no scheduling problems (the active and the nonactive connections have different weights in the schedulers). The backwards compatibility is preserved and the existing tools will show the true connection states even on the backup director. Signed-off-by:
Rumen G. Bogdanovski <rumen@voicecho.com> Signed-off-by:
Simon Horman <horms@verge.net.au> Signed-off-by:
-
Rumen G. Bogdanovski authored
This patch labels the sync-created connections with IP_VS_CONN_F_SYNC flag and creates /proc/net/ip_vs_conn_sync to enable monitoring of the origin of the connections, if they are local or created by the synchronization. Signed-off-by:
-
Michael Wu authored
This patch adds IEEE80211_MAX_FRAME_LEN which is useful for drivers trying to determine how much to allocate for their RX buffers. It also updates the comment on IEEE80211_MAX_DATA_LEN based on revisions in 802.11e. IEEE80211_MAX_FRAG_THRESHOLD and IEEE80211_MAX_RTS_THRESHOLD are also revised due to the new maximum frame size. Signed-off-by:
Michael Wu <flamingice@sourmilk.net> Signed-off-by:
John W. Linville <linville@tuxdriver.com> Signed-off-by:
-
Mattias Nissler authored
This changes the SIWTXPOWER ioctl to also accept a txpower setting of "automatic". Since mac80211 currently cannot tell drivers to automatically adjust tx power, we select the tx power level of the current channel. While this is kind of a hack, it certainly saves some iwconfig users from headaches. Signed-off-by:
Mattias Nissler <mattias.nissler@gmx.de> Signed-off-by:
-
Stephen Hemminger authored
The rx_flags variable is redundant. Turning rx on/off is done via setting the rx_np pointer. Signed-off-by:
Stephen Hemminger <shemminger@linux-foundation.org> Signed-off-by:
-
Stephen Hemminger authored
Signed-off-by:
-
Stephen Hemminger authored
The local_mac is managed by the network device, no need to keep a spare copy and all the management problems that could cause. Signed-off-by:
-
Stephen Hemminger authored
Restructure code slightly to improve readability: * dereference device once * change obvious while() loop * let poll_napi() handle null list itself Signed-off-by:
-
Stephen Hemminger authored
Use standard routine for flushing queue. Signed-off-by:
-
Ilpo Järvinen authored
Previously one of the in-block skip branches was missing it. Also, drop it from tail-fully-processed case because the next iteration will do exactly the same thing, i.e., process the SACK block that contains the DSACK information. Signed-off-by:
Ilpo Järvinen <ilpo.jarvinen@helsinki.fi> Signed-off-by:
-
Oliver Hartkopp authored
This patch adds documentation for the PF_CAN protocol family. Signed-off-by:
Oliver Hartkopp <oliver.hartkopp@volkswagen.de> Signed-off-by:
Urs Thuermann <urs.thuermann@volkswagen.de> Signed-off-by:
-
Oliver Hartkopp authored
This patch adds entries in the CREDITS and MAINTAINERS file for CAN. Signed-off-by:
-
Oliver Hartkopp authored
This patch adds the missing Kbuild entries and the missing Kbuild file in include/linux/can for the CAN subsystem. Signed-off-by:
Oliver Hartkopp <oliver@hartkopp.net> Acked-by:
Sam Ravnborg <sam@ravnborg.org> Signed-off-by:
-
Oliver Hartkopp authored
This patch fixes the use of plain integers instead of __u32 in a struct that is visible from kernel space and user space. Thanks to Sam Ravnborg for pointing out the wrong plain int usage. Signed-off-by:
-
Oliver Hartkopp authored
This patch adds the virtual CAN bus (vcan) network driver. The vcan device is just a loopback device for CAN frames, no real CAN hardware is involved. Signed-off-by:
-
Oliver Hartkopp authored
This patch adds the CAN broadcast manager (bcm) protocol. Signed-off-by:
-
Oliver Hartkopp authored
This patch adds the CAN raw protocol. Signed-off-by:
-
Oliver Hartkopp authored
This patch adds the CAN core functionality but no protocols or drivers. No protocol implementations are included here. They come as separate patches. Protocol numbers are already in include/linux/can.h. Signed-off-by:
-
Oliver Hartkopp authored
This patch adds a protocol/address family number, ARP hardware type, ethernet packet type, and a line discipline number for the SocketCAN implementation. Signed-off-by:
-
Eric Dumazet authored
ip_rt_acct needs 4096 bytes per cpu to perform some accounting. It is actually allocated as a single huge array [4096*NR_CPUS] (rounded up to a power of two) Converting it to a per cpu variable is wanted to : - Save space on machines were num_possible_cpus() < NR_CPUS - Better NUMA placement (each cpu gets memory on its node) Signed-off-by:
Eric Dumazet <dada1@cosmosbay.com> Signed-off-by:
-
Ilpo Järvinen authored
Key points of this patch are: - In case new SACK information is advance only type, no skb processing below previously discovered highest point is done - Optimize cases below highest point too since there's no need to always go up to highest point (which is very likely still present in that SACK), this is not entirely true though because I'm dropping the fastpath_skb_hint which could previously optimize those cases even better. Whether that's significant, I'm not too sure. Currently it will provide skipping by walking. Combined with RB-tree, all skipping would become fast too regardless of window size (can be done incrementally later). Previously a number of cases in TCP SACK processing fails to take advantage of costly stored information in sack_recv_cache, most importantly, expected events such as cumulative ACK and new hole ACKs. Processing on such ACKs result in rather long walks building up latencies (which easily gets nasty when window is huge). Those latencies are often completely unnecessary compared with the amount of _new_ information received, usually for cumulative ACK there's no new information at all, yet TCP walks whole queue unnecessary potentially taking a number of costly cache misses on the way, etc.! Since the inclusion of highest_sack, there's a lot information that is very likely redundant (SACK fastpath hint stuff, fackets_out, highest_sack), though there's no ultimate guarantee that they'll remain the same whole the time (in all unearthly scenarios). Take advantage of this knowledge here and drop fastpath hint and use direct access to highest SACKed skb as a replacement. Effectively "special cased" fastpath is dropped. This change adds some complexity to introduce better coveraged "fastpath", though the added complexity should make TCP behave more cache friendly. The current ACK's SACK blocks are compared against each cached block individially and only ranges that are new are then scanned by the high constant walk. For other parts of write queue, even when in previously known part of the SACK blocks, a faster skip function is used (if necessary at all). In addition, whenever possible, TCP fast-forwards to highest_sack skb that was made available by an earlier patch. In typical case, no other things but this fast-forward and mandatory markings after that occur making the access pattern quite similar to the former fastpath "special case". DSACKs are special case that must always be walked. The local to recv_sack_cache copying could be more intelligent w.r.t DSACKs which are likely to be there only once but that is left to a separate patch. Signed-off-by: -
Ilpo Järvinen authored
Signed-off-by:
-
Ilpo Järvinen authored
Worker function that implements the main logic of the inner-most loop of tcp_sacktag_write_queue(). Idea was originally presented by David S. Miller. Signed-off-by:
-
Ilpo Järvinen authored
Signed-off-by:
-
Ilpo Järvinen authored
Highest_sack_end_seq is no longer calculated in the loop, thus it can be pushed to the worker function altogether making that function independent of the sacktag. Signed-off-by:
-
Ilpo Järvinen authored
It is going to replace the sack fastpath hint quite soon... :-) Signed-off-by:
-
Ilpo Järvinen authored
Many assumptions that are true when no reordering or other strange events happen are not a part of the RFC3517. FACK implementation is based on such assumptions. Previously (before the rewrite) the non-FACK SACK was basically doing fast rexmit and then it times out all skbs when first cumulative ACK arrives, which cannot really be called SACK based recovery :-). RFC3517 SACK disables these things: - Per SKB timeouts & head timeout entry to recovery - Marking at least one skb while in recovery (RFC3517 does this only for the fast retransmission but not for the other skbs when cumulative ACKs arrive in the recovery) - Sacktag's loss detection flavors B and C (see comment before tcp_sacktag_write_queue) This does not implement the "last resort" rule 3 of NextSeg, which allows retransmissions also when not enough SACK blocks have yet arrived above a segment for IsLost to return true [RFC3517]. The implementation differs from RFC3517 in these points: - Rate-halving is used instead of FlightSize / 2 - Instead of using dupACKs to trigger the recovery, the number of SACK blocks is used as FACK does with SACK blocks+holes (which provides more accurate number). It seems that the difference can affect negatively only if the receiver does not generate SACK blocks at all even though it claimed to be SACK-capable. - Dupthresh is not a constant one. Dynamical adjustments include both holes and sacked segments (equal to what FACK has) due to complexity involved in determining the number sacked blocks between highest_sack and the reordered segment. Thus it's will be an over-estimate. Implementation note: tcp_clean_rtx_queue doesn't need a lost_cnt tweak because head skb at that point cannot be SACKED_ACKED (nor would such situation last for long enough to cause problems). Signed-off-by:
-
Ilpo Järvinen authored
This implements more accurately what is stated in sacktag's overall comment: "Both of these heuristics are not used in Loss state, when we cannot account for retransmits accurately." When CA_Loss state is entered, the state changer ensures that undo_marker is only set if no TCPCB_RETRANS skbs were found, thus having non-zero undo_marker in CA_Loss basically tells that the R-bits still accurately reflect the current state of TCP. Signed-off-by:
-
Ilpo Järvinen authored
All intermediate conditions include it already, make them simpler as well. Signed-off-by:
-
