aboutsummaryrefslogtreecommitdiff
path: root/net
AgeCommit message (Collapse)Author
2005-06-23[TCP]: Add Scalable TCP congestion control module.John Heffner
This patch implements Tom Kelly's Scalable TCP congestion control algorithm for the modular framework. The algorithm has some nice scaling properties, and has been used a fair bit in research, though is known to have significant fairness issues, so it's not really suitable for general purpose use. Signed-off-by: John Heffner <jheffner@psc.edu> Signed-off-by: David S. Miller <davem@davemloft.net>
2005-06-23[TCP]: Add H-TCP congestion control module.Baruch Even
H-TCP is a congestion control algorithm developed at the Hamilton Institute, by Douglas Leith and Robert Shorten. It is extending the standard Reno algorithm with mode switching is thus a relatively simple modification. H-TCP is defined in a layered manner as it is still a research platform. The basic form includes the modification of beta according to the ratio of maxRTT to min RTT and the alpha=2*factor*(1-beta) relation, where factor is dependant on the time since last congestion. The other layers improve convergence by adding appropriate factors to alpha. The following patch implements the H-TCP algorithm in it's basic form. Signed-Off-By: Baruch Even <baruch@ev-en.org> Signed-off-by: David S. Miller <davem@davemloft.net>
2005-06-23[TCP]: Add TCP Vegas congestion control module.Stephen Hemminger
TCP Vegas code modified for the new TCP infrastructure. Vegas now uses microsecond resolution timestamps for better estimation of performance over higher speed links. Signed-off-by: Stephen Hemminger <shemminger@osdl.org> Signed-off-by: David S. Miller <davem@davemloft.net>
2005-06-23[TCP]: Add TCP Hybla congestion control module.Daniele Lacamera
TCP Hybla congestion avoidance. - "In heterogeneous networks, TCP connections that incorporate a terrestrial or satellite radio link are greatly disadvantaged with respect to entirely wired connections, because of their longer round trip times (RTTs). To cope with this problem, a new TCP proposal, the TCP Hybla, is presented and discussed in the paper[1]. It stems from an analytical evaluation of the congestion window dynamics in the TCP standard versions (Tahoe, Reno, NewReno), which suggests the necessary modifications to remove the performance dependence on RTT.[...]"[1] [1]: Carlo Caini, Rosario Firrincieli, "TCP Hybla: a TCP enhancement for heterogeneous networks", International Journal of Satellite Communications and Networking Volume 22, Issue 5 , Pages 547 - 566. September 2004. Signed-off-by: Daniele Lacamera (root at danielinux.net)net Signed-off-by: Stephen Hemminger <shemminger@osdl.org> Signed-off-by: David S. Miller <davem@davemloft.net>
2005-06-23[TCP]: Add High Speed TCP congestion control module.John Heffner
Sally Floyd's high speed TCP congestion control. This is useful for comparison and research. Signed-off-by: John Heffner <jheffner@psc.edu> Signed-off-by: Stephen Hemminger <shemminger@osdl.org> Signed-off-by: David S. Miller <davem@davemloft.net>
2005-06-23[TCP]: Add TCP Westwood congestion control module.Stephen Hemminger
This is the existing 2.6.12 Westwood code moved from tcp_input to the new congestion framework. A lot of the inline functions have been eliminated to try and make it clearer. Signed-off-by: Stephen Hemminger <shemminger@osdl.org> Signed-off-by: David S. Miller <davem@davemloft.net>
2005-06-23[TCP]: Add TCP BIC congestion control module.Stephen Hemminger
TCP BIC congestion control reworked to use the new congestion control infrastructure. This version is more up to date than the BIC code in 2.6.12; it incorporates enhancements from BICTCP 1.1, to handle low latency links. Signed-off-by: Stephen Hemminger <shemminger@osdl.org> Signed-off-by: David S. Miller <davem@davemloft.net>
2005-06-23[TCP]: Report congestion control algorithm in tcp_diag.Stephen Hemminger
Enhancement to the tcp_diag interface used by the iproute2 ss command to report the tcp congestion control being used by a socket. Signed-off-by: Stephen Hemminger <shemminger@osdl.org> Signed-off-by: David S. Miller <davem@davemloft.net>
2005-06-23[TCP]: Change tcp_diag to use the existing __RTA_PUT() macro.Stephen Hemminger
Signed-off-by: Stephen Hemminger <shemminger@osdl.org> Signed-off-by: David S. Miller <davem@davemloft.net>
2005-06-23[TCP]: Add pluggable congestion control algorithm infrastructure.Stephen Hemminger
Allow TCP to have multiple pluggable congestion control algorithms. Algorithms are defined by a set of operations and can be built in or modules. The legacy "new RENO" algorithm is used as a starting point and fallback. Signed-off-by: Stephen Hemminger <shemminger@osdl.org> Signed-off-by: David S. Miller <davem@davemloft.net>
2005-06-23[PATCH] create a kstrdup library functionPaulo Marques
This patch creates a new kstrdup library function and changes the "local" implementations in several places to use this function. Most of the changes come from the sound and net subsystems. The sound part had already been acknowledged by Takashi Iwai and the net part by David S. Miller. I left UML alone for now because I would need more time to read the code carefully before making changes there. Signed-off-by: Paulo Marques <pmarques@grupopie.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2005-06-22Merge rsync://rsync.kernel.org/pub/scm/linux/kernel/git/davem/net-2.6Linus Torvalds
2005-06-22[X25]: Fast select with no restriction on responseShaun Pereira
This patch is a follow up to patch 1 regarding "Selective Sub Address matching with call user data". It allows use of the Fast-Select-Acceptance optional user facility for X.25. This patch just implements fast select with no restriction on response (NRR). What this means (according to ITU-T Recomendation 10/96 section 6.16) is that if in an incoming call packet, the relevant facility bits are set for fast-select-NRR, then the called DTE can issue a direct response to the incoming packet using a call-accepted packet that contains call-user-data. This patch allows such a response. The called DTE can also respond with a clear-request packet that contains call-user-data. However, this feature is currently not implemented by the patch. How is Fast Select Acceptance used? By default, the system does not allow fast select acceptance (as before). To enable a response to fast select acceptance, After a listen socket in created and bound as follows socket(AF_X25, SOCK_SEQPACKET, 0); bind(call_soc, (struct sockaddr *)&locl_addr, sizeof(locl_addr)); but before a listen system call is made, the following ioctl should be used. ioctl(call_soc,SIOCX25CALLACCPTAPPRV); Now the listen system call can be made listen(call_soc, 4); After this, an incoming-call packet will be accepted, but no call-accepted packet will be sent back until the following system call is made on the socket that accepts the call ioctl(vc_soc,SIOCX25SENDCALLACCPT); The network (or cisco xot router used for testing here) will allow the application server's call-user-data in the call-accepted packet, provided the call-request was made with Fast-select NRR. Signed-off-by: Shaun Pereira <spereira@tusc.com.au> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: David S. Miller <davem@davemloft.net>
2005-06-22[X25]: Selective sub-address matching with call user data.Shaun Pereira
From: Shaun Pereira <spereira@tusc.com.au> This is the first (independent of the second) patch of two that I am working on with x25 on linux (tested with xot on a cisco router). Details are as follows. Current state of module: A server using the current implementation (2.6.11.7) of the x25 module will accept a call request/ incoming call packet at the listening x.25 address, from all callers to that address, as long as NO call user data is present in the packet header. If the server needs to choose to accept a particular call request/ incoming call packet arriving at its listening x25 address, then the kernel has to allow a match of call user data present in the call request packet with its own. This is required when multiple servers listen at the same x25 address and device interface. The kernel currently matches ALL call user data, if present. Current Changes: This patch is a follow up to the patch submitted previously by Andrew Hendry, and allows the user to selectively control the number of octets of call user data in the call request packet, that the kernel will match. By default no call user data is matched, even if call user data is present. To allow call user data matching, a cudmatchlength > 0 has to be passed into the kernel after which the passed number of octets will be matched. Otherwise the kernel behavior is exactly as the original implementation. This patch also ensures that as is normally the case, no call user data will be present in the Call accepted / call connected packet sent back to the caller Future Changes on next patch: There are cases however when call user data may be present in the call accepted packet. According to the X.25 recommendation (ITU-T 10/96) section 5.2.3.2 call user data may be present in the call accepted packet provided the fast select facility is used. My next patch will include this fast select utility and the ability to send up to 128 octets call user data in the call accepted packet provided the fast select facility is used. I am currently testing this, again with xot on linux and cisco. Signed-off-by: Shaun Pereira <spereira@tusc.com.au> (With a fix from Alexey Dobriyan <adobriyan@gmail.com>) Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: David S. Miller <davem@davemloft.net>
2005-06-22[EBTABLES]: vfree() checking cleanupsJames Lamanna
From: jlamanna@gmail.com ebtables.c vfree() checking cleanups. Signed-off by: James Lamanna <jlamanna@gmail.com> Signed-off-by: Domen Puncer <domen@coderock.org> Signed-off-by: David S. Miller <davem@davemloft.net>
2005-06-22[ATALK] aarp: replace schedule_timeout() with msleep()Nishanth Aravamudan
From: Nishanth Aravamudan <nacc@us.ibm.com> Use msleep() instead of schedule_timeout() to guarantee the task delays as expected. The current code is not wrong, but it does not account for early return due to signals, so I think msleep() should be appropriate. Signed-off-by: Nishanth Aravamudan <nacc@us.ibm.com> Signed-off-by: Domen Puncer <domen@coderock.org> Signed-off-by: David S. Miller <davem@davemloft.net>
2005-06-22[IPV4]: Fix route.c gcc4 warningsChuck Short
Signed-off by: Chuck Short <zulcss@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2005-06-22[NETPOLL]: allow multiple netpoll_clients to register against one interfaceJeff Moyer
This patch provides support for registering multiple netpoll clients to the same network device. Only one of these clients may register an rx_hook, however. In practice, this restriction has not been problematic. It is worth mentioning, though, that the current design can be easily extended to allow for the registration of multiple rx_hooks. The basic idea of the patch is that the rx_np pointer in the netpoll_info structure points to the struct netpoll that has rx_hook filled in. Aside from this one case, there is no need for a pointer from the struct net_device to an individual struct netpoll. A lock is introduced to protect the setting and clearing of the np_rx pointer. The pointer will only be cleared upon netpoll client module removal, and the lock should be uncontested. Signed-off-by: Jeff Moyer <jmoyer@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2005-06-22[NETPOLL]: Introduce a netpoll_info structJeff Moyer
This patch introduces a netpoll_info structure, which the struct net_device will now point to instead of pointing to a struct netpoll. The reason for this is two-fold: 1) fields such as the rx_flags, poll_owner, and poll_lock should be maintained per net_device, not per netpoll; and 2) this is a first step in providing support for multiple netpoll clients to register against the same net_device. The struct netpoll is now pointed to by the netpoll_info structure. As such, the previous behaviour of the code is preserved. Signed-off-by: Jeff Moyer <jmoyer@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2005-06-22[NET]: dont use strlen() but the result from a prior sprintf()Eric Dumazet
Small patch to save an unecessary call to strlen() : sprintf() gave us the length, just trust it. Signed-off-by: Eric Dumazet <dada1@cosmosbay.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2005-06-22[PATCH] RPC: kick off socket connect operations fasterChuck Lever
Make the socket transport kick the event queue to start socket connects immediately. This should improve responsiveness of applications that are sensitive to slow mount operations (like automounters). We are now also careful to cancel the connect worker before destroying the xprt. This eliminates a race where xprt_destroy can finish before the connect worker is even allowed to run. Test-plan: Destructive testing (unplugging the network temporarily). Connectathon with UDP and TCP. Hard-code impossibly small connect timeout. Version: Fri, 29 Apr 2005 15:32:01 -0400 Signed-off-by: Chuck Lever <cel@netapp.com> Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
2005-06-22[PATCH] RPC: TCP reconnects are too slowChuck Lever
When the network layer reports a connection close, the RPC task waiting to reconnect should be notified so it can retry immediately instead of waiting for the normal connection establishment timeout. This reverts a change made in 2.6.6 as part of adding client support for RPC over TCP socket idle timeouts. Test-plan: Destructive testing with NFS over TCP mounts. Version: Fri, 29 Apr 2005 15:31:46 -0400 Signed-off-by: Chuck Lever <cel@netapp.com> Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
2005-06-22[PATCH] RPC: Clean up socket autodisconnectTrond Myklebust
Cancel autodisconnect requests inside xprt_transmit() in order to avoid races. Use more efficient del_singleshot_timer_sync() Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
2005-06-22[PATCH] RPC: Ensure rpc calls respects the RPC_NOINTR flagTrond Myklebust
For internal purposes, the rpc_clnt_sigmask() call is replaced by a call to rpc_task_sigmask(), which ensures that the current task sigmask respects both the client cl_intr flag and the per-task NOINTR flag. Problem noted by Jiaying Zhang. Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
2005-06-22[PATCH] RPC: Allow the sunrpc server to multiplex serveral programs on a ↵Andreas Gruenbacher
single port The NFS and NFSACL programs run on the same RPC transport. This patch adds support for this by converting svc_program into a chained list of programs (server-side). Signed-off-by: Andreas Gruenbacher <agruen@suse.de> Signed-off-by: Olaf Kirch <okir@suse.de> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
2005-06-22[PATCH] RPC: Encode and decode arbitrary XDR arraysAndreas Gruenbacher
Signed-off-by: Andreas Gruenbacher <agruen@suse.de> Acked-by: Olaf Kirch <okir@suse.de> Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
2005-06-22[PATCH] RPC: fix accounting bug in the case of a truncated RPC messageTrond Myklebust
Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
2005-06-22[PATCH] RPC: Lazy RPC receive buffer allocationOlaf Kirch
Signed-off-by: Olaf Kirch <okir@suse.de> Signed-off-by: Andreas Gruenbacher <agruen@suse.de> Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
2005-06-22[PATCH] RPC: Allow multiple RPC client programs to share the same transportAndreas Gruenbacher
Signed-off-by: Andreas Gruenbacher <agruen@suse.de> Acked-by: Olaf Kirch <okir@suse.de> Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
2005-06-22[PATCH] RPC: Return -EPFNOSUPPORT for RPC programs that are unavailableAndreas Gruenbacher
Signed-off-by: Andreas Gruenbacher <agruen@suse.de> Signed-off-by: Olaf Kirch <okir@suse.de> Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
2005-06-22[PATCH] RPC: [PATCH] improve rpcauthauth_create error returnsJ. Bruce Fields
Currently we return -ENOMEM for every single failure to create a new auth. This is actually accurate for auth_null and auth_unix, but for auth_gss it's a bit confusing. Allow rpcauth_create (and the ->create methods) to return errors. With this patch, the user may sometimes see an EINVAL instead. Whee. Signed-off-by: J. Bruce Fields <bfields@citi.umich.edu> Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
2005-06-22[PATCH] RPC: Don't fall back from krb5p to krb5iJ. Bruce Fields
We shouldn't be silently falling back from krb5p to krb5i. Signed-off-by: J. Bruce Fields <bfields@citi.umich.edu> Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
2005-06-22[PATCH] RPC: Shrink struct rpc_task by switching to wait_on_bit()Trond Myklebust
Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
2005-06-22[PATCH] RPC: Make rpc_create_client() probe server for RPC program+version ↵Trond Myklebust
support Ensure that we don't create an RPC client without checking that the server does indeed support the RPC program + version that we are trying to set up. This enables us to immediately return an error to "mount" if it turns out that the server is only supporting NFSv2, when we requested NFSv3 or NFSv4. Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
2005-06-22[PATCH] RPC: Make rpc_create_client() destroy the transport on failure.Trond Myklebust
This saves us a couple of lines of cleanup code for each call. Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
2005-06-22[PATCH] RPC: Ensure XDR iovec length is initialized correctly in call_headerTrond Myklebust
Fix up call_header() so that it calls xdr_adjust_iovec(). Fix calculation of the scratch buffer length in xdr_init_encode(). Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
2005-06-22[PATCH] RPC: Fix a race with rpc_restart_call()Trond Myklebust
If the task->tk_exit() wants to restart the RPC call after delaying then the current RPC code will clobber the timer by calling rpc_delete_timer() immediately after re-entering the loop in __rpc_execute(). Problem noticed by Oleg Nesterov <oleg@tv-sign.ru> Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
2005-06-22[NETFILTER]: Fix handling of ICMP packets (RELATED) in ipt_CLUSTERIP target.Harald Welte
Signed-off-by: Harald Welte <laforge@netfilter.org> Signed-off-by: David S. Miller <davem@davemloft.net>
2005-06-22[PATCH] Fix extra double quote in IPV4 KconfigKumar Gala
Kconfig option had an extra double quote at the end of the line which was causing in warning when building. Signed-off-by: Kumar Gala <kumar.gala@freescale.com> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2005-06-21[IPV4]: Fix fib_trie.c's args to fib_dump_info().David S. Miller
Signed-off-by: David S. Miller <davem@davemloft.net>
2005-06-21[NETFILTER]: Fix ip6t_LOG sit tunnel loggingPatrick McHardy
Sit tunnel logging is currently broken: MAC=01:23:45:67:89:ab->01:23:45:47:89:ac TUNNEL=123.123. 0.123-> 12.123. 6.123 Apart from the broken IP address, MAC addresses are printed differently for sit tunnels than for everything else. Signed-off-by: Patrick McHardy <kaber@trash.net> Signed-off-by: David S. Miller <davem@davemloft.net>
2005-06-21[NETFILTER]: Drop conntrack reference in ip_call_ra_chain()/ip_mr_input()Patrick McHardy
Drop reference before handing the packets to raw_rcv() Signed-off-by: Patrick McHardy <kaber@trash.net> Signed-off-by: David S. Miller <davem@davemloft.net>
2005-06-21[NETFILTER]: Check TCP checksum in ipt_REJECTPatrick McHardy
Signed-off-by: Patrick McHardy <kaber@trash.net> Signed-off-by: David S. Miller <davem@davemloft.net>
2005-06-21[NETFILTER]: Avoid unncessary checksum validation in UDP connection trackingKeir Fraser
Signed-off-by: Keir Fraser <Keir.Fraser@xl.cam.ac.uk> Signed-off-by: Patrick McHardy <kaber@trash.net> Signed-off-by: David S. Miller <davem@davemloft.net>
2005-06-21[NETFILTER]: Missing owner-field initialization in ip6table_rawPatrick McHardy
I missed this one when fixing up iptable_raw. Signed-off-by: Patrick McHardy <kaber@trash.net> Signed-off-by: David S. Miller <davem@davemloft.net>
2005-06-21[NETFILTER]: expectation timeouts are compulsoryPhil Oester
Since expectation timeouts were made compulsory [1], there is no need to check for them in ip_conntrack_expect_insert. [1] https://lists.netfilter.org/pipermail/netfilter-devel/2005-January/018143.html Signed-off-by: Phil Oester <kernel@linuxace.com> Signed-off-by: Patrick McHardy <kaber@trash.net> Signed-off-by: David S. Miller <davem@davemloft.net>
2005-06-21[NETFILTER]: Restore netfilter assumptions in IPv6 multicastPatrick McHardy
Netfilter assumes that skb->data == skb->nh.ipv6h Signed-off-by: Patrick McHardy <kaber@trash.net> Signed-off-by: David S. Miller <davem@davemloft.net>
2005-06-21[NETFILTER]: Kill nf_debugPatrick McHardy
Signed-off-by: Patrick McHardy <kaber@trash.net> Signed-off-by: David S. Miller <davem@davemloft.net>
2005-06-21[NETFILTER]: Kill lockhelp.hPatrick McHardy
Signed-off-by: Patrick McHardy <kaber@trash.net> Signed-off-by: David S. Miller <davem@davemloft.net>
2005-06-21[IPV6]: multicast join and miscDavid L Stevens
Here is a simplified version of the patch to fix a bug in IPv6 multicasting. It: 1) adds existence check & EADDRINUSE error for regular joins 2) adds an exception for EADDRINUSE in the source-specific multicast join (where a prior join is ok) 3) adds a missing/needed read_lock on sock_mc_list; would've raced with destroying the socket on interface down without 4) adds a "leave group" in the (INCLUDE, empty) source filter case. This frees unneeded socket buffer memory, but also prevents an inappropriate interaction among the 8 socket options that mess with this. Some would fail as if in the group when you aren't really. Item #4 had a locking bug in the last version of this patch; rather than removing the idev->lock read lock only, I've simplified it to remove all lock state in the path and treat it as a direct "leave group" call for the (INCLUDE,empty) case it covers. Tested on an MP machine. :-) Much thanks to HoerdtMickael <hoerdt@clarinet.u-strasbg.fr> who reported the original bug. Signed-off-by: David L Stevens <dlstevens@us.ibm.com> Signed-off-by: David S. Miller <davem@davemloft.net>