aboutsummaryrefslogtreecommitdiff
path: root/net
AgeCommit message (Collapse)Author
2009-03-27nl80211: rework lockingJohannes Berg
When I added scanning to cfg80211, we got a lock dependency like this: rtnl --> cfg80211_mtx nl80211, on the other hand, has the reverse lock dependency: cfg80211_mtx --> rtnl which clearly is a bad idea. This patch reworks nl80211 to take these two locks in the other order to fix the possible, and easily triggerable, deadlock. Signed-off-by: Johannes Berg <johannes@sipsolutions.net> Signed-off-by: John W. Linville <linville@tuxdriver.com>
2009-03-27mac80211: Tear down aggregation sessions for suspend/resumeSujith
When the driver has been notified with a STA_REMOVE, it tears down the internal ADDBA state. On resume, trying to initiate aggregation would fail because mac80211 has not cleared the operational state for that <TID,STA>. This can be fixed by tearing down the existing sessions on a suspend. Also, the driver can initiate a new BA session when suspend is in progress. This is fixed by marking the station as being in suspend state and denying ADDBA requests for such STAs. Signed-off-by: Sujith <Sujith.Manoharan@atheros.com> Acked-by: Johannes Berg <johannes@sipsolutions.net> Signed-off-by: John W. Linville <linville@tuxdriver.com>
2009-03-27mac80211: acquire sta_lock for station suspend/resumeJohannes Berg
To avoid concurrent manipulations of the sta list (which shouldn't be possible at this point, but anyway) we need to hold the sta_lock around iterating the list. At the same time, we do not need to iterate the list at all if the driver doesn't want to be notified. Signed-off-by: Johannes Berg <johannes@sipsolutions.net> Acked-by: Bob Copeland <me@bobcopeland.com> Signed-off-by: John W. Linville <linville@tuxdriver.com>
2009-03-27nl80211: export supported commandsJohannes Berg
This makes nl80211 export the supported commands (command groups) per wiphy so userspace has an idea what it can do -- this will be required reading for userspace when we introduce auth/assoc /or/ connect for older hardware that cannot separate auth and assoc. Signed-off-by: Johannes Berg <johannes@sipsolutions.net> Signed-off-by: John W. Linville <linville@tuxdriver.com>
2009-03-27mac80211: Populate HT limitation with TKIP/WEP to the handler for ↵Vasanthakumar Thiagarajan
SIOCSIWENCODE too Signed-off-by: Vasanthakumar Thiagarajan <vasanth@atheros.com> Signed-off-by: John W. Linville <linville@tuxdriver.com>
2009-03-27wireless: radiotap updatesJohannes Berg
Radiotap was updated to include a "bad PLCP" flag and standardise the "bad FCS" flag in the "flags" rather than "RX flags" field, this patch updates Linux to that standard. Signed-off-by: Johannes Berg <johannes@sipsolutions.net> Signed-off-by: John W. Linville <linville@tuxdriver.com>
2009-03-27mac80211: stop queues across suspend/resumeJohannes Berg
Even though userland probably cannot submit packets, there might still be some coming, and that's no good when the driver doesn't expect them. Stop the queues across suspend/resume. Signed-off-by: Johannes Berg <johannes@sipsolutions.net> Signed-off-by: John W. Linville <linville@tuxdriver.com>
2009-03-27mac80211: fix warnings in ieee80211_if_configJohannes Berg
The last warning can never trigger, and the explicit AP_VLAN check is pointless if we move the config_interface check down, in practice config_interface is required anyway. Signed-off-by: Johannes Berg <johannes@sipsolutions.net> Signed-off-by: John W. Linville <linville@tuxdriver.com>
2009-03-27mac80211: start pending scan after probe/auth/assoc timed outHelmut Schaa
If a scan is queued in STA mode while the interface is in state direct probe, authenticate or associate the scan is delayed until the interface enters disabled or associated state. But in case of direct probe-, authentication- or association- timeout sta_work will not be scheduled anymore (without external trigger) and thus the pending scan is not executed and prevents a new scan from being triggered (-EBUSY). Fix this by queueing the sta work again after direct probe-, authentication- and association- timeout. Signed-off-by: Helmut Schaa <helmut.schaa@googlemail.com> Signed-off-by: John W. Linville <linville@tuxdriver.com>
2009-03-27mac80211: remove ieee80211_num_regular_queuesJohannes Berg
This inline is useless and actually makes the code _longer_ rather than shorter. Signed-off-by: Johannes Berg <johannes@sipsolutions.net> Signed-off-by: John W. Linville <linville@tuxdriver.com>
2009-03-27cfg80211/nl80211: remove usage of CONFIG_NL80211Reinette Chatre
The scan capability added to cfg80211/nl80211 introduced a dependency on nl80211 by cfg80211. We can thus no longer have just cfg80211 without nl80211. Specifically, cfg80211_scan_done() calls nl80211_send_scan_aborted() or nl80211_send_scan_done(). Now we remove the option for user to select nl80211. It will always be compiled if user selects cfg80211. Signed-off-by: Reinette Chatre <reinette.chatre@intel.com> Signed-off-by: John W. Linville <linville@tuxdriver.com>
2009-03-27mac80211: ieee80211_ibss_commit() cleanupAlina Friedrichsen
Don't call ieee80211_sta_find_ibss() directly, like it's done in STA mode, so that the commit() call is more harmless respectively has less site-effects. Signed-off-by: Alina Friedrichsen <x-alina@gmx.net> Signed-off-by: John W. Linville <linville@tuxdriver.com>
2009-03-27af_rose/x25: Sanity check the maximum user frame sizeAlan Cox
Otherwise we can wrap the sizes and end up sending garbage. Closes #10423 Signed-off-by: Alan Cox <alan@lxorguk.ukuu.org.uk> Signed-off-by: David S. Miller <davem@davemloft.net>
2009-03-27appletalk: this warning can go I thinkAlan Cox
Its past 2.2 ... Signed-off-by: Alan Cox <alan@lxorguk.ukuu.org.uk> Signed-off-by: David S. Miller <davem@davemloft.net>
2009-03-27xfrm: spin_lock() should be spin_unlock() in xfrm_state.cChuck Ebbert
spin_lock() should be spin_unlock() in xfrm_state_walk_done(). caused by: commit 12a169e7d8f4b1c95252d8b04ed0f1033ed7cfe2 "ipsec: Put dumpers on the dump list" Reported-by: Marc Milgram <mmilgram@redhat.com> Signed-off-by: Chuck Ebbert <cebbert@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2009-03-27ipv6: Plug sk_buff leak in ipv6_rcv (net/ipv6/ip6_input.c)Jesper Nilsson
Commit 778d80be52699596bf70e0eb0761cf5e1e46088d (ipv6: Add disable_ipv6 sysctl to disable IPv6 operaion on specific interface) seems to have introduced a leak of sk_buff's for ipv6 traffic, at least in some configurations where idev is NULL, or when ipv6 is disabled via sysctl. The problem is that if the first condition of the if-statement returns non-NULL, it returns an skb with only one reference, and when the other conditions apply, execution jumps to the "out" label, which does not call kfree_skb for it. To plug this leak, change to use the "drop" label instead. (this relies on it being ok to call kfree_skb on NULL) This also allows us to avoid calling rcu_read_unlock here, and removes the only user of the "out" label. Signed-off-by: Jesper Nilsson <jesper.nilsson@axis.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2009-03-26Merge branch 'master' of ↵David S. Miller
git://git.kernel.org/pub/scm/linux/kernel/git/kaber/nf-next-2.6
2009-03-26GRO: Disable GRO on legacy netif_rx pathHerbert Xu
When I fixed the GRO crash in the legacy receive path I used napi_complete to replace __napi_complete. Unfortunately they're not the same when NETPOLL is enabled, which may result in us not calling __napi_complete at all. What's more, we really do need to keep the __napi_complete call within the IRQ-off section since in theory an IRQ can occur in between and fill up the backlog to the maximum, causing us to lock up. Since we can't seem to find a fix that works properly right now, this patch reverts all the GRO support from the netif_rx path. Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au> Signed-off-by: David S. Miller <davem@davemloft.net>
2009-03-26Merge branch 'bkl-removal' of git://git.lwn.net/linux-2.6Linus Torvalds
* 'bkl-removal' of git://git.lwn.net/linux-2.6: Rationalize fasync return values Move FASYNC bit handling to f_op->fasync() Use f_lock to protect f_flags Rename struct file->f_ep_lock
2009-03-26Merge branch 'master' of /home/davem/src/GIT/linux-2.6/David S. Miller
Conflicts: drivers/net/wimax/i2400m/usb-notif.c
2009-03-26Merge git://git.kernel.org/pub/scm/linux/kernel/git/gregkh/driver-core-2.6Linus Torvalds
* git://git.kernel.org/pub/scm/linux/kernel/git/gregkh/driver-core-2.6: (61 commits) Dynamic debug: fix pr_fmt() build error Dynamic debug: allow simple quoting of words dynamic debug: update docs dynamic debug: combine dprintk and dynamic printk sysfs: fix some bin_vm_ops errors kobject: don't block for each kobject_uevent sysfs: only allow one scheduled removal callback per kobj Driver core: Fix device_move() vs. dpm list ordering, v2 Driver core: some cleanup on drivers/base/sys.c Driver core: implement uevent suppress in kobject vcs: hook sysfs devices into object lifetime instead of "binding" driver core: fix passing platform_data driver core: move platform_data into platform_device sysfs: don't block indefinitely for unmapped files. driver core: move knode_bus into private structure driver core: move knode_driver into private structure driver core: move klist_children into private structure driver core: create a private portion of struct device driver core: remove polling for driver_probe_done(v5) sysfs: reference sysfs_dirent from sysfs inodes ... Fixed conflicts in drivers/sh/maple/maple.c manually
2009-03-26Merge git://git.kernel.org/pub/scm/linux/kernel/git/herbert/crypto-2.6Linus Torvalds
* git://git.kernel.org/pub/scm/linux/kernel/git/herbert/crypto-2.6: (29 commits) crypto: sha512-s390 - Add missing block size hwrng: timeriomem - Breaks an allyesconfig build on s390: nlattr: Fix build error with NET off crypto: testmgr - add zlib test crypto: zlib - New zlib crypto module, using pcomp crypto: testmgr - Add support for the pcomp interface crypto: compress - Add pcomp interface netlink: Move netlink attribute parsing support to lib crypto: Fix dead links hwrng: timeriomem - New driver crypto: chainiv - Use kcrypto_wq instead of keventd_wq crypto: cryptd - Per-CPU thread implementation based on kcrypto_wq crypto: api - Use dedicated workqueue for crypto subsystem crypto: testmgr - Test skciphers with no IVs crypto: aead - Avoid infinite loop when nivaead fails selftest crypto: skcipher - Avoid infinite loop when cipher fails selftest crypto: api - Fix crypto_alloc_tfm/create_create_tfm return convention crypto: api - crypto_alg_mod_lookup either tested or untested crypto: amcc - Add crypt4xx driver crypto: ansi_cprng - Add maintainer ...
2009-03-26ctnetlink: compute generic part of event more acuratelyHolger Eitzenberger
On a box with most of the optional Netfilter switches turned off some of the NLAs are never send, e. g. secmark, mark or the conntrack byte/packet counters. As a worst case scenario this may possibly still lead to ctnetlink skbs being reallocated in netlink_trim() later, loosing all the nice effects from the previous patches. I try to solve that (at least partly) by correctly #ifdef'ing the NLAs in the computation. Signed-off-by: Holger Eitzenberger <holger@eitzenberger.org> Signed-off-by: Patrick McHardy <kaber@trash.net>
2009-03-26Merge branch 'master' of ↵David S. Miller
master.kernel.org:/pub/scm/linux/kernel/git/davem/net-2.6
2009-03-26net: core: remove unneeded include in net/core/utils.c.Rami Rosen
Signed-off-by: Rami Rosen <ramirose@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2009-03-26netfilter: fix nf_logger name in ebt_ulog.Eric Leblond
This patch renames the ebt_ulog nf_logger from "ulog" to "ebt_ulog" to be in sync with other modules naming. As this name was currently only used for informational purpose, the renaming should be harmless. Signed-off-by: Eric Leblond <eric@inl.fr> Signed-off-by: David S. Miller <davem@davemloft.net>
2009-03-26netfilter: fix warning in ebt_ulog init function.Eric Leblond
The ebt_ulog module does not follow the fixed convention about function return. Loading the module is triggering the following message: sys_init_module: 'ebt_ulog'->init suspiciously returned 1, it should follow 0/-E convention sys_init_module: loading module anyway... Pid: 2334, comm: modprobe Not tainted 2.6.29-rc5edenwall0-00883-g199e57b #146 Call Trace: [<c0441b81>] ? printk+0xf/0x16 [<c02311af>] sys_init_module+0x107/0x186 [<c0202cfa>] syscall_call+0x7/0xb The following patch fixes the return treatment in ebt_ulog_init() function. Signed-off-by: Eric Leblond <eric@inl.fr> Signed-off-by: David S. Miller <davem@davemloft.net>
2009-03-26netfilter: fix warning about invalid const usageEric Leblond
This patch fixes the declaration of the logger structure in ebt_log and ebt_ulog: I forgot to remove the const option from their declaration in the commit ca735b3aaa945626ba65a3e51145bfe4ecd9e222 ("netfilter: use a linked list of loggers"). Pointed-out-by: Stephen Rothwell <sfr@canb.auug.org.au> Signed-off-by: Eric Leblond <eric@inl.fr> Signed-off-by: David S. Miller <davem@davemloft.net>
2009-03-25bridge: bad error handling when adding invalid ether addressStephen Hemminger
This fixes an crash when empty bond device is added to a bridge. If an interface with invalid ethernet address (all zero) is added to a bridge, then bridge code detects it when setting up the forward databas entry. But the error unwind is broken, the bridge port object can get freed twice: once when ref count went to zeo, and once by kfree. Since object is never really accessible, just free it. Signed-off-by: Stephen Hemminger <shemminger@vyatta.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2009-03-25netfilter: nf_conntrack: calculate per-protocol nlattr sizeHolger Eitzenberger
Signed-off-by: Holger Eitzenberger <holger@eitzenberger.org> Signed-off-by: Patrick McHardy <kaber@trash.net>
2009-03-25netfilter: nf_conntrack: add generic function to get len of generic policyHolger Eitzenberger
Usefull for all protocols which do not add additional data, such as GRE or UDPlite. Signed-off-by: Holger Eitzenberger <holger@eitzenberger.org> Signed-off-by: Patrick McHardy <kaber@trash.net>
2009-03-25netfilter: ctnetlink: allocate right-sized ctnetlink skbHolger Eitzenberger
Try to allocate a Netlink skb roughly the size of the actual message, with the help from the l3 and l4 protocol helpers. This is all to prevent a reallocation in netlink_trim() later. The overhead of allocating the right-sized skb is rather small, with ctnetlink_alloc_skb() actually being inlined away on my x86_64 box. The size of the per-proto space is determined at registration time of the protocol helper. Signed-off-by: Holger Eitzenberger <holger@eitzenberger.org> Signed-off-by: Patrick McHardy <kaber@trash.net>
2009-03-25netfilter: nf_conntrack: use SLAB_DESTROY_BY_RCU and get rid of call_rcu()Eric Dumazet
Use "hlist_nulls" infrastructure we added in 2.6.29 for RCUification of UDP & TCP. This permits an easy conversion from call_rcu() based hash lists to a SLAB_DESTROY_BY_RCU one. Avoiding call_rcu() delay at nf_conn freeing time has numerous gains. First, it doesnt fill RCU queues (up to 10000 elements per cpu). This reduces OOM possibility, if queued elements are not taken into account This reduces latency problems when RCU queue size hits hilimit and triggers emergency mode. - It allows fast reuse of just freed elements, permitting better use of CPU cache. - We delete rcu_head from "struct nf_conn", shrinking size of this structure by 8 or 16 bytes. This patch only takes care of "struct nf_conn". call_rcu() is still used for less critical conntrack parts, that may be converted later if necessary. Signed-off-by: Eric Dumazet <dada1@cosmosbay.com> Signed-off-by: Patrick McHardy <kaber@trash.net>
2009-03-25netfilter: {ip,ip6,arp}_tables: fix incorrect loop detectionPatrick McHardy
Commit e1b4b9f ([NETFILTER]: {ip,ip6,arp}_tables: fix exponential worst-case search for loops) introduced a regression in the loop detection algorithm, causing sporadic incorrectly detected loops. When a chain has already been visited during the check, it is treated as having a standard target containing a RETURN verdict directly at the beginning in order to not check it again. The real target of the first rule is then incorrectly treated as STANDARD target and checked not to contain invalid verdicts. Fix by making sure the rule does actually contain a standard target. Based on patch by Francis Dupont <Francis_Dupont@isc.org> Signed-off-by: Patrick McHardy <kaber@trash.net>
2009-03-25netfilter: limit the length of the helper nameHolger Eitzenberger
This is necessary in order to have an upper bound for Netlink message calculation, which is not a problem at all, as there are no helpers with a longer name. Signed-off-by: Holger Eitzenberger <holger@eitzenberger.org> Signed-off-by: Patrick McHardy <kaber@trash.net>
2009-03-25netlink: add nla_policy_len()Holger Eitzenberger
It calculates the max. length of a Netlink policy, which is usefull for allocating Netlink buffers roughly the size of the actual message. Signed-off-by: Holger Eitzenberger <holger@eitzenberger.org> Signed-off-by: Patrick McHardy <kaber@trash.net>
2009-03-25netfilter: ctnetlink: add callbacks to the per-proto nlattrsHolger Eitzenberger
There is added a single callback for the l3 proto helper. The two callbacks for the l4 protos are necessary because of the general structure of a ctnetlink event, which is in short: CTA_TUPLE_ORIG <l3/l4-proto-attributes> CTA_TUPLE_REPLY <l3/l4-proto-attributes> CTA_ID ... CTA_PROTOINFO <l4-proto-attributes> CTA_TUPLE_MASTER <l3/l4-proto-attributes> Therefore the formular is size := sizeof(generic-nlas) + 3 * sizeof(tuple_nlas) + sizeof(protoinfo_nlas) Some of the NLAs are optional, e. g. CTA_TUPLE_MASTER, which is only set if it's an expected connection. But the number of optional NLAs is small enough to prevent netlink_trim() from reallocating if calculated properly. Signed-off-by: Holger Eitzenberger <holger@eitzenberger.org> Signed-off-by: Patrick McHardy <kaber@trash.net>
2009-03-25netfilter: factorize ifname_compare()Eric Dumazet
We use same not trivial helper function in four places. We can factorize it. Signed-off-by: Eric Dumazet <dada1@cosmosbay.com> Signed-off-by: Patrick McHardy <kaber@trash.net>
2009-03-25netfilter: nf_conntrack: use hlist_add_head_rcu() in nf_conntrack_set_hashsize()Eric Dumazet
Using hlist_add_head() in nf_conntrack_set_hashsize() is quite dangerous. Without any barrier, one CPU could see a loop while doing its lookup. Its true new table cannot be seen by another cpu, but previous table is still readable. Signed-off-by: Eric Dumazet <dada1@cosmosbay.com> Signed-off-by: Patrick McHardy <kaber@trash.net>
2009-03-25netfilter: fix xt_LED build failurePatrick McHardy
net/netfilter/xt_LED.c:40: error: field netfilter_led_trigger has incomplete type net/netfilter/xt_LED.c: In function led_timeout_callback: net/netfilter/xt_LED.c:78: warning: unused variable ledinternal net/netfilter/xt_LED.c: In function led_tg_check: net/netfilter/xt_LED.c:102: error: implicit declaration of function led_trigger_register net/netfilter/xt_LED.c: In function led_tg_destroy: net/netfilter/xt_LED.c:135: error: implicit declaration of function led_trigger_unregister Fix by adding a dependency on LED_TRIGGERS. Reported-by: Sachin Sant <sachinp@in.ibm.com> Tested-by: Subrata Modak <tosubrata@gmail.com> Signed-off-by: Patrick McHardy <kaber@trash.net>
2009-03-24ipv6: Fix conflict resolutions during ipv6 bindingVlad Yasevich
The ipv6 version of bind_conflict code calls ipv6_rcv_saddr_equal() which at times wrongly identified intersections between addresses. It particularly broke down under a few instances and caused erroneous bind conflicts. Signed-off-by: Vlad Yasevich <vladislav.yasevich@hp.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2009-03-24ipv6: Make v4-mapped bindings consistent with IPv4Vlad Yasevich
Binding to a v4-mapped address on an AF_INET6 socket should produce the same result as binding to an IPv4 address on AF_INET socket. The two are interchangable as v4-mapped address is really a portability aid. Signed-off-by: Vlad Yasevich <vladislav.yasevich@hp.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2009-03-24ipv6: Allow ipv4 wildcard binds after ipv6 address bindsVlad Yasevich
The IPv4 wildcard (0.0.0.0) address does not intersect in any way with explicit IPv6 addresses. These two should be permitted, but the IPv4 conflict code checks the ipv6only bit as part of the test. Since binding to an explicit IPv6 address restricts the socket to only that IPv6 address, the side-effect is that the socket behaves as v6-only. By explicitely setting ipv6only in this case, allows the 2 binds to succeed. Signed-off-by: Vlad Yasevich <vladislav.yasevich@hp.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2009-03-24ipv6: Disallow binding to v4-mapped address on v6-only socket.Vlad Yasevich
A socket marked v6-only, can not receive or send traffic to v4-mapped addresses. Thus allowing binding to v4-mapped address on such a socket makes no sense. Signed-off-by: Vlad Yasevich <vladislav.yasevich@hp.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2009-03-24Merge branch 'master' of ↵David S. Miller
git://git.kernel.org/pub/scm/linux/kernel/git/kaber/nf-2.6
2009-03-24dynamic debug: combine dprintk and dynamic printkJason Baron
This patch combines Greg Bank's dprintk() work with the existing dynamic printk patchset, we are now calling it 'dynamic debug'. The new feature of this patchset is a richer /debugfs control file interface, (an example output from my system is at the bottom), which allows fined grained control over the the debug output. The output can be controlled by function, file, module, format string, and line number. for example, enabled all debug messages in module 'nf_conntrack': echo -n 'module nf_conntrack +p' > /mnt/debugfs/dynamic_debug/control to disable them: echo -n 'module nf_conntrack -p' > /mnt/debugfs/dynamic_debug/control A further explanation can be found in the documentation patch. Signed-off-by: Greg Banks <gnb@sgi.com> Signed-off-by: Jason Baron <jbaron@redhat.com> Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
2009-03-24Driver core: Fix device_move() vs. dpm list ordering, v2Cornelia Huck
dpm_list currently relies on the fact that child devices will be registered after their parents to get a correct suspend order. Using device_move() however destroys this assumption, as an already registered device may be moved under a newly registered one. This patch adds a new argument to device_move(), allowing callers to specify how dpm_list should be adapted. Signed-off-by: Cornelia Huck <cornelia.huck@de.ibm.com> Acked-by: Alan Stern <stern@rowland.harvard.edu> Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
2009-03-24netlink: add NETLINK_NO_ENOBUFS socket flagPablo Neira Ayuso
This patch adds the NETLINK_NO_ENOBUFS socket flag. This flag can be used by unicast and broadcast listeners to avoid receiving ENOBUFS errors. Generally speaking, ENOBUFS errors are useful to notify two things to the listener: a) You may increase the receiver buffer size via setsockopt(). b) You have lost messages, you may be out of sync. In some cases, ignoring ENOBUFS errors can be useful. For example: a) nfnetlink_queue: this subsystem does not have any sort of resync method and you can decide to ignore ENOBUFS once you have set a given buffer size. b) ctnetlink: you can use this together with the socket flag NETLINK_BROADCAST_SEND_ERROR to stop getting ENOBUFS errors as you do not need to resync (packets whose event are not delivered are drop to provide reliable logging and state-synchronization). Moreover, the use of NETLINK_NO_ENOBUFS also reduces a "go up, go down" effect in terms of performance which is due to the netlink congestion control when the listener cannot back off. The effect is the following: 1) throughput rate goes up and netlink messages are inserted in the receiver buffer. 2) Then, netlink buffer fills and overruns (set on nlk->state bit 0). 3) While the listener empties the receiver buffer, netlink keeps dropping messages. Thus, throughput goes dramatically down. 4) Then, once the listener has emptied the buffer (nlk->state bit 0 is set off), goto step 1. This effect is easy to trigger with netlink broadcast under heavy load, and it is more noticeable when using a big receiver buffer. You can find some results in [1] that show this problem. [1] http://1984.lsi.us.es/linux/netlink/ This patch also includes the use of sk_drop to account the number of netlink messages drop due to overrun. This value is shown in /proc/net/netlink. Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org> Signed-off-by: David S. Miller <davem@davemloft.net>
2009-03-24arp_tables: ifname_compare() can assume 16bit alignmentEric Dumazet
Arches without efficient unaligned access can still perform a loop assuming 16bit alignment in ifname_compare() Signed-off-by: Eric Dumazet <dada1@cosmosbay.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2009-03-24netfilter: trivial Kconfig spelling fixesJan Engelhardt
Supplements commit 67c0d57930ff9a24c6c34abee1b01f7716a9b0e2. Signed-off-by: Jan Engelhardt <jengelh@medozas.de> Signed-off-by: David S. Miller <davem@davemloft.net>
generated by cgit v1.2.3 (git 2.25.1) at 2024-12-28 03:04:25 +0000