aboutsummaryrefslogtreecommitdiff
path: root/net
AgeCommit message (Collapse)AuthorFilesLines
2010-06-24cfg80211/mac80211: Update set_tx_power to use mBm instead of dBm unitsJuuso Oikarinen2-16/+16
In preparation for a TX power setting interface in the nl80211, change the .set_tx_power function to use mBm units instead of dBm for greater accuracy and smaller power levels. Also, already in advance move the tx_power_setting enumeration to nl80211. This change affects the .tx_set_power function prototype. As a result, the corresponding changes are needed to modules using it. These are mac80211, iwmc3200wifi and rndis_wlan. Cc: Samuel Ortiz <[email protected]> Cc: Jussi Kivilinna <[email protected]> Signed-off-by: Juuso Oikarinen <[email protected]> Acked-by: Samuel Ortiz <[email protected]> Acked-by: Jussi Kivilinna <[email protected]> Signed-off-by: John W. Linville <[email protected]>
2010-06-24mac80211: avoid scheduling while atomic in mesh_rx_plink_frameJohn W. Linville1-11/+31
While mesh_rx_plink_frame holds sta->lock... mesh_rx_plink_frame -> mesh_plink_inc_estab_count -> ieee80211_bss_info_change_notify ...but ieee80211_bss_info_change_notify is allowed to sleep. A driver taking advantage of that allowance can cause a scheduling while atomic bug. Similar paths exist for mesh_plink_dec_estab_count, so work around those as well. http://bugzilla.kernel.org/show_bug.cgi?id=16099 Also, correct a minor kerneldoc comment error (mismatched function names). Signed-off-by: John W. Linville <[email protected]> Cc: [email protected]
2010-06-24minstrel_ht: move minstrel_mcs_groups declaration to header fileJohn W. Linville2-2/+2
Signed-off-by: John W. Linville <[email protected]> Acked-by: Felix Fietkau <[email protected]>
2010-06-24wireless: mark reg_mutex as staticJohn W. Linville1-1/+1
Signed-off-by: John W. Linville <[email protected]>
2010-06-24minstrel_ht: make *idx unsigned in minstrel_downgrade_rateJohn W. Linville1-1/+2
net/mac80211/rc80211_minstrel_ht.c:440:46: warning: incorrect type in argument 2 (different signedness) net/mac80211/rc80211_minstrel_ht.c:440:46: expected int *idx net/mac80211/rc80211_minstrel_ht.c:440:46: got unsigned int *<noident> net/mac80211/rc80211_minstrel_ht.c:446:46: warning: incorrect type in argument 2 (different signedness) net/mac80211/rc80211_minstrel_ht.c:446:46: expected int *idx net/mac80211/rc80211_minstrel_ht.c:446:46: got unsigned int *<noident> Signed-off-by: John W. Linville <[email protected]> Acked-by: Felix Fietkau <[email protected]>
2010-06-24mac80211: don't shadow mgmt variable in ieee80211_rx_h_actionJohn W. Linville1-4/+4
net/mac80211/rx.c:2059:39: warning: symbol 'mgmt' shadows an earlier one net/mac80211/rx.c:1916:31: originally declared here Signed-off-by: John W. Linville <[email protected]>
2010-06-23Merge branch 'master' of ↵David S. Miller5-9/+15
master.kernel.org:/pub/scm/linux/kernel/git/davem/net-2.6 Conflicts: net/ipv4/ip_output.c
2010-06-23net - IP_NODEFRAG option for IPv4 socketJiri Olsa3-1/+15
this patch is implementing IP_NODEFRAG option for IPv4 socket. The reason is, there's no other way to send out the packet with user customized header of the reassembly part. Signed-off-by: Jiri Olsa <[email protected]> Signed-off-by: David S. Miller <[email protected]>
2010-06-23bridge: 64bit rx/tx countersEric Dumazet3-13/+23
Use u64_stats_sync infrastructure to provide 64bit rx/tx counters even on 32bit hosts. It is safe to use a single u64_stats_sync for rx and tx, because BH is disabled on both, and we use per_cpu data. Signed-off-by: Eric Dumazet <[email protected]> Signed-off-by: David S. Miller <[email protected]>
2010-06-23net: consolidate netif_needs_gso() checksJohn Fastabend1-36/+32
netif_needs_gso() is checked twice in the TX path once, before submitting the skb to the qdisc and once after it is dequeued from the qdisc just before calling ndo_hard_start(). This opens a window for a user to change the gso/tso or tx checksum settings that can cause netif_needs_gso to be true in one check and false in the other. Specifically, changing TX checksum setting may cause the warning in skb_gso_segment() to be triggered if the checksum is calculated earlier. This consolidates the netif_needs_gso() calls so that the stack only checks if gso is needed in dev_hard_start_xmit(). Signed-off-by: John Fastabend <[email protected]> Cc: Herbert Xu <[email protected]> Signed-off-by: Jeff Kirsher <[email protected]> Acked-by: Herbert Xu <[email protected]> Signed-off-by: David S. Miller <[email protected]>
2010-06-22SUNRPC: Fix a re-entrancy bug in xs_tcp_read_calldir()Trond Myklebust1-16/+22
If the attempt to read the calldir fails, then instead of storing the read bytes, we currently discard them. This leads to a garbage final result when upon re-entry to the same routine, we read the remaining bytes. Fixes the regression in bugzilla number 16213. Please see https://bugzilla.kernel.org/show_bug.cgi?id=16213 Signed-off-by: Trond Myklebust <[email protected]> Cc: [email protected]
2010-06-22netfilter: fix simple typo in KConfig for netfiltert xt_TEEArnd Hannemann1-1/+1
Destination was spelled wrong in KConfig. Signed-off-by: Arnd Hannemann <[email protected]> Signed-off-by: Patrick McHardy <[email protected]>
2010-06-22netfilter: xt_IDLETIMER needs kdev_t.hRandy Dunlap1-0/+1
Add header file to fix build error: net/netfilter/xt_IDLETIMER.c:276: error: implicit declaration of function 'MKDEV' Signed-off-by: Randy Dunlap <[email protected]> Signed-off-by: Patrick McHardy <[email protected]>
2010-06-22IPVS: one-packet schedulingNick Chalk3-11/+29
Allow one-packet scheduling for UDP connections. When the fwmark-based or normal virtual service is marked with '-o' or '--ops' options all connections are created only to schedule one packet. Useful to schedule UDP packets from same client port to different real servers. Recommended with RR or WRR schedulers (the connections are not visible with ipvsadm -L). Signed-off-by: Nick Chalk <[email protected]> Signed-off-by: Simon Horman <[email protected]> Signed-off-by: Patrick McHardy <[email protected]>
2010-06-21udp: Fix bogus UFO packet generationHerbert Xu1-3/+6
It has been reported that the new UFO software fallback path fails under certain conditions with NFS. I tracked the problem down to the generation of UFO packets that are smaller than the MTU. The software fallback path simply discards these packets. This patch fixes the problem by not generating such packets on the UFO path. Signed-off-by: Herbert Xu <[email protected]> Reviewed-by: Michael S. Tsirkin <[email protected]> Signed-off-by: David S. Miller <[email protected]>
2010-06-21mac80211: Add interface for driver to temporarily disable dynamic psJuuso Oikarinen2-1/+40
This mechanism introduced in this patch applies (at least) for hardware designs using a single shared antenna for both WLAN and BT. In these designs, the antenna must be toggled between WLAN and BT. In those hardware, managing WLAN co-existence with Bluetooth requires WLAN full power save whenever there is Bluetooth activity in order for WLAN to be able to periodically relinquish the antenna to be used for BT. This is because BT can only access the shared antenna when WLAN is idle or asleep. Some hardware, for instance the wl1271, are able to indicate to the host whenever there is BT traffic. In essence, the hardware will send an indication to the host whenever there is, for example, SCO traffic or A2DP traffic, and will send another indication when the traffic is over. The hardware gets information of Bluetooth traffic via hardware co-existence control lines - these lines are used to negotiate the shared antenna ownership. The hardware will give the antenna to BT whenever WLAN is sleeping. This patch adds the interface to mac80211 to facilitate temporarily disabling of dynamic power save as per request of the WLAN driver. This interface will immediately force WLAN to full powersave, hence allowing BT coexistence as described above. In these kind of shared antenna desings, when WLAN powersave is fully disabled, Bluetooth will not work simultaneously with WLAN at all. This patch does not address that problem. This interface will not change PSM state, so if PSM is disabled it will remain so. Solving this problem requires knowledge about BT state, and is best done in user-space. Signed-off-by: Juuso Oikarinen <[email protected]> Signed-off-by: John W. Linville <[email protected]>
2010-06-21mac80211: Fix compile warning in scan.c.Gertjan van Wingerde1-1/+1
Fix the following compile warning: CC [M] net/mac80211/scan.o net/mac80211/scan.c: In function 'ieee80211_request_internal_scan': net/mac80211/scan.c:749:23: warning: comparison between 'enum nl80211_band' and 'enum ieee80211_band' caused by the local variable band not being of the proper 'ieee80211_band' type. Signed-off-by: Gertjan van Wingerde <[email protected]> Signed-off-by: John W. Linville <[email protected]>
2010-06-20caif: Add debug connection type for CAIF.Sjur Braendeland1-0/+5
Added new CAIF protocol type CAIFPROTO_DEBUG for accessing CAIF debug on the ST Ericsson modems. There are two debug servers on the modem, one for radio related debug (CAIF_RADIO_DEBUG_SERVICE) and the other for communication/application related debug (CAIF_COM_DEBUG_SERVICE). The debug connection can contain trace debug printouts or interactive debug used for debugging and test. Debug connections can be of type STREAM or SEQPACKET. Signed-off-by: Sjur Braendeland <[email protected]> Signed-off-by: David S. Miller <[email protected]>
2010-06-20caif: Use link layer MTU instead of fixed MTUSjur Braendeland11-56/+155
Previously CAIF supported maximum transfer size of ~4050. The transfer size is now calculated dynamically based on the link layers mtu size. Signed-off-by: Sjur [email protected] Signed-off-by: David S. Miller <[email protected]>
2010-06-20caif: Bugfix - RFM must support segmentation.Sjur Braendeland5-65/+271
CAIF Remote File Manager may send or receive more than 4050 bytes. Due to this The CAIF RFM service have to support segmentation. Signed-off-by: Sjur [email protected] Signed-off-by: David S. Miller <[email protected]>
2010-06-20caif: Bugfix not all services uses flow-ctrl.Sjur Braendeland8-16/+22
Flow control is not used by all CAIF services. The usage of flow control is now part of the gerneal initialization function for CAIF Services. Signed-off-by: Sjur [email protected] Signed-off-by: David S. Miller <[email protected]>
2010-06-18mac80211: fix sw scan bracketingJohannes Berg1-2/+2
Currently, detection in hwsim and ath9k can detect that two sw scans are in flight at the same time, which isn't really true. It is caused by a race condition, because the scan complete callback is called too late, after the lock has been dropped, so that a new scan can be started before it is called. It is also called too early semantically, as it is currently called _after_ the return to the operating channel -- it should be before so that drivers know this is the operating channel again. Signed-off-by: Johannes Berg <[email protected]> Signed-off-by: John W. Linville <[email protected]>
2010-06-18wireless: move regulatory_init to .init.textUwe Kleine-König2-3/+3
regulatory_init is only called by cfg80211_init which is in .init.text, too. Signed-off-by: Uwe Kleine-König <[email protected]> Signed-off-by: John W. Linville <[email protected]>
2010-06-18cfg80211: move cfg80211_exit to .exit.textUwe Kleine-König1-1/+1
cfg80211_exit is only used as module_exit function, so it can go to .exit.text saving a few bytes when CONFIG_CFG80211=y. Signed-off-by: Uwe Kleine-König <[email protected]> Signed-off-by: John W. Linville <[email protected]>
2010-06-17Merge branch 'master' of ↵David S. Miller30-1013/+1242
git://git.kernel.org/pub/scm/linux/kernel/git/linville/wireless-next-2.6
2010-06-17bridge: fdb cleanup runs too oftenstephen hemminger1-4/+2
It is common in end-node, non STP bridges to set forwarding delay to zero; which causes the forwarding database cleanup to run every clock tick. Change to run only as soon as needed or at next ageing timer interval which ever is sooner. Use round_jiffies_up macro rather than attempting round up by changing value. Signed-off-by: Stephen Hemminger <[email protected]> Signed-off-by: David S. Miller <[email protected]>
2010-06-17Merge branch 'master' of ↵John W. Linville2-2/+39
git://git.kernel.org/pub/scm/linux/kernel/git/linville/wireless-2.6 Conflicts: net/mac80211/mlme.c
2010-06-17netfilter: nf_nat: support user-specified SNAT rules in LOCAL_INPatrick McHardy3-13/+11
2.6.34 introduced 'conntrack zones' to deal with cases where packets from multiple identical networks are handled by conntrack/NAT. Packets are looped through veth devices, during which they are NATed to private addresses, after which they can continue normally through the stack and possibly have NAT rules applied a second time. This works well, but is needlessly complicated for cases where only a single SNAT/DNAT mapping needs to be applied to these packets. In that case, all that needs to be done is to assign each network to a seperate zone and perform NAT as usual. However this doesn't work for packets destined for the machine performing NAT itself since its corrently not possible to configure SNAT mappings for the LOCAL_IN chain. This patch adds a new INPUT chain to the NAT table and changes the targets performing SNAT to be usable in that chain. Example usage with two identical networks (192.168.0.0/24) on eth0/eth1: iptables -t raw -A PREROUTING -i eth0 -j CT --zone 1 iptables -t raw -A PREROUTING -i eth0 -j MARK --set-mark 1 iptables -t raw -A PREROUTING -i eth1 -j CT --zone 2 iptabels -t raw -A PREROUTING -i eth1 -j MARK --set-mark 2 iptables -t nat -A INPUT -m mark --mark 1 -j NETMAP --to 10.0.0.0/24 iptables -t nat -A POSTROUTING -m mark --mark 1 -j NETMAP --to 10.0.0.0/24 iptables -t nat -A INPUT -m mark --mark 2 -j NETMAP --to 10.0.1.0/24 iptables -t nat -A POSTROUTING -m mark --mark 2 -j NETMAP --to 10.0.1.0/24 iptables -t raw -A PREROUTING -d 10.0.0.0/24 -j CT --zone 1 iptables -t raw -A OUTPUT -d 10.0.0.0/24 -j CT --zone 1 iptables -t raw -A PREROUTING -d 10.0.1.0/24 -j CT --zone 2 iptables -t raw -A OUTPUT -d 10.0.1.0/24 -j CT --zone 2 iptables -t nat -A PREROUTING -d 10.0.0.0/24 -j NETMAP --to 192.168.0.0/24 iptables -t nat -A OUTPUT -d 10.0.0.0/24 -j NETMAP --to 192.168.0.0/24 iptables -t nat -A PREROUTING -d 10.0.1.0/24 -j NETMAP --to 192.168.0.0/24 iptables -t nat -A OUTPUT -d 10.0.1.0/24 -j NETMAP --to 192.168.0.0/24 Signed-off-by: Patrick McHardy <[email protected]>
2010-06-16net: Export cred_to_ucred to modules.David S. Miller1-0/+1
AF_UNIX references this, and can be built as a module, so... Signed-off-by: David S. Miller <[email protected]>
2010-06-16af_unix: Allow connecting to sockets in other network namespaces.Eric W. Biederman1-5/+2
Remove the restriction that only allows connecting to a unix domain socket identified by unix path that is in the same network namespace. Crossing network namespaces is always tricky and we did not support this at first, because of a strict policy of don't mix the namespaces. Later after Pavel proposed this we did not support this because no one had performed the audit to make certain using unix domain sockets across namespaces is safe. What fundamentally makes connecting to af_unix sockets in other namespaces is safe is that you have to have the proper permissions on the unix domain socket inode that lives in the filesystem. If you want strict isolation you just don't create inodes where unfriendlys can get at them, or with permissions that allow unfriendlys to open them. All nicely handled for us by the mount namespace and other standard file system facilities. I looked through unix domain sockets and they are a very controlled environment so none of the work that goes on in dev_forward_skb to make crossing namespaces safe appears needed, we are not loosing controll of the skb and so do not need to set up the skb to look like it is comming in fresh from the outside world. Further the fields in struct unix_skb_parms should not have any problems crossing network namespaces. Now that we handle SCM_CREDENTIALS in a way that gives useable values across namespaces. There does not appear to be any operational problems with encouraging the use of unix domain sockets across containers either. Signed-off-by: Eric W. Biederman <[email protected]> Acked-by: Daniel Lezcano <[email protected]> Acked-by: Pavel Emelyanov <[email protected]> Signed-off-by: David S. Miller <[email protected]>
2010-06-16af_unix: Allow credentials to work across user and pid namespaces.Eric W. Biederman1-22/+31
In unix_skb_parms store pointers to struct pid and struct cred instead of raw uid, gid, and pid values, then translate the credentials on reception into values that are meaningful in the receiving processes namespaces. Signed-off-by: Eric W. Biederman <[email protected]> Acked-by: Pavel Emelyanov <[email protected]> Signed-off-by: David S. Miller <[email protected]>
2010-06-16scm: Capture the full credentials of the scm sender.Eric W. Biederman1-0/+24
Start capturing not only the userspace pid, uid and gid values of the sending process but also the struct pid and struct cred of the sending process as well. This is in preparation for properly supporting SCM_CREDENTIALS for sockets that have different uid and/or pid namespaces at the different ends. Signed-off-by: Eric W. Biederman <[email protected]> Acked-by: Serge E. Hallyn <[email protected]> Signed-off-by: David S. Miller <[email protected]>
2010-06-16af_netlink: Add needed scm_destroy after scm_send.Eric W. Biederman1-3/+8
scm_send occasionally allocates state in the scm_cookie, so I have modified netlink_sendmsg to guarantee that when scm_send succeeds scm_destory will be called to free that state. Signed-off-by: Eric W. Biederman <[email protected]> Reviewed-by: Daniel Lezcano <[email protected]> Acked-by: Pavel Emelyanov <[email protected]> Signed-off-by: David S. Miller <[email protected]>
2010-06-16af_unix: Allow SO_PEERCRED to work across namespaces.Eric W. Biederman2-15/+40
Use struct pid and struct cred to store the peer credentials on struct sock. This gives enough information to convert the peer credential information to a value relative to whatever namespace the socket is in at the time. This removes nasty surprises when using SO_PEERCRED on socket connetions where the processes on either side are in different pid and user namespaces. Signed-off-by: Eric W. Biederman <[email protected]> Acked-by: Daniel Lezcano <[email protected]> Acked-by: Pavel Emelyanov <[email protected]> Signed-off-by: David S. Miller <[email protected]>
2010-06-16sock: Introduce cred_to_ucredEric W. Biederman1-0/+14
To keep the coming code clear and to allow both the sock code and the scm code to share the logic introduce a fuction to translate from struct cred to struct ucred. Signed-off-by: Eric W. Biederman <[email protected]> Acked-by: Pavel Emelyanov <[email protected]> Signed-off-by: David S. Miller <[email protected]>
2010-06-16Clear IFF_XMIT_DST_RELEASE for teql interfacesTom Hughes1-0/+1
https://bugzilla.kernel.org/show_bug.cgi?id=16183 The sch_teql module, which can be used to load balance over a set of underlying interfaces, stopped working after 2.6.30 and has been broken in all kernels since then for any underlying interface which requires the addition of link level headers. The problem is that the transmit routine relies on being able to access the destination address in the skb in order to do address resolution once it has decided which underlying interface it is going to transmit through. In 2.6.31 the IFF_XMIT_DST_RELEASE flag was introduced, and set by default for all interfaces, which causes the destination address to be released before the transmit routine for the interface is called. The solution is to clear that flag for teql interfaces. Signed-off-by: Tom Hughes <[email protected]> Acked-by: Eric Dumazet <[email protected]> Signed-off-by: David S. Miller <[email protected]>
2010-06-16syncookies: check decoded options against sysctl settingsFlorian Westphal2-8/+21
Discard the ACK if we find options that do not match current sysctl settings. Previously it was possible to create a connection with sack, wscale, etc. enabled even if the feature was disabled via sysctl. Also remove an unneeded call to tcp_sack_reset() in cookie_check_timestamp: Both call sites (cookie_v4_check, cookie_v6_check) zero "struct tcp_options_received", hand it to tcp_parse_options() (which does not change tcp_opt->num_sacks/dsack) and then call cookie_check_timestamp(). Even if num_sacks/dsacks were changed, the structure is allocated on the stack and after cookie_check_timestamp returns only a few selected members are copied to the inet_request_sock. Signed-off-by: Florian Westphal <[email protected]> Signed-off-by: David S. Miller <[email protected]>
2010-06-16Merge branch 'master' of ↵David S. Miller1-1/+1
git://git.kernel.org/pub/scm/linux/kernel/git/linville/wireless-2.6
2010-06-16mac80211: fix warn, enum may be used uninitializedChristoph Fritz1-1/+1
regression introduced by b8d92c9c141ee3dc9b3537b1f0ffb4a54ea8d9b2 In function ‘ieee80211_work_rx_queued_mgmt’: warning: ‘rma’ may be used uninitialized in this function this re-adds default value WORK_ACT_NONE back to rma Signed-off-by: Christoph Fritz <[email protected]> Signed-off-by: John W. Linville <[email protected]>
2010-06-16inetpeer: restore small inet_peer structuresEric Dumazet3-6/+10
Addition of rcu_head to struct inet_peer added 16bytes on 64bit arches. Thats a bit unfortunate, since old size was exactly 64 bytes. This can be solved, using an union between this rcu_head an four fields, that are normally used only when a refcount is taken on inet_peer. rcu_head is used only when refcnt=-1, right before structure freeing. Add a inet_peer_refcheck() function to check this assertion for a while. We can bring back SLAB_HWCACHE_ALIGN qualifier in kmem cache creation. Signed-off-by: Eric Dumazet <[email protected]> Signed-off-by: David S. Miller <[email protected]>
2010-06-16Merge branch 'master' into for-nextJiri Kosina74-398/+731
2010-06-16fix typos concerning "initiali[zs]e"Uwe Kleine-König4-4/+4
Signed-off-by: Uwe Kleine-König <[email protected]> Signed-off-by: Jiri Kosina <[email protected]>
2010-06-15inetpeer: do not use zero refcnt for freed entriesEric Dumazet1-2/+8
Followup of commit aa1039e73cc2 (inetpeer: RCU conversion) Unused inet_peer entries have a null refcnt. Using atomic_inc_not_zero() in rcu lookups is not going to work for them, and slow path is taken. Fix this using -1 marker instead of 0 for deleted entries. Signed-off-by: Eric Dumazet <[email protected]> Signed-off-by: David S. Miller <[email protected]>
2010-06-15bridge: Add const to dummy br_netpoll_send_skbHerbert Xu1-1/+1
The version of br_netpoll_send_skb used when netpoll is off is missing a const thus causing a warning. Signed-off-by: Herbert Xu <[email protected]> Signed-off-by: David S. Miller <[email protected]>
2010-06-15bridge: Fix OOM crash in deliver_cloneHerbert Xu1-2/+2
The bridge multicast patches introduced an OOM crash in the forward path, when deliver_clone fails to clone the skb. Reported-by: Mark Wagner <[email protected]> Signed-off-by: Herbert Xu <[email protected]> Signed-off-by: David S. Miller <[email protected]>
2010-06-15ipfrag : frag_kfree_skb() cleanupEric Dumazet2-11/+5
Third param (work) is unused, remove it. Remove __inline__ and inline qualifiers. Signed-off-by: Eric Dumazet <[email protected]> Signed-off-by: David S. Miller <[email protected]>
2010-06-15ip_frag: Remove some atomic opsEric Dumazet2-4/+2
Instead of doing one atomic operation per frag, we can factorize them. Signed-off-by: Eric Dumazet <[email protected]> Signed-off-by: David S. Miller <[email protected]>
2010-06-15ipv6: syncookies: do not skip ->iif initializationFlorian Westphal1-6/+7
When syncookies are in effect, req->iif is left uninitialized. In case of e.g. link-local addresses the route lookup then fails and no syn-ack is sent. Rearrange things so ->iif is also initialized in the syncookie case. want_cookie can only be true when the isn was zero, thus move the want_cookie check into the "!isn" branch. Cc: Glenn Griffin <[email protected]> Signed-off-by: Florian Westphal <[email protected]> Signed-off-by: David S. Miller <[email protected]>
2010-06-15inetpeer: RCU conversionEric Dumazet1-69/+95
inetpeer currently uses an AVL tree protected by an rwlock. It's possible to make most lookups use RCU 1) Add a struct rcu_head to struct inet_peer 2) add a lookup_rcu_bh() helper to perform lockless and opportunistic lookup. This is a normal function, not a macro like lookup(). 3) Add a limit to number of links followed by lookup_rcu_bh(). This is needed in case we fall in a loop. 4) add an smp_wmb() in link_to_pool() right before node insert. 5) make unlink_from_pool() use atomic_cmpxchg() to make sure it can take last reference to an inet_peer, since lockless readers could increase refcount, even while we hold peers.lock. 6) Delay struct inet_peer freeing after rcu grace period so that lookup_rcu_bh() cannot crash. 7) inet_getpeer() first attempts lockless lookup. Note this lookup can fail even if target is in AVL tree, but a concurrent writer can let tree in a non correct form. If this attemps fails, lock is taken a regular lookup is performed again. 8) convert peers.lock from rwlock to a spinlock 9) Remove SLAB_HWCACHE_ALIGN when peer_cachep is created, because rcu_head adds 16 bytes on 64bit arches, doubling effective size (64 -> 128 bytes) In a future patch, this is probably possible to revert this part, if rcu field is put in an union to share space with rid, ip_id_count, tcp_ts & tcp_ts_stamp. These fields being manipulated only with refcnt > 0. Signed-off-by: Eric Dumazet <[email protected]> Signed-off-by: David S. Miller <[email protected]>
2010-06-15Merge branch 'master' of ↵David S. Miller29-198/+541
git://git.kernel.org/pub/scm/linux/kernel/git/kaber/nf-next-2.6
Powered by cgit, Gruvboxed by Blaster4385.