- 29 Aug, 2009 31 commits
-
-
Octavian Purdila authored
There is a race condition in the time-wait sockets code that can lead to premature termination of FIN_WAIT2 and, subsequently, to RST generation when the FIN,ACK from the peer finally arrives: Time TCP header 0.000000 30755 > http [SYN] Seq=0 Win=2920 Len=0 MSS=1460 TSV=282912 TSER=0 0.000008 http > 30755 aSYN, ACK] Seq=0 Ack=1 Win=2896 Len=0 MSS=1460 TSV=... 0.136899 HEAD /1b.html?n1Lg=v1 HTTP/1.0 [Packet size limited during capture] 0.136934 HTTP/1.0 200 OK [Packet size limited during capture] 0.136945 http > 30755 [FIN, ACK] Seq=187 Ack=207 Win=2690 Len=0 TSV=270521... 0.136974 30755 > http [ACK] Seq=207 Ack=187 Win=2734 Len=0 TSV=283049 TSER=... 0.177983 30755 > http [ACK] Seq=207 Ack=188 Win=2733 Len=0 TSV=283089 TSER=... 0.238618 30755 > http [FIN, ACK] Seq=207 Ack=188 Win=2733 Len=0 TSV=283151... 0.238625 http > 30755 [RST] Seq=188 Win=0 Len=0 Say twdr->slot = 1 and we are running inet_twdr_hangman and in this instance inet_twdr_do_twkill_work returns 1. At that point we will mark slot 1 and schedule inet_twdr_twkill_work. We will also make twdr->slot = 2. Next, a connection is closed and tcp_time_wait(TCP_FIN_WAIT2, timeo) is called which will create a new FIN_WAIT2 time-wait socket and will place it in the last to be reached slot, i.e. twdr->slot = 1. At this point say inet_twdr_twkill_work will run which will start destroying the time-wait sockets in slot 1, including the just added TCP_FIN_WAIT2 one. To avoid this issue we increment the slot only if all entries in the slot have been purged. This change may delay the slots cleanup by a time-wait death row period but only if the worker thread didn't had the time to run/purge the current slot in the next period (6 seconds with default sysctl settings). However, on such a busy system even without this change we would probably see delays... Signed-off-by:
Octavian Purdila <opurdila@ixiacom.com> Signed-off-by:
David S. Miller <davem@davemloft.net>
-
Jens Låås authored
Here is rework and cleanup of the resize function. Some bugs we had. We were using ->parent when we should use node_parent(). Also we used ->parent which is not assigned by inflate in inflate loop. Also a fix to set thresholds to power 2 to fit halve and double strategy. max_resize is renamed to max_work which better indicates it's function. Reaching max_work is not an error, so warning is removed. max_work only limits amount of work done per resize. (limits CPU-usage, outstanding memory etc). The clean-up makes it relatively easy to add fixed sized root-nodes if we would like to decrease the memory pressure on routers with large routing tables and dynamic routing. If we'll need that... Its been tested with 280k routes. Work done together with Robert Olsson. Signed-off-by:
Jens Låås <jens.laas@its.uu.se> Signed-off-by:
Robert Olsson <robert.olsson@its.uu.se> Signed-off-by:
-
Sascha Hlusiak authored
if tunnel parameters have frag_off set to IP_DF, pmtudisc on the ipv4 link will be performed by deriving the mtu from the ipv4 link and setting the DF-Flag of the encapsulating IPv4 Header. If fragmentation is needed on the way, the IPv4 pmtu gets adjusted, the ipv6 package will be resent eventually, using the new and lower mtu and everyone is happy. If the frag_off parameter is unset, the mtu for the tunnel will be derived from the tunnel device or the ipv6 pmtu, which might be higher than the ipv4 pmtu. In that case we must allow the fragmentation of the IPv4 packet because the IPv6 mtu wouldn't 'learn' from the adjusted IPv4 pmtu, resulting in frequent icmp_frag_needed and package loss on the IPv6 layer. This patch allows fragmentation when tunnel was created with parameter nopmtudisc, like in ipip/gre tunnels. Signed-off-by:
Sascha Hlusiak <contact@saschahlusiak.de> Signed-off-by:
-
Eric Dumazet authored
While doing some forwarding benchmarks, I noticed ip_rt_send_redirect() is rather expensive, even if send_redirects is false for the device. Fix is to avoid two atomic ops, we dont really need to take a reference on in_dev Signed-off-by:
Eric Dumazet <eric.dumazet@gmail.com> Signed-off-by:
-
Eric Dumazet authored
Introduce keepalive_probes(tp) helper, and use it, like keepalive_time_when(tp) and keepalive_intvl_when(tp) Signed-off-by:
-
Michael Chan authored
This will allow the 10G iSCSI code to reuse the function. Signed-off-by:
Michael Chan <mchan@broadcom.com> Signed-off-by:
-
Michael Chan authored
This will allow the 10G iSCSI code to reuse the function. Signed-off-by:
-
Eric Dumazet authored
Signed-off-by:
-
Alexey Dobriyan authored
It looks like after rename device proc entry is unusable, because of no ->read_proc or ->proc_fops. And create_proc_entry() is deprecated. Signed-off-by:
Alexey Dobriyan <adobriyan@gmail.com> Signed-off-by:
-
Stephen Hemminger authored
Increase module version, and cleanup module info. Signed-off-by:
Stephen Hemminger <shemminger@vyatta.com> Signed-off-by:
-
Stephen Hemminger authored
Signed-off-by:
-
Stephen Hemminger authored
Simpler to have one place that spins and accounts for delays, this will also make the last packet be detected faster for more repeatable timing. Signed-off-by:
-
Stephen Hemminger authored
This changes how the pktgen thread spins/waits between packets if delay is configured. It uses a high res timer to wait for time to arrive. Signed-off-by:
-
Stephen Hemminger authored
The kernel ktime_t is a nice generic infrastructure for mananging high resolution times, as is done in pktgen. Signed-off-by:
-
Stephen Hemminger authored
If not using delay then no need to update next_tx after each packet sent. This allows pktgen to send faster especially on systems with slower clock sources. Signed-off-by:
-
Stephen Hemminger authored
Handle standard (and non-standard) return values in a switch. Signed-off-by:
-
Stephen Hemminger authored
netdev_alloc_skb is NUMA node aware. Also, don't exhaust atomic emergency pool. Don't want pktgen to cause OOM behaviour. Signed-off-by:
-
Stephen Hemminger authored
The if statement to test for "should a new packet be used" can be simplified. Signed-off-by:
-
Stephen Hemminger authored
Do some reorganization of transmit logic path: * move transmit queue full idle to separate routine * add a cpu_relax() * eliminate some of the uneeded goto's * if queue is still stopped, go back to main thread loop. * don't give up transmitting if quantum is exhausted (be greedy) Signed-off-by:
-
Stephen Hemminger authored
All the callers were freeing skb after stopping device. Remove unneeded forward decl. Signed-off-by:
-
Stephen Hemminger authored
Signed-off-by:
-
Stephen Hemminger authored
Don't force inlining where not needed. Gcc does better job of deciding to inline local functions. Signed-off-by:
-
Stephen Hemminger authored
A couple of minor functions can be written more compactly. Signed-off-by:
-
Ron Mercer authored
TX completions were running in a workqueue queued by the ISR. This patch moves the processing of TX completions to an existing RSS NAPI context. Now each irq vector runs NAPI for one RSS ring and one or more TX completion rings. Signed-off-by:
Ron Mercer <ron.mercer@qlogic.com> Signed-off-by:
-
Ron Mercer authored
Currently we downshift to MSI/Legacy if we don't get enough vectors for cpu_count RSS rings plus cpu_count TX completion rings. This patch allows running MSIX with the vector count that the platform provides. Signed-off-by:
-
Ron Mercer authored
Currently we have three types of RX rings. 1) Default ring - services rx_ring for broadcast/multicast, handles firmware events, and errors. 2) TX completion ring - handles only outbound completions. 3) RSS ring - handles only inbound completions. This patch gets rid of the default ring type and moves it's functionality into the first RSS ring. This makes better use of MSIX vectors since they are a limited resource on some platforms. Signed-off-by:
-
-
Petri Gynther authored
bonding: Have bond_check_dev_link examine netif_running Some network devices do not call netif_carrier_off when they are set administratively down. Have the bonding link check function also inspect the netif_running state. Ignore netif_running if the bond_check_dev_link function is called with "reporting" set, as in that case it's inspecting the capabilities of the non-netif_carrier device driver. Signed-off-by:
Petri Gynther <pgynther@google.com> Signed-off-by:
Jay Vosburgh <fubar@us.ibm.com> Signed-off-by:
-
Nicolas de Pesloüan authored
max_bonds is of type int and cannot be greater than INT_MAX. Signed-off-by:
Nicolas de Pesloüan <nicolas.2p.debian@free.fr> Signed-off-by:
-
Stephen Hemminger authored
Bonding can use compare_ether_addr() in bond_release. Signed-off-by:
-
Jay Vosburgh authored
Propogate the vlan_features of the slave devices to the bonding master device, using the same logic as for regular features. Tested by Or Gerlitz <ogerlitz@voltaire.com>, who also removed the debug logic from the original test patch. Signed-off-by:
Or Gerlitz <ogerlitz@voltaire.com> Signed-off-by:
-
- 28 Aug, 2009 9 commits
-
-
Kiran Divekar authored
Most of the places in debugfs.c are missing a NULL check on the return value of get_zeroed_page API call. Added required NULL check at appropriate places. Signed-off-by:
Kiran Divekar <kirandivekar@gmail.com> Signed-off-by:
John W. Linville <linville@tuxdriver.com>
-
Jussi Kivilinna authored
Now that cfg80211 functions are added and wext converted to use wext-compat functions, remove wext structures and disabled code. Signed-off-by:
Jussi Kivilinna <jussi.kivilinna@mbnet.fi> Signed-off-by:
-
Jussi Kivilinna authored
Signed-off-by:
-
Jussi Kivilinna authored
Signed-off-by:
-
Jussi Kivilinna authored
Signed-off-by:
-
Jussi Kivilinna authored
Stats worker no longer poll stats from device anymore. It's still needed to poll device control channel for connect/disconnect events, so rename stats worker as device poller. Signed-off-by:
-
Jussi Kivilinna authored
Signed-off-by:
-
Jussi Kivilinna authored
Add cfg80211 get_station and convert SIOCGIWRATE and get_wireless_stats to cfg80211. Signed-off-by:
-
Jussi Kivilinna authored
Add cfg80211 add_key/del_key/set_default_key and convert wext to use theim. Signed-off-by:
-
