aboutsummaryrefslogtreecommitdiffstats
Commit message (Collapse)AuthorAge
* Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/netLinus Torvalds2012-01-24
|\ | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Davem says: 1) Fix JIT code generation on x86-64 for divide by zero, from Eric Dumazet. 2) tg3 header length computation correction from Eric Dumazet. 3) More build and reference counting fixes for socket memory cgroup code from Glauber Costa. 4) module.h snuck back into a core header after all the hard work we did to remove that, from Paul Gortmaker and Jesper Dangaard Brouer. 5) Fix PHY naming regression and add some new PCI IDs in stmmac, from Alessandro Rubini. 6) Netlink message generation fix in new team driver, should only advertise the entries that changed during events, from Jiri Pirko. 7) SRIOV VF registration and unregistration fixes, and also add a missing PCI ID, from Roopa Prabhu. 8) Fix infinite loop in tx queue flush code of brcmsmac, from Stanislaw Gruszka. 9) ftgmac100/ftmac100 build fix, missing interrupt.h include. 10) Memory leak fix in net/hyperv do_set_mutlicast() handling, from Wei Yongjun. 11) Off by one fix in netem packet scheduler, from Vijay Subramanian. 12) TCP loss detection fix from Yuchung Cheng. 13) TCP reset packet MD5 calculation uses wrong address, fix from Shawn Lu. 14) skge carrier assertion and DMA mapping fixes from Stephen Hemminger. 15) Congestion recovery undo performed at the wrong spot in BIC and CUBIC congestion control modules, fix from Neal Cardwell. 16) Ethtool ETHTOOL_GSSET_INFO is unnecessarily restrictive, from Michał Mirosław. 17) Fix triggerable race in ipv6 sysctl handling, from Francesco Ruggeri. 18) Statistics bug fixes in mlx4 from Eugenia Emantayev. 19) rds locking bug fix during info dumps, from your's truly. * git://git.kernel.org/pub/scm/linux/kernel/git/davem/net: (67 commits) rds: Make rds_sock_lock BH rather than IRQ safe. netprio_cgroup.h: dont include module.h from other includes net: flow_dissector.c missing include linux/export.h team: send only changed options/ports via netlink net/hyperv: fix possible memory leak in do_set_multicast() drivers/net: dsa/mv88e6xxx.c files need linux/module.h stmmac: added PCI identifiers llc: Fix race condition in llc_ui_recvmsg stmmac: fix phy naming inconsistency dsa: Add reporting of silicon revision for Marvell 88E6123/88E6161/88E6165 switches. tg3: fix ipv6 header length computation skge: add byte queue limit support mv643xx_eth: Add Rx Discard and Rx Overrun statistics bnx2x: fix compilation error with SOE in fw_dump bnx2x: handle CHIP_REVISION during init_one bnx2x: allow user to change ring size in ISCSI SD mode bnx2x: fix Big-Endianess in ethtool -t bnx2x: fixed ethtool statistics for MF modes bnx2x: credit-leakage fixup on vlan_mac_del_all macvlan: fix a possible use after free ...
| * rds: Make rds_sock_lock BH rather than IRQ safe.David S. Miller2012-01-24
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | rds_sock_info() triggers locking warnings because we try to perform a local_bh_enable() (via sock_i_ino()) while hardware interrupts are disabled (via taking rds_sock_lock). There is no reason for rds_sock_lock to be a hardware IRQ disabling lock, none of these access paths run in hardware interrupt context. Therefore making it a BH disabling lock is safe and sufficient to fix this bug. Reported-by: Kumar Sanghvi <kumaras@chelsio.com> Reported-by: Josh Boyer <jwboyer@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
| * netprio_cgroup.h: dont include module.h from other includesPaul Gortmaker2012-01-24
| | | | | | | | | | | | | | | | | | | | A considerable effort was invested in wiping out module.h from being present in all the other standard includes. This one leaked back in, but once again isn't strictly necessary, so remove it. Signed-off-by: Paul Gortmaker <paul.gortmaker@windriver.com> Signed-off-by: David S. Miller <davem@davemloft.net>
| * net: flow_dissector.c missing include linux/export.hJesper Dangaard Brouer2012-01-24
| | | | | | | | | | | | | | | | The file net/core/flow_dissector.c seems to be missing including linux/export.h. Signed-off-by: Jesper Dangaard Brouer <hawk@comx.dk> Signed-off-by: David S. Miller <davem@davemloft.net>
| * team: send only changed options/ports via netlinkJiri Pirko2012-01-24
| | | | | | | | | | | | | | | | | | This patch changes event message behaviour to send only updated records instead of whole list. This fixes bug on which userspace receives non-actual data in case multiple events occur in row. Signed-off-by: Jiri Pirko <jpirko@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
| * net/hyperv: fix possible memory leak in do_set_multicast()Wei Yongjun2012-01-24
| | | | | | | | | | | | | | | | | | | | do_set_multicast() may not free the memory malloc in netvsc_set_multicast_list(). Signed-off-by: Wei Yongjun <yongjun_wei@trendmicro.com.cn> Signed-off-by: Haiyang Zhang <haiyangz@microsoft.com> Signed-off-by: K. Y. Srinivasan <kys@microsoft.com> Signed-off-by: David S. Miller <davem@davemloft.net>
| * drivers/net: dsa/mv88e6xxx.c files need linux/module.hPaul Gortmaker2012-01-24
| | | | | | | | | | | | | | | | | | | | An implicit instance of module.h leaked back into existence and was masking the fact that these drivers weren't calling out the include for itself. Fix the drivers before we remove the implicit include path via net/netprio_cgroup.h file. Signed-off-by: Paul Gortmaker <paul.gortmaker@windriver.com> Signed-off-by: David S. Miller <davem@davemloft.net>
| * stmmac: added PCI identifiersAlessandro Rubini2012-01-24
| | | | | | | | | | | | | | | | | | | | STM has a device ID within its own VENDOR space, and it is being used in the STA2X11 I/O Hub. Signed-off-by: Alessandro Rubini <rubini@gnudd.com> Acked-by: Giancarlo Asnaghi <giancarlo.asnaghi@st.com> Acked-by: Giuseppe Cavallaro <peppe.cavallaro@st.com> Signed-off-by: David S. Miller <davem@davemloft.net>
| * llc: Fix race condition in llc_ui_recvmsgRadu Iliescu2012-01-24
| | | | | | | | | | | | | | | | | | | | | | There is a race on sk_receive_queue between llc_ui_recvmsg and sock_queue_rcv_skb. Our current solution is to protect skb_eat in llc_ui_recvmsg with the queue spinlock. Signed-off-by: Radu Iliescu <riliescu@ixiacom.com> Signed-off-by: David S. Miller <davem@davemloft.net>
| * stmmac: fix phy naming inconsistencyAlessandro Rubini2012-01-24
| | | | | | | | | | | | | | | | | | | | | | | | | | After commit "db8857b stmmac: use an unique MDIO bus name" my device stopped being probed because two different names were being used in different places. This fixes the inconsistency. Signed-off-by: Alessandro Rubini <rubini@gnudd.com> Acked-by: Giancarlo Asnaghi <giancarlo.asnaghi@st.com> Cc: Giuseppe Cavallaro <peppe.cavallaro@st.com> Cc: Florian Fainelli <florian@openwrt.org> Acked-by: Florian Fainelli <florian@openwrt.org> Signed-off-by: David S. Miller <davem@davemloft.net>
| * dsa: Add reporting of silicon revision for Marvell 88E6123/88E6161/88E6165 ↵Chris Healy2012-01-23
| | | | | | | | | | | | | | | | | | switches. Add reporting of silicon revision during the probe function for Marvell 88E6123/88E6161/88E6165 switches. Signed-off-by: Chris Healy <cphealy@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
| * tg3: fix ipv6 header length computationEric Dumazet2012-01-23
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | tg3_start_xmit() makes the wrong assumption for TSOV6 that skb->head doesnt include any payload data. if (skb_is_gso_v6(skb)) hdr_len = skb_headlen(skb) - ETH_HLEN; This is not true anymore after commit f07d960df3 (tcp: avoid frag allocation for small frames) We should instead use : skb_transport_offset(skb) + tcp_hdrlen(skb) Its also true for IPv4 Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com> CC: Matt Carlson <mcarlson@broadcom.com> CC: Michael Chan <mchan@broadcom.com> Signed-off-by: David S. Miller <davem@davemloft.net>
| * skge: add byte queue limit supportstephen hemminger2012-01-23
| | | | | | | | | | | | | | | | | | This also changes the cleanup logic slightly to aggregate completed notifications for multiple packets. Signed-off-by: Stephen Hemminger <shemminger@vyatta.com> Acked-by: Eric Dumazet <eric.dumazet@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
| * mv643xx_eth: Add Rx Discard and Rx Overrun statisticsPaulius Zaleckas2012-01-23
| | | | | | | | | | | | | | | | | | | | | | These statistics helped me a lot while searching who is losing packets in my setup. I added these stats to MIB group since they are very similar, but just in other registers. I have tested this patch on 88F6281 SoC. Signed-off-by: Paulius Zaleckas <paulius.zaleckas@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
| * bnx2x: fix compilation error with SOE in fw_dumpYuval Mintz2012-01-23
| | | | | | | | | | | | Signed-off-by: Yuval Mintz <yuvalmin@broadcom.com> Signed-off-by: Eilon Greenstein <eilong@broadcom.com> Signed-off-by: David S. Miller <davem@davemloft.net>
| * bnx2x: handle CHIP_REVISION during init_oneAriel Elior2012-01-23
| | | | | | | | | | | | | | | | | | | | The macro `CHIP_IS_E1x' requires `bp' to be initialized. As `bp' is not yet initialized during this phase of `bnx2x_init_dev', it accessed uninitialized fields in the struct. Signed-off-by: Ariel Elior <ariele@broadcom.com> Signed-off-by: Eilon Greenstein <eilong@broadcom.com> Signed-off-by: David S. Miller <davem@davemloft.net>
| * bnx2x: allow user to change ring size in ISCSI SD modeDmitry Kravkov2012-01-23
| | | | | | | | | | | | Signed-off-by: Dmitry Kravkov <dmitry@broadcom.com> Signed-off-by: Eilon Greenstein <eilong@broadcom.com> Signed-off-by: David S. Miller <davem@davemloft.net>
| * bnx2x: fix Big-Endianess in ethtool -tDmitry Kravkov2012-01-23
| | | | | | | | | | | | Signed-off-by: Dmitry Kravkov <dmitry@broadcom.com> Signed-off-by: Eilon Greenstein <eilong@broadcom.com> Signed-off-by: David S. Miller <davem@davemloft.net>
| * bnx2x: fixed ethtool statistics for MF modesYuval Mintz2012-01-23
| | | | | | | | | | | | | | | | | | Previosuly, in MF modes `ethtool -S' lacked some of the statistics which appeared in non-MF modes. This has been fixed. Signed-off-by: Yuval Mintz <yuvalmin@broadcom.com> Signed-off-by: Eilon Greenstein <eilong@broadcom.com> Signed-off-by: David S. Miller <davem@davemloft.net>
| * bnx2x: credit-leakage fixup on vlan_mac_del_allYuval Mintz2012-01-23
| | | | | | | | | | | | | | | | | | | | | | | | | | Upon insertion of elements into the execution queue, it is validated that there are enough credits to support additional vlan-macs, and the credits are consumed. However, when removing a pending command in `bnx2x_vland_mac_del_all' the consumed credits are not released, which might cause leakage and eventually the inability to add new vlan-macs in certain scenarios. Signed-off-by: Yuval Mintz <yuvalmin@broadcom.com> Signed-off-by: Eilon Greenstein <eilong@broadcom.com> Signed-off-by: David S. Miller <davem@davemloft.net>
| * macvlan: fix a possible use after freeEric Dumazet2012-01-23
| | | | | | | | | | | | | | | | | | | | Commit bc416d9768 (macvlan: handle fragmented multicast frames) added a possible use after free in macvlan_handle_frame(), since ip_check_defrag() uses pskb_may_pull() : skb header can be reallocated. Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com> Cc: Ben Greear <greearb@candelatech.com> Signed-off-by: David S. Miller <davem@davemloft.net>
| * ethtool: allow ETHTOOL_GSSET_INFO for usersMichał Mirosław2012-01-22
| | | | | | | | | | | | | | | | | | Allow ETHTOOL_GSSET_INFO ethtool ioctl() for unprivileged users. ETHTOOL_GSTRINGS is already allowed, but is unusable without this one. Signed-off-by: Michał Mirosław <mirq-linux@rere.qmqm.pl> Acked-by: Ben Hutchings <bhutchings@solarflare.com> Signed-off-by: David S. Miller <davem@davemloft.net>
| * bluetooth: hci: Fix type of "enable_hs" to bool.David S. Miller2012-01-22
| | | | | | | | | | | | | | | | | | Fixes: net/bluetooth/hci_core.c: In function ‘__check_enable_hs’: net/bluetooth/hci_core.c:2587:1: warning: return from incompatible pointer type [enabled by default] Signed-off-by: David S. Miller <davem@davemloft.net>
| * net: introduce res_counter_charge_nofail() for socket allocationsGlauber Costa2012-01-22
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | There is a case in __sk_mem_schedule(), where an allocation is beyond the maximum, but yet we are allowed to proceed. It happens under the following condition: sk->sk_wmem_queued + size >= sk->sk_sndbuf The network code won't revert the allocation in this case, meaning that at some point later it'll try to do it. Since this is never communicated to the underlying res_counter code, there is an inbalance in res_counter uncharge operation. I see two ways of fixing this: 1) storing the information about those allocations somewhere in memcg, and then deducting from that first, before we start draining the res_counter, 2) providing a slightly different allocation function for the res_counter, that matches the original behavior of the network code more closely. I decided to go for #2 here, believing it to be more elegant, since #1 would require us to do basically that, but in a more obscure way. Signed-off-by: Glauber Costa <glommer@parallels.com> Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Michal Hocko <mhocko@suse.cz> CC: Tejun Heo <tj@kernel.org> CC: Li Zefan <lizf@cn.fujitsu.com> CC: Laurent Chavey <chavey@google.com> Acked-by: Tejun Heo <tj@kernel.org> Signed-off-by: David S. Miller <davem@davemloft.net>
| * cgroup: make sure memcg margin is 0 when over limitGlauber Costa2012-01-22
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | For the memcg sock code, we'll need to register allocations that are temporarily over limit. Let's make sure that margin is 0 in this case. I am keeping this as a separate patch, so that if any weirdness interaction appears in the future, we can now exactly what caused it. Suggested by Johannes Weiner Signed-off-by: Glauber Costa <glommer@parallels.com> CC: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> CC: Johannes Weiner <hannes@cmpxchg.org> CC: Michal Hocko <mhocko@suse.cz> CC: Tejun Heo <tj@kernel.org> CC: Li Zefan <lizf@cn.fujitsu.com> Acked-by: Tejun Heo <tj@kernel.org> Signed-off-by: David S. Miller <davem@davemloft.net>
| * net: fix socket memcg build with !CONFIG_NETGlauber Costa2012-01-22
| | | | | | | | | | | | | | | | | | | | There is still a build bug with the sock memcg code, that triggers with !CONFIG_NET, that survived my series of randconfig builds. Signed-off-by: Glauber Costa <glommer@parallels.com> Reported-by: Randy Dunlap <rdunlap@xenotime.net> CC: Hiroyouki Kamezawa <kamezawa.hiroyu@jp.fujitsu.com> Signed-off-by: David S. Miller <davem@davemloft.net>
| * kernel-doc: fix new warning in net/sock.hRandy Dunlap2012-01-22
| | | | | | | | | | | | | | | | | | Fix new kernel-doc warning: Warning(include/net/sock.h:372): No description found for parameter 'sk_cgrp_prioidx' Signed-off-by: Randy Dunlap <rdunlap@xenotime.net> Signed-off-by: David S. Miller <davem@davemloft.net>
| * kernel-doc: fix new warning in net/phy/mdio_bus.cRandy Dunlap2012-01-22
| | | | | | | | | | | | | | | | | | Fix new kernel-doc warning: Warning(drivers/net/phy/mdio_bus.c:49): No description found for parameter 'size' Signed-off-by: Randy Dunlap <rdunlap@xenotime.net> Signed-off-by: David S. Miller <davem@davemloft.net>
| * tcp: md5: using remote adress for md5 lookup in rst packetshawnlu2012-01-22
| | | | | | | | | | | | | | | | | | md5 key is added in socket through remote address. remote address should be used in finding md5 key when sending out reset packet. Signed-off-by: shawnlu <shawn.lu@ericsson.com> Signed-off-by: David S. Miller <davem@davemloft.net>
| * be2net: create RSS rings even in multi-channel configsSathya Perla2012-01-22
| | | | | | | | | | | | | | | | | | | | | | | | Currently RSS rings are not created in a multi-channel config. RSS rings can be created on one (out of four) interfaces per port in a multi-channel config. Doing this insulates the driver from a FW bug wherin multi-channel config is wrongly reported even when not enabled. This also helps performance in a multi-channel config, as one interface per port gets RSS rings. Signed-off-by: Sathya Perla <sathya.perla@emulex.com> Signed-off-by: David S. Miller <davem@davemloft.net>
| * pktgen: Fix unsigned function that is returning negative valsPaul Gortmaker2012-01-22
| | | | | | | | | | | | | | | | | | | | Every call to num_args() immediately checks the return value for less than zero, as it will return -EFAULT for a failed get_user() call. So it makes no sense for the function to be declared as an unsigned long. Signed-off-by: Paul Gortmaker <paul.gortmaker@windriver.com> Signed-off-by: David S. Miller <davem@davemloft.net>
| * tcp: detect loss above high_seq in recoveryYuchung Cheng2012-01-22
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Correctly implement a loss detection heuristic: New sequences (above high_seq) sent during the fast recovery are deemed lost when higher sequences are SACKed. Current code does not catch these losses, because tcp_mark_head_lost() does not check packets beyond high_seq. The fix is straight-forward by checking packets until the highest sacked packet. In addition, all the FLAG_DATA_LOST logic are in-effective and redundant and can be removed. Update the loss heuristic comments. The algorithm above is documented as heuristic B, but it is redundant too because heuristic A already covers B. Note that this change only marks some forward-retransmitted packets LOST. It does NOT forbid TCP performing further CWR on new losses. A potential follow-up patch under preparation is to perform another CWR on "new" losses such as 1) sequence above high_seq is lost (by resetting high_seq to snd_nxt) 2) retransmission is lost. Signed-off-by: Yuchung Cheng <ycheng@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
| * skge: check for PCI dma mapping errorsstephen hemminger2012-01-22
| | | | | | | | | | | | | | | | | | | | | | Driver should check for mapping errors. Machines with limited DMA maps may return an error when a PCI map is requested (not an issue on standard x86). Also use upper/lower 32 bits macros for clarity. Signed-off-by: Stephen Hemminger <shemminger@vyatta.com> Signed-off-by: David S. Miller <davem@davemloft.net>
| * skge: don't assert carrier until link is upstephen hemminger2012-01-22
| | | | | | | | | | | | | | | | Skge device would assert carrier (link up) as soon as network device open was called, rather than waiting until PHY has detected link. Signed-off-by: Stephen Hemminger <shemminger@vyatta.com> Signed-off-by: David S. Miller <davem@davemloft.net>
| * netem: Fix off-by-one bug in reorderingVijay Subramanian2012-01-22
| | | | | | | | | | | | | | | | | | With netem reordering, a gap of N is supposed to reorder every Nth packet with given reorder probability. However, the code currently skips N packets and reorders every (N+1)th packet. Signed-off-by: Vijay Subramanian <subramanian.vijay@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
| * mlx4_core: map async events to arbitrary slave eqsMarcel Apfelbaum2012-01-22
| | | | | | | | | | | | | | | | | | Slave async events were mapped to single eq. This patch fixes this issue, so the slaves can map the async events to any eq. Signed-off-by: Marcel Apfelbaum <marcela@dev.mellanox.co.il> Reviewed-by: Jack Morgenstein <jackm@dev.mellanox.co.il> Signed-off-by: David S. Miller <davem@davemloft.net>
| * mlx4_core: Fix mtt profile issueMarcel Apfelbaum2012-01-22
| | | | | | | | | | | | | | | | | | | | Num mtts from profile is really the number of mtt segments. Thus, in make profile, to get the proper number of MTT entries, must multiply num_mtts by mtts per segment. Signed-off-by: Marcel Apfelbaum <marcela@dev.mellanox.co.il> Reviewed-by: Jack Morgenstein <jackm@dev.mellanox.co.il> Signed-off-by: David S. Miller <davem@davemloft.net>
| * mlx4_core: removed function index from vf.Marcel Apfelbaum2012-01-22
| | | | | | | | | | | | | | | | The Virtual Functions should not be aware their function number. Signed-off-by: Marcel Apfelbaum <marcela@dev.mellanox.co.il> Reviewed-by: Jack Morgenstein <jackm@dev.mellanox.co.il> Signed-off-by: David S. Miller <davem@davemloft.net>
| * mlx4_en: eth statistics modificationEugenia Emantayev2012-01-22
| | | | | | | | | | | | | | | | | | | | | | In native mode display all available staticstics. In SRIOV mode on VF display only SW counters statistics, in SRIOV mode on hypervisor display SW counters and errors (got from FW) statistics. Signed-off-by: Eugenia Emantayev <eugenia@mellanox.co.il> Reviewed-by: Yevgeny Petrilin <yevgenyp@mellanox.co.il> Signed-off-by: David S. Miller <davem@davemloft.net>
| * mlx4: VF is not allowed to perform dump statsEugenia Emantayev2012-01-22
| | | | | | | | | | | | | | | | | | In multifunction mode - DUMP_STATS command is not executed for VFs. Signed-off-by: Eugenia Emantayev <eugenia@mellanox.co.il> Reviewed-by: Yevgeny Petrilin <yevgenyp@mellanox.co.il> Signed-off-by: David S. Miller <davem@davemloft.net>
| * mlx4_en: clear all eth statistics when port goes upEugenia Emantayev2012-01-22
| | | | | | | | | | | | | | | | Bug fix: Not all stats fields were cleared. Signed-off-by: Eugenia Emantayev <eugenia@mellanox.co.il> Reviewed-by: Yevgeny Petriln <yevgenyp@mellanox.co.il> Signed-off-by: David S. Miller <davem@davemloft.net>
| * tcp: fix undo after RTO for CUBICNeal Cardwell2012-01-20
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | This patch fixes CUBIC so that cwnd reductions made during RTOs can be undone (just as they already can be undone when using the default/Reno behavior). When undoing cwnd reductions, BIC-derived congestion control modules were restoring the cwnd from last_max_cwnd. There were two problems with using last_max_cwnd to restore a cwnd during undo: (a) last_max_cwnd was set to 0 on state transitions into TCP_CA_Loss (by calling the module's reset() functions), so cwnd reductions from RTOs could not be undone. (b) when fast_covergence is enabled (which it is by default) last_max_cwnd does not actually hold the value of snd_cwnd before the loss; instead, it holds a scaled-down version of snd_cwnd. This patch makes the following changes: (1) upon undo, revert snd_cwnd to ca->loss_cwnd, which is already, as the existing comment notes, the "congestion window at last loss" (2) stop forgetting ca->loss_cwnd on TCP_CA_Loss events (3) use ca->last_max_cwnd to check if we're in slow start Signed-off-by: Neal Cardwell <ncardwell@google.com> Acked-by: Stephen Hemminger <shemminger@vyatta.com> Acked-by: Sangtae Ha <sangtae.ha@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
| * tcp: fix undo after RTO for BICNeal Cardwell2012-01-20
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | This patch fixes BIC so that cwnd reductions made during RTOs can be undone (just as they already can be undone when using the default/Reno behavior). When undoing cwnd reductions, BIC-derived congestion control modules were restoring the cwnd from last_max_cwnd. There were two problems with using last_max_cwnd to restore a cwnd during undo: (a) last_max_cwnd was set to 0 on state transitions into TCP_CA_Loss (by calling the module's reset() functions), so cwnd reductions from RTOs could not be undone. (b) when fast_covergence is enabled (which it is by default) last_max_cwnd does not actually hold the value of snd_cwnd before the loss; instead, it holds a scaled-down version of snd_cwnd. This patch makes the following changes: (1) upon undo, revert snd_cwnd to ca->loss_cwnd, which is already, as the existing comment notes, the "congestion window at last loss" (2) stop forgetting ca->loss_cwnd on TCP_CA_Loss events (3) use ca->last_max_cwnd to check if we're in slow start Signed-off-by: Neal Cardwell <ncardwell@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
| * enic: fix compile when CONFIG_PCI_IOV is not enabledRoopa Prabhu2012-01-20
| | | | | | | | | | | | | | | | | | reverting back change that access enic->num_vfs outside CONFIG_PCI_IOV Reported-by: Randy Dunlap <rdunlap@xenotime.net> Signed-off-by: Roopa Prabhu <roprabhu@cisco.com> Signed-off-by: David S. Miller <davem@davemloft.net>
| * ixgbevf: make operations tables constStephen Hemminger2012-01-19
| | | | | | | | | | | | | | | | | | | | The arrays of function pointers should be const to make life harder for rootkits. Signed-off-by: Stephen Hemminger <shemminger@vyatta.com> Tested-by: Sibai Li <sibai.li@intel.com> Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com> Signed-off-by: David S. Miller <davem@davemloft.net>
| * ixgbevf: fix sparse warningsStephen Hemminger2012-01-19
| | | | | | | | | | | | | | | | | | | | | | | | Fixes sparse warnings: drivers/net/ethernet/intel/ixgbevf/vf.c:418:21: warning: symbol 'ixgbevf_82599_vf_info' was not declared. Should it be static? drivers/net/ethernet/intel/ixgbevf/vf.c:423:21: warning: symbol 'ixgbevf_X540_vf_info' was not declared. Should it be static? drivers/net/ethernet/intel/ixgbevf/mbx.c:331:29: warning: symbol 'ixgbevf_mbx_ops' was not declared. Should it be static? Signed-off-by: Stephen Hemminger <shemminger@vyatta.com> Tested-by: Sibai Li <sibai.li@intel.com> Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com> Signed-off-by: David S. Miller <davem@davemloft.net>
| * ixgbevf: make ethtool ops and strings constStephen Hemminger2012-01-19
| | | | | | | | | | | | | | Signed-off-by: Stephen Hemminger <shemminger@vyatta.com> Tested-by: Sibai Li <sibai.li@intel.com> Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com> Signed-off-by: David S. Miller <davem@davemloft.net>
| * ixgbevf: Prevent possible race condition by checking for messageGreg Rose2012-01-19
| | | | | | | | | | | | | | | | | | | | The mailbox interrupt routine might cause a race condition sometimes and cause a message to be missed. Signed-off-by: Greg Rose <gregory.v.rose@intel.com> Tested-by: Sibai Li <sibai.li@intel.com> Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com> Signed-off-by: David S. Miller <davem@davemloft.net>
| * ixgbe: Fix register defines to correctly handle complex expressionsAlexander Duyck2012-01-19
| | | | | | | | | | | | | | | | | | | | | | This patch is meant to address possible issues with the IXGBE register defines generating incorrect values when given a complex expression for the register offset. Signed-off-by: Alexander Duyck <alexander.h.duyck@intel.com> Tested-by: Phil Schmitt <phillip.j.schmitt@intel.com> Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com> Signed-off-by: David S. Miller <davem@davemloft.net>
| * igbvf: Remove unnecessary irq disable/enableMitch A Williams2012-01-19
| | | | | | | | | | | | | | | | | | | | This irq disable/enable pair used to wrap access to the driver's vlgrp struct, which is no longer present. So, then, this could also so no longer be present. Signed-off-by: Mitch Williams <mitch.a.williams@intel.com> Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com> Signed-off-by: David S. Miller <davem@davemloft.net>
generated by cgit v1.2.2 (git 2.25.0) at 2025-01-06 10:47:00 -0500