aboutsummaryrefslogtreecommitdiffstats
AgeCommit message (Collapse)AuthorFilesLines
2014-03-13Merge branch 'napi_budget_zero'David S. Miller2-4/+4
Eric W. Biederman says: ==================== Don't receive packets when the napi budget == 0 To the best of understanding processing any received packets when the napi budget == 0 is broken driver behavior. At the same time I don't think we have ever cared before so there are a handful of drivers that need fixes. I care now as I will shortly be using htis in netpoll to get the tx queue processing without the rx queue processing. Drivers that need fixes are few and far between, and so far I have only found two of them. More similar patches later if I find more drivers that need fixes. ==================== Signed-off-by: David S. Miller <davem@davemloft.net>
2014-03-138139cp: Don't receive packets when the napi budget == 0Eric W. Biederman1-4/+1
Processing any incoming packets with a with a napi budget of 0 is incorrect driver behavior. This matters as netpoll will shortly call drivers with a budget of 0 to avoid receive packet processing happening in hard irq context. Signed-off-by: "Eric W. Biederman" <ebiederm@xmission.com Acked-by: Eric Dumazet <edumazet@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2014-03-13bnx2: Don't receive packets when the napi budget == 0Eric W. Biederman1-0/+3
Processing any incoming packets with a with a napi budget of 0 is incorrect driver behavior. This matters as netpoll will shortly call drivers with a budget of 0 to avoid receive packet processing happening in hard irq context. Signed-off-by: "Eric W. Biederman" <ebiederm@xmission.com> Acked-by: Eric Dumazet <edumazet@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2014-03-13consolidate duplicate code is skb_checksum_setup() helpersJan Beulich1-90/+50
consolidate duplicate code is skb_checksum_setup() helpers Realizing that the skb_maybe_pull_tail() calls in the IP-protocol specific portions of both helpers are terminal ones (i.e. no further pulls are expected), their maximum size to be pulled can be made match their minimal size needed, thus making the code identical and hence possible to be moved into another helper. Signed-off-by: Jan Beulich <jbeulich@suse.com> Cc: Paul Durrant <paul.durrant@citrix.com> Cc: David Miller <davem@davemloft.net> Cc: Eric Dumazet <edumazet@google.com> Reviewed-by: Paul Durrant <paul.durrant@citrix.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2014-03-13Merge branch 'master' of git://git.kernel.org/pub/scm/linux/kernel/git/jkirsher/net-nextDavid S. Miller29-51/+132
Jeff Kirsher says: ==================== Intel Wired LAN Driver Updates This series contains updates to igb, e1000e, ixgbe and ixgbevf. Tom Herbert provides changes to e1000e, igb and ixgbe to call skb_set_hash() to set the hash and its type in an skbuff. Carolyn provides a fix for igb where using ethtool for EEE settings, which was not working correctly. Jacob provides some trivial cleanups and fixes for ixgbe which mainly dealt with the file headers. Julia Lawall provides a one fix for ixgbevf where the driver did not need to adjust the power state on suspend, so the call to pci_set_power_state() in the resume function was a no-op. v2: - dropped patches 4-6 from original series which implemented debugfs for igb from Carolyn based on feed back from David Miller and Or Gerlitz ==================== Signed-off-by: David S. Miller <davem@davemloft.net>
2014-03-13Merge branch 'for-davem' of git://git.kernel.org/pub/scm/linux/kernel/git/linville/wireless-nextDavid S. Miller314-4597/+30338
John W. Linville says: ==================== For the mac80211 bits, Johannes says: "This time, I have a number of small fixes and improvements, and those are fairly straight-forward. More interesting changes come from Luca with some preparations for the CSA work, mostly around interface/channel combinations checking. One other possibly interesting change is a small one by myself to add NAPI support back to mac80211, which can help improve TCP behaviour through GRO." For the Bluetooth bits, Gustavo says: "This is our first pull request for 3.15, the main feature here is the addition of the privacy feature for low energy devices. Other than that we have a bunch of small improvements, fixes, and clean ups all over the tree." And... "Another pull request to 3.15. Here we have the second part of the LE private feature, the LE auto-connect feature and improvements to the power off procedures. The rest are small improvements, clean up, and fixes." For the iwlwifi bits, Emmanuel says: "I have here a whole bunch of various things. Trivial cleanups, debugfs handlers and new stuff for the new generation of devices along with new capabilities for monitor mode. We also have support for power save for dual interface mode, but that is not supported by the firmware currently available." And for the Atheros bits, Kalle says: "For ath10k Alexander did some cleanup to PCI error cases and switched ath10k to use pci_enable_msi_range(). Michal implemented AP CSA support and sta_rc_update() operation. I enabled firmware "STA quick kickout" functionality for faster detection of disappeared clients. Also there are lots of small fixes to everywhere from various people." I pulled the wireless tree to avoid some merge conflicts, and I reverted the staging patch that I had mistakenly merged previously. Along with that, mwifiex, brcmfmac, wil6210, ath9k, and a few other drivers get their usual round of updates. Also notable is the addition of yet another driver in the rtlwifi family. ... I have amended this commit request to correct the build problems in staging, including a warning added to one of the staging drivers by the wireless-next tree. I also included a fix from Larry Finger to address an issue found in rtl8723be by Dan Carpenter and smatch. ==================== Signed-off-by: David S. Miller <davem@davemloft.net>
2014-03-13Merge branch 'cxgb4-next'David S. Miller4-28/+219
Hariprasad Shenai says: ==================== Misc. fixes for cxgb4 This patch series provides miscelleneous fixes for Chelsio T4/T5 adapters cxgb4 driver related to SGE and MTU. Also fixes regression in LSO calcuation path. ("cxgb4: Calculate len properly for LSO path") The patches series is created against David Miller's 'net-next' tree. And includes patches on cxgb4 driver. We would like to request this patch series to get merged via David Miller's 'net-next' tree. We have included all the maintainers of respective drivers. Kindly review the change and let us know in case of any review comments. ==================== Signed-off-by: David S. Miller <davem@davemloft.net>
2014-03-13cxgb4: Calculate len properly for LSO pathKumar Sanghvi1-1/+1
Commit 0034b29 ("cxgb4: Don't assume LSO only uses SGL path in t4_eth_xmit()") introduced a regression where-in length was calculated wrongly for LSO path, causing chip hangs. So, correct the calculation of len. Fixes: 0034b29 ("cxgb4: Don't assume LSO only uses SGL path in t4_eth_xmit()") Signed-off-by: Kumar Sanghvi <kumaras@chelsio.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2014-03-13cxgb4: Updates for T5 SGE's Egress Congestion ThresholdKumar Sanghvi2-5/+19
Based on original work by Casey Leedom <leedom@chelsio.com> Signed-off-by: Kumar Sanghvi <kumaras@chelsio.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2014-03-13cxgb4: Rectify emitting messages about SGE Ingress DMA channels being potentially stuckKumar Sanghvi2-20/+79
Based on original work by Casey Leedom <leedom@chelsio.com> Signed-off-by: Kumar Sanghvi <kumaras@chelsio.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2014-03-13cxgb4: Add code to dump SGE registers when hitting idma hangsKumar Sanghvi3-0/+110
Based on original work by Casey Leedom <leedom@chelsio.com> Signed-off-by: Kumar Sanghvi <kumaras@chelsio.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2014-03-13cxgb4: Fix some small bugs in t4_sge_init_soft() when our Page Size is 64KBKumar Sanghvi1-2/+10
We'd come in with SGE_FL_BUFFER_SIZE[0] and [1] both equal to 64KB and the extant logic would flag that as an error. Based on original work by Casey Leedom <leedom@chelsio.com> Signed-off-by: Kumar Sanghvi <kumaras@chelsio.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2014-03-13Merge branch 'master' of git://git.kernel.org/pub/scm/linux/kernel/git/linville/wireless-next into for-davemJohn W. Linville314-4597/+30338
Conflicts: drivers/net/wireless/ath/ath9k/recv.c
2014-03-13rtlwifi: rtl8723be: Fix array dimension problemsLarry Finger1-5/+9
Commit a619d1abe20c leads to the following static checker warning: drivers/net/wireless/rtlwifi/rtl8723be/phy.c:667 _rtl8723be_store_tx_power_by_rate() error: buffer overflow 'rtlphy->tx_power_by_rate_offset[band]' 4 <= 5 This warning arises because the code is testing the indices for the wrong maximum values. In addition, the tests merely putput a warning, and then procedes to corrupt memory. With this change, any such invalid memory access is avoided. Signed-off-by: Larry Finger <Larry.Finger@lwfinger.net> Reported-by: Dan Carpenter <dan.carpenter@oracle.com> Signed-off-by: John W. Linville <linville@tuxdriver.com>
2014-03-13wlan-ng: fixup staging driver for removal of ieee80211_dsss_chan_to_freqJohn W. Linville1-1/+1
Commit 3ebe8e257307 ("ieee80211: remove function ieee80211_{dsss_chan_to_freq, freq_to_dsss_chan}") removed ieee80211_dsss_chan_to_freq, but it neglected to account for this staging driver... Cc: Zhao, Gang <gamerh2o@gmail.com> Signed-off-by: John W. Linville <linville@tuxdriver.com>
2014-03-13rtl8821ae: fixup staging driver for revised ieee80211_is_robust_mgmt_frameJohn W. Linville1-1/+1
Commit d8ca16db6bb2 ("mac80211: add length check in ieee80211_is_robust_mgmt_frame()") changed that API to take an skb, and added "_ieee80211_is_robust_mgmt_frame" as a direct replacement for the older API. This is the same fix that was applied to the other rtlwifi drivers in that commit. Cc: Johannes Berg <johannes.berg@intel.com> Signed-off-by: John W. Linville <linville@tuxdriver.com>
2014-03-13net: sctp: remove NULL check in sctp_assoc_update_retran_pathDaniel Borkmann1-2/+1
This is basically just to let Coverity et al shut up. Remove an unneeded NULL check in sctp_assoc_update_retran_path(). It is safe to remove it, because in sctp_assoc_update_retran_path() we iterate over the list of transports, our own transport which is asoc->peer.retran_path included. In the iteration, we skip the list head element and transports in state SCTP_UNCONFIRMED. Such transports came from peer addresses received in INIT/INIT-ACK address parameters. They are not yet confirmed by a heartbeat and not available for data transfers. We know however that in the list of transports, even if it contains such elements, it at least contains our asoc->peer.retran_path as well, so even if next to that element, we only encounter SCTP_UNCONFIRMED transports, we are always going to fall back to asoc->peer.retran_path through sctp_trans_elect_best(), as that is for sure not SCTP_UNCONFIRMED as per fbdf501c9374 ("sctp: Do no select unconfirmed transports for retransmissions"). Whenever we call sctp_trans_elect_best() it will give us a non-NULL element back, and therefore when we break out of the loop, we are guaranteed to have a non-NULL transport pointer, and can remove the NULL check. Reported-by: Dan Carpenter <dan.carpenter@oracle.com> Reported-by: Dave Jones <davej@redhat.com> Signed-off-by: Daniel Borkmann <dborkman@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2014-03-13Revert "Revert "Staging: rtl8812ae: remove modules field of rate_control_ops""John W. Linville1-1/+0
This reverts commit 161d7855543520cde5f49df788b0ea0553a9f83a. Reversal of fortune -- I thought this was going to be resolved by other means, but that hasn't materialized. Plus, apparently we now care more than I realized about not breaking staging drivers... Signed-off-by: John W. Linville <linville@tuxdriver.com>
2014-03-12ixgbevf: delete unneeded call to pci_set_power_stateJulia Lawall1-1/+0
This driver does not need to adjust the power state on suspend, so the call to pci_set_power_state in the resume function is a no-op. Drop it, to make the code more understandable. Signed-off-by: Julia Lawall <Julia.Lawall@lip6.fr> Tested-by: Phil Schmitt <phillip.j.schmitt@intel.com> Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
2014-03-12ixgbe: fix some multiline hw_dbg printsJacob Keller1-5/+3
This patch fixes some formatting on multilined print messages, so that the text of the print appears on a single line, which aids in grepping the sourcecode for where the error came from. Signed-off-by: Jacob Keller <jacob.e.keller@intel.com> Tested-by: Phil Schmitt <phillip.j.schmitt@intel.com> Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
2014-03-12ixgbe: fixup header for ixgbe_set_rxpba_82598Jacob Keller1-7/+7
The header above this function did not match the function prototype. This patch rewords the comment to specify the correct parameters. Signed-off-by: Jacob Keller <jacob.e.keller@intel.com> Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
2014-03-12ixgbe: add Linux NICS mailing list to contact infoJacob Keller23-0/+23
This patch updates the contact information on the ixgbe driver files so that every file includes the Linux NICS address, as it is still used, but only a few of the files mentioned it. Signed-off-by: Jacob Keller <jacob.e.keller@intel.com> Tested-by: Phil Schmitt <phillip.j.schmitt@intel.com> Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
2014-03-12ixgbe: move setting rx_pb_size into get_invariantsJacob Keller3-4/+3
Signed-off-by: Jacob Keller <jacob.e.keller@intel.com> Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
2014-03-12ixgbe: Fix format string in ixgbe_fcoe.cMasanari Iida1-1/+1
cppcheck detected following warning in ixgbe_fcoe.c (warning) %d in format string (no. 1) requires 'int' but the argument type is 'unsigned int'. Signed-off-by: Masanari Iida <standby24x7@gmail.com> Tested-By: Jack Morgan<jack.morgan@intel.com> Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
2014-03-12net: ixgbe calls skb_set_hashTom Herbert1-1/+3
Drivers should call skb_set_hash to set the hash and its type in an skbuff. Signed-off-by: Tom Herbert <therbert@google.com> Tested-by: Phil Schmitt <phillip.j.schmitt@intel.com> Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
2014-03-12igb: Fix for devices using ethtool for EEE settingsCarolyn Wyborny4-30/+88
This patch fixes a problem where using ethtool for EEE setting was not working correctly. This patch also fixes a problem where the function that checks for EEE status on i354 devices was not being called and was causing warnings with static analysis tools. Reported-by: Rashika Kheria <rashika.kheria@gmail.com> Reported-by: Josh Triplett <josh@joshtriplett.org> Reported-by: Stephen Hemminger <stephen@networkplumber.org> Signed-off-by: Carolyn Wyborny <carolyn.wyborny@intel.com> Tested-by: Jeff Pieper <jeffrey.e.pieper@intel.com> Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
2014-03-12net: igb calls skb_set_hashTom Herbert1-1/+3
Drivers should call skb_set_hash to set the hash and its type in an skbuff. Signed-off-by: Tom Herbert <therbert@google.com> Tested-by: Aaron Brown <aaron.f.brown@intel.com> Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
2014-03-12net: e1000e calls skb_set_hashTom Herbert1-1/+1
Drivers should call skb_set_hash to set the hash and its type in an skbuff. Signed-off-by: Tom Herbert <therbert@google.com> Tested-by: Aaron Brown <aaron.f.brown@intel.com> Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
2014-03-12Merge branch 'dev_kfree_skb_any'David S. Miller12-30/+30
Eric W. Biederman says: ==================== Using dev_kfree_skb_any for functions called in multiple contexts This patchset should be an uncontroversial set of changes to change dev_kfree_skb to dev_kfree_skb_any for code paths that are called in hard irq contexts in addition to other contexts. netpoll is the reason this code gets called in multiple contexts. There is more coming but these changes are a good starting place, and stand on their own. Since the last round changes to the rx path have been removed netpoll will changed to avoid that. ==================== Signed-off-by: David S. Miller <davem@davemloft.net> Acked-by: Eric Dumazet <edumazet@google.com>
2014-03-12gianfar: Carefully free skbs in functions called by netpoll.Eric W. Biederman1-2/+2
netpoll can call functions in hard irq context that are ordinarily called in lesser contexts. For those functions use dev_kfree_skb_any and dev_consume_skb_any so skbs are freed safely from hard irq context. Signed-off-by: "Eric W. Biederman" <ebiederm@xmission.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2014-03-12benet: Call dev_kfree_skby_any instead of kfree_skb.Eric W. Biederman1-1/+1
Replace free_skb with dev_kfree_skb_any in be_tx_compl_process as which can be called in hard irq by netpoll, softirq context by normal napi polling, and in normal sleepable context by the network device close method. Signed-off-by: "Eric W. Biederman" <ebiederm@xmission.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2014-03-12mlx4: Call dev_kfree_skby_any instead of dev_kfree_skb.Eric W. Biederman1-1/+1
Replace dev_kfree_skb with dev_kfree_skb_any in functions that can be called in hard irq and other contexts. Signed-off-by: "Eric W. Biederman" <ebiederm@xmission.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2014-03-12ixgb: Call dev_kfree_skby_any instead of dev_kfree_skb.Eric W. Biederman1-3/+3
Replace dev_kfree_skb with dev_kfree_skb_any in functions that can be called in hard irq and other contexts. Signed-off-by: "Eric W. Biederman" <ebiederm@xmission.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2014-03-12tg3: Call dev_kfree_skby_any instead of dev_kfree_skb.Eric W. Biederman1-7/+7
Replace dev_kfree_skb with dev_kfree_skb_any in functions that can be called in hard irq and other contexts. Signed-off-by: "Eric W. Biederman" <ebiederm@xmission.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2014-03-12bnx2: Call dev_kfree_skby_any instead of dev_kfree_skb.Eric W. Biederman1-3/+3
Replace dev_kfree_skb with dev_kfree_skb_any in functions that can be called in hard irq and other contexts. Signed-off-by: "Eric W. Biederman" <ebiederm@xmission.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2014-03-12bonding: Call dev_kfree_skby_any instead of kfree_skb.Eric W. Biederman3-7/+7
Replace kfree_skb with dev_kfree_skb_any in functions that can be called in hard irq and other contexts. Signed-off-by: "Eric W. Biederman" <ebiederm@xmission.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2014-03-12r8169: Call dev_kfree_skby_any instead of dev_kfree_skb.Eric W. Biederman1-3/+3
Replace dev_kfree_skb with dev_kfree_skb_any in functions that can be called in hard irq and other contexts. Signed-off-by: "Eric W. Biederman" <ebiederm@xmission.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2014-03-128139too: Call dev_kfree_skby_any instead of dev_kfree_skb.Eric W. Biederman1-2/+2
Replace dev_kfree_skb with dev_kfree_skb_any in functions that can be called in hard irq and other contexts. Signed-off-by: "Eric W. Biederman" <ebiederm@xmission.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2014-03-128139cp: Call dev_kfree_skby_any instead of kfree_skb.Eric W. Biederman1-1/+1
Replace kfree_skb with dev_kfree_skb_any in cp_start_xmit as it can be called in both hard irq and other contexts. Signed-off-by: "Eric W. Biederman" <ebiederm@xmission.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2014-03-12be2net: update driver version to 10.2Sathya Perla1-1/+1
Signed-off-by: Sathya Perla <sathya.perla@emulex.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2014-03-12be2net: Fix vlans_added counterVasundhara Volam1-2/+5
When a VLAN is added by user, adapter->vlans_added is incremented. But if the VLAN is already programmed in HW, driver ends up incrementing the counter wrongly. Increment the counter only if VLAN is not already programmed in the HW. Signed-off-by: Vasundhara Volam <vasundhara.volam@emulex.com> Signed-off-by: Sathya Perla <sathya.perla@emulex.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2014-03-12be2net: Create multiple TXQs on RSS capable multi-channel BE3-R interfacesVasundhara Volam1-3/+7
Currently the driver creates only a single TXQ on any BE3-R multi-channel interface. This patch changes this and creates multiple TXQs on RSS-capable multi-channel BE3-R interfaces. This change helps improve the TX pps performance on the affected interface. Signed-off-by: Vasundhara Volam <vasundhara.volam@emulex.com> Signed-off-by: Sathya Perla <sathya.perla@emulex.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2014-03-12be2net: fix pmac_id[] allocation sizeRavikumar Nelavelli1-3/+2
The allocation size must be be_max_uc() and not "be_max_uc() + 1" Signed-off-by: Ravikumar Nelavelli <ravikumar.nelavelli@emulex.com> Signed-off-by: Sathya Perla <sathya.perla@emulex.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2014-03-12be2net: log LPVID used in multi-channel configsRavikumar Nelavelli1-2/+4
Signed-off-by: Ravikumar Nelavelli <ravikumar.nelavelli@emulex.com> Signed-off-by: Sathya Perla <sathya.perla@emulex.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2014-03-12be2net: Add link state control for VFsSuresh Reddy4-5/+88
Add support to control VF's link state by implementing the ndo_set_vf_link_state() hook. Signed-off-by: Suresh Reddy <suresh.reddy@emulex.com> Signed-off-by: Sathya Perla <sathya.perla@emulex.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2014-03-12be2net: Use GET_PROFILE_CONFIG cmd for BE3-R to query max-vfsSuresh Reddy1-8/+11
Use GET_PROFILE_CONFIG_V1 cmd even for BE3-R (it's already used for Lancer-R and Skyhawk-R), to query max-vfs value supported by the FW. This is needed as on some configs, the value exported in the PCI-config space is not accurate. Signed-off-by: Suresh Reddy <suresh.reddy@emulex.com> Signed-off-by: Sathya Perla <sathya.perla@emulex.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2014-03-12Merge branch 'mlx4-next'David S. Miller15-139/+811
Or Gerlitz says: ==================== mlx4: Add SRIOV support for RoCE This series adds SRIOV support for RoCE (RDMA over Ethernet) to the mlx4 driver. The patches are against net-next, as of commit 2d8d40a "pkt_sched: fq: do not hold qdisc lock while allocating memory" changes from V1: - addressed feedback from Dave on patch #3 and changed get_real_sgid_index() to be called fill_in_real_sgid_index() and be a void function. - removed some checkpatch warnings on long lines changes from V0: - always check the return code of mlx4_get_roce_gid_from_slave(). The call we fixed is introduced in patch #1 and later removed by patch #3 that allows guests to have multiple GIDS. The 1..3 separation was done for proper division of patches to logical changes. ==================== Signed-off-by: David S. Miller <davem@davemloft.net>
2014-03-12mlx4: Activate RoCE/SRIOVJack Morgenstein2-15/+0
To activate RoCE/SRIOV, need to remove the following: 1. In mlx4_ib_add, need to remove the error return preventing initialization of a RoCE port under SRIOV. 2. In update_vport_qp_params (in resource_tracker.c) need to remove the error return when a RoCE RC or UD qp is detected. This error return causes the INIT-to-RTR qp transition to fail in the wrapper function under RoCE/SRIOV. Signed-off-by: Jack Morgenstein <jackm@dev.mellanox.co.il> Signed-off-by: Or Gerlitz <ogerlitz@mellanox.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2014-03-12mlx4_ib: Fix SIDR support of for UD QPs under SRIOV/RoCEShani Michaelli1-15/+57
* Handle CM_SIDR_REQ_ATTR_ID and CM_SIDR_REP_ATTR_ID in multiplex_cm_handler and demux_cm_handler. * Handle Service ID Resolution messages and REQ messages separately, for their formats are different. Signed-off-by: Shani Michaeli <shanim@mellanox.com> Signed-off-by: Matan Barak <matanb@mellanox.com> Signed-off-by: Jack Morgenstein <jackm@dev.mellanox.co.il> Signed-off-by: Or Gerlitz <ogerlitz@mellanox.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2014-03-12mlx4: Implement IP based gids support for RoCE/SRIOVJack Morgenstein8-25/+117
Since there is no connection between the MAC/VLAN and the GID when using IP-based addressing, the proxy QP1 (running on the slave) must pass the source-mac, destination-mac, and vlan_id information separately from the GID. Additionally, the Host must pass the remote source-mac and vlan_id back to the slave, This is achieved as follows: Outgoing MADs: 1. Source MAC: obtained from the CQ completion structure (struct ib_wc, smac field). 2. Destination MAC: obtained from the tunnel header 3. vlan_id: obtained from the tunnel header. Incoming MADs 1. The source (i.e., remote) MAC and vlan_id are passed in the tunnel header to the proxy QP1. VST mode support: For outgoing MADs, the vlan_id obtained from the header is discarded, and the vlan_id specified by the Hypervisor is used instead. For incoming MADs, the incoming vlan_id (in the wc) is discarded, and the "invalid" vlan (0xffff) is substituted when forwarding to the slave. Signed-off-by: Moni Shoua <monis@mellanox.co.il> Signed-off-by: Jack Morgenstein <jackm@dev.mellanox.co.il> Signed-off-by: Or Gerlitz <ogerlitz@mellanox.com> Signed-off-by: David S. Miller <davem@davemloft.net>