- 03 Apr, 2015 7 commits
-
-
Mitch Williams authored
The call to pci_disable_sriov got moved, but the message about not disabling VFs didn't move. So move it. While we're at, reword the message a bit to make it more consistent with other driver messages. Change-ID: I17d3e15e4fcfd5c9431a96ecb0117d728d3da18b Signed-off-by:
Mitch Williams <mitch.a.williams@intel.com> Tested-by:
Jim Young <james.m.young@intel.com> Signed-off-by:
Jeff Kirsher <jeffrey.t.kirsher@intel.com>
-
Jesse Brandeburg authored
A function was calling i40e_tx_map with return, but tx_map returns void, and the caller returns void, so just drop the return, and everything is good. Change-ID: I53fc676d517864761e7cbb8ca83f1ef0c15b1f8f Signed-off-by:
Jesse Brandeburg <jesse.brandeburg@intel.com> Tested-by:
-
Jesse Brandeburg authored
If the skb allocation fails we should not continue using the skb pointer. Breaking out at the point of failure means that at the next RX interrupt the driver will try the allocation again. Change-ID: Iefaad69856ced7418bfd92afe55322676341f82e Signed-off-by:
-
Jesse Brandeburg authored
Several memcpys are not necessary and can be changed to structure assignments. Struct assignments are always type safe so this is preferable. Change-ID: I7daf45a4b5e799c686b9d5c8ba9db047584ab82b Signed-off-by:
-
Anjali Singhai Jain authored
HMC_ERRORINFO and HMC_ERRORDATA helps explain the cause of HMC error. Change-ID: I053bbc175a5f4c5c3e9ec2ea7400d5c56aaa4ec1 Signed-off-by:
Anjali Singhai Jain <anjali.singhai@intel.com> Tested-by:
-
Mitch Williams authored
Validate that the VF has sent us a valid VSI index before actually using that index. Without this code, a malicious or buggy VF driver could panic the host by sending an invalid index into the VSI array. Change-ID: I66a177687a0dcc281ec83e714d3813d70d18c8b4 Reported-by:
Nick Nunley <nicholas.d.nunley@intel.com> Signed-off-by:
-
Anjali Singhai Jain authored
Inner protocol being UDP should not stop us from verifying Outer UDP checksum correctness. If the Outer protocol is not UDP (NVGRE) we should not be doing a UDP checksum check. If the packet has zero checksum, skip checksum check. Change-ID: Ie7f153feb276a59f66a54a0938901b2c0a8100fa Signed-off-by:
-
- 02 Apr, 2015 33 commits
-
-
David S. Miller authored
Eli Cohen says: ==================== mlx5 batch of patches for net-next This series contains small fixes to the mlx5 core driver and also preparation steps towards adding Ethernet support for ConnectX4 devices which will be part of mlx5 driver. ==================== Signed-off-by:David S. Miller <davem@davemloft.net>
-
Saeed Mahameed authored
Preparation for ethernet driver. Signed-off-by:
Achiad Shochat <achiad@mellanox.com> Signed-off-by:
Saeed Mahameed <saeedm@mellanox.com> Signed-off-by:
Eli Cohen <eli@mellanox.com> Signed-off-by:
-
Saeed Mahameed authored
Pass consumer index as a parameter to arm CQ Signed-off-by:
-
Saeed Mahameed authored
Preparation for ethernet driver. These functions will be used in drivers other than mlx5_ib. Signed-off-by:
-
Achiad Shochat authored
Declare the support of new ConnectX4 HCA in module info Pump up the module version Signed-off-by:
-
Saeed Mahameed authored
Signed-off-by:
-
Saeed Mahameed authored
Signed-off-by:
-
Achiad Shochat authored
In alloc_token(), the token '1' would be allocated twice consecutively. Signed-off-by:
-
Ira Gusinsky authored
Avoid usage of command work entry in cmd_work_handler since it can be released by mlx5_cmd_invoke before the work handler returns to running. Signed-off-by:
Ira Gusinsky <irenag@mellanox.com> Signed-off-by:
-
Eli Cohen authored
Avoid copying to the output buffer in cmd_exec since this is done after the command is completed. Failure to do this may cause cases where the callback handler is called before the copy done by cmd_exec which then overwrites it. Reported-by:
Tamer Hleihel <tamerh@mellanox.com> Signed-off-by:
-
Eli Cohen authored
Use coherent memory for the commands descriptor page. Take measures to make sure the page is aligned to MLX5_ADAPTER_PAGE_SIZE as required by the hardware. Reported-by:
Yevgeny Kliteynik <kliteyn@mellanox.com> Signed-off-by:
-
Achiad Shochat authored
struct mlx5_query_mkey_mbox_in rather than mlx5_destroy_mkey_mbox_in Signed-off-by:
-
Saeed Mahameed authored
Do it in one place instead of every where the function is invoked Signed-off-by:
-
Eli Cohen authored
PRM does not support setting these values so avoid setting them. Signed-off-by:
-
Eli Cohen authored
Put a line of space before return and next statement. Signed-off-by:
-
Haggai Abramonvsky authored
Pass 0 in the sqd_event parameter. Signed-off-by:
Haggai Abramovsky <hagaya@mellanox.com> Signed-off-by:
-
Eli Cohen authored
Allocate firmware pages from the NUMA node which is close to the device. Signed-off-by:
-
David S. Miller authored
Jon Maloy says: ==================== tipc: remove some unnecessary complexity The TIPC code is unnecessarily complex in some places, often because the conditions or assumptions that were the cause for the complexity are not valid anymore. In these three commits, we eliminate some cases of such redundant complexity. ==================== Signed-off-by: -
Jon Paul Maloy authored
When a link is being established, the two endpoints advertise their respective interface MTU in the transmitted RESET and ACTIVATE messages. If there is any difference, the lower of the two MTUs will be selected for use by both endpoints. However, as a remnant of earlier attempts to introduce TIPC level routing. there also exists an MTU discovery mechanism. If an intermediate node has a lower MTU than the two endpoints, they will discover this through a bisectional approach, and finally adopt this MTU for common use. Since there is no TIPC level routing, and probably never will be, this mechanism doesn't make any sense, and only serves to make the link level protocol unecessarily complex. In this commit, we eliminate the MTU discovery algorithm,and fall back to the simple MTU advertising approach. This change is fully backwards compatible. Reviewed-by:
Ying Xue <ying.xue@windriver.com> Signed-off-by:
Jon Maloy <jon.maloy@ericsson.com> Signed-off-by:
-
Jon Paul Maloy authored
When a bearer is disabled manually, all its links have to be reset and deleted. However, if there is a remaining, parallel link ready to take over a deleted link's traffic, we currently delay the delete of the removed link until the failover procedure is finished. This is because the remaining link needs to access state from the reset link, such as the last received packet number, and any partially reassembled buffer, in order to perform a successful failover. In this commit, we do instead move the state data over to the new link, so that it can fulfill the procedure autonomously, without accessing any data on the old link. This means that we can now proceed and delete all pertaining links immediately when a bearer is disabled. This saves us from some unnecessary complexity in such situations. We also choose to change the confusing definitions CHANGEOVER_PROTOCOL, ORIGINAL_MSG and DUPLICATE_MSG to the more descriptive TUNNEL_PROTOCOL, FAILOVER_MSG and SYNCH_MSG respectively. Reviewed-by:
-
Jon Paul Maloy authored
In commit 8b4ed863 ("tipc: eliminate race condition at dual link establishment") we introduced a parallel link synchronization mechanism that guarentees sequential delivery even for users switching from an old to a newly established link. The new mechanism makes it unnecessary to deliver the tunneled duplicate packets back to the old link, as we are currently doing. It is now sufficient to use the last tunneled packet's inner sequence number as synchronization point between the two parallel links, whereafter it can be dropped. In this commit, we drop the duplicate packets arriving on the new link, after updating the synchronization point at each new arrival. Although it would now have been sufficient for the other endpoint to only tunnel the last packet in its send queue, and not the entire queue, we must still do this to maintain compatibility with older nodes. This commit makes it possible to get rid if some complex interaction between the two parallel links. Reviewed-by:
-
David S. Miller authored
Or Gerlitz says: ==================== Mellanox mlx4 driver updates The main feature added by this series are Ido's changes to support Granular QoS for VFs, where for the time being only max rate is supported. Muhammad added support for setting rx-fcs and rx-all through ethtool, and Ido did the interface identify work. Last, add Ido as a maintainer for the mlx4 Ethernet driver! Some of next week is the Passover holiday here and I will be mostly OOO. If needed (...) Ido or Amir will send V1 and such. Rebased against net-next commit 033f46b3 "crypto: algif - explicitly mark end of data". ==================== Signed-off-by:
-
Or Gerlitz authored
Add Ido Shamay as co-maintainer for the mlx4 Ethernet driver. Signed-off-by:
Amir Vadai <amirv@mellanox.com> Signed-off-by:
Or Gerlitz <ogerlitz@mellanox.com> Signed-off-by:
-
Muhammad Mahajna authored
Enabled when the device supports KEEP FCS and IGNORE FCS. When the flag is set, pass all received frames up the stack, even ones with invalid FCS, controlled by ethtool. Signed-off-by:
Muhammad Mahajna <muhammadm@mellanox.com> Signed-off-by:
Ido Shamay <idos@mellanox.com> Signed-off-by:
-
Muhammad Mahajna authored
Enabled when device supports KEEP FCS. When the flag is set, Ethernet FCS is appended to the end of the frame, controlled by ethtool. Signed-off-by:
-
Ido Shamay authored
Add support for the interface ethtool identify feature. Make the physical port LED to blink with green and yellow colors. The device handles the LED blink by itself (synchrous use of set_phys_id), by returning 0 to ETHTOOL_ID_ACTIVE command. Signed-off-by:
Eyal Grossman <eyalgr@mellanox.com> Signed-off-by:
-
Ido Shamay authored
The calls to SET_PORT used hard-code numbers, when supplying command's opcode modifiers, fix that to use well defined constants. Signed-off-by:
-
Ido Shamay authored
If HCA supports ETS QoS feature, set enhanced QoS bit in init_hca as default. Signed-off-by:
-
Ido Shamay authored
A new capability bit was introduced in the past to to differ devices using the QoS ETS feature. The old was deprecated since then. If driver sees device which set only the old capabilty, it will print warning to user suggesting to upgrade the FW. Signed-off-by:
-
Ido Shamay authored
Support granular QoS per VF, by implementing the ndo_set_vf_rate. Enforce a rate limit per VF when called, and enabled only for VFs in VST mode with user priority supported by the device. We don't enforce VFs to be in VST mode at the moment of configuration, but rather save the given rate limit and enforce it when the VF is moved to VST with user priority which is supported (currently 0). VST<->VGT or VST qos value state changes are disallowed when a rate limit is configured. Minimum BW share is not supported yet. Signed-off-by:
-
Ido Shamay authored
Granular QoS per VF feature introduce a new QP field, qos_vport. PF administrator can connect VF QPs to a certain QoS Vport, to inherit its proporties. Connecting QPs to the default QoS Vport (defined as 0) is always allowed, even when there are no allocated VPPs. At this point, only the default vport is connected to QPs. Signed-off-by:
-
Ido Shamay authored
Initialization of granular Qos per VF mechanism. Query the port availible VPPs and allocates those on all supported priorities in an equal share. Allocation is done only in SRIOV mode, when the feature is supported by the device and port type is Ethernet. Allocation currently is done only on the default priority 0. Signed-off-by:
-
Ido Shamay authored
Checks in QUERY_DEV_CAP if the granular QoS per VF feature is supported by the device. Disabled for guests. Signed-off-by:
-
