- 29 Feb, 2016 40 commits
-
-
Jesse Brandeburg authored
BugLink: http://bugs.launchpad.net/bugs/1536474 Somehow an ID that has never been productized is in the code. There are no plans to use it, so just get rid of it. Change-ID: I59117d48ea9ee0360b0fe33833ac8092f8a24b4c Signed-off-by:
Jesse Brandeburg <jesse.brandeburg@intel.com> Tested-by:
Andrew Bowers <andrewx.bowers@intel.com> Signed-off-by:
Jeff Kirsher <jeffrey.t.kirsher@intel.com> (cherry picked from commit 56028154) Signed-off-by:
Tim Gardner <tim.gardner@canonical.com>
-
Anjali Singhai Jain authored
BugLink: http://bugs.launchpad.net/bugs/1536474 If the driver calls skb_set_hash even with a zero hash, that indicates to the stack that the hash calculation is offloaded in hardware. So the Stack doesn't do a SW hash which is required for load balancing if the user decides to turn of rx-hashing on our device. This patch fixes the path so that we do not call skb_set_hash if the feature is disabled. Change-ID: Ic4debfa4ff91b5a72e447348a75768ed7a2d3e1b Signed-off-by:
Anjali Singhai Jain <anjali.singhai@intel.com> Tested-by:
-
Sowmini Varadhan authored
BugLink: http://bugs.launchpad.net/bugs/1536474 This is the i40e equivalent of commit c762dff2 ("ixgbe: Look up MAC address in Open Firmware or IDPROM"). As with that fix, attempt to look up the MAC address in Open Firmware on systems that support it, and use IDPROM on SPARC if no OF address is found. In the case of the i40e there is an assumption that the default mac address has already been set up as the primary mac filter on probe, so if this filter is obtained from the Open Firmware or IDPROM, an explicit write is needed via i40e_aq_mac_address_write() and i40e_aq_add_macvlan() invocation. The I40E_FLAG_PF_MAC flag in the platform-private i40e_pf structure tracks whether a platform-specific mac address was found, in which case calls to i40e_aq_mac_address_write() and i40e_aq_add_macvlan() will be triggered. Reviewed-by:
Martin K. Petersen <martin.petersen@oracle.com> Signed-off-by:
Sowmini Varadhan <sowmini.varadhan@oracle.com> Acked-by:
Shannon Nelson <shannon.nelson@intel.com> Tested-by:
-
Mitch Williams authored
BugLink: http://bugs.launchpad.net/bugs/1536474 Allow the user to specify a zero MAC address for VFs. This removes the existing MAC address and allows the VF to use a random address. Libvirt does this normally when removing a VF from a VM. Signed-off-by:
Mitch Williams <mitch.a.williams@intel.com> Tested-by:
-
Mitch Williams authored
BugLink: http://bugs.launchpad.net/bugs/1536474 When VFs are being reset, there is a brief window of time when they cannot be configured because they don't have a VSI to configure. If a script is quick, it can fall through that window. To avoid defenestration, log a useful error message and return -EAGAIN. Signed-off-by:
-
Singhai, Anjali authored
BugLink: http://bugs.launchpad.net/bugs/1536474 This patch adds a call to geneve_get_rx_port in i40e so that when it comes up it can learn about the existing geneve tunnels. Signed-off-by:
David S. Miller <davem@davemloft.net> (cherry picked from commit cd866606) Signed-off-by:
-
Singhai, Anjali authored
BugLink: http://bugs.launchpad.net/bugs/1536474 This patch adds an op that the drivers can call into to get existing geneve ports. Signed-off-by:
-
Singhai, Anjali authored
BugLink: http://bugs.launchpad.net/bugs/1536474 This patch adds driver hooks to implement ndo_ops to add/del udp port in the HW to identify GENEVE tunnels. Signed-off-by:
Kiran Patil <kiran.patil@intel.com> Signed-off-by:
-
Singhai, Anjali authored
BugLink: http://bugs.launchpad.net/bugs/1536474 Add ndo_ops to add/del UDP ports to a device that supports geneve offload. v2: Comment fix. Signed-off-by:
-
Tom Herbert authored
BugLink: http://bugs.launchpad.net/bugs/1536474 Add support to enable and disable UDP checksums via netlink. This is similar to how VXLAN and GUE allow this. This includes support for enabling the UDP zero checksum (for both TX and RX). Signed-off-by:
Tom Herbert <tom@herbertland.com> Signed-off-by:
-
Catherine Sullivan authored
BugLink: http://bugs.launchpad.net/bugs/1536474 Bump. Change-ID: I2b8976bde070244de144e2ed8990b083de39f332 Signed-off-by:
Catherine Sullivan <catherine.sullivan@intel.com> Tested-by:
-
Mitch Williams authored
BugLink: http://bugs.launchpad.net/bugs/1536474 Generate version strings like the PF driver does. This gives us more flexibility to add suffixes to the version string at build time. Change-ID: I0a5ca0783dd8fb849516bfc1e37ea070127847bd Signed-off-by:
-
Shannon Nelson authored
BugLink: http://bugs.launchpad.net/bugs/1536474 Clean the whole mac filter list when resetting after an intermediate add or delete push to the firmware. The code had evolved from using a list from the stack to a heap allocation, but the memset() didn't follow the change correctly. This now cleans the whole list rather that just part of the first element. Change-ID: I4cd03d5a103b7407dd8556a3a231e800f2d6f2d5 Reported-by:
Rasmus Villemoes <linux@rasmusvillemoes.dk> Signed-off-by:
-
Anjali Singhai Jain authored
BugLink: http://bugs.launchpad.net/bugs/1536474 X722 supports Expanded version of TCP, UDP PCTYPES for RSS. Add a Virtchnl offload to support this. Without this patch with X722 devices, driver will set wrong PCTYPES for VF and UDP flows will not fan out. Change-ID: I04fe4988253b7cd108c9179a643c969764efcb76 Signed-off-by:
-
Mitch Williams authored
BugLink: http://bugs.launchpad.net/bugs/1536474 These messages seem big and scary, but they're really not. The driver can fully recover from any of these. The overflow error in particular can happen when enabling a bunch of VFs and the VF driver is not blacklisted. Since these messages are really for debugging purposes, reclassify them as such. Change-ID: I628d0f5e135e7063450ba05393a50b7af23aa6d7 Signed-off-by:
-
Michal Kosiarz authored
BugLink: http://bugs.launchpad.net/bugs/1536474 This is a part of implementation which contains data structures and opcode for new AQ command. There's a new ARQ message that gets sent near the end of the NVM update process that the driver should recognize and ignore, rather than printing an Unknown Event error. Change-ID: I04830a5bcae14823e16b9424cc4165e169336c1f Signed-off-by:
Michal Kosiarz <michal.kosiarz@intel.com> Acked-by:
-
Kamil Krawczyk authored
BugLink: http://bugs.launchpad.net/bugs/1536474 Current implementation generates compilation warnings. Change-ID: Icceefb50fe62aefaf90a64afb7192e08355a4ec5 Signed-off-by:
Kamil Krawczyk <kamil.krawczyk@intel.com> Acked-by:
-
Mitch Williams authored
BugLink: http://bugs.launchpad.net/bugs/1536474 If the driver gets unloaded during reset recovery, it's possible that it will attempt to free resources when they're already free. Add a check to make sure that the Tx and Rx rings actually exist before dereferencing them to free resources. Change-ID: I4d2b7e9ede49f634d421a4c5deaa5446bc755eee Signed-off-by:
-
Mitch Williams authored
BugLink: http://bugs.launchpad.net/bugs/1536474 When VFs are created, the MAC address defaults to all zeros, indicating to the VF driver that it should use a random MAC address. However, the PF driver was incorrectly adding this zero MAC to the filter table, along with the VF's randomly generated MAC address. Check for a good address before adding the default filter. While we're at it, make the error message a bit more useful. Change-ID: Ia100947d68140e0f73a19ba755cbffc3e79a8fcf Signed-off-by:
-
Mitch Williams authored
BugLink: http://bugs.launchpad.net/bugs/1536474 The virtual channel interface was using incorrect semantics to remove MAC addresses, which would leave incorrect filters active when using VLANs. To correct this, add a new function that unconditionally removes MAC addresses from all VLANs, and call this function when the VF requests a MAC filter removal. Change-ID: I69826908ae4f6c847f5bf9b32f11faa760189c74 Signed-off-by:
-
Jesse Brandeburg authored
BugLink: http://bugs.launchpad.net/bugs/1536474 BIT_ULL was used on a u32 or less where it can simply be BIT. This fixes some trivial static analyzer warnings. Chomp, chomp. Tested with objdump of binary before and after, no changes to code. Change-ID: I6245e9abd447192dbde1669c747aeb2878126c7d Signed-off-by:
-
Singhai, Anjali authored
BugLink: http://bugs.launchpad.net/bugs/1536474 This reverts commit 8fe26999. The case where VXLAN is a module and i40e driver is inbuilt will not be handled properly with this change since i40e will have an undefined symbol vxlan_get_rx_port in it. v2: Add a signed-off-by. Signed-off-by:
-
Joe Perches authored
BugLink: http://bugs.launchpad.net/bugs/1536474 Commit 7fd89545 ("i40e: remove BUG_ON from feature string building") added defective output when I40E_FLAG_VEB_MODE_ENABLED was set in function i40e_print_features. Fix it. Miscellanea: - Remove unnecessary string variable - Add space before not after fixed strings - Use kmalloc not kzalloc - Don't initialize i to 0, use result of first snprintf Reported-by:
Sergei Shtylyov <sergei.shtylyov@cogentembedded.com> Signed-off-by:
Joe Perches <joe@perches.com> Signed-off-by:
-
Jesse Brandeburg authored
BugLink: http://bugs.launchpad.net/bugs/1536474 1) remove duplicate include of tcp.h 2) put an ampersand at the end of a line instead of the beginning 3) remove a useless dev_info 4) match declaration of function to the implementation 5) repair incorrect comment 6) correct whitespace 7) remove unused define Signed-off-by:
-
Catherine Sullivan authored
BugLink: http://bugs.launchpad.net/bugs/1536474 Bump. Change-ID: Id8c83c64c973349a722bab40d285ad8ded8c28f7 Signed-off-by:
-
Mitch Williams authored
BugLink: http://bugs.launchpad.net/bugs/1536474 We shouldn't be using a bitwise operator here; it's not a bitwise operation. Use a logical operator instead. Why doesn't c have a logical-or-and-assign operator? Change-ID: Id84f3ca884910bed7073c84b1e16a102e958d0de Signed-off-by:
-
Mitch Williams authored
BugLink: http://bugs.launchpad.net/bugs/1536474 Operators should have spaces around them. Change-ID: I64735e9aa8618b9a5059a87ace1c999d6d3bfcfb Signed-off-by:
-
Neerav Parikh authored
BugLink: http://bugs.launchpad.net/bugs/1536474 The separate functions to gather Flow control Rx XOFF stats was to determine if the Tx for a queue was paused due to Link Flow Control(LFC) or Priority Flow Control(PFC). But, with recent change in the i40e driver the logic for checking th Tx hang has been removed and these functions don't do anything meaningful. Hence, there is no need to keep these separate functions to gather Rx XOFF stats for LFC or PFC. This patch removes these functions and moves the stat collection for XOFF Rx to the i40e_update_pf_stats() that collects all the PF stats. Change-ID: Iec1452dac3a6766f0d968e754cb407530d7c60cd Signed-off-by:
Neerav Parikh <neerav.parikh@intel.com> Tested-by:
-
Jesse Brandeburg authored
BugLink: http://bugs.launchpad.net/bugs/1536474 Instead of having our own custom symbol, we can just rely on whether or not the kernel has the feature enabled. In this case use IS_ENABLED(CONFIG_VXLAN) in order to handle built-in or module in the current BKM way. Change-ID: I5890fbb518ff8ed6bb07c3362fb0a8a829f9b241 Signed-off-by:
-
Jesse Brandeburg authored
BugLink: http://bugs.launchpad.net/bugs/1536474 Ethtool priv flags implementation to enable or disable packet split, which is a hardware feature that inspects headers and will put headers in a separate DMA buffer from the payload data. The driver was automatically choosing to enable packet split in some cases and this gives the user the ability to turn it off/on explicitly. to query state: ethtool --show-priv-flags ethx to enable: ethtool --set-priv-flags ethx packet-split on to disable: ethtool --set-priv-flags ethx packet-split off Why would anyone want this? Because some environments benefit from header/data split in the receive buffer, and the driver defaults to one or the other depending on environment/kernel parameters. Why didn't you implement a generic ethtool control for this feature? Because Intel hardware is the only hardware that supports header/data split. Change-ID: I803121e1eecc9ccb2884031fd85dd1110b3af66d Signed-off-by:
-
Mitch Williams authored
BugLink: http://bugs.launchpad.net/bugs/1536474 Don't use uint32_t type the kernel. Use u32 instead. No functional change. Change-ID: I77bbf3b6464edaef747c7104b43534032a4dba63 Signed-off-by:
-
Mitch Williams authored
BugLink: http://bugs.launchpad.net/bugs/1536474 i40e_sync_vsi_filters() is the surly teenager of this driver. It says it's going to report errors, but it doesn't actually do that most of the time. And when it does, it leaves a mess. Change this function to have a common exit point so it will properly release the busy lock on the VSI. Propagate errors to the callers. Finally, adjust a few callers to check for and deal with errors from this function. Change-ID: Ic6af4956491e72402ebb3c538a3c31a0ad7f8667 Signed-off-by:
-
Mitch Williams authored
BugLink: http://bugs.launchpad.net/bugs/1536474 These allocations don't need to be at atomic level. GFP_KERNEL is fine and they'll reduce stress on the allocator when the system is starved for memory. Change-ID: I3561d0399a681de0ad25291b6c848b224c1fde12 Signed-off-by:
-
Kiran Patil authored
BugLink: http://bugs.launchpad.net/bugs/1536474 This patch fixes the memory leak which would be seen otherwise when user programs flow-director filter using ethtool (sideband filter programming). When ethtool is used to program flow directory filter, 'raw_buf' gets allocated and it is supposed to be freed as part of queue cleanup. But check of 'tx_buffer->skb' was preventing it from being freed. Change-ID: Ief4f0a1a32a653180498bf6e987c1b4342ab8923 Signed-off-by:
-
Kiran Patil authored
BugLink: http://bugs.launchpad.net/bugs/1536474 This patch contains following changes: - detection and recovery logic (issue SW interrupt) has been moved to service_task from timeout function. - added some more debug info from tx_timeout. Logic to detect and recover TX queue hung is now two step process: - service_task detects TX queue hung and sets a bit(hung_detected) if it was not set. - if bit was set (means this is back-back hung condition detected), issue SW interrupt and clear the bit. - napi_poll clears the bit unconditionally since it cleans TX/RX queues. Change-ID: Ieed03a48927c845a988b3ff375090bf37caeb903 Signed-off-by:
-
Mitch Williams authored
BugLink: http://bugs.launchpad.net/bugs/1536474 We already print the driver info string in probe, so don't print it again in init. No need to repeat. No need to repeat. Change-ID: Ief597997f580a8c54d5950e3a84c29f2075be66b Signed-off-by:
-
Mitch Williams authored
BugLink: http://bugs.launchpad.net/bugs/1536474 Use the helper function to set the real number of RX queues, and also set the real number of TX queues. Change-ID: I67982799de3f248fb4158ccdc9b1a74385f42ddd Signed-off-by:
-
Mitch Williams authored
BugLink: http://bugs.launchpad.net/bugs/1536474 Future devices will allow for more queue pairs, so allocate a netdev that can handle them. While we're at it, get rid of the separate MAX_TX/MAX_RX defines. Since we always get matched queue pairs, having these makes no sense. Change-ID: I0e3556cd9a962506e509eb7c0afa36b329e8cb51 Signed-off-by:
-
Jesse Brandeburg authored
BugLink: http://bugs.launchpad.net/bugs/1536474 With the final edition of the patches to remove sleeps from the driver's entry points, the grab_rtnl argument is no longer needed, so partially revert the commit that added it. Change-ID: Ib9778476242586cc9e58b670f5f48d415cb59003 Signed-off-by:
-
Jesse Brandeburg authored
BugLink: http://bugs.launchpad.net/bugs/1536474 The driver was being called by VLAN, bonding, teaming operations that expected to be able to hold locks like rcu_read_lock(). This causes the driver to be held to the requirement to not sleep, and was found by the kernel debug options for checking sleep inside critical section, and the locking validator. Change-ID: Ibc68c835f5ffa8ffe0638ffe910a66fc5649a7f7 Signed-off-by:
-
