- 29 Feb, 2016 40 commits
-
-
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:
Kiran Patil <kiran.patil@intel.com> Tested-by:
Andrew Bowers <andrewx.bowers@intel.com> Signed-off-by:
Jeff Kirsher <jeffrey.t.kirsher@intel.com> (cherry picked from commit 9c6c1259) Signed-off-by:
Tim Gardner <tim.gardner@canonical.com>
-
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 <mitch.a.williams@intel.com> Tested-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 <jesse.brandeburg@intel.com> Tested-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:
-
Catherine Sullivan authored
BugLink: http://bugs.launchpad.net/bugs/1536474 Bump. Change-ID: I00ebbb2e5e5572f947502b8f6db4d94f666d6b14 Signed-off-by:
Catherine Sullivan <catherine.sullivan@intel.com> Tested-by:
-
Mitch Williams authored
BugLink: http://bugs.launchpad.net/bugs/1536474 Instead of awkwardly keeping a fixed array of pointers in the adapter struct and then allocating ring structs individually, just keep a single pointer and allocate a single blob for the arrays. This simplifies code, shrinks the adapter structure, and future-proofs the driver by not limiting the number of rings we can handle. Change-ID: I31334ff911a6474954232cfe4bc98ccca3c769ff Signed-off-by:
-
Mitch Williams authored
BugLink: http://bugs.launchpad.net/bugs/1536474 Change the queue_vector array from a statically-sized member of the adapter structure to a dynamically-allocated and -sized array. This reduces the size of the adapter structure, and allows us to support any number of queue vectors in the future without changing the code. Change-ID: I08dc622cb2f2ad01e832e51c1ad9b86524730693 Signed-off-by:
-
Mitch Williams authored
BugLink: http://bugs.launchpad.net/bugs/1536474 If, upon a midnight dreary, the PF returns ERR_PARAM when the VF is requesting resources, that's fatal. Either the firmware or NVM is badly, badly misconfigured, or this VF has been disabled due to a previous VF driver sending a bunch of bogus messages. Either way, there is no recovery from this. Don't ponder weak and weary, just quit. Change-ID: I09d9f16cc4ee7fec3b57646a289d33838c1c5bf5 Signed-off-by:
-
Mitch Williams authored
BugLink: http://bugs.launchpad.net/bugs/1536474 If we get an invalid message from a VF, we should tell the user which VF is being naughty, rather than making them guess. Change-ID: I9252cef7baea3d8584043ed6ff12619a94e2f99c Signed-off-by:
-
Helin Zhang authored
BugLink: http://bugs.launchpad.net/bugs/1536474 This patch fixes the confusing kernel message of enabled RSS size, by reporting it together with the hardware maximum RSS size. Change-ID: I64864dbfbc13beccc180a7871680def1f3d5a339 Signed-off-by:
Helin Zhang <helin.zhang@intel.com> Tested-by:
-
Carolyn Wyborny authored
BugLink: http://bugs.launchpad.net/bugs/1536474 This patch fixes an issue where adminq init failures always provided a message that NVM was newer than expected. This is not always the case for init_adminq failures. Without this patch, if adminq init fails for any reason, newer NVM message would be given. This problem is fixed by adding a check for that specific error condition and a different hopefully helpful message otherwise. Change-ID: Iaeaebee4e398989eae40bb70f943ab66a3a521a5 Signed-off-by:
Carolyn Wyborny <carolyn.wyborny@intel.com> Tested-by:
-
Helin Zhang authored
BugLink: http://bugs.launchpad.net/bugs/1536474 This patch adds new fields to i40e_vsi to store user configured RSS config data and code to use it. Change-ID: Ic5d3db8d9df52182b560248f8cdca9c5c7546879 Signed-off-by:
-
Helin Zhang authored
BugLink: http://bugs.launchpad.net/bugs/1536474 There are two ways to get RSS, this patch implements two functions with the same input parameters, and creates a more generic function for getting RSS configuration. Change-ID: I12d3b712c21455d47dd0a5aae58fc9b7c680db59 Signed-off-by:
-
Helin Zhang authored
BugLink: http://bugs.launchpad.net/bugs/1536474 There are two ways to configure RSS, this patch adjusts those two functions with the same input parameters, and creates a more generic function for configuring RSS. Change-ID: Iace73bdeba4831909979bef221011060ab327f71 Signed-off-by:
-
Helin Zhang authored
BugLink: http://bugs.launchpad.net/bugs/1536474 This patch renames old VF adapter specific RSS function to clarify its scope. Change-ID: Ie5253083a44c677ebb7709a8a3a18402ad2dc6a6 Signed-off-by:
-
Jesse Brandeburg authored
BugLink: http://bugs.launchpad.net/bugs/1536474 Issue a prefetch for data early in the transmit path. This should not be generally needed for Tx traffic, but it helps immensely for pktgen workloads and should help for forwarding workloads as well. Change-ID: Iefee870c20599e0c4240e1d8637e4f16b625f83a Signed-off-by:
-
Anjali Singhai Jain authored
BugLink: http://bugs.launchpad.net/bugs/1536474 This patch fixes the issue of forcing WB too often causing us to not benefit from NAPI. Without this patch we were forcing WB/arming interrupt too often taking away the benefits of NAPI and causing a performance impact. With this patch we disable force WB in the clean routine for X710 and XL710 adapters. X722 adapters do not enable interrupt to force a WB and benefit from WB_ON_ITR and hence force WB is left enabled for those adapters. For XL710 and X710 adapters if we have less than 4 packets pending a software Interrupt triggered from service task will force a WB. This patch also changes the conditions for setting RS bit as described in code comments. This optimizes when the HW does a tail bump amd when it does a WB. It also optimizes when we do a wmb. Change-ID: Id831e1ae7d3e2ec3f52cd0917b41ce1d22d75d9d Signed-off-by:
Anjali Singhai Jain <anjali.singhai@intel.com> Tested-by:
-
Helin Zhang authored
BugLink: http://bugs.launchpad.net/bugs/1536474 This patch renames rss_size to alloc_rss_size in i40e_pf, which is clearer and avoids confusion. It also adds comments to the other related structure members to help clarify usage. Change-ID: Ia90090609d006ab589cb639975bb8a0af795d16f Signed-off-by:
-
Helin Zhang authored
BugLink: http://bugs.launchpad.net/bugs/1536474 This patch adds new fields to i40e_vsi to store user configured RSS config data and code to use it. Signed-off-by:
-
Catherine Sullivan authored
BugLink: http://bugs.launchpad.net/bugs/1536474 Bump. Change-ID: I2d1ce93b2ce74e4eef2394c932aef52cba99713f Signed-off-by:
-
Helin Zhang authored
BugLink: http://bugs.launchpad.net/bugs/1536474 This patch renames the old pf-specific function in order to clarify its scope. This patch also creates a more generic configure RSS function with the old name. This patch also creates a new more generic function to get RSS configuration, using the appropriate method. Change-ID: Ieddca2707b708ef19f1ebccdfd03a0a0cd63d3af Signed-off-by:
-
Helin Zhang authored
BugLink: http://bugs.launchpad.net/bugs/1536474 Adjust the RSS configure functions so that there is a generic way to hook to ethtool hooks. Change-ID: If446e34fcfaf1bc3320d9d319829a095b5976e67 Signed-off-by:
-
Helin Zhang authored
BugLink: http://bugs.launchpad.net/bugs/1536474 This patch fixes a problem where using ethtool rxnfc command could let RX flow hash be set on disabled queues. This patch fixes the problem by returning the number of enabled queues before setting rxnfc. Change-ID: Idbac86b0b47ddacc8deee7cd257e41de01cbe5c0 Signed-off-by:
-
Mitch Williams authored
BugLink: http://bugs.launchpad.net/bugs/1536474 When a lot (many hundreds) of MAC or VLAN filters are added at one time, we can overflow the Admin Queue buffer size with all the requests. Unfortunately, the driver would then calculate the message size incorrectly, causing it to be rejected by the PF. Furthermore, there was no mechanism to trigger another request to allow for configuring the rest of the filters that didn't fit into the first request. To fix this, recalculate the correct buffer size when we detect the overflow condition instead of just assuming the max buffer size. Also, don't clear the request bit in adapter->aq_required when we have an overflow, so that the rest of the filters can be processed later. Change-ID: Idd7cbbc5af31315e0dcb1b10e6a02ad9817ce65c Signed-off-by:
-
Mitch Williams authored
BugLink: http://bugs.launchpad.net/bugs/1536474 Clean up and enhance error messages related to VF MAC/VLAN filters. Indicate which VF is having issues, and if possible indicate the MAC address or VLAN involved. Also, when an error is returned from the PF driver, print useful information about what went wrong, for the most likely cases. Change-ID: Ib3d15eef9e3369a78fd142948671e5fa26d921b8 Signed-off-by:
-
Helin Zhang authored
BugLink: http://bugs.launchpad.net/bugs/1536474 Add a comment to the #endif to more easily match it with its #if. Change-ID: I47eb0a60a17dc6d2f01a930e45006d2dc82e044f Signed-off-by:
-
Catherine Sullivan authored
BugLink: http://bugs.launchpad.net/bugs/1536474 The watchdog only calls link_event not handle_link_event which means that we need to save the old information in link_event. Previously when polling we were comparing current data to the old data saved the last time we actually received a link event. This means that the polling would only fix link status changes in one direction depending on what the last old data saved off was. Change-ID: Ie590f30fdbcb133d0ddad4e07e3eb1aad58255b3 Signed-off-by:
-
Anjali Singhai Jain authored
BugLink: http://bugs.launchpad.net/bugs/1536474 When in NAPI with interrupts disabled, the HW needs to be forced to do a write back on TX if the number of descriptors pending are less than a cache line. This stat helps keep track of how many times we get into this situation. Change-ID: I76c1bcc7ebccd6bffcc5aa33bfe05f2fa1c9a984 Signed-off-by:
-
Anjali Singhai Jain authored
BugLink: http://bugs.launchpad.net/bugs/1536474 HW/NVM sets a limit of no less than 256 bytes for MSS. Stack can send as low as 76 bytes MSS. This patch lowers the HW limit to 64 bytes to avoid MDDs from firing and causing a reset when the MSS is lower than 256. Change-ID: I36b500a6bb227d283c3e321a7718e0672b11fab0 Signed-off-by:
-
Shannon Nelson authored
BugLink: http://bugs.launchpad.net/bugs/1536474 There's no need to kill the kernel thread here. If this condition was true, the probe() would have died long before we got here. In any case, we'll get the same result when this code tries to use the VSI pointer being checked. Prompted by a recent Linus diatribe. Change-ID: I62f531cac34d4fc28ff9657d5b2d9523ae5e33a4 Signed-off-by:
Shannon Nelson <shannon.nelson@intel.com> Tested-by:
-
Shannon Nelson authored
BugLink: http://bugs.launchpad.net/bugs/1536474 There's really no reason to kill the kernel thread just because of a little info string. This reworks the code to use snprintf's limiting to assure that the string is never too long, and WARN_ON to still put out a warning that we might want to look at the feature list length. Prompted by a recent Linus diatribe. Change-ID: If52ba5ca1c2344d8bf454a31bbb805eb5d2c5802 Signed-off-by:
-
Shannon Nelson authored
BugLink: http://bugs.launchpad.net/bugs/1536474 There's no need to kill the thread and eventually the kernel in this case. In fact, the remainder of the code won't hurt anything anyway, so just complain that we're here and move along. Prompted by a recent Linus diatribe. Change-ID: Iec020d8bcfedffc1cd2553cc6905fd915bb3e670 Signed-off-by:
-
Shannon Nelson authored
BugLink: http://bugs.launchpad.net/bugs/1536474 Code was moved into a separate function some time ago. Change-ID: Icabbe71ce05cf5d716d3e1152cdd9cd41d11bcb5 Signed-off-by:
-
Rasmus Villemoes authored
BugLink: http://bugs.launchpad.net/bugs/1536474 This code is pretty confused. The variable name 'bytes_not_copied' clearly indicates that the programmer knew the semantics of copy_{to,from}_user, but then the return value is checked for being negative and used as a -Exxx return value. I'm not sure this is the proper fix, but at least we get rid of the dead code which pretended to check for access faults. Signed-off-by:
Rasmus Villemoes <linux@rasmusvillemoes.dk> Acked-by:
-
Jesse Brandeburg authored
BugLink: http://bugs.launchpad.net/bugs/1536474 Compiler complained of an unused variable, which the driver was just using to store the result of a rd32 which is used to clear a register unconditionally. Just drop the unused variable and re-use one. Signed-off-by:
-
Tim Gardner authored
Signed-off-by: -
Tim Gardner authored
BugLink: http://bugs.launchpad.net/bugs/1536719Signed-off-by:
-
Colin Ian King authored
UBUNTU: SAUCE: ACPI / tables: Add acpi_force_32bit_fadt_addr option to force 32 bit FADT addresses (LP: #1529381) BugLink: https://bugs.launchpad.net/bugs/1529381 Some HP laptops seem to have invalid 64 bit FADT X_PM* addresses which are causing various boot issues. In these cases, it would be useful to force ACPI to use the valid legacy 32 bit equivalent PM addresses. Add a acpi_force_32bit_fadt_addr to set the ACPICA acpi_gbl_use32_bit_fadt_addresses to TRUE to force this override. Signed-off-by:
Colin Ian King <colin.king@canonical.com> Signed-off-by:
-
