Page MenuHomeFreeBSD

krzysztof.galazka_intel.com (Krzysztof Galazka)
User

Projects

User Details

User Since
Jan 4 2016, 7:08 PM (485 w, 2 d)

Recent Activity

Tue, Mar 25

krzysztof.galazka_intel.com updated the diff for D49484: pci: Save MSIX ctrl value before pci_mask_msix call.

Implement feedback from jhb.

Tue, Mar 25, 5:48 PM

Mar 24 2025

krzysztof.galazka_intel.com requested review of D49484: pci: Save MSIX ctrl value before pci_mask_msix call.
Mar 24 2025, 9:51 AM

Mar 14 2025

krzysztof.galazka_intel.com added inline comments to D48498: ice(4): Add host SR-IOV support.
Mar 14 2025, 4:00 PM
krzysztof.galazka_intel.com updated the diff for D48498: ice(4): Add host SR-IOV support.

Update with recent changes from Github PR: https://github.com/freebsd/freebsd-src/pull/1573

Mar 14 2025, 3:57 PM

Mar 7 2025

krzysztof.galazka_intel.com accepted D49251: dev: Use recently added improvements to PME# support to simplify drivers.

Looks good to me. Unfortunately I don't have any EM HW to test it.

Mar 7 2025, 8:09 PM
krzysztof.galazka_intel.com accepted D49250: pci: Add helper routines to manage PME in device drivers.

LGTM

Mar 7 2025, 7:42 PM

Feb 10 2025

krzysztof.galazka_intel.com accepted D48889: pci: Cosmetic cleanups to MSI/MSI-X routines.

The one thing I think drivers would like to do is allocate additional MSI-X IRQs on the fly

Feb 10 2025, 3:56 PM

Feb 7 2025

krzysztof.galazka_intel.com added inline comments to D48889: pci: Cosmetic cleanups to MSI/MSI-X routines.
Feb 7 2025, 8:36 PM
krzysztof.galazka_intel.com accepted D48890: pci: Don't cache the count of MSI/MSI-X messages before allocation.

Ah, that makes sense. Thanks a lot for clarification!

Feb 7 2025, 7:54 PM
krzysztof.galazka_intel.com added inline comments to D48890: pci: Don't cache the count of MSI/MSI-X messages before allocation.
Feb 7 2025, 6:20 PM
krzysztof.galazka_intel.com added a comment to D48812: ppt: Fix panic when configuring unavailable MSI-X vector.
In D48812#1114102, @jhb wrote:

I'm worried that this might have other side effects for things like EA caps. However, I think it's also true that caching the MSI counts is probably wrong in general. It's not just VFs, in theory writing to some other register in a PF can change the value of the MSI control registers and we should just always read them.

Feb 7 2025, 11:29 AM

Feb 4 2025

krzysztof.galazka_intel.com added a comment to D48812: ppt: Fix panic when configuring unavailable MSI-X vector.
In D48812#1113788, @jhb wrote:

I believe pci_msix_count() is returning a cached value from when the VF was first created in pci_read_cap() called from pci_fill_devinfo() called from pci_add_iov_child() called from PCI_CREATE_IOV_CHILD. If the MSI-X count is then adjusted by the driver in the PCI_IOV_ADD_VF callback, the cached value will be wrong.

Feb 4 2025, 5:49 PM

Feb 3 2025

krzysztof.galazka_intel.com added a comment to D48812: ppt: Fix panic when configuring unavailable MSI-X vector.

I'm not sure why pci_msix_count returns incorrect number. pciconf output looks fine:

Feb 3 2025, 2:31 PM
krzysztof.galazka_intel.com requested review of D48812: ppt: Fix panic when configuring unavailable MSI-X vector.
Feb 3 2025, 2:28 PM

Jan 29 2025

krzysztof.galazka_intel.com added a comment to D47709: ice(4): allow to turn off/on tx lldp filter.

TX filter for LLDP frames is added to prevent i.e. VFs from messing up with DCB config. My colleagues suggest using an override in TX path like it's done in the Linux driver: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/tree/drivers/net/ethernet/intel/ice/ice_txrx.c?h=v6.13#n2360 instead of removing this filter. I'm still digging in the docs to better understand if this is the only option when SR-IOV is in use. Could you please wait until ice(4): Add host SR-IOV support is ready?

Jan 29 2025, 10:14 PM

Jan 28 2025

krzysztof.galazka_intel.com accepted D48446: iflib: Simplify CACHE_PTR_NEXT.

LGTM

Jan 28 2025, 5:47 PM

Jan 17 2025

krzysztof.galazka_intel.com added a comment to D48498: ice(4): Add host SR-IOV support.

We're trying a different approach to make the work more transparent and enable receiving feedback earlier during development. This patch will be updated with bug fixes and missing features. There is also a pull request on Github if you'd like to see commits history: https://github.com/freebsd/freebsd-src/pull/1573

Jan 17 2025, 2:17 PM
krzysztof.galazka_intel.com requested review of D48498: ice(4): Add host SR-IOV support.
Jan 17 2025, 2:07 PM

Jan 3 2025

krzysztof.galazka_intel.com updated subscribers of D48054: IfAPI: hide struct ifaddr from if_foreach_addr_type() callbacks.

LGTM but let me ask @bartosz.sobczak_intel.com to take a look at irdma changes.

Jan 3 2025, 2:08 PM

Jan 2 2025

krzysztof.galazka_intel.com added a comment to D46062: iflib(4): Replace admin taskqueue group with per-interface taskqueues.

@kbowling Do you want me to make any additional changes in this patch?

Jan 2 2025, 8:30 PM

Dec 6 2024

krzysztof.galazka_intel.com added inline comments to D46062: iflib(4): Replace admin taskqueue group with per-interface taskqueues.
Dec 6 2024, 8:21 PM
krzysztof.galazka_intel.com updated the diff for D46062: iflib(4): Replace admin taskqueue group with per-interface taskqueues.

Prefix taskqueue name with 'if_'.

Dec 6 2024, 7:59 PM

Nov 25 2024

krzysztof.galazka_intel.com updated the diff for D46062: iflib(4): Replace admin taskqueue group with per-interface taskqueues.

Add forgotten task init for IFLIB_INTR_IOV soft irq type.

Nov 25 2024, 5:49 PM

Oct 23 2024

krzysztof.galazka_intel.com added a comment to D46062: iflib(4): Replace admin taskqueue group with per-interface taskqueues.

Seems reasonable to me. If there is any work that depends or interacts with these changes it would be nice to see them linked/referenced so we can look at that too but I can't foresee any problems.

Oct 23 2024, 8:11 PM

Oct 21 2024

krzysztof.galazka_intel.com added a reviewer for D46062: iflib(4): Replace admin taskqueue group with per-interface taskqueues: jeffrey.e.pieper_intel.com.
Oct 21 2024, 4:10 PM

Oct 18 2024

krzysztof.galazka_intel.com updated the diff for D46062: iflib(4): Replace admin taskqueue group with per-interface taskqueues.

Rebased on top of master.
Free taskqueue after releasing interrupts per jhb comment on Github.

Oct 18 2024, 10:28 AM

Oct 1 2024

krzysztof.galazka_intel.com added a comment to D12142: Don't start grouptaskqueue threads for unused grouptaskqueues.

@krzysztof.galazka_intel.com can you rebase this on main?

Did autocompletion tricked you, or am I really the target of your message? I'm not sure if @kmacy will be happy with me messing with his patch.

Sorry I was looking at another review and got the wires crossed, for some reason I thought this was an Intel patch but I was looking at something else.

Oct 1 2024, 3:24 PM
krzysztof.galazka_intel.com added a comment to D12142: Don't start grouptaskqueue threads for unused grouptaskqueues.

@krzysztof.galazka_intel.com can you rebase this on main?

Oct 1 2024, 1:15 PM

Aug 14 2024

krzysztof.galazka_intel.com added a comment to D40860: ixl: fix multicast filters handling.

@franco_opnsense.org Output from sysctl dev.ixl.<N>.debug.filter_list and ifmcstat may shed some light on the problem. IPv4/v6 addresses can be removed. I'd like to compare mcast-macaddr list and filters configured by driver. Could you please open also a PR on FreeBSD bugzilla?

Aug 14 2024, 8:52 PM

Jul 22 2024

krzysztof.galazka_intel.com added a reviewer for D46061: iflib: Simplify iflib_legacy_setup: markj.
Jul 22 2024, 4:32 PM
krzysztof.galazka_intel.com requested review of D46062: iflib(4): Replace admin taskqueue group with per-interface taskqueues.
Jul 22 2024, 4:26 PM
krzysztof.galazka_intel.com requested review of D46061: iflib: Simplify iflib_legacy_setup.
Jul 22 2024, 4:26 PM

May 29 2024

krzysztof.galazka_intel.com requested review of D45403: ixl(4): Add more debug information for queues' config.
May 29 2024, 10:45 PM

May 14 2024

krzysztof.galazka_intel.com added 1 blocking reviewer(s) for D45198: ixl(4): Don't process admin queue when handling ifmedia request: Intel Networking.
May 14 2024, 11:29 AM
krzysztof.galazka_intel.com requested review of D45198: ixl(4): Don't process admin queue when handling ifmedia request.
May 14 2024, 11:28 AM

Jul 6 2023

krzysztof.galazka_intel.com requested review of D40899: ixl(4): Add link state polling.
Jul 6 2023, 9:17 PM

Feb 6 2023

krzysztof.galazka_intel.com requested review of D38395: ixgbe(4): Filter out spurious link up indication.
Feb 6 2023, 8:07 AM

Jan 10 2023

krzysztof.galazka_intel.com added a member for Intel Networking: przemyslawx.lewandowski_intel.com.
Jan 10 2023, 8:52 AM

Nov 21 2022

krzysztof.galazka_intel.com requested review of D37457: ixl(4): Fix MAC/VLAN filters accounting.
Nov 21 2022, 10:26 PM

Jul 1 2022

krzysztof.galazka_intel.com accepted D35649: Fix ixl SR-IOV..
Jul 1 2022, 3:50 PM

Apr 19 2022

krzysztof.galazka_intel.com updated the diff for D34924: ixl(4): Add support for I710 devices and remove non-inclusive language.

Fixed typo in device id, was 5G instead of 1G.

Apr 19 2022, 11:06 AM

Apr 15 2022

krzysztof.galazka_intel.com requested review of D34924: ixl(4): Add support for I710 devices and remove non-inclusive language.
Apr 15 2022, 7:54 AM

Feb 8 2022

krzysztof.galazka_intel.com updated the diff for D32004: ixv(4): Allow PF to control the VF link state.

Update patch to apply on top of HEAD

Feb 8 2022, 11:13 AM
krzysztof.galazka_intel.com commandeered D32004: ixv(4): Allow PF to control the VF link state.
Feb 8 2022, 11:12 AM

Feb 7 2022

krzysztof.galazka_intel.com updated the diff for D26245: ix(4): Add control of 2.5/5G autonegotiation speeds.

Update patch to apply on top of HEAD

Feb 7 2022, 9:46 PM
krzysztof.galazka_intel.com commandeered D26245: ix(4): Add control of 2.5/5G autonegotiation speeds.
Feb 7 2022, 9:45 PM

Sep 13 2021

mike.jakubik_gmail.com awarded D31565: ixl(4): Fix 2.5 and 5G speeds reporting and update shared code a Like token.
Sep 13 2021, 12:31 PM

Aug 16 2021

krzysztof.galazka_intel.com updated the diff for D31565: ixl(4): Fix 2.5 and 5G speeds reporting and update shared code.
Aug 16 2021, 6:10 PM
krzysztof.galazka_intel.com requested review of D31565: ixl(4): Fix 2.5 and 5G speeds reporting and update shared code.
Aug 16 2021, 5:51 PM

Jul 23 2021

krzysztof.galazka_intel.com added a comment to D30733: ixl(4): Fix reporting of unqualified transceivers.
Jul 23 2021, 6:00 PM
krzysztof.galazka_intel.com updated the diff for D30733: ixl(4): Fix reporting of unqualified transceivers.
  • Do not rely on information from link event
Jul 23 2021, 5:53 PM

Jul 9 2021

krzysztof.galazka_intel.com added a comment to D30733: ixl(4): Fix reporting of unqualified transceivers.

I'm still not able to reproduce this issue with any of my switches. Could you, please, modify printf in the ixl_link_event function to dump hex values of status->link_info, status->an_info, hw->phy.link_info.link_info and hw->phy.link_info.an_info, and send me the log?

Jul 9 2021, 2:43 PM

Jun 30 2021

krzysztof.galazka_intel.com added a comment to D30733: ixl(4): Fix reporting of unqualified transceivers.

Thank you Sai! Now I understand what I should be looking for.

Jun 30 2021, 5:36 PM

Jun 23 2021

krzysztof.galazka_intel.com added a comment to D30733: ixl(4): Fix reporting of unqualified transceivers.

I have connected the cable back-to-back between two servers and rebooted them both at a time. During boot, on both the nodes, immediately after the driver is attached, receives link-event and notices MEDIA_AVAILABLE + IFF_UP + UNQUALIFIED + NO_LINK_UP.

Jun 23 2021, 2:38 PM

Jun 17 2021

krzysztof.galazka_intel.com added a comment to D30733: ixl(4): Fix reporting of unqualified transceivers.

So, thinking on this, my guess is that when you reboot the machine, we would be finding an "unqualified" for a qualified cable because FW see this as link down. Also, my guess, the cable will show up as unqualified when you shut the link on link-partner.

Jun 17 2021, 9:42 PM

Jun 14 2021

krzysztof.galazka_intel.com added a reviewer for D30758: Check for non-empty sysctl_ctx before attempting free: Intel Networking.

Actually using separate sysctl_ctx was necessary in non-iflib version of the driver to allow releasing and re-allocating queues while handling EMP reset. In this version Rx queues memory is managed by the iflib with IFDI interface so using separate syssctl context may be not required. Let me double check that.

Jun 14 2021, 4:50 PM
krzysztof.galazka_intel.com added a comment to D30733: ixl(4): Fix reporting of unqualified transceivers.

Also, in original change, https://reviews.freebsd.org/D28028, I noticed that after executing ixl_set_link(pf, false), the PHY capabilities query for an_info has I40E_AQ_QUALIFIED_MODULE unset. So, the same supported/qualified module becomes unqualified.
I think the crux of the problem is with ixl_set_link() unsetting I40E_AQ_QUALIFIED_MODULE.

Jun 14 2021, 3:59 PM

Jun 11 2021

krzysztof.galazka_intel.com requested review of D30733: ixl(4): Fix reporting of unqualified transceivers.
Jun 11 2021, 4:28 PM

Jun 8 2021

krzysztof.galazka_intel.com added reviewers for D30691: ixl(4): Add VxLAN HW offloads support: Intel Networking, stallamr_netapp.com.
Jun 8 2021, 7:16 AM
krzysztof.galazka_intel.com requested review of D30691: ixl(4): Add VxLAN HW offloads support.
Jun 8 2021, 7:13 AM

May 18 2021

krzysztof.galazka_intel.com added inline comments to D30178: ixgbe: Print NVM and Option ROM versions.
May 18 2021, 3:19 PM

Mar 19 2021

krzysztof.galazka_intel.com requested review of D29338: ixl(4): Add tunable to override Flow Control settings.
Mar 19 2021, 11:41 AM

Mar 3 2021

krzysztof.galazka_intel.com abandoned D21769: em/igb: Properly re-arm link interrupt.

Fixed with D21924 by marius

Mar 3 2021, 2:00 PM
krzysztof.galazka_intel.com added a reviewer for D29037: iflib: Add fields for tunneled packets in if_pkt_info: gallatin.
Mar 3 2021, 1:50 PM
krzysztof.galazka_intel.com requested review of D29037: iflib: Add fields for tunneled packets in if_pkt_info.
Mar 3 2021, 1:48 PM

Feb 16 2021

krzysztof.galazka_intel.com added a watcher for iflib: krzysztof.galazka_intel.com.
Feb 16 2021, 8:00 PM

Jan 14 2021

krzysztof.galazka_intel.com added a member for Intel Networking: gowtham.kumar.ks_intel.com.
Jan 14 2021, 11:50 AM

Jan 13 2021

krzysztof.galazka_intel.com requested review of D28137: ixl(4): Fix VLAN HW filtering.
Jan 13 2021, 3:42 PM
krzysztof.galazka_intel.com updated the diff for D28028: ixl(4): Add ability to control link state on ifconfig down.
  • Fix unqualified transceivers reporting
Jan 13 2021, 1:47 PM

Jan 7 2021

krzysztof.galazka_intel.com requested review of D28028: ixl(4): Add ability to control link state on ifconfig down.
Jan 7 2021, 8:38 PM

Dec 16 2020

krzysztof.galazka_intel.com requested review of D27639: ixl(4): Report RX errors as sum of all RX error counters.
Dec 16 2020, 7:39 PM

Dec 3 2020

krzysztof.galazka_intel.com removed a reviewer for D27344: Bring back AIM (Adaptive Interrupt Moderation) that was lost in IFLIB migration.: Intel Networking.

At least on real hardware I've used with iflib, with both ix and ixl, one needs to adjust irq moderation manually in order to get a decent amount of packets per irq. I honestly think AIM might be the best path forward for less tuning knobs, if it were the default with a wider range of min and max irq rates.

Dec 3 2020, 9:44 PM
krzysztof.galazka_intel.com requested review of D27465: iflib: Add rx_wait_irq configuration option.
Dec 3 2020, 8:07 PM

Aug 26 2020

krzysztof.galazka_intel.com updated the diff for D25549: ixl(4): Add support for X710-T*L devices.

Fix PHY configuration parameters when enabling EEE

Aug 26 2020, 11:47 AM

Aug 10 2020

krzysztof.galazka_intel.com added a comment to D25954: Remove redeclaration found by gcc build.

@lwhsu: Could you, please, remove the declaration in line 610 instead? The first occurrence is in a group of other LED functions.

Aug 10 2020, 7:23 PM

Aug 4 2020

krzysztof.galazka_intel.com updated the diff for D25549: ixl(4): Add support for X710-T*L devices.
  • Add missing cases in ixl_if_media_status for 2.5 and 5G
Aug 4 2020, 6:33 PM

Jul 2 2020

krzysztof.galazka_intel.com requested review of D25549: ixl(4): Add support for X710-T*L devices.
Jul 2 2020, 6:52 PM

Jun 9 2020

krzysztof.galazka_intel.com updated the diff for D24564: ixl(4): Add FW recovery mode support.
  • Replace 'if 1' with 'ifdef IXL_DEBUG' in ixl_pf.h to match with if_ixl.c
Jun 9 2020, 10:01 PM

Jun 2 2020

krzysztof.galazka_intel.com updated the diff for D24564: ixl(4): Add FW recovery mode support.
  • Fix sysctl ctx handling in IAVF
Jun 2 2020, 5:50 PM

May 16 2020

krzysztof.galazka_intel.com updated the diff for D21223: ixl(4): Fix issues with MTU change while passing traffic.

Backported disable rings fix implemented by Eric Joyner in ixl-iflib version of the driver. It prevents queue hangs when interface is reconfigured while receiving heavy traffic.

May 16 2020, 4:36 PM

May 12 2020

krzysztof.galazka_intel.com updated the diff for D24564: ixl(4): Add FW recovery mode support.
  • Remove redundant PF reset after EMP reset
May 12 2020, 7:33 PM

May 7 2020

krzysztof.galazka_intel.com updated the diff for D24564: ixl(4): Add FW recovery mode support.
  • Don't process admin queue if its not configured
May 7 2020, 10:26 PM

May 4 2020

krzysztof.galazka_intel.com updated the diff for D24564: ixl(4): Add FW recovery mode support.
  • Fix receiving broadcast frames after reset
May 4 2020, 1:14 PM

Apr 24 2020

krzysztof.galazka_intel.com created D24564: ixl(4): Add FW recovery mode support.
Apr 24 2020, 9:03 PM

Sep 23 2019

krzysztof.galazka_intel.com created D21769: em/igb: Properly re-arm link interrupt.
Sep 23 2019, 6:10 PM

Sep 20 2019

krzysztof.galazka_intel.com added a comment to D21712: iflib: Prevent watchdog from resetting idle queues.

I'm not sure, but I think the only way this can happen is when the link is down. Is that the caee here?

Sep 20 2019, 11:17 AM

Sep 19 2019

krzysztof.galazka_intel.com added a reviewer for D21705: if_ixv: disable RSS configuration on 82599 and X540 VFs: Intel Networking.
Sep 19 2019, 9:09 AM

Sep 6 2019

krzysztof.galazka_intel.com added reviewers for D21547: ix, ixv: Read msix_bar from device configuration: marius, shurd.
Sep 6 2019, 4:34 PM

Aug 12 2019

krzysztof.galazka_intel.com updated the summary of D21223: ixl(4): Fix issues with MTU change while passing traffic.
Aug 12 2019, 8:59 AM
krzysztof.galazka_intel.com created D21223: ixl(4): Fix issues with MTU change while passing traffic.
Aug 12 2019, 8:33 AM

Jul 1 2019

krzysztof.galazka_intel.com created D20826: ixgbe(4): Fix enabling/disabling and reconfiguration of queues.
Jul 1 2019, 5:21 PM

Jun 5 2019

krzysztof.galazka_intel.com updated the diff for D20290: Update Intel XL710 PF and VF drivers to version ixl-1.11.9 and ixlv-1.5.8.

ixlv: Use old implementation of _msec_pause for reset flow to avoid panic.

Jun 5 2019, 11:54 AM

May 24 2019

krzysztof.galazka_intel.com updated the diff for D20290: Update Intel XL710 PF and VF drivers to version ixl-1.11.9 and ixlv-1.5.8.

Changes in Netmap support for ixl caused that ixlv cannot be loaded when built as KLD. Move ixl specific Netmap includes from ixl_txrx.c file, which is shared by ixl and ixlv, to ixl_pf_main.c which is used only by ixl.

May 24 2019, 2:08 PM

May 20 2019

krzysztof.galazka_intel.com added reviewers for D20290: Update Intel XL710 PF and VF drivers to version ixl-1.11.9 and ixlv-1.5.8: shurd, marius.
May 20 2019, 11:16 AM

May 17 2019

krzysztof.galazka_intel.com created D20290: Update Intel XL710 PF and VF drivers to version ixl-1.11.9 and ixlv-1.5.8.
May 17 2019, 12:58 PM

Feb 28 2019

krzysztof.galazka_intel.com created D19402: ixv(4): Add missing IFLIB_IS_VF flag in iflib shared ctx.
Feb 28 2019, 11:43 AM

Jan 28 2019

krzysztof.galazka_intel.com added a reviewer for D18984: ixl: remove unnecessary limitations related to netmap: Intel Networking.

This limitation came from our out-of-tree driver, where we had to keep backwards compatibility, but there is no reason to keep it in the in-kernel version. Thanks Vincenzo for the patch. It looks good to me but let's wait for Eric to have a look too.

Jan 28 2019, 10:43 AM

Jan 11 2019

krzysztof.galazka_intel.com created D18817: ixl(4): Fix handling data passed with ioctl from NVM update tool.
Jan 11 2019, 8:57 AM

Dec 11 2018

krzysztof.galazka_intel.com added a reviewer for D18469: ix: Fix accessing wrong register, improve WoL support recognition ix, ixv: Update link status with autonegotiated baudrate value: jeffrey.e.pieper_intel.com.
Dec 11 2018, 2:03 PM
krzysztof.galazka_intel.com added a reviewer for D18470: ix(4),ixv(4): Fix TSO offloads when TXCSUM is disabled: jeffrey.e.pieper_intel.com.
Dec 11 2018, 2:01 PM