Query: Advanced Search

cxgbe(4): Update all firmwares to 1.19.1.0.

cxgbe(4): Move all TCAM filter code into a separate file.

cxgbe(4): Destroy the cdev before disabling interrupts in driver detach.

cxgbe(4): Convert ACT_OPEN_RPL to a shared CPL.

cxgbe/t4_tom: Use appropriate macros instead of magic math while

cxgbe(4): Use opaque cookies or tid range-checks to determine the

cxgbe(4): Move release_tid to the base NIC driver for future consumers.

cxgbe(4): Break up alloc_tid_tabs and move the atid routines to the base

cxgbe(4): Fix bugs in the handling of COP rules that match on VLAN tag.

Fix typo in cxgbetool.8.

cxgbe(4): Add support for Connection Offload Policy (aka COP).

cxgbe(4): Always display an error message if SIOCSIFFLAGS will leave

cxgbe: Implement tcp_info handler for connections handled by t4_tom.

Add a hook to allow the toedev handling an offloaded connection to

Fix RSS build (broken in r331309).

MFC r323006 and r324386.

	Include stories about projects I am a member of.

Kevin mentioned offline that he has no objections to this change. Anyone else want to review?

Disconnect iw_cxgb from the build.

Make a private copy of dequeue_socket from existing iwcm in 11 and use

Use soupcall_set/clear because listen-only sockets are available in

In D14816#311651, @kevin.bowling_kev009.com wrote:

This should use some kind of serdes to the toe understanding of tcpi is not dependent on the freebsd understanding of tcpi (which is in flux atm)

cxgbe(4): Always initialize requested_speed to a valid value.

cxgbe(4): Do not read MFG diags information from custom boards.

cxgbe(4): Tunnel congestion drops on a port should be cleared when the

Add mergeinfo. This should have been part of r331320.

MFC r326169 (cxgbe portion).

MFC r320418. Note that the socket lock _is_ the same as so_rcv's lock

Back out r329017 and r329391, which were direct commits to stable/11.

cxgbetool(8): Add the ability to decode hardware TCBs.

MFC r322659 (by glebius):

MFC r319506, r319872, r321063, r321103, r321179, r321390, r321435,

Catch up with the removal of nktr_slot_flags from upstream netmap. No

I wonder what __builtin_prefetch does on i386/amd64. It may be possible to use it unconditionally, and not just for !(i386|amd64).

iw_cxgbe: Follow-up fix to r329017, which updated the code associated

iw_cxgbe: Manually backport changes related to QP flush. This fixes a

iw_cxgbe: Remove declaration of a function that no longer exists.

cxgbe(4): Accept old names of a couple of tunables.

cxgbe(4): Do not display harmless warning in non-debug builds.

cxgb(4): Validate offset/len in the GET_EEPROM ioctl.

Do not generate illegal mbuf chains during IP fragment reassembly. Only

ugh. I still need reviewers for this. I accidentally accepted it as myself and on behalf of network.

In D14009#293983, @ae wrote:

I think the description that you gave in IRC was better :)
I.e. a !WRITABLE mbuf is reflected by ICMP code.

cxgbe/iw_cxgbe: Remove duplicates to fix compilation with recent gcc.

cxgbe(4): Add a knob to enable/disable PCIe relaxed ordering. Disable it by

cxgbe(4): Reduce duplication by consolidating minor variations of the

cxgbe/iw_cxgbe: Fix iWARP over VLANs (catch up with r326169).

cxgbe(4): Do not forward interrupts to queues with freelists. This

cxgbe(4): Read the MFG diags version from the VPD and make it available

cxgbe(4): Fix unsafe mailbox access in cudbg.

cxgbe(4): Add a custom board to the device id list.

cxgbe(4): Add core Vdd to the sysctl MIB.

cxgbe(4): Remove rsrv_noflowq from intrs_and_queues structure as it does

cxgbe(4): Sanitize t4_num_vis during MOD_LOAD like all other t4_*

cxgbe(4): Combine all _10g and _1g tunables and drop the suffix from

Have you tested this change on x86 to make sure it still works on LE hardware? It looks ok but it would be nice to test...

In D11378#247102, @erj wrote:

In D11378#247048, @sbruno wrote:

@erj are you going to commit this once you've made the IXL updates required for it to function?

Yeah, that's the plan. If @bartosz.sobczak_intel.com is okay with the current version.

Can you please verify that the output of "sysctl dev.t6nex.0.doorbells " looks ok before commiting this? It should show the names of the bits and not just the numeric value.

Fix iw_cxgbe build in the projects branch.

cxgbe(4): Excluce mdi from the check against port capabilities.

cxgbe(4): Do not request settings not supported by the port.

Update the iw_cxgbe bits in the projects branch.

cxgbe(4): Read the MPS buffer group map from the firmware as it could be

cxgbetool(8): Do not close uninitialized fd on malloc failure.

cxgbe(4): Update T6, T5, and T4 firmwares to 1.16.63.0.

cxgbetool(8): Do not create a large file devoid of useful content when

cxgbe(4): Provide knobs to set the holdoff parameters of TOE rx queues

Advanced SearchUse ResultsEdit QueryHide Query

May 5 2018

May 1 2018

Apr 30 2018

Apr 26 2018

Apr 19 2018

Apr 15 2018

Apr 14 2018

Apr 4 2018

Apr 3 2018

Mar 29 2018

Mar 28 2018

Mar 27 2018

Mar 26 2018

Mar 24 2018

Mar 22 2018

Mar 21 2018

Mar 14 2018

Mar 12 2018

Mar 8 2018

Mar 3 2018

Feb 20 2018

Feb 16 2018

Feb 8 2018

Feb 7 2018

Jan 26 2018

Jan 24 2018

Jan 22 2018

Jan 21 2018

Jan 18 2018

Jan 13 2018

Jan 9 2018

Jan 3 2018

Dec 29 2017

Dec 27 2017

Dec 22 2017

Dec 21 2017

Nov 21 2017

Nov 20 2017

Nov 17 2017

Nov 16 2017

Nov 15 2017

Nov 14 2017

Nov 10 2017

Nov 9 2017

Nov 8 2017

Oct 24 2017

Oct 19 2017

Oct 15 2017

Oct 9 2017

Oct 7 2017

Oct 5 2017

Sep 25 2017

Advanced Search
Use Results
Edit Query
Hide Query