On 22/09/2024 21:22, Eric wrote: The bisect is complete and yields this result15115033f056cbd7649b8e1806287f71bdb7ce5c is the first bad commit commit 15115033f056cbd7649b8e1806287f71bdb7ce5c Author: Maciej Fijalkowski <maciej.fijalkow...@intel.com> Date: Fri Jul 26 20:17:10 2024 +0200 ice: don't busy wait for Rx queue disable in ice_qp_dis() [ Upstream commit 1ff72a2f67791cd4ddad19ed830445f57b30e992 ] When ice driver is spammed with multiple xdpsock instances and flow control is enabled, there are cases when Rx queue gets stuck and unable to reflect the disable state in QRX_CTRL register. Similar issue has previously been addressed in commit 13a6233b033f ("ice: Add support to enable/disable all Rx queues before waiting"). To workaround this, let us simply not wait for a disabled state as later patch will make sure that regardless of the encountered error in the process of disabling a queue pair, the Rx queue will be enabled. Fixes: 2d4238f55697 ("ice: Add support for AF_XDP") Reviewed-by: Shannon Nelson <shannon.nel...@amd.com> Tested-by: Chandan Kumar Rout <chandanx.r...@intel.com> (A Contingent Worker at Intel) Signed-off-by: Maciej Fijalkowski <maciej.fijalkow...@intel.com> Signed-off-by: Tony Nguyen <anthony.l.ngu...@intel.com> Signed-off-by: Sasha Levin <sas...@kernel.org>
I posted too early ... looking back I found that nonsensical. Turns out on that last commit I had made a mistake. I suspect I booted on the wrong kernel that time. I'll redo the last few rounds and post only after checking that the "first bad commit" indeed is bad. Sorry for the noise Eric
