From mboxrd@z Thu Jan 1 00:00:00 1970 From: Jesse Brandeburg Date: Tue, 12 Apr 2022 11:29:48 -0700 Subject: [Intel-wired-lan] [PATCH] ice: wait for EMP reset after firmware flash In-Reply-To: <20220412160856.1027597-1-alexandr.lobakin@intel.com> References: <20220412102753.670867-1-poros@redhat.com> <20220412160856.1027597-1-alexandr.lobakin@intel.com> Message-ID: MIME-Version: 1.0 Content-Type: text/plain; charset="us-ascii" Content-Transfer-Encoding: 7bit To: intel-wired-lan@osuosl.org List-ID: On 4/12/2022 9:08 AM, Alexander Lobakin wrote: >> +#define ICE_EMP_RESET_SLEEP 5000 > > Ooof, 5 sec is a lot! Is there any way to poll the device readiness? > Does it really need the whole 5 sec? The problem with resets is usually you don't want to disturb the hardware with PCIe pokes while it's resetting. In this case, this code only runs if it was indicated by the update status that the firmware could internally reset itself to pick up new updates, avoiding a reboot. Yes the five seconds is less than ideal, but it was the value we found that offered the most stability / likelihood of reset completing. In this case the 5 seconds is a tradeoff vs a reboot. Thank you Ivan for chasing down this bug!