I am seeing this error on a Lenovo ThinkSystem SR665 V3 with a BCM57416 NetXtreme-E Dual-Media 10G RDMA Ethernet Controller.
It appears that the driver is unable to communicate with the network card's firmware, causing it to fail. This is appearing in the 6.8.0-79-generic #79-Ubuntu with the bnxt_en driver. This appears to be triggered when the bnxt_re (RoCE) module is loaded. It's this specific interaction that seems to trigger the firmware stall. uname -a Linux romano 6.8.0-79-generic #79-Ubuntu SMP PREEMPT_DYNAMIC Tue Aug 12 14:42:46 UTC 2025 x86_64 x86_64 x86_64 GNU/Linux As a workaround I blackisted the bnxt_re driver and the system booted and the BCM57416 NIC is working. ** Attachment added: "bcm57416_boot_log.txt" https://bugs.launchpad.net/ubuntu/+source/linux/+bug/2099708/+attachment/5905327/+files/bcm57416_boot_log.txt ** Changed in: linux (Ubuntu) Status: Invalid => Confirmed -- You received this bug notification because you are a member of Kernel Packages, which is subscribed to linux in Ubuntu. https://bugs.launchpad.net/bugs/2099708 Title: Broadcom RDMA over Converged Ethernet driver bnxt_re stalling on 24.04 Status in linux package in Ubuntu: Confirmed Bug description: We have a set of servers, equipped with Broadcom BCM57414 NetXtreme-E 10Gb/25Gb RDMA Ethernet Controllers. Booting Ubuntu 24.04 (on 6.8 kernel) on these machines leads to the bnxt_re driver stalling during boot, and outputting the following kernel log: bnxt_en 0000:ab:00.0: QPLIB: bnxt_re_is_fw_stalled: FW STALL Detected. cmdq[0xf]=0x3 waited (102721 > 100000) msec active 1 bnxt_en 0000:ab:00.0 bnxt_re0: Failed to modify HW QP infiniband bnxt_re0: Couldn't change QP1 state to INIT: -110 infiniband bnxt_re0: Couldn't start port bnxt_en 0000:ab:00.0 bnxt_re0: Failed to destroy HW QP This causes systemd-udev-settle.service to fail: udevadm[1212]: Timed out for waiting the udev queue being empty. After this point, if the machine is PXE booting and/ or provisioning via MaaS (which is the case), the provisioning basically fails. The current workaround is to disable RDMA in the BIOS, thus avoiding loading bnxt_re, I believe. This behavior doesn't seem to affect Ubuntu 22.04 with 5.15 kernel. The following Blog seems to explain this issue in great detail: https://utcc.utoronto.ca/~cks/space/blog/linux/BroadcomNetworkDriverAndRDMA To manage notifications about this bug go to: https://bugs.launchpad.net/ubuntu/+source/linux/+bug/2099708/+subscriptions -- Mailing list: https://launchpad.net/~kernel-packages Post to : kernel-packages@lists.launchpad.net Unsubscribe : https://launchpad.net/~kernel-packages More help : https://help.launchpad.net/ListHelp
