Hi Saeed, I'm having issues loading mlx5 driver on v4.19 kernels (tested both net-next and bpf-next), while kernel v4.18 seems to work. It happens with a Mellanox ConnectX-5 NIC (and also a CX4-Lx but I removed that from the system now).
One pain point is very long boot-time, caused by some timeout code in the driver. The kernel console log (dmesg) says: [ 5.763330] mlx5_core 0000:03:00.0: firmware version: 16.22.1002 [ 5.769367] mlx5_core 0000:03:00.0: 126.016 Gb/s available PCIe bandwidth, limited by 8 GT/s x16 link at 0000:00:02.0 (capable of 252.048 Gb/s with 16 GT/s x16 link) (...) other drivers loading [ 66.816635] mlx5_core 0000:03:00.0: wait_func:964:(pid 112): ENABLE_HCA(0x104) timeout. Will cause a leak of a command resource [ 66.828123] mlx5_core 0000:03:00.0: enable hca failed [ 66.845516] mlx5_core 0000:03:00.0: mlx5_load_one failed with error code -110 [ 66.852802] mlx5_core: probe of 0000:03:00.0 failed with error -110 [ 66.859347] mlx5_core 0000:03:00.1: firmware version: 16.22.1002 [ 66.865388] mlx5_core 0000:03:00.1: 126.016 Gb/s available PCIe bandwidth, limited by 8 GT/s x16 link at 0000:00:02.0 (capable of 252.048 Gb/s with 16 GT/s x16 link) [ 125.787395] XFS (sda3): Mounting V5 Filesystem [ 125.848509] XFS (sda3): Ending clean mount [ 127.984784] mlx5_core 0000:03:00.1: wait_func:964:(pid 5): ENABLE_HCA(0x104) timeout. Will cause a leak of a command resource [ 127.996090] mlx5_core 0000:03:00.1: enable hca failed [ 128.013819] mlx5_core 0000:03:00.1: mlx5_load_one failed with error code -110 [ 128.021076] mlx5_core: probe of 0000:03:00.1 failed with error -110 Do you have any idea what could be causing this? -- Best regards, Jesper Dangaard Brouer MSc.CS, Principal Kernel Engineer at Red Hat LinkedIn: http://www.linkedin.com/in/brouer
