Re: [PATCH 1/2] igc: don't rd/wr iomem when PCI is removed

[Aaron Ma]

On 7/5/21 3:47 PM, Dave Airlie wrote:
> Drive-by, but won't this add a lot of overhead on every register
> access? has this been benchmarked with lots of small network transfers
> or anything?

iperf3 is tested, the result is the same as before.
Due to the registers are rd/wr even after error_handler and remove.
Didn't find better fix.
Please let me know if you have any idea.

Thanks,
Aaron

> Dave.