Re: [PATCH 1/1] net-next/hinic:optmize rx refill buffer mechanism

From: David Miller
Date: Sat Dec 15 2018 - 14:31:31 EST


From: Xue Chaojing <xuechaojing@xxxxxxxxxx>
Date: Sun, 9 Dec 2018 19:14:19 +0000

> There is no need to schedule a different tasklet for refill,
> This patch remove it.
>
> Suggested-by: Neil Horman <nhorman@xxxxxxxxxx>
> Signed-off-by: Xue Chaojing <xuechaojing@xxxxxxxxxx>

I completely agree with Neil's analysis.

You should never receive a packet if refilling the ring entry
resources fails.

It is so dangerous to allow the RX ring to reach an empty state,
not only does it mean that the device will stop receiving frames
but also this is probably one of the least tested conditions in
ring based networking designs and it proabably has bugs that hang
the chip and require a HW reset to recover from.