In the patch called "xen-netback: Turn off the carrier if the guest is not able to receive" NAPI was descheduled when the carrier was set off. That's not what most of the drivers do, and we don't have any specific reason to do so as well, so revert that change.
Signed-off-by: Zoltan Kiss <[email protected]> Cc: [email protected] Cc: [email protected] Cc: [email protected] --- v2: delete spurious space diff --git a/drivers/net/xen-netback/interface.c b/drivers/net/xen-netback/interface.c index 48a55cd..bfd10cb 100644 --- a/drivers/net/xen-netback/interface.c +++ b/drivers/net/xen-netback/interface.c @@ -78,12 +78,8 @@ int xenvif_poll(struct napi_struct *napi, int budget) /* This vif is rogue, we pretend we've there is nothing to do * for this vif to deschedule it from NAPI. But this interface * will be turned off in thread context later. - * Also, if a guest doesn't post enough slots to receive data on one of - * its queues, the carrier goes down and NAPI is descheduled here so - * the guest can't send more packets until it's ready to receive. */ - if (unlikely(queue->vif->disabled || - !netif_carrier_ok(queue->vif->dev))) { + if (unlikely(queue->vif->disabled)) { napi_complete(napi); return 0; } -- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to [email protected] More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/
