On 03/03/15 05:53, Nicolas Schichan wrote: > On 03/03/2015 02:42 PM, Eric Dumazet wrote: >>> To avoid that, I would take priv->tx_lock only once, or add a limit on >>> the number of skbs that can be drained per round. >> >> Something like this (untested) patch > > I'm not against testing this patch, but we do not have any SMP capable bcm63xx > board here so I don't think it will be of any use. > > bcm6358 and bcm6368 do indeed have two MIPS threads, but SMP is not possible > (due to a data cache or TLB shared across all MIPS threads , unbearably > complicating things, IIRC).
6358 does have the shared TLB (early BMIPS4350), but 6368 (later BMIPS4350) runs just fine in a regular SMP configuration, that's the default for OpenWrt actually. Maybe Jonas has something readily available he could test on? > > bcm63xx ARM SoCs look like they can support SMP though. These SoCs do not use this Ethernet controller at all. -- Florian -- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majord...@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/
