01:43:53 on the plus side, with the 'malicious' driver notifications in e810, it is a bit easier to figure out when things have gone wrong :) 03:08:44 Malicious driver notifications? 03:44:27 So, someone with a Boston driver? 03:44:36 er, a Boston driver. (so much for editing) 12:51:32 since the NIC allows virtualizing itself and presenting a subset of its resources to a VM, it has notifications if bad data is passed to it 12:52:18 the name i think is likely misleading as it's more likely to be just a bug than malicious intent from a VM (obviously possible, but on the range of probabilities) 12:56:08 [illumos-gate] 18317 libzfs mnttab cache aborts on duplicate mnttab entries -- Brian Behlendorf 12:56:08 [illumos-gate] 18272 vioif: add multi-queue (VIRTIO_NET_F_MQ) support -- Andy Fiddaman 15:52:20 Yeah, those existed in the 700 series too. Ultimately we should never get one of those from the hardware otherwise something has gone really wrong. 15:53:05 yeah, i added a bit to print out the specific errors, since that did help spot a few bugs 16:15:16 my kingdom to be able to get more than an hour at a time to focus :) 20:12:57 boy when it rains... so a full adminq error on an i40e nic... 22:28:00 [illumos-gate] 18363 cxgbetool cudbg --collect rss panics host -- Ryan Zezeski 23:01:55 [illumos-gate] 18304 add ddi_ncpus_expected(9F) for sizing per-CPU resources -- Andy Fiddaman 23:01:55 [illumos-gate] 18358 virtio_map_cap() reuses another device's BAR register number -- Andy Fiddaman 23:01:55 [illumos-gate] 18361 vioif accepts offload features whose dependencies are missing -- Andy Fiddaman 23:01:55 [illumos-gate] 18360 vioif reports a nonsense MAC_PROP_SPEED when the device speed is unknown -- Andy Fiddaman 23:01:55 [illumos-gate] 18359 virtio: virtio_queue_alloc() can return with vio_mutex held -- Andy Fiddaman