search for: node_dead

...rs/net/virtio_net.c @@ -138,8 +138,9 @@ struct virtnet_info { /* Does the affinity hint is set for virtqueues? */ bool affinity_hint_set; - /* CPU hot plug notifier */ - struct notifier_block nb; + /* CPU hotplug instances for online & dead */ + struct hlist_node node; + struct hlist_node node_dead; /* Control VQ buffers: protected by the rtnl lock */ struct virtio_net_ctrl_hdr ctrl_hdr; @@ -1237,25 +1238,53 @@ static void virtnet_set_affinity(struct virtnet_info *vi) vi->affinity_hint_set = true; } -static int virtnet_cpu_callback(struct notifier_block *nfb, - unsigne...

...rs/net/virtio_net.c @@ -138,8 +138,9 @@ struct virtnet_info { /* Does the affinity hint is set for virtqueues? */ bool affinity_hint_set; - /* CPU hot plug notifier */ - struct notifier_block nb; + /* CPU hotplug instances for online & dead */ + struct hlist_node node; + struct hlist_node node_dead; /* Control VQ buffers: protected by the rtnl lock */ struct virtio_net_ctrl_hdr ctrl_hdr; @@ -1237,25 +1238,53 @@ static void virtnet_set_affinity(struct virtnet_info *vi) vi->affinity_hint_set = true; } -static int virtnet_cpu_callback(struct notifier_block *nfb, - unsigne...

.../ > > + u16 single_pkt_max_descs; > > + > > + /* Do we have virtqueues with small vrings? */ > > + bool svring; > > + > > /* CPU hotplug instances for online & dead */ > > struct hlist_node node; > > struct hlist_node node_dead; > > worth checking that all these layout changes don't push useful things to > a different cache line. can you add that analysis? > Good point. I think that we can just move these to the bottom of the struct. > > I see confusiong here wrt whether some rings are "sma...

...hdr hdr; + virtio_net_ctrl_ack status; + struct virtio_net_ctrl_mq mq; + u8 promisc; + u8 allmulti; + u16 vid; + u64 offloads; +}; + struct virtnet_info { struct virtio_device *vdev; struct virtqueue *cvq; @@ -192,14 +203,7 @@ struct virtnet_info { struct hlist_node node; struct hlist_node node_dead; - /* Control VQ buffers: protected by the rtnl lock */ - struct virtio_net_ctrl_hdr ctrl_hdr; - virtio_net_ctrl_ack ctrl_status; - struct virtio_net_ctrl_mq ctrl_mq; - u8 ctrl_promisc; - u8 ctrl_allmulti; - u16 ctrl_vid; - u64 ctrl_offloads; + struct control_buf *ctrl; /* Ethtool settings */...

...many ring descriptors we may need to transmit a single packet */ > + u16 single_pkt_max_descs; > + > + /* Do we have virtqueues with small vrings? */ > + bool svring; > + > /* CPU hotplug instances for online & dead */ > struct hlist_node node; > struct hlist_node node_dead; worth checking that all these layout changes don't push useful things to a different cache line. can you add that analysis? I see confusiong here wrt whether some rings are "small"? all of them? some rx rings? some tx rings? names should make it clear. also do we really need bool s...

...*/ bool affinity_hint_set; + /* How many ring descriptors we may need to transmit a single packet */ + u16 single_pkt_max_descs; + + /* Do we have virtqueues with small vrings? */ + bool svring; + /* CPU hotplug instances for online & dead */ struct hlist_node node; struct hlist_node node_dead; @@ -455,6 +463,7 @@ static struct sk_buff *page_to_skb(struct virtnet_info *vi, unsigned int copy, hdr_len, hdr_padded_len; struct page *page_to_free = NULL; int tailroom, shinfo_size; + u16 max_frags = MAX_SKB_FRAGS; char *p, *hdr_p, *buf; p = page_address(page) + offset; @@ -520,7 +5...

...hdr hdr; + virtio_net_ctrl_ack status; + struct virtio_net_ctrl_mq mq; + u8 promisc; + u8 allmulti; + u16 vid; + u64 offloads; +}; + struct virtnet_info { struct virtio_device *vdev; struct virtqueue *cvq; @@ -192,14 +203,7 @@ struct virtnet_info { struct hlist_node node; struct hlist_node node_dead; - /* Control VQ buffers: protected by the rtnl lock */ - struct virtio_net_ctrl_hdr ctrl_hdr; - virtio_net_ctrl_ack ctrl_status; - struct virtio_net_ctrl_mq ctrl_mq; - u8 ctrl_promisc; - u8 ctrl_allmulti; - u16 ctrl_vid; - u64 ctrl_offloads; + struct control_buf *ctrl; /* Ethtool settings */...

...x_descs; > > > + > > > + /* Do we have virtqueues with small vrings? */ > > > + bool svring; > > > + > > > /* CPU hotplug instances for online & dead */ > > > struct hlist_node node; > > > struct hlist_node node_dead; > > > > worth checking that all these layout changes don't push useful things to > > a different cache line. can you add that analysis? > > > > Good point. > I think that we can just move these to the bottom of the struct. > > > > > I see co...

At the moment, if a virtio network device uses vrings with less than MAX_SKB_FRAGS + 2 entries, the device won't be functional. The following condition vq->num_free >= 2 + MAX_SKB_FRAGS will always evaluate to false, leading to TX timeouts. This patchset attempts this fix this bug, and to allow small rings down to 4 entries. The first patch introduces a new mechanism in virtio core -

Hi Michael, hi Jason, This patches applies a few cleanups to the virtio PCI interrupt handling code, and then converts the virtio PCI code to use the automatic MSI-X vectors spreading, as well as using the information in virtio-blk and virtio-scsi to automatically align the blk-mq queues to the MSI-X vectors. Changes since V2: - remove a redundant callback check - calculate ->msix_vectors

Hi Michael, hi Jason, This patches applies a few cleanups to the virtio PCI interrupt handling code, and then converts the virtio PCI code to use the automatic MSI-X vectors spreading, as well as using the information in virtio-blk and virtio-scsi to automatically align the blk-mq queues to the MSI-X vectors. Changes since V2: - remove a redundant callback check - calculate ->msix_vectors

Hi Michael, hi Jason, This patches applies a few cleanups to the virtio PCI interrupt handling code, and then converts the virtio PCI code to use the automatic MSI-X vectors spreading, as well as using the information in virtio-blk and virtio-scsi to automatically align the blk-mq queues to the MSI-X vectors. Changes since V1: - dropped the patches already merged for 4.10-rc - new patch to

Hi Michael, hi Jason, This patches applies a few cleanups to the virtio PCI interrupt handling code, and then converts the virtio PCI code to use the automatic MSI-X vectors spreading, as well as using the information in virtio-blk and virtio-scsi to automatically align the blk-mq queues to the MSI-X vectors. Changes since V1: - dropped the patches already merged for 4.10-rc - new patch to