search for: eventq

...> > the ctrl-vq can be special as well. > > > > Then maybe it's better to introduce vhost-mdev-net on top? > > Looking at the other type of virtio device: > > - console have two control virtqueues when multiqueue port is enabled > > - SCSI has controlq + eventq > > - GPU has controlq > > - Crypto device has one controlq > > - Socket has eventq > > ... Thanks for the list! It looks dirty to define specific commands and types in vhost UAPI for each of them in the future. It's definitely much better to find an approach to sol...

...'s request, while still leaving TARGET fields out. Added dummy event and clarified some aspects of the event protocol. First version sent to a wider audience (linux-kernel and virtio lists). Configuration ------------- Subsystem Device ID TBD Virtqueues 0:controlq 1:eventq 2..n:request queues Feature bits VIRTIO_SCSI_F_INOUT (0) - Whether a single request can include both read-only and write-only data buffers. Device configuration layout struct virtio_scsi_config { u32 num_queues; u32 event_info_size; u32 sense_size;...

...'s request, while still leaving TARGET fields out. Added dummy event and clarified some aspects of the event protocol. First version sent to a wider audience (linux-kernel and virtio lists). Configuration ------------- Subsystem Device ID TBD Virtqueues 0:controlq 1:eventq 2..n:request queues Feature bits VIRTIO_SCSI_F_INOUT (0) - Whether a single request can include both read-only and write-only data buffers. Device configuration layout struct virtio_scsi_config { u32 num_queues; u32 event_info_size; u32 sense_size;...

...guration +\end_layout + +\begin_layout Description + +\change_inserted 1531152142 1322651166 +Subsystem +\begin_inset space ~ +\end_inset + +Device +\begin_inset space ~ +\end_inset + +ID 7 +\end_layout + +\begin_layout Description + +\change_inserted 1531152142 1322571777 +Virtqueues 0:controlq; 1:eventq; 2..n:request queues. +\end_layout + +\begin_layout Description + +\change_inserted 1531152142 1322571813 +Feature +\begin_inset space ~ +\end_inset + +bits +\end_layout + +\begin_deeper +\begin_layout Description + +\change_inserted 1531152142 1322653523 +VIRTIO_SCSI_F_INOUT +\begin_inset space ~...

...guration +\end_layout + +\begin_layout Description + +\change_inserted 1531152142 1322651166 +Subsystem +\begin_inset space ~ +\end_inset + +Device +\begin_inset space ~ +\end_inset + +ID 7 +\end_layout + +\begin_layout Description + +\change_inserted 1531152142 1322571777 +Virtqueues 0:controlq; 1:eventq; 2..n:request queues. +\end_layout + +\begin_layout Description + +\change_inserted 1531152142 1322571813 +Feature +\begin_inset space ~ +\end_inset + +bits +\end_layout + +\begin_deeper +\begin_layout Description + +\change_inserted 1531152142 1322653523 +VIRTIO_SCSI_F_INOUT +\begin_inset space ~...

...k segfaults, but in pthread_kill in /lib/tls/libpthread.so not in the asterisk code. Is this something others have seen? This is with glibc-2.3.4-2 I just upgraded to 2.3.6 (the lastest for Fedora core 3) and it's the same. Not much of a traceback, it's happening here: static struct eventqent *unref_event(struct eventqent *e) { struct eventqent *ret = AST_LIST_NEXT(e, eq_next); if (ast_atomic_dec_and_test(&e->usecount) && ret) pthread_kill(accept_thread_ptr, SIGURG); return ret; } Should I file a bug on this? I would presume i...

...guration +\end_layout + +\begin_layout Description + +\change_inserted 1531152142 1322651166 +Subsystem +\begin_inset space ~ +\end_inset + +Device +\begin_inset space ~ +\end_inset + +ID 7 +\end_layout + +\begin_layout Description + +\change_inserted 1531152142 1322571777 +Virtqueues 0:controlq; 1:eventq; 2..n:request queues. +\end_layout + +\begin_layout Description + +\change_inserted 1531152142 1322571813 +Feature +\begin_inset space ~ +\end_inset + +bits +\end_layout + +\begin_deeper +\begin_layout Description + +\change_inserted 1531152142 1322653523 +VIRTIO_SCSI_F_INOUT +\begin_inset space ~...

...guration +\end_layout + +\begin_layout Description + +\change_inserted 1531152142 1322651166 +Subsystem +\begin_inset space ~ +\end_inset + +Device +\begin_inset space ~ +\end_inset + +ID 7 +\end_layout + +\begin_layout Description + +\change_inserted 1531152142 1322571777 +Virtqueues 0:controlq; 1:eventq; 2..n:request queues. +\end_layout + +\begin_layout Description + +\change_inserted 1531152142 1322571813 +Feature +\begin_inset space ~ +\end_inset + +bits +\end_layout + +\begin_deeper +\begin_layout Description + +\change_inserted 1531152142 1322653523 +VIRTIO_SCSI_F_INOUT +\begin_inset space ~...

On Tue, Oct 29, 2019 at 06:51:32PM +0800, Jason Wang wrote: > On 2019/10/29 ??6:17, Tiwei Bie wrote: > > This patch adds the network control vq support in vhost-mdev. > > A vhost-mdev specific op is introduced to allow parent drivers > > to handle the network control commands come from userspace. > > Probably work for userspace driver but not kernel driver. Exactly.

On Tue, Oct 29, 2019 at 06:51:32PM +0800, Jason Wang wrote: > On 2019/10/29 ??6:17, Tiwei Bie wrote: > > This patch adds the network control vq support in vhost-mdev. > > A vhost-mdev specific op is introduced to allow parent drivers > > to handle the network control commands come from userspace. > > Probably work for userspace driver but not kernel driver. Exactly.

...guration +\end_layout + +\begin_layout Description + +\change_inserted 1531152142 1322651166 +Subsystem +\begin_inset space ~ +\end_inset + +Device +\begin_inset space ~ +\end_inset + +ID 7 +\end_layout + +\begin_layout Description + +\change_inserted 1531152142 1322571777 +Virtqueues 0:controlq; 1:eventq; 2..n:request queues. +\end_layout + +\begin_layout Description + +\change_inserted 1531152142 1322571813 +Feature +\begin_inset space ~ +\end_inset + +bits +\end_layout + +\begin_deeper +\begin_layout Description + +\change_inserted 1531152142 1328438975 +VIRTIO_SCSI_F_INOUT +\begin_inset space ~...

...guration +\end_layout + +\begin_layout Description + +\change_inserted 1531152142 1322651166 +Subsystem +\begin_inset space ~ +\end_inset + +Device +\begin_inset space ~ +\end_inset + +ID 7 +\end_layout + +\begin_layout Description + +\change_inserted 1531152142 1322571777 +Virtqueues 0:controlq; 1:eventq; 2..n:request queues. +\end_layout + +\begin_layout Description + +\change_inserted 1531152142 1322571813 +Feature +\begin_inset space ~ +\end_inset + +bits +\end_layout + +\begin_deeper +\begin_layout Description + +\change_inserted 1531152142 1328438975 +VIRTIO_SCSI_F_INOUT +\begin_inset space ~...

...your point now. In virtio-mdev kernel driver case, > the ctrl-vq can be special as well. > Then maybe it's better to introduce vhost-mdev-net on top? Looking at the other type of virtio device: - console have two control virtqueues when multiqueue port is enabled - SCSI has controlq + eventq - GPU has controlq - Crypto device has one controlq - Socket has eventq ... Thanks

..._entry *) 0x81197a0 x = 2 dup = 0x8137cc0 "reload" tws = 0 #5 0x080aef0f in action_command (s=0x81ead18, m=0xbddfaac0) at manager.c:927 No locals. #6 0x080b3ee4 in process_message (s=0x81ead18, m=0xbddfaac0) at manager.c:1305 ret = 0 eqe = (struct eventqent *) 0x0 action = "Command", '\0' <repeats 72 times> tmp = (struct manager_action *) 0x8144818 idText = "ActionID: 2007-01-03 15:17:39.165755\r\n", '\0' <repeats 217 times> iabuf = "216.187.141.250" #7 0x080...

...t; +- virtio_transport : phandle of the virtio device. This device must support one > + virtqueue for transmitting commands ("tx", cmdq), and, > + optionally, one more virtqueue for receiving notifications > + and delayed responses ("rx", eventq). Isn't what the virtio device provides discoverable? We don't have virtio protocols in DT for anything else. Why is SCMI special? Rob

...as sensitive to > writes from the producer.) > > I have two quick comments on your patch -- > 1) I think you need to kfree vq->avail when deleting the virtqueue. > > 2) Should we avoid allocating a cache for virtqueues that are not > performance critical? (ex: virtio-scsi eventq/controlq, virtio-net > controlq) > > Should I post comments in reply to the original patch email (given that it > is ~2 months old)? > > Thanks! > -- vs; >

...but our tests w/ polling are not as sensitive to writes from the producer.) I have two quick comments on your patch -- 1) I think you need to kfree vq->avail when deleting the virtqueue. 2) Should we avoid allocating a cache for virtqueues that are not performance critical? (ex: virtio-scsi eventq/controlq, virtio-net controlq) Should I post comments in reply to the original patch email (given that it is ~2 months old)? Thanks! -- vs;

...but our tests w/ polling are not as sensitive to writes from the producer.) I have two quick comments on your patch -- 1) I think you need to kfree vq->avail when deleting the virtqueue. 2) Should we avoid allocating a cache for virtqueues that are not performance critical? (ex: virtio-scsi eventq/controlq, virtio-net controlq) Should I post comments in reply to the original patch email (given that it is ~2 months old)? Thanks! -- vs;

Improves cacheline transfer flow of available ring header. Virtqueues are implemented as a pair of rings, one producer->consumer avail ring and one consumer->producer used ring; preceding the avail ring in memory are two contiguous u16 fields -- avail->flags and avail->idx. A producer posts work by writing to avail->idx and a consumer reads avail->idx. The flags and idx fields

Improves cacheline transfer flow of available ring header. Virtqueues are implemented as a pair of rings, one producer->consumer avail ring and one consumer->producer used ring; preceding the avail ring in memory are two contiguous u16 fields -- avail->flags and avail->idx. A producer posts work by writing to avail->idx and a consumer reads avail->idx. The flags and idx fields