vDPA support in qemu
cover vDPA support in qemu
vDPA device is a device that uses a datapath which complies with the virtio specifications with vendor specific control path. vDPA devices can be both physically located on the hardware or emulated by software. This RFC introduce the vDPA support in qemu
TODO
1) vIOMMU support
2) live migration support
Cindy Lu (8):
net: introduce qemu_get_peer
vhost_net: use the function qemu_get_peer
vhost-backend: export the vhost backend helper
vhsot_net: introduce set_config & get_config function
vhost: introduce new VhostOps vhost_dev_start
vhost: implement vhost_dev_start method
vhost-vdpa: introduce vhost-vdpa backend
vhost-vdpa: introduce vhost-vdpa net client
Jason Wang (2):
virtio-bus: introduce queue_enabled method
virtio-pci: implement queue_enabled method
configure | 21 ++ hw/net/vhost_net.c | 46 +++- hw/net/virtio-net.c | 19 +- hw/virtio/Makefile.objs | 1 + hw/virtio/vhost-backend.c | 40 ++- hw/virtio/vhost-vdpa.c | 406 ++++++++++++++++++++++++++++++ hw/virtio/vhost.c | 59 ++++- hw/virtio/virtio-pci.c | 18 ++ hw/virtio/virtio.c | 6 + include/hw/virtio/vhost-backend.h | 36 ++- include/hw/virtio/vhost-vdpa.h | 26 ++ include/hw/virtio/vhost.h | 8 + include/hw/virtio/virtio-bus.h | 4 + include/net/net.h | 1 + include/net/vhost-vdpa.h | 21 ++ include/net/vhost_net.h | 6 +- net/Makefile.objs | 2 +- net/clients.h | 2 + net/net.c | 9 + net/vhost-vdpa.c | 230 +++++++++++++++++ qapi/net.json | 23 +- qemu-options.hx | 12 + 22 files changed, 952 insertions(+), 44 deletions(-) create mode 100644 hw/virtio/vhost-vdpa.c create mode 100644 include/hw/virtio/vhost-vdpa.h create mode 100644 include/net/vhost-vdpa.h create mode 100644 net/vhost-vdpa.c
Signature · 1 line
2.21.1
PATCH 1/10 net: introduce qemu_get_peer
This is a small function that can get the peer
from given NetClientState and queue_index
--- include/net/net.h | 1 + net/net.c | 6 ++++++ 2 files changed, 7 insertions(+)
include/net/net.h +1 -0
@@ -176,6 +176,7 @@ void hmp_info_network(Monitor *mon, const QDict *qdict);void net_socket_rs_init (SocketReadState *rs,SocketReadStateFinalize *finalize,bool vnet_hdr); +NetClientState *qemu_get_peer (NetClientState *nc,int queue_index);/* NIC info */
net/net.c +6 -0
@@ -324,6 +324,12 @@ void *qemu_get_nic_opaque(NetClientState *nc)return nic->opaque; } +NetClientState *qemu_get_peer (NetClientState *nc,int queue_index) +{ +assert (nc !=NULL ); +NetClientState *ncs = nc + queue_index; +return ncs->peer; +}static void qemu_cleanup_net_client (NetClientState *nc) {
Signature · 1 line
2.21.1
Re: [PATCH v1 01/10] net: introduce qemu_get_peer
Quoted 26 lines · Cindy Lu
This is a small function that can get the peer
from given NetClientState andqueue_indexSigned-off-by Cindy Lu <[email protected]>--- include/net/net.h | 1 + net/net.c | 6 ++++++ 2 files changed, 7 insertions(+)include/net/net.h +1
-0@@ -176,6 +176,7 @@ void hmp_info_network(Monitor *mon, const QDict *qdict);void net_socket_rs_init (SocketReadState *rs,SocketReadStateFinalize *finalize,bool vnet_hdr); +NetClientState *qemu_get_peer (NetClientState *nc,int queue_index);/* NIC info */ net/net.c +0
-0
net/net.c void *qemu_get_nic_opaque(NetClientState *nc) · line 326
Quoted 3 lines
net/net.c +0
-0@@ -324,6 +324,12 @@ void *qemu_get_nic_opaque(NetClientState *nc)return nic->opaque; }
newline please.
Thanks
Quoted 9 lines
net/net.c +6
-0+NetClientState *qemu_get_peer (NetClientState *nc,int queue_index) +{ +assert (nc !=NULL ); +NetClientState *ncs = nc + queue_index; +return ncs->peer; +}static void qemu_cleanup_net_client (NetClientState *nc) {
Re: [PATCH v1 01/10] net: introduce qemu_get_peer
Quoted 30 lines · Jason Wang
Quoted 27 lines · Cindy Lu
This is a small function that can get the peer
from given NetClientState andqueue_indexSigned-off-by Cindy Lu <[email protected]>--- include/net/net.h | 1 + net/net.c | 6 ++++++ 2 files changed, 7 insertions(+)include/net/net.h +1
-0@@ -176,6 +176,7 @@ void hmp_info_network(Monitor *mon, const QDict *qdict);void net_socket_rs_init (SocketReadState *rs,SocketReadStateFinalize *finalize,bool vnet_hdr); +NetClientState *qemu_get_peer (NetClientState *nc,int queue_index);/* NIC info */ net/net.c +0
-0@@ -324,6 +324,12 @@ void *qemu_get_nic_opaque(NetClientState *nc)
Quoted 8 lines
net/net.c void *qemu_get_nic_opaque(NetClientState *nc) · line 326
Quoted 2 lines
net/net.c +0
-0return nic->opaque; }newline please.
Thanks
will add this
Quoted 11 lines
Quoted 10 lines
net/net.c +6
-0+NetClientState *qemu_get_peer (NetClientState *nc,int queue_index) +{ +assert (nc !=NULL ); +NetClientState *ncs = nc + queue_index; +return ncs->peer; +}static void qemu_cleanup_net_client (NetClientState *nc) {
PATCH 2/10 vhost_net: use the function qemu_get_peer
In reply to Cindy Luuser the qemu_get_peer to replace the old process
--- hw/net/vhost_net.c | 16 ++++++++++------ 1 file changed, 10 insertions(+), 6 deletions(-)
hw/net/vhost_net.c +10 -6
@@ -306,7 +306,9 @@ int vhost_net_start(VirtIODevice *dev, NetClientState *ncs,BusState *qbus =BUS (qdev_get_parent_bus (DEVICE (dev)));VirtioBusState *vbus =VIRTIO_BUS (qbus);VirtioBusClass *k =VIRTIO_BUS_GET_CLASS (vbus); +struct vhost_net *net;int r, e, i; +NetClientState *peer;if (!k->set_guest_notifiers) {error_report ("binding does not support guest notifiers" );
@@ -314,9 +316,9 @@ int vhost_net_start(VirtIODevice *dev, NetClientState *ncs, }for (i =0 ; i < total_queues; i++) { -struct vhost_net *net; - net =get_vhost_net (ncs[i].peer); + peer =qemu_get_peer (ncs, i); + net =get_vhost_net (peer);vhost_net_set_vq_index (net, i *2 );/* Suppress the masking guest notifiers on vhost user
@@ -335,15 +337,16 @@ int vhost_net_start(VirtIODevice *dev, NetClientState *ncs, }for (i =0 ; i < total_queues; i++) { - r =vhost_net_start_one (get_vhost_net (ncs[i].peer), dev); + peer =qemu_get_peer (ncs, i); + r =vhost_net_start_one (get_vhost_net (peer), dev);if (r <0 ) { goto err_start; } -if (ncs[i].peer->vring_enable) { +if (peer->vring_enable) {/* restore vring enable state */ - r =vhost_set_vring_enable (ncs[i].peer, ncs[i].peer->vring_enable); + r =vhost_set_vring_enable (peer, peer->vring_enable);if (r <0 ) { goto err_start;
@@ -355,7 +358,8 @@ int vhost_net_start(VirtIODevice *dev, NetClientState *ncs, err_start:while (--i >=0 ) { -vhost_net_stop_one (get_vhost_net (ncs[i].peer), dev); + peer =qemu_get_peer (ncs , i); +vhost_net_stop_one (get_vhost_net (peer), dev); } e = k->set_guest_notifiers (qbus->parent, total_queues *2 , false);if (e <0 ) {
Signature · 1 line
2.21.1
Re: [PATCH v1 02/10] vhost_net: use the function qemu_get_peer
Quoted 7 lines · Cindy Lu
user the
qemu_get_peerto replace the old processSigned-off-by Cindy Lu <[email protected]>--- hw/net/vhost_net.c | 16 ++++++++++------ 1 file changed, 10 insertions(+), 6 deletions(-)
PATCH 3/10 virtio-bus: introduce queue_enabled method
In reply to Cindy LuFrom: Jason Wang <[email protected]>
This patch introduces queue_enabled() method which allows the transport to implement its own way to report whether or not a queue is enabled.
--- hw/virtio/virtio.c | 6 ++++++ include/hw/virtio/virtio-bus.h | 4 ++++ 2 files changed, 10 insertions(+)
hw/virtio/virtio.c +6 -0
@@ -3285,6 +3285,12 @@ hwaddr virtio_queue_get_desc_addr(VirtIODevice *vdev, int n)bool virtio_queue_enabled (VirtIODevice *vdev,int n) { +BusState *qbus =qdev_get_parent_bus (DEVICE (vdev)); +VirtioBusClass *k =VIRTIO_BUS_GET_CLASS (qbus); + +if (k->queue_enabled) { +return k->queue_enabled (qbus->parent, n); + }return virtio_queue_get_desc_addr (vdev, n) !=0 ; }
include/hw/virtio/virtio-bus.h +4 -0
@@ -83,6 +83,10 @@ typedef struct VirtioBusClass {*/ int (*ioeventfd_assign)(DeviceState *d,EventNotifier *notifier,int n,bool assign); +/* +* Whether queue number n is enabled. +*/ +bool (*queue_enabled)(DeviceState *d,int n);/* * Does the transport have variable vring alignment? * (ie can it ever call virtio_queue_set_align()?)
Signature · 1 line
2.21.1
PATCH 4/10 virtio-pci: implement queue_enabled method
In reply to Cindy LuFrom: Jason Wang <[email protected]>
With version 1, we can detect whether a queue is enabled via queue_enabled.
--- hw/virtio/virtio-pci.c | 18 ++++++++++++++++++ 1 file changed, 18 insertions(+)
hw/virtio/virtio-pci.c +18 -0
@@ -1107,6 +1107,23 @@ static AddressSpace *virtio_pci_get_dma_as(DeviceState *d)return pci_get_address_space (dev); } +static bool virtio_queue_check_enabled (VirtIODevice *vdev,int n) +{ +return virtio_queue_get_desc_addr (vdev, n) !=0 ; +} + +static bool virtio_pci_queue_enabled (DeviceState *d,int n) +{ +VirtIOPCIProxy *proxy =VIRTIO_PCI (d); +VirtIODevice *vdev =virtio_bus_get_device (&proxy->bus); + +if (virtio_vdev_has_feature (vdev,VIRTIO_F_VERSION_1 )) { +return proxy->vqs[vdev->queue_sel].enabled; + } + +return virtio_queue_check_enabled (vdev, n); +} +static int virtio_pci_add_mem_cap (VirtIOPCIProxy *proxy,struct virtio_pci_cap *cap) {
@@ -2059,6 +2076,7 @@ static void virtio_pci_bus_class_init(ObjectClass *klass, void *data) k->ioeventfd_enabled = virtio_pci_ioeventfd_enabled; k->ioeventfd_assign = virtio_pci_ioeventfd_assign; k->get_dma_as = virtio_pci_get_dma_as; + k->queue_enabled = virtio_pci_queue_enabled; }static const TypeInfo virtio_pci_bus_info = {
Signature · 1 line
2.21.1
Re: [PATCH v1 04/10] virtio-pci: implement queue_enabled method
Quoted 16 lines · Cindy Lu
From: Jason Wang <[email protected]>
With version 1, we can detect whether a queue is enabled via
queue_enabled.Signed-off-by Jason Wang <[email protected]>Signed-off-by Cindy Lu <[email protected]>--- hw/virtio/virtio-pci.c | 18 ++++++++++++++++++ 1 file changed, 18 insertions(+)hw/virtio/virtio-pci.c +0
-0
hw/virtio/virtio-pci.c static AddressSpace *virtio_pci_get_dma_as(DeviceState *d) · line 1110
Quoted 4 lines
hw/virtio/virtio-pci.c +1
-0@@ -1107,6 +1107,23 @@ static AddressSpace *virtio_pci_get_dma_as(DeviceState *d)return pci_get_address_space (dev); } +static bool virtio_queue_check_enabled (VirtIODevice *vdev,int n)
One space is sufficient between bool and virtio_queue_check_enabled.
Quoted 4 lines
hw/virtio/virtio-pci.c +4
-0+{ +return virtio_queue_get_desc_addr (vdev, n) !=0 ; +} +
hw/virtio/virtio-pci.c static AddressSpace *virtio_pci_get_dma_as(DeviceState *d) · line 1124
Quoted 10 lines
hw/virtio/virtio-pci.c +10
-0+static bool virtio_pci_queue_enabled (DeviceState *d,int n) +{ +VirtIOPCIProxy *proxy =VIRTIO_PCI (d); +VirtIODevice *vdev =virtio_bus_get_device (&proxy->bus); + +if (virtio_vdev_has_feature (vdev,VIRTIO_F_VERSION_1 )) { +return proxy->vqs[vdev->queue_sel].enabled; + } + +return virtio_queue_check_enabled (vdev, n);
Similar issue here.
Thanks
Quoted 13 lines
hw/virtio/virtio-pci.c +3
-0+} +static int virtio_pci_add_mem_cap (VirtIOPCIProxy *proxy,struct virtio_pci_cap *cap) {@@ -2059,6 +2076,7 @@ static void virtio_pci_bus_class_init(ObjectClass *klass, void *data) k->ioeventfd_enabled = virtio_pci_ioeventfd_enabled; k->ioeventfd_assign = virtio_pci_ioeventfd_assign; k->get_dma_as = virtio_pci_get_dma_as; + k->queue_enabled = virtio_pci_queue_enabled; }static const TypeInfo virtio_pci_bus_info = {
Re: [PATCH v1 04/10] virtio-pci: implement queue_enabled method
Quoted 46 lines · Jason Wang
Quoted 16 lines · Cindy Lu
From: Jason Wang <[email protected]>
With version 1, we can detect whether a queue is enabled via
queue_enabled.Signed-off-by Jason Wang <[email protected]>Signed-off-by Cindy Lu <[email protected]>--- hw/virtio/virtio-pci.c | 18 ++++++++++++++++++ 1 file changed, 18 insertions(+)hw/virtio/virtio-pci.c +0
-0hw/virtio/virtio-pci.c static AddressSpace *virtio_pci_get_dma_as(DeviceState *d) · line 1110
Quoted 4 lines
hw/virtio/virtio-pci.c +1
-0@@ -1107,6 +1107,23 @@ static AddressSpace *virtio_pci_get_dma_as(DeviceState *d)return pci_get_address_space (dev); } +static bool virtio_queue_check_enabled (VirtIODevice *vdev,int n)One space is sufficient between bool and
virtio_queue_check_enabled.Quoted 4 lines
hw/virtio/virtio-pci.c +4
-0+{ +return virtio_queue_get_desc_addr (vdev, n) !=0 ; +} +hw/virtio/virtio-pci.c static AddressSpace *virtio_pci_get_dma_as(DeviceState *d) · line 1124
Quoted 10 lines
hw/virtio/virtio-pci.c +10
-0+static bool virtio_pci_queue_enabled (DeviceState *d,int n) +{ +VirtIOPCIProxy *proxy =VIRTIO_PCI (d); +VirtIODevice *vdev =virtio_bus_get_device (&proxy->bus); + +if (virtio_vdev_has_feature (vdev,VIRTIO_F_VERSION_1 )) { +return proxy->vqs[vdev->queue_sel].enabled; + } + +return virtio_queue_check_enabled (vdev, n);Similar issue here.
Quoted 2 lines
Thanks
Thanks, I will correct this
Quoted 15 lines
Quoted 14 lines
hw/virtio/virtio-pci.c +3
-0+} +static int virtio_pci_add_mem_cap (VirtIOPCIProxy *proxy,struct virtio_pci_cap *cap) {@@ -2059,6 +2076,7 @@ static void virtio_pci_bus_class_init(ObjectClass *klass, void *data) k->ioeventfd_enabled = virtio_pci_ioeventfd_enabled; k->ioeventfd_assign = virtio_pci_ioeventfd_assign; k->get_dma_as = virtio_pci_get_dma_as; + k->queue_enabled = virtio_pci_queue_enabled; }static const TypeInfo virtio_pci_bus_info = {
Re: [PATCH v1 04/10] virtio-pci: implement queue_enabled method
In reply to Cindy LuQuoted 16 lines · Cindy Lu
From: Jason Wang <[email protected]>
With version 1, we can detect whether a queue is enabled via
queue_enabled.Signed-off-by Jason Wang <[email protected]>Signed-off-by Cindy Lu <[email protected]>--- hw/virtio/virtio-pci.c | 18 ++++++++++++++++++ 1 file changed, 18 insertions(+)hw/virtio/virtio-pci.c +0
-0
hw/virtio/virtio-pci.c static AddressSpace *virtio_pci_get_dma_as(DeviceState *d) · line 1113
Quoted 7 lines
hw/virtio/virtio-pci.c +4
-0@@ -1107,6 +1107,23 @@ static AddressSpace *virtio_pci_get_dma_as(DeviceState *d)return pci_get_address_space (dev); } +static bool virtio_queue_check_enabled (VirtIODevice *vdev,int n) +{ +return virtio_queue_get_desc_addr (vdev, n) !=0 ; +}
This function is already defined under a different name in hw/virtio/virtio.c:
3287 bool virtio_queue_enabled(VirtIODevice *vdev, int n)
3288 {
3289 return virtio_queue_get_desc_addr(vdev, n) != 0;
3290 }As this file includes "hw/virtio/virtio.h" you can use it directly.
Thanks,
Laurent
Re: [PATCH v1 04/10] virtio-pci: implement queue_enabled method
Quoted 30 lines · Laurent Vivier
Quoted 16 lines · Cindy Lu
From: Jason Wang <[email protected]>
With version 1, we can detect whether a queue is enabled via
queue_enabled.Signed-off-by Jason Wang <[email protected]>Signed-off-by Cindy Lu <[email protected]>--- hw/virtio/virtio-pci.c | 18 ++++++++++++++++++ 1 file changed, 18 insertions(+)hw/virtio/virtio-pci.c +0
-0hw/virtio/virtio-pci.c static AddressSpace *virtio_pci_get_dma_as(DeviceState *d) · line 1113
Quoted 7 lines
hw/virtio/virtio-pci.c +4
-0@@ -1107,6 +1107,23 @@ static AddressSpace *virtio_pci_get_dma_as(DeviceState *d)return pci_get_address_space (dev); } +static bool virtio_queue_check_enabled (VirtIODevice *vdev,int n) +{ +return virtio_queue_get_desc_addr (vdev, n) !=0 ; +}This function is already defined under a different name in
hw/virtio/virtio.c:
Quoted 7 lines
3287 bool virtio_queue_enabled(VirtIODevice *vdev, int n) 3288 { 3289 return virtio_queue_get_desc_addr(vdev, n) != 0; 3290 }As this file includes "
hw/virtio/virtio.h" you can use it directly.
Thanks Laurent, Will fix this
Quoted 3 lines
Thanks,
Laurent
PATCH 5/10 vhost-backend: export the vhost backend helper
In reply to Cindy Luexport the helper then we can reuse them in other backend
--- hw/virtio/vhost-backend.c | 18 +++++++++--------- include/hw/virtio/vhost-backend.h | 28 ++++++++++++++++++++++++++++ 2 files changed, 37 insertions(+), 9 deletions(-)
hw/virtio/vhost-backend.c +9 -9
@@ -89,7 +89,7 @@ static int vhost_kernel_scsi_get_abi_version(struct vhost_dev *dev, int *versionreturn vhost_kernel_call (dev,VHOST_SCSI_GET_ABI_VERSION , version); } -static int vhost_kernel_set_log_base (struct vhost_dev *dev,uint64_t base, +int vhost_kernel_set_log_base (struct vhost_dev *dev,uint64_t base,struct vhost_log *log) {return vhost_kernel_call (dev,VHOST_SET_LOG_BASE , &base);
@@ -101,7 +101,7 @@ static int vhost_kernel_set_mem_table(struct vhost_dev *dev,return vhost_kernel_call (dev,VHOST_SET_MEM_TABLE , mem); } -static int vhost_kernel_set_vring_addr (struct vhost_dev *dev, +int vhost_kernel_set_vring_addr (struct vhost_dev *dev,struct vhost_vring_addr *addr) {return vhost_kernel_call (dev,VHOST_SET_VRING_ADDR , addr);
@@ -113,31 +113,31 @@ static int vhost_kernel_set_vring_endian(struct vhost_dev *dev,return vhost_kernel_call (dev,VHOST_SET_VRING_ENDIAN , ring); } -static int vhost_kernel_set_vring_num (struct vhost_dev *dev, +int vhost_kernel_set_vring_num (struct vhost_dev *dev,struct vhost_vring_state *ring) {return vhost_kernel_call (dev,VHOST_SET_VRING_NUM , ring); } -static int vhost_kernel_set_vring_base (struct vhost_dev *dev, +int vhost_kernel_set_vring_base (struct vhost_dev *dev,struct vhost_vring_state *ring) {return vhost_kernel_call (dev,VHOST_SET_VRING_BASE , ring); } -static int vhost_kernel_get_vring_base (struct vhost_dev *dev, +int vhost_kernel_get_vring_base (struct vhost_dev *dev,struct vhost_vring_state *ring) {return vhost_kernel_call (dev,VHOST_GET_VRING_BASE , ring); } -static int vhost_kernel_set_vring_kick (struct vhost_dev *dev, +int vhost_kernel_set_vring_kick (struct vhost_dev *dev,struct vhost_vring_file *file) {return vhost_kernel_call (dev,VHOST_SET_VRING_KICK , file); } -static int vhost_kernel_set_vring_call (struct vhost_dev *dev, +int vhost_kernel_set_vring_call (struct vhost_dev *dev,struct vhost_vring_file *file) {return vhost_kernel_call (dev,VHOST_SET_VRING_CALL , file);
@@ -155,13 +155,13 @@ static int vhost_kernel_set_features(struct vhost_dev *dev,return vhost_kernel_call (dev,VHOST_SET_FEATURES , &features); } -static int vhost_kernel_get_features (struct vhost_dev *dev, +int vhost_kernel_get_features (struct vhost_dev *dev,uint64_t *features) {return vhost_kernel_call (dev,VHOST_GET_FEATURES , features); } -static int vhost_kernel_set_owner (struct vhost_dev *dev) +int vhost_kernel_set_owner (struct vhost_dev *dev) {return vhost_kernel_call (dev,VHOST_SET_OWNER ,NULL ); }
include/hw/virtio/vhost-backend.h +28 -0
@@ -172,4 +172,32 @@ int vhost_backend_handle_iotlb_msg(struct vhost_dev *dev,int vhost_user_gpu_set_socket (struct vhost_dev *dev,int fd); + +int vhost_kernel_set_log_base (struct vhost_dev *dev,uint64_t base, +struct vhost_log *log); + +int vhost_kernel_set_vring_addr (struct vhost_dev *dev, +struct vhost_vring_addr *addr); + +int vhost_kernel_set_vring_num (struct vhost_dev *dev, +struct vhost_vring_state *ring); + +int vhost_kernel_set_vring_base (struct vhost_dev *dev, +struct vhost_vring_state *ring); + +int vhost_kernel_get_vring_base (struct vhost_dev *dev, +struct vhost_vring_state *ring); + +int vhost_kernel_set_vring_kick (struct vhost_dev *dev, +struct vhost_vring_file *file); + +int vhost_kernel_set_vring_call (struct vhost_dev *dev, +struct vhost_vring_file *file); + +int vhost_kernel_set_owner (struct vhost_dev *dev); + +int vhost_kernel_get_features (struct vhost_dev *dev, +uint64_t *features); + +#endif /* VHOST_BACKEND_H */
Signature · 1 line
2.21.1
Re: [PATCH v1 05/10] vhost-backend: export the vhost backend helper
Quoted 8 lines · Cindy Lu
export the helper then we can reuse them in other backend
Signed-off-by Cindy Lu <[email protected]>--- hw/virtio/vhost-backend.c | 18 +++++++++--------- include/hw/virtio/vhost-backend.h | 28 ++++++++++++++++++++++++++++ 2 files changed, 37 insertions(+), 9 deletions(-)
This looks weird to export all these functions whereas they are all already exported by the vhost_ops structure.
So if vhost-vdpa is not a subset of vhost-kernel and if these functions will diverge from vhost-backend.c definition in the future, perhaps it is wise to already copy their definitions right now in vhost-vdpa.c rather than exporting them now and to have to copy them in the future in vhost-vdpa.c to modify them.
It will also simplify the definition of vhost_kernel_call().
Thanks,
Laurent
Quoted 113 lines
hw/virtio/vhost-backend.c +9
-9@@ -89,7 +89,7 @@ static int vhost_kernel_scsi_get_abi_version(struct vhost_dev *dev, int *versionreturn vhost_kernel_call (dev,VHOST_SCSI_GET_ABI_VERSION , version); } -static int vhost_kernel_set_log_base (struct vhost_dev *dev,uint64_t base, +int vhost_kernel_set_log_base (struct vhost_dev *dev,uint64_t base,struct vhost_log *log) {return vhost_kernel_call (dev,VHOST_SET_LOG_BASE , &base);@@ -101,7 +101,7 @@ static int vhost_kernel_set_mem_table(struct vhost_dev *dev,return vhost_kernel_call (dev,VHOST_SET_MEM_TABLE , mem); } -static int vhost_kernel_set_vring_addr (struct vhost_dev *dev, +int vhost_kernel_set_vring_addr (struct vhost_dev *dev,struct vhost_vring_addr *addr) {return vhost_kernel_call (dev,VHOST_SET_VRING_ADDR , addr);@@ -113,31 +113,31 @@ static int vhost_kernel_set_vring_endian(struct vhost_dev *dev,return vhost_kernel_call (dev,VHOST_SET_VRING_ENDIAN , ring); } -static int vhost_kernel_set_vring_num (struct vhost_dev *dev, +int vhost_kernel_set_vring_num (struct vhost_dev *dev,struct vhost_vring_state *ring) {return vhost_kernel_call (dev,VHOST_SET_VRING_NUM , ring); } -static int vhost_kernel_set_vring_base (struct vhost_dev *dev, +int vhost_kernel_set_vring_base (struct vhost_dev *dev,struct vhost_vring_state *ring) {return vhost_kernel_call (dev,VHOST_SET_VRING_BASE , ring); } -static int vhost_kernel_get_vring_base (struct vhost_dev *dev, +int vhost_kernel_get_vring_base (struct vhost_dev *dev,struct vhost_vring_state *ring) {return vhost_kernel_call (dev,VHOST_GET_VRING_BASE , ring); } -static int vhost_kernel_set_vring_kick (struct vhost_dev *dev, +int vhost_kernel_set_vring_kick (struct vhost_dev *dev,struct vhost_vring_file *file) {return vhost_kernel_call (dev,VHOST_SET_VRING_KICK , file); } -static int vhost_kernel_set_vring_call (struct vhost_dev *dev, +int vhost_kernel_set_vring_call (struct vhost_dev *dev,struct vhost_vring_file *file) {return vhost_kernel_call (dev,VHOST_SET_VRING_CALL , file);@@ -155,13 +155,13 @@ static int vhost_kernel_set_features(struct vhost_dev *dev,return vhost_kernel_call (dev,VHOST_SET_FEATURES , &features); } -static int vhost_kernel_get_features (struct vhost_dev *dev, +int vhost_kernel_get_features (struct vhost_dev *dev,uint64_t *features) {return vhost_kernel_call (dev,VHOST_GET_FEATURES , features); } -static int vhost_kernel_set_owner (struct vhost_dev *dev) +int vhost_kernel_set_owner (struct vhost_dev *dev) {return vhost_kernel_call (dev,VHOST_SET_OWNER ,NULL ); }include/hw/virtio/vhost-backend.h +28
-0@@ -172,4 +172,32 @@ int vhost_backend_handle_iotlb_msg(struct vhost_dev *dev,int vhost_user_gpu_set_socket (struct vhost_dev *dev,int fd); + +int vhost_kernel_set_log_base (struct vhost_dev *dev,uint64_t base, +struct vhost_log *log); + +int vhost_kernel_set_vring_addr (struct vhost_dev *dev, +struct vhost_vring_addr *addr); + +int vhost_kernel_set_vring_num (struct vhost_dev *dev, +struct vhost_vring_state *ring); + +int vhost_kernel_set_vring_base (struct vhost_dev *dev, +struct vhost_vring_state *ring); + +int vhost_kernel_get_vring_base (struct vhost_dev *dev, +struct vhost_vring_state *ring); + +int vhost_kernel_set_vring_kick (struct vhost_dev *dev, +struct vhost_vring_file *file); + +int vhost_kernel_set_vring_call (struct vhost_dev *dev, +struct vhost_vring_file *file); + +int vhost_kernel_set_owner (struct vhost_dev *dev); + +int vhost_kernel_get_features (struct vhost_dev *dev, +uint64_t *features); + +#endif /* VHOST_BACKEND_H */
Re: [PATCH v1 05/10] vhost-backend: export the vhost backend helper
Quoted 20 lines · Laurent Vivier
Quoted 8 lines · Cindy Lu
export the helper then we can reuse them in other backend
Signed-off-by Cindy Lu <[email protected]>--- hw/virtio/vhost-backend.c | 18 +++++++++--------- include/hw/virtio/vhost-backend.h | 28 ++++++++++++++++++++++++++++ 2 files changed, 37 insertions(+), 9 deletions(-)This looks weird to export all these functions whereas they are all already exported by the
vhost_opsstructure.So if vhost-vdpa is not a subset of vhost-kernel and if these functions will diverge from
vhost-backend.cdefinition in the future, perhaps it is wise to already copy their definitions right now invhost-vdpa.crather than exporting them now and to have to copy them in the future invhost-vdpa.cto modify them.
Quoted 5 lines
It will also simplify the definition of
vhost_kernel_call().Thanks,
Laurent
Thanks Laurent, will fix this
Quoted 114 lines
Quoted 113 lines
hw/virtio/vhost-backend.c +9
-9@@ -89,7 +89,7 @@ static int vhost_kernel_scsi_get_abi_version(struct vhost_dev *dev, int *versionreturn vhost_kernel_call (dev,VHOST_SCSI_GET_ABI_VERSION , version); } -static int vhost_kernel_set_log_base (struct vhost_dev *dev,uint64_t base, +int vhost_kernel_set_log_base (struct vhost_dev *dev,uint64_t base,struct vhost_log *log) {return vhost_kernel_call (dev,VHOST_SET_LOG_BASE , &base);@@ -101,7 +101,7 @@ static int vhost_kernel_set_mem_table(struct vhost_dev *dev,return vhost_kernel_call (dev,VHOST_SET_MEM_TABLE , mem); } -static int vhost_kernel_set_vring_addr (struct vhost_dev *dev, +int vhost_kernel_set_vring_addr (struct vhost_dev *dev,struct vhost_vring_addr *addr) {return vhost_kernel_call (dev,VHOST_SET_VRING_ADDR , addr);@@ -113,31 +113,31 @@ static int vhost_kernel_set_vring_endian(struct vhost_dev *dev,return vhost_kernel_call (dev,VHOST_SET_VRING_ENDIAN , ring); } -static int vhost_kernel_set_vring_num (struct vhost_dev *dev, +int vhost_kernel_set_vring_num (struct vhost_dev *dev,struct vhost_vring_state *ring) {return vhost_kernel_call (dev,VHOST_SET_VRING_NUM , ring); } -static int vhost_kernel_set_vring_base (struct vhost_dev *dev, +int vhost_kernel_set_vring_base (struct vhost_dev *dev,struct vhost_vring_state *ring) {return vhost_kernel_call (dev,VHOST_SET_VRING_BASE , ring); } -static int vhost_kernel_get_vring_base (struct vhost_dev *dev, +int vhost_kernel_get_vring_base (struct vhost_dev *dev,struct vhost_vring_state *ring) {return vhost_kernel_call (dev,VHOST_GET_VRING_BASE , ring); } -static int vhost_kernel_set_vring_kick (struct vhost_dev *dev, +int vhost_kernel_set_vring_kick (struct vhost_dev *dev,struct vhost_vring_file *file) {return vhost_kernel_call (dev,VHOST_SET_VRING_KICK , file); } -static int vhost_kernel_set_vring_call (struct vhost_dev *dev, +int vhost_kernel_set_vring_call (struct vhost_dev *dev,struct vhost_vring_file *file) {return vhost_kernel_call (dev,VHOST_SET_VRING_CALL , file);@@ -155,13 +155,13 @@ static int vhost_kernel_set_features(struct vhost_dev *dev,return vhost_kernel_call (dev,VHOST_SET_FEATURES , &features); } -static int vhost_kernel_get_features (struct vhost_dev *dev, +int vhost_kernel_get_features (struct vhost_dev *dev,uint64_t *features) {return vhost_kernel_call (dev,VHOST_GET_FEATURES , features); } -static int vhost_kernel_set_owner (struct vhost_dev *dev) +int vhost_kernel_set_owner (struct vhost_dev *dev) {return vhost_kernel_call (dev,VHOST_SET_OWNER ,NULL ); }include/hw/virtio/vhost-backend.h +28
-0@@ -172,4 +172,32 @@ int vhost_backend_handle_iotlb_msg(struct vhost_dev *dev,int vhost_user_gpu_set_socket (struct vhost_dev *dev,int fd); + +int vhost_kernel_set_log_base (struct vhost_dev *dev,uint64_t base, +struct vhost_log *log); + +int vhost_kernel_set_vring_addr (struct vhost_dev *dev, +struct vhost_vring_addr *addr); + +int vhost_kernel_set_vring_num (struct vhost_dev *dev, +struct vhost_vring_state *ring); + +int vhost_kernel_set_vring_base (struct vhost_dev *dev, +struct vhost_vring_state *ring); + +int vhost_kernel_get_vring_base (struct vhost_dev *dev, +struct vhost_vring_state *ring); + +int vhost_kernel_set_vring_kick (struct vhost_dev *dev, +struct vhost_vring_file *file); + +int vhost_kernel_set_vring_call (struct vhost_dev *dev, +struct vhost_vring_file *file); + +int vhost_kernel_set_owner (struct vhost_dev *dev); + +int vhost_kernel_get_features (struct vhost_dev *dev, +uint64_t *features); + +#endif /* VHOST_BACKEND_H */
PATCH 6/10 vhsot_net: introduce set_config & get_config function
In reply to Cindy LuThis patch introduces set_config & get_config method which allows vhost_net set/get the config to backend
--- hw/net/vhost_net.c | 11 +++++++++++ include/net/vhost_net.h | 5 +++++ 2 files changed, 16 insertions(+)
hw/net/vhost_net.c +11 -0
@@ -111,6 +111,17 @@ uint64_t vhost_net_get_features(struct vhost_net *net, uint64_t features) features); } +int vhost_net_get_config (struct vhost_net *net,uint8_t *config, +uint32_t config_len) +{ +return vhost_dev_get_config (&net->dev, config, config_len); +} +int vhost_net_set_config (struct vhost_net *net,const uint8_t *data, +uint32_t offset,uint32_t size,uint32_t flags) +{ +return vhost_dev_set_config (&net->dev, data, offset, size, flags); +} +void vhost_net_ack_features (struct vhost_net *net,uint64_t features) { net->dev.acked_features = net->dev.backend_features;
include/net/vhost_net.h +5 -0
@@ -27,6 +27,11 @@ void vhost_net_cleanup(VHostNetState *net);uint64_t vhost_net_get_features (VHostNetState *net,uint64_t features);void vhost_net_ack_features (VHostNetState *net,uint64_t features); +int vhost_net_get_config (struct vhost_net *net,uint8_t *config, +uint32_t config_len); + +int vhost_net_set_config (struct vhost_net *net,const uint8_t *data, +uint32_t offset,uint32_t size,uint32_t flags);bool vhost_net_virtqueue_pending (VHostNetState *net,int n); void vhost_net_virtqueue_mask(VHostNetState *net, VirtIODevice *dev,
Signature · 1 line
2.21.1
Re: [PATCH v1 06/10] vhsot_net: introduce set_config & get_config function
Quoted 1 line · Cindy Lu
This patch introduces
set_config&get_configmethod which allows
One space is sufficient between get_config and method.
Quoted 1 line
vhost_netset/get the config to backend
Typo in the subject.
hw/net/vhost_net.c
Quoted 11 lines
Signed-off-by Cindy Lu <[email protected]>--- hw/net/vhost_net.c | 11 +++++++++++ include/net/vhost_net.h | 5 +++++ 2 files changed, 16 insertions(+)hw/net/vhost_net.c +0
-0
Is there any reason that making this net specific? I guess it could be used by other vhost devices as well.
Thanks
Quoted 34 lines
hw/net/vhost_net.c +11
-0@@ -111,6 +111,17 @@ uint64_t vhost_net_get_features(struct vhost_net *net, uint64_t features) features); } +int vhost_net_get_config (struct vhost_net *net,uint8_t *config, +uint32_t config_len) +{ +return vhost_dev_get_config (&net->dev, config, config_len); +} +int vhost_net_set_config (struct vhost_net *net,const uint8_t *data, +uint32_t offset,uint32_t size,uint32_t flags) +{ +return vhost_dev_set_config (&net->dev, data, offset, size, flags); +} +void vhost_net_ack_features (struct vhost_net *net,uint64_t features) { net->dev.acked_features = net->dev.backend_features;include/net/vhost_net.h +5
-0@@ -27,6 +27,11 @@ void vhost_net_cleanup(VHostNetState *net);uint64_t vhost_net_get_features (VHostNetState *net,uint64_t features);void vhost_net_ack_features (VHostNetState *net,uint64_t features); +int vhost_net_get_config (struct vhost_net *net,uint8_t *config, +uint32_t config_len); + +int vhost_net_set_config (struct vhost_net *net,const uint8_t *data, +uint32_t offset,uint32_t size,uint32_t flags);bool vhost_net_virtqueue_pending (VHostNetState *net,int n); void vhost_net_virtqueue_mask(VHostNetState *net, VirtIODevice *dev,
Re: [PATCH v1 06/10] vhsot_net: introduce set_config & get_config function
Quoted 6 lines · Jason Wang
Quoted 1 line · Cindy Lu
This patch introduces
set_config&get_configmethod which allows
Quoted 9 lines
One space is sufficient between
get_configand method.Quoted 1 line
vhost_netset/get the config to backendTypo in the subject.
thanks jason, I will correct this
Quoted 15 lines
hw/net/vhost_net.c
Quoted 11 lines
Signed-off-by Cindy Lu <[email protected]>--- hw/net/vhost_net.c | 11 +++++++++++ include/net/vhost_net.h | 5 +++++ 2 files changed, 16 insertions(+)hw/net/vhost_net.c +0
-0Is there any reason that making this net specific? I guess it could be used by other vhost devices as well.
Quoted 2 lines
Thanks
Thanks jason I will correct this
Quoted 36 lines
Quoted 35 lines
hw/net/vhost_net.c +11
-0@@ -111,6 +111,17 @@ uint64_t vhost_net_get_features(struct vhost_net *net, uint64_t features) features); } +int vhost_net_get_config (struct vhost_net *net,uint8_t *config, +uint32_t config_len) +{ +return vhost_dev_get_config (&net->dev, config, config_len); +} +int vhost_net_set_config (struct vhost_net *net,const uint8_t *data, +uint32_t offset,uint32_t size,uint32_t flags) +{ +return vhost_dev_set_config (&net->dev, data, offset, size, flags); +} +void vhost_net_ack_features (struct vhost_net *net,uint64_t features) { net->dev.acked_features = net->dev.backend_features;include/net/vhost_net.h +5
-0@@ -27,6 +27,11 @@ void vhost_net_cleanup(VHostNetState *net);uint64_t vhost_net_get_features (VHostNetState *net,uint64_t features);void vhost_net_ack_features (VHostNetState *net,uint64_t features); +int vhost_net_get_config (struct vhost_net *net,uint8_t *config, +uint32_t config_len); + +int vhost_net_set_config (struct vhost_net *net,const uint8_t *data, +uint32_t offset,uint32_t size,uint32_t flags);bool vhost_net_virtqueue_pending (VHostNetState *net,int n); void vhost_net_virtqueue_mask(VHostNetState *net, VirtIODevice *dev,
PATCH 7/10 vhost: introduce new VhostOps vhost_dev_start
In reply to Cindy LuThis patch introduces vhost_dev_start() callback which allows the vhost_net set the start/stop status to backend
--- include/hw/virtio/vhost-backend.h | 2 ++ 1 file changed, 2 insertions(+)
include/hw/virtio/vhost-backend.h +2 -0
@@ -112,6 +112,7 @@ typedef int (*vhost_get_inflight_fd_op)(struct vhost_dev *dev,typedef int (*vhost_set_inflight_fd_op )(struct vhost_dev *dev,struct vhost_inflight *inflight); +typedef int (*vhost_dev_start_op )(struct vhost_dev *dev,bool started); typedef struct VhostOps { VhostBackendType backend_type; vhost_backend_init vhost_backend_init;
@@ -152,6 +153,7 @@ typedef struct VhostOps {vhost_backend_mem_section_filter_op vhost_backend_mem_section_filter;vhost_get_inflight_fd_op vhost_get_inflight_fd;vhost_set_inflight_fd_op vhost_set_inflight_fd; +vhost_dev_start_op vhost_dev_start; } VhostOps;extern const VhostOps user_ops;
Signature · 1 line
2.21.1
PATCH 8/10 vhost: implement vhost_dev_start method
In reply to Cindy Luuse the vhost_dev_start callback to send the status to backend
--- hw/virtio/vhost.c | 17 +++++++++++++++++ include/hw/virtio/vhost.h | 2 ++ 2 files changed, 19 insertions(+)
hw/virtio/vhost.c +17 -0
@@ -744,6 +744,7 @@ static void vhost_iommu_region_del(MemoryListener *listener, } } +static int vhost_virtqueue_set_addr (struct vhost_dev *dev,struct vhost_virtqueue *vq,unsigned idx,bool enable_log)
@@ -1661,6 +1662,11 @@ int vhost_dev_start(struct vhost_dev *hdev, VirtIODevice *vdev) } } + r =vhost_set_start (hdev, true); +if (r) { + goto fail_log; + } +if (vhost_dev_has_iommu (hdev)) { hdev->vhost_ops->vhost_set_iotlb_callback (hdev, true);
@@ -1697,6 +1703,8 @@ void vhost_dev_stop(struct vhost_dev *hdev, VirtIODevice *vdev)/* should only be called after backend is connected */ assert (hdev->vhost_ops); +vhost_set_start (hdev, false); +for (i =0 ; i < hdev->nvqs; ++i) { vhost_virtqueue_stop(hdev, vdev,
@@ -1722,3 +1730,12 @@ int vhost_net_set_backend(struct vhost_dev *hdev,return -1 ; } + +int vhost_set_start (struct vhost_dev *hdev,bool started) +{ + +if (hdev->vhost_ops->vhost_dev_start) { + hdev->vhost_ops->vhost_dev_start (hdev, started); + } +return 0 ; +}
include/hw/virtio/vhost.h +2 -0
@@ -92,6 +92,7 @@ struct vhost_dev {const VhostDevConfigOps *config_ops; }; +int vhost_dev_init (struct vhost_dev *hdev,void *opaque,VhostBackendType backend_type,uint32_t busyloop_timeout);
@@ -137,4 +138,5 @@ int vhost_dev_set_inflight(struct vhost_dev *dev, struct vhost_inflight *inflight);int vhost_dev_get_inflight (struct vhost_dev *dev,uint16_t queue_size,struct vhost_inflight *inflight); +int vhost_set_start (struct vhost_dev *dev,bool started);#endif
Signature · 1 line
2.21.1
Re: [PATCH v1 08/10] vhost: implement vhost_dev_start method
Quoted 1 line · Cindy Lu
use the
vhost_dev_startcallback to send the status to backend
I suggest to squash this into previous patch.
Quoted 20 lines
Signed-off-by Cindy Lu <[email protected]>--- hw/virtio/vhost.c | 17 +++++++++++++++++ include/hw/virtio/vhost.h | 2 ++ 2 files changed, 19 insertions(+)hw/virtio/vhost.c +1
-0@@ -744,6 +744,7 @@ static void vhost_iommu_region_del(MemoryListener *listener, } } +static int vhost_virtqueue_set_addr (struct vhost_dev *dev,struct vhost_virtqueue *vq,unsigned idx,bool enable_log)
hw/virtio/vhost.c int vhost_dev_start(struct vhost_dev *hdev, VirtIODevice *vdev) · line 1665
Quoted 4 lines
hw/virtio/vhost.c +1
-0@@ -1661,6 +1662,11 @@ int vhost_dev_start(struct vhost_dev *hdev, VirtIODevice *vdev) } } + r =vhost_set_start (hdev, true);
I think we need a better name for this function.
Quoted 42 lines
hw/virtio/vhost.c +15
-0+if (r) { + goto fail_log; + } +if (vhost_dev_has_iommu (hdev)) { hdev->vhost_ops->vhost_set_iotlb_callback (hdev, true);@@ -1697,6 +1703,8 @@ void vhost_dev_stop(struct vhost_dev *hdev, VirtIODevice *vdev)/* should only be called after backend is connected */ assert (hdev->vhost_ops); +vhost_set_start (hdev, false); +for (i =0 ; i < hdev->nvqs; ++i) { vhost_virtqueue_stop(hdev, vdev,@@ -1722,3 +1730,12 @@ int vhost_net_set_backend(struct vhost_dev *hdev,return -1 ; } + +int vhost_set_start (struct vhost_dev *hdev,bool started) +{ + +if (hdev->vhost_ops->vhost_dev_start) { + hdev->vhost_ops->vhost_dev_start (hdev, started); + } +return 0 ; +}include/hw/virtio/vhost.h +1
-0@@ -92,6 +92,7 @@ struct vhost_dev {const VhostDevConfigOps *config_ops; }; +int vhost_dev_init (struct vhost_dev *hdev,void *opaque,VhostBackendType backend_type,uint32_t busyloop_timeout);
include/hw/virtio/vhost.h int vhost_dev_set_inflight(struct vhost_dev *dev, · line 141
Quoted 4 lines
include/hw/virtio/vhost.h +1
-0@@ -137,4 +138,5 @@ int vhost_dev_set_inflight(struct vhost_dev *dev, struct vhost_inflight *inflight);int vhost_dev_get_inflight (struct vhost_dev *dev,uint16_t queue_size,struct vhost_inflight *inflight); +int vhost_set_start (struct vhost_dev *dev,bool started);
Any reason for exporting this? It looks to me there's no real user out this file.
Thanks
Quoted 1 line
include/hw/virtio/vhost.h +0
-0#endif
Re: [PATCH v1 08/10] vhost: implement vhost_dev_start method
Quoted 8 lines · Jason Wang
Quoted 1 line · Cindy Lu
use the
vhost_dev_startcallback to send the status to backendI suggest to squash this into previous patch.
Sure will do
Quoted 24 lines
Quoted 24 lines
Signed-off-by Cindy Lu <[email protected]>--- hw/virtio/vhost.c | 17 +++++++++++++++++ include/hw/virtio/vhost.h | 2 ++ 2 files changed, 19 insertions(+)hw/virtio/vhost.c +1
-0@@ -744,6 +744,7 @@ static void vhost_iommu_region_del(MemoryListener *listener, } } +static int vhost_virtqueue_set_addr (struct vhost_dev *dev,struct vhost_virtqueue *vq,unsigned idx,bool enable_log)@@ -1661,6 +1662,11 @@ int vhost_dev_start(struct vhost_dev *hdev, VirtIODevice *vdev) } }
Quoted 5 lines
hw/virtio/vhost.c int vhost_dev_start(struct vhost_dev *hdev, VirtIODevice *vdev) · line 1665
Quoted 1 line
hw/virtio/vhost.c +1
-0+ r =vhost_set_start (hdev, true);I think we need a better name for this function.
Shall we change it to vhost_set_device_start ? Since the vhost_dev_start was occupied by other function
Quoted 52 lines
Quoted 43 lines
hw/virtio/vhost.c +15
-0+if (r) { + goto fail_log; + } +if (vhost_dev_has_iommu (hdev)) { hdev->vhost_ops->vhost_set_iotlb_callback (hdev, true);@@ -1697,6 +1703,8 @@ void vhost_dev_stop(struct vhost_dev *hdev, VirtIODevice *vdev)/* should only be called after backend is connected */ assert (hdev->vhost_ops); +vhost_set_start (hdev, false); +for (i =0 ; i < hdev->nvqs; ++i) { vhost_virtqueue_stop(hdev, vdev,@@ -1722,3 +1730,12 @@ int vhost_net_set_backend(struct vhost_dev *hdev,return -1 ; } + +int vhost_set_start (struct vhost_dev *hdev,bool started) +{ + +if (hdev->vhost_ops->vhost_dev_start) { + hdev->vhost_ops->vhost_dev_start (hdev, started); + } +return 0 ; +}include/hw/virtio/vhost.h +1
-0@@ -92,6 +92,7 @@ struct vhost_dev {const VhostDevConfigOps *config_ops; }; +int vhost_dev_init (struct vhost_dev *hdev,void *opaque,VhostBackendType backend_type,uint32_t busyloop_timeout);include/hw/virtio/vhost.h int vhost_dev_set_inflight(struct vhost_dev *dev, · line 141
Quoted 4 lines
include/hw/virtio/vhost.h +1
-0@@ -137,4 +138,5 @@ int vhost_dev_set_inflight(struct vhost_dev *dev, struct vhost_inflight *inflight);int vhost_dev_get_inflight (struct vhost_dev *dev,uint16_t queue_size,struct vhost_inflight *inflight); +int vhost_set_start (struct vhost_dev *dev,bool started);Any reason for exporting this? It looks to me there's no real user out this file.
Quoted 2 lines
Thanks
Sure will fix this
Quoted 3 lines
Quoted 2 lines
include/hw/virtio/vhost.h +0
-0#endif
Re: [PATCH v1 08/10] vhost: implement vhost_dev_start method
Quoted 28 lines · Cindy Lu
Quoted 4 lines · Jason Wang
Quoted 1 line · Cindy Lu
use the
vhost_dev_startcallback to send the status to backendI suggest to squash this into previous patch.
Sure will do
Quoted 22 lines
Quoted 22 lines
Signed-off-by Cindy Lu<[email protected]>--- hw/virtio/vhost.c | 17 +++++++++++++++++ include/hw/virtio/vhost.h | 2 ++ 2 files changed, 19 insertions(+)hw/virtio/vhost.c +1
-0@@ -744,6 +744,7 @@ static void vhost_iommu_region_del(MemoryListener *listener, } } +static int vhost_virtqueue_set_addr (struct vhost_dev *dev,struct vhost_virtqueue *vq,unsigned idx,bool enable_log)@@ -1661,6 +1662,11 @@ int vhost_dev_start(struct vhost_dev *hdev, VirtIODevice *vdev) } }
Quoted 5 lines
Quoted 3 lines
hw/virtio/vhost.c int vhost_dev_start(struct vhost_dev *hdev, VirtIODevice *vdev) · line 1665
Quoted 1 line
hw/virtio/vhost.c +1
-0+ r =vhost_set_start (hdev, true);I think we need a better name for this function.
Shall we change it to
vhost_set_device_start? Since thevhost_dev_startwas occupied by other function
Or maybe just open code the vhost_set_start here since there's no other users.
Thanks
Re: [PATCH v1 08/10] vhost: implement vhost_dev_start method
Quoted 34 lines · Jason Wang
Quoted 31 lines · Cindy Lu
Quoted 4 lines · Jason Wang
Quoted 1 line · Cindy Lu
use the
vhost_dev_startcallback to send the status to backendI suggest to squash this into previous patch.
Sure will do
Quoted 25 lines
Quoted 19 lines
Signed-off-by Cindy Lu<[email protected]>--- hw/virtio/vhost.c | 17 +++++++++++++++++ include/hw/virtio/vhost.h | 2 ++ 2 files changed, 19 insertions(+)hw/virtio/vhost.c +1
-0@@ -744,6 +744,7 @@ static void vhost_iommu_region_del(MemoryListener *listener, } } +static int vhost_virtqueue_set_addr (struct vhost_dev *dev,struct vhost_virtqueue *vq,unsigned idx,bool enable_log)hw/virtio/vhost.c int vhost_dev_start(struct vhost_dev *hdev, VirtIODevice *vdev) · line 1665
Quoted 4 lines
hw/virtio/vhost.c +1
-0@@ -1661,6 +1662,11 @@ int vhost_dev_start(struct vhost_dev *hdev, VirtIODevice *vdev) } } + r =vhost_set_start (hdev, true);I think we need a better name for this function.
Quoted 9 lines
Quoted 2 lines
Shall we change it to
vhost_set_device_start? Since thevhost_dev_startwas occupied by other functionOr maybe just open code the
vhost_set_starthere since there's no other users.Thanks
Sure will do
Quoted 1 line
Re: [PATCH v1 08/10] vhost: implement vhost_dev_start method
In reply to Cindy LuQuoted 1 line · Cindy Lu
use the
vhost_dev_startcallback to send the status to backend
I agree with Jason, squash this patch with the previous one.
Quoted 19 lines
Signed-off-by Cindy Lu <[email protected]>--- hw/virtio/vhost.c | 17 +++++++++++++++++ include/hw/virtio/vhost.h | 2 ++ 2 files changed, 19 insertions(+)hw/virtio/vhost.c +1
-0@@ -744,6 +744,7 @@ static void vhost_iommu_region_del(MemoryListener *listener, } } +static int vhost_virtqueue_set_addr (struct vhost_dev *dev,struct vhost_virtqueue *vq,unsigned idx,bool enable_log)
hw/virtio/vhost.c int vhost_dev_start(struct vhost_dev *hdev, VirtIODevice *vdev) · line 1665
Quoted 4 lines
hw/virtio/vhost.c +1
-0@@ -1661,6 +1662,11 @@ int vhost_dev_start(struct vhost_dev *hdev, VirtIODevice *vdev) } } + r =vhost_set_start (hdev, true);
Perhaps you can use the same kind of name we have for the queue (queue_set_started()) and use something like vhost_dev_set_started()?
Quoted 17 lines
hw/virtio/vhost.c +6
-0+if (r) { + goto fail_log; + } +if (vhost_dev_has_iommu (hdev)) { hdev->vhost_ops->vhost_set_iotlb_callback (hdev, true);@@ -1697,6 +1703,8 @@ void vhost_dev_stop(struct vhost_dev *hdev, VirtIODevice *vdev)/* should only be called after backend is connected */ assert (hdev->vhost_ops); +vhost_set_start (hdev, false); +for (i =0 ; i < hdev->nvqs; ++i) { vhost_virtqueue_stop(hdev, vdev,
hw/virtio/vhost.c int vhost_net_set_backend(struct vhost_dev *hdev, · line 1738
Quoted 9 lines
hw/virtio/vhost.c +6
-0@@ -1722,3 +1730,12 @@ int vhost_net_set_backend(struct vhost_dev *hdev,return -1 ; } + +int vhost_set_start (struct vhost_dev *hdev,bool started) +{ + +if (hdev->vhost_ops->vhost_dev_start) { + hdev->vhost_ops->vhost_dev_start (hdev, started);
The "return" is missing.
And generally a function that only embeds a call to a hook has the same as the hook.
hw/virtio/vhost.c int vhost_net_set_backend(struct vhost_dev *hdev, · line 1741
Quoted 3 lines
hw/virtio/vhost.c +3
-0+ } +return 0 ; +}
so something like:
int vhost_dev_set_started(struct vhost_dev *hdev, bool started)
{
if (hdev->vhost_ops->dev_set_started) {
return hdev->vhost_ops->dev_set_started(hdev, started);
}
return 0;
}Quoted 13 lines
include/hw/virtio/vhost.h +1
-0@@ -92,6 +92,7 @@ struct vhost_dev {const VhostDevConfigOps *config_ops; }; +int vhost_dev_init (struct vhost_dev *hdev,void *opaque,VhostBackendType backend_type,uint32_t busyloop_timeout);
include/hw/virtio/vhost.h int vhost_dev_set_inflight(struct vhost_dev *dev, · line 141
Quoted 4 lines
include/hw/virtio/vhost.h +1
-0@@ -137,4 +138,5 @@ int vhost_dev_set_inflight(struct vhost_dev *dev, struct vhost_inflight *inflight);int vhost_dev_get_inflight (struct vhost_dev *dev,uint16_t queue_size,struct vhost_inflight *inflight); +int vhost_set_start (struct vhost_dev *dev,bool started);
There is no need to export it, so set it "static" in hw/virtio/vhost.c and move the definition before the use.
Thanks,
Laurent
Re: [PATCH v1 08/10] vhost: implement vhost_dev_start method
Quoted 6 lines · Laurent Vivier
Quoted 1 line · Cindy Lu
use the
vhost_dev_startcallback to send the status to backendI agree with Jason, squash this patch with the previous one.
will fix this
Quoted 22 lines
Quoted 22 lines
Signed-off-by Cindy Lu <[email protected]>--- hw/virtio/vhost.c | 17 +++++++++++++++++ include/hw/virtio/vhost.h | 2 ++ 2 files changed, 19 insertions(+)hw/virtio/vhost.c +1
-0@@ -744,6 +744,7 @@ static void vhost_iommu_region_del(MemoryListener *listener, } } +static int vhost_virtqueue_set_addr (struct vhost_dev *dev,struct vhost_virtqueue *vq,unsigned idx,bool enable_log)@@ -1661,6 +1662,11 @@ int vhost_dev_start(struct vhost_dev *hdev, VirtIODevice *vdev) } }
Quoted 5 lines
hw/virtio/vhost.c int vhost_dev_start(struct vhost_dev *hdev, VirtIODevice *vdev) · line 1665
Quoted 1 line
hw/virtio/vhost.c +1
-0+ r =vhost_set_start (hdev, true);Perhaps you can use the same kind of name we have for the queue (
queue_set_started()) and use something likevhost_dev_set_started()?
sure, will fix this
Quoted 38 lines
Quoted 17 lines
hw/virtio/vhost.c +6
-0+if (r) { + goto fail_log; + } +if (vhost_dev_has_iommu (hdev)) { hdev->vhost_ops->vhost_set_iotlb_callback (hdev, true);@@ -1697,6 +1703,8 @@ void vhost_dev_stop(struct vhost_dev *hdev, VirtIODevice *vdev)/* should only be called after backend is connected */ assert (hdev->vhost_ops); +vhost_set_start (hdev, false); +for (i =0 ; i < hdev->nvqs; ++i) { vhost_virtqueue_stop(hdev, vdev,hw/virtio/vhost.c int vhost_net_set_backend(struct vhost_dev *hdev, · line 1738
Quoted 9 lines
hw/virtio/vhost.c +6
-0@@ -1722,3 +1730,12 @@ int vhost_net_set_backend(struct vhost_dev *hdev,return -1 ; } + +int vhost_set_start (struct vhost_dev *hdev,bool started) +{ + +if (hdev->vhost_ops->vhost_dev_start) { + hdev->vhost_ops->vhost_dev_start (hdev, started);The "return" is missing.
And generally a function that only embeds a call to a hook has the same as the hook.
hw/virtio/vhost.c int vhost_net_set_backend(struct vhost_dev *hdev, · line 1741
Quoted 3 lines
hw/virtio/vhost.c +3
-0+ } +return 0 ; +}so something like:
Quoted 9 lines
int vhost_dev_set_started(struct vhost_dev *hdev, bool started)
{
if (hdev->vhost_ops->dev_set_started) {
return hdev->vhost_ops->dev_set_started(hdev, started);
}
return 0;
}thanks will fix this
Quoted 8 lines
Quoted 8 lines
include/hw/virtio/vhost.h +0
-0@@ -92,6 +92,7 @@ struct vhost_dev {const VhostDevConfigOps *config_ops; };
Quoted 13 lines
include/hw/virtio/vhost.h int vhost_dev_set_inflight(struct vhost_dev *dev, · line 141
Quoted 9 lines
include/hw/virtio/vhost.h +2
-0+int vhost_dev_init (struct vhost_dev *hdev,void *opaque,VhostBackendType backend_type,uint32_t busyloop_timeout);@@ -137,4 +138,5 @@ int vhost_dev_set_inflight(struct vhost_dev *dev, struct vhost_inflight *inflight);int vhost_dev_get_inflight (struct vhost_dev *dev,uint16_t queue_size,struct vhost_inflight *inflight); +int vhost_set_start (struct vhost_dev *dev,bool started);There is no need to export it, so set it "static" in
hw/virtio/vhost.cand move the definition before the use.
thanks will fix this
Quoted 3 lines
Thanks,
Laurent
PATCH 9/10 vhost-vdpa: introduce vhost-vdpa backend
In reply to Cindy LuCurrently we have 2 types of vhost backends in QEMU: vhost kernel and vhost-user. The above patch provides a generic device for vDPA purpose, this vDPA device exposes to user space a non-vendor-specific configuration interface for setting up a vhost HW accelerator, this patch set introduces a third vhost backend called vhost-vdpa based on the vDPA interface.
Vhost-vdpa usage:
qemu-system-x86_64 -cpu host -enable-kvm \
......
-netdev type=vhost-vdpa,vhostdev=/dev/vhost-vdpa-id,id=vhost-vdpa0 \
-device virtio-net-pci,netdev=vhost-vdpa0,page-per-vq=on \--- configure | 21 ++ hw/net/vhost_net.c | 19 +- hw/net/virtio-net.c | 19 +- hw/virtio/Makefile.objs | 1 + hw/virtio/vhost-backend.c | 22 +- hw/virtio/vhost-vdpa.c | 406 ++++++++++++++++++++++++++++++ hw/virtio/vhost.c | 42 +++- include/hw/virtio/vhost-backend.h | 6 +- include/hw/virtio/vhost-vdpa.h | 26 ++ include/hw/virtio/vhost.h | 6 + qemu-options.hx | 12 + 11 files changed, 555 insertions(+), 25 deletions(-) create mode 100644 hw/virtio/vhost-vdpa.c create mode 100644 include/hw/virtio/vhost-vdpa.h
configure +21 -0
@@ -1557,6 +1557,10 @@ for opt do ;; --enable-vhost-user) vhost_user="yes" ;; + --disable-vhost-vdpa) vhost_vdpa="no" + ;; + --enable-vhost-vdpa) vhost_vdpa="yes" + ;; --disable-vhost-kernel) vhost_kernel="no" ;; --enable-vhost-kernel) vhost_kernel="yes"
@@ -1846,6 +1850,7 @@ disabled with --disable-FEATURE, default is enabled if available: vhost-crypto vhost-user-crypto backend support vhost-kernel vhost kernel backend support vhost-user vhost-user backend support + vhost-vdpa vhost-vdpa kernel backend support spice spice rbd rados block device (rbd) libiscsi iscsi support
@@ -2336,6 +2341,10 @@ test "$vhost_user" = "" && vhost_user=yes if test "$vhost_user" = "yes" && test "$mingw32" = "yes"; then error_exit "vhost-user isn't available on win32" fi +test "$vhost_vdpa" = "" && vhost_vdpa=$linux +if test "$vhost_vdpa" = "yes" && test "$linux" != "yes"; then + error_exit "vhost-vdpa is only available on Linux" +fi test "$vhost_kernel" = "" && vhost_kernel=$linux if test "$vhost_kernel" = "yes" && test "$linux" != "yes"; then error_exit "vhost-kernel is only available on Linux"
@@ -2364,6 +2373,11 @@ test "$vhost_user_fs" = "" && vhost_user_fs=$vhost_user if test "$vhost_user_fs" = "yes" && test "$vhost_user" = "no"; then error_exit "--enable-vhost-user-fs requires --enable-vhost-user" fi +#vhost-vdpa backends +test "$vhost_net_vdpa" = "" && vhost_net_vdpa=$vhost_vdpa +if test "$vhost_net_vdpa" = "yes" && test "$vhost_vdpa" = "no"; then + error_exit "--enable-vhost-net-vdpa requires --enable-vhost-vdpa" +fi # OR the vhost-kernel and vhost-user values for simplicity if test "$vhost_net" = ""; then
@@ -6673,6 +6687,7 @@ echo "vhost-scsi support $vhost_scsi" echo "vhost-vsock support $vhost_vsock" echo "vhost-user support $vhost_user" echo "vhost-user-fs support $vhost_user_fs" +echo "vhost-vdpa support $vhost_vdpa" echo "Trace backends $trace_backends" if have_backend "simple"; then echo "Trace output file $trace_file-<pid>"
@@ -7170,6 +7185,9 @@ fi if test "$vhost_net_user" = "yes" ; then echo "CONFIG_VHOST_NET_USER=y" >> $config_host_mak fi +if test "$vhost_net_vdpa" = "yes" ; then + echo "CONFIG_VHOST_NET_VDPA=y" >> $config_host_mak +fi if test "$vhost_crypto" = "yes" ; then echo "CONFIG_VHOST_CRYPTO=y" >> $config_host_mak fi
@@ -7182,6 +7200,9 @@ fi if test "$vhost_user" = "yes" ; then echo "CONFIG_VHOST_USER=y" >> $config_host_mak fi +if test "$vhost_vdpa" = "yes" ; then + echo "CONFIG_VHOST_VDPA=y" >> $config_host_mak +fi if test "$vhost_user_fs" = "yes" ; then echo "CONFIG_VHOST_USER_FS=y" >> $config_host_mak fi
hw/net/vhost_net.c +12 -7
@@ -17,8 +17,10 @@#include "net/net.h" #include "net/tap.h" #include "net/vhost-user.h" +#include "net/vhost-vdpa.h" #include "standard-headers/linux/vhost_types.h" +#include "linux-headers/linux/vhost.h" #include "hw/virtio/virtio-net.h" #include "net/vhost_net.h" #include "qemu/error-report.h"
@@ -33,12 +35,6 @@#include "hw/virtio/vhost.h" #include "hw/virtio/virtio-bus.h" -struct vhost_net { -struct vhost_dev dev; -struct vhost_virtqueue vqs[2 ]; -int backend; -NetClientState *nc; -};/* Features supported by host kernel. */ static const int kernel_feature_bits[] = {
@@ -84,7 +80,6 @@ static const int user_feature_bits[] = { VHOST_INVALID_FEATURE_BIT }; -static const int *vhost_net_get_feature_bits (struct vhost_net *net) {const int *feature_bits =0 ;
@@ -96,6 +91,9 @@ static const int *vhost_net_get_feature_bits(struct vhost_net *net)case NET_CLIENT_DRIVER_VHOST_USER : feature_bits = user_feature_bits;break ; +case NET_CLIENT_DRIVER_VHOST_VDPA : + feature_bits = vdpa_feature_bits; +break ;default :error_report ("Feature bits not defined for this type: %d" , net->nc->info->type);
@@ -348,6 +346,7 @@ int vhost_net_start(VirtIODevice *dev, NetClientState *ncs, }for (i =0 ; i < total_queues; i++) { + peer =qemu_get_peer (ncs, i); r =vhost_net_start_one (get_vhost_net (peer), dev);
@@ -444,6 +443,12 @@ VHostNetState *get_vhost_net(NetClientState *nc) vhost_net =vhost_user_get_vhost_net (nc);assert (vhost_net);break ; +#endif +#ifdef CONFIG_VHOST_NET_VDPA +case NET_CLIENT_DRIVER_VHOST_VDPA : + vhost_net =vhost_vdpa_get_vhost_net (nc); +assert (vhost_net); +break ;#endif default :break ;
hw/net/virtio-net.c +17 -2
@@ -42,6 +42,7 @@#include "trace.h" #include "monitor/qdev.h" #include "hw/pci/pci.h" +#include "hw/virtio/vhost.h" #define VIRTIO_NET_VM_VERSION 11
@@ -131,6 +132,8 @@ static void virtio_net_get_config(VirtIODevice *vdev, uint8_t *config) {VirtIONet *n =VIRTIO_NET (vdev);struct virtio_net_config netcfg; +int ret =0 ; +memset (&netcfg,0 ,sizeof (struct virtio_net_config ));virtio_stw_p (vdev, &netcfg.status, n->status);virtio_stw_p (vdev, &netcfg.max_virtqueue_pairs, n->max_queues);
@@ -139,13 +142,21 @@ static void virtio_net_get_config(VirtIODevice *vdev, uint8_t *config)virtio_stl_p (vdev, &netcfg.speed, n->net_conf.speed); netcfg.duplex = n->net_conf.duplex;memcpy (config, &netcfg, n->config_size); +NetClientState *nc =qemu_get_queue (n->nic); +if (nc->peer->info->type ==NET_CLIENT_DRIVER_VHOST_VDPA ) { + ret =vhost_net_get_config (get_vhost_net (nc->peer), (uint8_t *)&netcfg, + n->config_size); +if (ret !=-1 ) { +memcpy (config, &netcfg, n->config_size); + } + } }static void virtio_net_set_config (VirtIODevice *vdev,const uint8_t *config) {VirtIONet *n =VIRTIO_NET (vdev); +NetClientState *nc =qemu_get_queue (n->nic);struct virtio_net_config netcfg = {}; -memcpy (&netcfg, config, n->config_size); if (!virtio_vdev_has_feature(vdev, VIRTIO_NET_F_CTRL_MAC_ADDR) &&
@@ -154,6 +165,11 @@ static void virtio_net_set_config(VirtIODevice *vdev, const uint8_t *config)memcpy (n->mac, netcfg.mac,ETH_ALEN );qemu_format_nic_info_str (qemu_get_queue (n->nic), n->mac); } +if (nc->peer->info->type ==NET_CLIENT_DRIVER_VHOST_VDPA ) { +vhost_net_set_config (get_vhost_net (nc->peer), (uint8_t *)&netcfg, +0 , n->config_size, +VHOST_SET_CONFIG_TYPE_MASTER ); + } }static bool virtio_net_started (VirtIONet *n,uint8_t status)
@@ -2958,7 +2974,6 @@ static void virtio_net_device_realize(DeviceState *dev, Error **errp) }else if (n->net_conf.speed >=0 ) { n->host_features |= (1ULL <<VIRTIO_NET_F_SPEED_DUPLEX ); } -if (n->failover) { n->primary_listener.should_be_hidden = virtio_net_primary_should_be_hidden;
hw/virtio/Makefile.objs +1 -0
@@ -5,6 +5,7 @@ obj-y += virtio.o obj-$(CONFIG_VHOST) += vhost.o vhost-backend.o common-obj-$(call lnot,$(CONFIG_VHOST)) += vhost-stub.o obj-$(CONFIG_VHOST_USER) += vhost-user.o +obj-$(CONFIG_VHOST_VDPA) += vhost-vdpa.o common-obj-$(CONFIG_VIRTIO_RNG) += virtio-rng.o common-obj-$(CONFIG_VIRTIO_PCI) += virtio-pci.o
hw/virtio/vhost-backend.c +18 -4
@@ -14,7 +14,7 @@#include "qemu/error-report.h" #include "qemu/main-loop.h" #include "standard-headers/linux/vhost_types.h" - +#include "hw/virtio/vhost-vdpa.h" #ifdef CONFIG_VHOST_KERNEL #include <linux/vhost.h> #include <sys/ioctl.h>
@@ -22,10 +22,19 @@static int vhost_kernel_call (struct vhost_dev *dev,unsigned long int request,void *arg) { -int fd = (uintptr_t ) dev->opaque; - -assert (dev->vhost_ops->backend_type ==VHOST_BACKEND_TYPE_KERNEL ); +int fd =-1 ; +switch (dev->vhost_ops->backend_type) { +case VHOST_BACKEND_TYPE_KERNEL : + fd = (uintptr_t )dev->opaque; +break ; +case VHOST_BACKEND_TYPE_VDPA : + fd = ((struct vhost_vdpa *)dev->opaque)->device_fd; +break ; +default : +g_assert_not_reached (); + } +assert (fd !=-1 );return ioctl (fd, request, arg); }
@@ -285,6 +294,11 @@ int vhost_set_backend_type(struct vhost_dev *dev, VhostBackendType backend_type)case VHOST_BACKEND_TYPE_USER : dev->vhost_ops = &user_ops;break ; +#endif +#ifdef CONFIG_VHOST_VDPA +case VHOST_BACKEND_TYPE_VDPA : + dev->vhost_ops = &vdpa_ops; +break ;#endif default :error_report ("Unknown vhost backend type" );
hw/virtio/vhost-vdpa.c new file +406 -0
406 lines not on this page · raw message
hw/virtio/vhost.c +31 -11
71 lines not on this page · raw message
include/hw/virtio/vhost-backend.h +5 -1
@@ -17,7 +17,8 @@ typedef enum VhostBackendType {VHOST_BACKEND_TYPE_NONE =0 ,VHOST_BACKEND_TYPE_KERNEL =1 ,VHOST_BACKEND_TYPE_USER =2 , -VHOST_BACKEND_TYPE_MAX =3 , +VHOST_BACKEND_TYPE_VDPA =3 , +VHOST_BACKEND_TYPE_MAX =4 , } VhostBackendType; typedef enum VhostSetConfigType {
@@ -113,6 +114,7 @@ typedef int (*vhost_set_inflight_fd_op)(struct vhost_dev *dev, struct vhost_inflight *inflight);typedef int (*vhost_dev_start_op )(struct vhost_dev *dev,bool started); +typedef int (*vhost_get_device_id_op )(struct vhost_dev *dev,uint32_t *dev_id); typedef struct VhostOps { VhostBackendType backend_type; vhost_backend_init vhost_backend_init;
@@ -154,9 +156,11 @@ typedef struct VhostOps {vhost_get_inflight_fd_op vhost_get_inflight_fd;vhost_set_inflight_fd_op vhost_set_inflight_fd;vhost_dev_start_op vhost_dev_start; +vhost_get_device_id_op vhost_get_device_id; } VhostOps;extern const VhostOps user_ops; +extern const VhostOps vdpa_ops;int vhost_set_backend_type (struct vhost_dev *dev,VhostBackendType backend_type);
include/hw/virtio/vhost-vdpa.h new file +26 -0
@@ -0,0 +1,26 @@ +/* +* vhost-vdpa.h +* +* Copyright(c) 2017-2018 Intel Corporation. +* Copyright(c) 2020 Red Hat, Inc. +* +* This work is licensed under the terms of the GNU GPL, version 2 or later. +* See the COPYING file in the top-level directory. +* +*/ + +#ifndef HW_VIRTIO_VHOST_VDPA_H +#define HW_VIRTIO_VHOST_VDPA_H + +#include "hw/virtio/virtio.h" + +typedef struct vhost_vdpa { +int device_fd; +uint32_t msg_type; +MemoryListener listener; +}VhostVDPA ; + +extern AddressSpace address_space_memory; +extern int vhost_vdpa_get_device_id (struct vhost_dev *dev, +uint32_t *device_id); +#endif
include/hw/virtio/vhost.h +6 -0
@@ -92,6 +92,12 @@ struct vhost_dev {const VhostDevConfigOps *config_ops; }; +struct vhost_net { +struct vhost_dev dev; +struct vhost_virtqueue vqs[2 ]; +int backend; +NetClientState *nc; +}; int vhost_dev_init(struct vhost_dev *hdev, void *opaque, VhostBackendType backend_type,
qemu-options.hx +12 -0
@@ -2409,6 +2409,10 @@ DEF("netdev", HAS_ARG, QEMU_OPTION_netdev, #ifdef CONFIG_POSIX "-netdev vhost-user,id=str,chardev=dev[,vhostforce=on|off]\n" " configure a vhost-user network, backed by a chardev 'dev'\n" +#endif +#ifdef __linux__ + "-netdev vhost-vdpa,id=str,vhostdev=/path/to/dev\n" + " configure a vhost-vdpa network,Establish a vhost-vdpa netdev\n" #endif "-netdev hubport,id=str,hubid=n[,netdev=nd]\n" " configure a hub port on the hub with ID 'n'\n", QEMU_ARCH_ALL)
@@ -2888,6 +2892,14 @@ SRST -netdev type=vhost-user,id=net0,chardev=chr0 \ -device virtio-net-pci,netdev=net0 +``-netdev vhost-vdpa,vhostdev=/path/to/dev`` + Establish a vhost-vdpa netdev. + + vDPA device is a device that uses a datapath which complies with + the virtio specifications with a vendor specific control path. + vDPA devices can be both physically located on the hardware or + emulated by software. + ``-netdev hubport,id=id,hubid=hubid[,netdev=nd]`` Create a hub port on the emulated hub with ID hubid.
Signature · 1 line
2.21.1
Re: [PATCH v1 09/10] vhost-vdpa: introduce vhost-vdpa backend
Quoted 135 lines · Cindy Lu
Currently we have 2 types of vhost backends in QEMU: vhost kernel and vhost-user. The above patch provides a generic device for vDPA purpose, this vDPA device exposes to user space a non-vendor-specific configuration interface for setting up a vhost HW accelerator, this patch set introduces a third vhost backend called vhost-vdpa based on the vDPA interface.
Vhost-vdpa usage:
qemu-system-x86_64 -cpu host -enable-kvm \ ...... -netdev type=vhost-vdpa,vhostdev=/dev/vhost-vdpa-id,id=vhost-vdpa0 \ -device virtio-net-pci,netdev=vhost-vdpa0,page-per-vq=on \Signed-off-by Lingshan zhu <[email protected]>Signed-off-by Tiwei Bie <[email protected]>Signed-off-by Cindy Lu <[email protected]>--- configure | 21 ++ hw/net/vhost_net.c | 19 +- hw/net/virtio-net.c | 19 +- hw/virtio/Makefile.objs | 1 + hw/virtio/vhost-backend.c | 22 +- hw/virtio/vhost-vdpa.c | 406 ++++++++++++++++++++++++++++++ hw/virtio/vhost.c | 42 +++- include/hw/virtio/vhost-backend.h | 6 +- include/hw/virtio/vhost-vdpa.h | 26 ++ include/hw/virtio/vhost.h | 6 + qemu-options.hx | 12 + 11 files changed, 555 insertions(+), 25 deletions(-)create mode 100644
hw/virtio/vhost-vdpa.ccreate mode 100644include/hw/virtio/vhost-vdpa.hconfigure +21
-0@@ -1557,6 +1557,10 @@ for opt do ;; --enable-vhost-user) vhost_user="yes" ;; + --disable-vhost-vdpa) vhost_vdpa="no" + ;; + --enable-vhost-vdpa) vhost_vdpa="yes" + ;; --disable-vhost-kernel) vhost_kernel="no" ;; --enable-vhost-kernel) vhost_kernel="yes"@@ -1846,6 +1850,7 @@ disabled with --disable-FEATURE, default is enabled if available: vhost-crypto vhost-user-crypto backend support vhost-kernel vhost kernel backend support vhost-user vhost-user backend support + vhost-vdpa vhost-vdpa kernel backend support spice spice rbd rados block device (rbd) libiscsi iscsi support@@ -2336,6 +2341,10 @@ test "$vhost_user" = "" && vhost_user=yes if test "$vhost_user" = "yes" && test "$mingw32" = "yes"; then error_exit "vhost-user isn't available on win32" fi +test "$vhost_vdpa" = "" && vhost_vdpa=$linux +if test "$vhost_vdpa" = "yes" && test "$linux" != "yes"; then + error_exit "vhost-vdpa is only available on Linux" +fi test "$vhost_kernel" = "" && vhost_kernel=$linux if test "$vhost_kernel" = "yes" && test "$linux" != "yes"; then error_exit "vhost-kernel is only available on Linux"@@ -2364,6 +2373,11 @@ test "$vhost_user_fs" = "" && vhost_user_fs=$vhost_user if test "$vhost_user_fs" = "yes" && test "$vhost_user" = "no"; then error_exit "--enable-vhost-user-fs requires --enable-vhost-user" fi +#vhost-vdpa backends +test "$vhost_net_vdpa" = "" && vhost_net_vdpa=$vhost_vdpa +if test "$vhost_net_vdpa" = "yes" && test "$vhost_vdpa" = "no"; then + error_exit "--enable-vhost-net-vdpa requires --enable-vhost-vdpa" +fi # OR the vhost-kernel and vhost-user values for simplicity if test "$vhost_net" = ""; then@@ -6673,6 +6687,7 @@ echo "vhost-scsi support $vhost_scsi" echo "vhost-vsock support $vhost_vsock" echo "vhost-user support $vhost_user" echo "vhost-user-fs support $vhost_user_fs" +echo "vhost-vdpa support $vhost_vdpa" echo "Trace backends $trace_backends" if have_backend "simple"; then echo "Trace output file $trace_file-<pid>"@@ -7170,6 +7185,9 @@ fi if test "$vhost_net_user" = "yes" ; then echo "CONFIG_VHOST_NET_USER=y" >> $config_host_mak fi +if test "$vhost_net_vdpa" = "yes" ; then + echo "CONFIG_VHOST_NET_VDPA=y" >> $config_host_mak +fi if test "$vhost_crypto" = "yes" ; then echo "CONFIG_VHOST_CRYPTO=y" >> $config_host_mak fi@@ -7182,6 +7200,9 @@ fi if test "$vhost_user" = "yes" ; then echo "CONFIG_VHOST_USER=y" >> $config_host_mak fi +if test "$vhost_vdpa" = "yes" ; then + echo "CONFIG_VHOST_VDPA=y" >> $config_host_mak +fi if test "$vhost_user_fs" = "yes" ; then echo "CONFIG_VHOST_USER_FS=y" >> $config_host_mak fihw/net/vhost_net.c +2
-6@@ -17,8 +17,10 @@#include "net/net.h" #include "net/tap.h" #include "net/vhost-user.h" +#include "net/vhost-vdpa.h" #include "standard-headers/linux/vhost_types.h" +#include "linux-headers/linux/vhost.h" #include "hw/virtio/virtio-net.h" #include "net/vhost_net.h" #include "qemu/error-report.h" @@ -33,12 +35,6 @@#include "hw/virtio/vhost.h" #include "hw/virtio/virtio-bus.h" -struct vhost_net { -struct vhost_dev dev; -struct vhost_virtqueue vqs[2 ]; -int backend; -NetClientState *nc; -};/* Features supported by host kernel. */ static const int kernel_feature_bits[] = {
hw/net/vhost_net.c static const int user_feature_bits[] = { · line 87
Quoted 4 lines
hw/net/vhost_net.c +0
-1@@ -84,7 +80,6 @@ static const int user_feature_bits[] = { VHOST_INVALID_FEATURE_BIT }; -
Unnecessary change.
Quoted 14 lines
hw/net/vhost_net.c +3
-0static const int *vhost_net_get_feature_bits (struct vhost_net *net) {const int *feature_bits =0 ;@@ -96,6 +91,9 @@ static const int *vhost_net_get_feature_bits(struct vhost_net *net)case NET_CLIENT_DRIVER_VHOST_USER : feature_bits = user_feature_bits;break ; +case NET_CLIENT_DRIVER_VHOST_VDPA : + feature_bits = vdpa_feature_bits; +break ;default :error_report ("Feature bits not defined for this type: %d" , net->nc->info->type);
hw/net/vhost_net.c int vhost_net_start(VirtIODevice *dev, NetClientState *ncs, · line 349
Quoted 4 lines
hw/net/vhost_net.c +1
-0@@ -348,6 +346,7 @@ int vhost_net_start(VirtIODevice *dev, NetClientState *ncs, }for (i =0 ; i < total_queues; i++) { +
Unnecessary change.
Quoted 39 lines
hw/net/vhost_net.c +6
-0peer =qemu_get_peer (ncs, i); r =vhost_net_start_one (get_vhost_net (peer), dev);@@ -444,6 +443,12 @@ VHostNetState *get_vhost_net(NetClientState *nc) vhost_net =vhost_user_get_vhost_net (nc);assert (vhost_net);break ; +#endif +#ifdef CONFIG_VHOST_NET_VDPA +case NET_CLIENT_DRIVER_VHOST_VDPA : + vhost_net =vhost_vdpa_get_vhost_net (nc); +assert (vhost_net); +break ;#endif default :break ;hw/net/virtio-net.c +3
-0@@ -42,6 +42,7 @@#include "trace.h" #include "monitor/qdev.h" #include "hw/pci/pci.h" +#include "hw/virtio/vhost.h" #define VIRTIO_NET_VM_VERSION 11@@ -131,6 +132,8 @@ static void virtio_net_get_config(VirtIODevice *vdev, uint8_t *config) {VirtIONet *n =VIRTIO_NET (vdev);struct virtio_net_config netcfg; +int ret =0 ; +memset (&netcfg,0 ,sizeof (struct virtio_net_config ));virtio_stw_p (vdev, &netcfg.status, n->status);virtio_stw_p (vdev, &netcfg.max_virtqueue_pairs, n->max_queues);@@ -139,13 +142,21 @@ static void virtio_net_get_config(VirtIODevice *vdev, uint8_t *config)virtio_stl_p (vdev, &netcfg.speed, n->net_conf.speed);
hw/net/virtio-net.c static void virtio_net_get_config(VirtIODevice *vdev, uint8_t *config) · line 152
Quoted 10 lines
hw/net/virtio-net.c +8
-0netcfg.duplex = n->net_conf.duplex;memcpy (config, &netcfg, n->config_size); +NetClientState *nc =qemu_get_queue (n->nic); +if (nc->peer->info->type ==NET_CLIENT_DRIVER_VHOST_VDPA ) { + ret =vhost_net_get_config (get_vhost_net (nc->peer), (uint8_t *)&netcfg, + n->config_size); +if (ret !=-1 ) { +memcpy (config, &netcfg, n->config_size); + } + }
This is kind of sub-optimal.
I think the a better approach is deal all the stuffs inside vhost_net_get_config().
hw/net/virtio-net.c static void virtio_net_get_config(VirtIODevice *vdev, uint8_t *config) · line 148
Quoted 8 lines
hw/net/virtio-net.c +1
-1}static void virtio_net_set_config (VirtIODevice *vdev,const uint8_t *config) {VirtIONet *n =VIRTIO_NET (vdev); +NetClientState *nc =qemu_get_queue (n->nic);struct virtio_net_config netcfg = {}; -
Unnecessary change.
hw/net/virtio-net.c static void virtio_net_set_config(VirtIODevice *vdev, const uint8_t *config) · line 172
Quoted 12 lines
hw/net/virtio-net.c +5
-0memcpy (&netcfg, config, n->config_size); if (!virtio_vdev_has_feature(vdev, VIRTIO_NET_F_CTRL_MAC_ADDR) &&@@ -154,6 +165,11 @@ static void virtio_net_set_config(VirtIODevice *vdev, const uint8_t *config)memcpy (n->mac, netcfg.mac,ETH_ALEN );qemu_format_nic_info_str (qemu_get_queue (n->nic), n->mac); } +if (nc->peer->info->type ==NET_CLIENT_DRIVER_VHOST_VDPA ) { +vhost_net_set_config (get_vhost_net (nc->peer), (uint8_t *)&netcfg, +0 , n->config_size, +VHOST_SET_CONFIG_TYPE_MASTER ); + }
Similar issues as get_config.
hw/net/virtio-net.c static void virtio_net_device_realize(DeviceState *dev, Error **errp) · line 2961
Quoted 8 lines
hw/net/virtio-net.c +0
-1}static bool virtio_net_started (VirtIONet *n,uint8_t status)@@ -2958,7 +2974,6 @@ static void virtio_net_device_realize(DeviceState *dev, Error **errp) }else if (n->net_conf.speed >=0 ) { n->host_features |= (1ULL <<VIRTIO_NET_F_SPEED_DUPLEX ); } -
Unnecessary change.
Quoted 93 lines
hw/net/virtio-net.c +0
-0if (n->failover) { n->primary_listener.should_be_hidden = virtio_net_primary_should_be_hidden;hw/virtio/Makefile.objs +1
-0@@ -5,6 +5,7 @@ obj-y += virtio.o obj-$(CONFIG_VHOST) += vhost.o vhost-backend.o common-obj-$(call lnot,$(CONFIG_VHOST)) += vhost-stub.o obj-$(CONFIG_VHOST_USER) += vhost-user.o +obj-$(CONFIG_VHOST_VDPA) += vhost-vdpa.o common-obj-$(CONFIG_VIRTIO_RNG) += virtio-rng.o common-obj-$(CONFIG_VIRTIO_PCI) += virtio-pci.ohw/virtio/vhost-backend.c +18
-4@@ -14,7 +14,7 @@#include "qemu/error-report.h" #include "qemu/main-loop.h" #include "standard-headers/linux/vhost_types.h" - +#include "hw/virtio/vhost-vdpa.h" #ifdef CONFIG_VHOST_KERNEL #include <linux/vhost.h> #include <sys/ioctl.h> @@ -22,10 +22,19 @@static int vhost_kernel_call (struct vhost_dev *dev,unsigned long int request,void *arg) { -int fd = (uintptr_t ) dev->opaque; - -assert (dev->vhost_ops->backend_type ==VHOST_BACKEND_TYPE_KERNEL ); +int fd =-1 ; +switch (dev->vhost_ops->backend_type) { +case VHOST_BACKEND_TYPE_KERNEL : + fd = (uintptr_t )dev->opaque; +break ; +case VHOST_BACKEND_TYPE_VDPA : + fd = ((struct vhost_vdpa *)dev->opaque)->device_fd; +break ; +default : +g_assert_not_reached (); + } +assert (fd !=-1 );return ioctl (fd, request, arg); }@@ -285,6 +294,11 @@ int vhost_set_backend_type(struct vhost_dev *dev, VhostBackendType backend_type)case VHOST_BACKEND_TYPE_USER : dev->vhost_ops = &user_ops;break ; +#endif +#ifdef CONFIG_VHOST_VDPA +case VHOST_BACKEND_TYPE_VDPA : + dev->vhost_ops = &vdpa_ops; +break ;#endif default :error_report ("Unknown vhost backend type" );hw/virtio/vhost-vdpa.c new file +24
-0@@ -0,0 +1,406 @@ +/* +* vhost-vdpa +* +* Copyright(c) 2017-2018 Intel Corporation. +* Copyright(c) 2020 Red Hat, Inc. +* +* This work is licensed under the terms of the GNU GPL, version 2 or later. +* See the COPYING file in the top-level directory. +* +*/ + +#include "qemu/osdep.h" +#include <linux/vhost.h> +#include <linux/vfio.h> +#include <sys/eventfd.h> +#include <sys/ioctl.h> +#include "hw/virtio/vhost.h" +#include "hw/virtio/vhost-backend.h" +#include "hw/virtio/virtio-net.h" +#include "hw/virtio/vhost-vdpa.h" +#include "qemu/main-loop.h" +#include <linux/kvm.h> +#include "sysemu/kvm.h" +
hw/virtio/vhost-vdpa.c line 34
Quoted 10 lines
hw/virtio/vhost-vdpa.c new file +10
-0+ +static bool vhost_vdpa_listener_skipped_section (MemoryRegionSection *section) +{ +return (!memory_region_is_ram (section->mr) && + !memory_region_is_iommu (section->mr)) || +/* +* Sizing an enabled 64-bit BAR can cause spurious mappings to +* addresses in the upper part of the 64-bit address space. These +* are never accessed by the CPU and beyond the address width of +* some IOMMU hardware. TODO: VDPA should tell us the IOMMU width.
Note that, I post patches for reporting IOVA range, we need add the check through that in the future.
Quoted 314 lines
hw/virtio/vhost-vdpa.c new file +314
-0+*/ + section->offset_within_address_space & (1ULL <<63 ); +} + +static int vhost_vdpa_dma_map (struct vhost_vdpa *v,hwaddr iova,hwaddr size, +void *vaddr,bool readonly) +{ +struct vhost_msg_v2 msg; +int fd = v->device_fd; +int ret =0 ; + + msg.type = v->msg_type; + msg.iotlb.iova = iova; + msg.iotlb.size = size; + msg.iotlb.uaddr = (uint64_t )vaddr; + msg.iotlb.perm = readonly ?VHOST_ACCESS_RO :VHOST_ACCESS_RW ; + msg.iotlb.type =VHOST_IOTLB_UPDATE ; + +if (write (fd, &msg,sizeof (msg)) !=sizeof (msg)) { +error_report ("failed to write, fd=%d, errno=%d (%s)" , + fd, errno,strerror (errno)); +return -EIO ; + } + +return ret; +} + +static int vhost_vdpa_dma_unmap (struct vhost_vdpa *v,hwaddr iova, +hwaddr size) +{ +struct vhost_msg_v2 msg; +int fd = v->device_fd; +int ret =0 ; + + msg.type = v->msg_type; + msg.iotlb.iova = iova; + msg.iotlb.size = size; + msg.iotlb.type =VHOST_IOTLB_INVALIDATE ; + +if (write (fd, &msg,sizeof (msg)) !=sizeof (msg)) { +error_report ("failed to write, fd=%d, errno=%d (%s)" , + fd, errno,strerror (errno)); +return -EIO ; + } + +return ret; +} + +static void vhost_vdpa_listener_region_add (MemoryListener *listener, +MemoryRegionSection *section) +{ + struct vhost_vdpa *v = container_of(listener, struct vhost_vdpa, listener); +hwaddr iova; +Int128 llend, llsize; +void *vaddr; +int ret; + +if (vhost_vdpa_listener_skipped_section (section)) { +return ; + } + +if (unlikely ((section->offset_within_address_space & ~TARGET_PAGE_MASK ) != + (section->offset_within_region & ~TARGET_PAGE_MASK ))) { +error_report ("%s received unaligned region" , __func__); +return ; + } + + iova =TARGET_PAGE_ALIGN (section->offset_within_address_space); + llend =int128_make64 (section->offset_within_address_space); + llend =int128_add (llend, section->size); + llend =int128_and (llend,int128_exts64 (TARGET_PAGE_MASK )); + +if (int128_ge (int128_make64 (iova), llend)) { +return ; + } + +memory_region_ref (section->mr); + +/* Here we assume that memory_region_is_ram(section->mr)==true */ + + vaddr =memory_region_get_ram_ptr (section->mr) + + section->offset_within_region + + (iova - section->offset_within_address_space); + + llsize =int128_sub (llend,int128_make64 (iova)); + + ret =vhost_vdpa_dma_map (v, iova,int128_get64 (llsize), + vaddr, section->readonly); +if (ret) { +error_report ("vhost vdpa map fail!" ); +if (memory_region_is_ram_device (section->mr)) { +/* Allow unexpected mappings not to be fatal for RAM devices */ +error_report ("map ram fail!" ); +return ; + } + goto fail; + } + +return ; + +fail: +if (memory_region_is_ram_device (section->mr)) { +error_report ("failed to vdpa_dma_map. pci p2p may not work" ); +return ; + + } +/* +* On the initfn path, store the first error in the container so we +* can gracefully fail. Runtime, there's not much we can do other +* than throw a hardware error. +*/ +error_report ("vhost-vdpa: DMA mapping failed, unable to continue" ); +return ; + +} + +static void vhost_vdpa_listener_region_del (MemoryListener *listener, +MemoryRegionSection *section) +{ + struct vhost_vdpa *v = container_of(listener, struct vhost_vdpa, listener); +hwaddr iova; +Int128 llend, llsize; +int ret; +bool try_unmap = true; + +if (vhost_vdpa_listener_skipped_section (section)) { +return ; + } + +if (unlikely ((section->offset_within_address_space & ~TARGET_PAGE_MASK ) != + (section->offset_within_region & ~TARGET_PAGE_MASK ))) { +error_report ("%s received unaligned region" , __func__); +return ; + } + + iova =TARGET_PAGE_ALIGN (section->offset_within_address_space); + llend =int128_make64 (section->offset_within_address_space); + llend =int128_add (llend, section->size); + llend =int128_and (llend,int128_exts64 (TARGET_PAGE_MASK )); + +if (int128_ge (int128_make64 (iova), llend)) { +return ; + } + + llsize =int128_sub (llend,int128_make64 (iova)); + +if (try_unmap) { + ret =vhost_vdpa_dma_unmap (v, iova,int128_get64 (llsize)); +if (ret) { +error_report ("vhost_vdpa dma unmap error!" ); + } + } + +memory_region_unref (section->mr); +} +/* +* IOTLB API is used by vhost-vpda which requires incremental updating +* of the mapping. So we can not use generic vhost memory listener which +* depends on the addnop(). +*/ +static const MemoryListener vhost_vdpa_memory_listener = { + .region_add = vhost_vdpa_listener_region_add, + .region_del = vhost_vdpa_listener_region_del, +}; + +static int vhost_vdpa_call (struct vhost_dev *dev,unsigned long int request, +void *arg) +{ +struct vhost_vdpa *v = dev->opaque; +int fd = v->device_fd; + +assert (dev->vhost_ops->backend_type ==VHOST_BACKEND_TYPE_VDPA ); + +return ioctl (fd, request, arg); +} + +static void vhost_vdpa_add_status (struct vhost_dev *dev,uint8_t status) +{ +uint8_t s; + +if (vhost_vdpa_call (dev,VHOST_VDPA_GET_STATUS , &s)) { +return ; + } + + s |= status; + +vhost_vdpa_call (dev,VHOST_VDPA_SET_STATUS , &s); +} + +static int vhost_vdpa_init (struct vhost_dev *dev,void *opaque) +{ +struct vhost_vdpa *v; +uint64_t features; +assert (dev->vhost_ops->backend_type ==VHOST_BACKEND_TYPE_VDPA ); + + v = opaque; + dev->opaque = opaque ; +vhost_vdpa_call (dev,VHOST_GET_FEATURES , &features); + dev->backend_features = features; + v->listener = vhost_vdpa_memory_listener; + v->msg_type =VHOST_IOTLB_MSG_V2 ; + +vhost_vdpa_add_status (dev,VIRTIO_CONFIG_S_ACKNOWLEDGE | +VIRTIO_CONFIG_S_DRIVER ); + +return 0 ; +} + +static int vhost_vdpa_cleanup (struct vhost_dev *dev) +{ +struct vhost_vdpa *v; +assert (dev->vhost_ops->backend_type ==VHOST_BACKEND_TYPE_VDPA ); + v = dev->opaque; +memory_listener_unregister (&v->listener); + + dev->opaque =NULL ; +return 0 ; +} + +static int vhost_vdpa_memslots_limit (struct vhost_dev *dev) +{ +return INT_MAX ; +} + +static int vhost_vdpa_set_mem_table (struct vhost_dev *dev, +struct vhost_memory *mem) +{ + +if (mem->padding) { +return -1 ; + } + +return 0 ; +} + +static int vhost_vdpa_set_features (struct vhost_dev *dev, +uint64_t features) +{ +int ret; + ret =vhost_vdpa_call (dev,VHOST_SET_FEATURES , &features); +uint8_t status =0 ; +if (ret) { +return ret; + } +vhost_vdpa_add_status (dev,VIRTIO_CONFIG_S_FEATURES_OK ); +vhost_vdpa_call (dev,VHOST_VDPA_GET_STATUS , &status); + +return !(status &VIRTIO_CONFIG_S_FEATURES_OK ); +} + +int vhost_vdpa_get_device_id (struct vhost_dev *dev, +uint32_t *device_id) +{ +return vhost_vdpa_call (dev,VHOST_VDPA_GET_DEVICE_ID , device_id); +} + +static int vhost_vdpa_reset_device (struct vhost_dev *dev) +{ +uint8_t status =0 ; + +return vhost_vdpa_call (dev,VHOST_VDPA_SET_STATUS , &status); +} + +static int vhost_vdpa_get_vq_index (struct vhost_dev *dev,int idx) +{ +assert (idx >= dev->vq_index && idx < dev->vq_index + dev->nvqs); + +return idx - dev->vq_index; +} + +static int vhost_vdpa_set_vring_ready (struct vhost_dev *dev) +{ +int i; +for (i =0 ; i < dev->nvqs; ++i) { +struct vhost_vring_state state = { + .index = dev->vq_index + i, + .num =1 , + }; +vhost_vdpa_call (dev,VHOST_VDPA_SET_VRING_ENABLE , &state); + } +return 0 ; +} + +static int vhost_vdpa_set_config (struct vhost_dev *dev,const uint8_t *data, +uint32_t offset,uint32_t size, +uint32_t flags) +{ +struct vhost_vdpa_config *config; +int ret; +unsigned long config_size = offsetof(struct vhost_vdpa_config , buf); + config =g_malloc (size + config_size); +if (config ==NULL ) { +return -1 ; + } + config->off = offset; + config->len = size; +memcpy (config->buf, data, size); + ret =vhost_vdpa_call (dev,VHOST_VDPA_SET_CONFIG , config); +g_free (config); +return ret; +} + +static int vhost_vdpa_get_config (struct vhost_dev *dev,uint8_t *config, +uint32_t config_len) +{ +struct vhost_vdpa_config *v_config; +unsigned long config_size = offsetof(struct vhost_vdpa_config , buf); +int ret; + + v_config =g_malloc (config_len + config_size); +if (v_config ==NULL ) { +return -1 ; + } + v_config->len = config_len;
hw/virtio/vhost-vdpa.c line 358
Quoted 10 lines
hw/virtio/vhost-vdpa.c new file +10
-0+ v_config->off =0 ; + ret =vhost_vdpa_call (dev,VHOST_VDPA_GET_CONFIG , v_config); +memcpy (config, v_config->buf, config_len); +g_free (v_config); +return ret; + } + +static int vhost_vdpa_dev_start (struct vhost_dev *dev,bool started) +{ +struct vhost_vdpa *v = dev->opaque;
newline is needed.
Quoted 53 lines
hw/virtio/vhost-vdpa.c new file +48
-0+if (started) { +uint8_t status =0 ; +memory_listener_register (&v->listener, &address_space_memory); +vhost_vdpa_set_vring_ready (dev); +vhost_vdpa_add_status (dev,VIRTIO_CONFIG_S_DRIVER_OK ); +vhost_vdpa_call (dev,VHOST_VDPA_GET_STATUS , &status); + +return !(status &VIRTIO_CONFIG_S_DRIVER_OK ); + }else { +vhost_vdpa_reset_device (dev); +vhost_vdpa_add_status (dev,VIRTIO_CONFIG_S_ACKNOWLEDGE | +VIRTIO_CONFIG_S_DRIVER ); +memory_listener_unregister (&v->listener); + +return 0 ; + } +} + +const VhostOps vdpa_ops = { + .backend_type =VHOST_BACKEND_TYPE_VDPA , + .vhost_backend_init = vhost_vdpa_init, + .vhost_backend_cleanup = vhost_vdpa_cleanup, + .vhost_set_log_base = vhost_kernel_set_log_base, + .vhost_set_vring_addr = vhost_kernel_set_vring_addr, + .vhost_set_vring_num = vhost_kernel_set_vring_num, + .vhost_set_vring_base = vhost_kernel_set_vring_base, + .vhost_get_vring_base = vhost_kernel_get_vring_base, + .vhost_set_vring_kick = vhost_kernel_set_vring_kick, + .vhost_set_vring_call = vhost_kernel_set_vring_call, + .vhost_get_features = vhost_kernel_get_features, + .vhost_set_owner = vhost_kernel_set_owner, + .vhost_set_vring_endian =NULL , + .vhost_backend_memslots_limit = vhost_vdpa_memslots_limit, + .vhost_set_mem_table = vhost_vdpa_set_mem_table, + .vhost_set_features = vhost_vdpa_set_features, + .vhost_reset_device = vhost_vdpa_reset_device, + .vhost_get_vq_index = vhost_vdpa_get_vq_index, + .vhost_get_config = vhost_vdpa_get_config, + .vhost_set_config = vhost_vdpa_set_config, + .vhost_requires_shm_log =NULL , + .vhost_migration_done =NULL , + .vhost_backend_can_merge =NULL , + .vhost_net_set_mtu =NULL , + .vhost_set_iotlb_callback =NULL , + .vhost_send_device_iotlb_msg =NULL , + .vhost_dev_start = vhost_vdpa_dev_start, + .vhost_get_device_id = vhost_vdpa_get_device_id, +};hw/virtio/vhost.c +0
-0
hw/virtio/vhost.c static void vhost_iommu_region_del(MemoryListener *listener, · line 752
Quoted 9 lines
hw/virtio/vhost.c +6
-0@@ -744,19 +744,34 @@ static void vhost_iommu_region_del(MemoryListener *listener, } } +static void vhost_virtqueue_get_addr (struct vhost_dev *dev, +struct vhost_vring_addr *addr, +struct vhost_virtqueue *vq) +{ +/*vDPA need to use the IOVA here to set to hardware*/ +if (dev->vhost_ops->backend_type ==VHOST_BACKEND_TYPE_VDPA ) {
Let's introduce a new vhost_ops for this.
Quoted 19 lines
hw/virtio/vhost.c +9
-5+ addr->desc_user_addr = (uint64_t )(unsigned long )vq->desc_phys; + addr->avail_user_addr = (uint64_t )(unsigned long )vq->avail_phys; + addr->used_user_addr = (uint64_t )(unsigned long )vq->used_phys; + }else { + addr->desc_user_addr = (uint64_t )(unsigned long )vq->desc; + addr->avail_user_addr = (uint64_t )(unsigned long )vq->avail; + addr->used_user_addr = (uint64_t )(unsigned long )vq->used; + } +}static int vhost_virtqueue_set_addr (struct vhost_dev *dev,struct vhost_virtqueue *vq,unsigned idx,bool enable_log) { -struct vhost_vring_addr addr = { - .index = idx, - .desc_user_addr = (uint64_t )(unsigned long )vq->desc, - .avail_user_addr = (uint64_t )(unsigned long )vq->avail, - .used_user_addr = (uint64_t )(unsigned long )vq->used,
hw/virtio/vhost.c static void vhost_iommu_region_del(MemoryListener *listener, · line 773
Quoted 10 lines
hw/virtio/vhost.c +7
-3- .log_guest_addr = vq->used_phys, - .flags = enable_log ? (1 << VHOST_VRING_F_LOG) : 0, - }; +struct vhost_vring_addr addr; +memset (&addr,0 ,sizeof (struct vhost_vring_addr )); + +vhost_virtqueue_get_addr (dev, &addr, vq); + addr.index = idx; + addr .log_guest_addr = vq->used_phys; + addr .flags = enable_log ? (1 <<VHOST_VRING_F_LOG ) :0 ;
Unnecessary spaces between addr and log_guest_addr/flags.
hw/virtio/vhost.c static int vhost_dev_set_features(struct vhost_dev *dev, · line 777
Quoted 9 lines
hw/virtio/vhost.c +1
-1+int r = dev->vhost_ops->vhost_set_vring_addr (dev, &addr);if (r <0 ) {VHOST_OPS_DEBUG ("vhost_set_vring_addr failed" );@@ -774,7 +789,9 @@ static int vhost_dev_set_features(struct vhost_dev *dev, features |=0x1ULL <<VHOST_F_LOG_ALL ; }if (!vhost_dev_has_iommu (dev)) { - features &= ~(0x1ULL <<VIRTIO_F_IOMMU_PLATFORM );
A comment is needed here.
hw/virtio/vhost.c int vhost_dev_start(struct vhost_dev *hdev, VirtIODevice *vdev) · line 1688
Quoted 13 lines
hw/virtio/vhost.c +5
-1+if (dev->vhost_ops->backend_type !=VHOST_BACKEND_TYPE_VDPA ) { + features &= ~(0x1ULL <<VIRTIO_F_IOMMU_PLATFORM ); + } } r = dev->vhost_ops->vhost_set_features (dev, features);if (r <0 ) {@@ -1667,7 +1684,8 @@ int vhost_dev_start(struct vhost_dev *hdev, VirtIODevice *vdev) goto fail_log; } -if (vhost_dev_has_iommu (hdev)) { +if (vhost_dev_has_iommu (hdev) && + hdev->vhost_ops->vhost_set_iotlb_callback) {
A separate patch for this please
hw/virtio/vhost.c void vhost_dev_stop(struct vhost_dev *hdev, VirtIODevice *vdev) · line 1736
Quoted 11 lines
hw/virtio/vhost.c +3
-1hdev->vhost_ops->vhost_set_iotlb_callback (hdev, true);/* Update used ring information for IOTLB to work correctly, @@ -1713,7 +1731,9 @@ void vhost_dev_stop(struct vhost_dev *hdev, VirtIODevice *vdev) }if (vhost_dev_has_iommu (hdev)) { - hdev->vhost_ops->vhost_set_iotlb_callback (hdev, false); +if (hdev->vhost_ops->vhost_set_iotlb_callback) { + hdev->vhost_ops->vhost_set_iotlb_callback (hdev, false); + }
A separate patch for this.
Quoted 26 lines
hw/virtio/vhost.c +0
-0memory_listener_unregister (&hdev->iommu_listener); }vhost_log_put (hdev, true);include/hw/virtio/vhost-backend.h +3
-1@@ -17,7 +17,8 @@ typedef enum VhostBackendType {VHOST_BACKEND_TYPE_NONE =0 ,VHOST_BACKEND_TYPE_KERNEL =1 ,VHOST_BACKEND_TYPE_USER =2 , -VHOST_BACKEND_TYPE_MAX =3 , +VHOST_BACKEND_TYPE_VDPA =3 , +VHOST_BACKEND_TYPE_MAX =4 , } VhostBackendType; typedef enum VhostSetConfigType {@@ -113,6 +114,7 @@ typedef int (*vhost_set_inflight_fd_op)(struct vhost_dev *dev, struct vhost_inflight *inflight);typedef int (*vhost_dev_start_op )(struct vhost_dev *dev,bool started); +typedef int (*vhost_get_device_id_op )(struct vhost_dev *dev,uint32_t *dev_id); typedef struct VhostOps { VhostBackendType backend_type; vhost_backend_init vhost_backend_init;
include/hw/virtio/vhost-backend.h typedef struct VhostOps { · line 160
Quoted 5 lines
include/hw/virtio/vhost-backend.h +1
-0@@ -154,9 +156,11 @@ typedef struct VhostOps {vhost_get_inflight_fd_op vhost_get_inflight_fd;vhost_set_inflight_fd_op vhost_set_inflight_fd;vhost_dev_start_op vhost_dev_start; +vhost_get_device_id_op vhost_get_device_id; } VhostOps;
A separate patch for introducing this please.
Quoted 43 lines
include/hw/virtio/vhost-backend.h +1
-0extern const VhostOps user_ops; +extern const VhostOps vdpa_ops;int vhost_set_backend_type (struct vhost_dev *dev,VhostBackendType backend_type);include/hw/virtio/vhost-vdpa.h new file +26
-0@@ -0,0 +1,26 @@ +/* +* vhost-vdpa.h +* +* Copyright(c) 2017-2018 Intel Corporation. +* Copyright(c) 2020 Red Hat, Inc. +* +* This work is licensed under the terms of the GNU GPL, version 2 or later. +* See the COPYING file in the top-level directory. +* +*/ + +#ifndef HW_VIRTIO_VHOST_VDPA_H +#define HW_VIRTIO_VHOST_VDPA_H + +#include "hw/virtio/virtio.h" + +typedef struct vhost_vdpa { +int device_fd; +uint32_t msg_type; +MemoryListener listener; +}VhostVDPA ; + +extern AddressSpace address_space_memory; +extern int vhost_vdpa_get_device_id (struct vhost_dev *dev, +uint32_t *device_id); +#endif include/hw/virtio/vhost.h +0
-0
include/hw/virtio/vhost.h struct vhost_dev { · line 100
Quoted 9 lines
include/hw/virtio/vhost.h +6
-0@@ -92,6 +92,12 @@ struct vhost_dev {const VhostDevConfigOps *config_ops; }; +struct vhost_net { +struct vhost_dev dev; +struct vhost_virtqueue vqs[2 ]; +int backend; +NetClientState *nc; +};
A separate patch for this exporting please.
Thanks
Quoted 33 lines
include/hw/virtio/vhost.h +0
-0int vhost_dev_init(struct vhost_dev *hdev, void *opaque, VhostBackendType backend_type,qemu-options.hx +12
-0@@ -2409,6 +2409,10 @@ DEF("netdev", HAS_ARG, QEMU_OPTION_netdev, #ifdef CONFIG_POSIX "-netdev vhost-user,id=str,chardev=dev[,vhostforce=on|off]\n" " configure a vhost-user network, backed by a chardev 'dev'\n" +#endif +#ifdef __linux__ + "-netdev vhost-vdpa,id=str,vhostdev=/path/to/dev\n" + " configure a vhost-vdpa network,Establish a vhost-vdpa netdev\n" #endif "-netdev hubport,id=str,hubid=n[,netdev=nd]\n" " configure a hub port on the hub with ID 'n'\n", QEMU_ARCH_ALL)@@ -2888,6 +2892,14 @@ SRST -netdev type=vhost-user,id=net0,chardev=chr0 \ -device virtio-net-pci,netdev=net0 +``-netdev vhost-vdpa,vhostdev=/path/to/dev`` + Establish a vhost-vdpa netdev. + + vDPA device is a device that uses a datapath which complies with + the virtio specifications with a vendor specific control path. + vDPA devices can be both physically located on the hardware or + emulated by software. + ``-netdev hubport,id=id,hubid=hubid[,netdev=nd]`` Create a hub port on the emulated hub with ID hubid.
Re: [PATCH v1 09/10] vhost-vdpa: introduce vhost-vdpa backend
Quoted 139 lines · Jason Wang
Quoted 136 lines · Cindy Lu
Currently we have 2 types of vhost backends in QEMU: vhost kernel and vhost-user. The above patch provides a generic device for vDPA purpose, this vDPA device exposes to user space a non-vendor-specific configuration interface for setting up a vhost HW accelerator, this patch set introduces a third vhost backend called vhost-vdpa based on the vDPA interface.
Vhost-vdpa usage:
qemu-system-x86_64 -cpu host -enable-kvm \ ...... -netdev type=vhost-vdpa,vhostdev=/dev/vhost-vdpa-id,id=vhost-vdpa0 \ -device virtio-net-pci,netdev=vhost-vdpa0,page-per-vq=on \Signed-off-by Lingshan zhu <[email protected]>Signed-off-by Tiwei Bie <[email protected]>Signed-off-by Cindy Lu <[email protected]>--- configure | 21 ++ hw/net/vhost_net.c | 19 +- hw/net/virtio-net.c | 19 +- hw/virtio/Makefile.objs | 1 + hw/virtio/vhost-backend.c | 22 +- hw/virtio/vhost-vdpa.c | 406 ++++++++++++++++++++++++++++++ hw/virtio/vhost.c | 42 +++- include/hw/virtio/vhost-backend.h | 6 +- include/hw/virtio/vhost-vdpa.h | 26 ++ include/hw/virtio/vhost.h | 6 + qemu-options.hx | 12 + 11 files changed, 555 insertions(+), 25 deletions(-)create mode 100644
hw/virtio/vhost-vdpa.ccreate mode 100644include/hw/virtio/vhost-vdpa.hconfigure +21
-0@@ -1557,6 +1557,10 @@ for opt do ;; --enable-vhost-user) vhost_user="yes" ;; + --disable-vhost-vdpa) vhost_vdpa="no" + ;; + --enable-vhost-vdpa) vhost_vdpa="yes" + ;; --disable-vhost-kernel) vhost_kernel="no" ;; --enable-vhost-kernel) vhost_kernel="yes"@@ -1846,6 +1850,7 @@ disabled with --disable-FEATURE, default is enabled if available: vhost-crypto vhost-user-crypto backend support vhost-kernel vhost kernel backend support vhost-user vhost-user backend support + vhost-vdpa vhost-vdpa kernel backend support spice spice rbd rados block device (rbd) libiscsi iscsi support@@ -2336,6 +2341,10 @@ test "$vhost_user" = "" && vhost_user=yes if test "$vhost_user" = "yes" && test "$mingw32" = "yes"; then error_exit "vhost-user isn't available on win32" fi +test "$vhost_vdpa" = "" && vhost_vdpa=$linux +if test "$vhost_vdpa" = "yes" && test "$linux" != "yes"; then + error_exit "vhost-vdpa is only available on Linux" +fi test "$vhost_kernel" = "" && vhost_kernel=$linux if test "$vhost_kernel" = "yes" && test "$linux" != "yes"; then error_exit "vhost-kernel is only available on Linux"@@ -2364,6 +2373,11 @@ test "$vhost_user_fs" = "" && vhost_user_fs=$vhost_user if test "$vhost_user_fs" = "yes" && test "$vhost_user" = "no"; then error_exit "--enable-vhost-user-fs requires --enable-vhost-user" fi +#vhost-vdpa backends +test "$vhost_net_vdpa" = "" && vhost_net_vdpa=$vhost_vdpa +if test "$vhost_net_vdpa" = "yes" && test "$vhost_vdpa" = "no"; then + error_exit "--enable-vhost-net-vdpa requires --enable-vhost-vdpa" +fi # OR the vhost-kernel and vhost-user values for simplicity if test "$vhost_net" = ""; then@@ -6673,6 +6687,7 @@ echo "vhost-scsi support $vhost_scsi" echo "vhost-vsock support $vhost_vsock" echo "vhost-user support $vhost_user" echo "vhost-user-fs support $vhost_user_fs" +echo "vhost-vdpa support $vhost_vdpa" echo "Trace backends $trace_backends" if have_backend "simple"; then echo "Trace output file $trace_file-<pid>"@@ -7170,6 +7185,9 @@ fi if test "$vhost_net_user" = "yes" ; then echo "CONFIG_VHOST_NET_USER=y" >> $config_host_mak fi +if test "$vhost_net_vdpa" = "yes" ; then + echo "CONFIG_VHOST_NET_VDPA=y" >> $config_host_mak +fi if test "$vhost_crypto" = "yes" ; then echo "CONFIG_VHOST_CRYPTO=y" >> $config_host_mak fi@@ -7182,6 +7200,9 @@ fi if test "$vhost_user" = "yes" ; then echo "CONFIG_VHOST_USER=y" >> $config_host_mak fi +if test "$vhost_vdpa" = "yes" ; then + echo "CONFIG_VHOST_VDPA=y" >> $config_host_mak +fi if test "$vhost_user_fs" = "yes" ; then echo "CONFIG_VHOST_USER_FS=y" >> $config_host_mak fihw/net/vhost_net.c +2
-6@@ -17,8 +17,10 @@#include "net/net.h" #include "net/tap.h" #include "net/vhost-user.h" +#include "net/vhost-vdpa.h" #include "standard-headers/linux/vhost_types.h" +#include "linux-headers/linux/vhost.h" #include "hw/virtio/virtio-net.h" #include "net/vhost_net.h" #include "qemu/error-report.h" @@ -33,12 +35,6 @@#include "hw/virtio/vhost.h" #include "hw/virtio/virtio-bus.h" -struct vhost_net { -struct vhost_dev dev; -struct vhost_virtqueue vqs[2 ]; -int backend; -NetClientState *nc; -};/* Features supported by host kernel. */ static const int kernel_feature_bits[] = {@@ -84,7 +80,6 @@ static const int user_feature_bits[] = {
Quoted 8 lines
hw/net/vhost_net.c static const int user_feature_bits[] = { · line 87
Quoted 3 lines
hw/net/vhost_net.c +0
-1VHOST_INVALID_FEATURE_BIT }; -Unnecessary change.
Will remove this
Quoted 16 lines
Quoted 16 lines
hw/net/vhost_net.c +3
-0static const int *vhost_net_get_feature_bits (struct vhost_net *net) {const int *feature_bits =0 ;@@ -96,6 +91,9 @@ static const int *vhost_net_get_feature_bits(struct vhost_net *net)case NET_CLIENT_DRIVER_VHOST_USER : feature_bits = user_feature_bits;break ; +case NET_CLIENT_DRIVER_VHOST_VDPA : + feature_bits = vdpa_feature_bits; +break ;default :error_report ("Feature bits not defined for this type: %d" , net->nc->info->type);@@ -348,6 +346,7 @@ int vhost_net_start(VirtIODevice *dev, NetClientState *ncs, }
Quoted 6 lines
hw/net/vhost_net.c int vhost_net_start(VirtIODevice *dev, NetClientState *ncs, · line 349
Quoted 2 lines
hw/net/vhost_net.c +1
-0for (i =0 ; i < total_queues; i++) { +Unnecessary change.
Will remove this
Quoted 54 lines
Quoted 40 lines
hw/net/vhost_net.c +6
-0peer =qemu_get_peer (ncs, i); r =vhost_net_start_one (get_vhost_net (peer), dev);@@ -444,6 +443,12 @@ VHostNetState *get_vhost_net(NetClientState *nc) vhost_net =vhost_user_get_vhost_net (nc);assert (vhost_net);break ; +#endif +#ifdef CONFIG_VHOST_NET_VDPA +case NET_CLIENT_DRIVER_VHOST_VDPA : + vhost_net =vhost_vdpa_get_vhost_net (nc); +assert (vhost_net); +break ;#endif default :break ;hw/net/virtio-net.c +3
-0@@ -42,6 +42,7 @@#include "trace.h" #include "monitor/qdev.h" #include "hw/pci/pci.h" +#include "hw/virtio/vhost.h" #define VIRTIO_NET_VM_VERSION 11@@ -131,6 +132,8 @@ static void virtio_net_get_config(VirtIODevice *vdev, uint8_t *config) {VirtIONet *n =VIRTIO_NET (vdev);struct virtio_net_config netcfg; +int ret =0 ; +memset (&netcfg,0 ,sizeof (struct virtio_net_config ));virtio_stw_p (vdev, &netcfg.status, n->status);virtio_stw_p (vdev, &netcfg.max_virtqueue_pairs, n->max_queues);@@ -139,13 +142,21 @@ static void virtio_net_get_config(VirtIODevice *vdev, uint8_t *config)virtio_stl_p (vdev, &netcfg.speed, n->net_conf.speed);hw/net/virtio-net.c static void virtio_net_get_config(VirtIODevice *vdev, uint8_t *config) · line 152
Quoted 10 lines
hw/net/virtio-net.c +8
-0netcfg.duplex = n->net_conf.duplex;memcpy (config, &netcfg, n->config_size); +NetClientState *nc =qemu_get_queue (n->nic); +if (nc->peer->info->type ==NET_CLIENT_DRIVER_VHOST_VDPA ) { + ret =vhost_net_get_config (get_vhost_net (nc->peer), (uint8_t *)&netcfg, + n->config_size); +if (ret !=-1 ) { +memcpy (config, &netcfg, n->config_size); + } + }This is kind of sub-optimal.
Quoted 4 lines
I think the a better approach is deal all the stuffs inside
vhost_net_get_config().
Sure will do
Quoted 10 lines
hw/net/virtio-net.c static void virtio_net_get_config(VirtIODevice *vdev, uint8_t *config) · line 148
Quoted 8 lines
hw/net/virtio-net.c +1
-1}static void virtio_net_set_config (VirtIODevice *vdev,const uint8_t *config) {VirtIONet *n =VIRTIO_NET (vdev); +NetClientState *nc =qemu_get_queue (n->nic);struct virtio_net_config netcfg = {}; -
Quoted 2 lines
Unnecessary change.
Will remove this
Quoted 20 lines
hw/net/virtio-net.c static void virtio_net_set_config(VirtIODevice *vdev, const uint8_t *config) · line 172
Quoted 13 lines
hw/net/virtio-net.c +5
-0memcpy (&netcfg, config, n->config_size); if (!virtio_vdev_has_feature(vdev, VIRTIO_NET_F_CTRL_MAC_ADDR) &&@@ -154,6 +165,11 @@ static void virtio_net_set_config(VirtIODevice *vdev, const uint8_t *config)memcpy (n->mac, netcfg.mac,ETH_ALEN );qemu_format_nic_info_str (qemu_get_queue (n->nic), n->mac); } +if (nc->peer->info->type ==NET_CLIENT_DRIVER_VHOST_VDPA ) { +vhost_net_set_config (get_vhost_net (nc->peer), (uint8_t *)&netcfg, +0 , n->config_size, +VHOST_SET_CONFIG_TYPE_MASTER ); + }Similar issues as
get_config.Quoted 2 lines
hw/net/virtio-net.c +0
-0}
Quoted 10 lines
hw/net/virtio-net.c static void virtio_net_device_realize(DeviceState *dev, Error **errp) · line 2961
Quoted 6 lines
hw/net/virtio-net.c +0
-1static bool virtio_net_started (VirtIONet *n,uint8_t status)@@ -2958,7 +2974,6 @@ static void virtio_net_device_realize(DeviceState *dev, Error **errp) }else if (n->net_conf.speed >=0 ) { n->host_features |= (1ULL <<VIRTIO_NET_F_SPEED_DUPLEX ); } -Unnecessary change.
Will remove this
Quoted 429 lines
Quoted 94 lines
hw/net/virtio-net.c +0
-0if (n->failover) { n->primary_listener.should_be_hidden = virtio_net_primary_should_be_hidden;hw/virtio/Makefile.objs +1
-0@@ -5,6 +5,7 @@ obj-y += virtio.o obj-$(CONFIG_VHOST) += vhost.o vhost-backend.o common-obj-$(call lnot,$(CONFIG_VHOST)) += vhost-stub.o obj-$(CONFIG_VHOST_USER) += vhost-user.o +obj-$(CONFIG_VHOST_VDPA) += vhost-vdpa.o common-obj-$(CONFIG_VIRTIO_RNG) += virtio-rng.o common-obj-$(CONFIG_VIRTIO_PCI) += virtio-pci.ohw/virtio/vhost-backend.c +18
-4@@ -14,7 +14,7 @@#include "qemu/error-report.h" #include "qemu/main-loop.h" #include "standard-headers/linux/vhost_types.h" - +#include "hw/virtio/vhost-vdpa.h" #ifdef CONFIG_VHOST_KERNEL #include <linux/vhost.h> #include <sys/ioctl.h> @@ -22,10 +22,19 @@static int vhost_kernel_call (struct vhost_dev *dev,unsigned long int request,void *arg) { -int fd = (uintptr_t ) dev->opaque; - -assert (dev->vhost_ops->backend_type ==VHOST_BACKEND_TYPE_KERNEL ); +int fd =-1 ; +switch (dev->vhost_ops->backend_type) { +case VHOST_BACKEND_TYPE_KERNEL : + fd = (uintptr_t )dev->opaque; +break ; +case VHOST_BACKEND_TYPE_VDPA : + fd = ((struct vhost_vdpa *)dev->opaque)->device_fd; +break ; +default : +g_assert_not_reached (); + } +assert (fd !=-1 );return ioctl (fd, request, arg); }@@ -285,6 +294,11 @@ int vhost_set_backend_type(struct vhost_dev *dev, VhostBackendType backend_type)case VHOST_BACKEND_TYPE_USER : dev->vhost_ops = &user_ops;break ; +#endif +#ifdef CONFIG_VHOST_VDPA +case VHOST_BACKEND_TYPE_VDPA : + dev->vhost_ops = &vdpa_ops; +break ;#endif default :error_report ("Unknown vhost backend type" );hw/virtio/vhost-vdpa.c new file +24
-0@@ -0,0 +1,406 @@ +/* +* vhost-vdpa +* +* Copyright(c) 2017-2018 Intel Corporation. +* Copyright(c) 2020 Red Hat, Inc. +* +* This work is licensed under the terms of the GNU GPL, version 2 or later. +* See the COPYING file in the top-level directory. +* +*/ + +#include "qemu/osdep.h" +#include <linux/vhost.h> +#include <linux/vfio.h> +#include <sys/eventfd.h> +#include <sys/ioctl.h> +#include "hw/virtio/vhost.h" +#include "hw/virtio/vhost-backend.h" +#include "hw/virtio/virtio-net.h" +#include "hw/virtio/vhost-vdpa.h" +#include "qemu/main-loop.h" +#include <linux/kvm.h> +#include "sysemu/kvm.h" +hw/virtio/vhost-vdpa.c line 34
Quoted 10 lines
hw/virtio/vhost-vdpa.c new file +10
-0+ +static bool vhost_vdpa_listener_skipped_section (MemoryRegionSection *section) +{ +return (!memory_region_is_ram (section->mr) && + !memory_region_is_iommu (section->mr)) || +/* +* Sizing an enabled 64-bit BAR can cause spurious mappings to +* addresses in the upper part of the 64-bit address space. These +* are never accessed by the CPU and beyond the address width of +* some IOMMU hardware. TODO: VDPA should tell us the IOMMU width. Note that, I post patches for reporting IOVA range, we need add the check through that in the future.
Quoted 319 lines
hw/virtio/vhost-vdpa.c new file +319
-0+*/ + section->offset_within_address_space & (1ULL <<63 ); +} + +static int vhost_vdpa_dma_map (struct vhost_vdpa *v,hwaddr iova,hwaddr size, +void *vaddr,bool readonly) +{ +struct vhost_msg_v2 msg; +int fd = v->device_fd; +int ret =0 ; + + msg.type = v->msg_type; + msg.iotlb.iova = iova; + msg.iotlb.size = size; + msg.iotlb.uaddr = (uint64_t )vaddr; + msg.iotlb.perm = readonly ?VHOST_ACCESS_RO :VHOST_ACCESS_RW ; + msg.iotlb.type =VHOST_IOTLB_UPDATE ; + +if (write (fd, &msg,sizeof (msg)) !=sizeof (msg)) { +error_report ("failed to write, fd=%d, errno=%d (%s)" , + fd, errno,strerror (errno)); +return -EIO ; + } + +return ret; +} + +static int vhost_vdpa_dma_unmap (struct vhost_vdpa *v,hwaddr iova, +hwaddr size) +{ +struct vhost_msg_v2 msg; +int fd = v->device_fd; +int ret =0 ; + + msg.type = v->msg_type; + msg.iotlb.iova = iova; + msg.iotlb.size = size; + msg.iotlb.type =VHOST_IOTLB_INVALIDATE ; + +if (write (fd, &msg,sizeof (msg)) !=sizeof (msg)) { +error_report ("failed to write, fd=%d, errno=%d (%s)" , + fd, errno,strerror (errno)); +return -EIO ; + } + +return ret; +} + +static void vhost_vdpa_listener_region_add (MemoryListener *listener, +MemoryRegionSection *section) +{ + struct vhost_vdpa *v = container_of(listener, struct vhost_vdpa, listener); +hwaddr iova; +Int128 llend, llsize; +void *vaddr; +int ret; + +if (vhost_vdpa_listener_skipped_section (section)) { +return ; + } + +if (unlikely ((section->offset_within_address_space & ~TARGET_PAGE_MASK ) != + (section->offset_within_region & ~TARGET_PAGE_MASK ))) { +error_report ("%s received unaligned region" , __func__); +return ; + } + + iova =TARGET_PAGE_ALIGN (section->offset_within_address_space); + llend =int128_make64 (section->offset_within_address_space); + llend =int128_add (llend, section->size); + llend =int128_and (llend,int128_exts64 (TARGET_PAGE_MASK )); + +if (int128_ge (int128_make64 (iova), llend)) { +return ; + } + +memory_region_ref (section->mr); + +/* Here we assume that memory_region_is_ram(section->mr)==true */ + + vaddr =memory_region_get_ram_ptr (section->mr) + + section->offset_within_region + + (iova - section->offset_within_address_space); + + llsize =int128_sub (llend,int128_make64 (iova)); + + ret =vhost_vdpa_dma_map (v, iova,int128_get64 (llsize), + vaddr, section->readonly); +if (ret) { +error_report ("vhost vdpa map fail!" ); +if (memory_region_is_ram_device (section->mr)) { +/* Allow unexpected mappings not to be fatal for RAM devices */ +error_report ("map ram fail!" ); +return ; + } + goto fail; + } + +return ; + +fail: +if (memory_region_is_ram_device (section->mr)) { +error_report ("failed to vdpa_dma_map. pci p2p may not work" ); +return ; + + } +/* +* On the initfn path, store the first error in the container so we +* can gracefully fail. Runtime, there's not much we can do other +* than throw a hardware error. +*/ +error_report ("vhost-vdpa: DMA mapping failed, unable to continue" ); +return ; + +} + +static void vhost_vdpa_listener_region_del (MemoryListener *listener, +MemoryRegionSection *section) +{ + struct vhost_vdpa *v = container_of(listener, struct vhost_vdpa, listener); +hwaddr iova; +Int128 llend, llsize; +int ret; +bool try_unmap = true; + +if (vhost_vdpa_listener_skipped_section (section)) { +return ; + } + +if (unlikely ((section->offset_within_address_space & ~TARGET_PAGE_MASK ) != + (section->offset_within_region & ~TARGET_PAGE_MASK ))) { +error_report ("%s received unaligned region" , __func__); +return ; + } + + iova =TARGET_PAGE_ALIGN (section->offset_within_address_space); + llend =int128_make64 (section->offset_within_address_space); + llend =int128_add (llend, section->size); + llend =int128_and (llend,int128_exts64 (TARGET_PAGE_MASK )); + +if (int128_ge (int128_make64 (iova), llend)) { +return ; + } + + llsize =int128_sub (llend,int128_make64 (iova)); + +if (try_unmap) { + ret =vhost_vdpa_dma_unmap (v, iova,int128_get64 (llsize)); +if (ret) { +error_report ("vhost_vdpa dma unmap error!" ); + } + } + +memory_region_unref (section->mr); +} +/* +* IOTLB API is used by vhost-vpda which requires incremental updating +* of the mapping. So we can not use generic vhost memory listener which +* depends on the addnop(). +*/ +static const MemoryListener vhost_vdpa_memory_listener = { + .region_add = vhost_vdpa_listener_region_add, + .region_del = vhost_vdpa_listener_region_del, +}; + +static int vhost_vdpa_call (struct vhost_dev *dev,unsigned long int request, +void *arg) +{ +struct vhost_vdpa *v = dev->opaque; +int fd = v->device_fd; + +assert (dev->vhost_ops->backend_type ==VHOST_BACKEND_TYPE_VDPA ); + +return ioctl (fd, request, arg); +} + +static void vhost_vdpa_add_status (struct vhost_dev *dev,uint8_t status) +{ +uint8_t s; + +if (vhost_vdpa_call (dev,VHOST_VDPA_GET_STATUS , &s)) { +return ; + } + + s |= status; + +vhost_vdpa_call (dev,VHOST_VDPA_SET_STATUS , &s); +} + +static int vhost_vdpa_init (struct vhost_dev *dev,void *opaque) +{ +struct vhost_vdpa *v; +uint64_t features; +assert (dev->vhost_ops->backend_type ==VHOST_BACKEND_TYPE_VDPA ); + + v = opaque; + dev->opaque = opaque ; +vhost_vdpa_call (dev,VHOST_GET_FEATURES , &features); + dev->backend_features = features; + v->listener = vhost_vdpa_memory_listener; + v->msg_type =VHOST_IOTLB_MSG_V2 ; + +vhost_vdpa_add_status (dev,VIRTIO_CONFIG_S_ACKNOWLEDGE | +VIRTIO_CONFIG_S_DRIVER ); + +return 0 ; +} + +static int vhost_vdpa_cleanup (struct vhost_dev *dev) +{ +struct vhost_vdpa *v; +assert (dev->vhost_ops->backend_type ==VHOST_BACKEND_TYPE_VDPA ); + v = dev->opaque; +memory_listener_unregister (&v->listener); + + dev->opaque =NULL ; +return 0 ; +} + +static int vhost_vdpa_memslots_limit (struct vhost_dev *dev) +{ +return INT_MAX ; +} + +static int vhost_vdpa_set_mem_table (struct vhost_dev *dev, +struct vhost_memory *mem) +{ + +if (mem->padding) { +return -1 ; + } + +return 0 ; +} + +static int vhost_vdpa_set_features (struct vhost_dev *dev, +uint64_t features) +{ +int ret; + ret =vhost_vdpa_call (dev,VHOST_SET_FEATURES , &features); +uint8_t status =0 ; +if (ret) { +return ret; + } +vhost_vdpa_add_status (dev,VIRTIO_CONFIG_S_FEATURES_OK ); +vhost_vdpa_call (dev,VHOST_VDPA_GET_STATUS , &status); + +return !(status &VIRTIO_CONFIG_S_FEATURES_OK ); +} + +int vhost_vdpa_get_device_id (struct vhost_dev *dev, +uint32_t *device_id) +{ +return vhost_vdpa_call (dev,VHOST_VDPA_GET_DEVICE_ID , device_id); +} + +static int vhost_vdpa_reset_device (struct vhost_dev *dev) +{ +uint8_t status =0 ; + +return vhost_vdpa_call (dev,VHOST_VDPA_SET_STATUS , &status); +} + +static int vhost_vdpa_get_vq_index (struct vhost_dev *dev,int idx) +{ +assert (idx >= dev->vq_index && idx < dev->vq_index + dev->nvqs); + +return idx - dev->vq_index; +} + +static int vhost_vdpa_set_vring_ready (struct vhost_dev *dev) +{ +int i; +for (i =0 ; i < dev->nvqs; ++i) { +struct vhost_vring_state state = { + .index = dev->vq_index + i, + .num =1 , + }; +vhost_vdpa_call (dev,VHOST_VDPA_SET_VRING_ENABLE , &state); + } +return 0 ; +} + +static int vhost_vdpa_set_config (struct vhost_dev *dev,const uint8_t *data, +uint32_t offset,uint32_t size, +uint32_t flags) +{ +struct vhost_vdpa_config *config; +int ret; +unsigned long config_size = offsetof(struct vhost_vdpa_config , buf); + config =g_malloc (size + config_size); +if (config ==NULL ) { +return -1 ; + } + config->off = offset; + config->len = size; +memcpy (config->buf, data, size); + ret =vhost_vdpa_call (dev,VHOST_VDPA_SET_CONFIG , config); +g_free (config); +return ret; +} + +static int vhost_vdpa_get_config (struct vhost_dev *dev,uint8_t *config, +uint32_t config_len) +{ +struct vhost_vdpa_config *v_config; +unsigned long config_size = offsetof(struct vhost_vdpa_config , buf); +int ret; + + v_config =g_malloc (config_len + config_size); +if (v_config ==NULL ) { +return -1 ; + } + v_config->len = config_len; + v_config->off =0 ; + ret =vhost_vdpa_call (dev,VHOST_VDPA_GET_CONFIG , v_config); +memcpy (config, v_config->buf, config_len); +g_free (v_config); +return ret;
Quoted 10 lines
hw/virtio/vhost-vdpa.c line 358
Quoted 5 lines
hw/virtio/vhost-vdpa.c new file +5
-0+ } + +static int vhost_vdpa_dev_start (struct vhost_dev *dev,bool started) +{ +struct vhost_vdpa *v = dev->opaque;newline is needed.
will add this
Quoted 56 lines
Quoted 56 lines
hw/virtio/vhost-vdpa.c new file +48
-0+if (started) { +uint8_t status =0 ; +memory_listener_register (&v->listener, &address_space_memory); +vhost_vdpa_set_vring_ready (dev); +vhost_vdpa_add_status (dev,VIRTIO_CONFIG_S_DRIVER_OK ); +vhost_vdpa_call (dev,VHOST_VDPA_GET_STATUS , &status); + +return !(status &VIRTIO_CONFIG_S_DRIVER_OK ); + }else { +vhost_vdpa_reset_device (dev); +vhost_vdpa_add_status (dev,VIRTIO_CONFIG_S_ACKNOWLEDGE | +VIRTIO_CONFIG_S_DRIVER ); +memory_listener_unregister (&v->listener); + +return 0 ; + } +} + +const VhostOps vdpa_ops = { + .backend_type =VHOST_BACKEND_TYPE_VDPA , + .vhost_backend_init = vhost_vdpa_init, + .vhost_backend_cleanup = vhost_vdpa_cleanup, + .vhost_set_log_base = vhost_kernel_set_log_base, + .vhost_set_vring_addr = vhost_kernel_set_vring_addr, + .vhost_set_vring_num = vhost_kernel_set_vring_num, + .vhost_set_vring_base = vhost_kernel_set_vring_base, + .vhost_get_vring_base = vhost_kernel_get_vring_base, + .vhost_set_vring_kick = vhost_kernel_set_vring_kick, + .vhost_set_vring_call = vhost_kernel_set_vring_call, + .vhost_get_features = vhost_kernel_get_features, + .vhost_set_owner = vhost_kernel_set_owner, + .vhost_set_vring_endian =NULL , + .vhost_backend_memslots_limit = vhost_vdpa_memslots_limit, + .vhost_set_mem_table = vhost_vdpa_set_mem_table, + .vhost_set_features = vhost_vdpa_set_features, + .vhost_reset_device = vhost_vdpa_reset_device, + .vhost_get_vq_index = vhost_vdpa_get_vq_index, + .vhost_get_config = vhost_vdpa_get_config, + .vhost_set_config = vhost_vdpa_set_config, + .vhost_requires_shm_log =NULL , + .vhost_migration_done =NULL , + .vhost_backend_can_merge =NULL , + .vhost_net_set_mtu =NULL , + .vhost_set_iotlb_callback =NULL , + .vhost_send_device_iotlb_msg =NULL , + .vhost_dev_start = vhost_vdpa_dev_start, + .vhost_get_device_id = vhost_vdpa_get_device_id, +};hw/virtio/vhost.c +0
-0@@ -744,19 +744,34 @@ static void vhost_iommu_region_del(MemoryListener *listener, } }
Quoted 10 lines
hw/virtio/vhost.c static void vhost_iommu_region_del(MemoryListener *listener, · line 752
Quoted 6 lines
hw/virtio/vhost.c +6
-0+static void vhost_virtqueue_get_addr (struct vhost_dev *dev, +struct vhost_vring_addr *addr, +struct vhost_virtqueue *vq) +{ +/*vDPA need to use the IOVA here to set to hardware*/ +if (dev->vhost_ops->backend_type ==VHOST_BACKEND_TYPE_VDPA ) {Let's introduce a new
vhost_opsfor this.
will add this
Quoted 25 lines
Quoted 25 lines
hw/virtio/vhost.c +11
-8+ addr->desc_user_addr = (uint64_t )(unsigned long )vq->desc_phys; + addr->avail_user_addr = (uint64_t )(unsigned long )vq->avail_phys; + addr->used_user_addr = (uint64_t )(unsigned long )vq->used_phys; + }else { + addr->desc_user_addr = (uint64_t )(unsigned long )vq->desc; + addr->avail_user_addr = (uint64_t )(unsigned long )vq->avail; + addr->used_user_addr = (uint64_t )(unsigned long )vq->used; + } +}static int vhost_virtqueue_set_addr (struct vhost_dev *dev,struct vhost_virtqueue *vq,unsigned idx,bool enable_log) { -struct vhost_vring_addr addr = { - .index = idx, - .desc_user_addr = (uint64_t )(unsigned long )vq->desc, - .avail_user_addr = (uint64_t )(unsigned long )vq->avail, - .used_user_addr = (uint64_t )(unsigned long )vq->used, - .log_guest_addr = vq->used_phys, - .flags = enable_log ? (1 <<VHOST_VRING_F_LOG ) :0 , - }; +struct vhost_vring_addr addr; +memset (&addr,0 ,sizeof (struct vhost_vring_addr ));
Quoted 10 lines
hw/virtio/vhost.c static void vhost_iommu_region_del(MemoryListener *listener, · line 773
Quoted 5 lines
hw/virtio/vhost.c +5
-0+ +vhost_virtqueue_get_addr (dev, &addr, vq); + addr.index = idx; + addr .log_guest_addr = vq->used_phys; + addr .flags = enable_log ? (1 <<VHOST_VRING_F_LOG ) :0 ;Unnecessary spaces between addr and log_guest_addr/flags.
Will remove this
Quoted 5 lines
Quoted 5 lines
hw/virtio/vhost.c +1
-0+int r = dev->vhost_ops->vhost_set_vring_addr (dev, &addr);if (r <0 ) {VHOST_OPS_DEBUG ("vhost_set_vring_addr failed" );@@ -774,7 +789,9 @@ static int vhost_dev_set_features(struct vhost_dev *dev,
Quoted 9 lines
hw/virtio/vhost.c static int vhost_dev_set_features(struct vhost_dev *dev, · line 777
Quoted 4 lines
hw/virtio/vhost.c +0
-1features |=0x1ULL <<VHOST_F_LOG_ALL ; }if (!vhost_dev_has_iommu (dev)) { - features &= ~(0x1ULL <<VIRTIO_F_IOMMU_PLATFORM );A comment is needed here.
will add this
Quoted 25 lines
Quoted 8 lines
hw/virtio/vhost.c +3
-0+if (dev->vhost_ops->backend_type !=VHOST_BACKEND_TYPE_VDPA ) { + features &= ~(0x1ULL <<VIRTIO_F_IOMMU_PLATFORM ); + } } r = dev->vhost_ops->vhost_set_features (dev, features);if (r <0 ) {hw/virtio/vhost.c int vhost_dev_start(struct vhost_dev *hdev, VirtIODevice *vdev) · line 1688
Quoted 6 lines
hw/virtio/vhost.c +2
-1@@ -1667,7 +1684,8 @@ int vhost_dev_start(struct vhost_dev *hdev, VirtIODevice *vdev) goto fail_log; } -if (vhost_dev_has_iommu (hdev)) { +if (vhost_dev_has_iommu (hdev) && + hdev->vhost_ops->vhost_set_iotlb_callback) {A separate patch for this please
Quoted 6 lines
hw/virtio/vhost.c +0
-0hdev->vhost_ops->vhost_set_iotlb_callback (hdev, true);/* Update used ring information for IOTLB to work correctly, @@ -1713,7 +1731,9 @@ void vhost_dev_stop(struct vhost_dev *hdev, VirtIODevice *vdev) }
Quoted 9 lines
hw/virtio/vhost.c void vhost_dev_stop(struct vhost_dev *hdev, VirtIODevice *vdev) · line 1736
Quoted 5 lines
hw/virtio/vhost.c +3
-1if (vhost_dev_has_iommu (hdev)) { - hdev->vhost_ops->vhost_set_iotlb_callback (hdev, false); +if (hdev->vhost_ops->vhost_set_iotlb_callback) { + hdev->vhost_ops->vhost_set_iotlb_callback (hdev, false); + }A separate patch for this.
will do
Quoted 21 lines
Quoted 21 lines
hw/virtio/vhost.c +0
-0memory_listener_unregister (&hdev->iommu_listener); }vhost_log_put (hdev, true);include/hw/virtio/vhost-backend.h +2
-1@@ -17,7 +17,8 @@ typedef enum VhostBackendType {VHOST_BACKEND_TYPE_NONE =0 ,VHOST_BACKEND_TYPE_KERNEL =1 ,VHOST_BACKEND_TYPE_USER =2 , -VHOST_BACKEND_TYPE_MAX =3 , +VHOST_BACKEND_TYPE_VDPA =3 , +VHOST_BACKEND_TYPE_MAX =4 , } VhostBackendType; typedef enum VhostSetConfigType {@@ -113,6 +114,7 @@ typedef int (*vhost_set_inflight_fd_op)(struct vhost_dev *dev, struct vhost_inflight *inflight);
Quoted 16 lines
include/hw/virtio/vhost-backend.h typedef struct VhostOps { · line 160
Quoted 11 lines
include/hw/virtio/vhost-backend.h +2
-0typedef int (*vhost_dev_start_op )(struct vhost_dev *dev,bool started); +typedef int (*vhost_get_device_id_op )(struct vhost_dev *dev,uint32_t *dev_id); typedef struct VhostOps { VhostBackendType backend_type; vhost_backend_init vhost_backend_init;@@ -154,9 +156,11 @@ typedef struct VhostOps {vhost_get_inflight_fd_op vhost_get_inflight_fd;vhost_set_inflight_fd_op vhost_set_inflight_fd;vhost_dev_start_op vhost_dev_start; +vhost_get_device_id_op vhost_get_device_id; } VhostOps;A separate patch for introducing this please.
will do
Quoted 56 lines
Quoted 43 lines
include/hw/virtio/vhost-backend.h +1
-0extern const VhostOps user_ops; +extern const VhostOps vdpa_ops;int vhost_set_backend_type (struct vhost_dev *dev,VhostBackendType backend_type);include/hw/virtio/vhost-vdpa.h new file +26
-0@@ -0,0 +1,26 @@ +/* +* vhost-vdpa.h +* +* Copyright(c) 2017-2018 Intel Corporation. +* Copyright(c) 2020 Red Hat, Inc. +* +* This work is licensed under the terms of the GNU GPL, version 2 or later. +* See the COPYING file in the top-level directory. +* +*/ + +#ifndef HW_VIRTIO_VHOST_VDPA_H +#define HW_VIRTIO_VHOST_VDPA_H + +#include "hw/virtio/virtio.h" + +typedef struct vhost_vdpa { +int device_fd; +uint32_t msg_type; +MemoryListener listener; +}VhostVDPA ; + +extern AddressSpace address_space_memory; +extern int vhost_vdpa_get_device_id (struct vhost_dev *dev, +uint32_t *device_id); +#endif include/hw/virtio/vhost.h +0
-0include/hw/virtio/vhost.h struct vhost_dev { · line 100
Quoted 9 lines
include/hw/virtio/vhost.h +6
-0@@ -92,6 +92,12 @@ struct vhost_dev {const VhostDevConfigOps *config_ops; }; +struct vhost_net { +struct vhost_dev dev; +struct vhost_virtqueue vqs[2 ]; +int backend; +NetClientState *nc; +};A separate patch for this exporting please.
Quoted 3 lines
Thanks
will do
Quoted 34 lines
Quoted 33 lines
include/hw/virtio/vhost.h +0
-0int vhost_dev_init(struct vhost_dev *hdev, void *opaque, VhostBackendType backend_type,qemu-options.hx +12
-0@@ -2409,6 +2409,10 @@ DEF("netdev", HAS_ARG, QEMU_OPTION_netdev, #ifdef CONFIG_POSIX "-netdev vhost-user,id=str,chardev=dev[,vhostforce=on|off]\n" " configure a vhost-user network, backed by a chardev 'dev'\n" +#endif +#ifdef __linux__ + "-netdev vhost-vdpa,id=str,vhostdev=/path/to/dev\n" + " configure a vhost-vdpa network,Establish a vhost-vdpa netdev\n" #endif "-netdev hubport,id=str,hubid=n[,netdev=nd]\n" " configure a hub port on the hub with ID 'n'\n", QEMU_ARCH_ALL)@@ -2888,6 +2892,14 @@ SRST -netdev type=vhost-user,id=net0,chardev=chr0 \ -device virtio-net-pci,netdev=net0 +``-netdev vhost-vdpa,vhostdev=/path/to/dev`` + Establish a vhost-vdpa netdev. + + vDPA device is a device that uses a datapath which complies with + the virtio specifications with a vendor specific control path. + vDPA devices can be both physically located on the hardware or + emulated by software. + ``-netdev hubport,id=id,hubid=hubid[,netdev=nd]`` Create a hub port on the emulated hub with ID hubid.
Re: [PATCH v1 09/10] vhost-vdpa: introduce vhost-vdpa backend
In reply to Cindy LuQuoted 32 lines · Cindy Lu
Currently we have 2 types of vhost backends in QEMU: vhost kernel and vhost-user. The above patch provides a generic device for vDPA purpose, this vDPA device exposes to user space a non-vendor-specific configuration interface for setting up a vhost HW accelerator, this patch set introduces a third vhost backend called vhost-vdpa based on the vDPA interface.
Vhost-vdpa usage:
qemu-system-x86_64 -cpu host -enable-kvm \ ...... -netdev type=vhost-vdpa,vhostdev=/dev/vhost-vdpa-id,id=vhost-vdpa0 \ -device virtio-net-pci,netdev=vhost-vdpa0,page-per-vq=on \Signed-off-by Lingshan zhu <[email protected]>Signed-off-by Tiwei Bie <[email protected]>Signed-off-by Cindy Lu <[email protected]>--- configure | 21 ++ hw/net/vhost_net.c | 19 +- hw/net/virtio-net.c | 19 +- hw/virtio/Makefile.objs | 1 + hw/virtio/vhost-backend.c | 22 +- hw/virtio/vhost-vdpa.c | 406 ++++++++++++++++++++++++++++++ hw/virtio/vhost.c | 42 +++- include/hw/virtio/vhost-backend.h | 6 +- include/hw/virtio/vhost-vdpa.h | 26 ++ include/hw/virtio/vhost.h | 6 + qemu-options.hx | 12 + 11 files changed, 555 insertions(+), 25 deletions(-) create mode 100644 hw/virtio/vhost-vdpa.c create mode 100644 include/hw/virtio/vhost-vdpa.h
...
Quoted 14 lines
hw/virtio/vhost-backend.c +1
-1@@ -14,7 +14,7 @@#include "qemu/error-report.h" #include "qemu/main-loop.h" #include "standard-headers/linux/vhost_types.h" - +#include "hw/virtio/vhost-vdpa.h" #ifdef CONFIG_VHOST_KERNEL #include <linux/vhost.h> #include <sys/ioctl.h>
hw/virtio/vhost-backend.c line 25
Quoted 7 lines
hw/virtio/vhost-backend.c +1
-3@@ -22,10 +22,19 @@static int vhost_kernel_call (struct vhost_dev *dev,unsigned long int request,void *arg) { -int fd = (uintptr_t ) dev->opaque; - -assert (dev->vhost_ops->backend_type ==VHOST_BACKEND_TYPE_KERNEL ); +int fd =-1 ;
You don't need to initialize fd before the switch() because all cases will set a value to it or assert.
hw/virtio/vhost-backend.c line 37
Quoted 12 lines
hw/virtio/vhost-backend.c +11
-0+switch (dev->vhost_ops->backend_type) { +case VHOST_BACKEND_TYPE_KERNEL : + fd = (uintptr_t )dev->opaque; +break ; +case VHOST_BACKEND_TYPE_VDPA : + fd = ((struct vhost_vdpa *)dev->opaque)->device_fd; +break ; +default : +g_assert_not_reached (); + } +assert (fd !=-1 );
Perhaps this assert is not needed:
Unitialized value will be catched by "default:", and there was no such kind of check on "(uintptr_t)dev->opaque" before.
Thanks,
Laurent
Re: [PATCH v1 09/10] vhost-vdpa: introduce vhost-vdpa backend
Quoted 71 lines · Laurent Vivier
Quoted 32 lines · Cindy Lu
Currently we have 2 types of vhost backends in QEMU: vhost kernel and vhost-user. The above patch provides a generic device for vDPA purpose, this vDPA device exposes to user space a non-vendor-specific configuration interface for setting up a vhost HW accelerator, this patch set introduces a third vhost backend called vhost-vdpa based on the vDPA interface.
Vhost-vdpa usage:
qemu-system-x86_64 -cpu host -enable-kvm \ ...... -netdev type=vhost-vdpa,vhostdev=/dev/vhost-vdpa-id,id=vhost-vdpa0 \ -device virtio-net-pci,netdev=vhost-vdpa0,page-per-vq=on \Signed-off-by Lingshan zhu <[email protected]>Signed-off-by Tiwei Bie <[email protected]>Signed-off-by Cindy Lu <[email protected]>--- configure | 21 ++ hw/net/vhost_net.c | 19 +- hw/net/virtio-net.c | 19 +- hw/virtio/Makefile.objs | 1 + hw/virtio/vhost-backend.c | 22 +- hw/virtio/vhost-vdpa.c | 406 ++++++++++++++++++++++++++++++ hw/virtio/vhost.c | 42 +++- include/hw/virtio/vhost-backend.h | 6 +- include/hw/virtio/vhost-vdpa.h | 26 ++ include/hw/virtio/vhost.h | 6 + qemu-options.hx | 12 + 11 files changed, 555 insertions(+), 25 deletions(-) create mode 100644 hw/virtio/vhost-vdpa.c create mode 100644 include/hw/virtio/vhost-vdpa.h...
Quoted 14 lines
hw/virtio/vhost-backend.c +1
-1@@ -14,7 +14,7 @@#include "qemu/error-report.h" #include "qemu/main-loop.h" #include "standard-headers/linux/vhost_types.h" - +#include "hw/virtio/vhost-vdpa.h" #ifdef CONFIG_VHOST_KERNEL #include <linux/vhost.h> #include <sys/ioctl.h> hw/virtio/vhost-backend.c line 25
Quoted 7 lines
hw/virtio/vhost-backend.c +1
-3@@ -22,10 +22,19 @@static int vhost_kernel_call (struct vhost_dev *dev,unsigned long int request,void *arg) { -int fd = (uintptr_t ) dev->opaque; - -assert (dev->vhost_ops->backend_type ==VHOST_BACKEND_TYPE_KERNEL ); +int fd =-1 ;You don't need to initialize fd before the
switch()because all cases will set a value to it or assert.Quoted 11 lines
hw/virtio/vhost-backend.c +10
-0+switch (dev->vhost_ops->backend_type) { +case VHOST_BACKEND_TYPE_KERNEL : + fd = (uintptr_t )dev->opaque; +break ; +case VHOST_BACKEND_TYPE_VDPA : + fd = ((struct vhost_vdpa *)dev->opaque)->device_fd; +break ; +default : +g_assert_not_reached (); + }
Quoted 6 lines
hw/virtio/vhost-backend.c line 37
Quoted 1 line
hw/virtio/vhost-backend.c +1
-0+assert (fd !=-1 );Perhaps this assert is not needed:
Unitialized value will be catched by "default:", and there was no such kind of check on "(uintptr_t)dev->opaque" before.
sure, thanks will fix this
Quoted 3 lines
Thanks,
Laurent
Re: [PATCH v1 09/10] vhost-vdpa: introduce vhost-vdpa backend
In reply to Cindy LuQuoted 515 lines · Cindy Lu
Currently we have 2 types of vhost backends in QEMU: vhost kernel and vhost-user. The above patch provides a generic device for vDPA purpose, this vDPA device exposes to user space a non-vendor-specific configuration interface for setting up a vhost HW accelerator, this patch set introduces a third vhost backend called vhost-vdpa based on the vDPA interface.
Vhost-vdpa usage:
qemu-system-x86_64 -cpu host -enable-kvm \ ...... -netdev type=vhost-vdpa,vhostdev=/dev/vhost-vdpa-id,id=vhost-vdpa0 \ -device virtio-net-pci,netdev=vhost-vdpa0,page-per-vq=on \Signed-off-by Lingshan zhu <[email protected]>Signed-off-by Tiwei Bie <[email protected]>Signed-off-by Cindy Lu <[email protected]>--- configure | 21 ++ hw/net/vhost_net.c | 19 +- hw/net/virtio-net.c | 19 +- hw/virtio/Makefile.objs | 1 + hw/virtio/vhost-backend.c | 22 +- hw/virtio/vhost-vdpa.c | 406 ++++++++++++++++++++++++++++++ hw/virtio/vhost.c | 42 +++- include/hw/virtio/vhost-backend.h | 6 +- include/hw/virtio/vhost-vdpa.h | 26 ++ include/hw/virtio/vhost.h | 6 + qemu-options.hx | 12 + 11 files changed, 555 insertions(+), 25 deletions(-) create mode 100644 hw/virtio/vhost-vdpa.c create mode 100644 include/hw/virtio/vhost-vdpa.hconfigure +21
-0@@ -1557,6 +1557,10 @@ for opt do ;; --enable-vhost-user) vhost_user="yes" ;; + --disable-vhost-vdpa) vhost_vdpa="no" + ;; + --enable-vhost-vdpa) vhost_vdpa="yes" + ;; --disable-vhost-kernel) vhost_kernel="no" ;; --enable-vhost-kernel) vhost_kernel="yes"@@ -1846,6 +1850,7 @@ disabled with --disable-FEATURE, default is enabled if available: vhost-crypto vhost-user-crypto backend support vhost-kernel vhost kernel backend support vhost-user vhost-user backend support + vhost-vdpa vhost-vdpa kernel backend support spice spice rbd rados block device (rbd) libiscsi iscsi support@@ -2336,6 +2341,10 @@ test "$vhost_user" = "" && vhost_user=yes if test "$vhost_user" = "yes" && test "$mingw32" = "yes"; then error_exit "vhost-user isn't available on win32" fi +test "$vhost_vdpa" = "" && vhost_vdpa=$linux +if test "$vhost_vdpa" = "yes" && test "$linux" != "yes"; then + error_exit "vhost-vdpa is only available on Linux" +fi test "$vhost_kernel" = "" && vhost_kernel=$linux if test "$vhost_kernel" = "yes" && test "$linux" != "yes"; then error_exit "vhost-kernel is only available on Linux"@@ -2364,6 +2373,11 @@ test "$vhost_user_fs" = "" && vhost_user_fs=$vhost_user if test "$vhost_user_fs" = "yes" && test "$vhost_user" = "no"; then error_exit "--enable-vhost-user-fs requires --enable-vhost-user" fi +#vhost-vdpa backends +test "$vhost_net_vdpa" = "" && vhost_net_vdpa=$vhost_vdpa +if test "$vhost_net_vdpa" = "yes" && test "$vhost_vdpa" = "no"; then + error_exit "--enable-vhost-net-vdpa requires --enable-vhost-vdpa" +fi # OR the vhost-kernel and vhost-user values for simplicity if test "$vhost_net" = ""; then@@ -6673,6 +6687,7 @@ echo "vhost-scsi support $vhost_scsi" echo "vhost-vsock support $vhost_vsock" echo "vhost-user support $vhost_user" echo "vhost-user-fs support $vhost_user_fs" +echo "vhost-vdpa support $vhost_vdpa" echo "Trace backends $trace_backends" if have_backend "simple"; then echo "Trace output file $trace_file-<pid>"@@ -7170,6 +7185,9 @@ fi if test "$vhost_net_user" = "yes" ; then echo "CONFIG_VHOST_NET_USER=y" >> $config_host_mak fi +if test "$vhost_net_vdpa" = "yes" ; then + echo "CONFIG_VHOST_NET_VDPA=y" >> $config_host_mak +fi if test "$vhost_crypto" = "yes" ; then echo "CONFIG_VHOST_CRYPTO=y" >> $config_host_mak fi@@ -7182,6 +7200,9 @@ fi if test "$vhost_user" = "yes" ; then echo "CONFIG_VHOST_USER=y" >> $config_host_mak fi +if test "$vhost_vdpa" = "yes" ; then + echo "CONFIG_VHOST_VDPA=y" >> $config_host_mak +fi if test "$vhost_user_fs" = "yes" ; then echo "CONFIG_VHOST_USER_FS=y" >> $config_host_mak fihw/net/vhost_net.c +12
-7@@ -17,8 +17,10 @@#include "net/net.h" #include "net/tap.h" #include "net/vhost-user.h" +#include "net/vhost-vdpa.h" #include "standard-headers/linux/vhost_types.h" +#include "linux-headers/linux/vhost.h" #include "hw/virtio/virtio-net.h" #include "net/vhost_net.h" #include "qemu/error-report.h" @@ -33,12 +35,6 @@#include "hw/virtio/vhost.h" #include "hw/virtio/virtio-bus.h" -struct vhost_net { -struct vhost_dev dev; -struct vhost_virtqueue vqs[2 ]; -int backend; -NetClientState *nc; -};/* Features supported by host kernel. */ static const int kernel_feature_bits[] = {@@ -84,7 +80,6 @@ static const int user_feature_bits[] = { VHOST_INVALID_FEATURE_BIT }; -static const int *vhost_net_get_feature_bits (struct vhost_net *net) {const int *feature_bits =0 ;@@ -96,6 +91,9 @@ static const int *vhost_net_get_feature_bits(struct vhost_net *net)case NET_CLIENT_DRIVER_VHOST_USER : feature_bits = user_feature_bits;break ; +case NET_CLIENT_DRIVER_VHOST_VDPA : + feature_bits = vdpa_feature_bits; +break ;default :error_report ("Feature bits not defined for this type: %d" , net->nc->info->type);@@ -348,6 +346,7 @@ int vhost_net_start(VirtIODevice *dev, NetClientState *ncs, }for (i =0 ; i < total_queues; i++) { + peer =qemu_get_peer (ncs, i); r =vhost_net_start_one (get_vhost_net (peer), dev);@@ -444,6 +443,12 @@ VHostNetState *get_vhost_net(NetClientState *nc) vhost_net =vhost_user_get_vhost_net (nc);assert (vhost_net);break ; +#endif +#ifdef CONFIG_VHOST_NET_VDPA +case NET_CLIENT_DRIVER_VHOST_VDPA : + vhost_net =vhost_vdpa_get_vhost_net (nc); +assert (vhost_net); +break ;#endif default :break ;hw/net/virtio-net.c +17
-2@@ -42,6 +42,7 @@#include "trace.h" #include "monitor/qdev.h" #include "hw/pci/pci.h" +#include "hw/virtio/vhost.h" #define VIRTIO_NET_VM_VERSION 11@@ -131,6 +132,8 @@ static void virtio_net_get_config(VirtIODevice *vdev, uint8_t *config) {VirtIONet *n =VIRTIO_NET (vdev);struct virtio_net_config netcfg; +int ret =0 ; +memset (&netcfg,0 ,sizeof (struct virtio_net_config ));virtio_stw_p (vdev, &netcfg.status, n->status);virtio_stw_p (vdev, &netcfg.max_virtqueue_pairs, n->max_queues);@@ -139,13 +142,21 @@ static void virtio_net_get_config(VirtIODevice *vdev, uint8_t *config)virtio_stl_p (vdev, &netcfg.speed, n->net_conf.speed); netcfg.duplex = n->net_conf.duplex;memcpy (config, &netcfg, n->config_size); +NetClientState *nc =qemu_get_queue (n->nic); +if (nc->peer->info->type ==NET_CLIENT_DRIVER_VHOST_VDPA ) { + ret =vhost_net_get_config (get_vhost_net (nc->peer), (uint8_t *)&netcfg, + n->config_size); +if (ret !=-1 ) { +memcpy (config, &netcfg, n->config_size); + } + } }static void virtio_net_set_config (VirtIODevice *vdev,const uint8_t *config) {VirtIONet *n =VIRTIO_NET (vdev); +NetClientState *nc =qemu_get_queue (n->nic);struct virtio_net_config netcfg = {}; -memcpy (&netcfg, config, n->config_size); if (!virtio_vdev_has_feature(vdev, VIRTIO_NET_F_CTRL_MAC_ADDR) &&@@ -154,6 +165,11 @@ static void virtio_net_set_config(VirtIODevice *vdev, const uint8_t *config)memcpy (n->mac, netcfg.mac,ETH_ALEN );qemu_format_nic_info_str (qemu_get_queue (n->nic), n->mac); } +if (nc->peer->info->type ==NET_CLIENT_DRIVER_VHOST_VDPA ) { +vhost_net_set_config (get_vhost_net (nc->peer), (uint8_t *)&netcfg, +0 , n->config_size, +VHOST_SET_CONFIG_TYPE_MASTER ); + } }static bool virtio_net_started (VirtIONet *n,uint8_t status)@@ -2958,7 +2974,6 @@ static void virtio_net_device_realize(DeviceState *dev, Error **errp) }else if (n->net_conf.speed >=0 ) { n->host_features |= (1ULL <<VIRTIO_NET_F_SPEED_DUPLEX ); } -if (n->failover) { n->primary_listener.should_be_hidden = virtio_net_primary_should_be_hidden;hw/virtio/Makefile.objs +1
-0@@ -5,6 +5,7 @@ obj-y += virtio.o obj-$(CONFIG_VHOST) += vhost.o vhost-backend.o common-obj-$(call lnot,$(CONFIG_VHOST)) += vhost-stub.o obj-$(CONFIG_VHOST_USER) += vhost-user.o +obj-$(CONFIG_VHOST_VDPA) += vhost-vdpa.o common-obj-$(CONFIG_VIRTIO_RNG) += virtio-rng.o common-obj-$(CONFIG_VIRTIO_PCI) += virtio-pci.ohw/virtio/vhost-backend.c +18
-4@@ -14,7 +14,7 @@#include "qemu/error-report.h" #include "qemu/main-loop.h" #include "standard-headers/linux/vhost_types.h" - +#include "hw/virtio/vhost-vdpa.h" #ifdef CONFIG_VHOST_KERNEL #include <linux/vhost.h> #include <sys/ioctl.h> @@ -22,10 +22,19 @@static int vhost_kernel_call (struct vhost_dev *dev,unsigned long int request,void *arg) { -int fd = (uintptr_t ) dev->opaque; - -assert (dev->vhost_ops->backend_type ==VHOST_BACKEND_TYPE_KERNEL ); +int fd =-1 ; +switch (dev->vhost_ops->backend_type) { +case VHOST_BACKEND_TYPE_KERNEL : + fd = (uintptr_t )dev->opaque; +break ; +case VHOST_BACKEND_TYPE_VDPA : + fd = ((struct vhost_vdpa *)dev->opaque)->device_fd; +break ; +default : +g_assert_not_reached (); + } +assert (fd !=-1 );return ioctl (fd, request, arg); }@@ -285,6 +294,11 @@ int vhost_set_backend_type(struct vhost_dev *dev, VhostBackendType backend_type)case VHOST_BACKEND_TYPE_USER : dev->vhost_ops = &user_ops;break ; +#endif +#ifdef CONFIG_VHOST_VDPA +case VHOST_BACKEND_TYPE_VDPA : + dev->vhost_ops = &vdpa_ops; +break ;#endif default :error_report ("Unknown vhost backend type" );hw/virtio/vhost-vdpa.c new file +212
-0@@ -0,0 +1,406 @@ +/* +* vhost-vdpa +* +* Copyright(c) 2017-2018 Intel Corporation. +* Copyright(c) 2020 Red Hat, Inc. +* +* This work is licensed under the terms of the GNU GPL, version 2 or later. +* See the COPYING file in the top-level directory. +* +*/ + +#include "qemu/osdep.h" +#include <linux/vhost.h> +#include <linux/vfio.h> +#include <sys/eventfd.h> +#include <sys/ioctl.h> +#include "hw/virtio/vhost.h" +#include "hw/virtio/vhost-backend.h" +#include "hw/virtio/virtio-net.h" +#include "hw/virtio/vhost-vdpa.h" +#include "qemu/main-loop.h" +#include <linux/kvm.h> +#include "sysemu/kvm.h" + + +static bool vhost_vdpa_listener_skipped_section (MemoryRegionSection *section) +{ +return (!memory_region_is_ram (section->mr) && + !memory_region_is_iommu (section->mr)) || +/* +* Sizing an enabled 64-bit BAR can cause spurious mappings to +* addresses in the upper part of the 64-bit address space. These +* are never accessed by the CPU and beyond the address width of +* some IOMMU hardware. TODO: VDPA should tell us the IOMMU width. +*/ + section->offset_within_address_space & (1ULL <<63 ); +} + +static int vhost_vdpa_dma_map (struct vhost_vdpa *v,hwaddr iova,hwaddr size, +void *vaddr,bool readonly) +{ +struct vhost_msg_v2 msg; +int fd = v->device_fd; +int ret =0 ; + + msg.type = v->msg_type; + msg.iotlb.iova = iova; + msg.iotlb.size = size; + msg.iotlb.uaddr = (uint64_t )vaddr; + msg.iotlb.perm = readonly ?VHOST_ACCESS_RO :VHOST_ACCESS_RW ; + msg.iotlb.type =VHOST_IOTLB_UPDATE ; + +if (write (fd, &msg,sizeof (msg)) !=sizeof (msg)) { +error_report ("failed to write, fd=%d, errno=%d (%s)" , + fd, errno,strerror (errno)); +return -EIO ; + } + +return ret; +} + +static int vhost_vdpa_dma_unmap (struct vhost_vdpa *v,hwaddr iova, +hwaddr size) +{ +struct vhost_msg_v2 msg; +int fd = v->device_fd; +int ret =0 ; + + msg.type = v->msg_type; + msg.iotlb.iova = iova; + msg.iotlb.size = size; + msg.iotlb.type =VHOST_IOTLB_INVALIDATE ; + +if (write (fd, &msg,sizeof (msg)) !=sizeof (msg)) { +error_report ("failed to write, fd=%d, errno=%d (%s)" , + fd, errno,strerror (errno)); +return -EIO ; + } + +return ret; +} + +static void vhost_vdpa_listener_region_add (MemoryListener *listener, +MemoryRegionSection *section) +{ + struct vhost_vdpa *v = container_of(listener, struct vhost_vdpa, listener); +hwaddr iova; +Int128 llend, llsize; +void *vaddr; +int ret; + +if (vhost_vdpa_listener_skipped_section (section)) { +return ; + } + +if (unlikely ((section->offset_within_address_space & ~TARGET_PAGE_MASK ) != + (section->offset_within_region & ~TARGET_PAGE_MASK ))) { +error_report ("%s received unaligned region" , __func__); +return ; + } + + iova =TARGET_PAGE_ALIGN (section->offset_within_address_space); + llend =int128_make64 (section->offset_within_address_space); + llend =int128_add (llend, section->size); + llend =int128_and (llend,int128_exts64 (TARGET_PAGE_MASK )); + +if (int128_ge (int128_make64 (iova), llend)) { +return ; + } + +memory_region_ref (section->mr); + +/* Here we assume that memory_region_is_ram(section->mr)==true */ + + vaddr =memory_region_get_ram_ptr (section->mr) + + section->offset_within_region + + (iova - section->offset_within_address_space); + + llsize =int128_sub (llend,int128_make64 (iova)); + + ret =vhost_vdpa_dma_map (v, iova,int128_get64 (llsize), + vaddr, section->readonly); +if (ret) { +error_report ("vhost vdpa map fail!" ); +if (memory_region_is_ram_device (section->mr)) { +/* Allow unexpected mappings not to be fatal for RAM devices */ +error_report ("map ram fail!" ); +return ; + } + goto fail; + } + +return ; + +fail: +if (memory_region_is_ram_device (section->mr)) { +error_report ("failed to vdpa_dma_map. pci p2p may not work" ); +return ; + + } +/* +* On the initfn path, store the first error in the container so we +* can gracefully fail. Runtime, there's not much we can do other +* than throw a hardware error. +*/ +error_report ("vhost-vdpa: DMA mapping failed, unable to continue" ); +return ; + +} + +static void vhost_vdpa_listener_region_del (MemoryListener *listener, +MemoryRegionSection *section) +{ + struct vhost_vdpa *v = container_of(listener, struct vhost_vdpa, listener); +hwaddr iova; +Int128 llend, llsize; +int ret; +bool try_unmap = true; + +if (vhost_vdpa_listener_skipped_section (section)) { +return ; + } + +if (unlikely ((section->offset_within_address_space & ~TARGET_PAGE_MASK ) != + (section->offset_within_region & ~TARGET_PAGE_MASK ))) { +error_report ("%s received unaligned region" , __func__); +return ; + } + + iova =TARGET_PAGE_ALIGN (section->offset_within_address_space); + llend =int128_make64 (section->offset_within_address_space); + llend =int128_add (llend, section->size); + llend =int128_and (llend,int128_exts64 (TARGET_PAGE_MASK )); + +if (int128_ge (int128_make64 (iova), llend)) { +return ; + } + + llsize =int128_sub (llend,int128_make64 (iova)); + +if (try_unmap) { + ret =vhost_vdpa_dma_unmap (v, iova,int128_get64 (llsize)); +if (ret) { +error_report ("vhost_vdpa dma unmap error!" ); + } + } + +memory_region_unref (section->mr); +} +/* +* IOTLB API is used by vhost-vpda which requires incremental updating +* of the mapping. So we can not use generic vhost memory listener which +* depends on the addnop(). +*/ +static const MemoryListener vhost_vdpa_memory_listener = { + .region_add = vhost_vdpa_listener_region_add, + .region_del = vhost_vdpa_listener_region_del, +}; + +static int vhost_vdpa_call (struct vhost_dev *dev,unsigned long int request, +void *arg) +{ +struct vhost_vdpa *v = dev->opaque; +int fd = v->device_fd; + +assert (dev->vhost_ops->backend_type ==VHOST_BACKEND_TYPE_VDPA ); + +return ioctl (fd, request, arg); +} + +static void vhost_vdpa_add_status (struct vhost_dev *dev,uint8_t status) +{
hw/virtio/vhost-vdpa.c line 222
Quoted 10 lines
hw/virtio/vhost-vdpa.c new file +10
-0+uint8_t s; + +if (vhost_vdpa_call (dev,VHOST_VDPA_GET_STATUS , &s)) { +return ; + } + + s |= status; + +vhost_vdpa_call (dev,VHOST_VDPA_SET_STATUS , &s); +}
I think it would be better to have backend ops for SET_STATUS and GET_STATUS to avoid duplicating code in every backends that wish to support it.
Also, I think that SET_STATUS should forward directly the Virtio device status updates written by the Virtio driver.
Quoted 376 lines
hw/virtio/vhost-vdpa.c new file +183
-0+static int vhost_vdpa_init (struct vhost_dev *dev,void *opaque) +{ +struct vhost_vdpa *v; +uint64_t features; +assert (dev->vhost_ops->backend_type ==VHOST_BACKEND_TYPE_VDPA ); + + v = opaque; + dev->opaque = opaque ; +vhost_vdpa_call (dev,VHOST_GET_FEATURES , &features); + dev->backend_features = features; + v->listener = vhost_vdpa_memory_listener; + v->msg_type =VHOST_IOTLB_MSG_V2 ; + +vhost_vdpa_add_status (dev,VIRTIO_CONFIG_S_ACKNOWLEDGE | +VIRTIO_CONFIG_S_DRIVER ); + +return 0 ; +} + +static int vhost_vdpa_cleanup (struct vhost_dev *dev) +{ +struct vhost_vdpa *v; +assert (dev->vhost_ops->backend_type ==VHOST_BACKEND_TYPE_VDPA ); + v = dev->opaque; +memory_listener_unregister (&v->listener); + + dev->opaque =NULL ; +return 0 ; +} + +static int vhost_vdpa_memslots_limit (struct vhost_dev *dev) +{ +return INT_MAX ; +} + +static int vhost_vdpa_set_mem_table (struct vhost_dev *dev, +struct vhost_memory *mem) +{ + +if (mem->padding) { +return -1 ; + } + +return 0 ; +} + +static int vhost_vdpa_set_features (struct vhost_dev *dev, +uint64_t features) +{ +int ret; + ret =vhost_vdpa_call (dev,VHOST_SET_FEATURES , &features); +uint8_t status =0 ; +if (ret) { +return ret; + } +vhost_vdpa_add_status (dev,VIRTIO_CONFIG_S_FEATURES_OK ); +vhost_vdpa_call (dev,VHOST_VDPA_GET_STATUS , &status); + +return !(status &VIRTIO_CONFIG_S_FEATURES_OK ); +} + +int vhost_vdpa_get_device_id (struct vhost_dev *dev, +uint32_t *device_id) +{ +return vhost_vdpa_call (dev,VHOST_VDPA_GET_DEVICE_ID , device_id); +} + +static int vhost_vdpa_reset_device (struct vhost_dev *dev) +{ +uint8_t status =0 ; + +return vhost_vdpa_call (dev,VHOST_VDPA_SET_STATUS , &status); +} + +static int vhost_vdpa_get_vq_index (struct vhost_dev *dev,int idx) +{ +assert (idx >= dev->vq_index && idx < dev->vq_index + dev->nvqs); + +return idx - dev->vq_index; +} + +static int vhost_vdpa_set_vring_ready (struct vhost_dev *dev) +{ +int i; +for (i =0 ; i < dev->nvqs; ++i) { +struct vhost_vring_state state = { + .index = dev->vq_index + i, + .num =1 , + }; +vhost_vdpa_call (dev,VHOST_VDPA_SET_VRING_ENABLE , &state); + } +return 0 ; +} + +static int vhost_vdpa_set_config (struct vhost_dev *dev,const uint8_t *data, +uint32_t offset,uint32_t size, +uint32_t flags) +{ +struct vhost_vdpa_config *config; +int ret; +unsigned long config_size = offsetof(struct vhost_vdpa_config , buf); + config =g_malloc (size + config_size); +if (config ==NULL ) { +return -1 ; + } + config->off = offset; + config->len = size; +memcpy (config->buf, data, size); + ret =vhost_vdpa_call (dev,VHOST_VDPA_SET_CONFIG , config); +g_free (config); +return ret; +} + +static int vhost_vdpa_get_config (struct vhost_dev *dev,uint8_t *config, +uint32_t config_len) +{ +struct vhost_vdpa_config *v_config; +unsigned long config_size = offsetof(struct vhost_vdpa_config , buf); +int ret; + + v_config =g_malloc (config_len + config_size); +if (v_config ==NULL ) { +return -1 ; + } + v_config->len = config_len; + v_config->off =0 ; + ret =vhost_vdpa_call (dev,VHOST_VDPA_GET_CONFIG , v_config); +memcpy (config, v_config->buf, config_len); +g_free (v_config); +return ret; + } + +static int vhost_vdpa_dev_start (struct vhost_dev *dev,bool started) +{ +struct vhost_vdpa *v = dev->opaque; +if (started) { +uint8_t status =0 ; +memory_listener_register (&v->listener, &address_space_memory); +vhost_vdpa_set_vring_ready (dev); +vhost_vdpa_add_status (dev,VIRTIO_CONFIG_S_DRIVER_OK ); +vhost_vdpa_call (dev,VHOST_VDPA_GET_STATUS , &status); + +return !(status &VIRTIO_CONFIG_S_DRIVER_OK ); + }else { +vhost_vdpa_reset_device (dev); +vhost_vdpa_add_status (dev,VIRTIO_CONFIG_S_ACKNOWLEDGE | +VIRTIO_CONFIG_S_DRIVER ); +memory_listener_unregister (&v->listener); + +return 0 ; + } +} + +const VhostOps vdpa_ops = { + .backend_type =VHOST_BACKEND_TYPE_VDPA , + .vhost_backend_init = vhost_vdpa_init, + .vhost_backend_cleanup = vhost_vdpa_cleanup, + .vhost_set_log_base = vhost_kernel_set_log_base, + .vhost_set_vring_addr = vhost_kernel_set_vring_addr, + .vhost_set_vring_num = vhost_kernel_set_vring_num, + .vhost_set_vring_base = vhost_kernel_set_vring_base, + .vhost_get_vring_base = vhost_kernel_get_vring_base, + .vhost_set_vring_kick = vhost_kernel_set_vring_kick, + .vhost_set_vring_call = vhost_kernel_set_vring_call, + .vhost_get_features = vhost_kernel_get_features, + .vhost_set_owner = vhost_kernel_set_owner, + .vhost_set_vring_endian =NULL , + .vhost_backend_memslots_limit = vhost_vdpa_memslots_limit, + .vhost_set_mem_table = vhost_vdpa_set_mem_table, + .vhost_set_features = vhost_vdpa_set_features, + .vhost_reset_device = vhost_vdpa_reset_device, + .vhost_get_vq_index = vhost_vdpa_get_vq_index, + .vhost_get_config = vhost_vdpa_get_config, + .vhost_set_config = vhost_vdpa_set_config, + .vhost_requires_shm_log =NULL , + .vhost_migration_done =NULL , + .vhost_backend_can_merge =NULL , + .vhost_net_set_mtu =NULL , + .vhost_set_iotlb_callback =NULL , + .vhost_send_device_iotlb_msg =NULL , + .vhost_dev_start = vhost_vdpa_dev_start, + .vhost_get_device_id = vhost_vdpa_get_device_id, +};hw/virtio/vhost.c +31
-11@@ -744,19 +744,34 @@ static void vhost_iommu_region_del(MemoryListener *listener, } } +static void vhost_virtqueue_get_addr (struct vhost_dev *dev, +struct vhost_vring_addr *addr, +struct vhost_virtqueue *vq) +{ +/*vDPA need to use the IOVA here to set to hardware*/ +if (dev->vhost_ops->backend_type ==VHOST_BACKEND_TYPE_VDPA ) { + addr->desc_user_addr = (uint64_t )(unsigned long )vq->desc_phys; + addr->avail_user_addr = (uint64_t )(unsigned long )vq->avail_phys; + addr->used_user_addr = (uint64_t )(unsigned long )vq->used_phys; + }else { + addr->desc_user_addr = (uint64_t )(unsigned long )vq->desc; + addr->avail_user_addr = (uint64_t )(unsigned long )vq->avail; + addr->used_user_addr = (uint64_t )(unsigned long )vq->used; + } +}static int vhost_virtqueue_set_addr (struct vhost_dev *dev,struct vhost_virtqueue *vq,unsigned idx,bool enable_log) { -struct vhost_vring_addr addr = { - .index = idx, - .desc_user_addr = (uint64_t )(unsigned long )vq->desc, - .avail_user_addr = (uint64_t )(unsigned long )vq->avail, - .used_user_addr = (uint64_t )(unsigned long )vq->used, - .log_guest_addr = vq->used_phys, - .flags = enable_log ? (1 <<VHOST_VRING_F_LOG ) :0 , - }; +struct vhost_vring_addr addr; +memset (&addr,0 ,sizeof (struct vhost_vring_addr )); + +vhost_virtqueue_get_addr (dev, &addr, vq); + addr.index = idx; + addr .log_guest_addr = vq->used_phys; + addr .flags = enable_log ? (1 <<VHOST_VRING_F_LOG ) :0 ; +int r = dev->vhost_ops->vhost_set_vring_addr (dev, &addr);if (r <0 ) {VHOST_OPS_DEBUG ("vhost_set_vring_addr failed" );@@ -774,7 +789,9 @@ static int vhost_dev_set_features(struct vhost_dev *dev, features |=0x1ULL <<VHOST_F_LOG_ALL ; }if (!vhost_dev_has_iommu (dev)) { - features &= ~(0x1ULL <<VIRTIO_F_IOMMU_PLATFORM ); +if (dev->vhost_ops->backend_type !=VHOST_BACKEND_TYPE_VDPA ) { + features &= ~(0x1ULL <<VIRTIO_F_IOMMU_PLATFORM ); + } } r = dev->vhost_ops->vhost_set_features (dev, features);if (r <0 ) {@@ -1667,7 +1684,8 @@ int vhost_dev_start(struct vhost_dev *hdev, VirtIODevice *vdev) goto fail_log; } -if (vhost_dev_has_iommu (hdev)) { +if (vhost_dev_has_iommu (hdev) && + hdev->vhost_ops->vhost_set_iotlb_callback) { hdev->vhost_ops->vhost_set_iotlb_callback (hdev, true);/* Update used ring information for IOTLB to work correctly, @@ -1713,7 +1731,9 @@ void vhost_dev_stop(struct vhost_dev *hdev, VirtIODevice *vdev) }if (vhost_dev_has_iommu (hdev)) { - hdev->vhost_ops->vhost_set_iotlb_callback (hdev, false); +if (hdev->vhost_ops->vhost_set_iotlb_callback) { + hdev->vhost_ops->vhost_set_iotlb_callback (hdev, false); + }memory_listener_unregister (&hdev->iommu_listener); }vhost_log_put (hdev, true);include/hw/virtio/vhost-backend.h +5
-1@@ -17,7 +17,8 @@ typedef enum VhostBackendType {VHOST_BACKEND_TYPE_NONE =0 ,VHOST_BACKEND_TYPE_KERNEL =1 ,VHOST_BACKEND_TYPE_USER =2 , -VHOST_BACKEND_TYPE_MAX =3 , +VHOST_BACKEND_TYPE_VDPA =3 , +VHOST_BACKEND_TYPE_MAX =4 , } VhostBackendType; typedef enum VhostSetConfigType {@@ -113,6 +114,7 @@ typedef int (*vhost_set_inflight_fd_op)(struct vhost_dev *dev, struct vhost_inflight *inflight);typedef int (*vhost_dev_start_op )(struct vhost_dev *dev,bool started); +typedef int (*vhost_get_device_id_op )(struct vhost_dev *dev,uint32_t *dev_id); typedef struct VhostOps { VhostBackendType backend_type; vhost_backend_init vhost_backend_init;@@ -154,9 +156,11 @@ typedef struct VhostOps {vhost_get_inflight_fd_op vhost_get_inflight_fd;vhost_set_inflight_fd_op vhost_set_inflight_fd;vhost_dev_start_op vhost_dev_start; +vhost_get_device_id_op vhost_get_device_id; } VhostOps;extern const VhostOps user_ops; +extern const VhostOps vdpa_ops;int vhost_set_backend_type (struct vhost_dev *dev,VhostBackendType backend_type);include/hw/virtio/vhost-vdpa.h new file +26
-0@@ -0,0 +1,26 @@ +/* +* vhost-vdpa.h +* +* Copyright(c) 2017-2018 Intel Corporation. +* Copyright(c) 2020 Red Hat, Inc. +* +* This work is licensed under the terms of the GNU GPL, version 2 or later. +* See the COPYING file in the top-level directory. +* +*/ + +#ifndef HW_VIRTIO_VHOST_VDPA_H +#define HW_VIRTIO_VHOST_VDPA_H + +#include "hw/virtio/virtio.h" + +typedef struct vhost_vdpa { +int device_fd; +uint32_t msg_type; +MemoryListener listener; +}VhostVDPA ; + +extern AddressSpace address_space_memory; +extern int vhost_vdpa_get_device_id (struct vhost_dev *dev, +uint32_t *device_id); +#endif include/hw/virtio/vhost.h +6
-0@@ -92,6 +92,12 @@ struct vhost_dev {const VhostDevConfigOps *config_ops; }; +struct vhost_net { +struct vhost_dev dev; +struct vhost_virtqueue vqs[2 ]; +int backend; +NetClientState *nc; +}; int vhost_dev_init(struct vhost_dev *hdev, void *opaque, VhostBackendType backend_type,qemu-options.hx +12
-0@@ -2409,6 +2409,10 @@ DEF("netdev", HAS_ARG, QEMU_OPTION_netdev, #ifdef CONFIG_POSIX "-netdev vhost-user,id=str,chardev=dev[,vhostforce=on|off]\n" " configure a vhost-user network, backed by a chardev 'dev'\n" +#endif +#ifdef __linux__ + "-netdev vhost-vdpa,id=str,vhostdev=/path/to/dev\n" + " configure a vhost-vdpa network,Establish a vhost-vdpa netdev\n" #endif "-netdev hubport,id=str,hubid=n[,netdev=nd]\n" " configure a hub port on the hub with ID 'n'\n", QEMU_ARCH_ALL)@@ -2888,6 +2892,14 @@ SRST -netdev type=vhost-user,id=net0,chardev=chr0 \ -device virtio-net-pci,netdev=net0 +``-netdev vhost-vdpa,vhostdev=/path/to/dev`` + Establish a vhost-vdpa netdev. + + vDPA device is a device that uses a datapath which complies with + the virtio specifications with a vendor specific control path. + vDPA devices can be both physically located on the hardware or + emulated by software. + ``-netdev hubport,id=id,hubid=hubid[,netdev=nd]`` Create a hub port on the emulated hub with ID hubid.
Re: [PATCH v1 09/10] vhost-vdpa: introduce vhost-vdpa backend
Quoted 534 lines · Maxime Coquelin
Quoted 515 lines · Cindy Lu
Currently we have 2 types of vhost backends in QEMU: vhost kernel and vhost-user. The above patch provides a generic device for vDPA purpose, this vDPA device exposes to user space a non-vendor-specific configuration interface for setting up a vhost HW accelerator, this patch set introduces a third vhost backend called vhost-vdpa based on the vDPA interface.
Vhost-vdpa usage:
qemu-system-x86_64 -cpu host -enable-kvm \ ...... -netdev type=vhost-vdpa,vhostdev=/dev/vhost-vdpa-id,id=vhost-vdpa0 \ -device virtio-net-pci,netdev=vhost-vdpa0,page-per-vq=on \Signed-off-by Lingshan zhu <[email protected]>Signed-off-by Tiwei Bie <[email protected]>Signed-off-by Cindy Lu <[email protected]>--- configure | 21 ++ hw/net/vhost_net.c | 19 +- hw/net/virtio-net.c | 19 +- hw/virtio/Makefile.objs | 1 + hw/virtio/vhost-backend.c | 22 +- hw/virtio/vhost-vdpa.c | 406 ++++++++++++++++++++++++++++++ hw/virtio/vhost.c | 42 +++- include/hw/virtio/vhost-backend.h | 6 +- include/hw/virtio/vhost-vdpa.h | 26 ++ include/hw/virtio/vhost.h | 6 + qemu-options.hx | 12 + 11 files changed, 555 insertions(+), 25 deletions(-) create mode 100644 hw/virtio/vhost-vdpa.c create mode 100644 include/hw/virtio/vhost-vdpa.hconfigure +21
-0@@ -1557,6 +1557,10 @@ for opt do ;; --enable-vhost-user) vhost_user="yes" ;; + --disable-vhost-vdpa) vhost_vdpa="no" + ;; + --enable-vhost-vdpa) vhost_vdpa="yes" + ;; --disable-vhost-kernel) vhost_kernel="no" ;; --enable-vhost-kernel) vhost_kernel="yes"@@ -1846,6 +1850,7 @@ disabled with --disable-FEATURE, default is enabled if available: vhost-crypto vhost-user-crypto backend support vhost-kernel vhost kernel backend support vhost-user vhost-user backend support + vhost-vdpa vhost-vdpa kernel backend support spice spice rbd rados block device (rbd) libiscsi iscsi support@@ -2336,6 +2341,10 @@ test "$vhost_user" = "" && vhost_user=yes if test "$vhost_user" = "yes" && test "$mingw32" = "yes"; then error_exit "vhost-user isn't available on win32" fi +test "$vhost_vdpa" = "" && vhost_vdpa=$linux +if test "$vhost_vdpa" = "yes" && test "$linux" != "yes"; then + error_exit "vhost-vdpa is only available on Linux" +fi test "$vhost_kernel" = "" && vhost_kernel=$linux if test "$vhost_kernel" = "yes" && test "$linux" != "yes"; then error_exit "vhost-kernel is only available on Linux"@@ -2364,6 +2373,11 @@ test "$vhost_user_fs" = "" && vhost_user_fs=$vhost_user if test "$vhost_user_fs" = "yes" && test "$vhost_user" = "no"; then error_exit "--enable-vhost-user-fs requires --enable-vhost-user" fi +#vhost-vdpa backends +test "$vhost_net_vdpa" = "" && vhost_net_vdpa=$vhost_vdpa +if test "$vhost_net_vdpa" = "yes" && test "$vhost_vdpa" = "no"; then + error_exit "--enable-vhost-net-vdpa requires --enable-vhost-vdpa" +fi # OR the vhost-kernel and vhost-user values for simplicity if test "$vhost_net" = ""; then@@ -6673,6 +6687,7 @@ echo "vhost-scsi support $vhost_scsi" echo "vhost-vsock support $vhost_vsock" echo "vhost-user support $vhost_user" echo "vhost-user-fs support $vhost_user_fs" +echo "vhost-vdpa support $vhost_vdpa" echo "Trace backends $trace_backends" if have_backend "simple"; then echo "Trace output file $trace_file-<pid>"@@ -7170,6 +7185,9 @@ fi if test "$vhost_net_user" = "yes" ; then echo "CONFIG_VHOST_NET_USER=y" >> $config_host_mak fi +if test "$vhost_net_vdpa" = "yes" ; then + echo "CONFIG_VHOST_NET_VDPA=y" >> $config_host_mak +fi if test "$vhost_crypto" = "yes" ; then echo "CONFIG_VHOST_CRYPTO=y" >> $config_host_mak fi@@ -7182,6 +7200,9 @@ fi if test "$vhost_user" = "yes" ; then echo "CONFIG_VHOST_USER=y" >> $config_host_mak fi +if test "$vhost_vdpa" = "yes" ; then + echo "CONFIG_VHOST_VDPA=y" >> $config_host_mak +fi if test "$vhost_user_fs" = "yes" ; then echo "CONFIG_VHOST_USER_FS=y" >> $config_host_mak fihw/net/vhost_net.c +12
-7@@ -17,8 +17,10 @@#include "net/net.h" #include "net/tap.h" #include "net/vhost-user.h" +#include "net/vhost-vdpa.h" #include "standard-headers/linux/vhost_types.h" +#include "linux-headers/linux/vhost.h" #include "hw/virtio/virtio-net.h" #include "net/vhost_net.h" #include "qemu/error-report.h" @@ -33,12 +35,6 @@#include "hw/virtio/vhost.h" #include "hw/virtio/virtio-bus.h" -struct vhost_net { -struct vhost_dev dev; -struct vhost_virtqueue vqs[2 ]; -int backend; -NetClientState *nc; -};/* Features supported by host kernel. */ static const int kernel_feature_bits[] = {@@ -84,7 +80,6 @@ static const int user_feature_bits[] = { VHOST_INVALID_FEATURE_BIT }; -static const int *vhost_net_get_feature_bits (struct vhost_net *net) {const int *feature_bits =0 ;@@ -96,6 +91,9 @@ static const int *vhost_net_get_feature_bits(struct vhost_net *net)case NET_CLIENT_DRIVER_VHOST_USER : feature_bits = user_feature_bits;break ; +case NET_CLIENT_DRIVER_VHOST_VDPA : + feature_bits = vdpa_feature_bits; +break ;default :error_report ("Feature bits not defined for this type: %d" , net->nc->info->type);@@ -348,6 +346,7 @@ int vhost_net_start(VirtIODevice *dev, NetClientState *ncs, }for (i =0 ; i < total_queues; i++) { + peer =qemu_get_peer (ncs, i); r =vhost_net_start_one (get_vhost_net (peer), dev);@@ -444,6 +443,12 @@ VHostNetState *get_vhost_net(NetClientState *nc) vhost_net =vhost_user_get_vhost_net (nc);assert (vhost_net);break ; +#endif +#ifdef CONFIG_VHOST_NET_VDPA +case NET_CLIENT_DRIVER_VHOST_VDPA : + vhost_net =vhost_vdpa_get_vhost_net (nc); +assert (vhost_net); +break ;#endif default :break ;hw/net/virtio-net.c +17
-2@@ -42,6 +42,7 @@#include "trace.h" #include "monitor/qdev.h" #include "hw/pci/pci.h" +#include "hw/virtio/vhost.h" #define VIRTIO_NET_VM_VERSION 11@@ -131,6 +132,8 @@ static void virtio_net_get_config(VirtIODevice *vdev, uint8_t *config) {VirtIONet *n =VIRTIO_NET (vdev);struct virtio_net_config netcfg; +int ret =0 ; +memset (&netcfg,0 ,sizeof (struct virtio_net_config ));virtio_stw_p (vdev, &netcfg.status, n->status);virtio_stw_p (vdev, &netcfg.max_virtqueue_pairs, n->max_queues);@@ -139,13 +142,21 @@ static void virtio_net_get_config(VirtIODevice *vdev, uint8_t *config)virtio_stl_p (vdev, &netcfg.speed, n->net_conf.speed); netcfg.duplex = n->net_conf.duplex;memcpy (config, &netcfg, n->config_size); +NetClientState *nc =qemu_get_queue (n->nic); +if (nc->peer->info->type ==NET_CLIENT_DRIVER_VHOST_VDPA ) { + ret =vhost_net_get_config (get_vhost_net (nc->peer), (uint8_t *)&netcfg, + n->config_size); +if (ret !=-1 ) { +memcpy (config, &netcfg, n->config_size); + } + } }static void virtio_net_set_config (VirtIODevice *vdev,const uint8_t *config) {VirtIONet *n =VIRTIO_NET (vdev); +NetClientState *nc =qemu_get_queue (n->nic);struct virtio_net_config netcfg = {}; -memcpy (&netcfg, config, n->config_size); if (!virtio_vdev_has_feature(vdev, VIRTIO_NET_F_CTRL_MAC_ADDR) &&@@ -154,6 +165,11 @@ static void virtio_net_set_config(VirtIODevice *vdev, const uint8_t *config)memcpy (n->mac, netcfg.mac,ETH_ALEN );qemu_format_nic_info_str (qemu_get_queue (n->nic), n->mac); } +if (nc->peer->info->type ==NET_CLIENT_DRIVER_VHOST_VDPA ) { +vhost_net_set_config (get_vhost_net (nc->peer), (uint8_t *)&netcfg, +0 , n->config_size, +VHOST_SET_CONFIG_TYPE_MASTER ); + } }static bool virtio_net_started (VirtIONet *n,uint8_t status)@@ -2958,7 +2974,6 @@ static void virtio_net_device_realize(DeviceState *dev, Error **errp) }else if (n->net_conf.speed >=0 ) { n->host_features |= (1ULL <<VIRTIO_NET_F_SPEED_DUPLEX ); } -if (n->failover) { n->primary_listener.should_be_hidden = virtio_net_primary_should_be_hidden;hw/virtio/Makefile.objs +1
-0@@ -5,6 +5,7 @@ obj-y += virtio.o obj-$(CONFIG_VHOST) += vhost.o vhost-backend.o common-obj-$(call lnot,$(CONFIG_VHOST)) += vhost-stub.o obj-$(CONFIG_VHOST_USER) += vhost-user.o +obj-$(CONFIG_VHOST_VDPA) += vhost-vdpa.o common-obj-$(CONFIG_VIRTIO_RNG) += virtio-rng.o common-obj-$(CONFIG_VIRTIO_PCI) += virtio-pci.ohw/virtio/vhost-backend.c +18
-4@@ -14,7 +14,7 @@#include "qemu/error-report.h" #include "qemu/main-loop.h" #include "standard-headers/linux/vhost_types.h" - +#include "hw/virtio/vhost-vdpa.h" #ifdef CONFIG_VHOST_KERNEL #include <linux/vhost.h> #include <sys/ioctl.h> @@ -22,10 +22,19 @@static int vhost_kernel_call (struct vhost_dev *dev,unsigned long int request,void *arg) { -int fd = (uintptr_t ) dev->opaque; - -assert (dev->vhost_ops->backend_type ==VHOST_BACKEND_TYPE_KERNEL ); +int fd =-1 ; +switch (dev->vhost_ops->backend_type) { +case VHOST_BACKEND_TYPE_KERNEL : + fd = (uintptr_t )dev->opaque; +break ; +case VHOST_BACKEND_TYPE_VDPA : + fd = ((struct vhost_vdpa *)dev->opaque)->device_fd; +break ; +default : +g_assert_not_reached (); + } +assert (fd !=-1 );return ioctl (fd, request, arg); }@@ -285,6 +294,11 @@ int vhost_set_backend_type(struct vhost_dev *dev, VhostBackendType backend_type)case VHOST_BACKEND_TYPE_USER : dev->vhost_ops = &user_ops;break ; +#endif +#ifdef CONFIG_VHOST_VDPA +case VHOST_BACKEND_TYPE_VDPA : + dev->vhost_ops = &vdpa_ops; +break ;#endif default :error_report ("Unknown vhost backend type" );hw/virtio/vhost-vdpa.c new file +212
-0@@ -0,0 +1,406 @@ +/* +* vhost-vdpa +* +* Copyright(c) 2017-2018 Intel Corporation. +* Copyright(c) 2020 Red Hat, Inc. +* +* This work is licensed under the terms of the GNU GPL, version 2 or later. +* See the COPYING file in the top-level directory. +* +*/ + +#include "qemu/osdep.h" +#include <linux/vhost.h> +#include <linux/vfio.h> +#include <sys/eventfd.h> +#include <sys/ioctl.h> +#include "hw/virtio/vhost.h" +#include "hw/virtio/vhost-backend.h" +#include "hw/virtio/virtio-net.h" +#include "hw/virtio/vhost-vdpa.h" +#include "qemu/main-loop.h" +#include <linux/kvm.h> +#include "sysemu/kvm.h" + + +static bool vhost_vdpa_listener_skipped_section (MemoryRegionSection *section) +{ +return (!memory_region_is_ram (section->mr) && + !memory_region_is_iommu (section->mr)) || +/* +* Sizing an enabled 64-bit BAR can cause spurious mappings to +* addresses in the upper part of the 64-bit address space. These +* are never accessed by the CPU and beyond the address width of +* some IOMMU hardware. TODO: VDPA should tell us the IOMMU width. +*/ + section->offset_within_address_space & (1ULL <<63 ); +} + +static int vhost_vdpa_dma_map (struct vhost_vdpa *v,hwaddr iova,hwaddr size, +void *vaddr,bool readonly) +{ +struct vhost_msg_v2 msg; +int fd = v->device_fd; +int ret =0 ; + + msg.type = v->msg_type; + msg.iotlb.iova = iova; + msg.iotlb.size = size; + msg.iotlb.uaddr = (uint64_t )vaddr; + msg.iotlb.perm = readonly ?VHOST_ACCESS_RO :VHOST_ACCESS_RW ; + msg.iotlb.type =VHOST_IOTLB_UPDATE ; + +if (write (fd, &msg,sizeof (msg)) !=sizeof (msg)) { +error_report ("failed to write, fd=%d, errno=%d (%s)" , + fd, errno,strerror (errno)); +return -EIO ; + } + +return ret; +} + +static int vhost_vdpa_dma_unmap (struct vhost_vdpa *v,hwaddr iova, +hwaddr size) +{ +struct vhost_msg_v2 msg; +int fd = v->device_fd; +int ret =0 ; + + msg.type = v->msg_type; + msg.iotlb.iova = iova; + msg.iotlb.size = size; + msg.iotlb.type =VHOST_IOTLB_INVALIDATE ; + +if (write (fd, &msg,sizeof (msg)) !=sizeof (msg)) { +error_report ("failed to write, fd=%d, errno=%d (%s)" , + fd, errno,strerror (errno)); +return -EIO ; + } + +return ret; +} + +static void vhost_vdpa_listener_region_add (MemoryListener *listener, +MemoryRegionSection *section) +{ + struct vhost_vdpa *v = container_of(listener, struct vhost_vdpa, listener); +hwaddr iova; +Int128 llend, llsize; +void *vaddr; +int ret; + +if (vhost_vdpa_listener_skipped_section (section)) { +return ; + } + +if (unlikely ((section->offset_within_address_space & ~TARGET_PAGE_MASK ) != + (section->offset_within_region & ~TARGET_PAGE_MASK ))) { +error_report ("%s received unaligned region" , __func__); +return ; + } + + iova =TARGET_PAGE_ALIGN (section->offset_within_address_space); + llend =int128_make64 (section->offset_within_address_space); + llend =int128_add (llend, section->size); + llend =int128_and (llend,int128_exts64 (TARGET_PAGE_MASK )); + +if (int128_ge (int128_make64 (iova), llend)) { +return ; + } + +memory_region_ref (section->mr); + +/* Here we assume that memory_region_is_ram(section->mr)==true */ + + vaddr =memory_region_get_ram_ptr (section->mr) + + section->offset_within_region + + (iova - section->offset_within_address_space); + + llsize =int128_sub (llend,int128_make64 (iova)); + + ret =vhost_vdpa_dma_map (v, iova,int128_get64 (llsize), + vaddr, section->readonly); +if (ret) { +error_report ("vhost vdpa map fail!" ); +if (memory_region_is_ram_device (section->mr)) { +/* Allow unexpected mappings not to be fatal for RAM devices */ +error_report ("map ram fail!" ); +return ; + } + goto fail; + } + +return ; + +fail: +if (memory_region_is_ram_device (section->mr)) { +error_report ("failed to vdpa_dma_map. pci p2p may not work" ); +return ; + + } +/* +* On the initfn path, store the first error in the container so we +* can gracefully fail. Runtime, there's not much we can do other +* than throw a hardware error. +*/ +error_report ("vhost-vdpa: DMA mapping failed, unable to continue" ); +return ; + +} + +static void vhost_vdpa_listener_region_del (MemoryListener *listener, +MemoryRegionSection *section) +{ + struct vhost_vdpa *v = container_of(listener, struct vhost_vdpa, listener); +hwaddr iova; +Int128 llend, llsize; +int ret; +bool try_unmap = true; + +if (vhost_vdpa_listener_skipped_section (section)) { +return ; + } + +if (unlikely ((section->offset_within_address_space & ~TARGET_PAGE_MASK ) != + (section->offset_within_region & ~TARGET_PAGE_MASK ))) { +error_report ("%s received unaligned region" , __func__); +return ; + } + + iova =TARGET_PAGE_ALIGN (section->offset_within_address_space); + llend =int128_make64 (section->offset_within_address_space); + llend =int128_add (llend, section->size); + llend =int128_and (llend,int128_exts64 (TARGET_PAGE_MASK )); + +if (int128_ge (int128_make64 (iova), llend)) { +return ; + } + + llsize =int128_sub (llend,int128_make64 (iova)); + +if (try_unmap) { + ret =vhost_vdpa_dma_unmap (v, iova,int128_get64 (llsize)); +if (ret) { +error_report ("vhost_vdpa dma unmap error!" ); + } + } + +memory_region_unref (section->mr); +} +/* +* IOTLB API is used by vhost-vpda which requires incremental updating +* of the mapping. So we can not use generic vhost memory listener which +* depends on the addnop(). +*/ +static const MemoryListener vhost_vdpa_memory_listener = { + .region_add = vhost_vdpa_listener_region_add, + .region_del = vhost_vdpa_listener_region_del, +}; + +static int vhost_vdpa_call (struct vhost_dev *dev,unsigned long int request, +void *arg) +{ +struct vhost_vdpa *v = dev->opaque; +int fd = v->device_fd; + +assert (dev->vhost_ops->backend_type ==VHOST_BACKEND_TYPE_VDPA ); + +return ioctl (fd, request, arg); +} + +static void vhost_vdpa_add_status (struct vhost_dev *dev,uint8_t status) +{hw/virtio/vhost-vdpa.c line 222
Quoted 10 lines
hw/virtio/vhost-vdpa.c new file +10
-0+uint8_t s; + +if (vhost_vdpa_call (dev,VHOST_VDPA_GET_STATUS , &s)) { +return ; + } + + s |= status; + +vhost_vdpa_call (dev,VHOST_VDPA_SET_STATUS , &s); +}I think it would be better to have backend ops for
SET_STATUSandGET_STATUSto avoid duplicating code in every backends that wish to support it.
Quoted 3 lines
Also, I think that
SET_STATUSshould forward directly the Virtio device status updates written by the Virtio driver.
Hi Maxime,
I think maybe we can keep what is now, now we only export the vhostops vhost_dev_start.
That will make the code in vhost.c clear and easy to understand. Also if there are different processes in different kinds of backends, we can implement them in
their own file, hiden the difference to the uplayer.
Thanks
Cindy
Quoted 377 lines
Quoted 376 lines
hw/virtio/vhost-vdpa.c new file +183
-0+static int vhost_vdpa_init (struct vhost_dev *dev,void *opaque) +{ +struct vhost_vdpa *v; +uint64_t features; +assert (dev->vhost_ops->backend_type ==VHOST_BACKEND_TYPE_VDPA ); + + v = opaque; + dev->opaque = opaque ; +vhost_vdpa_call (dev,VHOST_GET_FEATURES , &features); + dev->backend_features = features; + v->listener = vhost_vdpa_memory_listener; + v->msg_type =VHOST_IOTLB_MSG_V2 ; + +vhost_vdpa_add_status (dev,VIRTIO_CONFIG_S_ACKNOWLEDGE | +VIRTIO_CONFIG_S_DRIVER ); + +return 0 ; +} + +static int vhost_vdpa_cleanup (struct vhost_dev *dev) +{ +struct vhost_vdpa *v; +assert (dev->vhost_ops->backend_type ==VHOST_BACKEND_TYPE_VDPA ); + v = dev->opaque; +memory_listener_unregister (&v->listener); + + dev->opaque =NULL ; +return 0 ; +} + +static int vhost_vdpa_memslots_limit (struct vhost_dev *dev) +{ +return INT_MAX ; +} + +static int vhost_vdpa_set_mem_table (struct vhost_dev *dev, +struct vhost_memory *mem) +{ + +if (mem->padding) { +return -1 ; + } + +return 0 ; +} + +static int vhost_vdpa_set_features (struct vhost_dev *dev, +uint64_t features) +{ +int ret; + ret =vhost_vdpa_call (dev,VHOST_SET_FEATURES , &features); +uint8_t status =0 ; +if (ret) { +return ret; + } +vhost_vdpa_add_status (dev,VIRTIO_CONFIG_S_FEATURES_OK ); +vhost_vdpa_call (dev,VHOST_VDPA_GET_STATUS , &status); + +return !(status &VIRTIO_CONFIG_S_FEATURES_OK ); +} + +int vhost_vdpa_get_device_id (struct vhost_dev *dev, +uint32_t *device_id) +{ +return vhost_vdpa_call (dev,VHOST_VDPA_GET_DEVICE_ID , device_id); +} + +static int vhost_vdpa_reset_device (struct vhost_dev *dev) +{ +uint8_t status =0 ; + +return vhost_vdpa_call (dev,VHOST_VDPA_SET_STATUS , &status); +} + +static int vhost_vdpa_get_vq_index (struct vhost_dev *dev,int idx) +{ +assert (idx >= dev->vq_index && idx < dev->vq_index + dev->nvqs); + +return idx - dev->vq_index; +} + +static int vhost_vdpa_set_vring_ready (struct vhost_dev *dev) +{ +int i; +for (i =0 ; i < dev->nvqs; ++i) { +struct vhost_vring_state state = { + .index = dev->vq_index + i, + .num =1 , + }; +vhost_vdpa_call (dev,VHOST_VDPA_SET_VRING_ENABLE , &state); + } +return 0 ; +} + +static int vhost_vdpa_set_config (struct vhost_dev *dev,const uint8_t *data, +uint32_t offset,uint32_t size, +uint32_t flags) +{ +struct vhost_vdpa_config *config; +int ret; +unsigned long config_size = offsetof(struct vhost_vdpa_config , buf); + config =g_malloc (size + config_size); +if (config ==NULL ) { +return -1 ; + } + config->off = offset; + config->len = size; +memcpy (config->buf, data, size); + ret =vhost_vdpa_call (dev,VHOST_VDPA_SET_CONFIG , config); +g_free (config); +return ret; +} + +static int vhost_vdpa_get_config (struct vhost_dev *dev,uint8_t *config, +uint32_t config_len) +{ +struct vhost_vdpa_config *v_config; +unsigned long config_size = offsetof(struct vhost_vdpa_config , buf); +int ret; + + v_config =g_malloc (config_len + config_size); +if (v_config ==NULL ) { +return -1 ; + } + v_config->len = config_len; + v_config->off =0 ; + ret =vhost_vdpa_call (dev,VHOST_VDPA_GET_CONFIG , v_config); +memcpy (config, v_config->buf, config_len); +g_free (v_config); +return ret; + } + +static int vhost_vdpa_dev_start (struct vhost_dev *dev,bool started) +{ +struct vhost_vdpa *v = dev->opaque; +if (started) { +uint8_t status =0 ; +memory_listener_register (&v->listener, &address_space_memory); +vhost_vdpa_set_vring_ready (dev); +vhost_vdpa_add_status (dev,VIRTIO_CONFIG_S_DRIVER_OK ); +vhost_vdpa_call (dev,VHOST_VDPA_GET_STATUS , &status); + +return !(status &VIRTIO_CONFIG_S_DRIVER_OK ); + }else { +vhost_vdpa_reset_device (dev); +vhost_vdpa_add_status (dev,VIRTIO_CONFIG_S_ACKNOWLEDGE | +VIRTIO_CONFIG_S_DRIVER ); +memory_listener_unregister (&v->listener); + +return 0 ; + } +} + +const VhostOps vdpa_ops = { + .backend_type =VHOST_BACKEND_TYPE_VDPA , + .vhost_backend_init = vhost_vdpa_init, + .vhost_backend_cleanup = vhost_vdpa_cleanup, + .vhost_set_log_base = vhost_kernel_set_log_base, + .vhost_set_vring_addr = vhost_kernel_set_vring_addr, + .vhost_set_vring_num = vhost_kernel_set_vring_num, + .vhost_set_vring_base = vhost_kernel_set_vring_base, + .vhost_get_vring_base = vhost_kernel_get_vring_base, + .vhost_set_vring_kick = vhost_kernel_set_vring_kick, + .vhost_set_vring_call = vhost_kernel_set_vring_call, + .vhost_get_features = vhost_kernel_get_features, + .vhost_set_owner = vhost_kernel_set_owner, + .vhost_set_vring_endian =NULL , + .vhost_backend_memslots_limit = vhost_vdpa_memslots_limit, + .vhost_set_mem_table = vhost_vdpa_set_mem_table, + .vhost_set_features = vhost_vdpa_set_features, + .vhost_reset_device = vhost_vdpa_reset_device, + .vhost_get_vq_index = vhost_vdpa_get_vq_index, + .vhost_get_config = vhost_vdpa_get_config, + .vhost_set_config = vhost_vdpa_set_config, + .vhost_requires_shm_log =NULL , + .vhost_migration_done =NULL , + .vhost_backend_can_merge =NULL , + .vhost_net_set_mtu =NULL , + .vhost_set_iotlb_callback =NULL , + .vhost_send_device_iotlb_msg =NULL , + .vhost_dev_start = vhost_vdpa_dev_start, + .vhost_get_device_id = vhost_vdpa_get_device_id, +};hw/virtio/vhost.c +31
-11@@ -744,19 +744,34 @@ static void vhost_iommu_region_del(MemoryListener *listener, } } +static void vhost_virtqueue_get_addr (struct vhost_dev *dev, +struct vhost_vring_addr *addr, +struct vhost_virtqueue *vq) +{ +/*vDPA need to use the IOVA here to set to hardware*/ +if (dev->vhost_ops->backend_type ==VHOST_BACKEND_TYPE_VDPA ) { + addr->desc_user_addr = (uint64_t )(unsigned long )vq->desc_phys; + addr->avail_user_addr = (uint64_t )(unsigned long )vq->avail_phys; + addr->used_user_addr = (uint64_t )(unsigned long )vq->used_phys; + }else { + addr->desc_user_addr = (uint64_t )(unsigned long )vq->desc; + addr->avail_user_addr = (uint64_t )(unsigned long )vq->avail; + addr->used_user_addr = (uint64_t )(unsigned long )vq->used; + } +}static int vhost_virtqueue_set_addr (struct vhost_dev *dev,struct vhost_virtqueue *vq,unsigned idx,bool enable_log) { -struct vhost_vring_addr addr = { - .index = idx, - .desc_user_addr = (uint64_t )(unsigned long )vq->desc, - .avail_user_addr = (uint64_t )(unsigned long )vq->avail, - .used_user_addr = (uint64_t )(unsigned long )vq->used, - .log_guest_addr = vq->used_phys, - .flags = enable_log ? (1 <<VHOST_VRING_F_LOG ) :0 , - }; +struct vhost_vring_addr addr; +memset (&addr,0 ,sizeof (struct vhost_vring_addr )); + +vhost_virtqueue_get_addr (dev, &addr, vq); + addr.index = idx; + addr .log_guest_addr = vq->used_phys; + addr .flags = enable_log ? (1 <<VHOST_VRING_F_LOG ) :0 ; +int r = dev->vhost_ops->vhost_set_vring_addr (dev, &addr);if (r <0 ) {VHOST_OPS_DEBUG ("vhost_set_vring_addr failed" );@@ -774,7 +789,9 @@ static int vhost_dev_set_features(struct vhost_dev *dev, features |=0x1ULL <<VHOST_F_LOG_ALL ; }if (!vhost_dev_has_iommu (dev)) { - features &= ~(0x1ULL <<VIRTIO_F_IOMMU_PLATFORM ); +if (dev->vhost_ops->backend_type !=VHOST_BACKEND_TYPE_VDPA ) { + features &= ~(0x1ULL <<VIRTIO_F_IOMMU_PLATFORM ); + } } r = dev->vhost_ops->vhost_set_features (dev, features);if (r <0 ) {@@ -1667,7 +1684,8 @@ int vhost_dev_start(struct vhost_dev *hdev, VirtIODevice *vdev) goto fail_log; } -if (vhost_dev_has_iommu (hdev)) { +if (vhost_dev_has_iommu (hdev) && + hdev->vhost_ops->vhost_set_iotlb_callback) { hdev->vhost_ops->vhost_set_iotlb_callback (hdev, true);/* Update used ring information for IOTLB to work correctly, @@ -1713,7 +1731,9 @@ void vhost_dev_stop(struct vhost_dev *hdev, VirtIODevice *vdev) }if (vhost_dev_has_iommu (hdev)) { - hdev->vhost_ops->vhost_set_iotlb_callback (hdev, false); +if (hdev->vhost_ops->vhost_set_iotlb_callback) { + hdev->vhost_ops->vhost_set_iotlb_callback (hdev, false); + }memory_listener_unregister (&hdev->iommu_listener); }vhost_log_put (hdev, true);include/hw/virtio/vhost-backend.h +5
-1@@ -17,7 +17,8 @@ typedef enum VhostBackendType {VHOST_BACKEND_TYPE_NONE =0 ,VHOST_BACKEND_TYPE_KERNEL =1 ,VHOST_BACKEND_TYPE_USER =2 , -VHOST_BACKEND_TYPE_MAX =3 , +VHOST_BACKEND_TYPE_VDPA =3 , +VHOST_BACKEND_TYPE_MAX =4 , } VhostBackendType; typedef enum VhostSetConfigType {@@ -113,6 +114,7 @@ typedef int (*vhost_set_inflight_fd_op)(struct vhost_dev *dev, struct vhost_inflight *inflight);typedef int (*vhost_dev_start_op )(struct vhost_dev *dev,bool started); +typedef int (*vhost_get_device_id_op )(struct vhost_dev *dev,uint32_t *dev_id); typedef struct VhostOps { VhostBackendType backend_type; vhost_backend_init vhost_backend_init;@@ -154,9 +156,11 @@ typedef struct VhostOps {vhost_get_inflight_fd_op vhost_get_inflight_fd;vhost_set_inflight_fd_op vhost_set_inflight_fd;vhost_dev_start_op vhost_dev_start; +vhost_get_device_id_op vhost_get_device_id; } VhostOps;extern const VhostOps user_ops; +extern const VhostOps vdpa_ops;int vhost_set_backend_type (struct vhost_dev *dev,VhostBackendType backend_type);include/hw/virtio/vhost-vdpa.h new file +26
-0@@ -0,0 +1,26 @@ +/* +* vhost-vdpa.h +* +* Copyright(c) 2017-2018 Intel Corporation. +* Copyright(c) 2020 Red Hat, Inc. +* +* This work is licensed under the terms of the GNU GPL, version 2 or later. +* See the COPYING file in the top-level directory. +* +*/ + +#ifndef HW_VIRTIO_VHOST_VDPA_H +#define HW_VIRTIO_VHOST_VDPA_H + +#include "hw/virtio/virtio.h" + +typedef struct vhost_vdpa { +int device_fd; +uint32_t msg_type; +MemoryListener listener; +}VhostVDPA ; + +extern AddressSpace address_space_memory; +extern int vhost_vdpa_get_device_id (struct vhost_dev *dev, +uint32_t *device_id); +#endif include/hw/virtio/vhost.h +6
-0@@ -92,6 +92,12 @@ struct vhost_dev {const VhostDevConfigOps *config_ops; }; +struct vhost_net { +struct vhost_dev dev; +struct vhost_virtqueue vqs[2 ]; +int backend; +NetClientState *nc; +}; int vhost_dev_init(struct vhost_dev *hdev, void *opaque, VhostBackendType backend_type,qemu-options.hx +12
-0@@ -2409,6 +2409,10 @@ DEF("netdev", HAS_ARG, QEMU_OPTION_netdev, #ifdef CONFIG_POSIX "-netdev vhost-user,id=str,chardev=dev[,vhostforce=on|off]\n" " configure a vhost-user network, backed by a chardev 'dev'\n" +#endif +#ifdef __linux__ + "-netdev vhost-vdpa,id=str,vhostdev=/path/to/dev\n" + " configure a vhost-vdpa network,Establish a vhost-vdpa netdev\n" #endif "-netdev hubport,id=str,hubid=n[,netdev=nd]\n" " configure a hub port on the hub with ID 'n'\n", QEMU_ARCH_ALL)@@ -2888,6 +2892,14 @@ SRST -netdev type=vhost-user,id=net0,chardev=chr0 \ -device virtio-net-pci,netdev=net0 +``-netdev vhost-vdpa,vhostdev=/path/to/dev`` + Establish a vhost-vdpa netdev. + + vDPA device is a device that uses a datapath which complies with + the virtio specifications with a vendor specific control path. + vDPA devices can be both physically located on the hardware or + emulated by software. + ``-netdev hubport,id=id,hubid=hubid[,netdev=nd]`` Create a hub port on the emulated hub with ID hubid.
PATCH 10/10 vhost-vdpa: introduce vhost-vdpa net client
In reply to Cindy LuThis patch set introduces a new net client type: vhost-vdpa. vhost-vdpa net client will set up a vDPA device which is specified by a "vhostdev" parameter.
--- include/net/vhost-vdpa.h | 21 ++++ include/net/vhost_net.h | 1 - net/Makefile.objs | 2 +- net/clients.h | 2 + net/net.c | 3 + net/vhost-vdpa.c | 230 +++++++++++++++++++++++++++++++++++++++ qapi/net.json | 23 +++- 7 files changed, 278 insertions(+), 4 deletions(-) create mode 100644 include/net/vhost-vdpa.h create mode 100644 net/vhost-vdpa.c
include/net/vhost-vdpa.h new file +21 -0
@@ -0,0 +1,21 @@ +/* +* vhost-vdpa.h +* +* Copyright(c) 2017-2018 Intel Corporation. +* Copyright(c) 2020 Red Hat, Inc. +* +* This work is licensed under the terms of the GNU GPL, version 2 or later. +* See the COPYING file in the top-level directory. +* +*/ + +#ifndef VHOST_VDPA_H +#define VHOST_VDPA_H + +struct vhost_net ; +struct vhost_net *vhost_vdpa_get_vhost_net (NetClientState *nc); +uint64_t vhost_vdpa_get_acked_features (NetClientState *nc); + +extern const int vdpa_feature_bits[]; + +#endif /* VHOST_VDPA_H */
include/net/vhost_net.h +0 -1
@@ -44,5 +44,4 @@ int vhost_set_vring_enable(NetClientState * nc, int enable);uint64_t vhost_net_get_acked_features (VHostNetState *net);int vhost_net_set_mtu (struct vhost_net *net,uint16_t mtu); -#endif
net/Makefile.objs +1 -1
@@ -26,7 +26,7 @@ tap-obj-$(CONFIG_SOLARIS) = tap-solaris.o tap-obj-y ?= tap-stub.o common-obj-$(CONFIG_POSIX) += tap.o $(tap-obj-y) common-obj-$(CONFIG_WIN32) += tap-win32.o - +common-obj-$(CONFIG_VHOST_NET_VDPA) += vhost-vdpa.o vde.o-libs = $(VDE_LIBS) common-obj-$(CONFIG_CAN_BUS) += can/
net/clients.h +2 -0
@@ -61,4 +61,6 @@ int net_init_netmap(const Netdev *netdev, const char *name,int net_init_vhost_user (const Netdev *netdev,const char *name,NetClientState *peer,Error **errp); +int net_init_vhost_vdpa (const Netdev *netdev,const char *name, +NetClientState *peer,Error **errp);#endif /* QEMU_NET_CLIENTS_H */
net/net.c +3 -0
@@ -965,6 +965,9 @@ static int (* const net_client_init_fun[NET_CLIENT_DRIVER__MAX])( #ifdef CONFIG_VHOST_NET_USER [NET_CLIENT_DRIVER_VHOST_USER ] = net_init_vhost_user, #endif +#ifdef CONFIG_VHOST_NET_VDPA + [NET_CLIENT_DRIVER_VHOST_VDPA ] = net_init_vhost_vdpa, +#endif #ifdef CONFIG_L2TPV3 [NET_CLIENT_DRIVER_L2TPV3] = net_init_l2tpv3, #endif
net/vhost-vdpa.c new file +230 -0
230 lines not on this page · raw message
qapi/net.json +21 -2
@@ -428,6 +428,24 @@ '*vhostforce': 'bool', '*queues': 'int' } } +## +# @NetdevVhostVDPAOptions: +# +# Vhost-vdpa network backend +# +# @vhostdev: name of a vdpa dev path in sysfs +# (default path:/dev/vhost-vdpa-$ID) +# +# @queues: number of queues to be created for multiqueue vhost-vdpa +# (default: 1) +# +# Since: 5.1 +## +{ 'struct': 'NetdevVhostVDPAOptions', + 'data': { + '*vhostdev': 'str', + '*queues': 'int' } } + ## # @NetClientDriver: #
@@ -437,7 +455,7 @@ ## { 'enum': 'NetClientDriver', 'data': [ 'none', 'nic', 'user', 'tap', 'l2tpv3', 'socket', 'vde', - 'bridge', 'hubport', 'netmap', 'vhost-user' ] } + 'bridge', 'hubport', 'netmap', 'vhost-user', 'vhost-vdpa' ] } ## # @Netdev:
@@ -465,7 +483,8 @@ 'bridge': 'NetdevBridgeOptions', 'hubport': 'NetdevHubPortOptions', 'netmap': 'NetdevNetmapOptions', - 'vhost-user': 'NetdevVhostUserOptions' } } + 'vhost-user': 'NetdevVhostUserOptions', + 'vhost-vdpa': 'NetdevVhostVDPAOptions' } } ## # @NetLegacy:
Signature · 1 line
2.21.1
Re: [PATCH v1 10/10] vhost-vdpa: introduce vhost-vdpa net client
QAPI schema review only.
Quoted 7 lines · Cindy Lu
This patch set introduces a new net client type: vhost-vdpa. vhost-vdpa net client will set up a vDPA device which is specified by a "vhostdev" parameter.
Signed-off-by Lingshan Zhu <[email protected]>Signed-off-by Tiwei Bie <[email protected]>Signed-off-by Cindy Lu <[email protected]>
[...]
qapi/net.json line 434
Quoted 12 lines
qapi/net.json +4
-0@@ -428,6 +428,24 @@ '*vhostforce': 'bool', '*queues': 'int' } } +## +# @NetdevVhostVDPAOptions: +# +# Vhost-vdpa network backend
Considering this ends up in QMP reference documentation, could you add a hint on what "Vhost-vdpa" is?
qapi/net.json line 436
Quoted 2 lines
qapi/net.json +2
-0+# +# @vhostdev: name of a vdpa dev path in sysfs
How is this thing to be spelled in text, vdpa, VDPA or vDPA?
Avoid unnecessary abbreviations in doc text, please: write "device path", not "dev path".
qapi/net.json line 437
Quoted 1 line
qapi/net.json +1
-0+# (default path:/dev/vhost-vdpa-$ID)
What's $ID?
Quoted 33 lines
qapi/net.json +14
-2+# +# @queues: number of queues to be created for multiqueue vhost-vdpa +# (default: 1) +# +# Since: 5.1 +## +{ 'struct': 'NetdevVhostVDPAOptions', + 'data': { + '*vhostdev': 'str', + '*queues': 'int' } } + ## # @NetClientDriver: #@@ -437,7 +455,7 @@ ## { 'enum': 'NetClientDriver', 'data': [ 'none', 'nic', 'user', 'tap', 'l2tpv3', 'socket', 'vde', - 'bridge', 'hubport', 'netmap', 'vhost-user' ] } + 'bridge', 'hubport', 'netmap', 'vhost-user', 'vhost-vdpa' ] } ## # @Netdev:@@ -465,7 +483,8 @@ 'bridge': 'NetdevBridgeOptions', 'hubport': 'NetdevHubPortOptions', 'netmap': 'NetdevNetmapOptions', - 'vhost-user': 'NetdevVhostUserOptions' } } + 'vhost-user': 'NetdevVhostUserOptions', + 'vhost-vdpa': 'NetdevVhostVDPAOptions' } } ## # @NetLegacy:
Re: [PATCH v1 10/10] vhost-vdpa: introduce vhost-vdpa net client
Quoted 34 lines · Markus Armbruster
QAPI schema review only.
Quoted 7 lines · Cindy Lu
This patch set introduces a new net client type: vhost-vdpa. vhost-vdpa net client will set up a vDPA device which is specified by a "vhostdev" parameter.
Signed-off-by Lingshan Zhu <[email protected]>Signed-off-by Tiwei Bie <[email protected]>Signed-off-by Cindy Lu <[email protected]>[...]
qapi/net.json line 434
Quoted 12 lines
qapi/net.json +4
-0@@ -428,6 +428,24 @@ '*vhostforce': 'bool', '*queues': 'int' } } +## +# @NetdevVhostVDPAOptions: +# +# Vhost-vdpa network backendConsidering this ends up in QMP reference documentation, could you add a hint on what "Vhost-vdpa" is?
qapi/net.json line 436
Quoted 2 lines
qapi/net.json +2
-0+# +# @vhostdev: name of a vdpa dev path in sysfsHow is this thing to be spelled in text, vdpa, VDPA or vDPA?
Quoted 7 lines
Avoid unnecessary abbreviations in doc text, please: write "device path", not "dev path".
qapi/net.json line 437
Quoted 1 line
qapi/net.json +1
-0+# (default path:/dev/vhost-vdpa-$ID)What's $ID?
Thanks, I will rewrite this part and make it clear
Quoted 34 lines
Quoted 33 lines
qapi/net.json +14
-2+# +# @queues: number of queues to be created for multiqueue vhost-vdpa +# (default: 1) +# +# Since: 5.1 +## +{ 'struct': 'NetdevVhostVDPAOptions', + 'data': { + '*vhostdev': 'str', + '*queues': 'int' } } + ## # @NetClientDriver: #@@ -437,7 +455,7 @@ ## { 'enum': 'NetClientDriver', 'data': [ 'none', 'nic', 'user', 'tap', 'l2tpv3', 'socket', 'vde', - 'bridge', 'hubport', 'netmap', 'vhost-user' ] } + 'bridge', 'hubport', 'netmap', 'vhost-user', 'vhost-vdpa' ] } ## # @Netdev:@@ -465,7 +483,8 @@ 'bridge': 'NetdevBridgeOptions', 'hubport': 'NetdevHubPortOptions', 'netmap': 'NetdevNetmapOptions', - 'vhost-user': 'NetdevVhostUserOptions' } } + 'vhost-user': 'NetdevVhostUserOptions', + 'vhost-vdpa': 'NetdevVhostVDPAOptions' } } ## # @NetLegacy:
Re: [PATCH v1 10/10] vhost-vdpa: introduce vhost-vdpa net client
In reply to Cindy LuQuoted 51 lines · Cindy Lu
This patch set introduces a new net client type: vhost-vdpa. vhost-vdpa net client will set up a vDPA device which is specified by a "vhostdev" parameter.
Signed-off-by Lingshan Zhu <[email protected]>Signed-off-by Tiwei Bie <[email protected]>Signed-off-by Cindy Lu <[email protected]>--- include/net/vhost-vdpa.h | 21 ++++ include/net/vhost_net.h | 1 - net/Makefile.objs | 2 +- net/clients.h | 2 + net/net.c | 3 + net/vhost-vdpa.c | 230 +++++++++++++++++++++++++++++++++++++++ qapi/net.json | 23 +++- 7 files changed, 278 insertions(+), 4 deletions(-)create mode 100644
include/net/vhost-vdpa.h
create mode 100644net/vhost-vdpa.cinclude/net/vhost-vdpa.h new file +21
-0@@ -0,0 +1,21 @@ +/* +* vhost-vdpa.h +* +* Copyright(c) 2017-2018 Intel Corporation. +* Copyright(c) 2020 Red Hat, Inc. +* +* This work is licensed under the terms of the GNU GPL, version 2 or later. +* See the COPYING file in the top-level directory. +* +*/ + +#ifndef VHOST_VDPA_H +#define VHOST_VDPA_H + +struct vhost_net ; +struct vhost_net *vhost_vdpa_get_vhost_net (NetClientState *nc); +uint64_t vhost_vdpa_get_acked_features (NetClientState *nc); + +extern const int vdpa_feature_bits[]; + +#endif /* VHOST_VDPA_H */ include/net/vhost_net.h +0
-0
include/net/vhost_net.h int vhost_set_vring_enable(NetClientState * nc, int enable); · line 47
Quoted 4 lines
include/net/vhost_net.h +0
-1@@ -44,5 +44,4 @@ int vhost_set_vring_enable(NetClientState * nc, int enable);uint64_t vhost_net_get_acked_features (VHostNetState *net);int vhost_net_set_mtu (struct vhost_net *net,uint16_t mtu); -
Let's keep this newline.
net/Makefile.objs tap-obj-$(CONFIG_SOLARIS) = tap-solaris.o · line 29
Quoted 10 lines
include/net/vhost_net.h +0
-0#endif net/Makefile.objs +0
-1@@ -26,7 +26,7 @@ tap-obj-$(CONFIG_SOLARIS) = tap-solaris.o tap-obj-y ?= tap-stub.o common-obj-$(CONFIG_POSIX) += tap.o $(tap-obj-y) common-obj-$(CONFIG_WIN32) += tap-win32.o -
And this.
Quoted 109 lines
net/Makefile.objs +1
-0+common-obj-$(CONFIG_VHOST_NET_VDPA) += vhost-vdpa.o vde.o-libs = $(VDE_LIBS) common-obj-$(CONFIG_CAN_BUS) += can/net/clients.h +2
-0@@ -61,4 +61,6 @@ int net_init_netmap(const Netdev *netdev, const char *name,int net_init_vhost_user (const Netdev *netdev,const char *name,NetClientState *peer,Error **errp); +int net_init_vhost_vdpa (const Netdev *netdev,const char *name, +NetClientState *peer,Error **errp);#endif /* QEMU_NET_CLIENTS_H */ net/net.c +3
-0@@ -965,6 +965,9 @@ static int (* const net_client_init_fun[NET_CLIENT_DRIVER__MAX])( #ifdef CONFIG_VHOST_NET_USER [NET_CLIENT_DRIVER_VHOST_USER ] = net_init_vhost_user, #endif +#ifdef CONFIG_VHOST_NET_VDPA + [NET_CLIENT_DRIVER_VHOST_VDPA ] = net_init_vhost_vdpa, +#endif #ifdef CONFIG_L2TPV3 [NET_CLIENT_DRIVER_L2TPV3] = net_init_l2tpv3, #endifnet/vhost-vdpa.c new file +74
-0@@ -0,0 +1,230 @@ +/* +* vhost-vdpa.c +* +* Copyright(c) 2017-2018 Intel Corporation. +* Copyright(c) 2020 Red Hat, Inc. +* +* This work is licensed under the terms of the GNU GPL, version 2 or later. +* See the COPYING file in the top-level directory. +* +*/ + +#include "qemu/osdep.h" +#include "clients.h" +#include "net/vhost_net.h" +#include "net/vhost-vdpa.h" +#include "hw/virtio/vhost-vdpa.h" +#include "qemu/config-file.h" +#include "qemu/error-report.h" +#include "qemu/option.h" +#include "qapi/error.h" +#include <sys/ioctl.h> +#include <err.h> +#include "standard-headers/linux/virtio_net.h" +#include "monitor/monitor.h" +#include "hw/virtio/vhost.h" + +/* Todo:need to add the multiqueue support here */ +typedef struct VhostVDPAState { +NetClientState nc; +struct vhost_vdpa vhost_vdpa; +VHostNetState *vhost_net; +uint64_t acked_features; +bool started; +}VhostVDPAState ; + +const int vdpa_feature_bits[] = { +VIRTIO_F_NOTIFY_ON_EMPTY , +VIRTIO_RING_F_INDIRECT_DESC , +VIRTIO_RING_F_EVENT_IDX , +VIRTIO_F_ANY_LAYOUT , +VIRTIO_F_VERSION_1 , +VIRTIO_NET_F_CSUM , +VIRTIO_NET_F_GUEST_CSUM , +VIRTIO_NET_F_GSO , +VIRTIO_NET_F_GUEST_TSO4 , +VIRTIO_NET_F_GUEST_TSO6 , +VIRTIO_NET_F_GUEST_ECN , +VIRTIO_NET_F_GUEST_UFO , +VIRTIO_NET_F_HOST_TSO4 , +VIRTIO_NET_F_HOST_TSO6 , +VIRTIO_NET_F_HOST_ECN , +VIRTIO_NET_F_HOST_UFO , +VIRTIO_NET_F_MRG_RXBUF , +VIRTIO_NET_F_MTU , +VIRTIO_F_IOMMU_PLATFORM , +VIRTIO_F_RING_PACKED , +VIRTIO_NET_F_GUEST_ANNOUNCE , +VHOST_INVALID_FEATURE_BIT +}; + +VHostNetState *vhost_vdpa_get_vhost_net (NetClientState *nc) +{ +VhostVDPAState *s =DO_UPCAST (VhostVDPAState, nc, nc); +assert (nc->info->type ==NET_CLIENT_DRIVER_VHOST_VDPA ); +return s->vhost_net; +} + +uint64_t vhost_vdpa_get_acked_features (NetClientState *nc) +{ +VhostVDPAState *s =DO_UPCAST (VhostVDPAState, nc, nc); +assert (nc->info->type ==NET_CLIENT_DRIVER_VHOST_VDPA ); + s->acked_features =vhost_net_get_acked_features (s->vhost_net); + +return s->acked_features;
net/vhost-vdpa.c line 84
Quoted 10 lines
net/vhost-vdpa.c new file +10
-0+} + +static int vhost_vdpa_net_check_device_id (NetClientState *nc) +{ +uint32_t device_id; +int ret; +struct vhost_net *net; +struct vhost_dev *hdev; +assert (nc->info->type ==NET_CLIENT_DRIVER_VHOST_VDPA ); +VhostVDPAState *s =DO_UPCAST (VhostVDPAState, nc, nc);
Let's try to avoid those unnecessary conversion and check since the caller knows e.g VhostVDPAState.
Quoted 33 lines
net/vhost-vdpa.c new file +33
-0+ net = s->vhost_net; + hdev = (struct vhost_dev *)&net->dev; + ret = hdev->vhost_ops->vhost_get_device_id (hdev, &device_id); +if (device_id !=VIRTIO_ID_NET ) { +return -ENOTSUP ; + } +return ret; +} + +static void vhost_vdpa_del (NetClientState *ncs) +{ +VhostVDPAState *s; +assert (ncs->info->type ==NET_CLIENT_DRIVER_VHOST_VDPA ); + s =DO_UPCAST (VhostVDPAState, nc, ncs); +if (s->vhost_net) { +vhost_net_cleanup (s->vhost_net); + } +} + +static int vhost_vdpa_add (NetClientState *ncs,void *be) +{ +VhostNetOptions options; +struct vhost_net *net =NULL ; +VhostVDPAState *s; +int ret; + + options.backend_type =VHOST_BACKEND_TYPE_VDPA ; +assert (ncs->info->type ==NET_CLIENT_DRIVER_VHOST_VDPA ); + s =DO_UPCAST (VhostVDPAState, nc, ncs); + options.net_backend = ncs; + options.opaque = be; + options.busyloop_timeout =0 ; + net =vhost_net_init (&options);
net/vhost-vdpa.c line 127
Quoted 10 lines
net/vhost-vdpa.c new file +10
-0+if (!net) { +error_report ("failed to init vhost_net for queue" ); + goto err; + } +if (s->vhost_net) { +vhost_net_cleanup (s->vhost_net); +g_free (s->vhost_net); + } + s->vhost_net = net; + ret =vhost_vdpa_net_check_device_id (ncs);
Eli pointed out it's better to validate device Id before vhost_net_init().
Otherwise driver may see e.g DRIVER before getting device id.
Quoted 25 lines
net/vhost-vdpa.c new file +25
-0+if (ret) { + goto err; + } +return 0 ; +err: +if (net) { +vhost_net_cleanup (net); + } +vhost_vdpa_del (ncs); +return -1 ; +} + +static void vhost_vdpa_cleanup (NetClientState *nc) +{ +VhostVDPAState *s =DO_UPCAST (VhostVDPAState, nc, nc); + +if (s->vhost_net) { +vhost_net_cleanup (s->vhost_net); +g_free (s->vhost_net); + s->vhost_net =NULL ; + } +} + +static bool vhost_vdpa_has_vnet_hdr (NetClientState *nc) +{
net/vhost-vdpa.c line 162
Quoted 10 lines
net/vhost-vdpa.c new file +10
-0+assert (nc->info->type ==NET_CLIENT_DRIVER_VHOST_VDPA ); + +return true; +} + +static bool vhost_vdpa_has_ufo (NetClientState *nc) +{ +assert (nc->info->type ==NET_CLIENT_DRIVER_VHOST_VDPA ); +VhostVDPAState *s =DO_UPCAST (VhostVDPAState, nc, nc); +uint64_t features =0 ;
Unnecessary spaces between uint64_t and features.
Quoted 14 lines
net/vhost-vdpa.c new file +14
-0+ features |= (1ULL <<VIRTIO_NET_F_HOST_UFO ); + features =vhost_net_get_features (s->vhost_net, features); +return !!(features & (1ULL <<VIRTIO_NET_F_HOST_UFO )); + +} + +static NetClientInfo net_vhost_vdpa_info = { + .type =NET_CLIENT_DRIVER_VHOST_VDPA , + .size =sizeof (VhostVDPAState), + .cleanup = vhost_vdpa_cleanup, + .has_vnet_hdr = vhost_vdpa_has_vnet_hdr, + .has_ufo = vhost_vdpa_has_ufo, +}; +
net/vhost-vdpa.c line 186
Quoted 10 lines
net/vhost-vdpa.c new file +10
-0+static int net_vhost_vdpa_init (NetClientState *peer,const char *device, +const char *name,const char *vhostdev) +{ +NetClientState *nc =NULL ; +VhostVDPAState *s; +int vdpa_device_fd =-1 ; +int ret =0 ; +assert (name); + nc =qemu_new_net_client (&net_vhost_vdpa_info, peer, device, name); +snprintf (nc->info_str,sizeof (nc->info_str),"vhost-vdpa" );
Do we need an identifier for this vhost-vdpa?
Thanks
Quoted 92 lines
net/vhost-vdpa.c new file +44
-0+ nc->queue_index =0 ; + s =DO_UPCAST (VhostVDPAState, nc, nc); + vdpa_device_fd =qemu_open (vhostdev,O_RDWR ); +if (vdpa_device_fd ==-1 ) { +return -errno; + } + s->vhost_vdpa.device_fd = vdpa_device_fd; + ret =vhost_vdpa_add (nc, (void *)&s->vhost_vdpa); +assert (s->vhost_net); +return ret; +} + +static int net_vhost_check_net (void *opaque,QemuOpts *opts,Error **errp) +{ +const char *name = opaque; +const char *driver, *netdev; + + driver =qemu_opt_get (opts,"driver" ); + netdev =qemu_opt_get (opts,"netdev" ); +if (!driver || !netdev) { +return 0 ; + } +if (strcmp (netdev, name) ==0 && + !g_str_has_prefix (driver,"virtio-net-" )) { +error_setg (errp,"vhost-vdpa requires frontend driver virtio-net-*" ); +return -1 ; + } +return 0 ; +} + +int net_init_vhost_vdpa (const Netdev *netdev,const char *name, +NetClientState *peer,Error **errp) +{ +const NetdevVhostVDPAOptions *opts; + +assert (netdev->type ==NET_CLIENT_DRIVER_VHOST_VDPA ); + opts = &netdev->u.vhost_vdpa; +/* verify net frontend */ +if (qemu_opts_foreach (qemu_find_opts ("device" ), net_vhost_check_net, + (char *)name, errp)) { +return -1 ; + } +return net_vhost_vdpa_init (peer,"vhost_vdpa" , name, opts->vhostdev); +}qapi/net.json +21
-2@@ -428,6 +428,24 @@ '*vhostforce': 'bool', '*queues': 'int' } } +## +# @NetdevVhostVDPAOptions: +# +# Vhost-vdpa network backend +# +# @vhostdev: name of a vdpa dev path in sysfs +# (default path:/dev/vhost-vdpa-$ID) +# +# @queues: number of queues to be created for multiqueue vhost-vdpa +# (default: 1) +# +# Since: 5.1 +## +{ 'struct': 'NetdevVhostVDPAOptions', + 'data': { + '*vhostdev': 'str', + '*queues': 'int' } } + ## # @NetClientDriver: #@@ -437,7 +455,7 @@ ## { 'enum': 'NetClientDriver', 'data': [ 'none', 'nic', 'user', 'tap', 'l2tpv3', 'socket', 'vde', - 'bridge', 'hubport', 'netmap', 'vhost-user' ] } + 'bridge', 'hubport', 'netmap', 'vhost-user', 'vhost-vdpa' ] } ## # @Netdev:@@ -465,7 +483,8 @@ 'bridge': 'NetdevBridgeOptions', 'hubport': 'NetdevHubPortOptions', 'netmap': 'NetdevNetmapOptions', - 'vhost-user': 'NetdevVhostUserOptions' } } + 'vhost-user': 'NetdevVhostUserOptions', + 'vhost-vdpa': 'NetdevVhostVDPAOptions' } } ## # @NetLegacy:
Re: [PATCH v1 10/10] vhost-vdpa: introduce vhost-vdpa net client
Quoted 63 lines · Jason Wang
Quoted 51 lines · Cindy Lu
This patch set introduces a new net client type: vhost-vdpa. vhost-vdpa net client will set up a vDPA device which is specified by a "vhostdev" parameter.
Signed-off-by Lingshan Zhu <[email protected]>Signed-off-by Tiwei Bie <[email protected]>Signed-off-by Cindy Lu <[email protected]>--- include/net/vhost-vdpa.h | 21 ++++ include/net/vhost_net.h | 1 - net/Makefile.objs | 2 +- net/clients.h | 2 + net/net.c | 3 + net/vhost-vdpa.c | 230 +++++++++++++++++++++++++++++++++++++++ qapi/net.json | 23 +++- 7 files changed, 278 insertions(+), 4 deletions(-)create mode 100644
include/net/vhost-vdpa.h
create mode 100644net/vhost-vdpa.cinclude/net/vhost-vdpa.h new file +21
-0@@ -0,0 +1,21 @@ +/* +* vhost-vdpa.h +* +* Copyright(c) 2017-2018 Intel Corporation. +* Copyright(c) 2020 Red Hat, Inc. +* +* This work is licensed under the terms of the GNU GPL, version 2 or later. +* See the COPYING file in the top-level directory. +* +*/ + +#ifndef VHOST_VDPA_H +#define VHOST_VDPA_H + +struct vhost_net ; +struct vhost_net *vhost_vdpa_get_vhost_net (NetClientState *nc); +uint64_t vhost_vdpa_get_acked_features (NetClientState *nc); + +extern const int vdpa_feature_bits[]; + +#endif /* VHOST_VDPA_H */ include/net/vhost_net.h +0
-0include/net/vhost_net.h int vhost_set_vring_enable(NetClientState * nc, int enable); · line 47
Quoted 4 lines
include/net/vhost_net.h +0
-1@@ -44,5 +44,4 @@ int vhost_set_vring_enable(NetClientState * nc, int enable);uint64_t vhost_net_get_acked_features (VHostNetState *net);int vhost_net_set_mtu (struct vhost_net *net,uint16_t mtu); -Let's keep this newline.
Quoted 15 lines
net/Makefile.objs tap-obj-$(CONFIG_SOLARIS) = tap-solaris.o · line 29
Quoted 10 lines
include/net/vhost_net.h +0
-0#endif net/Makefile.objs +0
-1@@ -26,7 +26,7 @@ tap-obj-$(CONFIG_SOLARIS) = tap-solaris.o tap-obj-y ?= tap-stub.o common-obj-$(CONFIG_POSIX) += tap.o $(tap-obj-y) common-obj-$(CONFIG_WIN32) += tap-win32.o -And this.
Sure will do, I will double check these issue next time
Quoted 115 lines
Quoted 115 lines
net/Makefile.objs +1
-0+common-obj-$(CONFIG_VHOST_NET_VDPA) += vhost-vdpa.o vde.o-libs = $(VDE_LIBS) common-obj-$(CONFIG_CAN_BUS) += can/net/clients.h +2
-0@@ -61,4 +61,6 @@ int net_init_netmap(const Netdev *netdev, const char *name,int net_init_vhost_user (const Netdev *netdev,const char *name,NetClientState *peer,Error **errp); +int net_init_vhost_vdpa (const Netdev *netdev,const char *name, +NetClientState *peer,Error **errp);#endif /* QEMU_NET_CLIENTS_H */ net/net.c +3
-0@@ -965,6 +965,9 @@ static int (* const net_client_init_fun[NET_CLIENT_DRIVER__MAX])( #ifdef CONFIG_VHOST_NET_USER [NET_CLIENT_DRIVER_VHOST_USER ] = net_init_vhost_user, #endif +#ifdef CONFIG_VHOST_NET_VDPA + [NET_CLIENT_DRIVER_VHOST_VDPA ] = net_init_vhost_vdpa, +#endif #ifdef CONFIG_L2TPV3 [NET_CLIENT_DRIVER_L2TPV3] = net_init_l2tpv3, #endifnet/vhost-vdpa.c new file +80
-0@@ -0,0 +1,230 @@ +/* +* vhost-vdpa.c +* +* Copyright(c) 2017-2018 Intel Corporation. +* Copyright(c) 2020 Red Hat, Inc. +* +* This work is licensed under the terms of the GNU GPL, version 2 or later. +* See the COPYING file in the top-level directory. +* +*/ + +#include "qemu/osdep.h" +#include "clients.h" +#include "net/vhost_net.h" +#include "net/vhost-vdpa.h" +#include "hw/virtio/vhost-vdpa.h" +#include "qemu/config-file.h" +#include "qemu/error-report.h" +#include "qemu/option.h" +#include "qapi/error.h" +#include <sys/ioctl.h> +#include <err.h> +#include "standard-headers/linux/virtio_net.h" +#include "monitor/monitor.h" +#include "hw/virtio/vhost.h" + +/* Todo:need to add the multiqueue support here */ +typedef struct VhostVDPAState { +NetClientState nc; +struct vhost_vdpa vhost_vdpa; +VHostNetState *vhost_net; +uint64_t acked_features; +bool started; +}VhostVDPAState ; + +const int vdpa_feature_bits[] = { +VIRTIO_F_NOTIFY_ON_EMPTY , +VIRTIO_RING_F_INDIRECT_DESC , +VIRTIO_RING_F_EVENT_IDX , +VIRTIO_F_ANY_LAYOUT , +VIRTIO_F_VERSION_1 , +VIRTIO_NET_F_CSUM , +VIRTIO_NET_F_GUEST_CSUM , +VIRTIO_NET_F_GSO , +VIRTIO_NET_F_GUEST_TSO4 , +VIRTIO_NET_F_GUEST_TSO6 , +VIRTIO_NET_F_GUEST_ECN , +VIRTIO_NET_F_GUEST_UFO , +VIRTIO_NET_F_HOST_TSO4 , +VIRTIO_NET_F_HOST_TSO6 , +VIRTIO_NET_F_HOST_ECN , +VIRTIO_NET_F_HOST_UFO , +VIRTIO_NET_F_MRG_RXBUF , +VIRTIO_NET_F_MTU , +VIRTIO_F_IOMMU_PLATFORM , +VIRTIO_F_RING_PACKED , +VIRTIO_NET_F_GUEST_ANNOUNCE , +VHOST_INVALID_FEATURE_BIT +}; + +VHostNetState *vhost_vdpa_get_vhost_net (NetClientState *nc) +{ +VhostVDPAState *s =DO_UPCAST (VhostVDPAState, nc, nc); +assert (nc->info->type ==NET_CLIENT_DRIVER_VHOST_VDPA ); +return s->vhost_net; +} + +uint64_t vhost_vdpa_get_acked_features (NetClientState *nc) +{ +VhostVDPAState *s =DO_UPCAST (VhostVDPAState, nc, nc); +assert (nc->info->type ==NET_CLIENT_DRIVER_VHOST_VDPA ); + s->acked_features =vhost_net_get_acked_features (s->vhost_net); + +return s->acked_features; +} + +static int vhost_vdpa_net_check_device_id (NetClientState *nc) +{ +uint32_t device_id; +int ret;
Quoted 9 lines
net/vhost-vdpa.c line 84
Quoted 4 lines
net/vhost-vdpa.c new file +4
-0+struct vhost_net *net; +struct vhost_dev *hdev; +assert (nc->info->type ==NET_CLIENT_DRIVER_VHOST_VDPA ); +VhostVDPAState *s =DO_UPCAST (VhostVDPAState, nc, nc);Let's try to avoid those unnecessary conversion and check since the caller knows e.g VhostVDPAState.
sure will change this
Quoted 48 lines
Quoted 34 lines
net/vhost-vdpa.c new file +33
-0+ net = s->vhost_net; + hdev = (struct vhost_dev *)&net->dev; + ret = hdev->vhost_ops->vhost_get_device_id (hdev, &device_id); +if (device_id !=VIRTIO_ID_NET ) { +return -ENOTSUP ; + } +return ret; +} + +static void vhost_vdpa_del (NetClientState *ncs) +{ +VhostVDPAState *s; +assert (ncs->info->type ==NET_CLIENT_DRIVER_VHOST_VDPA ); + s =DO_UPCAST (VhostVDPAState, nc, ncs); +if (s->vhost_net) { +vhost_net_cleanup (s->vhost_net); + } +} + +static int vhost_vdpa_add (NetClientState *ncs,void *be) +{ +VhostNetOptions options; +struct vhost_net *net =NULL ; +VhostVDPAState *s; +int ret; + + options.backend_type =VHOST_BACKEND_TYPE_VDPA ; +assert (ncs->info->type ==NET_CLIENT_DRIVER_VHOST_VDPA ); + s =DO_UPCAST (VhostVDPAState, nc, ncs); + options.net_backend = ncs; + options.opaque = be; + options.busyloop_timeout =0 ; + net =vhost_net_init (&options);net/vhost-vdpa.c line 127
Quoted 10 lines
net/vhost-vdpa.c new file +10
-0+if (!net) { +error_report ("failed to init vhost_net for queue" ); + goto err; + } +if (s->vhost_net) { +vhost_net_cleanup (s->vhost_net); +g_free (s->vhost_net); + } + s->vhost_net = net; + ret =vhost_vdpa_net_check_device_id (ncs);Eli pointed out it's better to validate device Id before
vhost_net_init().
Quoted 2 lines
Otherwise driver may see e.g DRIVER before getting device id.
Maybe we can't move this before vhost_net_init(), because the callback vhost_ops->vhost_get_device_id was init during vhost_net_init()
Quoted 31 lines
Quoted 31 lines
net/vhost-vdpa.c new file +30
-0+if (ret) { + goto err; + } +return 0 ; +err: +if (net) { +vhost_net_cleanup (net); + } +vhost_vdpa_del (ncs); +return -1 ; +} + +static void vhost_vdpa_cleanup (NetClientState *nc) +{ +VhostVDPAState *s =DO_UPCAST (VhostVDPAState, nc, nc); + +if (s->vhost_net) { +vhost_net_cleanup (s->vhost_net); +g_free (s->vhost_net); + s->vhost_net =NULL ; + } +} + +static bool vhost_vdpa_has_vnet_hdr (NetClientState *nc) +{ +assert (nc->info->type ==NET_CLIENT_DRIVER_VHOST_VDPA ); + +return true; +} +
Quoted 9 lines
net/vhost-vdpa.c line 162
Quoted 5 lines
net/vhost-vdpa.c new file +5
-0+static bool vhost_vdpa_has_ufo (NetClientState *nc) +{ +assert (nc->info->type ==NET_CLIENT_DRIVER_VHOST_VDPA ); +VhostVDPAState *s =DO_UPCAST (VhostVDPAState, nc, nc); +uint64_t features =0 ;Unnecessary spaces between
uint64_tand features.
will remove
Quoted 29 lines
Quoted 15 lines
net/vhost-vdpa.c new file +14
-0+ features |= (1ULL <<VIRTIO_NET_F_HOST_UFO ); + features =vhost_net_get_features (s->vhost_net, features); +return !!(features & (1ULL <<VIRTIO_NET_F_HOST_UFO )); + +} + +static NetClientInfo net_vhost_vdpa_info = { + .type =NET_CLIENT_DRIVER_VHOST_VDPA , + .size =sizeof (VhostVDPAState), + .cleanup = vhost_vdpa_cleanup, + .has_vnet_hdr = vhost_vdpa_has_vnet_hdr, + .has_ufo = vhost_vdpa_has_ufo, +}; +net/vhost-vdpa.c line 186
Quoted 10 lines
net/vhost-vdpa.c new file +10
-0+static int net_vhost_vdpa_init (NetClientState *peer,const char *device, +const char *name,const char *vhostdev) +{ +NetClientState *nc =NULL ; +VhostVDPAState *s; +int vdpa_device_fd =-1 ; +int ret =0 ; +assert (name); + nc =qemu_new_net_client (&net_vhost_vdpa_info, peer, device, name); +snprintf (nc->info_str,sizeof (nc->info_str),"vhost-vdpa" );Do we need an for this vhost-vdpa?
Quoted 3 lines
Thanks
Sure will add this
Quoted 93 lines
Quoted 92 lines
net/vhost-vdpa.c new file +44
-0+ nc->queue_index =0 ; + s =DO_UPCAST (VhostVDPAState, nc, nc); + vdpa_device_fd =qemu_open (vhostdev,O_RDWR ); +if (vdpa_device_fd ==-1 ) { +return -errno; + } + s->vhost_vdpa.device_fd = vdpa_device_fd; + ret =vhost_vdpa_add (nc, (void *)&s->vhost_vdpa); +assert (s->vhost_net); +return ret; +} + +static int net_vhost_check_net (void *opaque,QemuOpts *opts,Error **errp) +{ +const char *name = opaque; +const char *driver, *netdev; + + driver =qemu_opt_get (opts,"driver" ); + netdev =qemu_opt_get (opts,"netdev" ); +if (!driver || !netdev) { +return 0 ; + } +if (strcmp (netdev, name) ==0 && + !g_str_has_prefix (driver,"virtio-net-" )) { +error_setg (errp,"vhost-vdpa requires frontend driver virtio-net-*" ); +return -1 ; + } +return 0 ; +} + +int net_init_vhost_vdpa (const Netdev *netdev,const char *name, +NetClientState *peer,Error **errp) +{ +const NetdevVhostVDPAOptions *opts; + +assert (netdev->type ==NET_CLIENT_DRIVER_VHOST_VDPA ); + opts = &netdev->u.vhost_vdpa; +/* verify net frontend */ +if (qemu_opts_foreach (qemu_find_opts ("device" ), net_vhost_check_net, + (char *)name, errp)) { +return -1 ; + } +return net_vhost_vdpa_init (peer,"vhost_vdpa" , name, opts->vhostdev); +}qapi/net.json +21
-2@@ -428,6 +428,24 @@ '*vhostforce': 'bool', '*queues': 'int' } } +## +# @NetdevVhostVDPAOptions: +# +# Vhost-vdpa network backend +# +# @vhostdev: name of a vdpa dev path in sysfs +# (default path:/dev/vhost-vdpa-$ID) +# +# @queues: number of queues to be created for multiqueue vhost-vdpa +# (default: 1) +# +# Since: 5.1 +## +{ 'struct': 'NetdevVhostVDPAOptions', + 'data': { + '*vhostdev': 'str', + '*queues': 'int' } } + ## # @NetClientDriver: #@@ -437,7 +455,7 @@ ## { 'enum': 'NetClientDriver', 'data': [ 'none', 'nic', 'user', 'tap', 'l2tpv3', 'socket', 'vde', - 'bridge', 'hubport', 'netmap', 'vhost-user' ] } + 'bridge', 'hubport', 'netmap', 'vhost-user', 'vhost-vdpa' ] } ## # @Netdev:@@ -465,7 +483,8 @@ 'bridge': 'NetdevBridgeOptions', 'hubport': 'NetdevHubPortOptions', 'netmap': 'NetdevNetmapOptions', - 'vhost-user': 'NetdevVhostUserOptions' } } + 'vhost-user': 'NetdevVhostUserOptions', + 'vhost-vdpa': 'NetdevVhostVDPAOptions' } } ## # @NetLegacy:
Quoted 7 lines · Cindy Lu
vDPA device is a device that uses a datapath which complies with the virtio specifications with vendor specific control path. vDPA devices can be both physically located on the hardware or emulated by software. This RFC introduce the vDPA support in qemu
TODO
1) vIOMMU support
2) live migration support
This gives me the foggiest of ideas on what vDPA is. Could we use docs/interop/vhost-vdpa.rst?
Quoted 11 lines · Markus Armbruster
Quoted 7 lines · Cindy Lu
vDPA device is a device that uses a datapath which complies with the virtio specifications with vendor specific control path. vDPA devices can be both physically located on the hardware or emulated by software. This RFC introduce the vDPA support in qemu
TODO
1) vIOMMU support
2) live migration support
Quoted 3 lines
This gives me the foggiest of ideas on what vDPA is. Could we use
docs/interop/vhost-vdpa.rst?
Sure will add this
Quoted 10 lines · Cindy Lu
Quoted 9 lines · Markus Armbruster
Quoted 7 lines · Cindy Lu
vDPA device is a device that uses a datapath which complies with the virtio specifications with vendor specific control path. vDPA devices can be both physically located on the hardware or emulated by software. This RFC introduce the vDPA support in qemu
TODO
1) vIOMMU support
2) live migration support
Quoted 6 lines
Quoted 3 lines
This gives me the foggiest of ideas on what vDPA is. Could we use
docs/interop/vhost-vdpa.rst?Sure will add this
Not sure it's the best place since vhost-vdpa is kernel specific.
Maybe kernel docs (TBD) is a better place and we can refer it this file in the future.
But it doesn't harm if you said something more here and refer the kernel commit here: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?id=4c8cf31885f69e86be0b5b9e6677a26797365e1d
Thanks
Quoted 22 lines · Jason Wang
Quoted 10 lines · Cindy Lu
Quoted 9 lines · Markus Armbruster
Quoted 7 lines · Cindy Lu
vDPA device is a device that uses a datapath which complies with the virtio specifications with vendor specific control path. vDPA devices can be both physically located on the hardware or emulated by software. This RFC introduce the vDPA support in qemu
TODO
1) vIOMMU support
2) live migration supportQuoted 6 lines
Quoted 3 lines
This gives me the foggiest of ideas on what vDPA is. Could we use
docs/interop/vhost-vdpa.rst?Sure will add this
Not sure it's the best place since vhost-vdpa is kernel specific.
Quoted 10 lines
Maybe kernel docs (TBD) is a better place and we can refer it this file in the future.
But it doesn't harm if you said something more here and refer the kernel commit here:
https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?id=4c8cf31885f69e86be0b5b9e6677a26797365e1dThanks
Hi Markus,
I think I agree with Jason's opinion, kernel docs is a better place. Maybe we can keep what it is now, and do this job in the future.
Thanks
Cindy
Quoted 30 lines · Cindy Lu
Quoted 29 lines · Jason Wang
Quoted 10 lines · Cindy Lu
Quoted 9 lines · Markus Armbruster
Quoted 7 lines · Cindy Lu
vDPA device is a device that uses a datapath which complies with the virtio specifications with vendor specific control path. vDPA devices can be both physically located on the hardware or emulated by software. This RFC introduce the vDPA support in qemu
TODO
1) vIOMMU support
2) live migration supportQuoted 6 lines
Quoted 3 lines
This gives me the foggiest of ideas on what vDPA is. Could we use
docs/interop/vhost-vdpa.rst?Sure will add this
Not sure it's the best place since vhost-vdpa is kernel specific.
Maybe kernel docs (TBD) is a better place and we can refer it this file in the future.
But it doesn't harm if you said something more here and refer the kernel commit here:
https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?id=4c8cf31885f69e86be0b5b9e6677a26797365e1d
Quoted 6 lines
Quoted 3 lines
Thanks
Hi Markus,
I think I agree with Jason's opinion, kernel docs is a better place. Maybe we can keep what it is now, and do this job in the future.
I think a super-short description of vDPA here (one sentence?) together with a link to complete information would be helpful. If the link's target doesn't yet exist, adding the link later is okay.
Quoted 36 lines · Markus Armbruster
Quoted 33 lines · Cindy Lu
Quoted 32 lines · Jason Wang
Quoted 10 lines · Cindy Lu
Quoted 9 lines · Markus Armbruster
Quoted 7 lines · Cindy Lu
vDPA device is a device that uses a datapath which complies with the virtio specifications with vendor specific control path. vDPA devices can be both physically located on the hardware or emulated by software. This RFC introduce the vDPA support in qemu
TODO
1) vIOMMU support
2) live migration supportQuoted 6 lines
Quoted 3 lines
This gives me the foggiest of ideas on what vDPA is. Could we use
docs/interop/vhost-vdpa.rst?Sure will add this
Not sure it's the best place since vhost-vdpa is kernel specific.
Maybe kernel docs (TBD) is a better place and we can refer it this file in the future.
But it doesn't harm if you said something more here and refer the kernel commit here:
https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?id=4c8cf31885f69e86be0b5b9e6677a26797365e1dThanks
Quoted 8 lines
Quoted 3 lines
Hi Markus,
I think I agree with Jason's opinion, kernel docs is a better place. Maybe we can keep what it is now, and do this job in the future.I think a super-short description of vDPA here (one sentence?) together with a link to complete information would be helpful. If the link's target doesn't yet exist, adding the link later is okay.
sure thanks Markus, will do
Quoted 7 lines · Cindy Lu
vDPA device is a device that uses a datapath which complies with the virtio specifications with vendor specific control path. vDPA devices can be both physically located on the hardware or emulated by software. This RFC introduce the vDPA support in qemu
TODO
1) vIOMMU support
2) live migration support
Jut notice that the config interrupt [1] looks missed in this series.
Please add them in next version.
Thanks
Quoted 12 lines · Jason Wang
Quoted 7 lines · Cindy Lu
vDPA device is a device that uses a datapath which complies with the virtio specifications with vendor specific control path. vDPA devices can be both physically located on the hardware or emulated by software. This RFC introduce the vDPA support in qemu
TODO
1) vIOMMU support
2) live migration support
Quoted 9 lines
Jut notice that the config interrupt [1] looks missed in this series.
Please add them in next version.
Thanks
sure will add this part