Hi Maxime,
> -----Original Message-----
> From: Maxime Coquelin [mailto:maxime.coque...@redhat.com]
> Sent: Thursday, March 22, 2018 4:58 AM
> To: Wang, Xiao W <xiao.w.w...@intel.com>; y...@fridaylinux.org
> Cc: dev@dpdk.org; Wang, Zhihong <zhihong.w...@intel.com>; Bie, Tiwei
> <tiwei....@intel.com>; Chen, Junjie J <junjie.j.c...@intel.com>; Xu, Rosen
> <rosen...@intel.com>; Daly, Dan <dan.d...@intel.com>; Liang, Cunming
> <cunming.li...@intel.com>; Burakov, Anatoly <anatoly.bura...@intel.com>;
> gaetan.ri...@6wind.com
> Subject: Re: [PATCH v2 3/3] net/ifcvf: add ifcvf driver
>
>
>
> On 03/21/2018 02:21 PM, Xiao Wang wrote:
> > ifcvf driver uses vdev as a control domain to manage ifc VFs that belong
> > to it. It registers vDPA device ops to vhost lib to enable these VFs to be
> > used as vhost data path accelerator.
> >
> > Live migration feature is supported by ifc VF and this driver enables
> > it based on vhost lib.
> >
> > Because vDPA driver needs to set up MSI-X vector to interrupt the guest,
> > only vfio-pci is supported currently.
> >
> > Signed-off-by: Xiao Wang <xiao.w.w...@intel.com>
> > Signed-off-by: Rosen Xu <rosen...@intel.com>
> > ---
> > v2:
> > - Rebase on Zhihong's vDPA v3 patch set.
> > ---
> > config/common_base | 6 +
> > config/common_linuxapp | 1 +
> > drivers/net/Makefile | 1 +
> > drivers/net/ifcvf/Makefile | 40 +
> > drivers/net/ifcvf/base/ifcvf.c | 329 ++++++++
> > drivers/net/ifcvf/base/ifcvf.h | 156 ++++
> > drivers/net/ifcvf/base/ifcvf_osdep.h | 52 ++
> > drivers/net/ifcvf/ifcvf_ethdev.c | 1240
> +++++++++++++++++++++++++++++++
> > drivers/net/ifcvf/rte_ifcvf_version.map | 4 +
> > mk/rte.app.mk | 1 +
> > 10 files changed, 1830 insertions(+)
> > create mode 100644 drivers/net/ifcvf/Makefile
> > create mode 100644 drivers/net/ifcvf/base/ifcvf.c
> > create mode 100644 drivers/net/ifcvf/base/ifcvf.h
> > create mode 100644 drivers/net/ifcvf/base/ifcvf_osdep.h
> > create mode 100644 drivers/net/ifcvf/ifcvf_ethdev.c
> > create mode 100644 drivers/net/ifcvf/rte_ifcvf_version.map
> >
>
> ...
>
> > +static int
> > +eth_dev_ifcvf_create(struct rte_vdev_device *dev,
> > + struct rte_pci_addr *pci_addr, int devices)
> > +{
> > + const char *name = rte_vdev_device_name(dev);
> > + struct rte_eth_dev *eth_dev = NULL;
> > + struct ether_addr *eth_addr = NULL;
> > + struct ifcvf_internal *internal = NULL;
> > + struct internal_list *list = NULL;
> > + struct rte_eth_dev_data *data = NULL;
> > + struct rte_pci_addr pf_addr = *pci_addr;
> > + int i;
> > +
> > + list = rte_zmalloc_socket(name, sizeof(*list), 0,
> > + dev->device.numa_node);
> > + if (list == NULL)
> > + goto error;
> > +
> > + /* reserve an ethdev entry */
> > + eth_dev = rte_eth_vdev_allocate(dev, sizeof(*internal));
> > + if (eth_dev == NULL)
> > + goto error;
> > +
> > + eth_addr = rte_zmalloc_socket(name, sizeof(*eth_addr), 0,
> > + dev->device.numa_node);
> > + if (eth_addr == NULL)
> > + goto error;
> > +
> > + *eth_addr = base_eth_addr;
> > + eth_addr->addr_bytes[5] = eth_dev->data->port_id;
> > +
> > + internal = eth_dev->data->dev_private;
> > + internal->dev_name = strdup(name);
> > + if (internal->dev_name == NULL)
> > + goto error;
> > +
> > + internal->eng_addr.pci_addr = *pci_addr;
> > + for (i = 0; i < devices; i++) {
> > + pf_addr.domain = pci_addr->domain;
> > + pf_addr.bus = pci_addr->bus;
> > + pf_addr.devid = pci_addr->devid + (i + 1) / 8;
> > + pf_addr.function = pci_addr->function + (i + 1) % 8;
> > + internal->vf_info[i].pdev.addr = pf_addr;
> > + rte_spinlock_init(&internal->vf_info[i].lock);
> > + }
> > + internal->max_devices = devices;
> > +
> > + list->eth_dev = eth_dev;
> > + pthread_mutex_lock(&internal_list_lock);
> > + TAILQ_INSERT_TAIL(&internal_list, list, next);
> > + pthread_mutex_unlock(&internal_list_lock);
> > +
> > + data = eth_dev->data;
> > + data->nb_rx_queues = IFCVF_MAX_QUEUES;
> > + data->nb_tx_queues = IFCVF_MAX_QUEUES;
> > + data->dev_link = vdpa_link;
> > + data->mac_addrs = eth_addr;
>
> We might want one ethernet device per VF, as for example you set
> dev_link.link_status to UP as soon as a VF is configured, and DOWN
> as when a single VF is removed.
Ideally it will be one representor port per VF, each representor port
has a link_status. Will integrate port representor when it's ready.
I will remove the vdev's ethdev registering for now, and add it back when we
need to implement flow APIs on the vdev.
>
> > + data->dev_flags = RTE_ETH_DEV_INTR_LSC;
> > + eth_dev->dev_ops = &ops;
> > +
> > + /* assign rx and tx ops, could be used as vDPA fallback */
> > + eth_dev->rx_pkt_burst = eth_ifcvf_rx;
> > + eth_dev->tx_pkt_burst = eth_ifcvf_tx;
> > +
> > + if (rte_vdpa_register_engine(vdpa_ifcvf_driver.name,
> > + &internal->eng_addr) < 0)
> > + goto error;
> > +
> > + return 0;
> > +
> > +error:
> > + rte_free(list);
> > + rte_free(eth_addr);
> > + if (internal && internal->dev_name)
> > + free(internal->dev_name);
> > + rte_free(internal);
> > + if (eth_dev)
> > + rte_eth_dev_release_port(eth_dev);
> > +
> > + return -1;
> > +}
> > +
> > +static int
> > +get_pci_addr(const char *key __rte_unused, const char *value, void
> *extra_args)
> > +{
> > + if (value == NULL || extra_args == NULL)
> > + return -1;
> > +
> > + return rte_pci_addr_parse(value, extra_args);
> > +}
> > +
> > +static inline int
> > +open_int(const char *key __rte_unused, const char *value, void
> *extra_args)
> > +{
> > + uint16_t *n = extra_args;
> > +
> > + if (value == NULL || extra_args == NULL)
> > + return -EINVAL;
> > +
> > + *n = (uint16_t)strtoul(value, NULL, 0);
> > + if (*n == USHRT_MAX && errno == ERANGE)
> > + return -1;
> > +
> > + return 0;
> > +}
> > +
> > +/*
> > + * If this vdev is created by user, then ifcvf will be taken by
> > + * this vdev.
> > + */
> > +static int
> > +ifcvf_take_over(struct rte_pci_addr *pci_addr, int num)
> > +{
> > + uint16_t port_id;
> > + int i, ret;
> > + char devname[RTE_DEV_NAME_MAX_LEN];
> > + struct rte_pci_addr vf_addr = *pci_addr;
> > +
> > + for (i = 0; i < num; i++) {
> > + vf_addr.function += i % 8;
> > + vf_addr.devid += i / 8;
> > + rte_pci_device_name(&vf_addr, devname,
> RTE_DEV_NAME_MAX_LEN);
> > + ret = rte_eth_dev_get_port_by_name(devname, &port_id);
> > + if (ret == 0) {
> > + rte_eth_dev_close(port_id);
> > + if (rte_eth_dev_detach(port_id, devname) < 0)
> > + return -1;
> > + }
> That seems a bit hard.
> Shouldn't we at least check the port is not started?
That looks better, will do it.
Thanks for the comments,
-Xiao
