[dpdk-dev] [PATCH 3/7] hv: add basic vmbus support

[Stephen Hemminger]

The hyper-v device driver forces the base EAL code to change
to support multiple bus types. This is done changing the pci_device
in ether driver to a generic union.

As much as possible this is done in a backwards source compatiable
way. It will break ABI for device drivers.

Signed-off-by: Stephen Hemminger <stephen at networkplumber.org>
---
 lib/librte_eal/common/Makefile             |   2 +-
 lib/librte_eal/common/eal_common_options.c |   5 ++
 lib/librte_eal/common/eal_internal_cfg.h   |   1 +
 lib/librte_eal/common/eal_options.h        |   2 +
 lib/librte_eal/common/eal_private.h        |  10 +++
 lib/librte_eal/linuxapp/eal/Makefile       |   3 +
 lib/librte_eal/linuxapp/eal/eal.c          |  11 +++
 lib/librte_ether/rte_ethdev.c              | 128 +++++++++++++++++++++++++++--
 lib/librte_ether/rte_ethdev.h              |  15 +++-
 9 files changed, 168 insertions(+), 9 deletions(-)

diff --git a/lib/librte_eal/common/Makefile b/lib/librte_eal/common/Makefile
index 3ea3bbf..202485e 100644
--- a/lib/librte_eal/common/Makefile
+++ b/lib/librte_eal/common/Makefile
@@ -33,7 +33,7 @@ include $(RTE_SDK)/mk/rte.vars.mk
 
 INC := rte_branch_prediction.h rte_common.h
 INC += rte_debug.h rte_eal.h rte_errno.h rte_launch.h rte_lcore.h
-INC += rte_log.h rte_memory.h rte_memzone.h rte_pci.h
+INC += rte_log.h rte_memory.h rte_memzone.h rte_pci.h rte_vmbus.h
 INC += rte_pci_dev_ids.h rte_per_lcore.h rte_random.h
 INC += rte_rwlock.h rte_tailq.h rte_interrupts.h rte_alarm.h
 INC += rte_string_fns.h rte_version.h
diff --git a/lib/librte_eal/common/eal_common_options.c b/lib/librte_eal/common/eal_common_options.c
index 8fcb1ab..76a3394 100644
--- a/lib/librte_eal/common/eal_common_options.c
+++ b/lib/librte_eal/common/eal_common_options.c
@@ -80,6 +80,7 @@ eal_long_options[] = {
 	{OPT_NO_HPET,           0, NULL, OPT_NO_HPET_NUM          },
 	{OPT_NO_HUGE,           0, NULL, OPT_NO_HUGE_NUM          },
 	{OPT_NO_PCI,            0, NULL, OPT_NO_PCI_NUM           },
+	{OPT_NO_VMBUS,		0, NULL, OPT_NO_VMBUS_NUM	  },
 	{OPT_NO_SHCONF,         0, NULL, OPT_NO_SHCONF_NUM        },
 	{OPT_PCI_BLACKLIST,     1, NULL, OPT_PCI_BLACKLIST_NUM    },
 	{OPT_PCI_WHITELIST,     1, NULL, OPT_PCI_WHITELIST_NUM    },
@@ -726,6 +727,10 @@ eal_parse_common_option(int opt, const char *optarg,
 		conf->no_pci = 1;
 		break;
 
+	case OPT_NO_VMBUS_NUM:
+		conf->no_vmbus = 1;
+		break;
+
 	case OPT_NO_HPET_NUM:
 		conf->no_hpet = 1;
 		break;
diff --git a/lib/librte_eal/common/eal_internal_cfg.h b/lib/librte_eal/common/eal_internal_cfg.h
index e2ecb0d..0e7de34 100644
--- a/lib/librte_eal/common/eal_internal_cfg.h
+++ b/lib/librte_eal/common/eal_internal_cfg.h
@@ -66,6 +66,7 @@ struct internal_config {
 	volatile unsigned no_hugetlbfs;   /**< true to disable hugetlbfs */
 	volatile unsigned xen_dom0_support; /**< support app running on Xen Dom0*/
 	volatile unsigned no_pci;         /**< true to disable PCI */
+	volatile unsigned no_vmbus;	  /**< true to disable VMBUS */
 	volatile unsigned no_hpet;        /**< true to disable HPET */
 	volatile unsigned vmware_tsc_map; /**< true to use VMware TSC mapping
 										* instead of native TSC */
diff --git a/lib/librte_eal/common/eal_options.h b/lib/librte_eal/common/eal_options.h
index f6714d9..54f03dc 100644
--- a/lib/librte_eal/common/eal_options.h
+++ b/lib/librte_eal/common/eal_options.h
@@ -67,6 +67,8 @@ enum {
 	OPT_NO_HUGE_NUM,
 #define OPT_NO_PCI            "no-pci"
 	OPT_NO_PCI_NUM,
+#define OPT_NO_VMBUS          "no-vmbus"
+	OPT_NO_VMBUS_NUM,
 #define OPT_NO_SHCONF         "no-shconf"
 	OPT_NO_SHCONF_NUM,
 #define OPT_SOCKET_MEM        "socket-mem"
diff --git a/lib/librte_eal/common/eal_private.h b/lib/librte_eal/common/eal_private.h
index 4acf5a0..039e9f3 100644
--- a/lib/librte_eal/common/eal_private.h
+++ b/lib/librte_eal/common/eal_private.h
@@ -180,6 +180,16 @@ int rte_eal_pci_close_one_driver(struct rte_pci_driver *dr,
 		struct rte_pci_device *dev);
 
 /**
+ * VMBUS related functions and structures
+ */
+int rte_eal_vmbus_init(void);
+
+struct rte_vmbus_driver;
+struct rte_vmbus_device;
+
+int rte_eal_vmbus_probe_one_driver(struct rte_vmbus_driver *dr,
+		struct rte_vmbus_device *dev);
+/**
  * Init tail queues for non-EAL library structures. This is to allow
  * the rings, mempools, etc. lists to be shared among multiple processes
  *
diff --git a/lib/librte_eal/linuxapp/eal/Makefile b/lib/librte_eal/linuxapp/eal/Makefile
index 01f7b70..acd5127 100644
--- a/lib/librte_eal/linuxapp/eal/Makefile
+++ b/lib/librte_eal/linuxapp/eal/Makefile
@@ -74,6 +74,9 @@ SRCS-$(CONFIG_RTE_LIBRTE_EAL_LINUXAPP) += eal_alarm.c
 ifeq ($(CONFIG_RTE_LIBRTE_IVSHMEM),y)
 SRCS-$(CONFIG_RTE_LIBRTE_EAL_LINUXAPP) += eal_ivshmem.c
 endif
+ifeq ($(CONFIG_RTE_LIBRTE_HV_PMD),y)
+SRCS-$(CONFIG_RTE_LIBRTE_EAL_LINUXAPP) += eal_vmbus.c
+endif
 
 # from common dir
 SRCS-$(CONFIG_RTE_LIBRTE_EAL_LINUXAPP) += eal_common_memzone.c
diff --git a/lib/librte_eal/linuxapp/eal/eal.c b/lib/librte_eal/linuxapp/eal/eal.c
index bd770cf..86d0e31 100644
--- a/lib/librte_eal/linuxapp/eal/eal.c
+++ b/lib/librte_eal/linuxapp/eal/eal.c
@@ -70,6 +70,7 @@
 #include <rte_cpuflags.h>
 #include <rte_interrupts.h>
 #include <rte_pci.h>
+#include <rte_vmbus.h>
 #include <rte_devargs.h>
 #include <rte_common.h>
 #include <rte_version.h>
@@ -796,6 +797,11 @@ rte_eal_init(int argc, char **argv)
 
 	rte_eal_mcfg_complete();
 
+#ifdef RTE_LIBRTE_HV_PMD
+	if (rte_eal_vmbus_init() < 0)
+		RTE_LOG(ERR, EAL, "Cannot init VMBUS\n");
+#endif
+
 	TAILQ_FOREACH(solib, &solib_list, next) {
 		RTE_LOG(INFO, EAL, "open shared lib %s\n", solib->name);
 		solib->lib_handle = dlopen(solib->name, RTLD_NOW);
@@ -845,6 +851,11 @@ rte_eal_init(int argc, char **argv)
 	if (rte_eal_pci_probe())
 		rte_panic("Cannot probe PCI\n");
 
+#ifdef RTE_LIBRTE_HV_PMD
+	if (rte_eal_vmbus_probe() < 0)
+		rte_panic("Cannot probe VMBUS\n");
+#endif
+
 	return fctret;
 }
 
diff --git a/lib/librte_ether/rte_ethdev.c b/lib/librte_ether/rte_ethdev.c
index 9577d17..9093966 100644
--- a/lib/librte_ether/rte_ethdev.c
+++ b/lib/librte_ether/rte_ethdev.c
@@ -379,6 +379,98 @@ rte_eth_dev_uninit(struct rte_pci_device *pci_dev)
 	return 0;
 }
 
+#ifdef RTE_LIBRTE_HV_PMD
+static int
+rte_vmbus_dev_init(struct rte_vmbus_driver *vmbus_drv,
+		   struct rte_vmbus_device *vmbus_dev)
+{
+	struct eth_driver  *eth_drv = (struct eth_driver *)vmbus_drv;
+	struct rte_eth_dev *eth_dev;
+	char ethdev_name[RTE_ETH_NAME_MAX_LEN];
+	int diag;
+
+	snprintf(ethdev_name, RTE_ETH_NAME_MAX_LEN, "%u_%u",
+		 vmbus_dev->id.device_id, vmbus_dev->id.sysfs_num);
+
+	eth_dev = rte_eth_dev_allocate(ethdev_name, RTE_ETH_DEV_PCI);
+	if (eth_dev == NULL)
+		return -ENOMEM;
+
+	if (rte_eal_process_type() == RTE_PROC_PRIMARY) {
+		eth_dev->data->dev_private = rte_zmalloc("ethdev private structure",
+				  eth_drv->dev_private_size,
+				  RTE_CACHE_LINE_SIZE);
+		if (eth_dev->data->dev_private == NULL)
+			rte_panic("Cannot allocate memzone for private port data\n");
+	}
+	eth_dev->vmbus_dev = vmbus_dev;
+	eth_dev->driver = eth_drv;
+	eth_dev->data->rx_mbuf_alloc_failed = 0;
+
+	/* init user callbacks */
+	TAILQ_INIT(&(eth_dev->link_intr_cbs));
+
+	/*
+	 * Set the default maximum frame size.
+	 */
+	eth_dev->data->mtu = ETHER_MTU;
+
+	/* Invoke PMD device initialization function */
+	diag = (*eth_drv->eth_dev_init)(eth_dev);
+	if (diag == 0)
+		return 0;
+
+	PMD_DEBUG_TRACE("driver %s: eth_dev_init(device_id=0x%x)"
+			" failed\n", vmbus_drv->name,
+			(unsigned) vmbus_dev->id.device_id);
+	if (rte_eal_process_type() == RTE_PROC_PRIMARY)
+		rte_free(eth_dev->data->dev_private);
+	nb_ports--;
+	return diag;
+}
+
+
+static int
+rte_vmbus_dev_uninit(struct rte_vmbus_device *vmbus_dev)
+{
+	const struct eth_driver *eth_drv;
+	struct rte_eth_dev *eth_dev;
+	char ethdev_name[RTE_ETH_NAME_MAX_LEN];
+	int ret;
+
+	if (vmbus_dev == NULL)
+		return -EINVAL;
+
+	snprintf(ethdev_name, RTE_ETH_NAME_MAX_LEN, "%u_%u",
+		 vmbus_dev->id.device_id, vmbus_dev->id.sysfs_num);
+
+	eth_dev = rte_eth_dev_allocated(ethdev_name);
+	if (eth_dev == NULL)
+		return -ENODEV;
+
+	eth_drv = (const struct eth_driver *)vmbus_dev->driver;
+
+	/* Invoke PMD device uninit function */
+	if (*eth_drv->eth_dev_uninit) {
+		ret = (*eth_drv->eth_dev_uninit)(eth_dev);
+		if (ret)
+			return ret;
+	}
+
+	/* free ether device */
+	rte_eth_dev_release_port(eth_dev);
+
+	if (rte_eal_process_type() == RTE_PROC_PRIMARY)
+		rte_free(eth_dev->data->dev_private);
+
+	eth_dev->pci_dev = NULL;
+	eth_dev->driver = NULL;
+	eth_dev->data = NULL;
+
+	return 0;
+}
+#endif
+
 /**
  * Register an Ethernet [Poll Mode] driver.
  *
@@ -396,9 +488,22 @@ rte_eth_dev_uninit(struct rte_pci_device *pci_dev)
 void
 rte_eth_driver_register(struct eth_driver *eth_drv)
 {
-	eth_drv->pci_drv.devinit = rte_eth_dev_init;
-	eth_drv->pci_drv.devuninit = rte_eth_dev_uninit;
-	rte_eal_pci_register(&eth_drv->pci_drv);
+	switch (eth_drv->bus_type) {
+	case RTE_BUS_PCI:
+		eth_drv->pci_drv.devinit = rte_eth_dev_init;
+		eth_drv->pci_drv.devuninit = rte_eth_dev_uninit;
+		rte_eal_pci_register(&eth_drv->pci_drv);
+		break;
+#ifdef RTE_LIBRTE_HV_PMD
+	case RTE_BUS_VMBUS:
+		eth_drv->vmbus_drv.devinit = rte_vmbus_dev_init;
+		eth_drv->vmbus_drv.devuninit = rte_vmbus_dev_uninit;
+		rte_eal_vmbus_register(&eth_drv->vmbus_drv);
+		break;
+#endif
+	default:
+		rte_panic("unknown bus type %u\n", eth_drv->bus_type);
+	}
 }
 
 static int
@@ -1351,6 +1456,9 @@ rte_eth_has_link_state(uint8_t port_id)
 	}
 	dev = &rte_eth_devices[port_id];
 
+	if (dev->driver->bus_type != RTE_BUS_PCI)
+		return 0;
+
 	return (dev->pci_dev->driver->drv_flags & RTE_PCI_DRV_INTR_LSC) != 0;
 }
 
@@ -1901,9 +2009,17 @@ rte_eth_dev_info_get(uint8_t port_id, struct rte_eth_dev_info *dev_info)
 
 	FUNC_PTR_OR_RET(*dev->dev_ops->dev_infos_get);
 	(*dev->dev_ops->dev_infos_get)(dev, dev_info);
-	dev_info->pci_dev = dev->pci_dev;
-	if (dev->driver)
-		dev_info->driver_name = dev->driver->pci_drv.name;
+
+	if (dev->driver) {
+		switch (dev->driver->bus_type) {
+		case RTE_BUS_PCI:
+			dev_info->driver_name = dev->driver->pci_drv.name;
+			dev_info->pci_dev = dev->pci_dev;
+			break;
+		case RTE_BUS_VMBUS:
+			dev_info->driver_name = dev->driver->vmbus_drv.name;
+		}
+	}
 }
 
 void
diff --git a/lib/librte_ether/rte_ethdev.h b/lib/librte_ether/rte_ethdev.h
index 991023b..9e08f3e 100644
--- a/lib/librte_ether/rte_ethdev.h
+++ b/lib/librte_ether/rte_ethdev.h
@@ -178,6 +178,7 @@ extern "C" {
 #include <rte_log.h>
 #include <rte_interrupts.h>
 #include <rte_pci.h>
+#include <rte_vmbus.h>
 #include <rte_dev.h>
 #include <rte_devargs.h>
 #include <rte_mbuf.h>
@@ -1477,7 +1478,10 @@ struct rte_eth_dev {
 	struct rte_eth_dev_data *data;  /**< Pointer to device data */
 	const struct eth_driver *driver;/**< Driver for this device */
 	const struct eth_dev_ops *dev_ops; /**< Functions exported by PMD */
-	struct rte_pci_device *pci_dev; /**< PCI info. supplied by probing */
+	union {
+		struct rte_pci_device *pci_dev; /**< PCI info. supplied by probig */
+		struct rte_vmbus_device *vmbus_dev; /**< VMBUS info. supplied by probing */
+	};
 	/** User application callbacks for NIC interrupts */
 	struct rte_eth_dev_cb_list link_intr_cbs;
 	/**
@@ -1696,7 +1700,14 @@ typedef int (*eth_dev_uninit_t)(struct rte_eth_dev *eth_dev);
  * - The size of the private data to allocate for each matching device.
  */
 struct eth_driver {
-	struct rte_pci_driver pci_drv;    /**< The PMD is also a PCI driver. */
+	union {
+		struct rte_pci_driver pci_drv;    /**< The PMD is also a PCI driver. */
+		struct rte_vmbus_driver vmbus_drv;/**< The PMD is also a VMBUS drv. */
+	};
+	enum {
+		RTE_BUS_PCI=0,
+		RTE_BUS_VMBUS
+	} bus_type;			  /**< Device bus type. */
 	eth_dev_init_t eth_dev_init;      /**< Device init function. */
 	eth_dev_uninit_t eth_dev_uninit;  /**< Device uninit function. */
 	unsigned int dev_private_size;    /**< Size of device private data. */
-- 
2.1.4