[dpdk-dev] [PATCH V3 1/4] bus/pci: handle device hot unplug

[Jeff Guo]

When a hardware device is removed physically or the software disables
it, the hot unplug occur. App need to call ether dev API to detach the
device, to unplug the device at the bus level and make access to the device
invalid. But the problem is that, the removal of the device from the
software lists is not going to be instantaneous, at this time if the data
path still read/write the device, it will cause MMIO error and result of
the app crash out. So a hot unplug handle mechanism need to guaranty app
will not crash out when hot unplug device.

To handle device hot unplug is bus-specific behavior, this patch introduces
a bus ops so that each kind of bus can implement its own logic. Further,
this patch implements the ops for PCI bus: remap a dummy memory to avoid
bus read/write error.

Signed-off-by: Jeff Guo <jia.guo at intel.com>
---
v3->v2:
change bus ops name to bus_hotplug_handler.
---
 drivers/bus/pci/pci_common.c            | 34 +++++++++++++++++++++++++++++++++
 drivers/bus/pci/pci_common_uio.c        | 33 ++++++++++++++++++++++++++++++++
 drivers/bus/pci/private.h               | 12 ++++++++++++
 lib/librte_eal/common/include/rte_bus.h | 14 ++++++++++++++
 4 files changed, 93 insertions(+)

diff --git a/drivers/bus/pci/pci_common.c b/drivers/bus/pci/pci_common.c
index 7215aae..e607d08 100644
--- a/drivers/bus/pci/pci_common.c
+++ b/drivers/bus/pci/pci_common.c
@@ -473,6 +473,39 @@ pci_find_device(const struct rte_device *start, rte_dev_cmp_t cmp,
 }
 
 static int
+pci_hotplug_handler(struct rte_device *dev)
+{
+	struct rte_pci_device *pdev = NULL;
+	int ret = 0;
+
+	pdev = RTE_DEV_TO_PCI(dev);
+	if (!pdev)
+		return -1;
+
+	/* remap resources for devices */
+	switch (pdev->kdrv) {
+	case RTE_KDRV_VFIO:
+#ifdef VFIO_PRESENT
+		/* TODO */
+		ret = -1;
+#endif
+		break;
+	case RTE_KDRV_IGB_UIO:
+	case RTE_KDRV_UIO_GENERIC:
+	case RTE_KDRV_NIC_UIO:
+		ret = pci_uio_remap_resource(pdev);
+		break;
+	default:
+		RTE_LOG(DEBUG, EAL,
+			"Not managed by a supported kernel driver, skipped\n");
+		ret = -1;
+		break;
+	}
+
+	return ret;
+}
+
+static int
 pci_plug(struct rte_device *dev)
 {
 	return pci_probe_all_drivers(RTE_DEV_TO_PCI(dev));
@@ -502,6 +535,7 @@ struct rte_pci_bus rte_pci_bus = {
 		.unplug = pci_unplug,
 		.parse = pci_parse,
 		.get_iommu_class = rte_pci_get_iommu_class,
+		.hotplug_handler = pci_hotplug_handler,
 	},
 	.device_list = TAILQ_HEAD_INITIALIZER(rte_pci_bus.device_list),
 	.driver_list = TAILQ_HEAD_INITIALIZER(rte_pci_bus.driver_list),
diff --git a/drivers/bus/pci/pci_common_uio.c b/drivers/bus/pci/pci_common_uio.c
index 54bc20b..7ea73db 100644
--- a/drivers/bus/pci/pci_common_uio.c
+++ b/drivers/bus/pci/pci_common_uio.c
@@ -146,6 +146,39 @@ pci_uio_unmap(struct mapped_pci_resource *uio_res)
 	}
 }
 
+/* remap the PCI resource of a PCI device in anonymous virtual memory */
+int
+pci_uio_remap_resource(struct rte_pci_device *dev)
+{
+	int i;
+	void *map_address;
+
+	if (dev == NULL)
+		return -1;
+
+	/* Remap all BARs */
+	for (i = 0; i != PCI_MAX_RESOURCE; i++) {
+		/* skip empty BAR */
+		if (dev->mem_resource[i].phys_addr == 0)
+			continue;
+		map_address = mmap(dev->mem_resource[i].addr,
+				(size_t)dev->mem_resource[i].len,
+				PROT_READ | PROT_WRITE,
+				MAP_PRIVATE | MAP_ANONYMOUS | MAP_FIXED, -1, 0);
+		if (map_address == MAP_FAILED) {
+			RTE_LOG(ERR, EAL,
+				"Cannot remap resource for device %s\n",
+				dev->name);
+			return -1;
+		}
+		RTE_LOG(INFO, EAL,
+			"Successful remap resource for device %s\n",
+			dev->name);
+	}
+
+	return 0;
+}
+
 static struct mapped_pci_resource *
 pci_uio_find_resource(struct rte_pci_device *dev)
 {
diff --git a/drivers/bus/pci/private.h b/drivers/bus/pci/private.h
index 88fa587..5551506 100644
--- a/drivers/bus/pci/private.h
+++ b/drivers/bus/pci/private.h
@@ -173,6 +173,18 @@ void pci_uio_free_resource(struct rte_pci_device *dev,
 		struct mapped_pci_resource *uio_res);
 
 /**
+ * Remap the PCI resource of a PCI device in anonymous virtual memory.
+ *
+ * @param dev
+ *   Point to the struct rte pci device.
+ * @return
+ *   - On success, zero.
+ *   - On failure, a negative value.
+ */
+int
+pci_uio_remap_resource(struct rte_pci_device *dev);
+
+/**
  * Map device memory to uio resource
  *
  * This function is private to EAL.
diff --git a/lib/librte_eal/common/include/rte_bus.h b/lib/librte_eal/common/include/rte_bus.h
index eb9eded..6507f24 100644
--- a/lib/librte_eal/common/include/rte_bus.h
+++ b/lib/librte_eal/common/include/rte_bus.h
@@ -168,6 +168,19 @@ typedef int (*rte_bus_unplug_t)(struct rte_device *dev);
 typedef int (*rte_bus_parse_t)(const char *name, void *addr);
 
 /**
+ * Implementation a specific hot plug handler, which is responsible
+ * for handle the failure when hot remove the device, guaranty the system
+ * would not crash in the case.
+ * @param dev
+ *	Pointer of the device structure.
+ *
+ * @return
+ *	0 on success.
+ *	!0 on error.
+ */
+typedef int (*rte_bus_hotplug_handler_t)(struct rte_device *dev);
+
+/**
  * Bus scan policies
  */
 enum rte_bus_scan_mode {
@@ -211,6 +224,7 @@ struct rte_bus {
 	rte_bus_parse_t parse;       /**< Parse a device name */
 	struct rte_bus_conf conf;    /**< Bus configuration */
 	rte_bus_get_iommu_class_t get_iommu_class; /**< Get iommu class */
+	rte_bus_hotplug_handler_t hotplug_handler; /**< handle hot plug on bus */
 };
 
 /**
-- 
2.7.4