[Patch v9 05/18] net/mana: support device removal interrupts

[longli@linuxonhyperv.com]

From: Long Li <longli@microsoft.com>

MANA supports PCI hot plug events. Add this interrupt to DPDK core so its
parent PMD can detect device removal during Azure servicing or live
migration.

Signed-off-by: Long Li <longli@microsoft.com>
---
v8:
fix coding style of function definitions.
v9:
remove unused data fields.

 doc/guides/nics/features/mana.ini |   1 +
 drivers/net/mana/mana.c           | 103 ++++++++++++++++++++++++++++++
 drivers/net/mana/mana.h           |   1 +
 3 files changed, 105 insertions(+)

diff --git a/doc/guides/nics/features/mana.ini b/doc/guides/nics/features/mana.ini
index 62554b0a0a..8043e11f99 100644
--- a/doc/guides/nics/features/mana.ini
+++ b/doc/guides/nics/features/mana.ini
@@ -7,5 +7,6 @@
 Link status          = P
 Linux                = Y
 Multiprocess aware   = Y
+Removal event        = Y
 Usage doc            = Y
 x86-64               = Y
diff --git a/drivers/net/mana/mana.c b/drivers/net/mana/mana.c
index 90e713318a..2ee8c2dbe9 100644
--- a/drivers/net/mana/mana.c
+++ b/drivers/net/mana/mana.c
@@ -103,12 +103,18 @@ mana_dev_configure(struct rte_eth_dev *dev)
 	return 0;
 }
 
+static int mana_intr_uninstall(struct mana_priv *priv);
+
 static int
 mana_dev_close(struct rte_eth_dev *dev)
 {
 	struct mana_priv *priv = dev->data->dev_private;
 	int ret;
 
+	ret = mana_intr_uninstall(priv);
+	if (ret)
+		return ret;
+
 	ret = ibv_close_device(priv->ib_ctx);
 	if (ret) {
 		ret = errno;
@@ -340,6 +346,96 @@ mana_ibv_device_to_pci_addr(const struct ibv_device *device,
 	return 0;
 }
 
+/*
+ * Interrupt handler from IB layer to notify this device is being removed.
+ */
+static void
+mana_intr_handler(void *arg)
+{
+	struct mana_priv *priv = arg;
+	struct ibv_context *ctx = priv->ib_ctx;
+	struct ibv_async_event event;
+
+	/* Read and ack all messages from IB device */
+	while (true) {
+		if (ibv_get_async_event(ctx, &event))
+			break;
+
+		if (event.event_type == IBV_EVENT_DEVICE_FATAL) {
+			struct rte_eth_dev *dev;
+
+			dev = &rte_eth_devices[priv->port_id];
+			if (dev->data->dev_conf.intr_conf.rmv)
+				rte_eth_dev_callback_process(dev,
+					RTE_ETH_EVENT_INTR_RMV, NULL);
+		}
+
+		ibv_ack_async_event(&event);
+	}
+}
+
+static int
+mana_intr_uninstall(struct mana_priv *priv)
+{
+	int ret;
+
+	ret = rte_intr_callback_unregister(priv->intr_handle,
+					   mana_intr_handler, priv);
+	if (ret <= 0) {
+		DRV_LOG(ERR, "Failed to unregister intr callback ret %d", ret);
+		return ret;
+	}
+
+	rte_intr_instance_free(priv->intr_handle);
+
+	return 0;
+}
+
+static int
+mana_intr_install(struct mana_priv *priv)
+{
+	int ret, flags;
+	struct ibv_context *ctx = priv->ib_ctx;
+
+	priv->intr_handle = rte_intr_instance_alloc(RTE_INTR_INSTANCE_F_SHARED);
+	if (!priv->intr_handle) {
+		DRV_LOG(ERR, "Failed to allocate intr_handle");
+		rte_errno = ENOMEM;
+		return -ENOMEM;
+	}
+
+	rte_intr_fd_set(priv->intr_handle, -1);
+
+	flags = fcntl(ctx->async_fd, F_GETFL);
+	ret = fcntl(ctx->async_fd, F_SETFL, flags | O_NONBLOCK);
+	if (ret) {
+		DRV_LOG(ERR, "Failed to change async_fd to NONBLOCK");
+		goto free_intr;
+	}
+
+	rte_intr_fd_set(priv->intr_handle, ctx->async_fd);
+	rte_intr_type_set(priv->intr_handle, RTE_INTR_HANDLE_EXT);
+
+	ret = rte_intr_callback_register(priv->intr_handle,
+					 mana_intr_handler, priv);
+	if (ret) {
+		DRV_LOG(ERR, "Failed to register intr callback");
+		rte_intr_fd_set(priv->intr_handle, -1);
+		goto restore_fd;
+	}
+
+	return 0;
+
+restore_fd:
+	fcntl(ctx->async_fd, F_SETFL, flags);
+
+free_intr:
+	rte_intr_instance_free(priv->intr_handle);
+	priv->intr_handle = NULL;
+
+	return ret;
+}
+
 static int
 mana_proc_priv_init(struct rte_eth_dev *dev)
 {
@@ -667,6 +763,13 @@ mana_pci_probe_mac(struct rte_pci_device *pci_dev,
 				name, priv->max_rx_queues, priv->max_rx_desc,
 				priv->max_send_sge);
 
+			/* Create async interrupt handler */
+			ret = mana_intr_install(priv);
+			if (ret) {
+				DRV_LOG(ERR, "Failed to install intr handler");
+				goto failed;
+			}
+
 			rte_spinlock_lock(&mana_shared_data->lock);
 			mana_shared_data->primary_cnt++;
 			rte_spinlock_unlock(&mana_shared_data->lock);
diff --git a/drivers/net/mana/mana.h b/drivers/net/mana/mana.h
index 0b4a828b0a..d9eb19559d 100644
--- a/drivers/net/mana/mana.h
+++ b/drivers/net/mana/mana.h
@@ -40,6 +40,7 @@ struct mana_priv {
 	struct ibv_pd *ib_pd;
 	struct ibv_pd *ib_parent_pd;
 	void *db_page;
+	struct rte_intr_handle *intr_handle;
 	int max_rx_queues;
 	int max_tx_queues;
 	int max_rx_desc;
-- 
2.17.1