net/mana: add device reset support

1,220 lines not on this page · raw message

index 79cc47b6ab..115bc722f4 100644
@@ -5,6 +5,8 @@
 #ifndef __MANA_H__
 #define __MANA_H__
 
+#include <pthread.h>
+
 #define	PCI_VENDOR_ID_MICROSOFT		0x1414
 #define PCI_DEVICE_ID_MICROSOFT_MANA_PF	0x00b9
 #define PCI_DEVICE_ID_MICROSOFT_MANA	0x00ba

@@ -337,6 +339,20 @@ struct mana_process_priv {
 	void *db_page;
 };
 
+enum mana_device_state {
+	/* Normal running */
+	MANA_DEV_ACTIVE		= 0,
+	/* In reset enter processing */
+	MANA_DEV_RESET_ENTER	= 1,
+	/*
+	 * Reset enter processing completed.
+	 * Waiting for reset exit or in reset exit processing.
+	 */
+	MANA_DEV_RESET_EXIT	= 2,
+	/* Reset failed */
+	MANA_DEV_RESET_FAILED	= 3,
+};
+
 struct mana_priv {
 	struct rte_eth_dev_data *dev_data;
 	struct mana_process_priv *process_priv;

@@ -368,6 +384,16 @@ struct mana_priv {
 	uint64_t max_mr_size;
 	struct mana_mr_btree mr_btree;
 	rte_spinlock_t	mr_btree_lock;
+	RTE_ATOMIC(enum mana_device_state) dev_state;
+	struct rte_rcu_qsbr *dev_state_qsv;
+	/* mutex for synchronizing mana reset and some mana_dev_ops callbacks */
+	pthread_mutex_t reset_ops_lock;
+	/* Reset thread ID, valid when reset_thread_active is true */
+	rte_thread_t reset_thread;
+	RTE_ATOMIC(bool) reset_thread_active;
+	/* Condvar to wake reset thread early on PCI remove */
+	pthread_mutex_t reset_cond_mutex;
+	pthread_cond_t reset_cond;
 };
 
 struct mana_txq_desc {

@@ -427,6 +453,7 @@ struct mana_txq {
 	struct mana_mr_btree mr_btree;
 	struct mana_stats stats;
 	unsigned int socket;
+	unsigned int txq_idx;
 };
 
 struct mana_rxq {

@@ -462,6 +489,7 @@ struct mana_rxq {
 	struct mana_mr_btree mr_btree;
 
 	unsigned int socket;
+	unsigned int rxq_idx;
 };
 
 extern int mana_logtype_driver;

@@ -543,6 +571,8 @@ enum mana_mp_req_type {
 	MANA_MP_REQ_CREATE_MR,
 	MANA_MP_REQ_START_RXTX,
 	MANA_MP_REQ_STOP_RXTX,
+	MANA_MP_REQ_RESET_ENTER,
+	MANA_MP_REQ_RESET_EXIT,
 };
 
 /* Pameters for IPC. */

@@ -563,8 +593,9 @@ void mana_mp_uninit_primary(void);
 void mana_mp_uninit_secondary(void);
 int mana_mp_req_verbs_cmd_fd(struct rte_eth_dev *dev);
 int mana_mp_req_mr_create(struct mana_priv *priv, uintptr_t addr, uint32_t len);
+int mana_map_doorbell_secondary(struct rte_eth_dev *eth_dev, int fd);
 
-void mana_mp_req_on_rxtx(struct rte_eth_dev *dev, enum mana_mp_req_type type);
+int mana_mp_req_on_rxtx(struct rte_eth_dev *dev, enum mana_mp_req_type type);
 
 void *mana_alloc_verbs_buf(size_t size, void *data);
 void mana_free_verbs_buf(void *ptr, void *data __rte_unused);

153 lines not on this page · raw message

index c4045141bc..8914f4cf04 100644
@@ -314,8 +314,10 @@ mana_mr_btree_init(struct mana_mr_btree *bt, int n, int socket)
 void
 mana_mr_btree_free(struct mana_mr_btree *bt)
 {
-	rte_free(bt->table);
-	memset(bt, 0, sizeof(*bt));
+	if (bt && bt->table) {
+		rte_free(bt->table);
+		memset(bt, 0, sizeof(*bt));
+	}
 }
 
 int

index 1b8ba1f3a9..ae05d8dd2f 100644
@@ -2,6 +2,7 @@
  * Copyright 2022 Microsoft Corporation
  */
 #include <ethdev_driver.h>
+#include <rte_rcu_qsbr.h>
 
 #include <infiniband/verbs.h>
 #include <infiniband/manadv.h>

@@ -36,6 +37,11 @@ mana_rq_ring_doorbell(struct mana_rxq *rxq)
 		db_page = process_priv->db_page;
 	}
 
+	if (!db_page) {
+		DP_LOG(ERR, "db_page is NULL, cannot ring RX doorbell");
+		return -EINVAL;
+	}
+
 	/* Hardware Spec specifies that software client should set 0 for
 	 * wqe_cnt for Receive Queues.
 	 */

@@ -172,7 +178,7 @@ mana_stop_rx_queues(struct rte_eth_dev *dev)
 
 	for (i = 0; i < priv->num_queues; i++)
 		if (dev->data->rx_queue_state[i] == RTE_ETH_QUEUE_STATE_STOPPED)
-			return -EINVAL;
+			return 0;
 
 	if (priv->rwq_qp) {
 		ret = ibv_destroy_qp(priv->rwq_qp);

@@ -256,6 +262,9 @@ mana_start_rx_queues(struct rte_eth_dev *dev)
 		struct mana_rxq *rxq = dev->data->rx_queues[i];
 		struct ibv_wq_init_attr wq_attr = {};
 
+		rxq->rxq_idx = i;
+		DRV_LOG(DEBUG, "assigning rxq_idx to %d", i);
+
 		manadv_set_context_attr(priv->ib_ctx,
 			MANADV_CTX_ATTR_BUF_ALLOCATORS,
 			(void *)((uintptr_t)&(struct manadv_ctx_allocators){

@@ -451,6 +460,17 @@ mana_rx_burst(void *dpdk_rxq, struct rte_mbuf **pkts, uint16_t pkts_n)
 	uint32_t pkt_len;
 	uint32_t i;
 	int polled = 0;
+	struct rte_rcu_qsbr *dstate_qsv = priv->dev_state_qsv;
+	unsigned int tid = rxq->rxq_idx;
+
+	rte_rcu_qsbr_thread_online(dstate_qsv, tid);
+
+	if (unlikely(rte_atomic_load_explicit(&priv->dev_state,
+			    rte_memory_order_acquire) != MANA_DEV_ACTIVE)) {
+		/* Device reset occurred. */
+		rte_rcu_qsbr_thread_offline(dstate_qsv, tid);
+		return 0;
+	}
 
 repoll:
 	/* Polling on new completions if we have no backlog */

@@ -592,6 +612,8 @@ mana_rx_burst(void *dpdk_rxq, struct rte_mbuf **pkts, uint16_t pkts_n)
 				wqe_consumed, ret);
 	}
 
+	rte_rcu_qsbr_thread_offline(dstate_qsv, tid);
+
 	return pkt_received;
 }
 

index 57dbbc3651..3b07a8b9a6 100644
@@ -3,6 +3,7 @@
  */
 
 #include <ethdev_driver.h>
+#include <rte_rcu_qsbr.h>
 
 #include <infiniband/verbs.h>
 #include <infiniband/manadv.h>

@@ -17,7 +18,7 @@ mana_stop_tx_queues(struct rte_eth_dev *dev)
 
 	for (i = 0; i < priv->num_queues; i++)
 		if (dev->data->tx_queue_state[i] == RTE_ETH_QUEUE_STATE_STOPPED)
-			return -EINVAL;
+			return 0;
 
 	for (i = 0; i < priv->num_queues; i++) {
 		struct mana_txq *txq = dev->data->tx_queues[i];

@@ -83,6 +84,9 @@ mana_start_tx_queues(struct rte_eth_dev *dev)
 
 		txq = dev->data->tx_queues[i];
 
+		txq->txq_idx = i;
+		DRV_LOG(DEBUG, "assigning txq_idx to %d", txq->txq_idx);
+
 		manadv_set_context_attr(priv->ib_ctx,
 			MANADV_CTX_ATTR_BUF_ALLOCATORS,
 			(void *)((uintptr_t)&(struct manadv_ctx_allocators){

@@ -190,10 +194,30 @@ mana_tx_burst(void *dpdk_txq, struct rte_mbuf **tx_pkts, uint16_t nb_pkts)
 	void *db_page;
 	uint16_t pkt_sent = 0;
 	uint32_t num_comp, i;
+	unsigned int tid = priv->num_queues + txq->txq_idx;
+	struct rte_rcu_qsbr *dstate_qsv = priv->dev_state_qsv;
 #ifdef RTE_ARCH_32
 	uint32_t wqe_count = 0;
 #endif
 
+	db_page = priv->db_page;
+	if (rte_eal_process_type() == RTE_PROC_SECONDARY) {
+		struct rte_eth_dev *dev =
+			&rte_eth_devices[priv->dev_data->port_id];
+		struct mana_process_priv *process_priv = dev->process_private;
+
+		db_page = process_priv->db_page;
+	}
+
+	rte_rcu_qsbr_thread_online(dstate_qsv, tid);
+
+	if (unlikely(rte_atomic_load_explicit(&priv->dev_state,
+			    rte_memory_order_acquire) != MANA_DEV_ACTIVE || !db_page)) {
+		/* Device reset event occurred. */
+		rte_rcu_qsbr_thread_offline(dstate_qsv, tid);
+		return 0;
+	}
+
 	/* Process send completions from GDMA */
 	num_comp = gdma_poll_completion_queue(&txq->gdma_cq,
 			txq->gdma_comp_buf, txq->num_desc);

@@ -216,7 +240,8 @@ mana_tx_burst(void *dpdk_txq, struct rte_mbuf **tx_pkts, uint16_t nb_pkts)
 		}
 
 		if (!desc->pkt) {
-			DP_LOG(ERR, "mana_txq_desc has a NULL pkt");
+			DP_LOG(ERR, "mana_txq_desc has a NULL pkt, priv %p, "
+			       "txq = %d", priv, txq->txq_idx);
 		} else {
 			txq->stats.bytes += desc->pkt->pkt_len;
 			rte_pktmbuf_free(desc->pkt);

@@ -474,15 +499,6 @@ mana_tx_burst(void *dpdk_txq, struct rte_mbuf **tx_pkts, uint16_t nb_pkts)
 	}
 
 	/* Ring hardware door bell */
-	db_page = priv->db_page;
-	if (rte_eal_process_type() == RTE_PROC_SECONDARY) {
-		struct rte_eth_dev *dev =
-			&rte_eth_devices[priv->dev_data->port_id];
-		struct mana_process_priv *process_priv = dev->process_private;
-
-		db_page = process_priv->db_page;
-	}
-
 	if (pkt_sent) {
 #ifdef RTE_ARCH_32
 		ret = mana_ring_short_doorbell(db_page, GDMA_QUEUE_SEND,

@@ -501,5 +517,7 @@ mana_tx_burst(void *dpdk_txq, struct rte_mbuf **tx_pkts, uint16_t nb_pkts)
 			DP_LOG(ERR, "mana_ring_doorbell failed ret %d", ret);
 	}
 
+	rte_rcu_qsbr_thread_offline(dstate_qsv, tid);
+
 	return pkt_sent;
 }