vdpa/sfc: introduce Xilinx vDPA driver

index dbd099f..bedc76c 100644
@@ -21,7 +21,7 @@
 #define SFC_VDPA_DEFAULT_MCDI_IOVA		0x200000000000
 
 /* Broadcast & Unicast MAC filters are supported */
-#define SFC_MAX_SUPPORTED_FILTERS		2
+#define SFC_MAX_SUPPORTED_FILTERS		3
 
 /*
  * Get function-local index of the associated VI from the

@@ -32,6 +32,7 @@
 enum sfc_vdpa_filter_type {
 	SFC_VDPA_BCAST_MAC_FILTER = 0,
 	SFC_VDPA_UCAST_MAC_FILTER = 1,
+	SFC_VDPA_MCAST_DST_FILTER = 2,
 	SFC_VDPA_FILTER_NTYPE
 };
 

index 03b6a5d..74204d3 100644
@@ -39,8 +39,12 @@
 	spec->efs_flags = EFX_FILTER_FLAG_RX;
 	spec->efs_dmaq_id = qid;
 
-	rc = efx_filter_spec_set_eth_local(spec, EFX_FILTER_SPEC_VID_UNSPEC,
-					   eth_addr);
+	if (eth_addr == NULL)
+		rc = efx_filter_spec_set_mc_def(spec);
+	else
+		rc = efx_filter_spec_set_eth_local(spec,
+						   EFX_FILTER_SPEC_VID_UNSPEC,
+						   eth_addr);
 	if (rc != 0)
 		return rc;
 

@@ -114,6 +118,17 @@ int sfc_vdpa_filter_config(struct sfc_vdpa_ops_data *ops_data)
 	else
 		sva->filters.filter_cnt++;
 
+	sfc_vdpa_log_init(sva, "insert unknown mcast filter");
+	spec = &sva->filters.spec[SFC_VDPA_MCAST_DST_FILTER];
+
+	rc = sfc_vdpa_set_mac_filter(nic, spec, qid, NULL);
+	if (rc != 0)
+		sfc_vdpa_err(sva,
+			     "mcast filter insertion failed: %s",
+			     rte_strerror(rc));
+	else
+		sva->filters.filter_cnt++;
+
 	sfc_vdpa_log_init(sva, "done");
 
 	return rc;

282 lines not on this page · raw message

new file mode 100644
index 0000000..2ae9ec3
@@ -0,0 +1,39 @@
+/* SPDX-License-Identifier: BSD-3-Clause
+ *
+ * Copyright(c) 2020-2021 Xilinx, Inc.
+ */
+
+#ifndef _SFC_VDPA_H
+#define _SFC_VDPA_H
+
+#include <stdint.h>
+#include <sys/queue.h>
+
+#include <rte_bus_pci.h>
+
+#include "sfc_vdpa_log.h"
+
+/* Adapter private data */
+struct sfc_vdpa_adapter {
+	TAILQ_ENTRY(sfc_vdpa_adapter)	next;
+	struct rte_pci_device		*pdev;
+
+	char				log_prefix[SFC_VDPA_LOG_PREFIX_MAX];
+	uint32_t			logtype_main;
+
+	int				vfio_group_fd;
+	int				vfio_dev_fd;
+	int				vfio_container_fd;
+	int				iommu_group_num;
+};
+
+uint32_t
+sfc_vdpa_register_logtype(const struct rte_pci_addr *pci_addr,
+			  const char *lt_prefix_str,
+			  uint32_t ll_default);
+
+struct sfc_vdpa_adapter *
+sfc_vdpa_get_adapter_by_dev(struct rte_pci_device *pdev);
+
+#endif  /* _SFC_VDPA_H */
+

56 lines not on this page · raw message

index f087944..da75ba6 100644
@@ -228,6 +228,19 @@ struct sfc_vdpa_adapter *
 		goto fail_vfio_setup;
 	}
 
+	sfc_vdpa_log_init(sva, "hw init");
+	if (sfc_vdpa_hw_init(sva) != 0) {
+		sfc_vdpa_err(sva, "failed to init HW %s", pci_dev->name);
+		goto fail_hw_init;
+	}
+
+	sfc_vdpa_log_init(sva, "dev init");
+	sva->ops_data = sfc_vdpa_device_init(sva, SFC_VDPA_AS_VF);
+	if (sva->ops_data == NULL) {
+		sfc_vdpa_err(sva, "failed vDPA dev init %s", pci_dev->name);
+		goto fail_dev_init;
+	}
+
 	pthread_mutex_lock(&sfc_vdpa_adapter_list_lock);
 	TAILQ_INSERT_TAIL(&sfc_vdpa_adapter_list, sva, next);
 	pthread_mutex_unlock(&sfc_vdpa_adapter_list_lock);

@@ -236,6 +249,12 @@ struct sfc_vdpa_adapter *
 
 	return 0;
 
+fail_dev_init:
+	sfc_vdpa_hw_fini(sva);
+
+fail_hw_init:
+	sfc_vdpa_vfio_teardown(sva);
+
 fail_vfio_setup:
 fail_set_log_prefix:
 	rte_free(sva);

@@ -262,6 +281,10 @@ struct sfc_vdpa_adapter *
 	TAILQ_REMOVE(&sfc_vdpa_adapter_list, sva, next);
 	pthread_mutex_unlock(&sfc_vdpa_adapter_list_lock);
 
+	sfc_vdpa_device_fini(sva->ops_data);
+
+	sfc_vdpa_hw_fini(sva);
+
 	sfc_vdpa_vfio_teardown(sva);
 
 	rte_free(sva);

72 lines not on this page · raw message

new file mode 100644
index 0000000..cfa8cc5
@@ -0,0 +1,21 @@
+/* SPDX-License-Identifier: BSD-3-Clause
+ *
+ * Copyright(c) 2020-2021 Xilinx, Inc.
+ */
+
+#ifndef _SFC_VDPA_DEBUG_H_
+#define _SFC_VDPA_DEBUG_H_
+
+#include <rte_debug.h>
+
+#ifdef RTE_LIBRTE_SFC_VDPA_DEBUG
+/* Avoid dependency from RTE_LOG_DP_LEVEL to be able to enable debug check
+ * in the driver only.
+ */
+#define SFC_VDPA_ASSERT(exp)			RTE_VERIFY(exp)
+#else
+/* If the driver debug is not enabled, follow DPDK debug/non-debug */
+#define SFC_VDPA_ASSERT(exp)			RTE_ASSERT(exp)
+#endif
+
+#endif /* _SFC_VDPA_DEBUG_H_ */

326 lines not on this page · raw message

index 858e5ee..4e7a84f 100644
@@ -21,6 +21,9 @@
 /** Name prefix for the per-device log type used to report basic information */
 #define SFC_VDPA_LOGTYPE_MAIN_STR	SFC_VDPA_LOGTYPE_PREFIX "main"
 
+/** Device MCDI log type name prefix */
+#define SFC_VDPA_LOGTYPE_MCDI_STR	SFC_VDPA_LOGTYPE_PREFIX "mcdi"
+
 #define SFC_VDPA_LOG_PREFIX_MAX	32
 
 /* Log PMD message, automatically add prefix and \n */

74 lines not on this page · raw message

129 lines not on this page · raw message

new file mode 100644
index 0000000..baa4293
@@ -0,0 +1,34 @@
+/* SPDX-License-Identifier: BSD-3-Clause
+ *
+ * Copyright(c) 2020-2021 Xilinx, Inc.
+ */
+
+#ifndef _SFC_VDPA_OPS_H
+#define _SFC_VDPA_OPS_H
+
+#include <rte_vdpa.h>
+
+#define SFC_VDPA_MAX_QUEUE_PAIRS		1
+
+enum sfc_vdpa_context {
+	SFC_VDPA_AS_VF
+};
+
+enum sfc_vdpa_state {
+	SFC_VDPA_STATE_UNINITIALIZED = 0,
+	SFC_VDPA_STATE_INITIALIZED,
+};
+
+struct sfc_vdpa_ops_data {
+	void				*dev_handle;
+	struct rte_vdpa_device		*vdpa_dev;
+	enum sfc_vdpa_context		vdpa_context;
+	enum sfc_vdpa_state		state;
+};
+
+struct sfc_vdpa_ops_data *
+sfc_vdpa_device_init(void *adapter, enum sfc_vdpa_context context);
+void
+sfc_vdpa_device_fini(struct sfc_vdpa_ops_data *ops_data);
+
+#endif /* _SFC_VDPA_OPS_H */

index d133d61..37ec6b9 100644
@@ -187,7 +187,7 @@
 
 #define EFSYS_OPT_MAE 1
 
-#define EFSYS_OPT_VIRTIO 0
+#define EFSYS_OPT_VIRTIO 1
 
 /* ID */
 

index da75ba6..7b9ebcc 100644
@@ -43,6 +43,26 @@ struct sfc_vdpa_adapter *
 	return found ? sva : NULL;
 }
 
+struct sfc_vdpa_ops_data *
+sfc_vdpa_get_data_by_dev(struct rte_vdpa_device *vdpa_dev)
+{
+	bool found = false;
+	struct sfc_vdpa_adapter *sva;
+
+	pthread_mutex_lock(&sfc_vdpa_adapter_list_lock);
+
+	TAILQ_FOREACH(sva, &sfc_vdpa_adapter_list, next) {
+		if (vdpa_dev == sva->ops_data->vdpa_dev) {
+			found = true;
+			break;
+		}
+	}
+
+	pthread_mutex_unlock(&sfc_vdpa_adapter_list_lock);
+
+	return found ? sva->ops_data : NULL;
+}
+
 static int
 sfc_vdpa_vfio_setup(struct sfc_vdpa_adapter *sva)
 {

index bd3c437..dd3ca80 100644
@@ -59,6 +59,8 @@ struct sfc_vdpa_adapter {
 
 struct sfc_vdpa_adapter *
 sfc_vdpa_get_adapter_by_dev(struct rte_pci_device *pdev);
+struct sfc_vdpa_ops_data *
+sfc_vdpa_get_data_by_dev(struct rte_vdpa_device *vdpa_dev);
 
 int
 sfc_vdpa_hw_init(struct sfc_vdpa_adapter *sva);

index dfb6d4f..dca7034 100644
@@ -277,10 +277,20 @@
 	if (rc != 0)
 		goto fail_estimate_rsrc_limits;
 
+	sfc_vdpa_log_init(sva, "init virtio");
+	rc = efx_virtio_init(enp);
+	if (rc != 0) {
+		sfc_vdpa_err(sva, "virtio init failed: %s", rte_strerror(rc));
+		goto fail_virtio_init;
+	}
+
 	sfc_vdpa_log_init(sva, "done");
 
 	return 0;
 
+fail_virtio_init:
+	efx_nic_fini(enp);
+
 fail_estimate_rsrc_limits:
 fail_nic_reset:
 	efx_nic_unprobe(enp);

@@ -309,6 +319,9 @@
 
 	sfc_vdpa_log_init(sva, "entry");
 
+	sfc_vdpa_log_init(sva, "virtio fini");
+	efx_virtio_fini(enp);
+
 	sfc_vdpa_log_init(sva, "unprobe nic");
 	efx_nic_unprobe(enp);
 

138 lines not on this page · raw message

index baa4293..7b77df0 100644
@@ -24,6 +24,9 @@ struct sfc_vdpa_ops_data {
 	struct rte_vdpa_device		*vdpa_dev;
 	enum sfc_vdpa_context		vdpa_context;
 	enum sfc_vdpa_state		state;
+
+	uint64_t			dev_features;
+	uint64_t			drv_features;
 };
 
 struct sfc_vdpa_ops_data *

index 5750944..9a95211 100644
@@ -31,10 +31,20 @@
 static int
 sfc_vdpa_get_queue_num(struct rte_vdpa_device *vdpa_dev, uint32_t *queue_num)
 {
-	RTE_SET_USED(vdpa_dev);
-	RTE_SET_USED(queue_num);
+	struct sfc_vdpa_ops_data *ops_data;
+	void *dev;
 
-	return -1;
+	ops_data = sfc_vdpa_get_data_by_dev(vdpa_dev);
+	if (ops_data == NULL)
+		return -1;
+
+	dev = ops_data->dev_handle;
+	*queue_num = sfc_vdpa_adapter_by_dev_handle(dev)->max_queue_count;
+
+	sfc_vdpa_info(dev, "vDPA ops get_queue_num :: supported queue num : %u",
+		      *queue_num);
+
+	return 0;
 }
 
 static int

index 9a95211..b5815df 100644
@@ -145,6 +145,29 @@
 	return -1;
 }
 
+static int
+sfc_vdpa_get_vfio_device_fd(int vid)
+{
+	struct rte_vdpa_device *vdpa_dev;
+	struct sfc_vdpa_ops_data *ops_data;
+	int vfio_dev_fd;
+	void *dev;
+
+	vdpa_dev = rte_vhost_get_vdpa_device(vid);
+
+	ops_data = sfc_vdpa_get_data_by_dev(vdpa_dev);
+	if (ops_data == NULL)
+		return -1;
+
+	dev = ops_data->dev_handle;
+	vfio_dev_fd = sfc_vdpa_adapter_by_dev_handle(dev)->vfio_dev_fd;
+
+	sfc_vdpa_info(dev, "vDPA ops get_vfio_device_fd :: vfio fd : %d",
+		      vfio_dev_fd);
+
+	return vfio_dev_fd;
+}
+
 static struct rte_vdpa_dev_ops sfc_vdpa_ops = {
 	.get_queue_num = sfc_vdpa_get_queue_num,
 	.get_features = sfc_vdpa_get_features,

@@ -153,6 +176,7 @@
 	.dev_close = sfc_vdpa_dev_close,
 	.set_vring_state = sfc_vdpa_set_vring_state,
 	.set_features = sfc_vdpa_set_features,
+	.get_vfio_device_fd = sfc_vdpa_get_vfio_device_fd,
 };
 
 struct sfc_vdpa_ops_data *

index 7b9ebcc..f548c1e 100644
@@ -242,6 +242,8 @@ struct sfc_vdpa_ops_data *
 
 	sfc_vdpa_log_init(sva, "entry");
 
+	sfc_vdpa_adapter_lock_init(sva);
+
 	sfc_vdpa_log_init(sva, "vfio init");
 	if (sfc_vdpa_vfio_setup(sva) < 0) {
 		sfc_vdpa_err(sva, "failed to setup device %s", pci_dev->name);

@@ -276,6 +278,8 @@ struct sfc_vdpa_ops_data *
 	sfc_vdpa_vfio_teardown(sva);
 
 fail_vfio_setup:
+	sfc_vdpa_adapter_lock_fini(sva);
+
 fail_set_log_prefix:
 	rte_free(sva);
 

@@ -307,6 +311,8 @@ struct sfc_vdpa_ops_data *
 
 	sfc_vdpa_vfio_teardown(sva);
 
+	sfc_vdpa_adapter_lock_fini(sva);
+
 	rte_free(sva);
 
 	return 0;

53 lines not on this page · raw message

81 lines not on this page · raw message

561 lines not on this page · raw message

index 7b77df0..d20d219 100644
@@ -17,16 +17,44 @@ enum sfc_vdpa_context {
 enum sfc_vdpa_state {
 	SFC_VDPA_STATE_UNINITIALIZED = 0,
 	SFC_VDPA_STATE_INITIALIZED,
+	SFC_VDPA_STATE_CONFIGURING,
+	SFC_VDPA_STATE_CONFIGURED,
+	SFC_VDPA_STATE_CLOSING,
+	SFC_VDPA_STATE_CLOSED,
+	SFC_VDPA_STATE_STARTING,
+	SFC_VDPA_STATE_STARTED,
+	SFC_VDPA_STATE_STOPPING,
 };
 
+struct sfc_vdpa_vring_info {
+	uint64_t	desc;
+	uint64_t	avail;
+	uint64_t	used;
+	uint64_t	size;
+	uint16_t	last_avail_idx;
+	uint16_t	last_used_idx;
+};
+
+typedef struct sfc_vdpa_vq_context_s {
+	uint8_t				enable;
+	uint32_t			pidx;
+	uint32_t			cidx;
+	efx_virtio_vq_t			*vq;
+} sfc_vdpa_vq_context_t;
+
 struct sfc_vdpa_ops_data {
 	void				*dev_handle;
+	int				vid;
 	struct rte_vdpa_device		*vdpa_dev;
 	enum sfc_vdpa_context		vdpa_context;
 	enum sfc_vdpa_state		state;
 
 	uint64_t			dev_features;
 	uint64_t			drv_features;
+	uint64_t			req_features;
+
+	uint16_t			vq_count;
+	struct sfc_vdpa_vq_context_s	vq_cxt[SFC_VDPA_MAX_QUEUE_PAIRS * 2];
 };
 
 struct sfc_vdpa_ops_data *

index f0be652..1725597 100644
@@ -3,6 +3,8 @@
  * Copyright(c) 2020-2021 Xilinx, Inc.
  */
 
+#include <pthread.h>
+#include <unistd.h>
 #include <sys/ioctl.h>
 
 #include <rte_errno.h>

@@ -532,6 +534,55 @@
 	return 0;
 }
 
+static void *
+sfc_vdpa_notify_ctrl(void *arg)
+{
+	struct sfc_vdpa_ops_data *ops_data;
+	int vid;
+
+	ops_data = arg;
+	if (ops_data == NULL)
+		return NULL;
+
+	sfc_vdpa_adapter_lock(ops_data->dev_handle);
+
+	vid = ops_data->vid;
+
+	if (rte_vhost_host_notifier_ctrl(vid, RTE_VHOST_QUEUE_ALL, true) != 0)
+		sfc_vdpa_info(ops_data->dev_handle,
+			      "vDPA (%s): Notifier could not get configured",
+			      ops_data->vdpa_dev->device->name);
+
+	sfc_vdpa_adapter_unlock(ops_data->dev_handle);
+
+	return NULL;
+}
+
+static int
+sfc_vdpa_setup_notify_ctrl(struct sfc_vdpa_ops_data *ops_data)
+{
+	int ret;
+
+	ops_data->is_notify_thread_started = false;
+
+	/*
+	 * Use rte_vhost_host_notifier_ctrl in a thread to avoid
+	 * dead lock scenario when multiple VFs are used in single vdpa
+	 * application and multiple VFs are passed to a single VM.
+	 */
+	ret = pthread_create(&ops_data->notify_tid, NULL,
+			     sfc_vdpa_notify_ctrl, ops_data);
+	if (ret != 0) {
+		sfc_vdpa_err(ops_data->dev_handle,
+			     "failed to create notify_ctrl thread: %s",
+			     rte_strerror(ret));
+		return -1;
+	}
+	ops_data->is_notify_thread_started = true;
+
+	return 0;
+}
+
 static int
 sfc_vdpa_dev_config(int vid)
 {

@@ -565,18 +616,19 @@
 	if (rc != 0)
 		goto fail_vdpa_start;
 
-	sfc_vdpa_adapter_unlock(ops_data->dev_handle);
+	rc = sfc_vdpa_setup_notify_ctrl(ops_data);
+	if (rc != 0)
+		goto fail_vdpa_notify;
 
-	sfc_vdpa_log_init(ops_data->dev_handle, "vhost notifier ctrl");
-	if (rte_vhost_host_notifier_ctrl(vid, RTE_VHOST_QUEUE_ALL, true) != 0)
-		sfc_vdpa_info(ops_data->dev_handle,
-			      "vDPA (%s): software relay for notify is used.",
-			      vdpa_dev->device->name);
+	sfc_vdpa_adapter_unlock(ops_data->dev_handle);
 
 	sfc_vdpa_log_init(ops_data->dev_handle, "done");
 
 	return 0;
 
+fail_vdpa_notify:
+	sfc_vdpa_stop(ops_data);
+
 fail_vdpa_start:
 	sfc_vdpa_close(ops_data);
 

@@ -589,6 +641,7 @@
 static int
 sfc_vdpa_dev_close(int vid)
 {
+	int ret;
 	struct rte_vdpa_device *vdpa_dev;
 	struct sfc_vdpa_ops_data *ops_data;
 

@@ -603,6 +656,23 @@
 	}
 
 	sfc_vdpa_adapter_lock(ops_data->dev_handle);
+	if (ops_data->is_notify_thread_started == true) {
+		void *status;
+		ret = pthread_cancel(ops_data->notify_tid);
+		if (ret != 0) {
+			sfc_vdpa_err(ops_data->dev_handle,
+				     "failed to cancel notify_ctrl thread: %s",
+				     rte_strerror(ret));
+		}
+
+		ret = pthread_join(ops_data->notify_tid, &status);
+		if (ret != 0) {
+			sfc_vdpa_err(ops_data->dev_handle,
+				     "failed to join terminated notify_ctrl thread: %s",
+				     rte_strerror(ret));
+		}
+	}
+	ops_data->is_notify_thread_started = false;
 
 	sfc_vdpa_stop(ops_data);
 	sfc_vdpa_close(ops_data);

@@ -653,6 +723,79 @@
 	return vfio_dev_fd;
 }
 
+static int
+sfc_vdpa_get_notify_area(int vid, int qid, uint64_t *offset, uint64_t *size)
+{
+	int ret;
+	efx_nic_t *nic;
+	int vfio_dev_fd;
+	efx_rc_t rc;
+	unsigned int bar_offset;
+	struct rte_vdpa_device *vdpa_dev;
+	struct sfc_vdpa_ops_data *ops_data;
+	struct vfio_region_info reg = { .argsz = sizeof(reg) };
+	const efx_nic_cfg_t *encp;
+	int max_vring_cnt;
+	int64_t len;
+	void *dev;
+
+	vdpa_dev = rte_vhost_get_vdpa_device(vid);
+
+	ops_data = sfc_vdpa_get_data_by_dev(vdpa_dev);
+	if (ops_data == NULL)
+		return -1;
+
+	dev = ops_data->dev_handle;
+
+	vfio_dev_fd = sfc_vdpa_adapter_by_dev_handle(dev)->vfio_dev_fd;
+	max_vring_cnt =
+		(sfc_vdpa_adapter_by_dev_handle(dev)->max_queue_count * 2);
+
+	nic = sfc_vdpa_adapter_by_dev_handle(ops_data->dev_handle)->nic;
+	encp = efx_nic_cfg_get(nic);
+
+	if (qid >= max_vring_cnt) {
+		sfc_vdpa_err(dev, "invalid qid : %d", qid);
+		return -1;
+	}
+
+	if (ops_data->vq_cxt[qid].enable != B_TRUE) {
+		sfc_vdpa_err(dev, "vq is not enabled");
+		return -1;
+	}
+
+	rc = efx_virtio_get_doorbell_offset(ops_data->vq_cxt[qid].vq,
+					    &bar_offset);
+	if (rc != 0) {
+		sfc_vdpa_err(dev, "failed to get doorbell offset: %s",
+			     rte_strerror(rc));
+		return rc;
+	}
+
+	reg.index = sfc_vdpa_adapter_by_dev_handle(dev)->mem_bar.esb_rid;
+	ret = ioctl(vfio_dev_fd, VFIO_DEVICE_GET_REGION_INFO, &reg);
+	if (ret != 0) {
+		sfc_vdpa_err(dev, "could not get device region info: %s",
+			     strerror(errno));
+		return ret;
+	}
+
+	*offset = reg.offset + bar_offset;
+
+	len = (1U << encp->enc_vi_window_shift) / 2;
+	if (len >= sysconf(_SC_PAGESIZE)) {
+		*size = sysconf(_SC_PAGESIZE);
+	} else {
+		sfc_vdpa_err(dev, "invalid VI window size : 0x%" PRIx64, len);
+		return -1;
+	}
+
+	sfc_vdpa_info(dev, "vDPA ops get_notify_area :: offset : 0x%" PRIx64,
+		      *offset);
+
+	return 0;
+}
+
 static struct rte_vdpa_dev_ops sfc_vdpa_ops = {
 	.get_queue_num = sfc_vdpa_get_queue_num,
 	.get_features = sfc_vdpa_get_features,

@@ -662,6 +805,7 @@
 	.set_vring_state = sfc_vdpa_set_vring_state,
 	.set_features = sfc_vdpa_set_features,
 	.get_vfio_device_fd = sfc_vdpa_get_vfio_device_fd,
+	.get_notify_area = sfc_vdpa_get_notify_area,
 };
 
 struct sfc_vdpa_ops_data *

index d20d219..9b94aca 100644
@@ -48,6 +48,8 @@ struct sfc_vdpa_ops_data {
 	struct rte_vdpa_device		*vdpa_dev;
 	enum sfc_vdpa_context		vdpa_context;
 	enum sfc_vdpa_state		state;
+	pthread_t			notify_tid;
+	bool				is_notify_thread_started;
 
 	uint64_t			dev_features;
 	uint64_t			drv_features;

index f548c1e..78b280e 100644
@@ -8,7 +8,9 @@
 #include <sys/queue.h>
 
 #include <rte_common.h>
+#include <rte_devargs.h>
 #include <rte_errno.h>
+#include <rte_kvargs.h>
 #include <rte_string_fns.h>
 #include <rte_vfio.h>
 #include <rte_vhost.h>

@@ -198,6 +200,31 @@ struct sfc_vdpa_ops_data *
 	return ret < 0 ? RTE_LOGTYPE_PMD : ret;
 }
 
+static int
+sfc_vdpa_kvargs_parse(struct sfc_vdpa_adapter *sva)
+{
+	struct rte_pci_device *pci_dev = sva->pdev;
+	struct rte_devargs *devargs = pci_dev->device.devargs;
+	/*
+	 * To get the device class a mandatory param 'class' is being
+	 * used so included SFC_EFX_KVARG_DEV_CLASS in the param list.
+	 */
+	const char **params = (const char *[]){
+		RTE_DEVARGS_KEY_CLASS,
+		SFC_VDPA_MAC_ADDR,
+		NULL,
+	};
+
+	if (devargs == NULL)
+		return 0;
+
+	sva->kvargs = rte_kvargs_parse(devargs->args, params);
+	if (sva->kvargs == NULL)
+		return -EINVAL;
+
+	return 0;
+}
+
 static struct rte_pci_id pci_id_sfc_vdpa_efx_map[] = {
 	{ RTE_PCI_DEVICE(EFX_PCI_VENID_XILINX, EFX_PCI_DEVID_RIVERHEAD_VF) },
 	{ .vendor_id = 0, /* sentinel */ },

@@ -240,6 +267,10 @@ struct sfc_vdpa_ops_data *
 	if (ret != 0)
 		goto fail_set_log_prefix;
 
+	ret = sfc_vdpa_kvargs_parse(sva);
+	if (ret != 0)
+		goto fail_kvargs_parse;
+
 	sfc_vdpa_log_init(sva, "entry");
 
 	sfc_vdpa_adapter_lock_init(sva);

@@ -280,6 +311,7 @@ struct sfc_vdpa_ops_data *
 fail_vfio_setup:
 	sfc_vdpa_adapter_lock_fini(sva);
 
+fail_kvargs_parse:
 fail_set_log_prefix:
 	rte_free(sva);
 

index 38fd5de..81fc39d 100644
@@ -17,8 +17,29 @@
 #include "sfc_vdpa_log.h"
 #include "sfc_vdpa_ops.h"
 
+#define SFC_VDPA_MAC_ADDR			"mac"
 #define SFC_VDPA_DEFAULT_MCDI_IOVA		0x200000000000
 
+/* Broadcast & Unicast MAC filters are supported */
+#define SFC_MAX_SUPPORTED_FILTERS		2
+
+/*
+ * Get function-local index of the associated VI from the
+ * virtqueue number. Queue 0 is reserved for MCDI
+ */
+#define SFC_VDPA_GET_VI_INDEX(vq_num) (((vq_num) / 2) + 1)
+
+enum sfc_vdpa_filter_type {
+	SFC_VDPA_BCAST_MAC_FILTER = 0,
+	SFC_VDPA_UCAST_MAC_FILTER = 1,
+	SFC_VDPA_FILTER_NTYPE
+};
+
+typedef struct sfc_vdpa_filter_s {
+	int				filter_cnt;
+	efx_filter_spec_t		spec[SFC_MAX_SUPPORTED_FILTERS];
+} sfc_vdpa_filter_t;
+
 /* Adapter private data */
 struct sfc_vdpa_adapter {
 	TAILQ_ENTRY(sfc_vdpa_adapter)	next;

@@ -31,6 +52,8 @@ struct sfc_vdpa_adapter {
 	rte_spinlock_t			lock;
 	struct rte_pci_device		*pdev;
 
+	struct rte_kvargs		*kvargs;
+
 	efx_family_t			family;
 	efx_nic_t			*nic;
 	rte_spinlock_t			nic_lock;

@@ -45,6 +68,8 @@ struct sfc_vdpa_adapter {
 	char				log_prefix[SFC_VDPA_LOG_PREFIX_MAX];
 	uint32_t			logtype_main;
 
+	sfc_vdpa_filter_t		filters;
+
 	int				vfio_group_fd;
 	int				vfio_dev_fd;
 	int				vfio_container_fd;

@@ -82,6 +107,11 @@ struct sfc_vdpa_ops_data *
 int
 sfc_vdpa_dma_map(struct sfc_vdpa_ops_data *vdpa_data, bool do_map);
 
+int
+sfc_vdpa_filter_remove(struct sfc_vdpa_ops_data *ops_data);
+int
+sfc_vdpa_filter_config(struct sfc_vdpa_ops_data *ops_data);
+
 static inline struct sfc_vdpa_adapter *
 sfc_vdpa_adapter_by_dev_handle(void *dev_handle)
 {

136 lines not on this page · raw message

index d3459ee..463498c 100644
@@ -353,10 +353,20 @@
 		goto fail_virtio_init;
 	}
 
+	sfc_vdpa_log_init(sva, "init filter");
+	rc = efx_filter_init(enp);
+	if (rc != 0) {
+		sfc_vdpa_err(sva, "filter init failed: %s", rte_strerror(rc));
+		goto fail_filter_init;
+	}
+
 	sfc_vdpa_log_init(sva, "done");
 
 	return 0;
 
+fail_filter_init:
+	efx_virtio_fini(enp);
+
 fail_virtio_init:
 	efx_nic_fini(enp);
 

index 1725597..9d4ed34 100644
@@ -421,6 +421,8 @@
 
 	sfc_vdpa_disable_vfio_intr(ops_data);
 
+	sfc_vdpa_filter_remove(ops_data);
+
 	ops_data->state = SFC_VDPA_STATE_CONFIGURED;
 }
 

@@ -460,12 +462,27 @@
 			goto fail_vq_start;
 	}
 
+	ops_data->vq_count = i;
+
+	sfc_vdpa_log_init(ops_data->dev_handle,
+			  "configure MAC filters");
+	rc = sfc_vdpa_filter_config(ops_data);
+	if (rc != 0) {
+		sfc_vdpa_err(ops_data->dev_handle,
+			     "MAC filter config failed: %s",
+			     rte_strerror(rc));
+		goto fail_filter_cfg;
+	}
+
 	ops_data->state = SFC_VDPA_STATE_STARTED;
 
 	sfc_vdpa_log_init(ops_data->dev_handle, "done");
 
 	return 0;
 
+fail_filter_cfg:
+	/* remove already created filters */
+	sfc_vdpa_filter_remove(ops_data);
 fail_vq_start:
 	/* stop already started virtqueues */
 	for (j = 0; j < i; j++)

index 9d4ed34..c5c97b8 100644
@@ -702,11 +702,57 @@
 static int
 sfc_vdpa_set_vring_state(int vid, int vring, int state)
 {
-	RTE_SET_USED(vid);
-	RTE_SET_USED(vring);
-	RTE_SET_USED(state);
+	struct sfc_vdpa_ops_data *ops_data;
+	struct rte_vdpa_device *vdpa_dev;
+	efx_rc_t rc;
+	int vring_max;
+	void *dev;
 
-	return -1;
+	vdpa_dev = rte_vhost_get_vdpa_device(vid);
+
+	ops_data = sfc_vdpa_get_data_by_dev(vdpa_dev);
+	if (ops_data == NULL)
+		return -1;
+
+	dev = ops_data->dev_handle;
+
+	sfc_vdpa_info(dev,
+		      "vDPA ops set_vring_state: vid: %d, vring: %d, state:%d",
+		      vid, vring, state);
+
+	vring_max = (sfc_vdpa_adapter_by_dev_handle(dev)->max_queue_count * 2);
+
+	if (vring < 0 || vring > vring_max) {
+		sfc_vdpa_err(dev, "received invalid vring id : %d to set state",
+			     vring);
+		return -1;
+	}
+
+	/*
+	 * Skip if device is not yet started. virtqueues state can be
+	 * changed once it is created and other configurations are done.
+	 */
+	if (ops_data->state != SFC_VDPA_STATE_STARTED)
+		return 0;
+
+	if (ops_data->vq_cxt[vring].enable == state)
+		return 0;
+
+	if (state == 0) {
+		rc = sfc_vdpa_virtq_stop(ops_data, vring);
+		if (rc != 0) {
+			sfc_vdpa_err(dev, "virtqueue stop failed: %s",
+				     rte_strerror(rc));
+		}
+	} else {
+		rc = sfc_vdpa_virtq_start(ops_data, vring);
+		if (rc != 0) {
+			sfc_vdpa_err(dev, "virtqueue start failed: %s",
+				     rte_strerror(rc));
+		}
+	}
+
+	return rc;
 }
 
 static int

index 81fc39d..080f2d6 100644
@@ -21,7 +21,7 @@
 #define SFC_VDPA_DEFAULT_MCDI_IOVA		0x200000000000
 
 /* Broadcast & Unicast MAC filters are supported */
-#define SFC_MAX_SUPPORTED_FILTERS		2
+#define SFC_MAX_SUPPORTED_FILTERS		3
 
 /*
  * Get function-local index of the associated VI from the

@@ -32,6 +32,7 @@
 enum sfc_vdpa_filter_type {
 	SFC_VDPA_BCAST_MAC_FILTER = 0,
 	SFC_VDPA_UCAST_MAC_FILTER = 1,
+	SFC_VDPA_MCAST_DST_FILTER = 2,
 	SFC_VDPA_FILTER_NTYPE
 };
 

index 9687278..4c133aa 100644
@@ -39,8 +39,12 @@
 	spec->efs_flags = EFX_FILTER_FLAG_RX;
 	spec->efs_dmaq_id = qid;
 
-	rc = efx_filter_spec_set_eth_local(spec, EFX_FILTER_SPEC_VID_UNSPEC,
-					   eth_addr);
+	if (eth_addr == NULL)
+		rc = efx_filter_spec_set_mc_def(spec);
+	else
+		rc = efx_filter_spec_set_eth_local(spec,
+						   EFX_FILTER_SPEC_VID_UNSPEC,
+						   eth_addr);
 	if (rc != 0)
 		return rc;
 

@@ -103,8 +107,18 @@ int sfc_vdpa_filter_config(struct sfc_vdpa_ops_data *ops_data)
 	rc = sfc_vdpa_set_mac_filter(nic, spec, qid,
 				     ucast_eth_addr.addr_bytes);
 	if (rc != 0)
+		sfc_vdpa_err(sva, "unicast MAC filter insertion failed: %s",
+			     rte_strerror(rc));
+	else
+		sva->filters.filter_cnt++;
+
+	sfc_vdpa_log_init(sva, "insert unknown mcast filter");
+	spec = &sva->filters.spec[SFC_VDPA_MCAST_DST_FILTER];
+
+	rc = sfc_vdpa_set_mac_filter(nic, spec, qid, NULL);
+	if (rc != 0)
 		sfc_vdpa_err(sva,
-			     "unicast MAC filter insertion failed: %s",
+			     "mcast filter insertion failed: %s",
 			     rte_strerror(rc));
 	else
 		sva->filters.filter_cnt++;