New upstream version 18.02upstream/18.02

Change-Id: I89ed24cb2a49b78fe5be6970b99dd46c1499fcc3
Signed-off-by: Luca Boccassi <luca.boccassi@gmail.com>

10 files changed, 1325 insertions, 362 deletions

diff --git a/drivers/net/failsafe/Makefile b/drivers/net/failsafe/Makefile
index ea2a8fe4..bd2f0198 100644
--- a/drivers/net/failsafe/Makefile
+++ b/drivers/net/failsafe/Makefile
@@ -46,10 +46,17 @@ SRCS-$(CONFIG_RTE_LIBRTE_PMD_FAILSAFE) += failsafe_ops.c
 SRCS-$(CONFIG_RTE_LIBRTE_PMD_FAILSAFE) += failsafe_rxtx.c
 SRCS-$(CONFIG_RTE_LIBRTE_PMD_FAILSAFE) += failsafe_ether.c
 SRCS-$(CONFIG_RTE_LIBRTE_PMD_FAILSAFE) += failsafe_flow.c
+SRCS-$(CONFIG_RTE_LIBRTE_PMD_FAILSAFE) += failsafe_intr.c
+ifeq ($(CONFIG_RTE_EXEC_ENV_LINUXAPP),y)
+CFLAGS += -DLINUX
+else
+CFLAGS += -DBSD
+endif
 
 # No exported include files
 
 # Basic CFLAGS:
+CFLAGS += -DALLOW_EXPERIMENTAL_API
 CFLAGS += -std=gnu99 -Wextra
 CFLAGS += -O3
 CFLAGS += -I.
@@ -61,5 +68,6 @@ CFLAGS += -pedantic
 LDLIBS += -lrte_eal -lrte_mbuf -lrte_mempool -lrte_ring
 LDLIBS += -lrte_ethdev -lrte_net -lrte_kvargs
 LDLIBS += -lrte_bus_vdev
+LDLIBS += -lpthread
 
 include $(RTE_SDK)/mk/rte.lib.mk
diff --git a/drivers/net/failsafe/failsafe.c b/drivers/net/failsafe/failsafe.c
index 6bc5abac..c499bfb9 100644
--- a/drivers/net/failsafe/failsafe.c
+++ b/drivers/net/failsafe/failsafe.c
@@ -1,39 +1,11 @@
-/*-
- *   BSD LICENSE
- *
- *   Copyright 2017 6WIND S.A.
- *   Copyright 2017 Mellanox.
- *
- *   Redistribution and use in source and binary forms, with or without
- *   modification, are permitted provided that the following conditions
- *   are met:
- *
- *     * Redistributions of source code must retain the above copyright
- *       notice, this list of conditions and the following disclaimer.
- *     * Redistributions in binary form must reproduce the above copyright
- *       notice, this list of conditions and the following disclaimer in
- *       the documentation and/or other materials provided with the
- *       distribution.
- *     * Neither the name of 6WIND S.A. nor the names of its
- *       contributors may be used to endorse or promote products derived
- *       from this software without specific prior written permission.
- *
- *   THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
- *   "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
- *   LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
- *   A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
- *   OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
- *   SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
- *   LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
- *   DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
- *   THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
- *   (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
- *   OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+/* SPDX-License-Identifier: BSD-3-Clause
+ * Copyright 2017 6WIND S.A.
+ * Copyright 2017 Mellanox.
  */
 
 #include <rte_alarm.h>
 #include <rte_malloc.h>
-#include <rte_ethdev.h>
+#include <rte_ethdev_driver.h>
 #include <rte_ethdev_vdev.h>
 #include <rte_devargs.h>
 #include <rte_kvargs.h>
@@ -46,7 +18,7 @@ static const struct rte_eth_link eth_link = {
 	.link_speed = ETH_SPEED_NUM_10G,
 	.link_duplex = ETH_LINK_FULL_DUPLEX,
 	.link_status = ETH_LINK_UP,
-	.link_autoneg = ETH_LINK_SPEED_AUTONEG,
+	.link_autoneg = ETH_LINK_AUTONEG,
 };
 
 static int
@@ -55,6 +27,7 @@ fs_sub_device_alloc(struct rte_eth_dev *dev,
 {
 	uint8_t nb_subs;
 	int ret;
+	int i;
 
 	ret = failsafe_args_count_subdevice(dev, params);
 	if (ret)
@@ -72,6 +45,10 @@ fs_sub_device_alloc(struct rte_eth_dev *dev,
 		ERROR("Could not allocate sub_devices");
 		return -ENOMEM;
 	}
+	/* Initiate static sub devices linked list. */
+	for (i = 1; i < nb_subs; i++)
+		PRIV(dev)->subs[i - 1].next = PRIV(dev)->subs + i;
+	PRIV(dev)->subs[i - 1].next = PRIV(dev)->subs;
 	return 0;
 }
 
@@ -108,16 +85,14 @@ failsafe_hotplug_alarm_cancel(struct rte_eth_dev *dev)
 {
 	int ret = 0;
 
-	if (PRIV(dev)->pending_alarm) {
-		rte_errno = 0;
-		rte_eal_alarm_cancel(fs_hotplug_alarm, dev);
-		if (rte_errno) {
-			ERROR("rte_eal_alarm_cancel failed (errno: %s)",
-			      strerror(rte_errno));
-			ret = -rte_errno;
-		} else {
-			PRIV(dev)->pending_alarm = 0;
-		}
+	rte_errno = 0;
+	rte_eal_alarm_cancel(fs_hotplug_alarm, dev);
+	if (rte_errno) {
+		ERROR("rte_eal_alarm_cancel failed (errno: %s)",
+		      strerror(rte_errno));
+		ret = -rte_errno;
+	} else {
+		PRIV(dev)->pending_alarm = 0;
 	}
 	return ret;
 }
@@ -138,17 +113,46 @@ fs_hotplug_alarm(void *arg)
 			break;
 	/* if we have non-probed device */
 	if (i != PRIV(dev)->subs_tail) {
+		if (fs_lock(dev, 1) != 0)
+			goto reinstall;
 		ret = failsafe_eth_dev_state_sync(dev);
+		fs_unlock(dev, 1);
 		if (ret)
 			ERROR("Unable to synchronize sub_device state");
 	}
 	failsafe_dev_remove(dev);
+reinstall:
 	ret = failsafe_hotplug_alarm_install(dev);
 	if (ret)
 		ERROR("Unable to set up next alarm");
 }
 
 static int
+fs_mutex_init(struct fs_priv *priv)
+{
+	int ret;
+	pthread_mutexattr_t attr;
+
+	ret = pthread_mutexattr_init(&attr);
+	if (ret) {
+		ERROR("Cannot initiate mutex attributes - %s", strerror(ret));
+		return ret;
+	}
+	/* Allow mutex relocks for the thread holding the mutex. */
+	ret = pthread_mutexattr_settype(&attr, PTHREAD_MUTEX_RECURSIVE);
+	if (ret) {
+		ERROR("Cannot set mutex type - %s", strerror(ret));
+		return ret;
+	}
+	ret = pthread_mutex_init(&priv->hotplug_mutex, &attr);
+	if (ret) {
+		ERROR("Cannot initiate mutex - %s", strerror(ret));
+		return ret;
+	}
+	return 0;
+}
+
+static int
 fs_eth_dev_create(struct rte_vdev_device *vdev)
 {
 	struct rte_eth_dev *dev;
@@ -191,9 +195,19 @@ fs_eth_dev_create(struct rte_vdev_device *vdev)
 	ret = failsafe_args_parse(dev, params);
 	if (ret)
 		goto free_subs;
+	ret = rte_eth_dev_owner_new(&priv->my_owner.id);
+	if (ret) {
+		ERROR("Failed to get unique owner identifier");
+		goto free_args;
+	}
+	snprintf(priv->my_owner.name, sizeof(priv->my_owner.name),
+		 FAILSAFE_OWNER_NAME);
 	ret = failsafe_eal_init(dev);
 	if (ret)
 		goto free_args;
+	ret = fs_mutex_init(priv);
+	if (ret)
+		goto free_args;
 	ret = failsafe_hotplug_alarm_install(dev);
 	if (ret) {
 		ERROR("Could not set up plug-in event detection");
@@ -239,6 +253,10 @@ fs_eth_dev_create(struct rte_vdev_device *vdev)
 		mac->addr_bytes[2], mac->addr_bytes[3],
 		mac->addr_bytes[4], mac->addr_bytes[5]);
 	dev->data->dev_flags |= RTE_ETH_DEV_INTR_LSC;
+	PRIV(dev)->intr_handle = (struct rte_intr_handle){
+		.fd = -1,
+		.type = RTE_INTR_HANDLE_EXT,
+	};
 	return 0;
 free_args:
 	failsafe_args_free(dev);
@@ -264,6 +282,9 @@ fs_rte_eth_free(const char *name)
 		ERROR("Error while uninitializing sub-EAL");
 	failsafe_args_free(dev);
 	fs_sub_device_free(dev);
+	ret = pthread_mutex_destroy(&PRIV(dev)->hotplug_mutex);
+	if (ret)
+		ERROR("Error while destroying hotplug mutex");
 	rte_free(PRIV(dev));
 	rte_eth_dev_release_port(dev);
 	return ret;
diff --git a/drivers/net/failsafe/failsafe_args.c b/drivers/net/failsafe/failsafe_args.c
index cfc83e36..366dbea1 100644
--- a/drivers/net/failsafe/failsafe_args.c
+++ b/drivers/net/failsafe/failsafe_args.c
@@ -1,37 +1,13 @@
-/*-
- *   BSD LICENSE
- *
- *   Copyright 2017 6WIND S.A.
- *   Copyright 2017 Mellanox.
- *
- *   Redistribution and use in source and binary forms, with or without
- *   modification, are permitted provided that the following conditions
- *   are met:
- *
- *     * Redistributions of source code must retain the above copyright
- *       notice, this list of conditions and the following disclaimer.
- *     * Redistributions in binary form must reproduce the above copyright
- *       notice, this list of conditions and the following disclaimer in
- *       the documentation and/or other materials provided with the
- *       distribution.
- *     * Neither the name of 6WIND S.A. nor the names of its
- *       contributors may be used to endorse or promote products derived
- *       from this software without specific prior written permission.
- *
- *   THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
- *   "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
- *   LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
- *   A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
- *   OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
- *   SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
- *   LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
- *   DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
- *   THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
- *   (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
- *   OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+/* SPDX-License-Identifier: BSD-3-Clause
+ * Copyright 2017 6WIND S.A.
+ * Copyright 2017 Mellanox.
  */
 
+#include <fcntl.h>
+#include <stdio.h>
+#include <stdlib.h>
 #include <string.h>
+#include <unistd.h>
 #include <errno.h>
 
 #include <rte_debug.h>
@@ -41,8 +17,6 @@
 
 #include "failsafe_private.h"
 
-#define DEVARGS_MAXLEN 4096
-
 /* Callback used when a new device is found in devargs */
 typedef int (parse_cb)(struct rte_eth_dev *dev, const char *params,
 		uint8_t head);
@@ -161,6 +135,67 @@ ret_pclose:
 }
 
 static int
+fs_read_fd(struct sub_device *sdev, char *fd_str)
+{
+	FILE *fp = NULL;
+	int fd = -1;
+	/* store possible newline as well */
+	char output[DEVARGS_MAXLEN + 1];
+	int err = -ENODEV;
+	int oflags;
+	int lcount;
+
+	RTE_ASSERT(fd_str != NULL || sdev->fd_str != NULL);
+	if (sdev->fd_str == NULL) {
+		sdev->fd_str = strdup(fd_str);
+		if (sdev->fd_str == NULL) {
+			ERROR("Command line allocation failed");
+			return -ENOMEM;
+		}
+	}
+	errno = 0;
+	fd = strtol(fd_str, &fd_str, 0);
+	if (errno || *fd_str || fd < 0) {
+		ERROR("Parsing FD number failed");
+		goto error;
+	}
+	/* Fiddle with copy of file descriptor */
+	fd = dup(fd);
+	if (fd == -1)
+		goto error;
+	oflags = fcntl(fd, F_GETFL);
+	if (oflags == -1)
+		goto error;
+	if (fcntl(fd, F_SETFL, oflags | O_NONBLOCK) == -1)
+		goto error;
+	fp = fdopen(fd, "r");
+	if (fp == NULL)
+		goto error;
+	fd = -1;
+	/* Only take the last line into account */
+	lcount = 0;
+	while (fgets(output, sizeof(output), fp))
+		++lcount;
+	if (lcount == 0)
+		goto error;
+	else if (ferror(fp) && errno != EAGAIN)
+		goto error;
+	/* Line must end with a newline character */
+	fs_sanitize_cmdline(output);
+	if (output[0] == '\0')
+		goto error;
+	err = fs_parse_device(sdev, output);
+	if (err)
+		ERROR("Parsing device '%s' failed", output);
+error:
+	if (fp)
+		fclose(fp);
+	if (fd != -1)
+		close(fd);
+	return err;
+}
+
+static int
 fs_parse_device_param(struct rte_eth_dev *dev, const char *param,
 		uint8_t head)
 {
@@ -202,6 +237,14 @@ fs_parse_device_param(struct rte_eth_dev *dev, const char *param,
 		}
 		if (ret)
 			goto free_args;
+	} else if (strncmp(param, "fd(", 3) == 0) {
+		ret = fs_read_fd(sdev, args);
+		if (ret == -ENODEV) {
+			DEBUG("Reading device info from FD failed");
+			ret = 0;
+		}
+		if (ret)
+			goto free_args;
 	} else {
 		ERROR("Unrecognized device type: %.*s", (int)b, param);
 		return -EINVAL;
@@ -407,8 +450,10 @@ failsafe_args_free(struct rte_eth_dev *dev)
 	uint8_t i;
 
 	FOREACH_SUBDEV(sdev, i, dev) {
-		rte_free(sdev->cmdline);
+		free(sdev->cmdline);
 		sdev->cmdline = NULL;
+		free(sdev->fd_str);
+		sdev->fd_str = NULL;
 		free(sdev->devargs.args);
 		sdev->devargs.args = NULL;
 	}
@@ -424,7 +469,8 @@ fs_count_device(struct rte_eth_dev *dev, const char *param,
 		param[b] != '\0')
 		b++;
 	if (strncmp(param, "dev", b) != 0 &&
-	    strncmp(param, "exec", b) != 0) {
+	    strncmp(param, "exec", b) != 0 &&
+	    strncmp(param, "fd(", b) != 0) {
 		ERROR("Unrecognized device type: %.*s", (int)b, param);
 		return -EINVAL;
 	}
@@ -463,6 +509,8 @@ failsafe_args_parse_subs(struct rte_eth_dev *dev)
 			continue;
 		if (sdev->cmdline)
 			ret = fs_execute_cmd(sdev, sdev->cmdline);
+		else if (sdev->fd_str)
+			ret = fs_read_fd(sdev, sdev->fd_str);
 		else
 			ret = fs_parse_sub_device(sdev);
 		if (ret == 0)
diff --git a/drivers/net/failsafe/failsafe_eal.c b/drivers/net/failsafe/failsafe_eal.c
index 19d26f53..c3d67312 100644
--- a/drivers/net/failsafe/failsafe_eal.c
+++ b/drivers/net/failsafe/failsafe_eal.c
@@ -1,34 +1,6 @@
-/*-
- *   BSD LICENSE
- *
- *   Copyright 2017 6WIND S.A.
- *   Copyright 2017 Mellanox.
- *
- *   Redistribution and use in source and binary forms, with or without
- *   modification, are permitted provided that the following conditions
- *   are met:
- *
- *     * Redistributions of source code must retain the above copyright
- *       notice, this list of conditions and the following disclaimer.
- *     * Redistributions in binary form must reproduce the above copyright
- *       notice, this list of conditions and the following disclaimer in
- *       the documentation and/or other materials provided with the
- *       distribution.
- *     * Neither the name of 6WIND S.A. nor the names of its
- *       contributors may be used to endorse or promote products derived
- *       from this software without specific prior written permission.
- *
- *   THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
- *   "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
- *   LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
- *   A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
- *   OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
- *   SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
- *   LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
- *   DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
- *   THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
- *   (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
- *   OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+/* SPDX-License-Identifier: BSD-3-Clause
+ * Copyright 2017 6WIND S.A.
+ * Copyright 2017 Mellanox.
  */
 
 #include <rte_malloc.h>
@@ -36,39 +8,93 @@
 #include "failsafe_private.h"
 
 static int
+fs_ethdev_portid_get(const char *name, uint16_t *port_id)
+{
+	uint16_t pid;
+	size_t len;
+
+	if (name == NULL) {
+		DEBUG("Null pointer is specified\n");
+		return -EINVAL;
+	}
+	len = strlen(name);
+	RTE_ETH_FOREACH_DEV(pid) {
+		if (!strncmp(name, rte_eth_devices[pid].device->name, len)) {
+			*port_id = pid;
+			return 0;
+		}
+	}
+	return -ENODEV;
+}
+
+static int
 fs_bus_init(struct rte_eth_dev *dev)
 {
 	struct sub_device *sdev;
 	struct rte_devargs *da;
 	uint8_t i;
-	uint16_t j;
+	uint16_t pid;
 	int ret;
 
 	FOREACH_SUBDEV(sdev, i, dev) {
 		if (sdev->state != DEV_PARSED)
 			continue;
 		da = &sdev->devargs;
-		ret = rte_eal_hotplug_add(da->bus->name,
-					  da->name,
-					  da->args);
-		if (ret) {
-			ERROR("sub_device %d probe failed %s%s%s", i,
-			      rte_errno ? "(" : "",
-			      rte_errno ? strerror(rte_errno) : "",
-			      rte_errno ? ")" : "");
-			continue;
-		}
-		RTE_ETH_FOREACH_DEV(j) {
-			if (strcmp(rte_eth_devices[j].device->name,
-				    da->name) == 0) {
-				ETH(sdev) = &rte_eth_devices[j];
-				break;
+		if (fs_ethdev_portid_get(da->name, &pid) != 0) {
+			ret = rte_eal_hotplug_add(da->bus->name,
+						  da->name,
+						  da->args);
+			if (ret) {
+				ERROR("sub_device %d probe failed %s%s%s", i,
+				      rte_errno ? "(" : "",
+				      rte_errno ? strerror(rte_errno) : "",
+				      rte_errno ? ")" : "");
+				continue;
 			}
+			if (fs_ethdev_portid_get(da->name, &pid) != 0) {
+				ERROR("sub_device %d init went wrong", i);
+				return -ENODEV;
+			}
+		} else {
+			char devstr[DEVARGS_MAXLEN] = "";
+			struct rte_devargs *probed_da =
+					rte_eth_devices[pid].device->devargs;
+
+			/* Take control of device probed by EAL options. */
+			free(da->args);
+			memset(da, 0, sizeof(*da));
+			if (probed_da != NULL)
+				snprintf(devstr, sizeof(devstr), "%s,%s",
+					 probed_da->name, probed_da->args);
+			else
+				snprintf(devstr, sizeof(devstr), "%s",
+					 rte_eth_devices[pid].device->name);
+			ret = rte_eal_devargs_parse(devstr, da);
+			if (ret) {
+				ERROR("Probed devargs parsing failed with code"
+				      " %d", ret);
+				return ret;
+			}
+			INFO("Taking control of a probed sub device"
+			      " %d named %s", i, da->name);
 		}
-		if (ETH(sdev) == NULL) {
-			ERROR("sub_device %d init went wrong", i);
-			return -ENODEV;
+		ret = rte_eth_dev_owner_set(pid, &PRIV(dev)->my_owner);
+		if (ret < 0) {
+			INFO("sub_device %d owner set failed (%s),"
+			     " will try again later", i, strerror(-ret));
+			continue;
+		} else if (strncmp(rte_eth_devices[pid].device->name, da->name,
+			   strlen(da->name)) != 0) {
+			/*
+			 * The device probably was removed and its port id was
+			 * reallocated before ownership set.
+			 */
+			rte_eth_dev_owner_unset(pid, PRIV(dev)->my_owner.id);
+			INFO("sub_device %d was probably removed before taking"
+			     " ownership, will try again later", i);
+			continue;
 		}
+		ETH(sdev) = &rte_eth_devices[pid];
 		SUB_ID(sdev) = i;
 		sdev->fs_dev = dev;
 		sdev->dev = ETH(sdev)->device;
diff --git a/drivers/net/failsafe/failsafe_ether.c b/drivers/net/failsafe/failsafe_ether.c
index 21392e5a..2c0bf936 100644
--- a/drivers/net/failsafe/failsafe_ether.c
+++ b/drivers/net/failsafe/failsafe_ether.c
@@ -1,34 +1,6 @@
-/*-
- *   BSD LICENSE
- *
- *   Copyright 2017 6WIND S.A.
- *   Copyright 2017 Mellanox.
- *
- *   Redistribution and use in source and binary forms, with or without
- *   modification, are permitted provided that the following conditions
- *   are met:
- *
- *     * Redistributions of source code must retain the above copyright
- *       notice, this list of conditions and the following disclaimer.
- *     * Redistributions in binary form must reproduce the above copyright
- *       notice, this list of conditions and the following disclaimer in
- *       the documentation and/or other materials provided with the
- *       distribution.
- *     * Neither the name of 6WIND S.A. nor the names of its
- *       contributors may be used to endorse or promote products derived
- *       from this software without specific prior written permission.
- *
- *   THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
- *   "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
- *   LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
- *   A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
- *   OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
- *   SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
- *   LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
- *   DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
- *   THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
- *   (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
- *   OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+/* SPDX-License-Identifier: BSD-3-Clause
+ * Copyright 2017 6WIND S.A.
+ * Copyright 2017 Mellanox.
  */
 
 #include <unistd.h>
@@ -283,6 +255,7 @@ fs_dev_remove(struct sub_device *sdev)
 		return;
 	switch (sdev->state) {
 	case DEV_STARTED:
+		failsafe_rx_intr_uninstall_subdevice(sdev);
 		rte_eth_dev_stop(PORT_ID(sdev));
 		sdev->state = DEV_ACTIVE;
 		/* fallthrough */
@@ -297,7 +270,7 @@ fs_dev_remove(struct sub_device *sdev)
 			ERROR("Bus detach failed for sub_device %u",
 			      SUB_ID(sdev));
 		} else {
-			ETH(sdev)->state = RTE_ETH_DEV_UNUSED;
+			rte_eth_dev_release_port(ETH(sdev));
 		}
 		sdev->state = DEV_PARSED;
 		/* fallthrough */
@@ -307,6 +280,7 @@ fs_dev_remove(struct sub_device *sdev)
 		/* the end */
 		break;
 	}
+	sdev->remove = 0;
 	failsafe_hotplug_alarm_install(sdev->fs_dev);
 }
 
@@ -354,8 +328,11 @@ failsafe_dev_remove(struct rte_eth_dev *dev)
 
 	FOREACH_SUBDEV_STATE(sdev, i, dev, DEV_ACTIVE)
 		if (sdev->remove && fs_rxtx_clean(sdev)) {
+			if (fs_lock(dev, 1) != 0)
+				return;
 			fs_dev_stats_save(sdev);
 			fs_dev_remove(sdev);
+			fs_unlock(dev, 1);
 		}
 }
 
@@ -455,6 +432,7 @@ failsafe_eth_rmv_event_callback(uint16_t port_id __rte_unused,
 {
 	struct sub_device *sdev = cb_arg;
 
+	fs_lock(sdev->fs_dev, 0);
 	/* Switch as soon as possible tx_dev. */
 	fs_switch_dev(sdev->fs_dev, sdev);
 	/* Use safe bursts in any case. */
@@ -464,6 +442,7 @@ failsafe_eth_rmv_event_callback(uint16_t port_id __rte_unused,
 	 * the callback at the source of the current thread context.
 	 */
 	sdev->remove = 1;
+	fs_unlock(sdev->fs_dev, 0);
 	return 0;
 }
 
@@ -480,7 +459,7 @@ failsafe_eth_lsc_event_callback(uint16_t port_id __rte_unused,
 	if (ret)
 		return _rte_eth_dev_callback_process(dev,
 						     RTE_ETH_EVENT_INTR_LSC,
-						     NULL, NULL);
+						     NULL);
 	else
 		return 0;
 }
diff --git a/drivers/net/failsafe/failsafe_flow.c b/drivers/net/failsafe/failsafe_flow.c
index 153ceeed..ec8c909b 100644
--- a/drivers/net/failsafe/failsafe_flow.c
+++ b/drivers/net/failsafe/failsafe_flow.c
@@ -1,34 +1,6 @@
-/*-
- *   BSD LICENSE
- *
- *   Copyright 2017 6WIND S.A.
- *   Copyright 2017 Mellanox.
- *
- *   Redistribution and use in source and binary forms, with or without
- *   modification, are permitted provided that the following conditions
- *   are met:
- *
- *     * Redistributions of source code must retain the above copyright
- *       notice, this list of conditions and the following disclaimer.
- *     * Redistributions in binary form must reproduce the above copyright
- *       notice, this list of conditions and the following disclaimer in
- *       the documentation and/or other materials provided with the
- *       distribution.
- *     * Neither the name of 6WIND S.A. nor the names of its
- *       contributors may be used to endorse or promote products derived
- *       from this software without specific prior written permission.
- *
- *   THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
- *   "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
- *   LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
- *   A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
- *   OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
- *   SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
- *   LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
- *   DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
- *   THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
- *   (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
- *   OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+/* SPDX-License-Identifier: BSD-3-Clause
+ * Copyright 2017 6WIND S.A.
+ * Copyright 2017 Mellanox.
  */
 
 #include <sys/queue.h>
@@ -83,16 +55,19 @@ fs_flow_validate(struct rte_eth_dev *dev,
 	uint8_t i;
 	int ret;
 
+	fs_lock(dev, 0);
 	FOREACH_SUBDEV_STATE(sdev, i, dev, DEV_ACTIVE) {
 		DEBUG("Calling rte_flow_validate on sub_device %d", i);
 		ret = rte_flow_validate(PORT_ID(sdev),
 				attr, patterns, actions, error);
-		if (ret) {
+		if ((ret = fs_err(sdev, ret))) {
 			ERROR("Operation rte_flow_validate failed for sub_device %d"
 			      " with error %d", i, ret);
+			fs_unlock(dev, 0);
 			return ret;
 		}
 	}
+	fs_unlock(dev, 0);
 	return 0;
 }
 
@@ -107,17 +82,19 @@ fs_flow_create(struct rte_eth_dev *dev,
 	struct rte_flow *flow;
 	uint8_t i;
 
+	fs_lock(dev, 0);
 	flow = fs_flow_allocate(attr, patterns, actions);
 	FOREACH_SUBDEV_STATE(sdev, i, dev, DEV_ACTIVE) {
 		flow->flows[i] = rte_flow_create(PORT_ID(sdev),
 				attr, patterns, actions, error);
-		if (flow->flows[i] == NULL) {
+		if (flow->flows[i] == NULL && fs_err(sdev, -rte_errno)) {
 			ERROR("Failed to create flow on sub_device %d",
 				i);
 			goto err;
 		}
 	}
 	TAILQ_INSERT_TAIL(&PRIV(dev)->flow_list, flow, next);
+	fs_unlock(dev, 0);
 	return flow;
 err:
 	FOREACH_SUBDEV(sdev, i, dev) {
@@ -126,6 +103,7 @@ err:
 				flow->flows[i], error);
 	}
 	fs_flow_release(&flow);
+	fs_unlock(dev, 0);
 	return NULL;
 }
 
@@ -143,6 +121,7 @@ fs_flow_destroy(struct rte_eth_dev *dev,
 		return -EINVAL;
 	}
 	ret = 0;
+	fs_lock(dev, 0);
 	FOREACH_SUBDEV_STATE(sdev, i, dev, DEV_ACTIVE) {
 		int local_ret;
 
@@ -150,7 +129,7 @@ fs_flow_destroy(struct rte_eth_dev *dev,
 			continue;
 		local_ret = rte_flow_destroy(PORT_ID(sdev),
 				flow->flows[i], error);
-		if (local_ret) {
+		if ((local_ret = fs_err(sdev, local_ret))) {
 			ERROR("Failed to destroy flow on sub_device %d: %d",
 					i, local_ret);
 			if (ret == 0)
@@ -159,6 +138,7 @@ fs_flow_destroy(struct rte_eth_dev *dev,
 	}
 	TAILQ_REMOVE(&PRIV(dev)->flow_list, flow, next);
 	fs_flow_release(&flow);
+	fs_unlock(dev, 0);
 	return ret;
 }
 
@@ -172,12 +152,14 @@ fs_flow_flush(struct rte_eth_dev *dev,
 	uint8_t i;
 	int ret;
 
+	fs_lock(dev, 0);
 	FOREACH_SUBDEV_STATE(sdev, i, dev, DEV_ACTIVE) {
 		DEBUG("Calling rte_flow_flush on sub_device %d", i);
 		ret = rte_flow_flush(PORT_ID(sdev), error);
-		if (ret) {
+		if ((ret = fs_err(sdev, ret))) {
 			ERROR("Operation rte_flow_flush failed for sub_device %d"
 			      " with error %d", i, ret);
+			fs_unlock(dev, 0);
 			return ret;
 		}
 	}
@@ -185,6 +167,7 @@ fs_flow_flush(struct rte_eth_dev *dev,
 		TAILQ_REMOVE(&PRIV(dev)->flow_list, flow, next);
 		fs_flow_release(&flow);
 	}
+	fs_unlock(dev, 0);
 	return 0;
 }
 
@@ -197,11 +180,19 @@ fs_flow_query(struct rte_eth_dev *dev,
 {
 	struct sub_device *sdev;
 
+	fs_lock(dev, 0);
 	sdev = TX_SUBDEV(dev);
 	if (sdev != NULL) {
-		return rte_flow_query(PORT_ID(sdev),
-				flow->flows[SUB_ID(sdev)], type, arg, error);
+		int ret = rte_flow_query(PORT_ID(sdev),
+					 flow->flows[SUB_ID(sdev)],
+					 type, arg, error);
+
+		if ((ret = fs_err(sdev, ret))) {
+			fs_unlock(dev, 0);
+			return ret;
+		}
 	}
+	fs_unlock(dev, 0);
 	WARN("No active sub_device to query about its flow");
 	return -1;
 }
@@ -215,6 +206,7 @@ fs_flow_isolate(struct rte_eth_dev *dev,
 	uint8_t i;
 	int ret;
 
+	fs_lock(dev, 0);
 	FOREACH_SUBDEV(sdev, i, dev) {
 		if (sdev->state < DEV_PROBED)
 			continue;
@@ -223,14 +215,16 @@ fs_flow_isolate(struct rte_eth_dev *dev,
 			WARN("flow isolation mode of sub_device %d in incoherent state.",
 				i);
 		ret = rte_flow_isolate(PORT_ID(sdev), set, error);
-		if (ret) {
+		if ((ret = fs_err(sdev, ret))) {
 			ERROR("Operation rte_flow_isolate failed for sub_device %d"
 			      " with error %d", i, ret);
+			fs_unlock(dev, 0);
 			return ret;
 		}
 		sdev->flow_isolated = set;
 	}
 	PRIV(dev)->flow_isolated = set;
+	fs_unlock(dev, 0);
 	return 0;
 }
 
diff --git a/drivers/net/failsafe/failsafe_intr.c b/drivers/net/failsafe/failsafe_intr.c
new file mode 100644
index 00000000..6b7f9c1a
--- /dev/null
+++ b/drivers/net/failsafe/failsafe_intr.c
@@ -0,0 +1,536 @@
+/* SPDX-License-Identifier: BSD-3-Clause
+ * Copyright 2018 Mellanox Technologies, Ltd.
+ */
+
+/**
+ * @file
+ * Interrupts handling for failsafe driver.
+ */
+
+#if defined(LINUX)
+#include <sys/epoll.h>
+#endif
+#include <unistd.h>
+
+#include <rte_alarm.h>
+#include <rte_config.h>
+#include <rte_errno.h>
+#include <rte_ethdev.h>
+#include <rte_interrupts.h>
+#include <rte_io.h>
+#include <rte_service_component.h>
+
+#include "failsafe_private.h"
+
+#define NUM_RX_PROXIES (FAILSAFE_MAX_ETHPORTS * RTE_MAX_RXTX_INTR_VEC_ID)
+
+
+/**
+ * Open an epoll file descriptor.
+ *
+ * @param flags
+ *   Flags for defining epoll behavior.
+ * @return
+ *   0 on success, negative errno value otherwise.
+ */
+static int
+fs_epoll_create1(int flags)
+{
+#if defined(LINUX)
+	return epoll_create1(flags);
+#elif defined(BSD)
+	RTE_SET_USED(flags);
+	return -ENOTSUP;
+#endif
+}
+
+/**
+ * Install failsafe Rx event proxy service.
+ * The Rx event proxy is the service that listens to Rx events from the
+ * subdevices and triggers failsafe Rx events accordingly.
+ *
+ * @param priv
+ *   Pointer to failsafe private structure.
+ * @return
+ *   0 on success, negative errno value otherwise.
+ */
+static int
+fs_rx_event_proxy_routine(void *data)
+{
+	struct fs_priv *priv;
+	struct rxq *rxq;
+	struct rte_epoll_event *events;
+	uint64_t u64;
+	int i, n;
+	int rc = 0;
+
+	u64 = 1;
+	priv = data;
+	events = priv->rxp.evec;
+	n = rte_epoll_wait(priv->rxp.efd, events, NUM_RX_PROXIES, -1);
+	for (i = 0; i < n; i++) {
+		rxq = events[i].epdata.data;
+		if (rxq->enable_events && rxq->event_fd != -1) {
+			if (write(rxq->event_fd, &u64, sizeof(u64)) !=
+			    sizeof(u64)) {
+				ERROR("Failed to proxy Rx event to socket %d",
+				       rxq->event_fd);
+				rc = -EIO;
+			}
+		}
+	}
+	return rc;
+}
+
+/**
+ * Uninstall failsafe Rx event proxy service.
+ *
+ * @param priv
+ *   Pointer to failsafe private structure.
+ */
+static void
+fs_rx_event_proxy_service_uninstall(struct fs_priv *priv)
+{
+	/* Unregister the event service. */
+	switch (priv->rxp.sstate) {
+	case SS_RUNNING:
+		rte_service_map_lcore_set(priv->rxp.sid, priv->rxp.scid, 0);
+		/* fall through */
+	case SS_READY:
+		rte_service_runstate_set(priv->rxp.sid, 0);
+		rte_service_set_stats_enable(priv->rxp.sid, 0);
+		rte_service_component_runstate_set(priv->rxp.sid, 0);
+		/* fall through */
+	case SS_REGISTERED:
+		rte_service_component_unregister(priv->rxp.sid);
+		/* fall through */
+	default:
+		break;
+	}
+}
+
+/**
+ * Install the failsafe Rx event proxy service.
+ *
+ * @param priv
+ *   Pointer to failsafe private structure.
+ * @return
+ *   0 on success, negative errno value otherwise.
+ */
+static int
+fs_rx_event_proxy_service_install(struct fs_priv *priv)
+{
+	struct rte_service_spec service;
+	int32_t num_service_cores;
+	int ret = 0;
+
+	num_service_cores = rte_service_lcore_count();
+	if (num_service_cores <= 0) {
+		ERROR("Failed to install Rx interrupts, "
+		      "no service core found");
+		return -ENOTSUP;
+	}
+	/* prepare service info */
+	memset(&service, 0, sizeof(struct rte_service_spec));
+	snprintf(service.name, sizeof(service.name), "%s_Rx_service",
+		 priv->dev->data->name);
+	service.socket_id = priv->dev->data->numa_node;
+	service.callback = fs_rx_event_proxy_routine;
+	service.callback_userdata = priv;
+
+	if (priv->rxp.sstate == SS_NO_SERVICE) {
+		uint32_t service_core_list[num_service_cores];
+
+		/* get a service core to work with */
+		ret = rte_service_lcore_list(service_core_list,
+					     num_service_cores);
+		if (ret <= 0) {
+			ERROR("Failed to install Rx interrupts, "
+			      "service core list empty or corrupted");
+			return -ENOTSUP;
+		}
+		priv->rxp.scid = service_core_list[0];
+		ret = rte_service_lcore_add(priv->rxp.scid);
+		if (ret && ret != -EALREADY) {
+			ERROR("Failed adding service core");
+			return ret;
+		}
+		/* service core may be in "stopped" state, start it */
+		ret = rte_service_lcore_start(priv->rxp.scid);
+		if (ret && (ret != -EALREADY)) {
+			ERROR("Failed to install Rx interrupts, "
+			      "service core not started");
+			return ret;
+		}
+		/* register our service */
+		int32_t ret = rte_service_component_register(&service,
+							     &priv->rxp.sid);
+		if (ret) {
+			ERROR("service register() failed");
+			return -ENOEXEC;
+		}
+		priv->rxp.sstate = SS_REGISTERED;
+		/* run the service */
+		ret = rte_service_component_runstate_set(priv->rxp.sid, 1);
+		if (ret < 0) {
+			ERROR("Failed Setting component runstate\n");
+			return ret;
+		}
+		ret = rte_service_set_stats_enable(priv->rxp.sid, 1);
+		if (ret < 0) {
+			ERROR("Failed enabling stats\n");
+			return ret;
+		}
+		ret = rte_service_runstate_set(priv->rxp.sid, 1);
+		if (ret < 0) {
+			ERROR("Failed to run service\n");
+			return ret;
+		}
+		priv->rxp.sstate = SS_READY;
+		/* map the service with the service core */
+		ret = rte_service_map_lcore_set(priv->rxp.sid,
+						priv->rxp.scid, 1);
+		if (ret) {
+			ERROR("Failed to install Rx interrupts, "
+			      "could not map service core");
+			return ret;
+		}
+		priv->rxp.sstate = SS_RUNNING;
+	}
+	return 0;
+}
+
+/**
+ * Install failsafe Rx event proxy subsystem.
+ * This is the way the failsafe PMD generates Rx events on behalf of its
+ * subdevices.
+ *
+ * @param priv
+ *   Pointer to failsafe private structure.
+ * @return
+ *   0 on success, negative errno value otherwise and rte_errno is set.
+ */
+static int
+fs_rx_event_proxy_install(struct fs_priv *priv)
+{
+	int rc = 0;
+
+	/*
+	 * Create the epoll fd and event vector for the proxy service to
+	 * wait on for Rx events generated by the subdevices.
+	 */
+	priv->rxp.efd = fs_epoll_create1(0);
+	if (priv->rxp.efd < 0) {
+		rte_errno = errno;
+		ERROR("Failed to create epoll,"
+		      " Rx interrupts will not be supported");
+		return -rte_errno;
+	}
+	priv->rxp.evec = calloc(NUM_RX_PROXIES, sizeof(*priv->rxp.evec));
+	if (priv->rxp.evec == NULL) {
+		ERROR("Failed to allocate memory for event vectors,"
+		      " Rx interrupts will not be supported");
+		rc = -ENOMEM;
+		goto error;
+	}
+	rc = fs_rx_event_proxy_service_install(priv);
+	if (rc < 0)
+		goto error;
+	return 0;
+error:
+	if (priv->rxp.efd >= 0) {
+		close(priv->rxp.efd);
+		priv->rxp.efd = -1;
+	}
+	if (priv->rxp.evec != NULL) {
+		free(priv->rxp.evec);
+		priv->rxp.evec = NULL;
+	}
+	rte_errno = -rc;
+	return rc;
+}
+
+/**
+ * RX Interrupt control per subdevice.
+ *
+ * @param sdev
+ *   Pointer to sub-device structure.
+ * @param op
+ *   The operation be performed for the vector.
+ *   Operation type of {RTE_INTR_EVENT_ADD, RTE_INTR_EVENT_DEL}.
+ * @return
+ *   - On success, zero.
+ *   - On failure, a negative value.
+ */
+static int
+failsafe_eth_rx_intr_ctl_subdevice(struct sub_device *sdev, int op)
+{
+	struct rte_eth_dev *dev;
+	struct rte_eth_dev *fsdev;
+	int epfd;
+	uint16_t pid;
+	uint16_t qid;
+	struct rxq *fsrxq;
+	int rc;
+	int ret = 0;
+
+	if (sdev == NULL || (ETH(sdev) == NULL) ||
+	    sdev->fs_dev == NULL || (PRIV(sdev->fs_dev) == NULL)) {
+		ERROR("Called with invalid arguments");
+		return -EINVAL;
+	}
+	dev = ETH(sdev);
+	fsdev = sdev->fs_dev;
+	epfd = PRIV(sdev->fs_dev)->rxp.efd;
+	pid = PORT_ID(sdev);
+
+	if (epfd <= 0) {
+		if (op == RTE_INTR_EVENT_ADD) {
+			ERROR("Proxy events are not initialized");
+			return -EBADF;
+		} else {
+			return 0;
+		}
+	}
+	if (dev->data->nb_rx_queues > fsdev->data->nb_rx_queues) {
+		ERROR("subdevice has too many queues,"
+		      " Interrupts will not be enabled");
+			return -E2BIG;
+	}
+	for (qid = 0; qid < dev->data->nb_rx_queues; qid++) {
+		fsrxq = fsdev->data->rx_queues[qid];
+		rc = rte_eth_dev_rx_intr_ctl_q(pid, qid, epfd,
+					       op, (void *)fsrxq);
+		if (rc) {
+			ERROR("rte_eth_dev_rx_intr_ctl_q failed for "
+			      "port %d  queue %d, epfd %d, error %d",
+			      pid, qid, epfd, rc);
+			ret = rc;
+		}
+	}
+	return ret;
+}
+
+/**
+ * Install Rx interrupts subsystem for a subdevice.
+ * This is a support for dynamically adding subdevices.
+ *
+ * @param sdev
+ *   Pointer to subdevice structure.
+ *
+ * @return
+ *   0 on success, negative errno value otherwise and rte_errno is set.
+ */
+int failsafe_rx_intr_install_subdevice(struct sub_device *sdev)
+{
+	int rc;
+	int qid;
+	struct rte_eth_dev *fsdev;
+	struct rxq **rxq;
+	const struct rte_intr_conf *const intr_conf =
+				&ETH(sdev)->data->dev_conf.intr_conf;
+
+	fsdev = sdev->fs_dev;
+	rxq = (struct rxq **)fsdev->data->rx_queues;
+	if (intr_conf->rxq == 0)
+		return 0;
+	rc = failsafe_eth_rx_intr_ctl_subdevice(sdev, RTE_INTR_EVENT_ADD);
+	if (rc)
+		return rc;
+	/* enable interrupts on already-enabled queues */
+	for (qid = 0; qid < ETH(sdev)->data->nb_rx_queues; qid++) {
+		if (rxq[qid]->enable_events) {
+			int ret = rte_eth_dev_rx_intr_enable(PORT_ID(sdev),
+							     qid);
+			if (ret && (ret != -ENOTSUP)) {
+				ERROR("Failed to enable interrupts on "
+				      "port %d queue %d", PORT_ID(sdev), qid);
+				rc = ret;
+			}
+		}
+	}
+	return rc;
+}
+
+/**
+ * Uninstall Rx interrupts subsystem for a subdevice.
+ * This is a support for dynamically removing subdevices.
+ *
+ * @param sdev
+ *   Pointer to subdevice structure.
+ *
+ * @return
+ *   0 on success, negative errno value otherwise and rte_errno is set.
+ */
+void failsafe_rx_intr_uninstall_subdevice(struct sub_device *sdev)
+{
+	int qid;
+	struct rte_eth_dev *fsdev;
+	struct rxq *fsrxq;
+
+	fsdev = sdev->fs_dev;
+	for (qid = 0; qid < ETH(sdev)->data->nb_rx_queues; qid++) {
+		if (qid < fsdev->data->nb_rx_queues) {
+			fsrxq = fsdev->data->rx_queues[qid];
+			if (fsrxq->enable_events)
+				rte_eth_dev_rx_intr_disable(PORT_ID(sdev),
+							    qid);
+		}
+	}
+	failsafe_eth_rx_intr_ctl_subdevice(sdev, RTE_INTR_EVENT_DEL);
+}
+
+/**
+ * Uninstall failsafe Rx event proxy.
+ *
+ * @param priv
+ *   Pointer to failsafe private structure.
+ */
+static void
+fs_rx_event_proxy_uninstall(struct fs_priv *priv)
+{
+	fs_rx_event_proxy_service_uninstall(priv);
+	if (priv->rxp.evec != NULL) {
+		free(priv->rxp.evec);
+		priv->rxp.evec = NULL;
+	}
+	if (priv->rxp.efd > 0) {
+		close(priv->rxp.efd);
+		priv->rxp.efd = -1;
+	}
+}
+
+/**
+ * Uninstall failsafe interrupt vector.
+ *
+ * @param priv
+ *   Pointer to failsafe private structure.
+ */
+static void
+fs_rx_intr_vec_uninstall(struct fs_priv *priv)
+{
+	struct rte_intr_handle *intr_handle;
+
+	intr_handle = &priv->intr_handle;
+	if (intr_handle->intr_vec != NULL) {
+		free(intr_handle->intr_vec);
+		intr_handle->intr_vec = NULL;
+	}
+	intr_handle->nb_efd = 0;
+}
+
+/**
+ * Installs failsafe interrupt vector to be registered with EAL later on.
+ *
+ * @param priv
+ *   Pointer to failsafe private structure.
+ *
+ * @return
+ *   0 on success, negative errno value otherwise and rte_errno is set.
+ */
+static int
+fs_rx_intr_vec_install(struct fs_priv *priv)
+{
+	unsigned int i;
+	unsigned int rxqs_n;
+	unsigned int n;
+	unsigned int count;
+	struct rte_intr_handle *intr_handle;
+
+	rxqs_n = priv->dev->data->nb_rx_queues;
+	n = RTE_MIN(rxqs_n, (uint32_t)RTE_MAX_RXTX_INTR_VEC_ID);
+	count = 0;
+	intr_handle = &priv->intr_handle;
+	RTE_ASSERT(intr_handle->intr_vec == NULL);
+	/* Allocate the interrupt vector of the failsafe Rx proxy interrupts */
+	intr_handle->intr_vec = malloc(n * sizeof(intr_handle->intr_vec[0]));
+	if (intr_handle->intr_vec == NULL) {
+		fs_rx_intr_vec_uninstall(priv);
+		rte_errno = ENOMEM;
+		ERROR("Failed to allocate memory for interrupt vector,"
+		      " Rx interrupts will not be supported");
+		return -rte_errno;
+	}
+	for (i = 0; i < n; i++) {
+		struct rxq *rxq = priv->dev->data->rx_queues[i];
+
+		/* Skip queues that cannot request interrupts. */
+		if (rxq == NULL || rxq->event_fd < 0) {
+			/* Use invalid intr_vec[] index to disable entry. */
+			intr_handle->intr_vec[i] =
+				RTE_INTR_VEC_RXTX_OFFSET +
+				RTE_MAX_RXTX_INTR_VEC_ID;
+			continue;
+		}
+		if (count >= RTE_MAX_RXTX_INTR_VEC_ID) {
+			rte_errno = E2BIG;
+			ERROR("Too many Rx queues for interrupt vector size"
+			      " (%d), Rx interrupts cannot be enabled",
+			      RTE_MAX_RXTX_INTR_VEC_ID);
+			fs_rx_intr_vec_uninstall(priv);
+			return -rte_errno;
+		}
+		intr_handle->intr_vec[i] = RTE_INTR_VEC_RXTX_OFFSET + count;
+		intr_handle->efds[count] = rxq->event_fd;
+		count++;
+	}
+	if (count == 0) {
+		fs_rx_intr_vec_uninstall(priv);
+	} else {
+		intr_handle->nb_efd = count;
+		intr_handle->efd_counter_size = sizeof(uint64_t);
+	}
+	return 0;
+}
+
+
+/**
+ * Uninstall failsafe Rx interrupts subsystem.
+ *
+ * @param priv
+ *   Pointer to private structure.
+ *
+ * @return
+ *   0 on success, negative errno value otherwise and rte_errno is set.
+ */
+void
+failsafe_rx_intr_uninstall(struct rte_eth_dev *dev)
+{
+	struct fs_priv *priv;
+	struct rte_intr_handle *intr_handle;
+
+	priv = PRIV(dev);
+	intr_handle = &priv->intr_handle;
+	rte_intr_free_epoll_fd(intr_handle);
+	fs_rx_event_proxy_uninstall(priv);
+	fs_rx_intr_vec_uninstall(priv);
+	dev->intr_handle = NULL;
+}
+
+/**
+ * Install failsafe Rx interrupts subsystem.
+ *
+ * @param priv
+ *   Pointer to private structure.
+ *
+ * @return
+ *   0 on success, negative errno value otherwise and rte_errno is set.
+ */
+int
+failsafe_rx_intr_install(struct rte_eth_dev *dev)
+{
+	struct fs_priv *priv = PRIV(dev);
+	const struct rte_intr_conf *const intr_conf =
+			&priv->dev->data->dev_conf.intr_conf;
+
+	if (intr_conf->rxq == 0 || dev->intr_handle != NULL)
+		return 0;
+	if (fs_rx_intr_vec_install(priv) < 0)
+		return -rte_errno;
+	if (fs_rx_event_proxy_install(priv) < 0) {
+		fs_rx_intr_vec_uninstall(priv);
+		return -rte_errno;
+	}
+	dev->intr_handle = &priv->intr_handle;
+	return 0;
+}
diff --git a/drivers/net/failsafe/failsafe_ops.c b/drivers/net/failsafe/failsafe_ops.c
index e16a5903..057e435c 100644
--- a/drivers/net/failsafe/failsafe_ops.c
+++ b/drivers/net/failsafe/failsafe_ops.c
@@ -1,41 +1,15 @@
-/*-
- *   BSD LICENSE
- *
- *   Copyright 2017 6WIND S.A.
- *   Copyright 2017 Mellanox.
- *
- *   Redistribution and use in source and binary forms, with or without
- *   modification, are permitted provided that the following conditions
- *   are met:
- *
- *     * Redistributions of source code must retain the above copyright
- *       notice, this list of conditions and the following disclaimer.
- *     * Redistributions in binary form must reproduce the above copyright
- *       notice, this list of conditions and the following disclaimer in
- *       the documentation and/or other materials provided with the
- *       distribution.
- *     * Neither the name of 6WIND S.A. nor the names of its
- *       contributors may be used to endorse or promote products derived
- *       from this software without specific prior written permission.
- *
- *   THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
- *   "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
- *   LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
- *   A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
- *   OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
- *   SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
- *   LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
- *   DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
- *   THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
- *   (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
- *   OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+/* SPDX-License-Identifier: BSD-3-Clause
+ * Copyright 2017 6WIND S.A.
+ * Copyright 2017 Mellanox.
  */
 
+#include <stdbool.h>
 #include <stdint.h>
+#include <unistd.h>
 
 #include <rte_debug.h>
 #include <rte_atomic.h>
-#include <rte_ethdev.h>
+#include <rte_ethdev_driver.h>
 #include <rte_malloc.h>
 #include <rte_flow.h>
 #include <rte_cycles.h>
@@ -71,12 +45,43 @@ static struct rte_eth_dev_info default_infos = {
 	 */
 	.rx_offload_capa =
 		DEV_RX_OFFLOAD_VLAN_STRIP |
+		DEV_RX_OFFLOAD_IPV4_CKSUM |
+		DEV_RX_OFFLOAD_UDP_CKSUM |
+		DEV_RX_OFFLOAD_TCP_CKSUM |
+		DEV_RX_OFFLOAD_TCP_LRO |
 		DEV_RX_OFFLOAD_QINQ_STRIP |
+		DEV_RX_OFFLOAD_OUTER_IPV4_CKSUM |
+		DEV_RX_OFFLOAD_MACSEC_STRIP |
+		DEV_RX_OFFLOAD_HEADER_SPLIT |
+		DEV_RX_OFFLOAD_VLAN_FILTER |
+		DEV_RX_OFFLOAD_VLAN_EXTEND |
+		DEV_RX_OFFLOAD_JUMBO_FRAME |
+		DEV_RX_OFFLOAD_CRC_STRIP |
+		DEV_RX_OFFLOAD_SCATTER |
+		DEV_RX_OFFLOAD_TIMESTAMP |
+		DEV_RX_OFFLOAD_SECURITY,
+	.rx_queue_offload_capa =
+		DEV_RX_OFFLOAD_VLAN_STRIP |
 		DEV_RX_OFFLOAD_IPV4_CKSUM |
 		DEV_RX_OFFLOAD_UDP_CKSUM |
 		DEV_RX_OFFLOAD_TCP_CKSUM |
-		DEV_RX_OFFLOAD_TCP_LRO,
-	.tx_offload_capa = 0x0,
+		DEV_RX_OFFLOAD_TCP_LRO |
+		DEV_RX_OFFLOAD_QINQ_STRIP |
+		DEV_RX_OFFLOAD_OUTER_IPV4_CKSUM |
+		DEV_RX_OFFLOAD_MACSEC_STRIP |
+		DEV_RX_OFFLOAD_HEADER_SPLIT |
+		DEV_RX_OFFLOAD_VLAN_FILTER |
+		DEV_RX_OFFLOAD_VLAN_EXTEND |
+		DEV_RX_OFFLOAD_JUMBO_FRAME |
+		DEV_RX_OFFLOAD_CRC_STRIP |
+		DEV_RX_OFFLOAD_SCATTER |
+		DEV_RX_OFFLOAD_TIMESTAMP |
+		DEV_RX_OFFLOAD_SECURITY,
+	.tx_offload_capa =
+		DEV_TX_OFFLOAD_MULTI_SEGS |
+		DEV_TX_OFFLOAD_IPV4_CKSUM |
+		DEV_TX_OFFLOAD_UDP_CKSUM |
+		DEV_TX_OFFLOAD_TCP_CKSUM,
 	.flow_type_rss_offloads = 0x0,
 };
 
@@ -84,15 +89,29 @@ static int
 fs_dev_configure(struct rte_eth_dev *dev)
 {
 	struct sub_device *sdev;
+	uint64_t supp_tx_offloads;
+	uint64_t tx_offloads;
 	uint8_t i;
 	int ret;
 
+	fs_lock(dev, 0);
+	supp_tx_offloads = PRIV(dev)->infos.tx_offload_capa;
+	tx_offloads = dev->data->dev_conf.txmode.offloads;
+	if ((tx_offloads & supp_tx_offloads) != tx_offloads) {
+		rte_errno = ENOTSUP;
+		ERROR("Some Tx offloads are not supported, "
+		      "requested 0x%" PRIx64 " supported 0x%" PRIx64,
+		      tx_offloads, supp_tx_offloads);
+		fs_unlock(dev, 0);
+		return -rte_errno;
+	}
 	FOREACH_SUBDEV(sdev, i, dev) {
 		int rmv_interrupt = 0;
 		int lsc_interrupt = 0;
 		int lsc_enabled;
 
-		if (sdev->state != DEV_PROBED)
+		if (sdev->state != DEV_PROBED &&
+		    !(PRIV(dev)->alarm_lock == 0 && sdev->state == DEV_ACTIVE))
 			continue;
 
 		rmv_interrupt = ETH(sdev)->data->dev_flags &
@@ -115,13 +134,15 @@ fs_dev_configure(struct rte_eth_dev *dev)
 			dev->data->dev_conf.intr_conf.lsc = 0;
 		}
 		DEBUG("Configuring sub-device %d", i);
-		sdev->remove = 0;
 		ret = rte_eth_dev_configure(PORT_ID(sdev),
 					dev->data->nb_rx_queues,
 					dev->data->nb_tx_queues,
 					&dev->data->dev_conf);
 		if (ret) {
+			if (!fs_err(sdev, ret))
+				continue;
 			ERROR("Could not configure sub_device %d", i);
+			fs_unlock(dev, 0);
 			return ret;
 		}
 		if (rmv_interrupt) {
@@ -148,6 +169,7 @@ fs_dev_configure(struct rte_eth_dev *dev)
 	}
 	if (PRIV(dev)->state < DEV_ACTIVE)
 		PRIV(dev)->state = DEV_ACTIVE;
+	fs_unlock(dev, 0);
 	return 0;
 }
 
@@ -158,18 +180,37 @@ fs_dev_start(struct rte_eth_dev *dev)
 	uint8_t i;
 	int ret;
 
+	fs_lock(dev, 0);
+	ret = failsafe_rx_intr_install(dev);
+	if (ret) {
+		fs_unlock(dev, 0);
+		return ret;
+	}
 	FOREACH_SUBDEV(sdev, i, dev) {
 		if (sdev->state != DEV_ACTIVE)
 			continue;
 		DEBUG("Starting sub_device %d", i);
 		ret = rte_eth_dev_start(PORT_ID(sdev));
-		if (ret)
+		if (ret) {
+			if (!fs_err(sdev, ret))
+				continue;
+			fs_unlock(dev, 0);
+			return ret;
+		}
+		ret = failsafe_rx_intr_install_subdevice(sdev);
+		if (ret) {
+			if (!fs_err(sdev, ret))
+				continue;
+			rte_eth_dev_stop(PORT_ID(sdev));
+			fs_unlock(dev, 0);
 			return ret;
+		}
 		sdev->state = DEV_STARTED;
 	}
 	if (PRIV(dev)->state < DEV_STARTED)
 		PRIV(dev)->state = DEV_STARTED;
 	fs_switch_dev(dev, NULL);
+	fs_unlock(dev, 0);
 	return 0;
 }
 
@@ -179,11 +220,15 @@ fs_dev_stop(struct rte_eth_dev *dev)
 	struct sub_device *sdev;
 	uint8_t i;
 
+	fs_lock(dev, 0);
 	PRIV(dev)->state = DEV_STARTED - 1;
 	FOREACH_SUBDEV_STATE(sdev, i, dev, DEV_STARTED) {
 		rte_eth_dev_stop(PORT_ID(sdev));
+		failsafe_rx_intr_uninstall_subdevice(sdev);
 		sdev->state = DEV_STARTED - 1;
 	}
+	failsafe_rx_intr_uninstall(dev);
+	fs_unlock(dev, 0);
 }
 
 static int
@@ -193,15 +238,18 @@ fs_dev_set_link_up(struct rte_eth_dev *dev)
 	uint8_t i;
 	int ret;
 
+	fs_lock(dev, 0);
 	FOREACH_SUBDEV_STATE(sdev, i, dev, DEV_ACTIVE) {
 		DEBUG("Calling rte_eth_dev_set_link_up on sub_device %d", i);
 		ret = rte_eth_dev_set_link_up(PORT_ID(sdev));
-		if (ret) {
+		if ((ret = fs_err(sdev, ret))) {
 			ERROR("Operation rte_eth_dev_set_link_up failed for sub_device %d"
 			      " with error %d", i, ret);
+			fs_unlock(dev, 0);
 			return ret;
 		}
 	}
+	fs_unlock(dev, 0);
 	return 0;
 }
 
@@ -212,15 +260,18 @@ fs_dev_set_link_down(struct rte_eth_dev *dev)
 	uint8_t i;
 	int ret;
 
+	fs_lock(dev, 0);
 	FOREACH_SUBDEV_STATE(sdev, i, dev, DEV_ACTIVE) {
 		DEBUG("Calling rte_eth_dev_set_link_down on sub_device %d", i);
 		ret = rte_eth_dev_set_link_down(PORT_ID(sdev));
-		if (ret) {
+		if ((ret = fs_err(sdev, ret))) {
 			ERROR("Operation rte_eth_dev_set_link_down failed for sub_device %d"
 			      " with error %d", i, ret);
+			fs_unlock(dev, 0);
 			return ret;
 		}
 	}
+	fs_unlock(dev, 0);
 	return 0;
 }
 
@@ -231,6 +282,7 @@ fs_dev_close(struct rte_eth_dev *dev)
 	struct sub_device *sdev;
 	uint8_t i;
 
+	fs_lock(dev, 0);
 	failsafe_hotplug_alarm_cancel(dev);
 	if (PRIV(dev)->state == DEV_STARTED)
 		dev->dev_ops->dev_stop(dev);
@@ -241,6 +293,26 @@ fs_dev_close(struct rte_eth_dev *dev)
 		sdev->state = DEV_ACTIVE - 1;
 	}
 	fs_dev_free_queues(dev);
+	fs_unlock(dev, 0);
+}
+
+static bool
+fs_rxq_offloads_valid(struct rte_eth_dev *dev, uint64_t offloads)
+{
+	uint64_t port_offloads;
+	uint64_t queue_supp_offloads;
+	uint64_t port_supp_offloads;
+
+	port_offloads = dev->data->dev_conf.rxmode.offloads;
+	queue_supp_offloads = PRIV(dev)->infos.rx_queue_offload_capa;
+	port_supp_offloads = PRIV(dev)->infos.rx_offload_capa;
+	if ((offloads & (queue_supp_offloads | port_supp_offloads)) !=
+	     offloads)
+		return false;
+	/* Verify we have no conflict with port offloads */
+	if ((port_offloads ^ offloads) & port_supp_offloads)
+		return false;
+	return true;
 }
 
 static void
@@ -255,11 +327,15 @@ fs_rx_queue_release(void *queue)
 		return;
 	rxq = queue;
 	dev = rxq->priv->dev;
+	fs_lock(dev, 0);
+	if (rxq->event_fd > 0)
+		close(rxq->event_fd);
 	FOREACH_SUBDEV_STATE(sdev, i, dev, DEV_ACTIVE)
 		SUBOPS(sdev, rx_queue_release)
 			(ETH(sdev)->data->rx_queues[rxq->qid]);
 	dev->data->rx_queues[rxq->qid] = NULL;
 	rte_free(rxq);
+	fs_unlock(dev, 0);
 }
 
 static int
@@ -270,22 +346,48 @@ fs_rx_queue_setup(struct rte_eth_dev *dev,
 		const struct rte_eth_rxconf *rx_conf,
 		struct rte_mempool *mb_pool)
 {
+	/*
+	 * FIXME: Add a proper interface in rte_eal_interrupts for
+	 * allocating eventfd as an interrupt vector.
+	 * For the time being, fake as if we are using MSIX interrupts,
+	 * this will cause rte_intr_efd_enable to allocate an eventfd for us.
+	 */
+	struct rte_intr_handle intr_handle = {
+		.type = RTE_INTR_HANDLE_VFIO_MSIX,
+		.efds = { -1, },
+	};
 	struct sub_device *sdev;
 	struct rxq *rxq;
 	uint8_t i;
 	int ret;
 
+	fs_lock(dev, 0);
 	rxq = dev->data->rx_queues[rx_queue_id];
 	if (rxq != NULL) {
 		fs_rx_queue_release(rxq);
 		dev->data->rx_queues[rx_queue_id] = NULL;
 	}
+	/* Verify application offloads are valid for our port and queue. */
+	if (fs_rxq_offloads_valid(dev, rx_conf->offloads) == false) {
+		rte_errno = ENOTSUP;
+		ERROR("Rx queue offloads 0x%" PRIx64
+		      " don't match port offloads 0x%" PRIx64
+		      " or supported offloads 0x%" PRIx64,
+		      rx_conf->offloads,
+		      dev->data->dev_conf.rxmode.offloads,
+		      PRIV(dev)->infos.rx_offload_capa |
+		      PRIV(dev)->infos.rx_queue_offload_capa);
+		fs_unlock(dev, 0);
+		return -rte_errno;
+	}
 	rxq = rte_zmalloc(NULL,
 			  sizeof(*rxq) +
 			  sizeof(rte_atomic64_t) * PRIV(dev)->subs_tail,
 			  RTE_CACHE_LINE_SIZE);
-	if (rxq == NULL)
+	if (rxq == NULL) {
+		fs_unlock(dev, 0);
 		return -ENOMEM;
+	}
 	FOREACH_SUBDEV(sdev, i, dev)
 		rte_atomic64_init(&rxq->refcnt[i]);
 	rxq->qid = rx_queue_id;
@@ -294,23 +396,127 @@ fs_rx_queue_setup(struct rte_eth_dev *dev,
 	rxq->info.conf = *rx_conf;
 	rxq->info.nb_desc = nb_rx_desc;
 	rxq->priv = PRIV(dev);
+	rxq->sdev = PRIV(dev)->subs;
+	ret = rte_intr_efd_enable(&intr_handle, 1);
+	if (ret < 0) {
+		fs_unlock(dev, 0);
+		return ret;
+	}
+	rxq->event_fd = intr_handle.efds[0];
 	dev->data->rx_queues[rx_queue_id] = rxq;
 	FOREACH_SUBDEV_STATE(sdev, i, dev, DEV_ACTIVE) {
 		ret = rte_eth_rx_queue_setup(PORT_ID(sdev),
 				rx_queue_id,
 				nb_rx_desc, socket_id,
 				rx_conf, mb_pool);
-		if (ret) {
+		if ((ret = fs_err(sdev, ret))) {
 			ERROR("RX queue setup failed for sub_device %d", i);
 			goto free_rxq;
 		}
 	}
+	fs_unlock(dev, 0);
 	return 0;
 free_rxq:
 	fs_rx_queue_release(rxq);
+	fs_unlock(dev, 0);
 	return ret;
 }
 
+static int
+fs_rx_intr_enable(struct rte_eth_dev *dev, uint16_t idx)
+{
+	struct rxq *rxq;
+	struct sub_device *sdev;
+	uint8_t i;
+	int ret;
+	int rc = 0;
+
+	fs_lock(dev, 0);
+	if (idx >= dev->data->nb_rx_queues) {
+		rc = -EINVAL;
+		goto unlock;
+	}
+	rxq = dev->data->rx_queues[idx];
+	if (rxq == NULL || rxq->event_fd <= 0) {
+		rc = -EINVAL;
+		goto unlock;
+	}
+	/* Fail if proxy service is nor running. */
+	if (PRIV(dev)->rxp.sstate != SS_RUNNING) {
+		ERROR("failsafe interrupt services are not running");
+		rc = -EAGAIN;
+		goto unlock;
+	}
+	rxq->enable_events = 1;
+	FOREACH_SUBDEV_STATE(sdev, i, dev, DEV_ACTIVE) {
+		ret = rte_eth_dev_rx_intr_enable(PORT_ID(sdev), idx);
+		ret = fs_err(sdev, ret);
+		if (ret)
+			rc = ret;
+	}
+unlock:
+	fs_unlock(dev, 0);
+	if (rc)
+		rte_errno = -rc;
+	return rc;
+}
+
+static int
+fs_rx_intr_disable(struct rte_eth_dev *dev, uint16_t idx)
+{
+	struct rxq *rxq;
+	struct sub_device *sdev;
+	uint64_t u64;
+	uint8_t i;
+	int rc = 0;
+	int ret;
+
+	fs_lock(dev, 0);
+	if (idx >= dev->data->nb_rx_queues) {
+		rc = -EINVAL;
+		goto unlock;
+	}
+	rxq = dev->data->rx_queues[idx];
+	if (rxq == NULL || rxq->event_fd <= 0) {
+		rc = -EINVAL;
+		goto unlock;
+	}
+	rxq->enable_events = 0;
+	FOREACH_SUBDEV_STATE(sdev, i, dev, DEV_ACTIVE) {
+		ret = rte_eth_dev_rx_intr_disable(PORT_ID(sdev), idx);
+		ret = fs_err(sdev, ret);
+		if (ret)
+			rc = ret;
+	}
+	/* Clear pending events */
+	while (read(rxq->event_fd, &u64, sizeof(uint64_t)) >  0)
+		;
+unlock:
+	fs_unlock(dev, 0);
+	if (rc)
+		rte_errno = -rc;
+	return rc;
+}
+
+static bool
+fs_txq_offloads_valid(struct rte_eth_dev *dev, uint64_t offloads)
+{
+	uint64_t port_offloads;
+	uint64_t queue_supp_offloads;
+	uint64_t port_supp_offloads;
+
+	port_offloads = dev->data->dev_conf.txmode.offloads;
+	queue_supp_offloads = PRIV(dev)->infos.tx_queue_offload_capa;
+	port_supp_offloads = PRIV(dev)->infos.tx_offload_capa;
+	if ((offloads & (queue_supp_offloads | port_supp_offloads)) !=
+	     offloads)
+		return false;
+	/* Verify we have no conflict with port offloads */
+	if ((port_offloads ^ offloads) & port_supp_offloads)
+		return false;
+	return true;
+}
+
 static void
 fs_tx_queue_release(void *queue)
 {
@@ -323,11 +529,13 @@ fs_tx_queue_release(void *queue)
 		return;
 	txq = queue;
 	dev = txq->priv->dev;
+	fs_lock(dev, 0);
 	FOREACH_SUBDEV_STATE(sdev, i, dev, DEV_ACTIVE)
 		SUBOPS(sdev, tx_queue_release)
 			(ETH(sdev)->data->tx_queues[txq->qid]);
 	dev->data->tx_queues[txq->qid] = NULL;
 	rte_free(txq);
+	fs_unlock(dev, 0);
 }
 
 static int
@@ -342,17 +550,38 @@ fs_tx_queue_setup(struct rte_eth_dev *dev,
 	uint8_t i;
 	int ret;
 
+	fs_lock(dev, 0);
 	txq = dev->data->tx_queues[tx_queue_id];
 	if (txq != NULL) {
 		fs_tx_queue_release(txq);
 		dev->data->tx_queues[tx_queue_id] = NULL;
 	}
+	/*
+	 * Don't verify queue offloads for applications which
+	 * use the old API.
+	 */
+	if (tx_conf != NULL &&
+	    (tx_conf->txq_flags & ETH_TXQ_FLAGS_IGNORE) &&
+	    fs_txq_offloads_valid(dev, tx_conf->offloads) == false) {
+		rte_errno = ENOTSUP;
+		ERROR("Tx queue offloads 0x%" PRIx64
+		      " don't match port offloads 0x%" PRIx64
+		      " or supported offloads 0x%" PRIx64,
+		      tx_conf->offloads,
+		      dev->data->dev_conf.txmode.offloads,
+		      PRIV(dev)->infos.tx_offload_capa |
+		      PRIV(dev)->infos.tx_queue_offload_capa);
+		fs_unlock(dev, 0);
+		return -rte_errno;
+	}
 	txq = rte_zmalloc("ethdev TX queue",
 			  sizeof(*txq) +
 			  sizeof(rte_atomic64_t) * PRIV(dev)->subs_tail,
 			  RTE_CACHE_LINE_SIZE);
-	if (txq == NULL)
+	if (txq == NULL) {
+		fs_unlock(dev, 0);
 		return -ENOMEM;
+	}
 	FOREACH_SUBDEV(sdev, i, dev)
 		rte_atomic64_init(&txq->refcnt[i]);
 	txq->qid = tx_queue_id;
@@ -366,14 +595,16 @@ fs_tx_queue_setup(struct rte_eth_dev *dev,
 				tx_queue_id,
 				nb_tx_desc, socket_id,
 				tx_conf);
-		if (ret) {
+		if ((ret = fs_err(sdev, ret))) {
 			ERROR("TX queue setup failed for sub_device %d", i);
 			goto free_txq;
 		}
 	}
+	fs_unlock(dev, 0);
 	return 0;
 free_txq:
 	fs_tx_queue_release(txq);
+	fs_unlock(dev, 0);
 	return ret;
 }
 
@@ -400,8 +631,10 @@ fs_promiscuous_enable(struct rte_eth_dev *dev)
 	struct sub_device *sdev;
 	uint8_t i;
 
+	fs_lock(dev, 0);
 	FOREACH_SUBDEV_STATE(sdev, i, dev, DEV_ACTIVE)
 		rte_eth_promiscuous_enable(PORT_ID(sdev));
+	fs_unlock(dev, 0);
 }
 
 static void
@@ -410,8 +643,10 @@ fs_promiscuous_disable(struct rte_eth_dev *dev)
 	struct sub_device *sdev;
 	uint8_t i;
 
+	fs_lock(dev, 0);
 	FOREACH_SUBDEV_STATE(sdev, i, dev, DEV_ACTIVE)
 		rte_eth_promiscuous_disable(PORT_ID(sdev));
+	fs_unlock(dev, 0);
 }
 
 static void
@@ -420,8 +655,10 @@ fs_allmulticast_enable(struct rte_eth_dev *dev)
 	struct sub_device *sdev;
 	uint8_t i;
 
+	fs_lock(dev, 0);
 	FOREACH_SUBDEV_STATE(sdev, i, dev, DEV_ACTIVE)
 		rte_eth_allmulticast_enable(PORT_ID(sdev));
+	fs_unlock(dev, 0);
 }
 
 static void
@@ -430,8 +667,10 @@ fs_allmulticast_disable(struct rte_eth_dev *dev)
 	struct sub_device *sdev;
 	uint8_t i;
 
+	fs_lock(dev, 0);
 	FOREACH_SUBDEV_STATE(sdev, i, dev, DEV_ACTIVE)
 		rte_eth_allmulticast_disable(PORT_ID(sdev));
+	fs_unlock(dev, 0);
 }
 
 static int
@@ -442,12 +681,15 @@ fs_link_update(struct rte_eth_dev *dev,
 	uint8_t i;
 	int ret;
 
+	fs_lock(dev, 0);
 	FOREACH_SUBDEV_STATE(sdev, i, dev, DEV_ACTIVE) {
 		DEBUG("Calling link_update on sub_device %d", i);
 		ret = (SUBOPS(sdev, link_update))(ETH(sdev), wait_to_complete);
-		if (ret && ret != -1) {
+		if (ret && ret != -1 && sdev->remove == 0 &&
+		    rte_eth_dev_is_removed(PORT_ID(sdev)) == 0) {
 			ERROR("Link update failed for sub_device %d with error %d",
 			      i, ret);
+			fs_unlock(dev, 0);
 			return ret;
 		}
 	}
@@ -459,9 +701,11 @@ fs_link_update(struct rte_eth_dev *dev,
 		l2 = &ETH(TX_SUBDEV(dev))->data->dev_link;
 		if (memcmp(l1, l2, sizeof(*l1))) {
 			*l1 = *l2;
+			fs_unlock(dev, 0);
 			return 0;
 		}
 	}
+	fs_unlock(dev, 0);
 	return -1;
 }
 
@@ -469,25 +713,35 @@ static int
 fs_stats_get(struct rte_eth_dev *dev,
 	     struct rte_eth_stats *stats)
 {
+	struct rte_eth_stats backup;
 	struct sub_device *sdev;
 	uint8_t i;
 	int ret;
 
+	fs_lock(dev, 0);
 	rte_memcpy(stats, &PRIV(dev)->stats_accumulator, sizeof(*stats));
 	FOREACH_SUBDEV_STATE(sdev, i, dev, DEV_ACTIVE) {
 		struct rte_eth_stats *snapshot = &sdev->stats_snapshot.stats;
 		uint64_t *timestamp = &sdev->stats_snapshot.timestamp;
 
+		rte_memcpy(&backup, snapshot, sizeof(backup));
 		ret = rte_eth_stats_get(PORT_ID(sdev), snapshot);
 		if (ret) {
+			if (!fs_err(sdev, ret)) {
+				rte_memcpy(snapshot, &backup, sizeof(backup));
+				goto inc;
+			}
 			ERROR("Operation rte_eth_stats_get failed for sub_device %d with error %d",
 				  i, ret);
 			*timestamp = 0;
+			fs_unlock(dev, 0);
 			return ret;
 		}
 		*timestamp = rte_rdtsc();
+inc:
 		failsafe_stats_increment(stats, snapshot);
 	}
+	fs_unlock(dev, 0);
 	return 0;
 }
 
@@ -497,11 +751,13 @@ fs_stats_reset(struct rte_eth_dev *dev)
 	struct sub_device *sdev;
 	uint8_t i;
 
+	fs_lock(dev, 0);
 	FOREACH_SUBDEV_STATE(sdev, i, dev, DEV_ACTIVE) {
 		rte_eth_stats_reset(PORT_ID(sdev));
 		memset(&sdev->stats_snapshot, 0, sizeof(struct rte_eth_stats));
 	}
 	memset(&PRIV(dev)->stats_accumulator, 0, sizeof(struct rte_eth_stats));
+	fs_unlock(dev, 0);
 }
 
 /**
@@ -546,19 +802,26 @@ fs_dev_infos_get(struct rte_eth_dev *dev,
 		rte_memcpy(&PRIV(dev)->infos, &default_infos,
 			   sizeof(default_infos));
 	} else {
-		uint32_t rx_offload_capa;
+		uint64_t rx_offload_capa;
+		uint64_t rxq_offload_capa;
 
 		rx_offload_capa = default_infos.rx_offload_capa;
+		rxq_offload_capa = default_infos.rx_queue_offload_capa;
 		FOREACH_SUBDEV_STATE(sdev, i, dev, DEV_PROBED) {
 			rte_eth_dev_info_get(PORT_ID(sdev),
 					&PRIV(dev)->infos);
 			rx_offload_capa &= PRIV(dev)->infos.rx_offload_capa;
+			rxq_offload_capa &=
+					PRIV(dev)->infos.rx_queue_offload_capa;
 		}
 		sdev = TX_SUBDEV(dev);
 		rte_eth_dev_info_get(PORT_ID(sdev), &PRIV(dev)->infos);
 		PRIV(dev)->infos.rx_offload_capa = rx_offload_capa;
+		PRIV(dev)->infos.rx_queue_offload_capa = rxq_offload_capa;
 		PRIV(dev)->infos.tx_offload_capa &=
 					default_infos.tx_offload_capa;
+		PRIV(dev)->infos.tx_queue_offload_capa &=
+					default_infos.tx_queue_offload_capa;
 		PRIV(dev)->infos.flow_type_rss_offloads &=
 					default_infos.flow_type_rss_offloads;
 	}
@@ -570,14 +833,20 @@ fs_dev_supported_ptypes_get(struct rte_eth_dev *dev)
 {
 	struct sub_device *sdev;
 	struct rte_eth_dev *edev;
+	const uint32_t *ret;
 
+	fs_lock(dev, 0);
 	sdev = TX_SUBDEV(dev);
-	if (sdev == NULL)
-		return NULL;
+	if (sdev == NULL) {
+		ret = NULL;
+		goto unlock;
+	}
 	edev = ETH(sdev);
 	/* ENOTSUP: counts as no supported ptypes */
-	if (SUBOPS(sdev, dev_supported_ptypes_get) == NULL)
-		return NULL;
+	if (SUBOPS(sdev, dev_supported_ptypes_get) == NULL) {
+		ret = NULL;
+		goto unlock;
+	}
 	/*
 	 * The API does not permit to do a clean AND of all ptypes,
 	 * It is also incomplete by design and we do not really care
@@ -585,7 +854,10 @@ fs_dev_supported_ptypes_get(struct rte_eth_dev *dev)
 	 * We just return the ptypes of the device of highest
 	 * priority, usually the PREFERRED device.
 	 */
-	return SUBOPS(sdev, dev_supported_ptypes_get)(edev);
+	ret = SUBOPS(sdev, dev_supported_ptypes_get)(edev);
+unlock:
+	fs_unlock(dev, 0);
+	return ret;
 }
 
 static int
@@ -595,15 +867,18 @@ fs_mtu_set(struct rte_eth_dev *dev, uint16_t mtu)
 	uint8_t i;
 	int ret;
 
+	fs_lock(dev, 0);
 	FOREACH_SUBDEV_STATE(sdev, i, dev, DEV_ACTIVE) {
 		DEBUG("Calling rte_eth_dev_set_mtu on sub_device %d", i);
 		ret = rte_eth_dev_set_mtu(PORT_ID(sdev), mtu);
-		if (ret) {
+		if ((ret = fs_err(sdev, ret))) {
 			ERROR("Operation rte_eth_dev_set_mtu failed for sub_device %d with error %d",
 			      i, ret);
+			fs_unlock(dev, 0);
 			return ret;
 		}
 	}
+	fs_unlock(dev, 0);
 	return 0;
 }
 
@@ -614,15 +889,18 @@ fs_vlan_filter_set(struct rte_eth_dev *dev, uint16_t vlan_id, int on)
 	uint8_t i;
 	int ret;
 
+	fs_lock(dev, 0);
 	FOREACH_SUBDEV_STATE(sdev, i, dev, DEV_ACTIVE) {
 		DEBUG("Calling rte_eth_dev_vlan_filter on sub_device %d", i);
 		ret = rte_eth_dev_vlan_filter(PORT_ID(sdev), vlan_id, on);
-		if (ret) {
+		if ((ret = fs_err(sdev, ret))) {
 			ERROR("Operation rte_eth_dev_vlan_filter failed for sub_device %d"
 			      " with error %d", i, ret);
+			fs_unlock(dev, 0);
 			return ret;
 		}
 	}
+	fs_unlock(dev, 0);
 	return 0;
 }
 
@@ -631,13 +909,22 @@ fs_flow_ctrl_get(struct rte_eth_dev *dev,
 		struct rte_eth_fc_conf *fc_conf)
 {
 	struct sub_device *sdev;
+	int ret;
 
+	fs_lock(dev, 0);
 	sdev = TX_SUBDEV(dev);
-	if (sdev == NULL)
-		return 0;
-	if (SUBOPS(sdev, flow_ctrl_get) == NULL)
-		return -ENOTSUP;
-	return SUBOPS(sdev, flow_ctrl_get)(ETH(sdev), fc_conf);
+	if (sdev == NULL) {
+		ret = 0;
+		goto unlock;
+	}
+	if (SUBOPS(sdev, flow_ctrl_get) == NULL) {
+		ret = -ENOTSUP;
+		goto unlock;
+	}
+	ret = SUBOPS(sdev, flow_ctrl_get)(ETH(sdev), fc_conf);
+unlock:
+	fs_unlock(dev, 0);
+	return ret;
 }
 
 static int
@@ -648,15 +935,18 @@ fs_flow_ctrl_set(struct rte_eth_dev *dev,
 	uint8_t i;
 	int ret;
 
+	fs_lock(dev, 0);
 	FOREACH_SUBDEV_STATE(sdev, i, dev, DEV_ACTIVE) {
 		DEBUG("Calling rte_eth_dev_flow_ctrl_set on sub_device %d", i);
 		ret = rte_eth_dev_flow_ctrl_set(PORT_ID(sdev), fc_conf);
-		if (ret) {
+		if ((ret = fs_err(sdev, ret))) {
 			ERROR("Operation rte_eth_dev_flow_ctrl_set failed for sub_device %d"
 			      " with error %d", i, ret);
+			fs_unlock(dev, 0);
 			return ret;
 		}
 	}
+	fs_unlock(dev, 0);
 	return 0;
 }
 
@@ -666,6 +956,7 @@ fs_mac_addr_remove(struct rte_eth_dev *dev, uint32_t index)
 	struct sub_device *sdev;
 	uint8_t i;
 
+	fs_lock(dev, 0);
 	/* No check: already done within the rte_eth_dev_mac_addr_remove
 	 * call for the fail-safe device.
 	 */
@@ -673,6 +964,7 @@ fs_mac_addr_remove(struct rte_eth_dev *dev, uint32_t index)
 		rte_eth_dev_mac_addr_remove(PORT_ID(sdev),
 				&dev->data->mac_addrs[index]);
 	PRIV(dev)->mac_addr_pool[index] = 0;
+	fs_unlock(dev, 0);
 }
 
 static int
@@ -686,11 +978,13 @@ fs_mac_addr_add(struct rte_eth_dev *dev,
 	uint8_t i;
 
 	RTE_ASSERT(index < FAILSAFE_MAX_ETHADDR);
+	fs_lock(dev, 0);
 	FOREACH_SUBDEV_STATE(sdev, i, dev, DEV_ACTIVE) {
 		ret = rte_eth_dev_mac_addr_add(PORT_ID(sdev), mac_addr, vmdq);
-		if (ret) {
+		if ((ret = fs_err(sdev, ret))) {
 			ERROR("Operation rte_eth_dev_mac_addr_add failed for sub_device %"
 			      PRIu8 " with error %d", i, ret);
+			fs_unlock(dev, 0);
 			return ret;
 		}
 	}
@@ -699,6 +993,7 @@ fs_mac_addr_add(struct rte_eth_dev *dev,
 		PRIV(dev)->nb_mac_addr = index;
 	}
 	PRIV(dev)->mac_addr_pool[index] = vmdq;
+	fs_unlock(dev, 0);
 	return 0;
 }
 
@@ -708,8 +1003,10 @@ fs_mac_addr_set(struct rte_eth_dev *dev, struct ether_addr *mac_addr)
 	struct sub_device *sdev;
 	uint8_t i;
 
+	fs_lock(dev, 0);
 	FOREACH_SUBDEV_STATE(sdev, i, dev, DEV_ACTIVE)
 		rte_eth_dev_default_mac_addr_set(PORT_ID(sdev), mac_addr);
+	fs_unlock(dev, 0);
 }
 
 static int
@@ -727,15 +1024,18 @@ fs_filter_ctrl(struct rte_eth_dev *dev,
 		*(const void **)arg = &fs_flow_ops;
 		return 0;
 	}
+	fs_lock(dev, 0);
 	FOREACH_SUBDEV_STATE(sdev, i, dev, DEV_ACTIVE) {
 		DEBUG("Calling rte_eth_dev_filter_ctrl on sub_device %d", i);
 		ret = rte_eth_dev_filter_ctrl(PORT_ID(sdev), type, op, arg);
-		if (ret) {
+		if ((ret = fs_err(sdev, ret))) {
 			ERROR("Operation rte_eth_dev_filter_ctrl failed for sub_device %d"
 			      " with error %d", i, ret);
+			fs_unlock(dev, 0);
 			return ret;
 		}
 	}
+	fs_unlock(dev, 0);
 	return 0;
 }
 
@@ -761,6 +1061,8 @@ const struct eth_dev_ops failsafe_ops = {
 	.tx_queue_setup = fs_tx_queue_setup,
 	.rx_queue_release = fs_rx_queue_release,
 	.tx_queue_release = fs_tx_queue_release,
+	.rx_queue_intr_enable = fs_rx_intr_enable,
+	.rx_queue_intr_disable = fs_rx_intr_disable,
 	.flow_ctrl_get = fs_flow_ctrl_get,
 	.flow_ctrl_set = fs_flow_ctrl_set,
 	.mac_addr_remove = fs_mac_addr_remove,
diff --git a/drivers/net/failsafe/failsafe_private.h b/drivers/net/failsafe/failsafe_private.h
index d81cc3ca..2d16ba4c 100644
--- a/drivers/net/failsafe/failsafe_private.h
+++ b/drivers/net/failsafe/failsafe_private.h
@@ -1,53 +1,29 @@
-/*-
- *   BSD LICENSE
- *
- *   Copyright 2017 6WIND S.A.
- *   Copyright 2017 Mellanox.
- *
- *   Redistribution and use in source and binary forms, with or without
- *   modification, are permitted provided that the following conditions
- *   are met:
- *
- *     * Redistributions of source code must retain the above copyright
- *       notice, this list of conditions and the following disclaimer.
- *     * Redistributions in binary form must reproduce the above copyright
- *       notice, this list of conditions and the following disclaimer in
- *       the documentation and/or other materials provided with the
- *       distribution.
- *     * Neither the name of 6WIND S.A. nor the names of its
- *       contributors may be used to endorse or promote products derived
- *       from this software without specific prior written permission.
- *
- *   THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
- *   "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
- *   LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
- *   A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
- *   OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
- *   SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
- *   LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
- *   DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
- *   THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
- *   (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
- *   OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+/* SPDX-License-Identifier: BSD-3-Clause
+ * Copyright 2017 6WIND S.A.
+ * Copyright 2017 Mellanox.
  */
 
 #ifndef _RTE_ETH_FAILSAFE_PRIVATE_H_
 #define _RTE_ETH_FAILSAFE_PRIVATE_H_
 
 #include <sys/queue.h>
+#include <pthread.h>
 
 #include <rte_atomic.h>
 #include <rte_dev.h>
-#include <rte_ethdev.h>
+#include <rte_ethdev_driver.h>
 #include <rte_devargs.h>
+#include <rte_interrupts.h>
 
 #define FAILSAFE_DRIVER_NAME "Fail-safe PMD"
+#define FAILSAFE_OWNER_NAME "Fail-safe"
 
 #define PMD_FAILSAFE_MAC_KVARG "mac"
 #define PMD_FAILSAFE_HOTPLUG_POLL_KVARG "hotplug_poll"
 #define PMD_FAILSAFE_PARAM_STRING	\
 	"dev(<ifc>),"			\
 	"exec(<shell command>),"	\
+	"fd(<fd number>),"		\
 	"mac=mac_addr,"			\
 	"hotplug_poll=u64"		\
 	""
@@ -57,14 +33,37 @@
 #define FAILSAFE_MAX_ETHPORTS 2
 #define FAILSAFE_MAX_ETHADDR 128
 
+#define DEVARGS_MAXLEN 4096
+
+enum rxp_service_state {
+	SS_NO_SERVICE = 0,
+	SS_REGISTERED,
+	SS_READY,
+	SS_RUNNING,
+};
+
 /* TYPES */
 
+struct rx_proxy {
+	/* epoll file descriptor */
+	int efd;
+	/* event vector to be used by epoll */
+	struct rte_epoll_event *evec;
+	/* rte service id */
+	uint32_t sid;
+	/* service core id */
+	uint32_t scid;
+	enum rxp_service_state sstate;
+};
+
 struct rxq {
 	struct fs_priv *priv;
 	uint16_t qid;
-	/* id of last sub_device polled */
-	uint8_t last_polled;
+	/* next sub_device to poll */
+	struct sub_device *sdev;
 	unsigned int socket_id;
+	int event_fd;
+	unsigned int enable_events:1;
 	struct rte_eth_rxq_info info;
 	rte_atomic64_t refcnt[];
 };
@@ -100,6 +99,7 @@ struct fs_stats {
 
 struct sub_device {
 	/* Exhaustive DPDK device description */
+	struct sub_device *next;
 	struct rte_devargs devargs;
 	struct rte_bus *bus;
 	struct rte_device *dev;
@@ -111,6 +111,8 @@ struct sub_device {
 	struct fs_stats stats_snapshot;
 	/* Some device are defined as a command line */
 	char *cmdline;
+	/* Others are retrieved through a file descriptor */
+	char *fd_str;
 	/* fail-safe device backreference */
 	struct rte_eth_dev *fs_dev;
 	/* flag calling for recollection */
@@ -139,6 +141,8 @@ struct fs_priv {
 	uint32_t mac_addr_pool[FAILSAFE_MAX_ETHADDR];
 	/* current capabilities */
 	struct rte_eth_dev_info infos;
+	struct rte_eth_dev_owner my_owner; /* Unique owner. */
+	struct rte_intr_handle intr_handle; /* Port interrupt handle. */
 	/*
 	 * Fail-safe state machine.
 	 * This level will be tracking state of the EAL and eth
@@ -148,11 +152,31 @@ struct fs_priv {
 	 */
 	enum dev_state state;
 	struct rte_eth_stats stats_accumulator;
+	/*
+	 * Rx interrupts/events proxy.
+	 * The PMD issues Rx events to the EAL on behalf of its subdevices,
+	 * it does that by registering an event-fd for each of its queues with
+	 * the EAL. A PMD service thread listens to all the Rx events from the
+	 * subdevices, when an Rx event is issued by a subdevice it will be
+	 * caught by this service with will trigger an Rx event in the
+	 * appropriate failsafe Rx queue.
+	 */
+	struct rx_proxy rxp;
+	pthread_mutex_t hotplug_mutex;
+	/* Hot-plug mutex is locked by the alarm mechanism. */
+	volatile unsigned int alarm_lock:1;
 	unsigned int pending_alarm:1; /* An alarm is pending */
 	/* flow isolation state */
 	int flow_isolated:1;
 };
 
+/* FAILSAFE_INTR */
+
+int failsafe_rx_intr_install(struct rte_eth_dev *dev);
+void failsafe_rx_intr_uninstall(struct rte_eth_dev *dev);
+int failsafe_rx_intr_install_subdevice(struct sub_device *sdev);
+void failsafe_rx_intr_uninstall_subdevice(struct sub_device *sdev);
+
 /* MISC */
 
 int failsafe_hotplug_alarm_install(struct rte_eth_dev *dev);
@@ -269,13 +293,13 @@ extern int mac_from_arg;
  * a: (rte_atomic64_t)
  */
 #define FS_ATOMIC_P(a) \
-	rte_atomic64_add(&(a), 1)
+	rte_atomic64_set(&(a), 1)
 
 /**
  * a: (rte_atomic64_t)
  */
 #define FS_ATOMIC_V(a) \
-	rte_atomic64_sub(&(a), 1)
+	rte_atomic64_set(&(a), 0)
 
 /**
  * s: (struct sub_device *)
@@ -294,6 +318,14 @@ extern int mac_from_arg;
 	 &((struct txq *)((s)->fs_dev->data->tx_queues[i]))->refcnt[(s)->sid] \
 	)
 
+#ifdef RTE_EXEC_ENV_BSDAPP
+#define FS_THREADID_TYPE void*
+#define FS_THREADID_FMT  "p"
+#else
+#define FS_THREADID_TYPE unsigned long
+#define FS_THREADID_FMT  "lu"
+#endif
+
 #define LOG__(level, m, ...) \
 	RTE_LOG(level, PMD, "net_failsafe: " m "%c", __VA_ARGS__)
 #define LOG_(level, ...) LOG__(level, __VA_ARGS__, '\n')
@@ -327,6 +359,59 @@ fs_find_next(struct rte_eth_dev *dev,
 }
 
 /*
+ * Lock hot-plug mutex.
+ * is_alarm means that the caller is, for sure, the hot-plug alarm mechanism.
+ */
+static inline int
+fs_lock(struct rte_eth_dev *dev, unsigned int is_alarm)
+{
+	int ret;
+
+	if (is_alarm) {
+		ret = pthread_mutex_trylock(&PRIV(dev)->hotplug_mutex);
+		if (ret) {
+			DEBUG("Hot-plug mutex lock trying failed(%s), will try"
+			      " again later...", strerror(ret));
+			return ret;
+		}
+		PRIV(dev)->alarm_lock = 1;
+	} else {
+		ret = pthread_mutex_lock(&PRIV(dev)->hotplug_mutex);
+		if (ret) {
+			ERROR("Cannot lock mutex(%s)", strerror(ret));
+			return ret;
+		}
+	}
+	DEBUG("Hot-plug mutex was locked by thread %" FS_THREADID_FMT "%s",
+	      (FS_THREADID_TYPE)pthread_self(),
+	      PRIV(dev)->alarm_lock ? " by the hot-plug alarm" : "");
+	return ret;
+}
+
+/*
+ * Unlock hot-plug mutex.
+ * is_alarm means that the caller is, for sure, the hot-plug alarm mechanism.
+ */
+static inline void
+fs_unlock(struct rte_eth_dev *dev, unsigned int is_alarm)
+{
+	int ret;
+	unsigned int prev_alarm_lock = PRIV(dev)->alarm_lock;
+
+	if (is_alarm) {
+		RTE_ASSERT(PRIV(dev)->alarm_lock == 1);
+		PRIV(dev)->alarm_lock = 0;
+	}
+	ret = pthread_mutex_unlock(&PRIV(dev)->hotplug_mutex);
+	if (ret)
+		ERROR("Cannot unlock hot-plug mutex(%s)", strerror(ret));
+	else
+		DEBUG("Hot-plug mutex was unlocked by thread %" FS_THREADID_FMT "%s",
+		      (FS_THREADID_TYPE)pthread_self(),
+		      prev_alarm_lock ? " by the hot-plug alarm" : "");
+}
+
+/*
  * Switch emitting device.
  * If banned is set, banned must not be considered for
  * the role of emitting device.
@@ -375,4 +460,15 @@ fs_switch_dev(struct rte_eth_dev *dev,
 	rte_wmb();
 }
 
+/*
+ * Adjust error value and rte_errno to the fail-safe actual error value.
+ */
+static inline int
+fs_err(struct sub_device *sdev, int err)
+{
+	/* A device removal shouldn't be reported as an error. */
+	if (sdev->remove == 1 || err == -EIO)
+		return rte_errno = 0;
+	return err;
+}
 #endif /* _RTE_ETH_FAILSAFE_PRIVATE_H_ */
diff --git a/drivers/net/failsafe/failsafe_rxtx.c b/drivers/net/failsafe/failsafe_rxtx.c
index 70157c82..363cf7ba 100644
--- a/drivers/net/failsafe/failsafe_rxtx.c
+++ b/drivers/net/failsafe/failsafe_rxtx.c
@@ -1,40 +1,12 @@
-/*-
- *   BSD LICENSE
- *
- *   Copyright 2017 6WIND S.A.
- *   Copyright 2017 Mellanox.
- *
- *   Redistribution and use in source and binary forms, with or without
- *   modification, are permitted provided that the following conditions
- *   are met:
- *
- *     * Redistributions of source code must retain the above copyright
- *       notice, this list of conditions and the following disclaimer.
- *     * Redistributions in binary form must reproduce the above copyright
- *       notice, this list of conditions and the following disclaimer in
- *       the documentation and/or other materials provided with the
- *       distribution.
- *     * Neither the name of 6WIND S.A. nor the names of its
- *       contributors may be used to endorse or promote products derived
- *       from this software without specific prior written permission.
- *
- *   THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
- *   "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
- *   LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
- *   A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
- *   OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
- *   SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
- *   LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
- *   DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
- *   THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
- *   (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
- *   OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+/* SPDX-License-Identifier: BSD-3-Clause
+ * Copyright 2017 6WIND S.A.
+ * Copyright 2017 Mellanox.
  */
 
 #include <rte_atomic.h>
 #include <rte_debug.h>
 #include <rte_mbuf.h>
-#include <rte_ethdev.h>
+#include <rte_ethdev_driver.h>
 
 #include "failsafe_private.h"
 
@@ -94,36 +66,28 @@ failsafe_rx_burst(void *queue,
 		  struct rte_mbuf **rx_pkts,
 		  uint16_t nb_pkts)
 {
-	struct fs_priv *priv;
 	struct sub_device *sdev;
 	struct rxq *rxq;
 	void *sub_rxq;
 	uint16_t nb_rx;
-	uint8_t nb_polled, nb_subs;
-	uint8_t i;
 
 	rxq = queue;
-	priv = rxq->priv;
-	nb_subs = priv->subs_tail - priv->subs_head;
-	nb_polled = 0;
-	for (i = rxq->last_polled; nb_polled < nb_subs; nb_polled++) {
-		i++;
-		if (i == priv->subs_tail)
-			i = priv->subs_head;
-		sdev = &priv->subs[i];
-		if (unlikely(fs_rx_unsafe(sdev)))
+	sdev = rxq->sdev;
+	do {
+		if (fs_rx_unsafe(sdev)) {
+			nb_rx = 0;
+			sdev = sdev->next;
 			continue;
+		}
 		sub_rxq = ETH(sdev)->data->rx_queues[rxq->qid];
 		FS_ATOMIC_P(rxq->refcnt[sdev->sid]);
 		nb_rx = ETH(sdev)->
 			rx_pkt_burst(sub_rxq, rx_pkts, nb_pkts);
 		FS_ATOMIC_V(rxq->refcnt[sdev->sid]);
-		if (nb_rx) {
-			rxq->last_polled = i;
-			return nb_rx;
-		}
-	}
-	return 0;
+		sdev = sdev->next;
+	} while (nb_rx == 0 && sdev != rxq->sdev);
+	rxq->sdev = sdev;
+	return nb_rx;
 }
 
 uint16_t
@@ -131,35 +95,24 @@ failsafe_rx_burst_fast(void *queue,
 			 struct rte_mbuf **rx_pkts,
 			 uint16_t nb_pkts)
 {
-	struct fs_priv *priv;
 	struct sub_device *sdev;
 	struct rxq *rxq;
 	void *sub_rxq;
 	uint16_t nb_rx;
-	uint8_t nb_polled, nb_subs;
-	uint8_t i;
 
 	rxq = queue;
-	priv = rxq->priv;
-	nb_subs = priv->subs_tail - priv->subs_head;
-	nb_polled = 0;
-	for (i = rxq->last_polled; nb_polled < nb_subs; nb_polled++) {
-		i++;
-		if (i == priv->subs_tail)
-			i = priv->subs_head;
-		sdev = &priv->subs[i];
+	sdev = rxq->sdev;
+	do {
 		RTE_ASSERT(!fs_rx_unsafe(sdev));
 		sub_rxq = ETH(sdev)->data->rx_queues[rxq->qid];
 		FS_ATOMIC_P(rxq->refcnt[sdev->sid]);
 		nb_rx = ETH(sdev)->
 			rx_pkt_burst(sub_rxq, rx_pkts, nb_pkts);
 		FS_ATOMIC_V(rxq->refcnt[sdev->sid]);
-		if (nb_rx) {
-			rxq->last_polled = i;
-			return nb_rx;
-		}
-	}
-	return 0;
+		sdev = sdev->next;
+	} while (nb_rx == 0 && sdev != rxq->sdev);
+	rxq->sdev = sdev;
+	return nb_rx;
 }
 
 uint16_t