-/*-
- * 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 Technologies, Ltd
*/
-#ifndef _RTE_ETH_FAILSAFE_PRIVATE_H_
-#define _RTE_ETH_FAILSAFE_PRIVATE_H_
+#ifndef _ETH_FAILSAFE_PRIVATE_H_
+#define _ETH_FAILSAFE_PRIVATE_H_
+#include <stdint.h>
#include <sys/queue.h>
+#include <pthread.h>
#include <rte_atomic.h>
#include <rte_dev.h>
-#include <rte_ethdev.h>
+#include <ethdev_driver.h>
#include <rte_devargs.h>
+#include <rte_flow.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" \
""
#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;
+};
+
+#define FS_RX_PROXY_INIT (struct rx_proxy){ \
+ .efd = -1, \
+ .evec = NULL, \
+ .sid = 0, \
+ .scid = 0, \
+ .sstate = SS_NO_SERVICE, \
+}
+
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[];
};
/* sub_flows */
struct rte_flow *flows[FAILSAFE_MAX_ETHPORTS];
/* flow description for synchronization */
- struct rte_flow_desc *fd;
+ struct rte_flow_conv_rule rule;
+ uint8_t rule_data[];
};
enum dev_state {
DEV_STARTED,
};
+struct fs_stats {
+ struct rte_eth_stats stats;
+ uint64_t timestamp;
+};
+
+/*
+ * Allocated in shared memory.
+ */
struct sub_device {
/* Exhaustive DPDK device description */
+ struct sub_device *next;
struct rte_devargs devargs;
- struct rte_bus *bus;
- struct rte_device *dev;
- struct rte_eth_dev *edev;
+ struct rte_bus *bus; /* for primary process only. */
+ struct rte_device *dev; /* for primary process only. */
uint8_t sid;
/* Device state machine */
enum dev_state state;
/* Last stats snapshot passed to user */
- struct rte_eth_stats stats_snapshot;
+ 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;
+ uint16_t fs_port_id; /* shared between processes */
+ /* sub device port id*/
+ uint16_t sdev_port_id; /* shared between processes */
/* flag calling for recollection */
volatile unsigned int remove:1;
/* flow isolation state */
int flow_isolated:1;
+ /* RMV callback registration state */
+ unsigned int rmv_callback:1;
+ /* LSC callback registration state */
+ unsigned int lsc_callback:1;
};
+/*
+ * This is referenced by eth_dev->data->dev_private
+ * This is shared between processes.
+ */
struct fs_priv {
- struct rte_eth_dev *dev;
+ struct rte_eth_dev_data *data; /* backreference to shared data. */
/*
* Set of sub_devices.
* subs[0] is the preferred device
- * any other is just another slave
+ * any other is just another sub device
*/
- struct sub_device *subs;
+ struct sub_device *subs; /* shared between processes */
uint8_t subs_head; /* if head == tail, no subs */
uint8_t subs_tail; /* first invalid */
uint8_t subs_tx; /* current emitting device */
TAILQ_HEAD(sub_flows, rte_flow) flow_list;
/* current number of mac_addr slots allocated. */
uint32_t nb_mac_addr;
- struct ether_addr mac_addrs[FAILSAFE_MAX_ETHADDR];
+ struct rte_ether_addr mac_addrs[FAILSAFE_MAX_ETHADDR];
uint32_t mac_addr_pool[FAILSAFE_MAX_ETHADDR];
+ uint32_t nb_mcast_addr;
+ struct rte_ether_addr *mcast_addrs;
/* 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
*/
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);
/* RX / TX */
-void set_burst_fn(struct rte_eth_dev *dev, int force_safe);
+void failsafe_set_burst_fn(struct rte_eth_dev *dev, int force_safe);
uint16_t failsafe_rx_burst(void *rxq,
struct rte_mbuf **rx_pkts, uint16_t nb_pkts);
/* ETH_DEV */
int failsafe_eth_dev_state_sync(struct rte_eth_dev *dev);
+void failsafe_eth_dev_unregister_callbacks(struct sub_device *sdev);
+int failsafe_eth_dev_close(struct rte_eth_dev *dev);
void failsafe_dev_remove(struct rte_eth_dev *dev);
void failsafe_stats_increment(struct rte_eth_stats *to,
struct rte_eth_stats *from);
-int failsafe_eth_rmv_event_callback(uint8_t port_id,
+int failsafe_eth_rmv_event_callback(uint16_t port_id,
enum rte_eth_event_type type,
void *arg, void *out);
-int failsafe_eth_lsc_event_callback(uint8_t port_id,
+int failsafe_eth_lsc_event_callback(uint16_t port_id,
+ enum rte_eth_event_type event,
+ void *cb_arg, void *out);
+int failsafe_eth_new_event_callback(uint16_t port_id,
enum rte_eth_event_type event,
void *cb_arg, void *out);
extern const char pmd_failsafe_driver_name[];
extern const struct eth_dev_ops failsafe_ops;
extern const struct rte_flow_ops fs_flow_ops;
-extern uint64_t hotplug_poll;
-extern int mac_from_arg;
+extern uint64_t failsafe_hotplug_poll;
+extern int failsafe_mac_from_arg;
/* HELPERS */
/* sdev: (struct sub_device *) */
#define ETH(sdev) \
- ((sdev)->edev)
+ ((sdev)->sdev_port_id == RTE_MAX_ETHPORTS ? \
+ NULL : &rte_eth_devices[(sdev)->sdev_port_id])
/* sdev: (struct sub_device *) */
#define PORT_ID(sdev) \
- (ETH(sdev)->data->port_id)
+ ((sdev)->sdev_port_id)
/* sdev: (struct sub_device *) */
#define SUB_ID(sdev) \
* 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 *)
*/
#define FS_ATOMIC_RX(s, i) \
rte_atomic64_read( \
- &((struct rxq *)((s)->fs_dev->data->rx_queues[i]))->refcnt[(s)->sid] \
- )
+ &((struct rxq *) \
+ (fs_dev(s)->data->rx_queues[i]))->refcnt[(s)->sid])
/**
* s: (struct sub_device *)
* i: uint16_t qid
*/
#define FS_ATOMIC_TX(s, i) \
rte_atomic64_read( \
- &((struct txq *)((s)->fs_dev->data->tx_queues[i]))->refcnt[(s)->sid] \
- )
+ &((struct txq *) \
+ (fs_dev(s)->data->tx_queues[i]))->refcnt[(s)->sid])
+
+#ifdef RTE_EXEC_ENV_FREEBSD
+#define FS_THREADID_TYPE void*
+#define FS_THREADID_FMT "p"
+#else
+#define FS_THREADID_TYPE unsigned long
+#define FS_THREADID_FMT "lu"
+#endif
+
+extern int failsafe_logtype;
+
+#define LOG__(l, m, ...) \
+ rte_log(RTE_LOG_ ## l, failsafe_logtype, \
+ "net_failsafe: " m "%c", __VA_ARGS__)
-#define LOG__(level, m, ...) \
- RTE_LOG(level, PMD, "net_failsafe: " m "%c", __VA_ARGS__)
#define LOG_(level, ...) LOG__(level, __VA_ARGS__, '\n')
#define DEBUG(...) LOG_(DEBUG, __VA_ARGS__)
#define INFO(...) LOG_(INFO, __VA_ARGS__)
return &subs[sid];
}
+static inline struct rte_eth_dev *
+fs_dev(struct sub_device *sdev) {
+ return &rte_eth_devices[sdev->fs_port_id];
+}
+
+/*
+ * 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;
+ }
+ }
+ 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;
+
+ 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));
+}
+
/*
* Switch emitting device.
* If banned is set, banned must not be considered for
} else {
return;
}
- set_burst_fn(dev, 0);
+ failsafe_set_burst_fn(dev, 0);
rte_wmb();
}
-#endif /* _RTE_ETH_FAILSAFE_PRIVATE_H_ */
+/*
+ * 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 /* _ETH_FAILSAFE_PRIVATE_H_ */