/*
- * Copyright (c) 2009, 2010, 2011, 2012, 2013 Nicira, Inc.
+ * Copyright (c) 2009, 2010, 2011, 2012, 2013, 2014, 2016 Nicira, Inc.
*
* Licensed under the Apache License, Version 2.0 (the "License");
* you may not use this file except in compliance with the License.
/* Generic interface to network devices. */
+#include "connectivity.h"
#include "netdev.h"
-#include "list.h"
+#include "openvswitch/list.h"
+#include "ovs-numa.h"
+#include "packets.h"
+#include "seq.h"
#include "shash.h"
#include "smap.h"
extern "C" {
#endif
+struct netdev_tnl_build_header_params;
+#define NETDEV_NUMA_UNSPEC OVS_NUMA_UNSPEC
+
/* A network device (e.g. an Ethernet device).
*
* Network device implementations may read these members but should not modify
* them. */
struct netdev {
+ /* The following do not change during the lifetime of a struct netdev. */
char *name; /* Name of network device. */
const struct netdev_class *netdev_class; /* Functions to control
this device. */
+
+ /* A sequence number which indicates changes in one of 'netdev''s
+ * properties. It must be nonzero so that users have a value which
+ * they may use as a reset when tracking 'netdev'.
+ *
+ * Minimally, the sequence number is required to change whenever
+ * 'netdev''s flags, features, ethernet address, or carrier changes. */
+ uint64_t change_seq;
+
+ /* A netdev provider might be unable to change some of the device's
+ * parameter (n_rxq, mtu) when the device is in use. In this case
+ * the provider can notify the upper layer by calling
+ * netdev_request_reconfigure(). The upper layer will react by stopping
+ * the operations on the device and calling netdev_reconfigure() to allow
+ * the configuration changes. 'last_reconfigure_seq' remembers the value
+ * of 'reconfigure_seq' when the last reconfiguration happened. */
+ struct seq *reconfigure_seq;
+ uint64_t last_reconfigure_seq;
+
+ /* The core netdev code initializes these at netdev construction and only
+ * provide read-only access to its client. Netdev implementations may
+ * modify them. */
+ int n_txq;
+ int n_rxq;
int ref_cnt; /* Times this devices was opened. */
struct shash_node *node; /* Pointer to element in global map. */
- struct list saved_flags_list; /* Contains "struct netdev_saved_flags". */
+ struct ovs_list saved_flags_list; /* Contains "struct netdev_saved_flags". */
};
+static inline void
+netdev_change_seq_changed(const struct netdev *netdev_)
+{
+ struct netdev *netdev = CONST_CAST(struct netdev *, netdev_);
+ seq_change(connectivity_seq_get());
+ netdev->change_seq++;
+ if (!netdev->change_seq) {
+ netdev->change_seq++;
+ }
+}
+
+static inline void
+netdev_request_reconfigure(struct netdev *netdev)
+{
+ seq_change(netdev->reconfigure_seq);
+}
+
const char *netdev_get_type(const struct netdev *);
const struct netdev_class *netdev_get_class(const struct netdev *);
const char *netdev_get_name(const struct netdev *);
struct netdev *netdev_from_name(const char *name);
void netdev_get_devices(const struct netdev_class *,
struct shash *device_list);
+struct netdev **netdev_get_vports(size_t *size);
/* A data structure for capturing packets received by a network device.
*
* Network device implementations may read these members but should not modify
* them.
*
- * None of these members change during the lifetime of a struct netdev_rx. */
-struct netdev_rx {
+ * None of these members change during the lifetime of a struct netdev_rxq. */
+struct netdev_rxq {
struct netdev *netdev; /* Owns a reference to the netdev. */
+ int queue_id;
};
-struct netdev *netdev_rx_get_netdev(const struct netdev_rx *);
+struct netdev *netdev_rxq_get_netdev(const struct netdev_rxq *);
/* Network device class structure, to be defined by each implementation of a
* network device.
*
* - "struct netdev", which represents a network device.
*
- * - "struct netdev_rx", which represents a handle for capturing packets
+ * - "struct netdev_rxq", which represents a handle for capturing packets
* received on a network device
*
* Each of these data structures contains all of the implementation-independent
*
* Four stylized functions accompany each of these data structures:
*
- * "alloc" "construct" "destruct" "dealloc"
- * ------------ ---------------- --------------- --------------
- * netdev ->alloc ->construct ->destruct ->dealloc
- * netdev_rx ->rx_alloc ->rx_construct ->rx_destruct ->rx_dealloc
+ * "alloc" "construct" "destruct" "dealloc"
+ * ------------ ---------------- --------------- --------------
+ * netdev ->alloc ->construct ->destruct ->dealloc
+ * netdev_rxq ->rxq_alloc ->rxq_construct ->rxq_destruct ->rxq_dealloc
*
* Any instance of a given data structure goes through the following life
* cycle:
* implementation must not refer to base or derived state in the data
* structure, because it has already been uninitialized.
*
+ * If netdev support multi-queue IO then netdev->construct should set initialize
+ * netdev->n_rxq to number of queues.
+ *
* Each "alloc" function allocates and returns a new instance of the respective
* data structure. The "alloc" function is not given any information about the
* use of the new data structure, so it cannot perform much initialization.
* not yet been uninitialized, so the "destruct" function may refer to it. The
* "destruct" function is not allowed to fail.
*
- * Each "dealloc" function frees raw memory that was allocated by the the
+ * Each "dealloc" function frees raw memory that was allocated by the
* "alloc" function. The memory's base and derived members might not have ever
* been initialized (but if "construct" returned successfully, then it has been
- * "destruct"ed already). The "dealloc" function is not allowed to fail. */
+ * "destruct"ed already). The "dealloc" function is not allowed to fail.
+ *
+ *
+ * Device Change Notification
+ * ==========================
+ *
+ * Minimally, implementations are required to report changes to netdev flags,
+ * features, ethernet address or carrier through connectivity_seq. Changes to
+ * other properties are allowed to cause notification through this interface,
+ * although implementations should try to avoid this. connectivity_seq_get()
+ * can be used to acquire a reference to the struct seq. The interface is
+ * described in detail in seq.h. */
struct netdev_class {
/* Type of netdevs in this class, e.g. "system", "tap", "gre", etc.
*
* the system. */
const char *type;
+ /* If 'true' then this netdev should be polled by PMD threads. */
+ bool is_pmd;
+
/* ## ------------------- ## */
/* ## Top-Level Functions ## */
/* ## ------------------- ## */
const struct netdev_tunnel_config *
(*get_tunnel_config)(const struct netdev *netdev);
- /* Sends the 'size'-byte packet in 'buffer' on 'netdev'. Returns 0 if
- * successful, otherwise a positive errno value. Returns EAGAIN without
- * blocking if the packet cannot be queued immediately. Returns EMSGSIZE
- * if a partial packet was transmitted or if the packet is too big or too
- * small to transmit on the device.
- *
- * The caller retains ownership of 'buffer' in all cases.
- *
- * The network device is expected to maintain a packet transmission queue,
- * so that the caller does not ordinarily have to do additional queuing of
- * packets.
+ /* Build Tunnel header. Ethernet and ip header parameters are passed to
+ * tunnel implementation to build entire outer header for given flow. */
+ int (*build_header)(const struct netdev *, struct ovs_action_push_tnl *data,
+ const struct netdev_tnl_build_header_params *params);
+
+ /* build_header() can not build entire header for all packets for given
+ * flow. Push header is called for packet to build header specific to
+ * a packet on actual transmit. It uses partial header build by
+ * build_header() which is passed as data. */
+ void (*push_header)(struct dp_packet *packet,
+ const struct ovs_action_push_tnl *data);
+
+ /* Pop tunnel header from packet, build tunnel metadata and resize packet
+ * for further processing.
+ * Returns NULL in case of error or tunnel implementation queued packet for further
+ * processing. */
+ struct dp_packet * (*pop_header)(struct dp_packet *packet);
+
+ /* Returns the id of the numa node the 'netdev' is on. If there is no
+ * such info, returns NETDEV_NUMA_UNSPEC. */
+ int (*get_numa_id)(const struct netdev *netdev);
+
+ /* Configures the number of tx queues of 'netdev'. Returns 0 if successful,
+ * otherwise a positive errno value.
+ *
+ * 'n_txq' specifies the exact number of transmission queues to create.
+ * The caller will call netdev_send() concurrently from 'n_txq' different
+ * threads (with different qid). The netdev provider is responsible for
+ * making sure that these concurrent calls do not create a race condition
+ * by using multiple hw queues or locking.
+ *
+ * The caller will call netdev_reconfigure() (if necessary) before using
+ * netdev_send() on any of the newly configured queues, giving the provider
+ * a chance to adjust its settings.
+ *
+ * On error, the tx queue configuration is unchanged. */
+ int (*set_tx_multiq)(struct netdev *netdev, unsigned int n_txq);
+
+ /* Sends buffers on 'netdev'.
+ * Returns 0 if successful (for every buffer), otherwise a positive errno
+ * value. Returns EAGAIN without blocking if one or more packets cannot be
+ * queued immediately. Returns EMSGSIZE if a partial packet was transmitted
+ * or if a packet is too big or too small to transmit on the device.
+ *
+ * If the function returns a non-zero value, some of the packets might have
+ * been sent anyway.
+ *
+ * If 'may_steal' is false, the caller retains ownership of all the
+ * packets. If 'may_steal' is true, the caller transfers ownership of all
+ * the packets to the network device, regardless of success.
+ *
+ * The network device is expected to maintain one or more packet
+ * transmission queues, so that the caller does not ordinarily have to
+ * do additional queuing of packets. 'qid' specifies the queue to use
+ * and can be ignored if the implementation does not support multiple
+ * queues.
*
* May return EOPNOTSUPP if a network device does not implement packet
* transmission through this interface. This function may be set to null
* network device from being usefully used by the netdev-based "userspace
* datapath". It will also prevent the OVS implementation of bonding from
* working properly over 'netdev'.) */
- int (*send)(struct netdev *netdev, const void *buffer, size_t size);
+ int (*send)(struct netdev *netdev, int qid, struct dp_packet_batch *batch,
+ bool may_steal);
/* Registers with the poll loop to wake up from the next call to
* poll_block() when the packet transmission queue for 'netdev' has
* sufficient room to transmit a packet with netdev_send().
*
- * The network device is expected to maintain a packet transmission queue,
- * so that the caller does not ordinarily have to do additional queuing of
- * packets. Thus, this function is unlikely to ever be useful.
+ * The network device is expected to maintain one or more packet
+ * transmission queues, so that the caller does not ordinarily have to
+ * do additional queuing of packets. 'qid' specifies the queue to use
+ * and can be ignored if the implementation does not support multiple
+ * queues.
*
* May be null if not needed, such as for a network device that does not
* implement packet transmission through the 'send' member function. */
- void (*send_wait)(struct netdev *netdev);
+ void (*send_wait)(struct netdev *netdev, int qid);
/* Sets 'netdev''s Ethernet address to 'mac' */
- int (*set_etheraddr)(struct netdev *netdev, const uint8_t mac[6]);
+ int (*set_etheraddr)(struct netdev *netdev, const struct eth_addr mac);
/* Retrieves 'netdev''s Ethernet address into 'mac'.
*
* This address will be advertised as 'netdev''s MAC address through the
* OpenFlow protocol, among other uses. */
- int (*get_etheraddr)(const struct netdev *netdev, uint8_t mac[6]);
+ int (*get_etheraddr)(const struct netdev *netdev, struct eth_addr *mac);
/* Retrieves 'netdev''s MTU into '*mtup'.
*
/* Forces ->get_carrier() to poll 'netdev''s MII registers for link status
* instead of checking 'netdev''s carrier. 'netdev''s MII registers will
- * be polled once ever 'interval' milliseconds. If 'netdev' does not
+ * be polled once every 'interval' milliseconds. If 'netdev' does not
* support MII, another method may be used as a fallback. If 'interval' is
* less than or equal to zero, reverts ->get_carrier() to its normal
* behavior.
* (UINT64_MAX). */
int (*get_stats)(const struct netdev *netdev, struct netdev_stats *);
- /* Sets the device stats for 'netdev' to 'stats'.
- *
- * Most network devices won't support this feature and will set this
- * function pointer to NULL, which is equivalent to returning EOPNOTSUPP.
- *
- * Some network devices might only allow setting their stats to 0. */
- int (*set_stats)(struct netdev *netdev, const struct netdev_stats *);
-
/* Stores the features supported by 'netdev' into each of '*current',
* '*advertised', '*supported', and '*peer'. Each value is a bitmap of
* NETDEV_F_* bits.
int (*get_queue_stats)(const struct netdev *netdev, unsigned int queue_id,
struct netdev_queue_stats *stats);
- /* Iterates over all of 'netdev''s queues, calling 'cb' with the queue's
- * ID, its configuration, and the 'aux' specified by the caller. The order
- * of iteration is unspecified, but (when successful) each queue is visited
- * exactly once.
- *
- * 'cb' will not modify or free the 'details' argument passed in. It may
- * delete or modify the queue passed in as its 'queue_id' argument. It may
- * modify but will not delete any other queue within 'netdev'. If 'cb'
- * adds new queues, then ->dump_queues is allowed to visit some queues
- * twice or not at all.
- */
- int (*dump_queues)(const struct netdev *netdev,
- void (*cb)(unsigned int queue_id,
- const struct smap *details,
- void *aux),
- void *aux);
+ /* Attempts to begin dumping the queues in 'netdev'. On success, returns 0
+ * and initializes '*statep' with any data needed for iteration. On
+ * failure, returns a positive errno value.
+ *
+ * May be NULL if 'netdev' does not support QoS at all. */
+ int (*queue_dump_start)(const struct netdev *netdev, void **statep);
+
+ /* Attempts to retrieve another queue from 'netdev' for 'state', which was
+ * initialized by a successful call to the 'queue_dump_start' function for
+ * 'netdev'. On success, stores a queue ID into '*queue_id' and fills
+ * 'details' with the configuration of the queue with that ID. Returns EOF
+ * if the last queue has been dumped, or a positive errno value on error.
+ * This function will not be called again once it returns nonzero once for
+ * a given iteration (but the 'queue_dump_done' function will be called
+ * afterward).
+ *
+ * The caller initializes and clears 'details' before calling this
+ * function. The caller takes ownership of the string key-values pairs
+ * added to 'details'.
+ *
+ * The returned contents of 'details' should be documented as valid for the
+ * given 'type' in the "other_config" column in the "Queue" table in
+ * vswitchd/vswitch.xml (which is built as ovs-vswitchd.conf.db(8)).
+ *
+ * May be NULL if 'netdev' does not support QoS at all. */
+ int (*queue_dump_next)(const struct netdev *netdev, void *state,
+ unsigned int *queue_id, struct smap *details);
+
+ /* Releases resources from 'netdev' for 'state', which was initialized by a
+ * successful call to the 'queue_dump_start' function for 'netdev'.
+ *
+ * May be NULL if 'netdev' does not support QoS at all. */
+ int (*queue_dump_done)(const struct netdev *netdev, void *state);
/* Iterates over all of 'netdev''s queues, calling 'cb' with the queue's
* ID, its statistics, and the 'aux' specified by the caller. The order of
void *aux),
void *aux);
- /* If 'netdev' has an assigned IPv4 address, sets '*address' to that
- * address and '*netmask' to the associated netmask.
- *
- * The following error values have well-defined meanings:
- *
- * - EADDRNOTAVAIL: 'netdev' has no assigned IPv4 address.
- *
- * - EOPNOTSUPP: No IPv4 network stack attached to 'netdev'.
- *
- * This function may be set to null if it would always return EOPNOTSUPP
- * anyhow. */
- int (*get_in4)(const struct netdev *netdev, struct in_addr *address,
- struct in_addr *netmask);
-
/* Assigns 'addr' as 'netdev''s IPv4 address and 'mask' as its netmask. If
* 'addr' is INADDR_ANY, 'netdev''s IPv4 address is cleared.
*
int (*set_in4)(struct netdev *netdev, struct in_addr addr,
struct in_addr mask);
- /* If 'netdev' has an assigned IPv6 address, sets '*in6' to that address.
+ /* Returns all assigned IP address to 'netdev' and returns 0.
+ * API allocates array of address and masks and set it to
+ * '*addr' and '*mask'.
+ * Otherwise, returns a positive errno value and sets '*addr', '*mask
+ * and '*n_addr' to NULL.
*
* The following error values have well-defined meanings:
*
*
* - EOPNOTSUPP: No IPv6 network stack attached to 'netdev'.
*
- * This function may be set to null if it would always return EOPNOTSUPP
- * anyhow. */
- int (*get_in6)(const struct netdev *netdev, struct in6_addr *in6);
+ * 'addr' may be null, in which case the address itself is not reported. */
+ int (*get_addr_list)(const struct netdev *netdev, struct in6_addr **in,
+ struct in6_addr **mask, int *n_in6);
/* Adds 'router' as a default IP gateway for the TCP/IP stack that
* corresponds to 'netdev'.
* anyhow. */
int (*add_router)(struct netdev *netdev, struct in_addr router);
- /* Looks up the next hop for 'host'. If successful, stores the next hop
- * gateway's address (0 if 'host' is on a directly connected network) in
- * '*next_hop' and a copy of the name of the device to reach 'host' in
- * '*netdev_name', and returns 0. The caller is responsible for freeing
- * '*netdev_name' (by calling free()).
+ /* Looks up the next hop for 'host' in the host's routing table. If
+ * successful, stores the next hop gateway's address (0 if 'host' is on a
+ * directly connected network) in '*next_hop' and a copy of the name of the
+ * device to reach 'host' in '*netdev_name', and returns 0. The caller is
+ * responsible for freeing '*netdev_name' (by calling free()).
*
* This function may be set to null if it would always return EOPNOTSUPP
* anyhow. */
* This function may be set to null if it would always return EOPNOTSUPP
* anyhow. */
int (*arp_lookup)(const struct netdev *netdev, ovs_be32 ip,
- uint8_t mac[6]);
+ struct eth_addr *mac);
/* Retrieves the current set of flags on 'netdev' into '*old_flags'. Then,
* turns off the flags that are set to 1 in 'off' and turns on the flags
int (*update_flags)(struct netdev *netdev, enum netdev_flags off,
enum netdev_flags on, enum netdev_flags *old_flags);
- /* Returns a sequence number which indicates changes in one of 'netdev''s
- * properties. The returned sequence number must be nonzero so that
- * callers have a value which they may use as a reset when tracking
- * 'netdev'.
+ /* If the provider called netdev_request_reconfigure(), the upper layer
+ * will eventually call this. The provider can update the device
+ * configuration knowing that the upper layer will not call rxq_recv() or
+ * send() until this function returns.
*
- * Minimally, the returned sequence number is required to change whenever
- * 'netdev''s flags, features, ethernet address, or carrier changes. The
- * returned sequence number is allowed to change even when 'netdev' doesn't
- * change, although implementations should try to avoid this. */
- unsigned int (*change_seq)(const struct netdev *netdev);
-
-/* ## ------------------- ## */
-/* ## netdev_rx Functions ## */
-/* ## ------------------- ## */
+ * On error, the configuration is indeterminant and the device cannot be
+ * used to send and receive packets until a successful configuration is
+ * applied. */
+ int (*reconfigure)(struct netdev *netdev);
+/* ## -------------------- ## */
+/* ## netdev_rxq Functions ## */
+/* ## -------------------- ## */
/* If a particular netdev class does not support receiving packets, all these
* function pointers must be NULL. */
- /* Life-cycle functions for a netdev_rx. See the large comment above on
+ /* Life-cycle functions for a netdev_rxq. See the large comment above on
* struct netdev_class. */
- struct netdev_rx *(*rx_alloc)(void);
- int (*rx_construct)(struct netdev_rx *);
- void (*rx_destruct)(struct netdev_rx *);
- void (*rx_dealloc)(struct netdev_rx *);
-
- /* Attempts to receive a packet from 'rx' into the 'size' bytes in
- * 'buffer'. If successful, returns the number of bytes in the received
- * packet, otherwise a negative errno value. Returns -EAGAIN immediately
- * if no packet is ready to be received.
- *
- * Must return -EMSGSIZE, and discard the packet, if the received packet
- * is longer than 'size' bytes.
- *
- * Specify NULL if this */
- int (*rx_recv)(struct netdev_rx *rx, void *buffer, size_t size);
+ struct netdev_rxq *(*rxq_alloc)(void);
+ int (*rxq_construct)(struct netdev_rxq *);
+ void (*rxq_destruct)(struct netdev_rxq *);
+ void (*rxq_dealloc)(struct netdev_rxq *);
+
+ /* Attempts to receive a batch of packets from 'rx'. In 'batch', the
+ * caller supplies 'packets' as the pointer to the beginning of an array
+ * of MAX_RX_BATCH pointers to dp_packet. If successful, the
+ * implementation stores pointers to up to MAX_RX_BATCH dp_packets into
+ * the array, transferring ownership of the packets to the caller, stores
+ * the number of received packets into 'count', and returns 0.
+ *
+ * The implementation does not necessarily initialize any non-data members
+ * of 'packets' in 'batch'. That is, the caller must initialize layer
+ * pointers and metadata itself, if desired, e.g. with pkt_metadata_init()
+ * and miniflow_extract().
+ *
+ * Implementations should allocate buffers with DP_NETDEV_HEADROOM bytes of
+ * headroom.
+ *
+ * Returns EAGAIN immediately if no packet is ready to be received or
+ * another positive errno value if an error was encountered. */
+ int (*rxq_recv)(struct netdev_rxq *rx, struct dp_packet_batch *batch);
/* Registers with the poll loop to wake up from the next call to
- * poll_block() when a packet is ready to be received with netdev_rx_recv()
- * on 'rx'. */
- void (*rx_wait)(struct netdev_rx *rx);
+ * poll_block() when a packet is ready to be received with
+ * netdev_rxq_recv() on 'rx'. */
+ void (*rxq_wait)(struct netdev_rxq *rx);
/* Discards all packets waiting to be received from 'rx'. */
- int (*rx_drain)(struct netdev_rx *rx);
+ int (*rxq_drain)(struct netdev_rxq *rx);
};
int netdev_register_provider(const struct netdev_class *);
int netdev_unregister_provider(const char *type);
-const struct netdev_class *netdev_lookup_provider(const char *type);
-extern const struct netdev_class netdev_linux_class;
-extern const struct netdev_class netdev_internal_class;
-extern const struct netdev_class netdev_tap_class;
#if defined(__FreeBSD__) || defined(__NetBSD__)
extern const struct netdev_class netdev_bsd_class;
+#elif defined(_WIN32)
+extern const struct netdev_class netdev_windows_class;
+#else
+extern const struct netdev_class netdev_linux_class;
#endif
+extern const struct netdev_class netdev_internal_class;
+extern const struct netdev_class netdev_tap_class;
#ifdef __cplusplus
}