/*
- * Copyright (c) 2009, 2010, 2011, 2012, 2013, 2014 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.
#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 "openvswitch/shash.h"
#include "smap.h"
#ifdef __cplusplus
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
* 'netdev''s flags, features, ethernet address, or carrier changes. */
uint64_t change_seq;
- /* The following are protected by 'netdev_mutex' (internal to netdev.c). */
+ /* 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 void
+static inline void
netdev_change_seq_changed(const struct netdev *netdev_)
{
struct netdev *netdev = CONST_CAST(struct netdev *, netdev_);
}
}
+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 *);
* 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.
* 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);
+ /* 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
+ * 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.
*
- * To retain ownership of 'buffers' caller can set may_steal to false.
+ * 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 a packet transmission queue,
- * so that the caller does not ordinarily have to do additional queuing of
- * packets.
+ * 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, struct dpif_packet **buffers, int cnt,
+ 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.
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'.
* 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);
+ /* 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.
+ *
+ * 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 ## */
/* ## -------------------- ## */
void (*rxq_destruct)(struct netdev_rxq *);
void (*rxq_dealloc)(struct netdev_rxq *);
- /* Attempts to receive batch of packets from 'rx' and place array of
- * pointers into '*pkts'. netdev is responsible for allocating buffers.
- * '*cnt' points to packet count for given batch. Once packets are returned
- * to caller, netdev should give up ownership of ofpbuf data.
+ /* 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.
*
- * Implementations should allocate buffer with DP_NETDEV_HEADROOM headroom
- * and add a VLAN header which is obtained out-of-band to the packet.
+ * 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().
*
- * Caller is expected to pass array of size MAX_RX_BATCH.
- * This function may be set to null if it would always return EOPNOTSUPP
- * anyhow. */
- int (*rxq_recv)(struct netdev_rxq *rx, struct dpif_packet **pkts,
- int *cnt);
+ * 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_rxq_recv()
- * on '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 netdev_register_provider(const struct netdev_class *);
int netdev_unregister_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
}