/*
- * 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 "ovs-numa.h"
+#include "packets.h"
+#include "seq.h"
#include "shash.h"
#include "smap.h"
extern "C" {
#endif
+#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
const struct netdev_class *netdev_class; /* Functions to control
this device. */
- /* The following are protected by 'netdev_mutex' (internal to netdev.c). */
+ /* 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;
+
+ /* 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;
+ /* Number of rx queues requested by user. */
+ int requested_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
+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++;
+ }
+}
+
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.
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 Partial Tunnel header. Ethernet and ip header is already built,
+ * build_header() is suppose build protocol specific part of header. */
+ int (*build_header)(const struct netdev *, struct ovs_action_push_tnl *data,
+ const struct flow *tnl_flow);
+
+ /* 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. */
+ int (*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 and rx queues of 'netdev'.
+ * Return 0 if successful, otherwise a positive errno value.
+ *
+ * 'n_rxq' specifies the maximum number of receive queues to create.
+ * The netdev provider might choose to create less (e.g. if the hardware
+ * supports only a smaller number). The actual number of queues created
+ * is stored in the 'netdev->n_rxq' field.
+ *
+ * '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.
+ *
+ * On error, the tx queue and rx queue configuration is indeterminant.
+ * Caller should make decision on whether to restore the previous or
+ * the default configuration. Also, caller must make sure there is no
+ * other thread accessing the queues at the same time. */
+ int (*set_multiq)(struct netdev *netdev, unsigned int n_txq,
+ unsigned int n_rxq);
+
+ /* 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 **buffers,
+ int cnt, 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.
* 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);
-/* ## ------------------- ## */
-/* ## netdev_rx Functions ## */
-/* ## ------------------- ## */
+/* ## -------------------- ## */
+/* ## 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 tailroom of 'buffer',
- * which should initially be empty. If successful, returns 0 and
- * increments 'buffer->size' by the number of bytes in the received packet,
- * otherwise a positive 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 'ofpbuf_tailroom(buffer)'.
- *
- * Implementations may make use of VLAN_HEADER_LEN bytes of tailroom to
- * add a VLAN header which is obtained out-of-band to the packet. If
- * this occurs then VLAN_HEADER_LEN bytes of tailroom will no longer be
- * available for the packet, otherwise it may be used for the packet
- * itself.
- *
- * It is advised that the tailroom of 'buffer' should be
- * VLAN_HEADER_LEN bytes longer than the MTU to allow space for an
- * out-of-band VLAN header to be added to the packet.
- *
- * This function may be set to null if it would always return EOPNOTSUPP
- * anyhow. */
- int (*rx_recv)(struct netdev_rx *rx, struct ofpbuf *buffer);
+ 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'. The caller supplies
+ * 'pkts' 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 '*cnt', and returns 0.
+ *
+ * The implementation does not necessarily initialize any non-data members
+ * of 'pkts'. 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 **pkts,
+ int *cnt);
/* 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);
-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
}
projects / cascardo / ovs.git / blobdiff