X-Git-Url: http://git.cascardo.eti.br/?a=blobdiff_plain;f=lib%2Fnetdev-provider.h;h=1952a02492025852ed99eed24f529cab37678707;hb=e175dc83c5772438466bafb23a17ceb2e052e1c2;hp=2d43431f1bc2a3207cb83160c39e42a2cd39607e;hpb=666afb55e84e9118812de81a75655ec9567b7a5b;p=cascardo%2Fovs.git diff --git a/lib/netdev-provider.h b/lib/netdev-provider.h index 2d43431f1..1952a0249 100644 --- a/lib/netdev-provider.h +++ b/lib/netdev-provider.h @@ -1,5 +1,5 @@ /* - * 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. @@ -19,8 +19,12 @@ /* 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" @@ -28,39 +32,170 @@ extern "C" { #endif +#define NETDEV_NUMA_UNSPEC OVS_NUMA_UNSPEC + /* A network device (e.g. an Ethernet device). * - * Network device implementations should treat this structure as opaque. */ + * 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; + + /* 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". */ }; -void netdev_init(struct netdev *, const char *name, - const struct netdev_class *); -void netdev_uninit(struct netdev *, bool destroy); +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); -static inline void netdev_assert_class(const struct netdev *netdev, - const struct netdev_class *class_) -{ - ovs_assert(netdev->netdev_class == class_); -} +/* 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_rxq. */ +struct netdev_rxq { + struct netdev *netdev; /* Owns a reference to the netdev. */ + int queue_id; +}; + +struct netdev *netdev_rxq_get_netdev(const struct netdev_rxq *); /* Network device class structure, to be defined by each implementation of a * network device. * * These functions return 0 if successful or a positive errno value on failure, - * except where otherwise noted. */ + * except where otherwise noted. + * + * + * Data Structures + * =============== + * + * These functions work primarily with two different kinds of data structures: + * + * - "struct netdev", which represents a network device. + * + * - "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 + * generic state for the respective concept, called the "base" state. None of + * them contains any extra space for implementations to use. Instead, each + * implementation is expected to declare its own data structure that contains + * an instance of the generic data structure plus additional + * implementation-specific members, called the "derived" state. The + * implementation can use casts or (preferably) the CONTAINER_OF macro to + * obtain access to derived state given only a pointer to the embedded generic + * data structure. + * + * + * Life Cycle + * ========== + * + * Four stylized functions accompany each of these data structures: + * + * "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: + * + * 1. The client calls the "alloc" function to obtain raw memory. If "alloc" + * fails, skip all the other steps. + * + * 2. The client initializes all of the data structure's base state. If this + * fails, skip to step 7. + * + * 3. The client calls the "construct" function. The implementation + * initializes derived state. It may refer to the already-initialized + * base state. If "construct" fails, skip to step 6. + * + * 4. The data structure is now initialized and in use. + * + * 5. When the data structure is no longer needed, the client calls the + * "destruct" function. The implementation uninitializes derived state. + * The base state has not been uninitialized yet, so the implementation + * may still refer to it. + * + * 6. The client uninitializes all of the data structure's base state. + * + * 7. The client calls the "dealloc" to free the raw memory. The + * 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. + * Its purpose is just to ensure that the new data structure has enough room + * for base and derived state. It may return a null pointer if memory is not + * available, in which case none of the other functions is called. + * + * Each "construct" function initializes derived state in its respective data + * structure. When "construct" is called, all of the base state has already + * been initialized, so the "construct" function may refer to it. The + * "construct" function is allowed to fail, in which case the client calls the + * "dealloc" function (but not the "destruct" function). + * + * Each "destruct" function uninitializes and frees derived state in its + * respective data structure. When "destruct" is called, the base state has + * 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 + * "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. + * + * + * 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. * @@ -70,6 +205,10 @@ struct netdev_class { * the system. */ const char *type; +/* ## ------------------- ## */ +/* ## Top-Level Functions ## */ +/* ## ------------------- ## */ + /* Called when the netdev provider is registered, typically at program * startup. Returning an error from this function will prevent any network * device in this class from being opened. @@ -89,18 +228,16 @@ struct netdev_class { * needed here. */ void (*wait)(void); - /* Attempts to create a network device named 'name' in 'netdev_class'. On - * success sets 'netdevp' to the newly created device. */ - int (*create)(const struct netdev_class *netdev_class, const char *name, - struct netdev **netdevp); +/* ## ---------------- ## */ +/* ## netdev Functions ## */ +/* ## ---------------- ## */ - /* Destroys 'netdev'. - * - * Netdev devices maintain a reference count that is incremented on - * netdev_open() and decremented on netdev_close(). If 'netdev' - * has a non-zero reference count, then this function will not be - * called. */ - void (*destroy)(struct netdev *netdev); + /* Life-cycle functions for a netdev. See the large comment above on + * struct netdev_class. */ + struct netdev *(*alloc)(void); + int (*construct)(struct netdev *); + void (*destruct)(struct netdev *); + void (*dealloc)(struct netdev *); /* Fetches the device 'netdev''s configuration, storing it in 'args'. * The caller owns 'args' and pre-initializes it to an empty smap. @@ -122,29 +259,65 @@ struct netdev_class { const struct netdev_tunnel_config * (*get_tunnel_config)(const struct netdev *netdev); - /* Attempts to open a netdev_rx for receiving packets from 'netdev'. - * Returns 0 if successful, otherwise a positive errno value. Returns - * EOPNOTSUPP to indicate that the network device does not implement packet - * reception through this interface. This function may be set to null if - * it would always return EOPNOTSUPP anyhow. (This will prevent the - * network device from being usefully used by the netdev-based "userspace - * datapath".) - * - * On success, the implementation must set '*rxp' to a 'netdev_rx' for - * 'netdev' that it has already initialized (with netdev_rx_init()). */ - int (*rx_open)(struct netdev *netdev, struct netdev_rx **rxp); - - /* 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 @@ -152,28 +325,31 @@ struct netdev_class { * 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'. * @@ -222,7 +398,7 @@ struct netdev_class { /* 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. @@ -239,14 +415,6 @@ struct netdev_class { * (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. @@ -400,22 +568,39 @@ struct netdev_class { 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 @@ -470,11 +655,11 @@ struct netdev_class { * anyhow. */ int (*add_router)(struct netdev *netdev, struct in_addr router); - /* Looks up the next hop for 'host'. If succesful, 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. */ @@ -502,7 +687,7 @@ struct netdev_class { * 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 @@ -514,70 +699,61 @@ struct netdev_class { 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'. - * - * 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); -}; - -/* A data structure for capturing packets received by a network device. - * - * This structure should be treated as opaque by network device - * implementations. */ -struct netdev_rx { - const struct netdev_rx_class *rx_class; - struct netdev *netdev; -}; +/* ## -------------------- ## */ +/* ## netdev_rxq Functions ## */ +/* ## -------------------- ## */ -void netdev_rx_init(struct netdev_rx *, struct netdev *, - const struct netdev_rx_class *); -void netdev_rx_uninit(struct netdev_rx *); -struct netdev *netdev_rx_get_netdev(const struct netdev_rx *); +/* If a particular netdev class does not support receiving packets, all these + * function pointers must be NULL. */ -struct netdev_rx_class { - /* Destroys 'rx'. */ - void (*destroy)(struct netdev_rx *rx); + /* Life-cycle functions for a netdev_rxq. See the large comment above on + * struct netdev_class. */ + 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 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. + /* 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(). * - * Must return -EMSGSIZE, and discard the packet, if the received packet - * is longer than 'size' bytes. */ - int (*recv)(struct netdev_rx *rx, void *buffer, size_t size); + * 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 (*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 (*drain)(struct netdev_rx *rx); + int (*rxq_drain)(struct netdev_rxq *rx); }; -static inline void netdev_rx_assert_class(const struct netdev_rx *rx, - const struct netdev_rx_class *class_) -{ - ovs_assert(rx->rx_class == class_); -} - 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 }