summaryrefslogtreecommitdiff
path: root/drivers/infiniband/ulp/ipoib/ipoib.h
diff options
context:
space:
mode:
Diffstat (limited to 'drivers/infiniband/ulp/ipoib/ipoib.h')
-rw-r--r--drivers/infiniband/ulp/ipoib/ipoib.h227
1 files changed, 150 insertions, 77 deletions
diff --git a/drivers/infiniband/ulp/ipoib/ipoib.h b/drivers/infiniband/ulp/ipoib/ipoib.h
index eb71aaa26a9a..91f866e3fb8b 100644
--- a/drivers/infiniband/ulp/ipoib/ipoib.h
+++ b/drivers/infiniband/ulp/ipoib/ipoib.h
@@ -52,7 +52,6 @@
#include <rdma/ib_pack.h>
#include <rdma/ib_sa.h>
#include <linux/sched.h>
-
/* constants */
enum ipoib_flush_level {
@@ -63,6 +62,8 @@ enum ipoib_flush_level {
enum {
IPOIB_ENCAP_LEN = 4,
+ IPOIB_PSEUDO_LEN = 20,
+ IPOIB_HARD_LEN = IPOIB_ENCAP_LEN + IPOIB_PSEUDO_LEN,
IPOIB_UD_HEAD_SIZE = IB_GRH_BYTES + IPOIB_ENCAP_LEN,
IPOIB_UD_RX_SG = 2, /* max buffer needed for 4K mtu */
@@ -80,29 +81,35 @@ enum {
IPOIB_NUM_WC = 4,
IPOIB_MAX_PATH_REC_QUEUE = 3,
- IPOIB_MAX_MCAST_QUEUE = 3,
+ IPOIB_MAX_MCAST_QUEUE = 64,
IPOIB_FLAG_OPER_UP = 0,
IPOIB_FLAG_INITIALIZED = 1,
IPOIB_FLAG_ADMIN_UP = 2,
IPOIB_PKEY_ASSIGNED = 3,
- IPOIB_PKEY_STOP = 4,
IPOIB_FLAG_SUBINTERFACE = 5,
- IPOIB_MCAST_RUN = 6,
IPOIB_STOP_REAPER = 7,
IPOIB_FLAG_ADMIN_CM = 9,
IPOIB_FLAG_UMCAST = 10,
- IPOIB_STOP_NEIGH_GC = 11,
IPOIB_NEIGH_TBL_FLUSH = 12,
+ IPOIB_FLAG_DEV_ADDR_SET = 13,
+ IPOIB_FLAG_DEV_ADDR_CTRL = 14,
IPOIB_MAX_BACKOFF_SECONDS = 16,
IPOIB_MCAST_FLAG_FOUND = 0, /* used in set_multicast_list */
IPOIB_MCAST_FLAG_SENDONLY = 1,
- IPOIB_MCAST_FLAG_BUSY = 2, /* joining or already joined */
+ /*
+ * For IPOIB_MCAST_FLAG_BUSY
+ * When set, in flight join and mcast->mc is unreliable
+ * When clear and mcast->mc IS_ERR_OR_NULL, need to restart or
+ * haven't started yet
+ * When clear and mcast->mc is valid pointer, join was successful
+ */
+ IPOIB_MCAST_FLAG_BUSY = 2,
IPOIB_MCAST_FLAG_ATTACHED = 3,
- MAX_SEND_CQE = 16,
+ MAX_SEND_CQE = 64,
IPOIB_CM_COPYBREAK = 256,
IPOIB_NON_CHILD = 0,
@@ -126,11 +133,30 @@ struct ipoib_header {
u16 reserved;
};
-struct ipoib_cb {
- struct qdisc_skb_cb qdisc_cb;
- u8 hwaddr[INFINIBAND_ALEN];
+struct ipoib_pseudo_header {
+ u8 hwaddr[INFINIBAND_ALEN];
};
+static inline void skb_add_pseudo_hdr(struct sk_buff *skb)
+{
+ char *data = skb_push(skb, IPOIB_PSEUDO_LEN);
+
+ /*
+ * only the ipoib header is present now, make room for a dummy
+ * pseudo header and set skb field accordingly
+ */
+ memset(data, 0, IPOIB_PSEUDO_LEN);
+ skb_reset_mac_header(skb);
+ skb_pull(skb, IPOIB_HARD_LEN);
+}
+
+static inline struct ipoib_dev_priv *ipoib_priv(const struct net_device *dev)
+{
+ struct rdma_netdev *rn = netdev_priv(dev);
+
+ return rn->clnt_priv;
+}
+
/* Used for all multicast joins (broadcast, IPv4 mcast and IPv6 mcast) */
struct ipoib_mcast {
struct ib_sa_mcmember_rec mcmember;
@@ -142,6 +168,7 @@ struct ipoib_mcast {
unsigned long created;
unsigned long backoff;
+ unsigned long delay_until;
unsigned long flags;
unsigned char logcount;
@@ -151,6 +178,7 @@ struct ipoib_mcast {
struct sk_buff_head pkt_queue;
struct net_device *dev;
+ struct completion done;
};
struct ipoib_rx_buf {
@@ -163,11 +191,6 @@ struct ipoib_tx_buf {
u64 mapping[MAX_SKB_FRAGS + 1];
};
-struct ipoib_cm_tx_buf {
- struct sk_buff *skb;
- u64 mapping;
-};
-
struct ib_cm_id;
struct ipoib_cm_data {
@@ -225,12 +248,12 @@ struct ipoib_cm_tx {
struct list_head list;
struct net_device *dev;
struct ipoib_neigh *neigh;
- struct ipoib_path *path;
- struct ipoib_cm_tx_buf *tx_ring;
- unsigned tx_head;
- unsigned tx_tail;
+ struct ipoib_tx_buf *tx_ring;
+ unsigned int tx_head;
+ unsigned int tx_tail;
unsigned long flags;
u32 mtu;
+ unsigned int max_send_sge;
};
struct ipoib_cm_rx_buf {
@@ -285,6 +308,11 @@ struct ipoib_neigh_table {
struct completion deleted;
};
+struct ipoib_qp_state_validate {
+ struct work_struct work;
+ struct ipoib_dev_priv *priv;
+};
+
/*
* Device private locking: network stack tx_lock protects members used
* in TX fast path, lock protects everything else. lock nests inside
@@ -294,12 +322,14 @@ struct ipoib_dev_priv {
spinlock_t lock;
struct net_device *dev;
+ void (*next_priv_destructor)(struct net_device *dev);
- struct napi_struct napi;
+ struct napi_struct send_napi;
+ struct napi_struct recv_napi;
unsigned long flags;
- struct mutex vlan_mutex;
+ struct mutex mcast_mutex;
struct rb_root path_tree;
struct list_head path_list;
@@ -310,13 +340,15 @@ struct ipoib_dev_priv {
struct list_head multicast_list;
struct rb_root multicast_tree;
- struct delayed_work pkey_poll_task;
+ struct workqueue_struct *wq;
struct delayed_work mcast_task;
struct work_struct carrier_on_task;
+ struct work_struct reschedule_napi_work;
struct work_struct flush_light;
struct work_struct flush_normal;
struct work_struct flush_heavy;
struct work_struct restart_task;
+ struct work_struct tx_timeout_work;
struct delayed_work ah_reap_task;
struct delayed_work neigh_reap_task;
struct ib_device *ca;
@@ -324,14 +356,13 @@ struct ipoib_dev_priv {
u16 pkey;
u16 pkey_index;
struct ib_pd *pd;
- struct ib_mr *mr;
struct ib_cq *recv_cq;
struct ib_cq *send_cq;
struct ib_qp *qp;
u32 qkey;
union ib_gid local_gid;
- u16 local_lid;
+ u32 local_lid;
unsigned int admin_mtu;
unsigned int mcast_mtu;
@@ -340,11 +371,14 @@ struct ipoib_dev_priv {
struct ipoib_rx_buf *rx_ring;
struct ipoib_tx_buf *tx_ring;
- unsigned tx_head;
- unsigned tx_tail;
+ /* cyclic ring variables for managing tx_ring, for UD only */
+ unsigned int tx_head;
+ unsigned int tx_tail;
+ /* cyclic ring variables for counting overall outstanding send WRs */
+ unsigned int global_tx_head;
+ unsigned int global_tx_tail;
struct ib_sge tx_sge[MAX_SKB_FRAGS + 1];
- struct ib_send_wr tx_wr;
- unsigned tx_outstanding;
+ struct ib_ud_wr tx_wr;
struct ib_wc send_wc[MAX_SEND_CQE];
struct ib_recv_wr rx_wr;
@@ -357,6 +391,9 @@ struct ipoib_dev_priv {
struct ib_event_handler event_handler;
struct net_device *parent;
+ /* 'child_intfs' and 'list' membership of all child devices are
+ * protected by the netdev instance lock of 'dev'.
+ */
struct list_head child_intfs;
struct list_head list;
int child_type;
@@ -370,9 +407,11 @@ struct ipoib_dev_priv {
struct dentry *mcg_dentry;
struct dentry *path_dentry;
#endif
- int hca_caps;
+ u64 hca_caps;
+ u64 kernel_caps;
struct ipoib_ethtool_st ethtool;
- struct timer_list poll_timer;
+ unsigned int max_send_sge;
+ const struct net_device_ops *rn_ops;
};
struct ipoib_ah {
@@ -380,12 +419,13 @@ struct ipoib_ah {
struct ib_ah *ah;
struct list_head list;
struct kref ref;
- unsigned last_send;
+ unsigned int last_send;
+ int valid;
};
struct ipoib_path {
struct net_device *dev;
- struct ib_sa_path_rec pathrec;
+ struct sa_path_rec pathrec;
struct ipoib_ah *ah;
struct sk_buff_head queue;
@@ -397,7 +437,6 @@ struct ipoib_path {
struct rb_node rb_node;
struct list_head list;
- int valid;
};
struct ipoib_neigh {
@@ -413,22 +452,17 @@ struct ipoib_neigh {
struct list_head list;
struct ipoib_neigh __rcu *hnext;
struct rcu_head rcu;
- atomic_t refcnt;
+ refcount_t refcnt;
unsigned long alive;
};
#define IPOIB_UD_MTU(ib_mtu) (ib_mtu - IPOIB_ENCAP_LEN)
#define IPOIB_UD_BUF_SIZE(ib_mtu) (ib_mtu + IB_GRH_BYTES)
-static inline int ipoib_ud_need_sg(unsigned int ib_mtu)
-{
- return IPOIB_UD_BUF_SIZE(ib_mtu) > PAGE_SIZE;
-}
-
void ipoib_neigh_dtor(struct ipoib_neigh *neigh);
static inline void ipoib_neigh_put(struct ipoib_neigh *neigh)
{
- if (atomic_dec_and_test(&neigh->refcnt))
+ if (refcount_dec_and_test(&neigh->refcnt))
ipoib_neigh_dtor(neigh);
}
struct ipoib_neigh *ipoib_neigh_get(struct net_device *dev, u8 *daddr);
@@ -441,55 +475,90 @@ extern struct workqueue_struct *ipoib_workqueue;
/* functions */
-int ipoib_poll(struct napi_struct *napi, int budget);
-void ipoib_ib_completion(struct ib_cq *cq, void *dev_ptr);
-void ipoib_send_comp_handler(struct ib_cq *cq, void *dev_ptr);
+int ipoib_rx_poll(struct napi_struct *napi, int budget);
+int ipoib_tx_poll(struct napi_struct *napi, int budget);
+void ipoib_ib_rx_completion(struct ib_cq *cq, void *ctx_ptr);
+void ipoib_ib_tx_completion(struct ib_cq *cq, void *ctx_ptr);
struct ipoib_ah *ipoib_create_ah(struct net_device *dev,
- struct ib_pd *pd, struct ib_ah_attr *attr);
+ struct ib_pd *pd, struct rdma_ah_attr *attr);
void ipoib_free_ah(struct kref *kref);
static inline void ipoib_put_ah(struct ipoib_ah *ah)
{
kref_put(&ah->ref, ipoib_free_ah);
}
int ipoib_open(struct net_device *dev);
+void ipoib_intf_free(struct net_device *dev);
int ipoib_add_pkey_attr(struct net_device *dev);
int ipoib_add_umcast_attr(struct net_device *dev);
-void ipoib_send(struct net_device *dev, struct sk_buff *skb,
- struct ipoib_ah *address, u32 qpn);
+int ipoib_send(struct net_device *dev, struct sk_buff *skb,
+ struct ib_ah *address, u32 dqpn);
void ipoib_reap_ah(struct work_struct *work);
+void ipoib_napi_schedule_work(struct work_struct *work);
+struct ipoib_path *__path_find(struct net_device *dev, void *gid);
void ipoib_mark_paths_invalid(struct net_device *dev);
void ipoib_flush_paths(struct net_device *dev);
-struct ipoib_dev_priv *ipoib_intf_alloc(const char *format);
-
-int ipoib_ib_dev_init(struct net_device *dev, struct ib_device *ca, int port);
+struct net_device *ipoib_intf_alloc(struct ib_device *hca, u32 port,
+ const char *format);
+int ipoib_intf_init(struct ib_device *hca, u32 port, const char *format,
+ struct net_device *dev);
void ipoib_ib_dev_flush_light(struct work_struct *work);
void ipoib_ib_dev_flush_normal(struct work_struct *work);
void ipoib_ib_dev_flush_heavy(struct work_struct *work);
-void ipoib_pkey_event(struct work_struct *work);
+void ipoib_queue_work(struct ipoib_dev_priv *priv,
+ enum ipoib_flush_level level);
+void ipoib_ib_tx_timeout_work(struct work_struct *work);
void ipoib_ib_dev_cleanup(struct net_device *dev);
+int ipoib_ib_dev_open_default(struct net_device *dev);
int ipoib_ib_dev_open(struct net_device *dev);
-int ipoib_ib_dev_up(struct net_device *dev);
-int ipoib_ib_dev_down(struct net_device *dev, int flush);
-int ipoib_ib_dev_stop(struct net_device *dev, int flush);
-
-int ipoib_dev_init(struct net_device *dev, struct ib_device *ca, int port);
-void ipoib_dev_cleanup(struct net_device *dev);
+void ipoib_ib_dev_stop(struct net_device *dev);
+void ipoib_ib_dev_up(struct net_device *dev);
+void ipoib_ib_dev_down(struct net_device *dev);
+int ipoib_ib_dev_stop_default(struct net_device *dev);
+void ipoib_pkey_dev_check_presence(struct net_device *dev);
void ipoib_mcast_join_task(struct work_struct *work);
void ipoib_mcast_carrier_on_task(struct work_struct *work);
void ipoib_mcast_send(struct net_device *dev, u8 *daddr, struct sk_buff *skb);
void ipoib_mcast_restart_task(struct work_struct *work);
-int ipoib_mcast_start_thread(struct net_device *dev);
-int ipoib_mcast_stop_thread(struct net_device *dev, int flush);
+void ipoib_mcast_start_thread(struct net_device *dev);
+void ipoib_mcast_stop_thread(struct net_device *dev);
-void ipoib_mcast_dev_down(struct net_device *dev);
void ipoib_mcast_dev_flush(struct net_device *dev);
+int ipoib_dma_map_tx(struct ib_device *ca, struct ipoib_tx_buf *tx_req);
+void ipoib_dma_unmap_tx(struct ipoib_dev_priv *priv,
+ struct ipoib_tx_buf *tx_req);
+
+struct rtnl_link_ops *ipoib_get_link_ops(void);
+
+static inline void ipoib_build_sge(struct ipoib_dev_priv *priv,
+ struct ipoib_tx_buf *tx_req)
+{
+ int i, off;
+ struct sk_buff *skb = tx_req->skb;
+ skb_frag_t *frags = skb_shinfo(skb)->frags;
+ int nr_frags = skb_shinfo(skb)->nr_frags;
+ u64 *mapping = tx_req->mapping;
+
+ if (skb_headlen(skb)) {
+ priv->tx_sge[0].addr = mapping[0];
+ priv->tx_sge[0].length = skb_headlen(skb);
+ off = 1;
+ } else
+ off = 0;
+
+ for (i = 0; i < nr_frags; ++i) {
+ priv->tx_sge[i + off].addr = mapping[i + off];
+ priv->tx_sge[i + off].length = skb_frag_size(&frags[i]);
+ }
+ priv->tx_wr.wr.num_sge = nr_frags + off;
+}
+
#ifdef CONFIG_INFINIBAND_IPOIB_DEBUG
struct ipoib_mcast_iter *ipoib_mcast_iter_init(struct net_device *dev);
int ipoib_mcast_iter_next(struct ipoib_mcast_iter *iter);
@@ -506,8 +575,13 @@ void ipoib_path_iter_read(struct ipoib_path_iter *iter,
struct ipoib_path *path);
#endif
-int ipoib_mcast_attach(struct net_device *dev, u16 mlid,
- union ib_gid *mgid, int set_qkey);
+int ipoib_mcast_attach(struct net_device *dev, struct ib_device *hca,
+ union ib_gid *mgid, u16 mlid, int set_qkey, u32 qkey);
+int ipoib_mcast_detach(struct net_device *dev, struct ib_device *hca,
+ union ib_gid *mgid, u16 mlid);
+void ipoib_mcast_remove_list(struct list_head *remove_list);
+void ipoib_check_and_add_mcast_sendonly(struct ipoib_dev_priv *priv, u8 *mgid,
+ struct list_head *remove_list);
int ipoib_init_qp(struct net_device *dev);
int ipoib_transport_dev_init(struct net_device *dev, struct ib_device *ca);
@@ -528,14 +602,11 @@ void __exit ipoib_netlink_fini(void);
void ipoib_set_umcast(struct net_device *ndev, int umcast_val);
int ipoib_set_mode(struct net_device *dev, const char *buf);
-void ipoib_setup(struct net_device *dev);
+void ipoib_setup_common(struct net_device *dev);
-void ipoib_pkey_poll(struct work_struct *work);
-int ipoib_pkey_dev_delay_open(struct net_device *dev);
void ipoib_drain_cq(struct net_device *dev);
void ipoib_set_ethtool_ops(struct net_device *dev);
-int ipoib_set_dev_features(struct ipoib_dev_priv *priv, struct ib_device *hca);
#define IPOIB_FLAGS_RC 0x80
#define IPOIB_FLAGS_UC 0x40
@@ -549,14 +620,14 @@ extern int ipoib_max_conn_qp;
static inline int ipoib_cm_admin_enabled(struct net_device *dev)
{
- struct ipoib_dev_priv *priv = netdev_priv(dev);
+ struct ipoib_dev_priv *priv = ipoib_priv(dev);
return IPOIB_CM_SUPPORTED(dev->dev_addr) &&
test_bit(IPOIB_FLAG_ADMIN_CM, &priv->flags);
}
static inline int ipoib_cm_enabled(struct net_device *dev, u8 *hwaddr)
{
- struct ipoib_dev_priv *priv = netdev_priv(dev);
+ struct ipoib_dev_priv *priv = ipoib_priv(dev);
return IPOIB_CM_SUPPORTED(hwaddr) &&
test_bit(IPOIB_FLAG_ADMIN_CM, &priv->flags);
}
@@ -579,13 +650,13 @@ static inline void ipoib_cm_set(struct ipoib_neigh *neigh, struct ipoib_cm_tx *t
static inline int ipoib_cm_has_srq(struct net_device *dev)
{
- struct ipoib_dev_priv *priv = netdev_priv(dev);
+ struct ipoib_dev_priv *priv = ipoib_priv(dev);
return !!priv->cm.srq;
}
static inline unsigned int ipoib_cm_max_mtu(struct net_device *dev)
{
- struct ipoib_dev_priv *priv = netdev_priv(dev);
+ struct ipoib_dev_priv *priv = ipoib_priv(dev);
return priv->cm.max_cm_mtu;
}
@@ -604,8 +675,6 @@ void ipoib_cm_handle_rx_wc(struct net_device *dev, struct ib_wc *wc);
void ipoib_cm_handle_tx_wc(struct net_device *dev, struct ib_wc *wc);
#else
-struct ipoib_cm_tx;
-
#define ipoib_max_conn_qp 0
static inline int ipoib_cm_admin_enabled(struct net_device *dev)
@@ -664,7 +733,7 @@ void ipoib_cm_dev_stop(struct net_device *dev)
static inline
int ipoib_cm_dev_init(struct net_device *dev)
{
- return -ENOSYS;
+ return -EOPNOTSUPP;
}
static inline
@@ -710,19 +779,25 @@ static inline void ipoib_cm_handle_tx_wc(struct net_device *dev, struct ib_wc *w
#ifdef CONFIG_INFINIBAND_IPOIB_DEBUG
void ipoib_create_debug_files(struct net_device *dev);
void ipoib_delete_debug_files(struct net_device *dev);
-int ipoib_register_debugfs(void);
+void ipoib_register_debugfs(void);
void ipoib_unregister_debugfs(void);
#else
static inline void ipoib_create_debug_files(struct net_device *dev) { }
static inline void ipoib_delete_debug_files(struct net_device *dev) { }
-static inline int ipoib_register_debugfs(void) { return 0; }
+static inline void ipoib_register_debugfs(void) { }
static inline void ipoib_unregister_debugfs(void) { }
#endif
#define ipoib_printk(level, priv, format, arg...) \
printk(level "%s: " format, ((struct ipoib_dev_priv *) priv)->dev->name , ## arg)
#define ipoib_warn(priv, format, arg...) \
- ipoib_printk(KERN_WARNING, priv, format , ## arg)
+do { \
+ static DEFINE_RATELIMIT_STATE(_rs, \
+ 10 * HZ /*10 seconds */, \
+ 100); \
+ if (__ratelimit(&_rs)) \
+ ipoib_printk(KERN_WARNING, priv, format , ## arg);\
+} while (0)
extern int ipoib_sendq_size;
extern int ipoib_recvq_size;
@@ -762,6 +837,4 @@ extern int ipoib_debug_level;
#define IPOIB_QPN(ha) (be32_to_cpup((__be32 *) ha) & 0xffffff)
-extern const char ipoib_driver_version[];
-
#endif /* _IPOIB_H */
generated by cgit (git 2.34.1) at 2025-12-26 07:41:01 +0000