#include <linux/mm.h>
#include <linux/module.h>
#include <linux/pagemap.h>
+#include <linux/refcount.h>
#include <linux/stat.h>
#include <linux/string.h>
#include <linux/syscalls.h>
#include <lnet/lib-lnet.h>
#include <lnet/socklnd.h>
+#include <libcfs/linux/linux-net.h>
+
#ifndef NETIF_F_CSUM_MASK
# define NETIF_F_CSUM_MASK NETIF_F_ALL_CSUM
#endif
#define SOCKNAL_NSCHEDS_HIGH (SOCKNAL_NSCHEDS << 1)
#define SOCKNAL_PEER_HASH_BITS 7 /* log2 of # peer_ni lists */
-#define SOCKNAL_RESCHED 100 /* # scheduler loops before reschedule */
#define SOCKNAL_INSANITY_RECONN 5000 /* connd is trying on reconn infinitely */
#define SOCKNAL_ENOMEM_RETRY 1 /* seconds between retries */
#define KSOCK_THREAD_SID(id) ((id) & ((1UL << KSOCK_CPT_SHIFT) - 1))
struct ksock_interface { /* in-use interface */
- __u32 ksni_ipaddr; /* interface's IP address */
+ int ksni_index; /* Linux interface index */
+ struct sockaddr_storage ksni_addr; /* interface's address */
__u32 ksni_netmask; /* interface's network mask */
int ksni_nroutes; /* # routes using (active) */
int ksni_npeers; /* # peers using (passive) */
__u64 ksnn_incarnation; /* my epoch */
struct list_head ksnn_list; /* chain on global list */
atomic_t ksnn_npeers; /* # peers */
- int ksnn_ninterfaces; /* IP interfaces */
- struct ksock_interface ksnn_interfaces[LNET_INTERFACES_NUM];
+ struct ksock_interface ksnn_interface; /* IP interface */
};
/* When the ksock_net is shut down, this (negative) bias is added to
* ksnn_npeers, which prevents new peers from being added.
/* hash table of all my known peers */
DECLARE_HASHTABLE(ksnd_peers, SOCKNAL_PEER_HASH_BITS);
- int ksnd_nthreads; /* # live threads */
+ atomic_t ksnd_nthreads; /* # live threads */
int ksnd_shuttingdown; /* tell threads to exit */
/* schedulers information */
struct ksock_sched **ksnd_schedulers;
#define SOCKNAL_INIT_DATA 1
#define SOCKNAL_INIT_ALL 2
-/* A packet just assembled for transmission is represented by 1 or more
- * struct kvec fragments (the first frag contains the portals header),
- * followed by 0 or more lnet_kiov_t fragments.
+/* A packet just assembled for transmission is represented by 1
+ * struct iovec fragment - the portals header - followed by 0
+ * or more struct bio_vec fragments.
*
* On the receive side, initially 1 struct kvec fragment is posted for
* receive (the header). Once the header has been received, the payload is
- * received into either struct kvec or lnet_kiov_t fragments, depending on
- * what the header matched or whether the message needs forwarding. */
-
+ * received into struct bio_vec fragments.
+ */
struct ksock_conn; /* forward ref */
struct ksock_route; /* forward ref */
struct ksock_proto; /* forward ref */
struct ksock_tx { /* transmit packet */
- struct list_head tx_list; /* queue on conn for transmission etc */
- struct list_head tx_zc_list; /* queue on peer_ni for ZC request */
- atomic_t tx_refcount; /* tx reference count */
- int tx_nob; /* # packet bytes */
- int tx_resid; /* residual bytes */
- int tx_niov; /* # packet kvec frags */
- struct kvec *tx_iov; /* packet kvec frags */
- int tx_nkiov; /* # packet page frags */
- unsigned short tx_zc_aborted; /* aborted ZC request */
- unsigned short tx_zc_capable:1; /* payload is large enough for ZC */
- unsigned short tx_zc_checked:1; /* Have I checked if I should ZC? */
- unsigned short tx_nonblk:1; /* it's a non-blocking ACK */
- lnet_kiov_t *tx_kiov; /* packet page frags */
- struct ksock_conn *tx_conn; /* owning conn */
- struct lnet_msg *tx_lnetmsg; /* lnet message for lnet_finalize() */
- time64_t tx_deadline; /* when (in secs) tx times out */
- struct ksock_msg tx_msg; /* socklnd message buffer */
- int tx_desc_size; /* size of this descriptor */
+ struct list_head tx_list; /* queue on conn for transmission etc */
+ struct list_head tx_zc_list; /* queue on peer_ni for ZC request */
+ refcount_t tx_refcount; /* tx reference count */
+ int tx_nob; /* # packet bytes */
+ int tx_resid; /* residual bytes */
+ int tx_niov; /* # packet kvec frags */
+ int tx_nkiov; /* # packet page frags */
+ unsigned short tx_zc_aborted; /* aborted ZC request */
+ unsigned short tx_zc_capable:1; /* payload is large enough for ZC */
+ unsigned short tx_zc_checked:1; /* Have I checked if I should ZC? */
+ unsigned short tx_nonblk:1; /* it's a non-blocking ACK */
+ struct bio_vec *tx_kiov; /* packet page frags */
+ struct ksock_conn *tx_conn; /* owning conn */
+ struct lnet_msg *tx_lnetmsg; /* lnet message for lnet_finalize() */
+ time64_t tx_deadline; /* when (in secs) tx times out */
+ struct ksock_msg tx_msg; /* socklnd message buffer */
+ int tx_desc_size; /* size of this descriptor */
enum lnet_msg_hstatus tx_hstatus; /* health status of tx */
- union {
- struct {
- struct kvec iov; /* virt hdr */
- lnet_kiov_t kiov[0]; /* paged payload */
- } paged;
- struct {
- struct kvec iov[1]; /* virt hdr + payload */
- } virt;
- } tx_frags;
+ struct kvec tx_hdr; /* virt hdr */
+ struct bio_vec tx_payload[0]; /* paged payload */
};
-#define KSOCK_NOOP_TX_SIZE ((int)offsetof(struct ksock_tx, tx_frags.paged.kiov[0]))
-
-/* network zero copy callback descriptor embedded in struct ksock_tx */
+#define KSOCK_NOOP_TX_SIZE ((int)offsetof(struct ksock_tx, tx_payload[0]))
/* space for the rx frag descriptors; we either read a single contiguous
* header, or up to LNET_MAX_IOV frags of payload of either type. */
union ksock_rxiovspace {
struct kvec iov[LNET_MAX_IOV];
- lnet_kiov_t kiov[LNET_MAX_IOV];
+ struct bio_vec kiov[LNET_MAX_IOV];
};
#define SOCKNAL_RX_KSM_HEADER 1 /* reading ksock message header */
#define SOCKNAL_RX_SLOP 6 /* skipping body */
struct ksock_conn {
- struct ksock_peer_ni *ksnc_peer; /* owning peer_ni */
- struct ksock_route *ksnc_route; /* owning route */
- struct list_head ksnc_list; /* stash on peer_ni's conn list */
- struct socket *ksnc_sock; /* actual socket */
- void *ksnc_saved_data_ready; /* socket's original data_ready() callback */
- void *ksnc_saved_write_space; /* socket's original write_space() callback */
- atomic_t ksnc_conn_refcount; /* conn refcount */
- atomic_t ksnc_sock_refcount; /* sock refcount */
- struct ksock_sched *ksnc_scheduler; /* who schedules this connection */
- __u32 ksnc_myipaddr; /* my IP */
- __u32 ksnc_ipaddr; /* peer_ni's IP */
- int ksnc_port; /* peer_ni's port */
- signed int ksnc_type:3; /* type of connection,
- * should be signed value */
- unsigned int ksnc_closing:1; /* being shut down */
- unsigned int ksnc_flip:1; /* flip or not, only for V2.x */
- unsigned int ksnc_zc_capable:1; /* enable to ZC */
+ struct ksock_peer_ni *ksnc_peer; /* owning peer_ni */
+ struct ksock_route *ksnc_route; /* owning route */
+ struct list_head ksnc_list; /* on peer_ni's conn list */
+ struct socket *ksnc_sock; /* actual socket */
+ void *ksnc_saved_data_ready; /* socket's original
+ * data_ready() cb */
+ void *ksnc_saved_write_space; /* socket's original
+ * write_space() cb */
+ refcount_t ksnc_conn_refcount; /* conn refcount */
+ refcount_t ksnc_sock_refcount; /* sock refcount */
+ struct ksock_sched *ksnc_scheduler; /* who schedules this
+ * connection */
+ struct sockaddr_storage ksnc_myaddr; /* my address */
+ struct sockaddr_storage ksnc_peeraddr; /* peer_ni's address */
+ signed int ksnc_type:3; /* type of connection,
+ * should be signed
+ * value */
+ unsigned int ksnc_closing:1; /* being shut down */
+ unsigned int ksnc_flip:1; /* flip or not, only for V2.x */
+ unsigned int ksnc_zc_capable:1; /* enable to ZC */
const struct ksock_proto *ksnc_proto; /* protocol for the connection */
/* READER */
int ksnc_rx_nob_wanted; /* bytes actually wanted */
int ksnc_rx_niov; /* # kvec frags */
struct kvec *ksnc_rx_iov; /* the kvec frags */
- int ksnc_rx_nkiov; /* # page frags */
- lnet_kiov_t *ksnc_rx_kiov; /* the page frags */
+ int ksnc_rx_nkiov; /* # page frags */
+ struct bio_vec *ksnc_rx_kiov; /* the page frags */
union ksock_rxiovspace ksnc_rx_iov_space;/* space for frag descriptors */
- __u32 ksnc_rx_csum; /* partial checksum for incoming data */
+ __u32 ksnc_rx_csum; /* partial checksum for incoming
+ * data */
struct lnet_msg *ksnc_lnet_msg; /* rx lnet_finalize arg*/
struct ksock_msg ksnc_msg; /* incoming message buffer:
* V2.x message takes the
};
struct ksock_route {
- struct list_head ksnr_list; /* chain on peer_ni route list */
- struct list_head ksnr_connd_list; /* chain on ksnr_connd_routes */
- struct ksock_peer_ni *ksnr_peer; /* owning peer_ni */
- atomic_t ksnr_refcount; /* # users */
- time64_t ksnr_timeout; /* when (in secs) reconnection can happen next */
- time64_t ksnr_retry_interval; /* how long between retries */
- __u32 ksnr_myipaddr; /* my IP */
- __u32 ksnr_ipaddr; /* IP address to connect to */
- int ksnr_port; /* port to connect to */
- unsigned int ksnr_scheduled:1; /* scheduled for attention */
- unsigned int ksnr_connecting:1;/* connection establishment in progress */
- unsigned int ksnr_connected:4; /* connections established by type */
- unsigned int ksnr_deleted:1; /* been removed from peer_ni? */
- unsigned int ksnr_share_count; /* created explicitly? */
- int ksnr_conn_count; /* # conns established by this route */
+ struct list_head ksnr_list; /* chain on peer_ni route list*/
+ struct list_head ksnr_connd_list;/* chain on ksnr_connd_routes */
+ struct ksock_peer_ni *ksnr_peer; /* owning peer_ni */
+ refcount_t ksnr_refcount; /* # users */
+ time64_t ksnr_timeout; /* when (in secs) reconnection
+ * can happen next
+ */
+ time64_t ksnr_retry_interval;/* secs between retries */
+ int ksnr_myiface; /* interface index */
+ struct sockaddr_storage ksnr_addr; /* IP address to connect to */
+ unsigned int ksnr_scheduled:1;/* scheduled for attention */
+ unsigned int ksnr_connecting:1;/* connection in progress */
+ unsigned int ksnr_connected:4;/* connections by type */
+ unsigned int ksnr_deleted:1; /* been removed from peer_ni? */
+ unsigned int ksnr_share_count;/* created explicitly? */
+ int ksnr_conn_count;/* # conns for this route */
};
#define SOCKNAL_KEEPALIVE_PING 1 /* cookie for keepalive ping */
struct hlist_node ksnp_list; /* stash on global peer_ni list */
time64_t ksnp_last_alive;/* when (in seconds) I was last alive */
struct lnet_process_id ksnp_id; /* who's on the other end(s) */
- atomic_t ksnp_refcount; /* # users */
+ refcount_t ksnp_refcount; /* # users */
int ksnp_closing; /* being closed */
int ksnp_accepting; /* # passive connections pending */
int ksnp_error; /* errno on closing last conn */
static inline int
ksocknal_route_mask(void)
{
- if (!*ksocknal_tunables.ksnd_typed_conns)
- return (1 << SOCKLND_CONN_ANY);
+ if (!*ksocknal_tunables.ksnd_typed_conns)
+ return BIT(SOCKLND_CONN_ANY);
- return ((1 << SOCKLND_CONN_CONTROL) |
- (1 << SOCKLND_CONN_BULK_IN) |
- (1 << SOCKLND_CONN_BULK_OUT));
+ return (BIT(SOCKLND_CONN_CONTROL) |
+ BIT(SOCKLND_CONN_BULK_IN) |
+ BIT(SOCKLND_CONN_BULK_OUT));
}
static inline void
ksocknal_conn_addref(struct ksock_conn *conn)
{
- LASSERT(atomic_read(&conn->ksnc_conn_refcount) > 0);
- atomic_inc(&conn->ksnc_conn_refcount);
+ refcount_inc(&conn->ksnc_conn_refcount);
}
extern void ksocknal_queue_zombie_conn(struct ksock_conn *conn);
static inline void
ksocknal_conn_decref(struct ksock_conn *conn)
{
- LASSERT(atomic_read(&conn->ksnc_conn_refcount) > 0);
- if (atomic_dec_and_test(&conn->ksnc_conn_refcount))
+ if (refcount_dec_and_test(&conn->ksnc_conn_refcount))
ksocknal_queue_zombie_conn(conn);
}
read_lock(&ksocknal_data.ksnd_global_lock);
if (!conn->ksnc_closing) {
- LASSERT(atomic_read(&conn->ksnc_sock_refcount) > 0);
- atomic_inc(&conn->ksnc_sock_refcount);
+ refcount_inc(&conn->ksnc_sock_refcount);
rc = 0;
}
read_unlock(&ksocknal_data.ksnd_global_lock);
static inline void
ksocknal_connsock_decref(struct ksock_conn *conn)
{
- LASSERT(atomic_read(&conn->ksnc_sock_refcount) > 0);
- if (atomic_dec_and_test(&conn->ksnc_sock_refcount)) {
+ if (refcount_dec_and_test(&conn->ksnc_sock_refcount)) {
LASSERT (conn->ksnc_closing);
sock_release(conn->ksnc_sock);
conn->ksnc_sock = NULL;
static inline void
ksocknal_tx_addref(struct ksock_tx *tx)
{
- LASSERT(atomic_read(&tx->tx_refcount) > 0);
- atomic_inc(&tx->tx_refcount);
+ refcount_inc(&tx->tx_refcount);
}
extern void ksocknal_tx_prep(struct ksock_conn *, struct ksock_tx *tx);
static inline void
ksocknal_tx_decref(struct ksock_tx *tx)
{
- LASSERT(atomic_read(&tx->tx_refcount) > 0);
- if (atomic_dec_and_test(&tx->tx_refcount))
+ if (refcount_dec_and_test(&tx->tx_refcount))
ksocknal_tx_done(NULL, tx, 0);
}
static inline void
ksocknal_route_addref(struct ksock_route *route)
{
- LASSERT(atomic_read(&route->ksnr_refcount) > 0);
- atomic_inc(&route->ksnr_refcount);
+ refcount_inc(&route->ksnr_refcount);
}
extern void ksocknal_destroy_route(struct ksock_route *route);
static inline void
ksocknal_route_decref(struct ksock_route *route)
{
- LASSERT(atomic_read(&route->ksnr_refcount) > 0);
- if (atomic_dec_and_test(&route->ksnr_refcount))
+ if (refcount_dec_and_test(&route->ksnr_refcount))
ksocknal_destroy_route (route);
}
static inline void
ksocknal_peer_addref(struct ksock_peer_ni *peer_ni)
{
- LASSERT(atomic_read(&peer_ni->ksnp_refcount) > 0);
- atomic_inc(&peer_ni->ksnp_refcount);
+ refcount_inc(&peer_ni->ksnp_refcount);
}
extern void ksocknal_destroy_peer(struct ksock_peer_ni *peer_ni);
static inline void
ksocknal_peer_decref(struct ksock_peer_ni *peer_ni)
{
- LASSERT (atomic_read (&peer_ni->ksnp_refcount) > 0);
- if (atomic_dec_and_test(&peer_ni->ksnp_refcount))
+ if (refcount_dec_and_test(&peer_ni->ksnp_refcount))
ksocknal_destroy_peer(peer_ni);
}
+static inline int ksocknal_timeout(void)
+{
+ return *ksocknal_tunables.ksnd_timeout ?
+ *ksocknal_tunables.ksnd_timeout :
+ lnet_get_lnd_timeout();
+}
+
int ksocknal_startup(struct lnet_ni *ni);
void ksocknal_shutdown(struct lnet_ni *ni);
int ksocknal_ctl(struct lnet_ni *ni, unsigned int cmd, void *arg);
int ksocknal_send(struct lnet_ni *ni, void *private, struct lnet_msg *lntmsg);
int ksocknal_recv(struct lnet_ni *ni, void *private, struct lnet_msg *lntmsg,
int delayed, unsigned int niov,
- struct kvec *iov, lnet_kiov_t *kiov,
+ struct bio_vec *kiov,
unsigned int offset, unsigned int mlen, unsigned int rlen);
int ksocknal_accept(struct lnet_ni *ni, struct socket *sock);
-int ksocknal_add_peer(struct lnet_ni *ni, struct lnet_process_id id, __u32 ip,
- int port);
+int ksocknal_add_peer(struct lnet_ni *ni, struct lnet_process_id id,
+ struct sockaddr *addr);
struct ksock_peer_ni *ksocknal_find_peer_locked(struct lnet_ni *ni,
struct lnet_process_id id);
struct ksock_peer_ni *ksocknal_find_peer(struct lnet_ni *ni,
extern void ksocknal_terminate_conn(struct ksock_conn *conn);
extern void ksocknal_destroy_conn(struct ksock_conn *conn);
extern int ksocknal_close_peer_conns_locked(struct ksock_peer_ni *peer_ni,
- __u32 ipaddr, int why);
+ struct sockaddr *peer, int why);
extern int ksocknal_close_conn_and_siblings(struct ksock_conn *conn, int why);
int ksocknal_close_matching_conns(struct lnet_process_id id, __u32 ipaddr);
extern struct ksock_conn *ksocknal_find_conn_locked(struct ksock_peer_ni *peer_ni,
extern void ksocknal_queue_tx_locked(struct ksock_tx *tx, struct ksock_conn *conn);
extern void ksocknal_txlist_done(struct lnet_ni *ni, struct list_head *txlist,
int error);
-extern void ksocknal_notify(lnet_nid_t gw_nid);
-extern void ksocknal_query(struct lnet_ni *ni, lnet_nid_t nid, time64_t *when);
extern int ksocknal_thread_start(int (*fn)(void *arg), void *arg, char *name);
extern void ksocknal_thread_fini(void);
extern void ksocknal_launch_all_connections_locked(struct ksock_peer_ni *peer_ni);
extern void ksocknal_lib_push_conn(struct ksock_conn *conn);
extern int ksocknal_lib_get_conn_addrs(struct ksock_conn *conn);
extern int ksocknal_lib_setup_sock(struct socket *so);
-extern int ksocknal_lib_send_iov(struct ksock_conn *conn, struct ksock_tx *tx,
+extern int ksocknal_lib_send_hdr(struct ksock_conn *conn, struct ksock_tx *tx,
struct kvec *scratch_iov);
extern int ksocknal_lib_send_kiov(struct ksock_conn *conn, struct ksock_tx *tx,
struct kvec *scratch_iov);
extern void ksocknal_lib_csum_tx(struct ksock_tx *tx);
extern int ksocknal_lib_memory_pressure(struct ksock_conn *conn);
-extern int ksocknal_lib_bind_thread_to_cpu(int id);
#endif /* _SOCKLND_SOCKLND_H_ */