#include <linux/sysctl.h>
#include <linux/uio.h>
#include <linux/unistd.h>
+#include <linux/hashtable.h>
#include <net/sock.h>
#include <net/tcp.h>
#include <lnet/lib-lnet.h>
#include <lnet/socklnd.h>
-#ifdef HAVE_TCP_SENDPAGE_USE_SOCKET
-# define cfs_tcp_sendpage(sk, page, offset, size, flags) \
- tcp_sendpage((sk)->sk_socket, page, offset, size, flags)
-#else /* !HAVE_TCP_SENDPAGE_USE_SOCKET */
-# define cfs_tcp_sendpage(sk, page, offset, size, flags) \
- tcp_sendpage(sk, page, offset, size, flags)
-#endif /* HAVE_TCP_SENDPAGE_USE_SOCKET */
-
#ifndef NETIF_F_CSUM_MASK
# define NETIF_F_CSUM_MASK NETIF_F_ALL_CSUM
#endif
#define SOCKNAL_NSCHEDS 3
#define SOCKNAL_NSCHEDS_HIGH (SOCKNAL_NSCHEDS << 1)
-#define SOCKNAL_PEER_HASH_SIZE 101 /* # 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 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 SOCKNAL_SINGLE_FRAG_TX 0 /* disable multi-fragment sends */
-#define SOCKNAL_SINGLE_FRAG_RX 0 /* disable multi-fragment receives */
+#define SOCKNAL_SINGLE_FRAG_TX 0 /* disable multi-fragment sends */
+#define SOCKNAL_SINGLE_FRAG_RX 0 /* disable multi-fragment receives */
-#define SOCKNAL_VERSION_DEBUG 0 /* enable protocol version debugging */
+#define SOCKNAL_VERSION_DEBUG 0 /* enable protocol version debugging */
/* risk kmap deadlock on multi-frag I/O (backs off to single-frag if disabled).
* no risk if we're not running on a CONFIG_HIGHMEM platform. */
#define KSOCK_THREAD_SID(id) ((id) & ((1UL << KSOCK_CPT_SHIFT) - 1))
struct ksock_interface { /* in-use interface */
+ int ksni_index; /* Linux interface index */
__u32 ksni_ipaddr; /* interface's IP address */
__u32 ksni_netmask; /* interface's network mask */
int ksni_nroutes; /* # routes using (active) */
unsigned int *ksnd_zc_min_payload; /* minimum zero copy payload size */
int *ksnd_zc_recv; /* enable ZC receive (for Chelsio TOE) */
int *ksnd_zc_recv_min_nfrags; /* minimum # of fragments to enable ZC receive */
-#ifdef CPU_AFFINITY
int *ksnd_irq_affinity; /* enable IRQ affinity? */
-#endif
#ifdef SOCKNAL_BACKOFF
int *ksnd_backoff_init; /* initial TCP backoff */
int *ksnd_backoff_max; /* maximum TCP backoff */
struct ksock_net {
__u64 ksnn_incarnation; /* my epoch */
- spinlock_t ksnn_lock; /* serialise */
struct list_head ksnn_list; /* chain on global list */
- int ksnn_npeers; /* # peers */
- int ksnn_shutdown; /* shutting down? */
+ atomic_t ksnn_npeers; /* # peers */
int ksnn_ninterfaces; /* IP interfaces */
struct ksock_interface ksnn_interfaces[LNET_INTERFACES_NUM];
};
+/* When the ksock_net is shut down, this (negative) bias is added to
+ * ksnn_npeers, which prevents new peers from being added.
+ */
+#define SOCKNAL_SHUTDOWN_BIAS (INT_MIN+1)
/** connd timeout */
#define SOCKNAL_CONND_TIMEOUT 120
/* stabilize peer_ni/conn ops */
rwlock_t ksnd_global_lock;
/* hash table of all my known peers */
- struct list_head *ksnd_peers;
- int ksnd_peer_hash_size; /* size of ksnd_peers */
+ DECLARE_HASHTABLE(ksnd_peers, SOCKNAL_PEER_HASH_BITS);
int ksnd_nthreads; /* # live threads */
int ksnd_shuttingdown; /* tell threads to exit */
/* 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.
+ * 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
+ * received into either struct kvec or struct bio_vec fragments, depending on
* what the header matched or whether the message needs forwarding. */
-struct ksock_conn; /* forward ref */
-struct ksock_peer; /* forward ref */
-struct ksock_route; /* forward ref */
-struct ksock_proto; /* forward ref */
+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 */
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 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 */
union {
struct {
struct kvec iov; /* virt hdr */
- lnet_kiov_t kiov[0]; /* paged payload */
+ struct bio_vec kiov[0]; /* paged payload */
} paged;
struct {
struct kvec iov[1]; /* virt hdr + payload */
* 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 */
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_proto *ksnc_proto; /* protocol for the connection */
+ 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 */
+ atomic_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 */
+ __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 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 ksock_peer_ni {
- struct list_head ksnp_list; /* stash on global peer_ni list */
+ 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 */
- int ksnp_sharecount; /* lconf usage counter */
- int ksnp_closing; /* being closed */
- int ksnp_accepting;/* # passive connections pending */
- int ksnp_error; /* errno on closing last conn */
- __u64 ksnp_zc_next_cookie;/* ZC completion cookie */
- __u64 ksnp_incarnation; /* latest known peer_ni incarnation */
- struct ksock_proto *ksnp_proto; /* latest known peer_ni protocol */
+ atomic_t ksnp_refcount; /* # users */
+ int ksnp_closing; /* being closed */
+ int ksnp_accepting; /* # passive connections pending */
+ int ksnp_error; /* errno on closing last conn */
+ __u64 ksnp_zc_next_cookie;/* ZC completion cookie */
+ __u64 ksnp_incarnation; /* latest known peer_ni incarnation */
+ const struct ksock_proto *ksnp_proto; /* latest known protocol */
struct list_head ksnp_conns; /* all active connections */
struct list_head ksnp_routes; /* routes */
struct list_head ksnp_tx_queue; /* waiting packets */
- spinlock_t ksnp_lock; /* serialize, g_lock unsafe */
+ spinlock_t ksnp_lock; /* serialize, g_lock unsafe */
/* zero copy requests wait for ACK */
struct list_head ksnp_zc_req_list;
time64_t ksnp_send_keepalive; /* time to send keepalive */
- struct lnet_ni *ksnp_ni; /* which network */
- int ksnp_n_passive_ips; /* # of... */
- __u32 ksnp_passive_ips[LNET_INTERFACES_NUM]; /* preferred local interfaces */
+ struct lnet_ni *ksnp_ni; /* which network */
+ int ksnp_n_passive_ips; /* # of... */
+ __u32 ksnp_passive_ips[LNET_INTERFACES_NUM]; /* preferred local interfaces */
};
struct ksock_connreq {
* return MATCH_MAY : can be backup */
};
-extern struct ksock_proto ksocknal_protocol_v1x;
-extern struct ksock_proto ksocknal_protocol_v2x;
-extern struct ksock_proto ksocknal_protocol_v3x;
+extern const struct ksock_proto ksocknal_protocol_v1x;
+extern const struct ksock_proto ksocknal_protocol_v2x;
+extern const struct ksock_proto ksocknal_protocol_v3x;
#define KSOCK_PROTO_V1_MAJOR LNET_PROTO_TCP_VERSION_MAJOR
#define KSOCK_PROTO_V1_MINOR LNET_PROTO_TCP_VERSION_MINOR
static inline int
ksocknal_route_mask(void)
{
- if (!*ksocknal_tunables.ksnd_typed_conns)
- return (1 << SOCKLND_CONN_ANY);
-
- return ((1 << SOCKLND_CONN_CONTROL) |
- (1 << SOCKLND_CONN_BULK_IN) |
- (1 << SOCKLND_CONN_BULK_OUT));
-}
-
-static inline struct list_head *
-ksocknal_nid2peerlist (lnet_nid_t nid)
-{
- unsigned int hash = ((unsigned int)nid) % ksocknal_data.ksnd_peer_hash_size;
+ if (!*ksocknal_tunables.ksnd_typed_conns)
+ return BIT(SOCKLND_CONN_ANY);
- return (&ksocknal_data.ksnd_peers [hash]);
+ return (BIT(SOCKLND_CONN_CONTROL) |
+ BIT(SOCKLND_CONN_BULK_IN) |
+ BIT(SOCKLND_CONN_BULK_OUT));
}
static inline void
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);
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(struct lnet_ni *ni, lnet_nid_t gw_nid, int alive);
+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);
git://git.whamcloud.com / fs / lustre-release.git / blobdiff