#include <linux/interrupt.h>
#include <linux/kref.h>
#include <rdma/ib_pack.h>
+#include <rdma/ib_user_verbs.h>
#include "ipath_layer.h"
+#define IPATH_MAX_RDMA_ATOMIC 4
+
#define QPN_MAX (1 << 24)
#define QPNMAP_ENTRIES (QPN_MAX / PAGE_SIZE / BITS_PER_BYTE)
} __attribute__ ((packed));
struct ib_atomic_eth {
- __be64 vaddr;
+ __be32 vaddr[2]; /* unaligned so access as 2 32-bit words */
__be32 rkey;
__be64 swap_data;
__be64 compare_data;
} rc;
struct {
__be32 aeth;
- __be64 atomic_ack_eth;
+ __be32 atomic_ack_eth[2];
} at;
__be32 imm_data;
__be32 aeth;
* this as its vm_private_data.
*/
struct ipath_mmap_info {
- struct ipath_mmap_info *next;
+ struct list_head pending_mmaps;
struct ib_ucontext *context;
void *obj;
+ __u64 offset;
struct kref ref;
unsigned size;
- unsigned mmap_cnt;
};
/*
struct ipath_cq_wc {
u32 head; /* index of next entry to fill */
u32 tail; /* index of next ib_poll_cq() entry */
- struct ib_wc queue[1]; /* this is actually size ibcq.cqe + 1 */
+ struct ib_uverbs_wc queue[1]; /* this is actually size ibcq.cqe + 1 */
};
/*
};
struct ipath_mregion {
+ struct ib_pd *pd; /* shares refcnt of ibmr.pd */
u64 user_base; /* User's address for this region */
u64 iova; /* IB start address of this region */
size_t length;
u8 num_sge;
};
+/*
+ * This structure holds the information that the send tasklet needs
+ * to send a RDMA read response or atomic operation.
+ */
+struct ipath_ack_entry {
+ u8 opcode;
+ u32 psn;
+ union {
+ struct ipath_sge_state rdma_sge;
+ u64 atomic_data;
+ };
+};
+
/*
* Variables prefixed with s_ are for the requester (sender).
* Variables prefixed with r_ are for the responder (receiver).
struct ipath_mmap_info *ip;
struct ipath_sge_state *s_cur_sge;
struct ipath_sge_state s_sge; /* current send request data */
- /* current RDMA read send data */
- struct ipath_sge_state s_rdma_sge;
+ struct ipath_ack_entry s_ack_queue[IPATH_MAX_RDMA_ATOMIC + 1];
+ struct ipath_sge_state s_ack_rdma_sge;
+ struct ipath_sge_state s_rdma_read_sge;
struct ipath_sge_state r_sge; /* current receive data */
spinlock_t s_lock;
- unsigned long s_flags;
+ unsigned long s_busy;
u32 s_hdrwords; /* size of s_hdr in 32 bit words */
u32 s_cur_size; /* size of send packet in bytes */
u32 s_len; /* total length of s_sge */
- u32 s_rdma_len; /* total length of s_rdma_sge */
+ u32 s_rdma_read_len; /* total length of s_rdma_read_sge */
u32 s_next_psn; /* PSN for next request */
u32 s_last_psn; /* last response PSN processed */
u32 s_psn; /* current packet sequence number */
- u32 s_ack_psn; /* PSN for RDMA_READ */
+ u32 s_ack_rdma_psn; /* PSN for sending RDMA read responses */
+ u32 s_ack_psn; /* PSN for acking sends and RDMA writes */
u32 s_rnr_timeout; /* number of milliseconds for RNR timeout */
u32 r_ack_psn; /* PSN for next ACK or atomic ACK */
u64 r_wr_id; /* ID for current receive WQE */
- u64 r_atomic_data; /* data for last atomic op */
- u32 r_atomic_psn; /* PSN of last atomic op */
u32 r_len; /* total length of r_sge */
u32 r_rcv_len; /* receive data len processed */
u32 r_psn; /* expected rcv packet sequence number */
u8 s_ack_state; /* opcode of packet to ACK */
u8 s_nak_state; /* non-zero if NAK is pending */
u8 r_state; /* opcode of last packet received */
- u8 r_ack_state; /* opcode of packet to ACK */
u8 r_nak_state; /* non-zero if NAK is pending */
u8 r_min_rnr_timer; /* retry timeout value for RNR NAKs */
u8 r_reuse_sge; /* for UC receive errors */
u8 r_sge_inx; /* current index into sg_list */
+ u8 r_wrid_valid; /* r_wrid set but CQ entry not yet made */
+ u8 r_max_rd_atomic; /* max number of RDMA read/atomic to receive */
+ u8 r_head_ack_queue; /* index into s_ack_queue[] */
u8 qp_access_flags;
u8 s_max_sge; /* size of s_wq->sg_list */
u8 s_retry_cnt; /* number of times to retry */
u8 s_rnr_retry_cnt;
u8 s_retry; /* requester retry counter */
u8 s_rnr_retry; /* requester RNR retry counter */
+ u8 s_wait_credit; /* limit number of unacked packets sent */
u8 s_pkey_index; /* PKEY index to use */
+ u8 s_max_rd_atomic; /* max number of RDMA read/atomic to send */
+ u8 s_num_rd_atomic; /* number of RDMA read/atomic pending */
+ u8 s_tail_ack_queue; /* index into s_ack_queue[] */
+ u8 s_flags;
u8 timeout; /* Timeout for this QP */
enum ib_mtu path_mtu;
u32 remote_qpn;
struct ipath_sge r_sg_list[0]; /* verified SGEs */
};
+/* Bit definition for s_busy. */
+#define IPATH_S_BUSY 0
+
/*
* Bit definitions for s_flags.
*/
-#define IPATH_S_BUSY 0
-#define IPATH_S_SIGNAL_REQ_WR 1
+#define IPATH_S_SIGNAL_REQ_WR 0x01
+#define IPATH_S_FENCE_PENDING 0x02
+#define IPATH_S_RDMAR_PENDING 0x04
+#define IPATH_S_ACK_PENDING 0x08
+
+#define IPATH_PSN_CREDIT 512
/*
* Since struct ipath_swqe is not a fixed size, we can't simply index into
struct ipath_ibdev {
struct ib_device ibdev;
- struct list_head dev_list;
struct ipath_devdata *dd;
- struct ipath_mmap_info *pending_mmaps;
+ struct list_head pending_mmaps;
+ spinlock_t mmap_offset_lock;
+ u32 mmap_offset;
int ib_unit; /* This is the device number */
u16 sm_lid; /* in host order */
u8 sm_sl;
u32 n_rnr_naks;
u32 n_other_naks;
u32 n_timeouts;
+ u32 n_rc_stalls;
u32 n_pkt_drops;
u32 n_vl15_dropped;
u32 n_wqe_errs;
int ipath_destroy_qp(struct ib_qp *ibqp);
+void ipath_error_qp(struct ipath_qp *qp, enum ib_wc_status err);
+
int ipath_modify_qp(struct ib_qp *ibqp, struct ib_qp_attr *attr,
int attr_mask, struct ib_udata *udata);
void ipath_cq_enter(struct ipath_cq *cq, struct ib_wc *entry, int sig);
-int ipath_rkey_ok(struct ipath_ibdev *dev, struct ipath_sge_state *ss,
- u32 len, u64 vaddr, u32 rkey, int acc);
-
-int ipath_lkey_ok(struct ipath_lkey_table *rkt, struct ipath_sge *isge,
- struct ib_sge *sge, int acc);
-
void ipath_copy_sge(struct ipath_sge_state *ss, void *data, u32 length);
void ipath_skip_sge(struct ipath_sge_state *ss, u32 length);
void ipath_free_lkey(struct ipath_lkey_table *rkt, u32 lkey);
-int ipath_lkey_ok(struct ipath_lkey_table *rkt, struct ipath_sge *isge,
+int ipath_lkey_ok(struct ipath_qp *qp, struct ipath_sge *isge,
struct ib_sge *sge, int acc);
-int ipath_rkey_ok(struct ipath_ibdev *dev, struct ipath_sge_state *ss,
+int ipath_rkey_ok(struct ipath_qp *qp, struct ipath_sge_state *ss,
u32 len, u64 vaddr, u32 rkey, int acc);
int ipath_post_srq_receive(struct ib_srq *ibsrq, struct ib_recv_wr *wr,
int ipath_destroy_srq(struct ib_srq *ibsrq);
-void ipath_cq_enter(struct ipath_cq *cq, struct ib_wc *entry, int sig);
-
int ipath_poll_cq(struct ib_cq *ibcq, int num_entries, struct ib_wc *entry);
-struct ib_cq *ipath_create_cq(struct ib_device *ibdev, int entries,
+struct ib_cq *ipath_create_cq(struct ib_device *ibdev, int entries, int comp_vector,
struct ib_ucontext *context,
struct ib_udata *udata);
int ipath_destroy_cq(struct ib_cq *ibcq);
-int ipath_req_notify_cq(struct ib_cq *ibcq, enum ib_cq_notify notify);
+int ipath_req_notify_cq(struct ib_cq *ibcq, enum ib_cq_notify_flags notify_flags);
int ipath_resize_cq(struct ib_cq *ibcq, int cqe, struct ib_udata *udata);
void ipath_release_mmap_info(struct kref *ref);
+struct ipath_mmap_info *ipath_create_mmap_info(struct ipath_ibdev *dev,
+ u32 size,
+ struct ib_ucontext *context,
+ void *obj);
+
+void ipath_update_mmap_info(struct ipath_ibdev *dev,
+ struct ipath_mmap_info *ip,
+ u32 size, void *obj);
+
int ipath_mmap(struct ib_ucontext *context, struct vm_area_struct *vma);
void ipath_no_bufs_available(struct ipath_qp *qp, struct ipath_ibdev *dev);
void ipath_do_ruc_send(unsigned long data);
-u32 ipath_make_rc_ack(struct ipath_qp *qp, struct ipath_other_headers *ohdr,
- u32 pmtu);
-
int ipath_make_rc_req(struct ipath_qp *qp, struct ipath_other_headers *ohdr,
u32 pmtu, u32 *bth0p, u32 *bth2p);
extern const u32 ib_ipath_rnr_table[];
+extern struct ib_dma_mapping_ops ipath_dma_mapping_ops;
+
#endif /* IPATH_VERBS_H */
projects / cascardo / linux.git / blobdiff