IB/hfi1: Add functions to receive TID RDMA WRITE request

This patch adds the functions to receive TID RDMA WRITE request. The
request will be stored in the QP's s_ack_queue. This patch also adds
code to handle duplicate TID RDMA WRITE request and a function to
allocate TID resources for data receiving on the responder side.
Signed-off-by: Mitko Haralanov <mitko.haralanov@intel.com>
Signed-off-by: Mike Marciniszyn <mike.marciniszyn@intel.com>
Signed-off-by: Ashutosh Dixit <ashutosh.dixit@intel.com>
Signed-off-by: Kaike Wan <kaike.wan@intel.com>
Signed-off-by: Dennis Dalessandro <dennis.dalessandro@intel.com>
Signed-off-by: Doug Ledford <dledford@redhat.com>

drivers/infiniband/hw/hfi1/init.c

@@ -1512,6 +1512,7 @@ static int __init hfi1_mod_init(void)
 		goto bail_dev;
 	}
 
+	hfi1_compute_tid_rdma_flow_wt();
 	/*
 	 * These must be called before the driver is registered with
 	 * the PCI subsystem.

drivers/infiniband/hw/hfi1/rc.c

@@ -2411,6 +2411,7 @@ void hfi1_rc_rcv(struct hfi1_packet *packet)
 	void *data = packet->payload;
 	u32 tlen = packet->tlen;
 	struct rvt_qp *qp = packet->qp;
+	struct hfi1_qp_priv *qpriv = qp->priv;
 	struct hfi1_ibport *ibp = rcd_to_iport(rcd);
 	struct ib_other_headers *ohdr = packet->ohdr;
 	u32 opcode = packet->opcode;
@@ -2716,6 +2717,7 @@ void hfi1_rc_rcv(struct hfi1_packet *packet)
 		qp->r_state = opcode;
 		qp->r_nak_state = 0;
 		qp->r_head_ack_queue = next;
+		qpriv->r_tid_alloc = qp->r_head_ack_queue;
 
 		/* Schedule the send engine. */
 		qp->s_flags |= RVT_S_RESP_PENDING;
@@ -2789,6 +2791,7 @@ void hfi1_rc_rcv(struct hfi1_packet *packet)
 		qp->r_state = opcode;
 		qp->r_nak_state = 0;
 		qp->r_head_ack_queue = next;
+		qpriv->r_tid_alloc = qp->r_head_ack_queue;
 
 		/* Schedule the send engine. */
 		qp->s_flags |= RVT_S_RESP_PENDING;

drivers/infiniband/hw/hfi1/tid_rdma.h

@@ -26,7 +26,9 @@
  *
  * HFI1_S_TID_WAIT_INTERLCK - QP is waiting for requester interlock
  */
+/* BIT(4) reserved for RVT_S_ACK_PENDING. */
 #define HFI1_S_TID_WAIT_INTERLCK  BIT(5)
+#define HFI1_R_TID_SW_PSN         BIT(19)
 
 /*
  * Unlike regular IB RDMA VERBS, which do not require an entry
@@ -89,10 +91,12 @@ struct tid_rdma_request {
 	} e;
 
 	struct tid_rdma_flow *flows;	/* array of tid flows */
+	struct rvt_sge_state ss; /* SGE state for TID RDMA requests */
 	u16 n_flows;		/* size of the flow buffer window */
 	u16 setup_head;		/* flow index we are setting up */
 	u16 clear_tail;		/* flow index we are clearing */
 	u16 flow_idx;		/* flow index most recently set up */
+	u16 acked_tail;
 
 	u32 seg_len;
 	u32 total_len;
@@ -103,6 +107,7 @@ struct tid_rdma_request {
 	u32 cur_seg;		/* index of current segment */
 	u32 comp_seg;           /* index of last completed segment */
 	u32 ack_seg;            /* index of last ack'ed segment */
+	u32 alloc_seg;          /* index of next segment to be allocated */
 	u32 isge;		/* index of "current" sge */
 	u32 ack_pending;        /* num acks pending for this request */
 
@@ -174,6 +179,12 @@ struct tid_rdma_flow {
 	u32 tid_entry[TID_RDMA_MAX_PAGES];
 };
 
+enum tid_rnr_nak_state {
+	TID_RNR_NAK_INIT = 0,
+	TID_RNR_NAK_SEND,
+	TID_RNR_NAK_SENT,
+};
+
 bool tid_rdma_conn_req(struct rvt_qp *qp, u64 *data);
 bool tid_rdma_conn_reply(struct rvt_qp *qp, u64 data);
 bool tid_rdma_conn_resp(struct rvt_qp *qp, u64 *data);
@@ -247,4 +258,9 @@ static inline void hfi1_setup_tid_rdma_wqe(struct rvt_qp *qp,
 u32 hfi1_build_tid_rdma_write_req(struct rvt_qp *qp, struct rvt_swqe *wqe,
 				  struct ib_other_headers *ohdr,
 				  u32 *bth1, u32 *bth2, u32 *len);
+
+void hfi1_compute_tid_rdma_flow_wt(void);
+
+void hfi1_rc_rcv_tid_rdma_write_req(struct hfi1_packet *packet);
+
 #endif /* HFI1_TID_RDMA_H */

drivers/infiniband/hw/hfi1/verbs.h

@@ -172,7 +172,15 @@ struct hfi1_qp_priv {
 	unsigned long tid_timer_timeout_jiffies;
 
 	/* variables for the TID RDMA SE state machine */
+	u8 rnr_nak_state;       /* RNR NAK state */
 	u32 s_flags;
+	u32 r_tid_head;     /* Most recently added TID RDMA request */
+	u32 r_tid_tail;     /* the last completed TID RDMA request */
+	u32 r_tid_ack;      /* the TID RDMA request to be ACK'ed */
+	u32 r_tid_alloc;    /* Request for which we are allocating resources */
+	u32 pending_tid_w_segs; /* Num of pending tid write segments */
+	u32 alloc_w_segs;       /* Number of segments for which write */
+			       /* resources have been allocated for this QP */
 
 	/* For TID RDMA READ */
 	u32 tid_r_reqs;         /* Num of tid reads requested */
@@ -180,8 +188,12 @@ struct hfi1_qp_priv {
 	u32 pending_tid_r_segs; /* Num of pending tid read segments */
 	u16 pkts_ps;            /* packets per segment */
 	u8 timeout_shift;       /* account for number of packets per segment */
+
+	u8 sync_pt;           /* Set when QP reaches sync point */
 };
 
+#define HFI1_QP_WQE_INVALID   ((u32)-1)
+
 struct hfi1_swqe_priv {
 	struct tid_rdma_request tid_req;
 	struct rvt_sge_state ss;  /* Used for TID RDMA READ Request */