Merge branch 'tid-read' into hfi1-tid

This is the series for adding TID RDMA read. Kaike put in a lot of
effort into making this more consumable for review so special thanks to
him.

Allocating resources and tracing are separated out followed by patches
which build up the read request. Then we have the patches to receive
incoming TID RDMA read requests and handle integration with the RC
protocol.

See the cover letter of the original posting for more of a detailed
overview of TID.

https://www.spinics.net/lists/linux-rdma/msg66611.html

* tid-read:
  IB/hfi1: Add static trace for TID RDMA READ protocol
  IB/hfi1: Enable TID RDMA READ protocol
  IB/hfi1: Add interlock between a TID RDMA request and other requests
  IB/hfi1: Integrate TID RDMA READ protocol into RC protocol
  IB/hfi1: Increment the retry timeout value for TID RDMA READ request
  IB/hfi1: Add functions for restarting TID RDMA READ request
  IB/hfi1: Add TID RDMA handlers
  IB/hfi1: Add functions to receive TID RDMA READ response
  IB/hfi1: Add a function to build TID RDMA READ response
  IB/hfi1: Add functions to receive TID RDMA READ request
  IB/hfi1: Set PbcInsertHcrc for TID RDMA packets
  IB/hfi1: Add functions to build TID RDMA READ request
  IB/hfi1: Add static trace for flow and TID management functions
  IB/hfi1: Add the counter n_tidwait
  IB/hfi1: TID RDMA RcvArray programming and TID allocation
  IB/hfi1: TID RDMA flow allocation
  IB/hfi: Move RC functions into a header file

Signed-off-by: Doug Ledford <dledford@redhat.com>

4 files changed, 86 insertions, 5 deletions

diff --git a/include/rdma/ib_hdrs.h b/include/rdma/ib_hdrs.h
index 6e35416170a3..58a0a0f99e7f 100644
--- a/include/rdma/ib_hdrs.h
+++ b/include/rdma/ib_hdrs.h
@@ -1,5 +1,5 @@
 /*
- * Copyright(c) 2016 Intel Corporation.
+ * Copyright(c) 2016 - 2018 Intel Corporation.
  *
  * This file is provided under a dual BSD/GPLv2 license.  When using or
  * redistributing this file, you may do so under either license.
@@ -100,6 +100,8 @@ struct ib_atomic_eth {
 	__be64 compare_data; /* potentially unaligned */
 } __packed;
 
+#include <rdma/tid_rdma_defs.h>
+
 union ib_ehdrs {
 	struct {
 		__be32 deth[2];
@@ -117,6 +119,11 @@ union ib_ehdrs {
 	__be32 aeth;
 	__be32 ieth;
 	struct ib_atomic_eth atomic_eth;
+	/* TID RDMA headers */
+	union {
+		struct tid_rdma_read_req r_req;
+		struct tid_rdma_read_resp r_rsp;
+	} tid_rdma;
 }  __packed;
 
 struct ib_other_headers {
diff --git a/include/rdma/rdma_vt.h b/include/rdma/rdma_vt.h
index 168e40be183c..87d66c9630d7 100644
--- a/include/rdma/rdma_vt.h
+++ b/include/rdma/rdma_vt.h
@@ -574,9 +574,10 @@ static inline struct rvt_qp *rvt_lookup_qpn(struct rvt_dev_info *rdi,
 /**
  * rvt_mod_retry_timer - mod a retry timer
  * @qp - the QP
+ * @shift - timeout shift to wait for multiple packets
  * Modify a potentially already running retry timer
  */
-static inline void rvt_mod_retry_timer(struct rvt_qp *qp)
+static inline void rvt_mod_retry_timer_ext(struct rvt_qp *qp, u8 shift)
 {
 	struct ib_qp *ibqp = &qp->ibqp;
 	struct rvt_dev_info *rdi = ib_to_rvt(ibqp->device);
@@ -584,8 +585,13 @@ static inline void rvt_mod_retry_timer(struct rvt_qp *qp)
 	lockdep_assert_held(&qp->s_lock);
 	qp->s_flags |= RVT_S_TIMER;
 	/* 4.096 usec. * (1 << qp->timeout) */
-	mod_timer(&qp->s_timer, jiffies + qp->timeout_jiffies +
-		  rdi->busy_jiffies);
+	mod_timer(&qp->s_timer, jiffies + rdi->busy_jiffies +
+		  (qp->timeout_jiffies << shift));
+}
+
+static inline void rvt_mod_retry_timer(struct rvt_qp *qp)
+{
+	return rvt_mod_retry_timer_ext(qp, 0);
 }
 
 struct rvt_dev_info *rvt_alloc_device(size_t size, int nports);
diff --git a/include/rdma/rdmavt_qp.h b/include/rdma/rdmavt_qp.h
index cbafb1878669..d8d88d023092 100644
--- a/include/rdma/rdmavt_qp.h
+++ b/include/rdma/rdmavt_qp.h
@@ -174,6 +174,7 @@ struct rvt_swqe {
 	u32 lpsn;               /* last packet sequence number */
 	u32 ssn;                /* send sequence number */
 	u32 length;             /* total length of data in sg_list */
+	void *priv;             /* driver dependent field */
 	struct rvt_sge sg_list[0];
 };
 
@@ -235,6 +236,7 @@ struct rvt_ack_entry {
 	u32 lpsn;
 	u8 opcode;
 	u8 sent;
+	void *priv;
 };
 
 #define	RC_QP_SCALING_INTERVAL	5
@@ -629,6 +631,16 @@ __be32 rvt_compute_aeth(struct rvt_qp *qp);
 void rvt_get_credit(struct rvt_qp *qp, u32 aeth);
 
 /**
+ * rvt_restart_sge - rewind the sge state for a wqe
+ * @ss: the sge state pointer
+ * @wqe: the wqe to rewind
+ * @len: the data length from the start of the wqe in bytes
+ *
+ * Returns the remaining data length.
+ */
+u32 rvt_restart_sge(struct rvt_sge_state *ss, struct rvt_swqe *wqe, u32 len);
+
+/**
  * @qp - the qp pair
  * @len - the length
  *
@@ -676,7 +688,11 @@ enum hrtimer_restart rvt_rc_rnr_retry(struct hrtimer *t);
 void rvt_add_rnr_timer(struct rvt_qp *qp, u32 aeth);
 void rvt_del_timers_sync(struct rvt_qp *qp);
 void rvt_stop_rc_timers(struct rvt_qp *qp);
-void rvt_add_retry_timer(struct rvt_qp *qp);
+void rvt_add_retry_timer_ext(struct rvt_qp *qp, u8 shift);
+static inline void rvt_add_retry_timer(struct rvt_qp *qp)
+{
+	rvt_add_retry_timer_ext(qp, 0);
+}
 
 void rvt_copy_sge(struct rvt_qp *qp, struct rvt_sge_state *ss,
 		  void *data, u32 length,
diff --git a/include/rdma/tid_rdma_defs.h b/include/rdma/tid_rdma_defs.h
new file mode 100644
index 000000000000..1c431ea32b52
--- /dev/null
+++ b/include/rdma/tid_rdma_defs.h
@@ -0,0 +1,52 @@
+/* SPDX-License-Identifier: (GPL-2.0 OR BSD-3-Clause) */
+/*
+ * Copyright(c) 2018 Intel Corporation.
+ *
+ */
+
+#ifndef TID_RDMA_DEFS_H
+#define TID_RDMA_DEFS_H
+
+#include <rdma/ib_pack.h>
+
+struct tid_rdma_read_req {
+	__le32 kdeth0;
+	__le32 kdeth1;
+	struct ib_reth reth;
+	__be32 tid_flow_psn;
+	__be32 tid_flow_qp;
+	__be32 verbs_qp;
+};
+
+struct tid_rdma_read_resp {
+	__le32 kdeth0;
+	__le32 kdeth1;
+	__be32 aeth;
+	__be32 reserved[4];
+	__be32 verbs_psn;
+	__be32 verbs_qp;
+};
+
+/*
+ * TID RDMA Opcodes
+ */
+#define IB_OPCODE_TID_RDMA 0xe0
+enum {
+	IB_OPCODE_READ_REQ        = 0x4,
+	IB_OPCODE_READ_RESP       = 0x5,
+
+	IB_OPCODE(TID_RDMA, READ_REQ),
+	IB_OPCODE(TID_RDMA, READ_RESP),
+};
+
+#define TID_OP(x) IB_OPCODE_TID_RDMA_##x
+
+/*
+ * Define TID RDMA specific WR opcodes. The ib_wr_opcode
+ * enum already provides some reserved values for use by
+ * low level drivers. Two of those are used but renamed
+ * to be more descriptive.
+ */
+#define IB_WR_TID_RDMA_READ  IB_WR_RESERVED2
+
+#endif /* TID_RDMA_DEFS_H */