IB/rdmavt: Compress adjacent SGEs in rvt_lkey_ok()

SGEs that are contiguous needlessly consume driver dependent TX resources.

The lkey validation logic is enhanced to compress the SGE that ends
up in the send wqe when consecutive addresses are detected.

The lkey validation API used to return 1 (success) or 0 (fail).

The return value is now an -errno, 0 (compressed), or 1 (uncompressed).  A
additional argument is added to pass the last SQE for the compression.

Loopback callers always pass a NULL to last_sge since the optimization is
of little benefit in that situation.
Reviewed-by: Dennis Dalessandro <dennis.dalessandro@intel.com>
Signed-off-by: Brian Welty <brian.welty@intel.com>
Signed-off-by: Venkata Sandeep Dhanalakota <venkata.s.dhanalakota@intel.com>
Signed-off-by: Mike Marciniszyn <mike.marciniszyn@intel.com>
Signed-off-by: Dennis Dalessandro <dennis.dalessandro@intel.com>
Signed-off-by: Doug Ledford <dledford@redhat.com>

drivers/infiniband/hw/hfi1/ruc.c

@@ -75,7 +75,7 @@ static int init_sge(struct rvt_qp *qp, struct rvt_rwqe *wqe)
 			continue;
 		/* Check LKEY */
 		if (!rvt_lkey_ok(rkt, pd, j ? &ss->sg_list[j - 1] : &ss->sge,
-				 &wqe->sg_list[i], IB_ACCESS_LOCAL_WRITE))
+				 NULL, &wqe->sg_list[i], IB_ACCESS_LOCAL_WRITE))
 			goto bad_lkey;
 		qp->r_len += wqe->sg_list[i].length;
 		j++;

drivers/infiniband/hw/qib/qib_ruc.c

@@ -59,7 +59,7 @@ static int qib_init_sge(struct rvt_qp *qp, struct rvt_rwqe *wqe)
 			continue;
 		/* Check LKEY */
 		if (!rvt_lkey_ok(rkt, pd, j ? &ss->sg_list[j - 1] : &ss->sge,
-				 &wqe->sg_list[i], IB_ACCESS_LOCAL_WRITE))
+				 NULL, &wqe->sg_list[i], IB_ACCESS_LOCAL_WRITE))
 			goto bad_lkey;
 		qp->r_len += wqe->sg_list[i].length;
 		j++;

drivers/infiniband/sw/rdmavt/mr.c

@@ -777,24 +777,55 @@ int rvt_dealloc_fmr(struct ib_fmr *ibfmr)
 	return ret;
 }
 
+/**
+ * rvt_sge_adjacent - is isge compressible
+ * @isge: outgoing internal SGE
+ * @last_sge: last outgoing SGE written
+ * @sge: SGE to check
+ *
+ * If adjacent will update last_sge to add length.
+ *
+ * Return: true if isge is adjacent to last sge
+ */
+static inline bool rvt_sge_adjacent(struct rvt_sge *isge,
+				    struct rvt_sge *last_sge,
+				    struct ib_sge *sge)
+{
+	if (last_sge && sge->lkey == last_sge->mr->lkey &&
+	    ((uint64_t)(last_sge->vaddr + last_sge->length) == sge->addr)) {
+		if (sge->lkey) {
+			if (unlikely((sge->addr - last_sge->mr->user_base +
+			      sge->length > last_sge->mr->length)))
+				return false; /* overrun, caller will catch */
+		} else {
+			last_sge->length += sge->length;
+		}
+		last_sge->sge_length += sge->length;
+		trace_rvt_sge_adjacent(last_sge, sge);
+		return true;
+	}
+	return false;
+}
+
 /**
  * rvt_lkey_ok - check IB SGE for validity and initialize
  * @rkt: table containing lkey to check SGE against
  * @pd: protection domain
  * @isge: outgoing internal SGE
+ * @last_sge: last outgoing SGE written
  * @sge: SGE to check
  * @acc: access flags
  *
  * Check the IB SGE for validity and initialize our internal version
  * of it.
  *
- * Return: 1 if valid and successful, otherwise returns 0.
- *
- * increments the reference count upon success
+ * Increments the reference count when a new sge is stored.
  *
+ * Return: 0 if compressed, 1 if added , otherwise returns -errno.
  */
 int rvt_lkey_ok(struct rvt_lkey_table *rkt, struct rvt_pd *pd,
-		struct rvt_sge *isge, struct ib_sge *sge, int acc)
+		struct rvt_sge *isge, struct rvt_sge *last_sge,
+		struct ib_sge *sge, int acc)
 {
 	struct rvt_mregion *mr;
 	unsigned n, m;
@@ -804,12 +835,14 @@ int rvt_lkey_ok(struct rvt_lkey_table *rkt, struct rvt_pd *pd,
 	 * We use LKEY == zero for kernel virtual addresses
 	 * (see rvt_get_dma_mr() and dma_virt_ops).
 	 */
-	rcu_read_lock();
 	if (sge->lkey == 0) {
 		struct rvt_dev_info *dev = ib_to_rvt(pd->ibpd.device);
 
 		if (pd->user)
-			goto bail;
+			return -EINVAL;
+		if (rvt_sge_adjacent(isge, last_sge, sge))
+			return 0;
+		rcu_read_lock();
 		mr = rcu_dereference(dev->dma_mr);
 		if (!mr)
 			goto bail;
@@ -824,6 +857,9 @@ int rvt_lkey_ok(struct rvt_lkey_table *rkt, struct rvt_pd *pd,
 		isge->n = 0;
 		goto ok;
 	}
+	if (rvt_sge_adjacent(isge, last_sge, sge))
+		return 0;
+	rcu_read_lock();
 	mr = rcu_dereference(rkt->table[sge->lkey >> rkt->shift]);
 	if (!mr)
 		goto bail;
@@ -874,12 +910,13 @@ int rvt_lkey_ok(struct rvt_lkey_table *rkt, struct rvt_pd *pd,
 	isge->m = m;
 	isge->n = n;
 ok:
+	trace_rvt_sge_new(isge, sge);
 	return 1;
 bail_unref:
 	rvt_put_mr(mr);
 bail:
 	rcu_read_unlock();
-	return 0;
+	return -EINVAL;
 }
 EXPORT_SYMBOL(rvt_lkey_ok);
 

drivers/infiniband/sw/rdmavt/qp.c

@@ -1646,7 +1646,7 @@ static int rvt_post_one_wr(struct rvt_qp *qp,
 	struct rvt_pd *pd;
 	struct rvt_dev_info *rdi = ib_to_rvt(qp->ibqp.device);
 	u8 log_pmtu;
-	int ret;
+	int ret, incr;
 	size_t cplen;
 	bool reserved_op;
 	int local_ops_delayed = 0;
@@ -1719,22 +1719,23 @@ static int rvt_post_one_wr(struct rvt_qp *qp,
 	wqe->length = 0;
 	j = 0;
 	if (wr->num_sge) {
+		struct rvt_sge *last_sge = NULL;
+
 		acc = wr->opcode >= IB_WR_RDMA_READ ?
 			IB_ACCESS_LOCAL_WRITE : 0;
 		for (i = 0; i < wr->num_sge; i++) {
 			u32 length = wr->sg_list[i].length;
-			int ok;
 
 			if (length == 0)
 				continue;
-			ok = rvt_lkey_ok(rkt, pd, &wqe->sg_list[j],
+			incr = rvt_lkey_ok(rkt, pd, &wqe->sg_list[j], last_sge,
 					   &wr->sg_list[i], acc);
-			if (!ok) {
-				ret = -EINVAL;
-				goto bail_inval_free;
-			}
+			if (unlikely(incr < 0))
+				goto bail_lkey_error;
 			wqe->length += length;
-			j++;
+			if (incr)
+				last_sge = &wqe->sg_list[j];
+			j += incr;
 		}
 		wqe->wr.num_sge = j;
 	}
@@ -1781,12 +1782,14 @@ static int rvt_post_one_wr(struct rvt_qp *qp,
 		wqe->wr.send_flags &= ~RVT_SEND_RESERVE_USED;
 		qp->s_avail--;
 	}
-	trace_rvt_post_one_wr(qp, wqe);
+	trace_rvt_post_one_wr(qp, wqe, wr->num_sge);
 	smp_wmb(); /* see request builders */
 	qp->s_head = next;
 
 	return 0;
 
+bail_lkey_error:
+	ret = incr;
 bail_inval_free:
 	/* release mr holds */
 	while (j) {

drivers/infiniband/sw/rdmavt/trace_mr.h

@@ -103,6 +103,68 @@ DEFINE_EVENT(
 	TP_PROTO(struct rvt_mregion *mr, u16 m, u16 n, void *v, size_t len),
 	TP_ARGS(mr, m, n, v, len));
 
+DECLARE_EVENT_CLASS(
+	rvt_sge_template,
+	TP_PROTO(struct rvt_sge *sge, struct ib_sge *isge),
+	TP_ARGS(sge, isge),
+	TP_STRUCT__entry(
+		RDI_DEV_ENTRY(ib_to_rvt(sge->mr->pd->device))
+		__field(struct rvt_mregion *, mr)
+		__field(struct rvt_sge *, sge)
+		__field(struct ib_sge *, isge)
+		__field(void *, vaddr)
+		__field(u64, ivaddr)
+		__field(u32, lkey)
+		__field(u32, sge_length)
+		__field(u32, length)
+		__field(u32, ilength)
+		__field(int, user)
+		__field(u16, m)
+		__field(u16, n)
+	),
+	TP_fast_assign(
+		RDI_DEV_ASSIGN(ib_to_rvt(sge->mr->pd->device));
+		__entry->mr = sge->mr;
+		__entry->sge = sge;
+		__entry->isge = isge;
+		__entry->vaddr = sge->vaddr;
+		__entry->ivaddr = isge->addr;
+		__entry->lkey = sge->mr->lkey;
+		__entry->sge_length = sge->sge_length;
+		__entry->length = sge->length;
+		__entry->ilength = isge->length;
+		__entry->m = sge->m;
+		__entry->n = sge->m;
+		__entry->user = ibpd_to_rvtpd(sge->mr->pd)->user;
+	),
+	TP_printk(
+		"[%s] mr %p sge %p isge %p vaddr %p ivaddr %llx lkey %x sge_length %u length %u ilength %u m %u n %u user %u",
+		__get_str(dev),
+		__entry->mr,
+		__entry->sge,
+		__entry->isge,
+		__entry->vaddr,
+		__entry->ivaddr,
+		__entry->lkey,
+		__entry->sge_length,
+		__entry->length,
+		__entry->ilength,
+		__entry->m,
+		__entry->n,
+		__entry->user
+	)
+);
+
+DEFINE_EVENT(
+	rvt_sge_template, rvt_sge_adjacent,
+	TP_PROTO(struct rvt_sge *sge, struct ib_sge *isge),
+	TP_ARGS(sge, isge));
+
+DEFINE_EVENT(
+	rvt_sge_template, rvt_sge_new,
+	TP_PROTO(struct rvt_sge *sge, struct ib_sge *isge),
+	TP_ARGS(sge, isge));
+
 #endif /* __RVT_TRACE_MR_H */
 
 #undef TRACE_INCLUDE_PATH

drivers/infiniband/sw/rdmavt/trace_tx.h

@@ -84,12 +84,12 @@ __print_symbolic(opcode,                                   \
 	wr_opcode_name(RESERVED10))
 
 #define POS_PRN \
-"[%s] wqe %p wr_id %llx send_flags %x qpn %x qpt %u psn %x lpsn %x ssn %x length %u opcode 0x%.2x,%s size %u avail %u head %u last %u pid %u num_sge %u"
+"[%s] wqe %p wr_id %llx send_flags %x qpn %x qpt %u psn %x lpsn %x ssn %x length %u opcode 0x%.2x,%s size %u avail %u head %u last %u pid %u num_sge %u wr_num_sge %u"
 
 TRACE_EVENT(
 	rvt_post_one_wr,
-	TP_PROTO(struct rvt_qp *qp, struct rvt_swqe *wqe),
-	TP_ARGS(qp, wqe),
+	TP_PROTO(struct rvt_qp *qp, struct rvt_swqe *wqe, int wr_num_sge),
+	TP_ARGS(qp, wqe, wr_num_sge),
 	TP_STRUCT__entry(
 		RDI_DEV_ENTRY(ib_to_rvt(qp->ibqp.device))
 		__field(u64, wr_id)
@@ -108,6 +108,7 @@ TRACE_EVENT(
 		__field(int, send_flags)
 		__field(pid_t, pid)
 		__field(int, num_sge)
+		__field(int, wr_num_sge)
 	),
 	TP_fast_assign(
 		RDI_DEV_ASSIGN(ib_to_rvt(qp->ibqp.device))
@@ -127,6 +128,7 @@ TRACE_EVENT(
 		__entry->ssn = wqe->ssn;
 		__entry->send_flags = wqe->wr.send_flags;
 		__entry->num_sge = wqe->wr.num_sge;
+		__entry->wr_num_sge = wr_num_sge;
 	),
 	TP_printk(
 		POS_PRN,
@@ -146,7 +148,8 @@ TRACE_EVENT(
 		__entry->head,
 		__entry->last,
 		__entry->pid,
-		__entry->num_sge
+		__entry->num_sge,
+		__entry->wr_num_sge
 	)
 );
 

include/rdma/rdma_vt.h

@@ -515,7 +515,8 @@ int rvt_invalidate_rkey(struct rvt_qp *qp, u32 rkey);
 int rvt_rkey_ok(struct rvt_qp *qp, struct rvt_sge *sge,
 		u32 len, u64 vaddr, u32 rkey, int acc);
 int rvt_lkey_ok(struct rvt_lkey_table *rkt, struct rvt_pd *pd,
-		struct rvt_sge *isge, struct ib_sge *sge, int acc);
+		struct rvt_sge *isge, struct rvt_sge *last_sge,
+		struct ib_sge *sge, int acc);
 struct rvt_mcast *rvt_mcast_find(struct rvt_ibport *ibp, union ib_gid *mgid,
 				 u16 lid);