IB/hfi1: Add 16B UD support

Add 16B bypass packet support for UD traffic types.
Reviewed-by: Dennis Dalessandro <dennis.dalessandro@intel.com>
Signed-off-by: Dasaratharaman Chandramouli <dasaratharaman.chandramouli@intel.com>
Signed-off-by: Don Hiatt <don.hiatt@intel.com>
Signed-off-by: Dennis Dalessandro <dennis.dalessandro@intel.com>
Signed-off-by: Doug Ledford <dledford@redhat.com>

drivers/infiniband/hw/hfi1/driver.c

@@ -437,23 +437,33 @@ void hfi1_process_ecn_slowpath(struct rvt_qp *qp, struct hfi1_packet *pkt,
 			       bool do_cnp)
 {
 	struct hfi1_ibport *ibp = to_iport(qp->ibqp.device, qp->port_num);
-	struct ib_header *hdr = pkt->hdr;
 	struct ib_other_headers *ohdr = pkt->ohdr;
 	struct ib_grh *grh = pkt->grh;
 	u32 rqpn = 0, bth1;
-	u16 rlid, dlid = ib_get_dlid(hdr);
-	u8 sc, svc_type;
+	u16 pkey, rlid, dlid = ib_get_dlid(pkt->hdr);
+	u8 hdr_type, sc, svc_type;
 	bool is_mcast = false;
 
+	if (pkt->etype == RHF_RCV_TYPE_BYPASS) {
+		is_mcast = hfi1_is_16B_mcast(dlid);
+		pkey = hfi1_16B_get_pkey(pkt->hdr);
+		sc = hfi1_16B_get_sc(pkt->hdr);
+		hdr_type = HFI1_PKT_TYPE_16B;
+	} else {
+		is_mcast = (dlid > be16_to_cpu(IB_MULTICAST_LID_BASE)) &&
+			   (dlid != be16_to_cpu(IB_LID_PERMISSIVE));
+		pkey = ib_bth_get_pkey(ohdr);
+		sc = hfi1_9B_get_sc5(pkt->hdr, pkt->rhf);
+		hdr_type = HFI1_PKT_TYPE_9B;
+	}
+
 	switch (qp->ibqp.qp_type) {
 	case IB_QPT_SMI:
 	case IB_QPT_GSI:
 	case IB_QPT_UD:
-		rlid = ib_get_slid(hdr);
-		rqpn = ib_get_sqpn(ohdr);
+		rlid = ib_get_slid(pkt->hdr);
+		rqpn = ib_get_sqpn(pkt->ohdr);
 		svc_type = IB_CC_SVCTYPE_UD;
-		is_mcast = (dlid > be16_to_cpu(IB_MULTICAST_LID_BASE)) &&
-			(dlid != be16_to_cpu(IB_LID_PERMISSIVE));
 		break;
 	case IB_QPT_UC:
 		rlid = rdma_ah_get_dlid(&qp->remote_ah_attr);
@@ -469,14 +479,11 @@ void hfi1_process_ecn_slowpath(struct rvt_qp *qp, struct hfi1_packet *pkt,
 		return;
 	}
 
-	sc = hfi1_9B_get_sc5(hdr, pkt->rhf);
-
 	bth1 = be32_to_cpu(ohdr->bth[1]);
-	if (do_cnp && (bth1 & IB_FECN_SMASK)) {
-		u16 pkey = ib_bth_get_pkey(ohdr);
-
-		return_cnp(ibp, qp, rqpn, pkey, dlid, rlid, sc, grh);
-	}
+	/* Call appropriate CNP handler */
+	if (do_cnp && (bth1 & IB_FECN_SMASK))
+		hfi1_handle_cnp_tbl[hdr_type](ibp, qp, rqpn, pkey,
+					      dlid, rlid, sc, grh);
 
 	if (!is_mcast && (bth1 & IB_BECN_SMASK)) {
 		struct hfi1_pportdata *ppd = ppd_from_ibp(ibp);

drivers/infiniband/hw/hfi1/hfi.h

@@ -831,6 +831,10 @@ struct hfi1_pportdata {
 typedef int (*rhf_rcv_function_ptr)(struct hfi1_packet *packet);
 
 typedef void (*opcode_handler)(struct hfi1_packet *packet);
+typedef void (*hfi1_make_req)(struct rvt_qp *qp,
+			      struct hfi1_pkt_state *ps,
+			      struct rvt_swqe *wqe);
+
 
 /* return values for the RHF receive functions */
 #define RHF_RCV_CONTINUE  0	/* keep going */
@@ -1373,6 +1377,13 @@ void hfi1_set_vnic_msix_info(struct hfi1_ctxtdata *rcd);
 void hfi1_reset_vnic_msix_info(struct hfi1_ctxtdata *rcd);
 
 extern const struct pci_device_id hfi1_pci_tbl[];
+void hfi1_make_ud_req_9B(struct rvt_qp *qp,
+			 struct hfi1_pkt_state *ps,
+			 struct rvt_swqe *wqe);
+
+void hfi1_make_ud_req_16B(struct rvt_qp *qp,
+			  struct hfi1_pkt_state *ps,
+			  struct rvt_swqe *wqe);
 
 /* receive packet handler dispositions */
 #define RCV_PKT_OK      0x0 /* keep going */
@@ -1507,6 +1518,18 @@ void process_becn(struct hfi1_pportdata *ppd, u8 sl,  u16 rlid, u32 lqpn,
 void return_cnp(struct hfi1_ibport *ibp, struct rvt_qp *qp, u32 remote_qpn,
 		u32 pkey, u32 slid, u32 dlid, u8 sc5,
 		const struct ib_grh *old_grh);
+void return_cnp_16B(struct hfi1_ibport *ibp, struct rvt_qp *qp,
+		    u32 remote_qpn, u32 pkey, u32 slid, u32 dlid,
+		    u8 sc5, const struct ib_grh *old_grh);
+typedef void (*hfi1_handle_cnp)(struct hfi1_ibport *ibp, struct rvt_qp *qp,
+				u32 remote_qpn, u32 pkey, u32 slid, u32 dlid,
+				u8 sc5, const struct ib_grh *old_grh);
+
+/* We support only two types - 9B and 16B for now */
+static const hfi1_handle_cnp hfi1_handle_cnp_tbl[2] = {
+	[HFI1_PKT_TYPE_9B] = &return_cnp,
+	[HFI1_PKT_TYPE_16B] = &return_cnp_16B
+};
 #define PKEY_CHECK_INVALID -1
 int egress_pkey_check(struct hfi1_pportdata *ppd, __be16 *lrh, __be32 *bth,
 		      u8 sc5, int8_t s_pkey_index);
@@ -1747,12 +1770,22 @@ static inline bool process_ecn(struct rvt_qp *qp, struct hfi1_packet *pkt,
 			       bool do_cnp)
 {
 	struct ib_other_headers *ohdr = pkt->ohdr;
-	u32 bth1;
 
-	bth1 = be32_to_cpu(ohdr->bth[1]);
-	if (unlikely(bth1 & (IB_BECN_SMASK | IB_FECN_SMASK))) {
+	u32 bth1;
+	bool becn = false;
+	bool fecn = false;
+
+	if (pkt->etype == RHF_RCV_TYPE_BYPASS) {
+		fecn = hfi1_16B_get_fecn(pkt->hdr);
+		becn = hfi1_16B_get_becn(pkt->hdr);
+	} else {
+		bth1 = be32_to_cpu(ohdr->bth[1]);
+		fecn = bth1 & IB_FECN_SMASK;
+		becn = bth1 & IB_BECN_SMASK;
+	}
+	if (unlikely(fecn || becn)) {
 		hfi1_process_ecn_slowpath(qp, pkt, do_cnp);
-		return !!(bth1 & IB_FECN_SMASK);
+		return fecn;
 	}
 	return false;
 }
@@ -2315,4 +2348,80 @@ static inline bool hfi1_get_hdr_type(u32 lid, struct rdma_ah_attr *attr)
 
 	return hfi1_get_packet_type(lid);
 }
+
+static inline void hfi1_make_ext_grh(struct hfi1_packet *packet,
+				     struct ib_grh *grh, u32 slid,
+				     u32 dlid)
+{
+	struct hfi1_ibport *ibp = &packet->rcd->ppd->ibport_data;
+	struct hfi1_pportdata *ppd = ppd_from_ibp(ibp);
+
+	if (!ibp)
+		return;
+
+	grh->hop_limit = 1;
+	grh->sgid.global.subnet_prefix = ibp->rvp.gid_prefix;
+	if (slid == opa_get_lid(be32_to_cpu(OPA_LID_PERMISSIVE), 16B))
+		grh->sgid.global.interface_id =
+			OPA_MAKE_ID(be32_to_cpu(OPA_LID_PERMISSIVE));
+	else
+		grh->sgid.global.interface_id = OPA_MAKE_ID(slid);
+
+	/*
+	 * Upper layers (like mad) may compare the dgid in the
+	 * wc that is obtained here with the sgid_index in
+	 * the wr. Since sgid_index in wr is always 0 for
+	 * extended lids, set the dgid here to the default
+	 * IB gid.
+	 */
+	grh->dgid.global.subnet_prefix = ibp->rvp.gid_prefix;
+	grh->dgid.global.interface_id =
+		cpu_to_be64(ppd->guids[HFI1_PORT_GUID_INDEX]);
+}
+
+static inline int hfi1_get_16b_padding(u32 hdr_size, u32 payload)
+{
+	return -(hdr_size + payload + (SIZE_OF_CRC << 2) +
+		     SIZE_OF_LT) & 0x7;
+}
+
+static inline void hfi1_make_ib_hdr(struct ib_header *hdr,
+				    u16 lrh0, u16 len,
+				    u16 dlid, u16 slid)
+{
+	hdr->lrh[0] = cpu_to_be16(lrh0);
+	hdr->lrh[1] = cpu_to_be16(dlid);
+	hdr->lrh[2] = cpu_to_be16(len);
+	hdr->lrh[3] = cpu_to_be16(slid);
+}
+
+static inline void hfi1_make_16b_hdr(struct hfi1_16b_header *hdr,
+				     u32 slid, u32 dlid,
+				     u16 len, u16 pkey,
+				     u8 becn, u8 fecn, u8 l4,
+				     u8 sc)
+{
+	u32 lrh0 = 0;
+	u32 lrh1 = 0x40000000;
+	u32 lrh2 = 0;
+	u32 lrh3 = 0;
+
+	lrh0 = (lrh0 & ~OPA_16B_BECN_MASK) | (becn << OPA_16B_BECN_SHIFT);
+	lrh0 = (lrh0 & ~OPA_16B_LEN_MASK) | (len << OPA_16B_LEN_SHIFT);
+	lrh0 = (lrh0 & ~OPA_16B_LID_MASK)  | (slid & OPA_16B_LID_MASK);
+	lrh1 = (lrh1 & ~OPA_16B_FECN_MASK) | (fecn << OPA_16B_FECN_SHIFT);
+	lrh1 = (lrh1 & ~OPA_16B_SC_MASK) | (sc << OPA_16B_SC_SHIFT);
+	lrh1 = (lrh1 & ~OPA_16B_LID_MASK) | (dlid & OPA_16B_LID_MASK);
+	lrh2 = (lrh2 & ~OPA_16B_SLID_MASK) |
+		((slid >> OPA_16B_SLID_SHIFT) << OPA_16B_SLID_HIGH_SHIFT);
+	lrh2 = (lrh2 & ~OPA_16B_DLID_MASK) |
+		((dlid >> OPA_16B_DLID_SHIFT) << OPA_16B_DLID_HIGH_SHIFT);
+	lrh2 = (lrh2 & ~OPA_16B_PKEY_MASK) | (pkey << OPA_16B_PKEY_SHIFT);
+	lrh2 = (lrh2 & ~OPA_16B_L4_MASK) | l4;
+
+	hdr->lrh[0] = lrh0;
+	hdr->lrh[1] = lrh1;
+	hdr->lrh[2] = lrh2;
+	hdr->lrh[3] = lrh3;
+}
 #endif                          /* _HFI1_KERNEL_H */

drivers/infiniband/hw/hfi1/mad.c

@@ -373,12 +373,10 @@ static struct trap_node *create_trap_node(u8 type, __be16 trap_num, u32 lid)
  * Send a bad P_Key trap (ch. 14.3.8).
  */
 void hfi1_bad_pkey(struct hfi1_ibport *ibp, u32 key, u32 sl,
-		   u32 qp1, u32 qp2, u16 lid1, u16 lid2)
+		   u32 qp1, u32 qp2, u32 lid1, u32 lid2)
 {
 	struct trap_node *trap;
 	u32 lid = ppd_from_ibp(ibp)->lid;
-	u32 _lid1 = lid1;
-	u32 _lid2 = lid2;
 
 	ibp->rvp.n_pkt_drops++;
 	ibp->rvp.pkey_violations++;
@@ -389,8 +387,8 @@ void hfi1_bad_pkey(struct hfi1_ibport *ibp, u32 key, u32 sl,
 		return;
 
 	/* Send violation trap */
-	trap->data.ntc_257_258.lid1 = cpu_to_be32(_lid1);
-	trap->data.ntc_257_258.lid2 = cpu_to_be32(_lid2);
+	trap->data.ntc_257_258.lid1 = cpu_to_be32(lid1);
+	trap->data.ntc_257_258.lid2 = cpu_to_be32(lid2);
 	trap->data.ntc_257_258.key = cpu_to_be32(key);
 	trap->data.ntc_257_258.sl = sl << 3;
 	trap->data.ntc_257_258.qp1 = cpu_to_be32(qp1);

drivers/infiniband/hw/hfi1/ruc.c

@@ -649,7 +649,7 @@ static void ruc_loopback(struct rvt_qp *sqp)
  * @ibp: a pointer to the IB port
  * @hdr: a pointer to the GRH header being constructed
  * @grh: the global route address to send to
- * @hwords: the number of 32 bit words of header being sent
+ * @hwords: size of header after grh being sent in dwords
  * @nwords: the number of 32 bit words of data being sent
  *
  * Return the size of the header in 32 bit words.
@@ -661,7 +661,7 @@ u32 hfi1_make_grh(struct hfi1_ibport *ibp, struct ib_grh *hdr,
 		cpu_to_be32((IB_GRH_VERSION << IB_GRH_VERSION_SHIFT) |
 			    (grh->traffic_class << IB_GRH_TCLASS_SHIFT) |
 			    (grh->flow_label << IB_GRH_FLOW_SHIFT));
-	hdr->paylen = cpu_to_be16((hwords - 2 + nwords + SIZE_OF_CRC) << 2);
+	hdr->paylen = cpu_to_be16((hwords + nwords) << 2);
 	/* next_hdr is defined by C8-7 in ch. 8.4.1 */
 	hdr->next_hdr = IB_GRH_NEXT_HDR;
 	hdr->hop_limit = grh->hop_limit;

drivers/infiniband/hw/hfi1/verbs.h

@@ -259,7 +259,7 @@ static inline int hfi1_send_ok(struct rvt_qp *qp)
  * This must be called with s_lock held.
  */
 void hfi1_bad_pkey(struct hfi1_ibport *ibp, u32 key, u32 sl,
-		   u32 qp1, u32 qp2, u16 lid1, u16 lid2);
+		   u32 qp1, u32 qp2, u32 lid1, u32 lid2);
 void hfi1_cap_mask_chg(struct rvt_dev_info *rdi, u8 port_num);
 void hfi1_sys_guid_chg(struct hfi1_ibport *ibp);
 void hfi1_node_desc_chg(struct hfi1_ibport *ibp);

include/rdma/opa_addr.h

@@ -54,6 +54,7 @@
 #define OPA_MAKE_ID(x)          (cpu_to_be64(OPA_SPECIAL_OUI << 40 | (x)))
 #define OPA_TO_IB_UCAST_LID(x) (((x) >= be16_to_cpu(IB_MULTICAST_LID_BASE)) \
 				? 0 : x)
+#define OPA_GID_INDEX		0x1
 /**
  * 0xF8 - 4 bits of multicast range and 1 bit for collective range
  * Example: For 24 bit LID space,