IB/hfi1: Add support to receive 16B bypass packets

We introduce a struct hfi1_16b_header to support 16B headers.
16B bypass packets are received by the driver and processed
similar to 9B packets. Add basic support to handle 16B packets.

Reviewed-by: Dennis Dalessandro <dennis.dalessandro@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/chip.c

@@ -14468,6 +14468,7 @@ void hfi1_deinit_vnic_rsm(struct hfi1_devdata *dd)
 static void init_rxe(struct hfi1_devdata *dd)
 {
 	struct rsm_map_table *rmt;
+	u64 val;
 
 	/* enable all receive errors */
 	write_csr(dd, RCV_ERR_MASK, ~0ull);
@@ -14492,6 +14493,11 @@ static void init_rxe(struct hfi1_devdata *dd)
 	 * (64 bytes).  Max_Payload_Size is possibly modified upward in
 	 * tune_pcie_caps() which is called after this routine.
 	 */
+
+	/* Have 16 bytes (4DW) of bypass header available in header queue */
+	val = read_csr(dd, RCV_BYPASS);
+	val |= (4ull << 16);
+	write_csr(dd, RCV_BYPASS, val);
 }
 
 static void init_other(struct hfi1_devdata *dd)

drivers/infiniband/hw/hfi1/common.h

@@ -327,6 +327,7 @@ struct diag_pkt {
 /* misc. */
 #define SC15_PACKET 0xF
 #define SIZE_OF_CRC 1
+#define SIZE_OF_LT 1
 
 #define LIM_MGMT_P_KEY       0x7FFF
 #define FULL_MGMT_P_KEY      0xFFFF

drivers/infiniband/hw/hfi1/driver.c

@@ -237,6 +237,13 @@ static inline struct ib_header *hfi1_get_msgheader(struct hfi1_devdata *dd,
 	return (struct ib_header *)hfi1_get_header(dd, rhf_addr);
 }
 
+static inline struct hfi1_16b_header
+		*hfi1_get_16B_header(struct hfi1_devdata *dd,
+				     __le32 *rhf_addr)
+{
+	return (struct hfi1_16b_header *)hfi1_get_header(dd, rhf_addr);
+}
+
 /*
  * Validate and encode the a given RcvArray Buffer size.
  * The function will check whether the given size falls within
@@ -925,6 +932,11 @@ static inline int set_armed_to_active(struct hfi1_ctxtdata *rcd,
 		struct ib_header *hdr = hfi1_get_msgheader(packet->rcd->dd,
 							   packet->rhf_addr);
 		sc = hfi1_9B_get_sc5(hdr, packet->rhf);
+	} else if (etype == RHF_RCV_TYPE_BYPASS) {
+		struct hfi1_16b_header *hdr = hfi1_get_16B_header(
+						packet->rcd->dd,
+						packet->rhf_addr);
+		sc = hfi1_16B_get_sc(hdr);
 	}
 	if (sc != SC15_PACKET) {
 		int hwstate = driver_lstate(rcd->ppd);
@@ -1386,9 +1398,14 @@ static int hfi1_setup_9B_packet(struct hfi1_packet *packet)
 	}
 
 	/* Query commonly used fields from packet header */
+	packet->payload = packet->ebuf;
 	packet->opcode = ib_bth_get_opcode(packet->ohdr);
 	packet->slid = ib_get_slid(hdr);
 	packet->dlid = ib_get_dlid(hdr);
+	if (unlikely((packet->dlid >= be16_to_cpu(IB_MULTICAST_LID_BASE)) &&
+		     (packet->dlid != be16_to_cpu(IB_LID_PERMISSIVE))))
+		packet->dlid += opa_get_mcast_base(OPA_MCAST_NR) -
+				be16_to_cpu(IB_MULTICAST_LID_BASE);
 	packet->sl = ib_get_sl(hdr);
 	packet->sc = hfi1_9B_get_sc5(hdr, packet->rhf);
 	packet->pad = ib_bth_get_pad(packet->ohdr);
@@ -1402,6 +1419,73 @@ drop:
 	return -EINVAL;
 }
 
+static int hfi1_setup_bypass_packet(struct hfi1_packet *packet)
+{
+	/*
+	 * Bypass packets have a different header/payload split
+	 * compared to an IB packet.
+	 * Current split is set such that 16 bytes of the actual
+	 * header is in the header buffer and the remining is in
+	 * the eager buffer. We chose 16 since hfi1 driver only
+	 * supports 16B bypass packets and we will be able to
+	 * receive the entire LRH with such a split.
+	 */
+
+	struct hfi1_ctxtdata *rcd = packet->rcd;
+	struct hfi1_pportdata *ppd = rcd->ppd;
+	struct hfi1_ibport *ibp = &ppd->ibport_data;
+	u8 l4;
+	u8 grh_len;
+
+	packet->hdr = (struct hfi1_16b_header *)
+			hfi1_get_16B_header(packet->rcd->dd,
+					    packet->rhf_addr);
+	packet->hlen = (u8 *)packet->rhf_addr - (u8 *)packet->hdr;
+
+	l4 = hfi1_16B_get_l4(packet->hdr);
+	if (l4 == OPA_16B_L4_IB_LOCAL) {
+		grh_len = 0;
+		packet->ohdr = packet->ebuf;
+		packet->grh = NULL;
+	} else if (l4 == OPA_16B_L4_IB_GLOBAL) {
+		u32 vtf;
+
+		grh_len = sizeof(struct ib_grh);
+		packet->ohdr = packet->ebuf + grh_len;
+		packet->grh = packet->ebuf;
+		if (packet->grh->next_hdr != IB_GRH_NEXT_HDR)
+			goto drop;
+		vtf = be32_to_cpu(packet->grh->version_tclass_flow);
+		if ((vtf >> IB_GRH_VERSION_SHIFT) != IB_GRH_VERSION)
+			goto drop;
+	} else {
+		goto drop;
+	}
+
+	/* Query commonly used fields from packet header */
+	packet->opcode = ib_bth_get_opcode(packet->ohdr);
+	packet->hlen = hdr_len_by_opcode[packet->opcode] + 8 + grh_len;
+	packet->payload = packet->ebuf + packet->hlen - (4 * sizeof(u32));
+	packet->slid = hfi1_16B_get_slid(packet->hdr);
+	packet->dlid = hfi1_16B_get_dlid(packet->hdr);
+	if (unlikely(hfi1_is_16B_mcast(packet->dlid)))
+		packet->dlid += opa_get_mcast_base(OPA_MCAST_NR) -
+				opa_get_lid(opa_get_mcast_base(OPA_MCAST_NR),
+					    16B);
+	packet->sc = hfi1_16B_get_sc(packet->hdr);
+	packet->sl = ibp->sc_to_sl[packet->sc];
+	packet->pad = hfi1_16B_bth_get_pad(packet->ohdr);
+	packet->extra_byte = SIZE_OF_LT;
+	packet->fecn = hfi1_16B_get_fecn(packet->hdr);
+	packet->becn = hfi1_16B_get_becn(packet->hdr);
+
+	return 0;
+drop:
+	hfi1_cdbg(PKT, "%s: packet dropped\n", __func__);
+	ibp->rvp.n_pkt_drops++;
+	return -EINVAL;
+}
+
 void handle_eflags(struct hfi1_packet *packet)
 {
 	struct hfi1_ctxtdata *rcd = packet->rcd;
@@ -1464,8 +1548,8 @@ static inline bool hfi1_is_vnic_packet(struct hfi1_packet *packet)
 	if (packet->rcd->is_vnic)
 		return true;
 
-	if ((HFI1_GET_L2_TYPE(packet->ebuf) == OPA_VNIC_L2_TYPE) &&
-	    (HFI1_GET_L4_TYPE(packet->ebuf) == OPA_VNIC_L4_ETHR))
+	if ((hfi1_16B_get_l2(packet->ebuf) == OPA_16B_L2_TYPE) &&
+	    (hfi1_16B_get_l4(packet->ebuf) == OPA_16B_L4_ETHR))
 		return true;
 
 	return false;
@@ -1475,25 +1559,38 @@ int process_receive_bypass(struct hfi1_packet *packet)
 {
 	struct hfi1_devdata *dd = packet->rcd->dd;
 
-	if (unlikely(rhf_err_flags(packet->rhf))) {
-		handle_eflags(packet);
-	} else if (hfi1_is_vnic_packet(packet)) {
+	if (hfi1_is_vnic_packet(packet)) {
 		hfi1_vnic_bypass_rcv(packet);
 		return RHF_RCV_CONTINUE;
 	}
 
-	dd_dev_err(dd, "Unsupported bypass packet. Dropping\n");
-	incr_cntr64(&dd->sw_rcv_bypass_packet_errors);
-	if (!(dd->err_info_rcvport.status_and_code & OPA_EI_STATUS_SMASK)) {
-		u64 *flits = packet->ebuf;
+	if (hfi1_setup_bypass_packet(packet))
+		return RHF_RCV_CONTINUE;
+
+	if (unlikely(rhf_err_flags(packet->rhf))) {
+		handle_eflags(packet);
+		return RHF_RCV_CONTINUE;
+	}
 
-		if (flits && !(packet->rhf & RHF_LEN_ERR)) {
-			dd->err_info_rcvport.packet_flit1 = flits[0];
-			dd->err_info_rcvport.packet_flit2 =
-				packet->tlen > sizeof(flits[0]) ? flits[1] : 0;
+	if (hfi1_16B_get_l2(packet->hdr) == 0x2) {
+		hfi1_16B_rcv(packet);
+	} else {
+		dd_dev_err(dd,
+			   "Bypass packets other than 16B are not supported in normal operation. Dropping\n");
+		incr_cntr64(&dd->sw_rcv_bypass_packet_errors);
+		if (!(dd->err_info_rcvport.status_and_code &
+		      OPA_EI_STATUS_SMASK)) {
+			u64 *flits = packet->ebuf;
+
+			if (flits && !(packet->rhf & RHF_LEN_ERR)) {
+				dd->err_info_rcvport.packet_flit1 = flits[0];
+				dd->err_info_rcvport.packet_flit2 =
+					packet->tlen > sizeof(flits[0]) ?
+					flits[1] : 0;
+			}
+			dd->err_info_rcvport.status_and_code |=
+				(OPA_EI_STATUS_SMASK | BAD_L2_ERR);
 		}
-		dd->err_info_rcvport.status_and_code |=
-			(OPA_EI_STATUS_SMASK | BAD_L2_ERR);
 	}
 	return RHF_RCV_CONTINUE;
 }

drivers/infiniband/hw/hfi1/hfi.h

@@ -66,6 +66,7 @@
 #include <linux/i2c.h>
 #include <linux/i2c-algo-bit.h>
 #include <rdma/ib_hdrs.h>
+#include <rdma/opa_addr.h>
 #include <linux/rhashtable.h>
 #include <linux/netdevice.h>
 #include <rdma/rdma_vt.h>
@@ -325,6 +326,7 @@ struct hfi1_ctxtdata {
 struct hfi1_packet {
 	void *ebuf;
 	void *hdr;
+	void *payload;
 	struct hfi1_ctxtdata *rcd;
 	__le32 *rhf_addr;
 	struct rvt_qp *qp;
@@ -351,6 +353,83 @@ struct hfi1_packet {
 	bool fecn;
 };
 
+/*
+ * OPA 16B Header
+ */
+#define OPA_16B_L4_MASK		0xFFull
+#define OPA_16B_SC_MASK		0x1F00000ull
+#define OPA_16B_SC_SHIFT	20
+#define OPA_16B_LID_MASK	0xFFFFFull
+#define OPA_16B_DLID_MASK	0xF000ull
+#define OPA_16B_DLID_SHIFT	20
+#define OPA_16B_DLID_HIGH_SHIFT	12
+#define OPA_16B_SLID_MASK	0xF00ull
+#define OPA_16B_SLID_SHIFT	20
+#define OPA_16B_SLID_HIGH_SHIFT	8
+#define OPA_16B_BECN_MASK       0x80000000ull
+#define OPA_16B_BECN_SHIFT      31
+#define OPA_16B_FECN_MASK       0x10000000ull
+#define OPA_16B_FECN_SHIFT      28
+#define OPA_16B_L2_MASK		0x60000000ull
+#define OPA_16B_L2_SHIFT	29
+
+/*
+ * OPA 16B L2/L4 Encodings
+ */
+#define OPA_16B_L2_TYPE		0x02
+#define OPA_16B_L4_IB_LOCAL	0x09
+#define OPA_16B_L4_IB_GLOBAL	0x0A
+#define OPA_16B_L4_ETHR		OPA_VNIC_L4_ETHR
+
+static inline u8 hfi1_16B_get_l4(struct hfi1_16b_header *hdr)
+{
+	return (u8)(hdr->lrh[2] & OPA_16B_L4_MASK);
+}
+
+static inline u8 hfi1_16B_get_sc(struct hfi1_16b_header *hdr)
+{
+	return (u8)((hdr->lrh[1] & OPA_16B_SC_MASK) >> OPA_16B_SC_SHIFT);
+}
+
+static inline u32 hfi1_16B_get_dlid(struct hfi1_16b_header *hdr)
+{
+	return (u32)((hdr->lrh[1] & OPA_16B_LID_MASK) |
+		     (((hdr->lrh[2] & OPA_16B_DLID_MASK) >>
+		     OPA_16B_DLID_HIGH_SHIFT) << OPA_16B_DLID_SHIFT));
+}
+
+static inline u32 hfi1_16B_get_slid(struct hfi1_16b_header *hdr)
+{
+	return (u32)((hdr->lrh[0] & OPA_16B_LID_MASK) |
+		     (((hdr->lrh[2] & OPA_16B_SLID_MASK) >>
+		     OPA_16B_SLID_HIGH_SHIFT) << OPA_16B_SLID_SHIFT));
+}
+
+static inline u8 hfi1_16B_get_becn(struct hfi1_16b_header *hdr)
+{
+	return (u8)((hdr->lrh[0] & OPA_16B_BECN_MASK) >> OPA_16B_BECN_SHIFT);
+}
+
+static inline u8 hfi1_16B_get_fecn(struct hfi1_16b_header *hdr)
+{
+	return (u8)((hdr->lrh[1] & OPA_16B_FECN_MASK) >> OPA_16B_FECN_SHIFT);
+}
+
+static inline u8 hfi1_16B_get_l2(struct hfi1_16b_header *hdr)
+{
+	return (u8)((hdr->lrh[1] & OPA_16B_L2_MASK) >> OPA_16B_L2_SHIFT);
+}
+
+/*
+ * BTH
+ */
+#define OPA_16B_BTH_PAD_MASK	7
+static inline u8 hfi1_16B_bth_get_pad(struct ib_other_headers *ohdr)
+{
+	return (u8)((be32_to_cpu(ohdr->bth[0]) >> IB_BTH_PAD_SHIFT) &
+		   OPA_16B_BTH_PAD_MASK);
+}
+
 struct rvt_sge_state;
 
 /*
@@ -2084,11 +2163,55 @@ int hfi1_tempsense_rd(struct hfi1_devdata *dd, struct hfi1_temp *temp);
 
 /*
  * hfi1_check_mcast- Check if the given lid is
- * in the IB multicast range.
+ * in the OPA multicast range.
+ *
+ * The LID might either reside in ah.dlid or might be
+ * in the GRH of the address handle as DGID if extended
+ * addresses are in use.
  */
-static inline bool hfi1_check_mcast(u16 lid)
+static inline bool hfi1_check_mcast(u32 lid)
+{
+	return ((lid >= opa_get_mcast_base(OPA_MCAST_NR)) &&
+		(lid != be32_to_cpu(OPA_LID_PERMISSIVE)));
+}
+
+#define opa_get_lid(lid, format)	\
+	__opa_get_lid(lid, OPA_PORT_PACKET_FORMAT_##format)
+
+/* Convert a lid to a specific lid space */
+static inline u32 __opa_get_lid(u32 lid, u8 format)
+{
+	bool is_mcast = hfi1_check_mcast(lid);
+
+	switch (format) {
+	case OPA_PORT_PACKET_FORMAT_8B:
+	case OPA_PORT_PACKET_FORMAT_10B:
+		if (is_mcast)
+			return (lid - opa_get_mcast_base(OPA_MCAST_NR) +
+				0xF0000);
+		return lid & 0xFFFFF;
+	case OPA_PORT_PACKET_FORMAT_16B:
+		if (is_mcast)
+			return (lid - opa_get_mcast_base(OPA_MCAST_NR) +
+				0xF00000);
+		return lid & 0xFFFFFF;
+	case OPA_PORT_PACKET_FORMAT_9B:
+		if (is_mcast)
+			return (lid -
+				opa_get_mcast_base(OPA_MCAST_NR) +
+				be16_to_cpu(IB_MULTICAST_LID_BASE));
+		else
+			return lid & 0xFFFF;
+	default:
+		return lid;
+	}
+}
+
+/* Return true if the given lid is the OPA 16B multicast range */
+static inline bool hfi1_is_16B_mcast(u32 lid)
 {
-	return ((lid >= be16_to_cpu(IB_MULTICAST_LID_BASE)) &&
-		(lid != be16_to_cpu(IB_LID_PERMISSIVE)));
+	return ((lid >=
+		opa_get_lid(opa_get_mcast_base(OPA_MCAST_NR), 16B)) &&
+		(lid != opa_get_lid(be32_to_cpu(OPA_LID_PERMISSIVE), 16B)));
 }
 #endif                          /* _HFI1_KERNEL_H */

drivers/infiniband/hw/hfi1/rc.c

@@ -1916,7 +1916,7 @@ void process_becn(struct hfi1_pportdata *ppd, u8 sl, u16 rlid, u32 lqpn,
 void hfi1_rc_rcv(struct hfi1_packet *packet)
 {
 	struct hfi1_ctxtdata *rcd = packet->rcd;
-	void *data = packet->ebuf;
+	void *data = packet->payload;
 	u32 tlen = packet->tlen;
 	struct rvt_qp *qp = packet->qp;
 	struct hfi1_ibport *ibp = rcd_to_iport(rcd);

drivers/infiniband/hw/hfi1/uc.c

@@ -297,7 +297,7 @@ bail_no_tx:
 void hfi1_uc_rcv(struct hfi1_packet *packet)
 {
 	struct hfi1_ibport *ibp = rcd_to_iport(packet->rcd);
-	void *data = packet->ebuf;
+	void *data = packet->payload;
 	u32 tlen = packet->tlen;
 	struct rvt_qp *qp = packet->qp;
 	struct ib_other_headers *ohdr = packet->ohdr;

drivers/infiniband/hw/hfi1/ud.c

@@ -667,11 +667,10 @@ void hfi1_ud_rcv(struct hfi1_packet *packet)
 	struct hfi1_ibport *ibp = rcd_to_iport(packet->rcd);
 	struct hfi1_pportdata *ppd = ppd_from_ibp(ibp);
 	struct ib_header *hdr = packet->hdr;
-	void *data = packet->ebuf;
+	void *data = packet->payload;
 	u32 tlen = packet->tlen;
 	struct rvt_qp *qp = packet->qp;
 	u8 sc5 = hfi1_9B_get_sc5(hdr, packet->rhf);
-	u32 bth1;
 	u8 sl_from_sc;
 	u8 extra_bytes = packet->pad;
 	u8 opcode = packet->opcode;
@@ -679,7 +678,6 @@ void hfi1_ud_rcv(struct hfi1_packet *packet)
 	u32 dlid = packet->dlid;
 	u32 slid = packet->slid;
 
-	bth1 = be32_to_cpu(ohdr->bth[1]);
 	qkey = ib_get_qkey(ohdr);
 	src_qp = ib_get_sqpn(ohdr);
 	pkey = ib_bth_get_pkey(ohdr);

drivers/infiniband/hw/hfi1/verbs.c

@@ -571,7 +571,7 @@ static inline void hfi1_handle_packet(struct hfi1_packet *packet,
 			goto drop;
 		mcast = rvt_mcast_find(&ibp->rvp,
 				       &packet->grh->dgid,
-				       packet->dlid);
+				       opa_get_lid(packet->dlid, 9B));
 		if (!mcast)
 			goto drop;
 		list_for_each_entry_rcu(p, &mcast->qp_list, list) {
@@ -627,14 +627,17 @@ drop:
 void hfi1_ib_rcv(struct hfi1_packet *packet)
 {
 	struct hfi1_ctxtdata *rcd = packet->rcd;
-	bool is_mcast = false;
 
-	if (unlikely(hfi1_check_mcast(packet->dlid)))
-		is_mcast = true;
+	trace_input_ibhdr(rcd->dd, packet, !!(rhf_dc_info(packet->rhf)));
+	hfi1_handle_packet(packet, hfi1_check_mcast(packet->dlid));
+}
+
+void hfi1_16B_rcv(struct hfi1_packet *packet)
+{
+	struct hfi1_ctxtdata *rcd = packet->rcd;
 
-	trace_input_ibhdr(rcd->dd, packet,
-			  !!(packet->rhf & RHF_DC_INFO_SMASK));
-	hfi1_handle_packet(packet, is_mcast);
+	trace_input_ibhdr(rcd->dd, packet, false);
+	hfi1_handle_packet(packet, hfi1_check_mcast(packet->dlid));
 }
 
 /*

drivers/infiniband/hw/hfi1/verbs.h

@@ -104,6 +104,17 @@ enum {
 	HFI1_HAS_GRH = (1 << 0),
 };
 
+struct hfi1_16b_header {
+	u32 lrh[4];
+	union {
+		struct {
+			struct ib_grh grh;
+			struct ib_other_headers oth;
+		} l;
+		struct ib_other_headers oth;
+	} u;
+} __packed;
+
 struct hfi1_ahg_info {
 	u32 ahgdesc[2];
 	u16 tx_flags;
@@ -378,6 +389,8 @@ void hfi1_unregister_ib_device(struct hfi1_devdata *);
 
 void hfi1_ib_rcv(struct hfi1_packet *packet);
 
+void hfi1_16B_rcv(struct hfi1_packet *packet);
+
 unsigned hfi1_get_npkeys(struct hfi1_devdata *);
 
 int hfi1_verbs_send_dma(struct rvt_qp *qp, struct hfi1_pkt_state *ps,

drivers/infiniband/hw/hfi1/vnic.h

@@ -54,21 +54,6 @@
 #define HFI1_VNIC_MAX_TXQ     16
 #define HFI1_VNIC_MAX_PAD     12
 
-/* L2 header definitions */
-#define HFI1_L2_TYPE_OFFSET     0x7
-#define HFI1_L2_TYPE_SHFT       0x5
-#define HFI1_L2_TYPE_MASK       0x3
-
-#define HFI1_GET_L2_TYPE(hdr)                                            \
-	((*((u8 *)(hdr) + HFI1_L2_TYPE_OFFSET) >> HFI1_L2_TYPE_SHFT) &   \
-	 HFI1_L2_TYPE_MASK)
-
-/* L4 type definitions */
-#define HFI1_L4_TYPE_OFFSET 8
-
-#define HFI1_GET_L4_TYPE(data)   \
-	(*((u8 *)(data) + HFI1_L4_TYPE_OFFSET))
-
 /* L4 header definitions */
 #define HFI1_VNIC_L4_HDR_OFFSET  OPA_VNIC_L2_HDR_LEN
 

drivers/infiniband/hw/hfi1/vnic_main.c

@@ -564,8 +564,8 @@ void hfi1_vnic_bypass_rcv(struct hfi1_packet *packet)
 	int l4_type, vesw_id = -1;
 	u8 q_idx;
 
-	l4_type = HFI1_GET_L4_TYPE(packet->ebuf);
-	if (likely(l4_type == OPA_VNIC_L4_ETHR)) {
+	l4_type = hfi1_16B_get_l4(packet->ebuf);
+	if (likely(l4_type == OPA_16B_L4_ETHR)) {
 		vesw_id = HFI1_VNIC_GET_VESWID(packet->ebuf);
 		vinfo = idr_find(&dd->vnic.vesw_idr, vesw_id);
 

include/rdma/opa_vnic.h

@@ -54,9 +54,6 @@
 
 #include <rdma/ib_verbs.h>
 
-/* VNIC uses 16B header format */
-#define OPA_VNIC_L2_TYPE    0x2
-
 /* 16 header bytes + 2 reserved bytes */
 #define OPA_VNIC_L2_HDR_LEN   (16 + 2)