IB/hfi1,rdmavt,core: Patches for-next

index b9024fa..27fcbeb 100644
@@ -2647,6 +2647,7 @@ ssize_t ib_uverbs_detach_mcast(struct ib_uverbs_file *file,
 	struct ib_qp                 *qp;
 	struct ib_uverbs_mcast_entry *mcast;
 	int                           ret = -EINVAL;
+	bool                          found = false;
 
 	if (copy_from_user(&cmd, buf, sizeof cmd))
 		return -EFAULT;

@@ -2658,18 +2659,22 @@ ssize_t ib_uverbs_detach_mcast(struct ib_uverbs_file *file,
 	obj = container_of(qp->uobject, struct ib_uqp_object, uevent.uobject);
 	mutex_lock(&obj->mcast_lock);
 
-	ret = ib_detach_mcast(qp, (union ib_gid *) cmd.gid, cmd.mlid);
-	if (ret)
-		goto out_put;
-
 	list_for_each_entry(mcast, &obj->mcast_list, list)
 		if (cmd.mlid == mcast->lid &&
 		    !memcmp(cmd.gid, mcast->gid.raw, sizeof mcast->gid.raw)) {
 			list_del(&mcast->list);
 			kfree(mcast);
+			found = true;
 			break;
 		}
 
+	if (!found) {
+		ret = -EINVAL;
+		goto out_put;
+	}
+
+	ret = ib_detach_mcast(qp, (union ib_gid *)cmd.gid, cmd.mlid);
+
 out_put:
 	mutex_unlock(&obj->mcast_lock);
 	uobj_put_obj_read(qp);

index 1b783bb..804150f 100644
@@ -338,6 +338,15 @@ struct diag_pkt {
 #define HFI1_BECN_MASK 1
 #define HFI1_BECN_SMASK BIT(HFI1_BECN_SHIFT)
 
+/**
+ * 0xF8 - 4 bits of multicast range and 1 bit for collective range
+ * Example: For 24 bit LID space,
+ * Multicast range: 0xF00000 to 0xF7FFFF
+ * Collective range: 0xF80000 to 0xFFFFFE
+ */
+#define HFI1_MCAST_NR 0x4 /* Number of top bits set */
+#define HFI1_COLLECTIVE_NR 0x1 /* Number of bits after MCAST_NR */
+
 #define HFI1_PSM_IOC_BASE_SEQ 0x0
 
 static inline __u64 rhf_to_cpu(const __le32 *rbuf)

index 09cda3c..de34131 100644
@@ -702,6 +702,11 @@ static int __subn_get_opa_portinfo(struct opa_smp *smp, u32 am, u8 *data,
 	pi->buffer_units = cpu_to_be32(buffer_units);
 
 	pi->opa_cap_mask = cpu_to_be16(OPA_CAP_MASK3_IsSharedSpaceSupported);
+	/* Driver does not support mcast/collective configuration */
+	pi->opa_cap_mask &=
+		cpu_to_be16(~OPA_CAP_MASK3_IsAddrRangeConfigSupported);
+	pi->collectivemask_multicastmask = ((HFI1_COLLECTIVE_NR & 0x7)
+					    << 3 | (HFI1_MCAST_NR & 0x7));
 
 	/* HFI supports a replay buffer 128 LTPs in size */
 	pi->replay_depth.buffer = 0x80;

index 070a349..f74abb1 100644
@@ -603,7 +603,7 @@ void hfi1_ib_rcv(struct hfi1_packet *packet)
 
 		if (lnh != HFI1_LRH_GRH)
 			goto drop;
-		mcast = rvt_mcast_find(&ibp->rvp, &hdr->u.l.grh.dgid);
+		mcast = rvt_mcast_find(&ibp->rvp, &hdr->u.l.grh.dgid, lid);
 		if (!mcast)
 			goto drop;
 		list_for_each_entry_rcu(p, &mcast->qp_list, list) {

index e120efe..68d449c 100644
@@ -356,7 +356,7 @@ void qib_ib_rcv(struct qib_ctxtdata *rcd, void *rhdr, void *data, u32 tlen)
 
 		if (lnh != QIB_LRH_GRH)
 			goto drop;
-		mcast = rvt_mcast_find(&ibp->rvp, &hdr->u.l.grh.dgid);
+		mcast = rvt_mcast_find(&ibp->rvp, &hdr->u.l.grh.dgid, lid);
 		if (mcast == NULL)
 			goto drop;
 		this_cpu_inc(ibp->pmastats->n_multicast_rcv);

139 lines not on this page · raw message

index 8fc1ca7..7f89568 100644
@@ -516,6 +516,7 @@ 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_mcast *rvt_mcast_find(struct rvt_ibport *ibp, union ib_gid *mgid);
+struct rvt_mcast *rvt_mcast_find(struct rvt_ibport *ibp, union ib_gid *mgid,
+				 u16 lid);
 
 #endif          /* DEF_RDMA_VT_H */

index e3bb312..75a077c 100644
@@ -435,9 +435,14 @@ struct rvt_mcast_qp {
 	struct rvt_qp *qp;
 };
 
+struct rvt_mcast_addr {
+	union ib_gid mgid;
+	u16 lid;
+};
+
 struct rvt_mcast {
 	struct rb_node rb_node;
-	union ib_gid mgid;
+	struct rvt_mcast_addr mcast_addr;
 	struct list_head qp_list;
 	wait_queue_head_t wait;
 	atomic_t refcount;

index 4a82953..9b8bdf7 100644
@@ -578,6 +578,9 @@ int hfi1_user_exp_rcv_clear(struct file *fp, struct hfi1_tid_info *tinfo)
 	u32 *tidinfo;
 	unsigned tididx;
 
+	if (unlikely(tinfo->tidcnt > fd->tid_used))
+		return -EINVAL;
+
 	tidinfo = memdup_user((void __user *)(unsigned long)tinfo->tidlist,
 			      sizeof(tidinfo[0]) * tinfo->tidcnt);
 	if (IS_ERR(tidinfo))

index de34131..db5494d 100644
@@ -1,5 +1,5 @@
 /*
- * Copyright(c) 2015, 2016 Intel Corporation.
+ * Copyright(c) 2015-2017 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.

@@ -1470,25 +1470,15 @@ static int __subn_set_opa_pkeytable(struct opa_smp *smp, u32 am, u8 *data,
 	return __subn_get_opa_pkeytable(smp, am, data, ibdev, port, resp_len);
 }
 
-static int get_sc2vlt_tables(struct hfi1_devdata *dd, void *data)
-{
-	u64 *val = data;
-
-	*val++ = read_csr(dd, SEND_SC2VLT0);
-	*val++ = read_csr(dd, SEND_SC2VLT1);
-	*val++ = read_csr(dd, SEND_SC2VLT2);
-	*val++ = read_csr(dd, SEND_SC2VLT3);
-	return 0;
-}
-
 #define ILLEGAL_VL 12
 /*
  * filter_sc2vlt changes mappings to VL15 to ILLEGAL_VL (except
  * for SC15, which must map to VL15). If we don't remap things this
  * way it is possible for VL15 counters to increment when we try to
  * send on a SC which is mapped to an invalid VL.
+ * When getting the table convert ILLEGAL_VL back to VL15.
  */
-static void filter_sc2vlt(void *data)
+static void filter_sc2vlt(void *data, bool set)
 {
 	int i;
 	u8 *pd = data;

@@ -1496,8 +1486,14 @@ static void filter_sc2vlt(void *data)
 	for (i = 0; i < OPA_MAX_SCS; i++) {
 		if (i == 15)
 			continue;
-		if ((pd[i] & 0x1f) == 0xf)
-			pd[i] = ILLEGAL_VL;
+
+		if (set) {
+			if ((pd[i] & 0x1f) == 0xf)
+				pd[i] = ILLEGAL_VL;
+		} else {
+			if ((pd[i] & 0x1f) == ILLEGAL_VL)
+				pd[i] = 0xf;
+		}
 	}
 }
 

@@ -1505,7 +1501,7 @@ static int set_sc2vlt_tables(struct hfi1_devdata *dd, void *data)
 {
 	u64 *val = data;
 
-	filter_sc2vlt(data);
+	filter_sc2vlt(data, true);
 
 	write_csr(dd, SEND_SC2VLT0, *val++);
 	write_csr(dd, SEND_SC2VLT1, *val++);

@@ -1517,6 +1513,19 @@ static int set_sc2vlt_tables(struct hfi1_devdata *dd, void *data)
 	return 0;
 }
 
+static int get_sc2vlt_tables(struct hfi1_devdata *dd, void *data)
+{
+	u64 *val = (u64 *)data;
+
+	*val++ = read_csr(dd, SEND_SC2VLT0);
+	*val++ = read_csr(dd, SEND_SC2VLT1);
+	*val++ = read_csr(dd, SEND_SC2VLT2);
+	*val++ = read_csr(dd, SEND_SC2VLT3);
+
+	filter_sc2vlt((u64 *)data, false);
+	return 0;
+}
+
 static int __subn_get_opa_sl_to_sc(struct opa_smp *smp, u32 am, u8 *data,
 				   struct ib_device *ibdev, u8 port,
 				   u32 *resp_len)

index 64bdbce..d731b5e 100644
@@ -397,7 +397,7 @@ static void rcv_hdrerr(struct hfi1_ctxtdata *rcd, struct hfi1_pportdata *ppd,
 			u16 rlid;
 			u8 svc_type, sl, sc5;
 
-			sc5 = hdr2sc(rhdr, packet->rhf);
+			sc5 = hfi1_9B_get_sc5(rhdr, packet->rhf);
 			sl = ibp->sc_to_sl[sc5];
 
 			lqpn = be32_to_cpu(bth[1]) & RVT_QPN_MASK;

@@ -492,7 +492,7 @@ void hfi1_process_ecn_slowpath(struct rvt_qp *qp, struct hfi1_packet *pkt,
 		return;
 	}
 
-	sc = hdr2sc(hdr, pkt->rhf);
+	sc = hfi1_9B_get_sc5(hdr, pkt->rhf);
 
 	bth1 = be32_to_cpu(ohdr->bth[1]);
 	if (do_cnp && (bth1 & HFI1_FECN_SMASK)) {

@@ -909,7 +909,8 @@ static inline int set_armed_to_active(struct hfi1_ctxtdata *rcd,
 						   packet->rhf_addr);
 	u8 etype = rhf_rcv_type(packet->rhf);
 
-	if (etype == RHF_RCV_TYPE_IB && hdr2sc(hdr, packet->rhf) != 0xf) {
+	if (etype == RHF_RCV_TYPE_IB &&
+	    hfi1_9B_get_sc5(hdr, packet->rhf) != 0xf) {
 		int hwstate = read_logical_state(dd);
 
 		if (hwstate != LSTATE_ACTIVE) {

index a31638c..8509502 100644
@@ -1261,7 +1261,7 @@ static inline u32 driver_lstate(struct hfi1_pportdata *ppd)
 void receive_interrupt_work(struct work_struct *work);
 
 /* extract service channel from header and rhf */
-static inline int hdr2sc(struct ib_header *hdr, u64 rhf)
+static inline int hfi1_9B_get_sc5(struct ib_header *hdr, u64 rhf)
 {
 	return ((be16_to_cpu(hdr->lrh[0]) >> 12) & 0xf) |
 	       ((!!(rhf_dc_info(rhf))) << 4);

index 13ea4eb..fd105cf 100644
@@ -680,7 +680,7 @@ void hfi1_ud_rcv(struct hfi1_packet *packet)
 	u32 tlen = packet->tlen;
 	struct rvt_qp *qp = packet->qp;
 	bool has_grh = rcv_flags & HFI1_HAS_GRH;
-	u8 sc5 = hdr2sc(hdr, packet->rhf);
+	u8 sc5 = hfi1_9B_get_sc5(hdr, packet->rhf);
 	u32 bth1;
 	u8 sl_from_sc, sl;
 	u16 slid;

index f74abb1..66a2378 100644
@@ -1928,7 +1928,7 @@ void hfi1_cnp_rcv(struct hfi1_packet *packet)
 		return;
 	}
 
-	sc5 = hdr2sc(hdr, packet->rhf);
+	sc5 = hfi1_9B_get_sc5(hdr, packet->rhf);
 	sl = ibp->sc_to_sl[sc5];
 	lqpn = qp->ibqp.qp_num;
 

index d731b5e..7e6d86b 100644
@@ -284,7 +284,7 @@ static void rcv_hdrerr(struct hfi1_ctxtdata *rcd, struct hfi1_pportdata *ppd,
 {
 	struct ib_header *rhdr = packet->hdr;
 	u32 rte = rhf_rcv_type_err(packet->rhf);
-	int lnh = be16_to_cpu(rhdr->lrh[0]) & 3;
+	int lnh = ib_get_lnh(rhdr);
 	struct hfi1_ibport *ibp = rcd_to_iport(rcd);
 	struct hfi1_devdata *dd = ppd->dd;
 	struct rvt_dev_info *rdi = &dd->verbs_dev.rdi;

@@ -296,7 +296,7 @@ static void rcv_hdrerr(struct hfi1_ctxtdata *rcd, struct hfi1_pportdata *ppd,
 		/* For TIDERR and RC QPs preemptively schedule a NAK */
 		struct ib_other_headers *ohdr = NULL;
 		u32 tlen = rhf_pkt_len(packet->rhf); /* in bytes */
-		u16 lid  = be16_to_cpu(rhdr->lrh[1]);
+		u16 lid  = ib_get_dlid(rhdr);
 		u32 qp_num;
 		u32 rcv_flags = 0;
 

@@ -415,7 +415,7 @@ static void rcv_hdrerr(struct hfi1_ctxtdata *rcd, struct hfi1_pportdata *ppd,
 				svc_type = IB_CC_SVCTYPE_UD;
 				break;
 			case IB_QPT_UC:
-				rlid = be16_to_cpu(rhdr->lrh[3]);
+				rlid = ib_get_slid(rhdr);
 				rqpn = qp->remote_qpn;
 				svc_type = IB_CC_SVCTYPE_UC;
 				break;

@@ -461,7 +461,7 @@ void hfi1_process_ecn_slowpath(struct rvt_qp *qp, struct hfi1_packet *pkt,
 	struct ib_other_headers *ohdr = pkt->ohdr;
 	struct ib_grh *grh = NULL;
 	u32 rqpn = 0, bth1;
-	u16 rlid, dlid = be16_to_cpu(hdr->lrh[1]);
+	u16 rlid, dlid = ib_get_dlid(hdr);
 	u8 sc, svc_type;
 	bool is_mcast = false;
 

@@ -472,7 +472,7 @@ void hfi1_process_ecn_slowpath(struct rvt_qp *qp, struct hfi1_packet *pkt,
 	case IB_QPT_SMI:
 	case IB_QPT_GSI:
 	case IB_QPT_UD:
-		rlid = be16_to_cpu(hdr->lrh[3]);
+		rlid = ib_get_slid(hdr);
 		rqpn = be32_to_cpu(ohdr->u.ud.deth[1]) & RVT_QPN_MASK;
 		svc_type = IB_CC_SVCTYPE_UD;
 		is_mcast = (dlid > be16_to_cpu(IB_MULTICAST_LID_BASE)) &&

@@ -622,8 +622,7 @@ static void __prescan_rxq(struct hfi1_packet *packet)
 
 		packet->hdr = hfi1_get_msgheader(dd, rhf_addr);
 		hdr = packet->hdr;
-
-		lnh = be16_to_cpu(hdr->lrh[0]) & 3;
+		lnh = ib_get_lnh(hdr);
 
 		if (lnh == HFI1_LRH_BTH) {
 			packet->ohdr = &hdr->u.oth;

index 8509502..1d9436c 100644
@@ -1263,8 +1263,7 @@ static inline u32 driver_lstate(struct hfi1_pportdata *ppd)
 /* extract service channel from header and rhf */
 static inline int hfi1_9B_get_sc5(struct ib_header *hdr, u64 rhf)
 {
-	return ((be16_to_cpu(hdr->lrh[0]) >> 12) & 0xf) |
-	       ((!!(rhf_dc_info(rhf))) << 4);
+	return ib_get_sc(hdr) | ((!!(rhf_dc_info(rhf))) << 4);
 }
 
 #define HFI1_JKEY_WIDTH       16

index 0e56578..623209a 100644
@@ -994,12 +994,12 @@ void hfi1_rc_send_complete(struct rvt_qp *qp, struct ib_header *hdr)
 		return;
 
 	/* Find out where the BTH is */
-	if ((be16_to_cpu(hdr->lrh[0]) & 3) == HFI1_LRH_BTH)
+	if (ib_get_lnh(hdr) == HFI1_LRH_BTH)
 		ohdr = &hdr->u.oth;
 	else
 		ohdr = &hdr->u.l.oth;
 
-	opcode = be32_to_cpu(ohdr->bth[0]) >> 24;
+	opcode = ib_bth_get_opcode(ohdr);
 	if (opcode >= OP(RDMA_READ_RESPONSE_FIRST) &&
 	    opcode <= OP(ATOMIC_ACKNOWLEDGE)) {
 		WARN_ON(!qp->s_rdma_ack_cnt);

@@ -1524,7 +1524,7 @@ static void rc_rcv_resp(struct hfi1_ibport *ibp,
 		if (!do_rc_ack(qp, aeth, psn, opcode, 0, rcd))
 			goto ack_done;
 		/* Get the number of bytes the message was padded by. */
-		pad = (be32_to_cpu(ohdr->bth[0]) >> 20) & 3;
+		pad = ib_bth_get_pad(ohdr);
 		/*
 		 * Check that the data size is >= 0 && <= pmtu.
 		 * Remember to account for ICRC (4).

@@ -1548,7 +1548,7 @@ static void rc_rcv_resp(struct hfi1_ibport *ibp,
 		if (unlikely(wqe->wr.opcode != IB_WR_RDMA_READ))
 			goto ack_op_err;
 		/* Get the number of bytes the message was padded by. */
-		pad = (be32_to_cpu(ohdr->bth[0]) >> 20) & 3;
+		pad = ib_bth_get_pad(ohdr);
 		/*
 		 * Check that the data size is >= 1 && <= pmtu.
 		 * Remember to account for ICRC (4).

@@ -1942,7 +1942,7 @@ void hfi1_rc_rcv(struct hfi1_packet *packet)
 	is_fecn = process_ecn(qp, packet, false);
 
 	psn = be32_to_cpu(ohdr->bth[2]);
-	opcode = (bth0 >> 24) & 0xff;
+	opcode = ib_bth_get_opcode(ohdr);
 
 	/*
 	 * Process responses (ACKs) before anything else.  Note that the

@@ -2073,7 +2073,7 @@ void hfi1_rc_rcv(struct hfi1_packet *packet)
 		wc.ex.imm_data = 0;
 send_last:
 		/* Get the number of bytes the message was padded by. */
-		pad = (bth0 >> 20) & 3;
+		pad = ib_bth_get_pad(ohdr);
 		/* Check for invalid length. */
 		/* LAST len should be >= 1 */
 		if (unlikely(tlen < (hdrsize + pad + 4)))

@@ -2386,7 +2386,7 @@ void hfi1_rc_hdrerr(
 		return;
 
 	psn = be32_to_cpu(ohdr->bth[2]);
-	opcode = (bth0 >> 24) & 0xff;
+	opcode = ib_bth_get_opcode(ohdr);
 
 	/* Only deal with RDMA Writes for now */
 	if (opcode < IB_OPCODE_RC_RDMA_READ_RESPONSE_FIRST) {

index eeb650d..2730915 100644
@@ -238,18 +238,18 @@ int hfi1_ruc_check_hdr(struct hfi1_ibport *ibp, struct ib_header *hdr,
 				qp->alt_ah_attr.grh.dgid.global.interface_id))
 				goto err;
 		}
-		if (unlikely(rcv_pkey_check(ppd_from_ibp(ibp), (u16)bth0,
-					    sc5, be16_to_cpu(hdr->lrh[3])))) {
+		if (unlikely(rcv_pkey_check(ppd_from_ibp(ibp), (u16)bth0, sc5,
+					    ib_get_slid(hdr)))) {
 			hfi1_bad_pqkey(ibp, OPA_TRAP_BAD_P_KEY,
 				       (u16)bth0,
-				       (be16_to_cpu(hdr->lrh[0]) >> 4) & 0xF,
+				       ib_get_sl(hdr),
 				       0, qp->ibqp.qp_num,
-				       be16_to_cpu(hdr->lrh[3]),
-				       be16_to_cpu(hdr->lrh[1]));
+				       ib_get_slid(hdr),
+				       ib_get_dlid(hdr));
 			goto err;
 		}
 		/* Validate the SLID. See Ch. 9.6.1.5 and 17.2.8 */
-		if (be16_to_cpu(hdr->lrh[3]) != qp->alt_ah_attr.dlid ||
+		if (ib_get_slid(hdr) != qp->alt_ah_attr.dlid ||
 		    ppd_from_ibp(ibp)->port != qp->alt_ah_attr.port_num)
 			goto err;
 		spin_lock_irqsave(&qp->s_lock, flags);

@@ -273,18 +273,18 @@ int hfi1_ruc_check_hdr(struct hfi1_ibport *ibp, struct ib_header *hdr,
 			     qp->remote_ah_attr.grh.dgid.global.interface_id))
 				goto err;
 		}
-		if (unlikely(rcv_pkey_check(ppd_from_ibp(ibp), (u16)bth0,
-					    sc5, be16_to_cpu(hdr->lrh[3])))) {
+		if (unlikely(rcv_pkey_check(ppd_from_ibp(ibp), (u16)bth0, sc5,
+					    ib_get_slid(hdr)))) {
 			hfi1_bad_pqkey(ibp, OPA_TRAP_BAD_P_KEY,
 				       (u16)bth0,
-				       (be16_to_cpu(hdr->lrh[0]) >> 4) & 0xF,
+				       ib_get_sl(hdr),
 				       0, qp->ibqp.qp_num,
-				       be16_to_cpu(hdr->lrh[3]),
-				       be16_to_cpu(hdr->lrh[1]));
+				       ib_get_slid(hdr),
+				       ib_get_dlid(hdr));
 			goto err;
 		}
 		/* Validate the SLID. See Ch. 9.6.1.5 */
-		if (be16_to_cpu(hdr->lrh[3]) != qp->remote_ah_attr.dlid ||
+		if (ib_get_slid(hdr) != qp->remote_ah_attr.dlid ||
 		    ppd_from_ibp(ibp)->port != qp->port_num)
 			goto err;
 		if (qp->s_mig_state == IB_MIG_REARM &&

index e86798a..eafae48 100644
@@ -51,13 +51,12 @@ u8 ibhdr_exhdr_len(struct ib_header *hdr)
 {
 	struct ib_other_headers *ohdr;
 	u8 opcode;
-	u8 lnh = (u8)(be16_to_cpu(hdr->lrh[0]) & 3);
 
-	if (lnh == HFI1_LRH_BTH)
+	if (ib_get_lnh(hdr) == HFI1_LRH_BTH)
 		ohdr = &hdr->u.oth;
 	else
 		ohdr = &hdr->u.l.oth;
-	opcode = be32_to_cpu(ohdr->bth[0]) >> 24;
+	opcode = ib_bth_get_opcode(ohdr);
 	return hdr_len_by_opcode[opcode] == 0 ?
 	       0 : hdr_len_by_opcode[opcode] - (12 + 8);
 }

index 4b2a840..f0bdb10 100644
@@ -320,7 +320,7 @@ void hfi1_uc_rcv(struct hfi1_packet *packet)
 	process_ecn(qp, packet, true);
 
 	psn = be32_to_cpu(ohdr->bth[2]);
-	opcode = (bth0 >> 24) & 0xff;
+	opcode = ib_bth_get_opcode(ohdr);
 
 	/* Compare the PSN verses the expected PSN. */
 	if (unlikely(cmp_psn(psn, qp->r_psn) != 0)) {

@@ -433,7 +433,7 @@ void hfi1_uc_rcv(struct hfi1_packet *packet)
 		wc.wc_flags = 0;
 send_last:
 		/* Get the number of bytes the message was padded by. */
-		pad = (be32_to_cpu(ohdr->bth[0]) >> 20) & 3;
+		pad = ib_bth_get_pad(ohdr);
 		/* Check for invalid length. */
 		/* LAST len should be >= 1 */
 		if (unlikely(tlen < (hdrsize + pad + 4)))

@@ -528,7 +528,7 @@ void hfi1_uc_rcv(struct hfi1_packet *packet)
 		wc.wc_flags = IB_WC_WITH_IMM;
 
 		/* Get the number of bytes the message was padded by. */
-		pad = (be32_to_cpu(ohdr->bth[0]) >> 20) & 3;
+		pad = ib_bth_get_pad(ohdr);
 		/* Check for invalid length. */
 		/* LAST len should be >= 1 */
 		if (unlikely(tlen < (hdrsize + pad + 4)))

@@ -555,7 +555,7 @@ void hfi1_uc_rcv(struct hfi1_packet *packet)
 	case OP(RDMA_WRITE_LAST):
 rdma_last:
 		/* Get the number of bytes the message was padded by. */
-		pad = (be32_to_cpu(ohdr->bth[0]) >> 20) & 3;
+		pad = ib_bth_get_pad(ohdr);
 		/* Check for invalid length. */
 		/* LAST len should be >= 1 */
 		if (unlikely(tlen < (hdrsize + pad + 4)))

index fd105cf..8b3403a 100644
@@ -688,18 +688,16 @@ void hfi1_ud_rcv(struct hfi1_packet *packet)
 
 	qkey = be32_to_cpu(ohdr->u.ud.deth[0]);
 	src_qp = be32_to_cpu(ohdr->u.ud.deth[1]) & RVT_QPN_MASK;
-	dlid = be16_to_cpu(hdr->lrh[1]);
+	dlid = ib_get_dlid(hdr);
 	bth1 = be32_to_cpu(ohdr->bth[1]);
-	slid = be16_to_cpu(hdr->lrh[3]);
-	pkey = (u16)be32_to_cpu(ohdr->bth[0]);
-	sl = (be16_to_cpu(hdr->lrh[0]) >> 4) & 0xf;
-	extra_bytes = (be32_to_cpu(ohdr->bth[0]) >> 20) & 3;
+	slid = ib_get_slid(hdr);
+	pkey = ib_bth_get_pkey(ohdr);
+	opcode = ib_bth_get_opcode(ohdr);
+	sl = ib_get_sl(hdr);
+	extra_bytes = ib_bth_get_pad(ohdr);
 	extra_bytes += (SIZE_OF_CRC << 2);
 	sl_from_sc = ibp->sc_to_sl[sc5];
 
-	opcode = be32_to_cpu(ohdr->bth[0]) >> 24;
-	opcode &= 0xff;
-
 	process_ecn(qp, packet, (opcode != IB_OPCODE_CNP));
 	/*
 	 * Get the number of bytes the message was padded by

index 66a2378..7f49719 100644
@@ -571,7 +571,7 @@ void hfi1_ib_rcv(struct hfi1_packet *packet)
 	u16 lid;
 
 	/* Check for GRH */
-	lnh = be16_to_cpu(hdr->lrh[0]) & 3;
+	lnh = ib_get_lnh(hdr);
 	if (lnh == HFI1_LRH_BTH) {
 		packet->ohdr = &hdr->u.oth;
 	} else if (lnh == HFI1_LRH_GRH) {

@@ -590,12 +590,12 @@ void hfi1_ib_rcv(struct hfi1_packet *packet)
 
 	trace_input_ibhdr(rcd->dd, hdr);
 
-	opcode = (be32_to_cpu(packet->ohdr->bth[0]) >> 24);
+	opcode = ib_bth_get_opcode(packet->ohdr);
 	inc_opstats(tlen, &rcd->opstats->stats[opcode]);
 
 	/* Get the destination QP number. */
 	qp_num = be32_to_cpu(packet->ohdr->bth[1]) & RVT_QPN_MASK;
-	lid = be16_to_cpu(hdr->lrh[1]);
+	lid = ib_get_dlid(hdr);
 	if (unlikely((lid >= be16_to_cpu(IB_MULTICAST_LID_BASE)) &&
 		     (lid != be16_to_cpu(IB_LID_PERMISSIVE)))) {
 		struct rvt_mcast *mcast;

@@ -1230,7 +1230,7 @@ int hfi1_verbs_send(struct rvt_qp *qp, struct hfi1_pkt_state *ps)
 
 	hdr = &ps->s_txreq->phdr.hdr;
 	/* locate the pkey within the headers */
-	lnh = be16_to_cpu(hdr->lrh[0]) & 3;
+	lnh = ib_get_lnh(hdr);
 	if (lnh == HFI1_LRH_GRH)
 		ohdr = &hdr->u.l.oth;
 	else

64 lines not on this page · raw message

index 804150f..995d62c 100644
@@ -331,12 +331,6 @@ struct diag_pkt {
 #define FULL_MGMT_P_KEY      0xFFFF
 
 #define DEFAULT_P_KEY LIM_MGMT_P_KEY
-#define HFI1_FECN_SHIFT 31
-#define HFI1_FECN_MASK 1
-#define HFI1_FECN_SMASK BIT(HFI1_FECN_SHIFT)
-#define HFI1_BECN_SHIFT 30
-#define HFI1_BECN_MASK 1
-#define HFI1_BECN_SMASK BIT(HFI1_BECN_SHIFT)
 
 /**
  * 0xF8 - 4 bits of multicast range and 1 bit for collective range

index 7e6d86b..fc5753c 100644
@@ -495,13 +495,13 @@ void hfi1_process_ecn_slowpath(struct rvt_qp *qp, struct hfi1_packet *pkt,
 	sc = hfi1_9B_get_sc5(hdr, pkt->rhf);
 
 	bth1 = be32_to_cpu(ohdr->bth[1]);
-	if (do_cnp && (bth1 & HFI1_FECN_SMASK)) {
+	if (do_cnp && (bth1 & IB_FECN_SMASK)) {
 		u16 pkey = (u16)be32_to_cpu(ohdr->bth[0]);
 
 		return_cnp(ibp, qp, rqpn, pkey, dlid, rlid, sc, grh);
 	}
 
-	if (!is_mcast && (bth1 & HFI1_BECN_SMASK)) {
+	if (!is_mcast && (bth1 & IB_BECN_SMASK)) {
 		struct hfi1_pportdata *ppd = ppd_from_ibp(ibp);
 		u32 lqpn = bth1 & RVT_QPN_MASK;
 		u8 sl = ibp->sc_to_sl[sc];

@@ -634,7 +634,7 @@ static void __prescan_rxq(struct hfi1_packet *packet)
 		}
 
 		bth1 = be32_to_cpu(packet->ohdr->bth[1]);
-		is_ecn = !!(bth1 & (HFI1_FECN_SMASK | HFI1_BECN_SMASK));
+		is_ecn = !!(bth1 & (IB_FECN_SMASK | IB_BECN_SMASK));
 
 		if (!is_ecn)
 			goto next;

@@ -652,7 +652,7 @@ static void __prescan_rxq(struct hfi1_packet *packet)
 		rcu_read_unlock();
 
 		/* turn off BECN, FECN */
-		bth1 &= ~(HFI1_FECN_SMASK | HFI1_BECN_SMASK);
+		bth1 &= ~(IB_FECN_SMASK | IB_BECN_SMASK);
 		packet->ohdr->bth[1] = cpu_to_be32(bth1);
 next:
 		update_ps_mdata(&mdata, rcd);

index 1d9436c..79c4289 100644
@@ -1597,9 +1597,9 @@ static inline bool process_ecn(struct rvt_qp *qp, struct hfi1_packet *pkt,
 	u32 bth1;
 
 	bth1 = be32_to_cpu(ohdr->bth[1]);
-	if (unlikely(bth1 & (HFI1_BECN_SMASK | HFI1_FECN_SMASK))) {
+	if (unlikely(bth1 & (IB_BECN_SMASK | IB_FECN_SMASK))) {
 		hfi1_process_ecn_slowpath(qp, pkt, do_cnp);
-		return bth1 & HFI1_FECN_SMASK;
+		return bth1 & IB_FECN_SMASK;
 	}
 	return false;
 }

index 623209a..da968b7 100644
@@ -773,7 +773,7 @@ void hfi1_send_rc_ack(struct hfi1_ctxtdata *rcd, struct rvt_qp *qp,
 	hdr.lrh[3] = cpu_to_be16(ppd->lid | qp->remote_ah_attr.src_path_bits);
 	ohdr->bth[0] = cpu_to_be32(bth0);
 	ohdr->bth[1] = cpu_to_be32(qp->remote_qpn);
-	ohdr->bth[1] |= cpu_to_be32((!!is_fecn) << HFI1_BECN_SHIFT);
+	ohdr->bth[1] |= cpu_to_be32((!!is_fecn) << IB_BECN_SHIFT);
 	ohdr->bth[2] = cpu_to_be32(mask_psn(qp->r_ack_psn));
 
 	/* Don't try to send ACKs if the link isn't ACTIVE */

index 2730915..879eb9b 100644
@@ -775,7 +775,7 @@ void hfi1_make_ruc_header(struct rvt_qp *qp, struct ib_other_headers *ohdr,
 	if (qp->s_flags & RVT_S_ECN) {
 		qp->s_flags &= ~RVT_S_ECN;
 		/* we recently received a FECN, so return a BECN */
-		bth1 |= (HFI1_BECN_MASK << HFI1_BECN_SHIFT);
+		bth1 |= (IB_BECN_MASK << IB_BECN_SHIFT);
 	}
 	ohdr->bth[1] = cpu_to_be32(bth1);
 	ohdr->bth[2] = cpu_to_be32(bth2);

index 382fcda..090f6b5 100644
@@ -139,11 +139,11 @@
 			__entry->pkey =
 			be32_to_cpu(ohdr->bth[0]) & 0xffff;
 			__entry->f =
-			(be32_to_cpu(ohdr->bth[1]) >> HFI1_FECN_SHIFT) &
-			HFI1_FECN_MASK;
+			(be32_to_cpu(ohdr->bth[1]) >> IB_FECN_SHIFT) &
+			IB_FECN_MASK;
 			__entry->b =
-			(be32_to_cpu(ohdr->bth[1]) >> HFI1_BECN_SHIFT) &
-			HFI1_BECN_MASK;
+			(be32_to_cpu(ohdr->bth[1]) >> IB_BECN_SHIFT) &
+			IB_BECN_MASK;
 			__entry->qpn =
 			be32_to_cpu(ohdr->bth[1]) & RVT_QPN_MASK;
 			__entry->a =

index 8b3403a..45bc3f0 100644
@@ -537,7 +537,7 @@ void return_cnp(struct hfi1_ibport *ibp, struct rvt_qp *qp, u32 remote_qpn,
 	bth0 = pkey | (IB_OPCODE_CNP << 24);
 	ohdr->bth[0] = cpu_to_be32(bth0);
 
-	ohdr->bth[1] = cpu_to_be32(remote_qpn | (1 << HFI1_BECN_SHIFT));
+	ohdr->bth[1] = cpu_to_be32(remote_qpn | (1 << IB_BECN_SHIFT));
 	ohdr->bth[2] = 0; /* PSN 0 */
 
 	hdr.lrh[0] = cpu_to_be16(lrh0);

index 9cf42bc..5519f31 100644
@@ -74,6 +74,12 @@
 #define IB_GRH_FLOW_MASK	0xFFFFF
 #define IB_GRH_FLOW_SHIFT	0
 #define IB_GRH_NEXT_HDR		0x1B
+#define IB_FECN_SHIFT 31
+#define IB_FECN_MASK 1
+#define IB_FECN_SMASK BIT(IB_FECN_SHIFT)
+#define IB_BECN_SHIFT 30
+#define IB_BECN_MASK 1
+#define IB_BECN_SMASK BIT(IB_BECN_SHIFT)
 
 #define IB_AETH_CREDIT_SHIFT	24
 #define IB_AETH_CREDIT_MASK	0x1F

index 879eb9b..ccf8d80 100644
@@ -1,5 +1,5 @@
 /*
- * Copyright(c) 2015, 2016 Intel Corporation.
+ * Copyright(c) 2015 - 2017 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.

@@ -784,23 +784,29 @@ void hfi1_make_ruc_header(struct rvt_qp *qp, struct ib_other_headers *ohdr,
 /* when sending, force a reschedule every one of these periods */
 #define SEND_RESCHED_TIMEOUT (5 * HZ)  /* 5s in jiffies */
 
+void hfi1_do_send_from_rvt(struct rvt_qp *qp)
+{
+	hfi1_do_send(qp, false);
+}
+
 void _hfi1_do_send(struct work_struct *work)
 {
 	struct iowait *wait = container_of(work, struct iowait, iowork);
 	struct rvt_qp *qp = iowait_to_qp(wait);
 
-	hfi1_do_send(qp);
+	hfi1_do_send(qp, true);
 }
 
 /**
  * hfi1_do_send - perform a send on a QP
  * @work: contains a pointer to the QP
+ * @in_thread: true if in a workqueue thread
  *
  * Process entries in the send work queue until credit or queue is
  * exhausted.  Only allow one CPU to send a packet per QP.
  * Otherwise, two threads could send packets out of order.
  */
-void hfi1_do_send(struct rvt_qp *qp)
+void hfi1_do_send(struct rvt_qp *qp, bool in_thread)
 {
 	struct hfi1_pkt_state ps;
 	struct hfi1_qp_priv *priv = qp->priv;

@@ -868,8 +874,10 @@ void hfi1_do_send(struct rvt_qp *qp)
 			qp->s_hdrwords = 0;
 			/* allow other tasks to run */
 			if (unlikely(time_after(jiffies, timeout))) {
-				if (workqueue_congested(cpu,
-							ps.ppd->hfi1_wq)) {
+				if (!in_thread ||
+				    workqueue_congested(
+						cpu,
+						ps.ppd->hfi1_wq)) {
 					spin_lock_irqsave(
 						&qp->s_lock,
 						ps.flags);

@@ -882,11 +890,9 @@ void hfi1_do_send(struct rvt_qp *qp)
 						*ps.ppd->dd->send_schedule);
 					return;
 				}
-				if (!irqs_disabled()) {
-					cond_resched();
-					this_cpu_inc(
-					   *ps.ppd->dd->send_schedule);
-				}
+				cond_resched();
+				this_cpu_inc(
+					*ps.ppd->dd->send_schedule);
 				timeout = jiffies + (timeout_int) / 8;
 			}
 			spin_lock_irqsave(&qp->s_lock, ps.flags);

index 7f49719..e112762 100644
@@ -1,5 +1,5 @@
 /*
- * Copyright(c) 2015, 2016 Intel Corporation.
+ * Copyright(c) 2015 - 2017 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.

@@ -1816,7 +1816,7 @@ int hfi1_register_ib_device(struct hfi1_devdata *dd)
 	dd->verbs_dev.rdi.driver_f.qp_priv_free = qp_priv_free;
 	dd->verbs_dev.rdi.driver_f.free_all_qps = free_all_qps;
 	dd->verbs_dev.rdi.driver_f.notify_qp_reset = notify_qp_reset;
-	dd->verbs_dev.rdi.driver_f.do_send = hfi1_do_send;
+	dd->verbs_dev.rdi.driver_f.do_send = hfi1_do_send_from_rvt;
 	dd->verbs_dev.rdi.driver_f.schedule_send = hfi1_schedule_send;
 	dd->verbs_dev.rdi.driver_f.schedule_send_no_lock = _hfi1_schedule_send;
 	dd->verbs_dev.rdi.driver_f.get_pmtu_from_attr = get_pmtu_from_attr;

index 6c549e7..46b00ed 100644
@@ -1,5 +1,5 @@
 /*
- * Copyright(c) 2015, 2016 Intel Corporation.
+ * Copyright(c) 2015 - 2017 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.

@@ -355,7 +355,9 @@ void hfi1_make_ruc_header(struct rvt_qp *qp, struct ib_other_headers *ohdr,
 
 void _hfi1_do_send(struct work_struct *work);
 
-void hfi1_do_send(struct rvt_qp *qp);
+void hfi1_do_send_from_rvt(struct rvt_qp *qp);
+
+void hfi1_do_send(struct rvt_qp *qp, bool in_thread);
 
 void hfi1_send_complete(struct rvt_qp *qp, struct rvt_swqe *wqe,
 			enum ib_wc_status status);

index 79a316a..6b70d1d 100644
@@ -6381,18 +6381,17 @@ static void lcb_shutdown(struct hfi1_devdata *dd, int abort)
  *
  * The expectation is that the caller of this routine would have taken
  * care of properly transitioning the link into the correct state.
+ * NOTE: the caller needs to acquire the dd->dc8051_lock lock
+ *       before calling this function.
  */
-static void dc_shutdown(struct hfi1_devdata *dd)
+static void _dc_shutdown(struct hfi1_devdata *dd)
 {
-	unsigned long flags;
+	lockdep_assert_held(&dd->dc8051_lock);
 
-	spin_lock_irqsave(&dd->dc8051_lock, flags);
-	if (dd->dc_shutdown) {
-		spin_unlock_irqrestore(&dd->dc8051_lock, flags);
+	if (dd->dc_shutdown)
 		return;
-	}
+
 	dd->dc_shutdown = 1;
-	spin_unlock_irqrestore(&dd->dc8051_lock, flags);
 	/* Shutdown the LCB */
 	lcb_shutdown(dd, 1);
 	/*

@@ -6403,35 +6402,45 @@ static void dc_shutdown(struct hfi1_devdata *dd)
 	write_csr(dd, DC_DC8051_CFG_RST, 0x1);
 }
 
+static void dc_shutdown(struct hfi1_devdata *dd)
+{
+	mutex_lock(&dd->dc8051_lock);
+	_dc_shutdown(dd);
+	mutex_unlock(&dd->dc8051_lock);
+}
+
 /*
  * Calling this after the DC has been brought out of reset should not
  * do any damage.
+ * NOTE: the caller needs to acquire the dd->dc8051_lock lock
+ *       before calling this function.
  */
-static void dc_start(struct hfi1_devdata *dd)
+static void _dc_start(struct hfi1_devdata *dd)
 {
-	unsigned long flags;
-	int ret;
+	lockdep_assert_held(&dd->dc8051_lock);
 
-	spin_lock_irqsave(&dd->dc8051_lock, flags);
 	if (!dd->dc_shutdown)
-		goto done;
-	spin_unlock_irqrestore(&dd->dc8051_lock, flags);
+		return;
+
 	/* Take the 8051 out of reset */
 	write_csr(dd, DC_DC8051_CFG_RST, 0ull);
 	/* Wait until 8051 is ready */
-	ret = wait_fm_ready(dd, TIMEOUT_8051_START);
-	if (ret) {
+	if (wait_fm_ready(dd, TIMEOUT_8051_START))
 		dd_dev_err(dd, "%s: timeout starting 8051 firmware\n",
 			   __func__);
-	}
+
 	/* Take away reset for LCB and RX FPE (set in lcb_shutdown). */
 	write_csr(dd, DCC_CFG_RESET, 0x10);
 	/* lcb_shutdown() with abort=1 does not restore these */
 	write_csr(dd, DC_LCB_ERR_EN, dd->lcb_err_en);
-	spin_lock_irqsave(&dd->dc8051_lock, flags);
 	dd->dc_shutdown = 0;
-done:
-	spin_unlock_irqrestore(&dd->dc8051_lock, flags);
+}
+
+static void dc_start(struct hfi1_devdata *dd)
+{
+	mutex_lock(&dd->dc8051_lock);
+	_dc_start(dd);
+	mutex_unlock(&dd->dc8051_lock);
 }
 
 /*

@@ -8475,16 +8484,11 @@ static int do_8051_command(
 {
 	u64 reg, completed;
 	int return_code;
-	unsigned long flags;
 	unsigned long timeout;
 
 	hfi1_cdbg(DC8051, "type %d, data 0x%012llx", type, in_data);
 
-	/*
-	 * Alternative to holding the lock for a long time:
-	 * - keep busy wait - have other users bounce off
-	 */
-	spin_lock_irqsave(&dd->dc8051_lock, flags);
+	mutex_lock(&dd->dc8051_lock);
 
 	/* We can't send any commands to the 8051 if it's in reset */
 	if (dd->dc_shutdown) {

@@ -8510,10 +8514,8 @@ static int do_8051_command(
 			return_code = -ENXIO;
 			goto fail;
 		}
-		spin_unlock_irqrestore(&dd->dc8051_lock, flags);
-		dc_shutdown(dd);
-		dc_start(dd);
-		spin_lock_irqsave(&dd->dc8051_lock, flags);
+		_dc_shutdown(dd);
+		_dc_start(dd);
 	}
 
 	/*

@@ -8594,8 +8596,7 @@ static int do_8051_command(
 	write_csr(dd, DC_DC8051_CFG_HOST_CMD_0, 0);
 
 fail:
-	spin_unlock_irqrestore(&dd->dc8051_lock, flags);
-
+	mutex_unlock(&dd->dc8051_lock);
 	return return_code;
 }
 

@@ -11969,6 +11970,10 @@ static void free_cntrs(struct hfi1_devdata *dd)
 	dd->scntrs = NULL;
 	kfree(dd->cntrnames);
 	dd->cntrnames = NULL;
+	if (dd->update_cntr_wq) {
+		destroy_workqueue(dd->update_cntr_wq);
+		dd->update_cntr_wq = NULL;
+	}
 }
 
 static u64 read_dev_port_cntr(struct hfi1_devdata *dd, struct cntr_entry *entry,

@@ -12124,7 +12129,7 @@ u64 write_port_cntr(struct hfi1_pportdata *ppd, int index, int vl, u64 data)
 	return write_dev_port_cntr(ppd->dd, entry, sval, ppd, vl, data);
 }
 
-static void update_synth_timer(unsigned long opaque)
+static void do_update_synth_timer(struct work_struct *work)
 {
 	u64 cur_tx;
 	u64 cur_rx;

@@ -12133,8 +12138,8 @@ static void update_synth_timer(unsigned long opaque)
 	int i, j, vl;
 	struct hfi1_pportdata *ppd;
 	struct cntr_entry *entry;
-
-	struct hfi1_devdata *dd = (struct hfi1_devdata *)opaque;
+	struct hfi1_devdata *dd = container_of(work, struct hfi1_devdata,
+					       update_cntr_work);
 
 	/*
 	 * Rather than keep beating on the CSRs pick a minimal set that we can

@@ -12217,7 +12222,13 @@ static void update_synth_timer(unsigned long opaque)
 	} else {
 		hfi1_cdbg(CNTR, "[%d] No update necessary", dd->unit);
 	}
+}
 
+static void update_synth_timer(unsigned long opaque)
+{
+	struct hfi1_devdata *dd = (struct hfi1_devdata *)opaque;
+
+	queue_work(dd->update_cntr_wq, &dd->update_cntr_work);
 	mod_timer(&dd->synth_stats_timer, jiffies + HZ * SYNTH_CNT_TIME);
 }
 

@@ -12453,6 +12464,13 @@ static int init_cntrs(struct hfi1_devdata *dd)
 	if (init_cpu_counters(dd))
 		goto bail;
 
+	dd->update_cntr_wq = alloc_ordered_workqueue("hfi1_update_cntr_%d",
+						     WQ_MEM_RECLAIM, dd->unit);
+	if (!dd->update_cntr_wq)
+		goto bail;
+
+	INIT_WORK(&dd->update_cntr_work, do_update_synth_timer);
+
 	mod_timer(&dd->synth_stats_timer, jiffies + HZ * SYNTH_CNT_TIME);
 	return 0;
 bail:

index 79c4289..c6b6853 100644
@@ -474,7 +474,7 @@ struct hfi1_packet {
 #define HFI1_PART_ENFORCE_OUT	0x2
 
 /* how often we check for synthetic counter wrap around */
-#define SYNTH_CNT_TIME 2
+#define SYNTH_CNT_TIME 3
 
 /* Counter flags */
 #define CNTR_NORMAL		0x0 /* Normal counters, just read register */

@@ -926,8 +926,9 @@ struct hfi1_devdata {
 	spinlock_t rcvctrl_lock; /* protect changes to RcvCtrl */
 	/* around rcd and (user ctxts) ctxt_cnt use (intr vs free) */
 	spinlock_t uctxt_lock; /* rcd and user context changes */
-	/* exclusive access to 8051 */
-	spinlock_t dc8051_lock;
+	struct mutex dc8051_lock; /* exclusive access to 8051 */
+	struct workqueue_struct *update_cntr_wq;
+	struct work_struct update_cntr_work;
 	/* exclusive access to 8051 memory */
 	spinlock_t dc8051_memlock;
 	int dc8051_timed_out;	/* remember if the 8051 timed out */

index 9bfb8eb..55a11a6 100644
@@ -1078,11 +1078,11 @@ struct hfi1_devdata *hfi1_alloc_devdata(struct pci_dev *pdev, size_t extra)
 	spin_lock_init(&dd->uctxt_lock);
 	spin_lock_init(&dd->hfi1_diag_trans_lock);
 	spin_lock_init(&dd->sc_init_lock);
-	spin_lock_init(&dd->dc8051_lock);
 	spin_lock_init(&dd->dc8051_memlock);
 	seqlock_init(&dd->sc2vl_lock);
 	spin_lock_init(&dd->sde_map_lock);
 	spin_lock_init(&dd->pio_map_lock);
+	mutex_init(&dd->dc8051_lock);
 	init_waitqueue_head(&dd->event_queue);
 
 	dd->int_counter = alloc_percpu(u64);

index 6b70d1d..0fec6be 100644
@@ -9325,7 +9325,7 @@ static int handle_qsfp_error_conditions(struct hfi1_pportdata *ppd,
 
 	if ((qsfp_interrupt_status[0] & QSFP_HIGH_TEMP_ALARM) ||
 	    (qsfp_interrupt_status[0] & QSFP_HIGH_TEMP_WARNING))
-		dd_dev_info(dd, "%s: QSFP cable on fire\n",
+		dd_dev_info(dd, "%s: QSFP cable temperature too high\n",
 			    __func__);
 
 	if ((qsfp_interrupt_status[0] & QSFP_LOW_TEMP_ALARM) ||

index 0fec6be..1ce560e 100644
@@ -7288,15 +7288,6 @@ void handle_verify_cap(struct work_struct *work)
 	lcb_shutdown(dd, 0);
 	adjust_lcb_for_fpga_serdes(dd);
 
-	/*
-	 * These are now valid:
-	 *	remote VerifyCap fields in the general LNI config
-	 *	CSR DC8051_STS_REMOTE_GUID
-	 *	CSR DC8051_STS_REMOTE_NODE_TYPE
-	 *	CSR DC8051_STS_REMOTE_FM_SECURITY
-	 *	CSR DC8051_STS_REMOTE_PORT_NO
-	 */
-
 	read_vc_remote_phy(dd, &power_management, &continious);
 	read_vc_remote_fabric(dd, &vau, &z, &vcu, &vl15buf,
 			      &partner_supported_crc);

@@ -7427,20 +7418,6 @@ void handle_verify_cap(struct work_struct *work)
 	write_csr(dd, DC_LCB_ERR_EN, 0); /* mask LCB errors */
 	set_8051_lcb_access(dd);
 
-	ppd->neighbor_guid =
-		read_csr(dd, DC_DC8051_STS_REMOTE_GUID);
-	ppd->neighbor_port_number = read_csr(dd, DC_DC8051_STS_REMOTE_PORT_NO) &
-					DC_DC8051_STS_REMOTE_PORT_NO_VAL_SMASK;
-	ppd->neighbor_type =
-		read_csr(dd, DC_DC8051_STS_REMOTE_NODE_TYPE) &
-		DC_DC8051_STS_REMOTE_NODE_TYPE_VAL_MASK;
-	ppd->neighbor_fm_security =
-		read_csr(dd, DC_DC8051_STS_REMOTE_FM_SECURITY) &
-		DC_DC8051_STS_LOCAL_FM_SECURITY_DISABLED_MASK;
-	dd_dev_info(dd,
-		    "Neighbor Guid: %llx Neighbor type %d MgmtAllowed %d FM security bypass %d\n",
-		    ppd->neighbor_guid, ppd->neighbor_type,
-		    ppd->mgmt_allowed, ppd->neighbor_fm_security);
 	if (ppd->mgmt_allowed)
 		add_full_mgmt_pkey(ppd);
 

@@ -10497,11 +10474,8 @@ int set_link_state(struct hfi1_pportdata *ppd, u32 state)
 			goto unexpected;
 		}
 
-		ppd->host_link_state = HLS_UP_INIT;
 		ret = wait_logical_linkstate(ppd, IB_PORT_INIT, 1000);
 		if (ret) {
-			/* logical state didn't change, stay at going_up */
-			ppd->host_link_state = HLS_GOING_UP;
 			dd_dev_err(dd,
 				   "%s: logical state did not change to INIT\n",
 				   __func__);

@@ -10515,6 +10489,7 @@ int set_link_state(struct hfi1_pportdata *ppd, u32 state)
 			add_rcvctrl(dd, RCV_CTRL_RCV_PORT_ENABLE_SMASK);
 
 			handle_linkup_change(dd, 1);
+			ppd->host_link_state = HLS_UP_INIT;
 		}
 		break;
 	case HLS_UP_ARMED:

index c6b6853..fec6eb6 100644
@@ -1256,7 +1256,16 @@ void hfi1_init_pportdata(struct pci_dev *, struct hfi1_pportdata *,
 /* return the driver's idea of the logical OPA port state */
 static inline u32 driver_lstate(struct hfi1_pportdata *ppd)
 {
-	return ppd->lstate; /* use the cached value */
+	/*
+	 * The driver does some processing from the time the logical
+	 * link state is at INIT to the time the SM can be notified
+	 * as such. Return IB_PORT_DOWN until the software state
+	 * is ready.
+	 */
+	if (ppd->lstate == IB_PORT_INIT && !(ppd->host_link_state & HLS_UP))
+		return IB_PORT_DOWN;
+	else
+		return ppd->lstate;
 }
 
 void receive_interrupt_work(struct work_struct *work);

index 65348d1..232014d 100644
@@ -131,19 +131,24 @@ void handle_linkup_change(struct hfi1_devdata *dd, u32 linkup)
 		if (quick_linkup || dd->icode == ICODE_FUNCTIONAL_SIMULATOR) {
 			set_up_vl15(dd, dd->vau, dd->vl15_init);
 			assign_remote_cm_au_table(dd, dd->vcu);
-			ppd->neighbor_guid =
-				read_csr(dd, DC_DC8051_STS_REMOTE_GUID);
-			ppd->neighbor_type =
-				read_csr(dd, DC_DC8051_STS_REMOTE_NODE_TYPE) &
-					DC_DC8051_STS_REMOTE_NODE_TYPE_VAL_MASK;
-			ppd->neighbor_port_number =
-				read_csr(dd, DC_DC8051_STS_REMOTE_PORT_NO) &
-					 DC_DC8051_STS_REMOTE_PORT_NO_VAL_SMASK;
-			dd_dev_info(dd, "Neighbor GUID: %llx Neighbor type %d\n",
-				    ppd->neighbor_guid,
-				    ppd->neighbor_type);
 		}
 
+		ppd->neighbor_guid =
+			read_csr(dd, DC_DC8051_STS_REMOTE_GUID);
+		ppd->neighbor_type =
+			read_csr(dd, DC_DC8051_STS_REMOTE_NODE_TYPE) &
+				 DC_DC8051_STS_REMOTE_NODE_TYPE_VAL_MASK;
+		ppd->neighbor_port_number =
+			read_csr(dd, DC_DC8051_STS_REMOTE_PORT_NO) &
+				 DC_DC8051_STS_REMOTE_PORT_NO_VAL_SMASK;
+		ppd->neighbor_fm_security =
+			read_csr(dd, DC_DC8051_STS_REMOTE_FM_SECURITY) &
+				 DC_DC8051_STS_LOCAL_FM_SECURITY_DISABLED_MASK;
+		dd_dev_info(dd,
+			    "Neighbor Guid %llx, Type %d, Port Num %d\n",
+			    ppd->neighbor_guid, ppd->neighbor_type,
+			    ppd->neighbor_port_number);
+
 		/* physical link went up */
 		ppd->linkup = 1;
 		ppd->offline_disabled_reason =

index 55a11a6..838d3a8 100644
@@ -482,6 +482,9 @@ void hfi1_init_pportdata(struct pci_dev *pdev, struct hfi1_pportdata *ppd,
 	default_pkey_idx = 1;
 
 	ppd->pkeys[default_pkey_idx] = DEFAULT_P_KEY;
+	ppd->part_enforce |= HFI1_PART_ENFORCE_IN;
+	ppd->part_enforce |= HFI1_PART_ENFORCE_OUT;
+
 	if (loopback) {
 		hfi1_early_err(&pdev->dev,
 			       "Faking data partition 0x8001 in idx %u\n",

index db5494d..7059a0f 100644
@@ -1151,16 +1151,6 @@ static int __subn_set_opa_portinfo(struct opa_smp *smp, u32 am, u8 *data,
 		ppd->linkinit_reason =
 			(pi->partenforce_filterraw &
 			 OPA_PI_MASK_LINKINIT_REASON);
-	/* enable/disable SW pkey checking as per FM control */
-	if (pi->partenforce_filterraw & OPA_PI_MASK_PARTITION_ENFORCE_IN)
-		ppd->part_enforce |= HFI1_PART_ENFORCE_IN;
-	else
-		ppd->part_enforce &= ~HFI1_PART_ENFORCE_IN;
-
-	if (pi->partenforce_filterraw & OPA_PI_MASK_PARTITION_ENFORCE_OUT)
-		ppd->part_enforce |= HFI1_PART_ENFORCE_OUT;
-	else
-		ppd->part_enforce &= ~HFI1_PART_ENFORCE_OUT;
 
 	/* Must be a valid unicast LID address. */
 	if ((smlid == 0 && ls_old > IB_PORT_INIT) ||

index 1ce560e..500b857 100644
@@ -7088,7 +7088,7 @@ static void add_full_mgmt_pkey(struct hfi1_pportdata *ppd)
 {
 	struct hfi1_devdata *dd = ppd->dd;
 
-	/* Sanity check - ppd->pkeys[2] should be 0, or already initalized */
+	/* Sanity check - ppd->pkeys[2] should be 0, or already initialized */
 	if (!((ppd->pkeys[2] == 0) || (ppd->pkeys[2] == FULL_MGMT_P_KEY)))
 		dd_dev_warn(dd, "%s pkey[2] already set to 0x%x, resetting it to 0x%x\n",
 			    __func__, ppd->pkeys[2], FULL_MGMT_P_KEY);

index 0829fce..e39e01b 100644
@@ -583,7 +583,7 @@ static void tune_pcie_caps(struct hfi1_devdata *dd)
 		if (words == ~0ULL)
 			ret = PCI_ERS_RESULT_NEED_RESET;
 		dd_dev_info(dd,
-			    "HFI1 mmio_enabled function called, read wordscntr %Lx, returning %d\n",
+			    "HFI1 mmio_enabled function called, read wordscntr %llx, returning %d\n",
 			    words, ret);
 	}
 	return  ret;

index 500b857..e97851a 100644
@@ -8147,10 +8147,10 @@ static irqreturn_t sdma_interrupt(int irq, void *data)
 
 		/* handle the interrupt(s) */
 		sdma_engine_interrupt(sde, status);
-	} else
+	} else {
 		dd_dev_err(dd, "SDMA engine %u interrupt, but no status bits set\n",
 			   sde->this_idx);
-
+	}
 	return IRQ_HANDLED;
 }
 

index 838d3a8..e9b33c8 100644
@@ -245,9 +245,10 @@ struct hfi1_ctxtdata *hfi1_create_ctxtdata(struct hfi1_pportdata *ppd, u32 ctxt,
 			if (ctxt < kctxt_ngroups) {
 				base = ctxt * (dd->rcv_entries.ngroups + 1);
 				rcd->rcv_array_groups++;
-			} else
+			} else {
 				base = kctxt_ngroups +
 					(ctxt * dd->rcv_entries.ngroups);
+			}
 		} else {
 			u16 ct = ctxt - dd->first_user_ctxt;
 

@@ -256,9 +257,10 @@ struct hfi1_ctxtdata *hfi1_create_ctxtdata(struct hfi1_pportdata *ppd, u32 ctxt,
 			if (ct < dd->rcv_entries.nctxt_extra) {
 				base += ct * (dd->rcv_entries.ngroups + 1);
 				rcd->rcv_array_groups++;
-			} else
+			} else {
 				base += dd->rcv_entries.nctxt_extra +
 					(ct * dd->rcv_entries.ngroups);
+			}
 		}
 		rcd->eager_base = base * dd->rcv_entries.group_size;
 

index f78c739..d575499 100644
@@ -597,6 +597,10 @@ static int hfi1_file_mmap(struct file *fp, struct vm_area_struct *vma)
 		vmf = 1;
 		break;
 	case STATUS:
+		if (flags & (unsigned long)(VM_WRITE | VM_EXEC)) {
+			ret = -EPERM;
+			goto done;
+		}
 		memaddr = kvirt_to_phys((void *)dd->status);
 		memlen = PAGE_SIZE;
 		flags |= VM_IO | VM_DONTEXPAND;

index 85ed505..207e5c2 100644
@@ -1519,7 +1519,9 @@ int ib_attach_mcast(struct ib_qp *qp, union ib_gid *gid, u16 lid)
 
 	if (!qp->device->attach_mcast)
 		return -ENOSYS;
-	if (gid->raw[0] != 0xff || qp->qp_type != IB_QPT_UD)
+	if (gid->raw[0] != 0xff || qp->qp_type != IB_QPT_UD ||
+	    lid < be16_to_cpu(IB_MULTICAST_LID_BASE) ||
+	    lid == be16_to_cpu(IB_LID_PERMISSIVE))
 		return -EINVAL;
 
 	ret = qp->device->attach_mcast(qp, gid, lid);

@@ -1535,7 +1537,9 @@ int ib_detach_mcast(struct ib_qp *qp, union ib_gid *gid, u16 lid)
 
 	if (!qp->device->detach_mcast)
 		return -ENOSYS;
-	if (gid->raw[0] != 0xff || qp->qp_type != IB_QPT_UD)
+	if (gid->raw[0] != 0xff || qp->qp_type != IB_QPT_UD ||
+	    lid < be16_to_cpu(IB_MULTICAST_LID_BASE) ||
+	    lid == be16_to_cpu(IB_LID_PERMISSIVE))
 		return -EINVAL;
 
 	ret = qp->device->detach_mcast(qp, gid, lid);

index fec6eb6..51fffdf 100644
@@ -1609,7 +1609,7 @@ static inline bool process_ecn(struct rvt_qp *qp, struct hfi1_packet *pkt,
 	bth1 = be32_to_cpu(ohdr->bth[1]);
 	if (unlikely(bth1 & (IB_BECN_SMASK | IB_FECN_SMASK))) {
 		hfi1_process_ecn_slowpath(qp, pkt, do_cnp);
-		return bth1 & IB_FECN_SMASK;
+		return !!(bth1 & IB_FECN_SMASK);
 	}
 	return false;
 }

index da968b7..9b3333f 100644
@@ -1930,7 +1930,8 @@ void hfi1_rc_rcv(struct hfi1_packet *packet)
 	int diff;
 	struct ib_reth *reth;
 	unsigned long flags;
-	int ret, is_fecn = 0;
+	int ret;
+	bool is_fecn = false;
 	bool copy_last = false;
 	u32 rkey;